| 2 2 2 2 7 6 1 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2012-2016 Pablo Neira Ayuso <pablo@netfilter.org> */ #include <linux/init.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #define nft_objref_priv(expr) *((struct nft_object **)nft_expr_priv(expr)) void nft_objref_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_object *obj = nft_objref_priv(expr); obj->ops->eval(obj, regs, pkt); } static int nft_objref_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_object *obj = nft_objref_priv(expr); u8 genmask = nft_genmask_next(ctx->net); u32 objtype; if (!tb[NFTA_OBJREF_IMM_NAME] || !tb[NFTA_OBJREF_IMM_TYPE]) return -EINVAL; objtype = ntohl(nla_get_be32(tb[NFTA_OBJREF_IMM_TYPE])); obj = nft_obj_lookup(ctx->net, ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype, genmask); if (IS_ERR(obj)) return -ENOENT; if (!nft_use_inc(&obj->use)) return -EMFILE; nft_objref_priv(expr) = obj; return 0; } static int nft_objref_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_object *obj = nft_objref_priv(expr); if (nla_put_string(skb, NFTA_OBJREF_IMM_NAME, obj->key.name) || nla_put_be32(skb, NFTA_OBJREF_IMM_TYPE, htonl(obj->ops->type->type))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static void nft_objref_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { struct nft_object *obj = nft_objref_priv(expr); if (phase == NFT_TRANS_COMMIT) return; nft_use_dec(&obj->use); } static void nft_objref_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_object *obj = nft_objref_priv(expr); nft_use_inc_restore(&obj->use); } static const struct nft_expr_ops nft_objref_ops = { .type = &nft_objref_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_object *)), .eval = nft_objref_eval, .init = nft_objref_init, .activate = nft_objref_activate, .deactivate = nft_objref_deactivate, .dump = nft_objref_dump, .reduce = NFT_REDUCE_READONLY, }; struct nft_objref_map { struct nft_set *set; u8 sreg; struct nft_set_binding binding; }; void nft_objref_map_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_objref_map *priv = nft_expr_priv(expr); const struct nft_set *set = priv->set; struct net *net = nft_net(pkt); const struct nft_set_ext *ext; struct nft_object *obj; bool found; found = nft_set_do_lookup(net, set, ®s->data[priv->sreg], &ext); if (!found) { ext = nft_set_catchall_lookup(net, set); if (!ext) { regs->verdict.code = NFT_BREAK; return; } } obj = *nft_set_ext_obj(ext); obj->ops->eval(obj, regs, pkt); } static int nft_objref_map_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_objref_map *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_set *set; int err; set = nft_set_lookup_global(ctx->net, ctx->table, tb[NFTA_OBJREF_SET_NAME], tb[NFTA_OBJREF_SET_ID], genmask); if (IS_ERR(set)) return PTR_ERR(set); if (!(set->flags & NFT_SET_OBJECT)) return -EINVAL; err = nft_parse_register_load(ctx, tb[NFTA_OBJREF_SET_SREG], &priv->sreg, set->klen); if (err < 0) return err; priv->binding.flags = set->flags & NFT_SET_OBJECT; err = nf_tables_bind_set(ctx, set, &priv->binding); if (err < 0) return err; priv->set = set; return 0; } static int nft_objref_map_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_objref_map *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_OBJREF_SET_SREG, priv->sreg) || nla_put_string(skb, NFTA_OBJREF_SET_NAME, priv->set->name)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static void nft_objref_map_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { struct nft_objref_map *priv = nft_expr_priv(expr); nf_tables_deactivate_set(ctx, priv->set, &priv->binding, phase); } static void nft_objref_map_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_objref_map *priv = nft_expr_priv(expr); nf_tables_activate_set(ctx, priv->set); } static void nft_objref_map_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_objref_map *priv = nft_expr_priv(expr); nf_tables_destroy_set(ctx, priv->set); } static const struct nft_expr_ops nft_objref_map_ops = { .type = &nft_objref_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)), .eval = nft_objref_map_eval, .init = nft_objref_map_init, .activate = nft_objref_map_activate, .deactivate = nft_objref_map_deactivate, .destroy = nft_objref_map_destroy, .dump = nft_objref_map_dump, .reduce = NFT_REDUCE_READONLY, }; static const struct nft_expr_ops * nft_objref_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { if (tb[NFTA_OBJREF_SET_SREG] && (tb[NFTA_OBJREF_SET_NAME] || tb[NFTA_OBJREF_SET_ID])) return &nft_objref_map_ops; else if (tb[NFTA_OBJREF_IMM_NAME] && tb[NFTA_OBJREF_IMM_TYPE]) return &nft_objref_ops; return ERR_PTR(-EOPNOTSUPP); } static const struct nla_policy nft_objref_policy[NFTA_OBJREF_MAX + 1] = { [NFTA_OBJREF_IMM_NAME] = { .type = NLA_STRING, .len = NFT_OBJ_MAXNAMELEN - 1 }, [NFTA_OBJREF_IMM_TYPE] = { .type = NLA_U32 }, [NFTA_OBJREF_SET_SREG] = { .type = NLA_U32 }, [NFTA_OBJREF_SET_NAME] = { .type = NLA_STRING, .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_OBJREF_SET_ID] = { .type = NLA_U32 }, }; struct nft_expr_type nft_objref_type __read_mostly = { .name = "objref", .select_ops = nft_objref_select_ops, .policy = nft_objref_policy, .maxattr = NFTA_OBJREF_MAX, .owner = THIS_MODULE, }; |
| 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_meta.h> #include <linux/if_bridge.h> #include <uapi/linux/netfilter_bridge.h> /* NF_BR_PRE_ROUTING */ #include "../br_private.h" static const struct net_device * nft_meta_get_bridge(const struct net_device *dev) { if (dev && netif_is_bridge_port(dev)) return netdev_master_upper_dev_get_rcu((struct net_device *)dev); return NULL; } static void nft_meta_bridge_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct net_device *in = nft_in(pkt), *out = nft_out(pkt); u32 *dest = ®s->data[priv->dreg]; const struct net_device *br_dev; switch (priv->key) { case NFT_META_BRI_IIFNAME: br_dev = nft_meta_get_bridge(in); break; case NFT_META_BRI_OIFNAME: br_dev = nft_meta_get_bridge(out); break; case NFT_META_BRI_IIFPVID: { u16 p_pvid; br_dev = nft_meta_get_bridge(in); if (!br_dev || !br_vlan_enabled(br_dev)) goto err; br_vlan_get_pvid_rcu(in, &p_pvid); nft_reg_store16(dest, p_pvid); return; } case NFT_META_BRI_IIFVPROTO: { u16 p_proto; br_dev = nft_meta_get_bridge(in); if (!br_dev || !br_vlan_enabled(br_dev)) goto err; br_vlan_get_proto(br_dev, &p_proto); nft_reg_store_be16(dest, htons(p_proto)); return; } default: return nft_meta_get_eval(expr, regs, pkt); } strncpy((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ); return; err: regs->verdict.code = NFT_BREAK; } static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { case NFT_META_BRI_IIFNAME: case NFT_META_BRI_OIFNAME: len = IFNAMSIZ; break; case NFT_META_BRI_IIFPVID: case NFT_META_BRI_IIFVPROTO: len = sizeof(u16); break; default: return nft_meta_get_init(ctx, expr, tb); } priv->len = len; return nft_parse_register_store(ctx, tb[NFTA_META_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, len); } static struct nft_expr_type nft_meta_bridge_type; static const struct nft_expr_ops nft_meta_bridge_get_ops = { .type = &nft_meta_bridge_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), .eval = nft_meta_bridge_get_eval, .init = nft_meta_bridge_get_init, .dump = nft_meta_get_dump, .reduce = nft_meta_get_reduce, }; static void nft_meta_bridge_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_meta *meta = nft_expr_priv(expr); u32 *sreg = ®s->data[meta->sreg]; struct sk_buff *skb = pkt->skb; u8 value8; switch (meta->key) { case NFT_META_BRI_BROUTE: value8 = nft_reg_load8(sreg); BR_INPUT_SKB_CB(skb)->br_netfilter_broute = !!value8; break; default: nft_meta_set_eval(expr, regs, pkt); } } static int nft_meta_bridge_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; int err; priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { case NFT_META_BRI_BROUTE: len = sizeof(u8); break; default: return nft_meta_set_init(ctx, expr, tb); } priv->len = len; err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; return 0; } static bool nft_meta_bridge_set_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { int i; for (i = 0; i < NFT_REG32_NUM; i++) { if (!track->regs[i].selector) continue; if (track->regs[i].selector->ops != &nft_meta_bridge_get_ops) continue; __nft_reg_track_cancel(track, i); } return false; } static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; switch (priv->key) { case NFT_META_BRI_BROUTE: hooks = 1 << NF_BR_PRE_ROUTING; break; default: return nft_meta_set_validate(ctx, expr); } return nft_chain_validate_hooks(ctx->chain, hooks); } static const struct nft_expr_ops nft_meta_bridge_set_ops = { .type = &nft_meta_bridge_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), .eval = nft_meta_bridge_set_eval, .init = nft_meta_bridge_set_init, .destroy = nft_meta_set_destroy, .dump = nft_meta_set_dump, .reduce = nft_meta_bridge_set_reduce, .validate = nft_meta_bridge_set_validate, }; static const struct nft_expr_ops * nft_meta_bridge_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { if (tb[NFTA_META_KEY] == NULL) return ERR_PTR(-EINVAL); if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) return ERR_PTR(-EINVAL); if (tb[NFTA_META_DREG]) return &nft_meta_bridge_get_ops; if (tb[NFTA_META_SREG]) return &nft_meta_bridge_set_ops; return ERR_PTR(-EINVAL); } static struct nft_expr_type nft_meta_bridge_type __read_mostly = { .family = NFPROTO_BRIDGE, .name = "meta", .select_ops = nft_meta_bridge_select_ops, .policy = nft_meta_policy, .maxattr = NFTA_META_MAX, .owner = THIS_MODULE, }; static int __init nft_meta_bridge_module_init(void) { return nft_register_expr(&nft_meta_bridge_type); } static void __exit nft_meta_bridge_module_exit(void) { nft_unregister_expr(&nft_meta_bridge_type); } module_init(nft_meta_bridge_module_init); module_exit(nft_meta_bridge_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("wenxu <wenxu@ucloud.cn>"); MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta"); MODULE_DESCRIPTION("Support for bridge dedicated meta key"); |
| 4 2 2 7 3 1 3 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/io_uring.h> #include <linux/fsnotify.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "sync.h" struct io_sync { struct file *file; loff_t len; loff_t off; int flags; int mode; }; int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync); if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; sync->off = READ_ONCE(sqe->off); sync->len = READ_ONCE(sqe->len); sync->flags = READ_ONCE(sqe->sync_range_flags); req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) { struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync); int ret; /* sync_file_range always requires a blocking context */ WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = sync_file_range(req->file, sync->off, sync->len, sync->flags); io_req_set_res(req, ret, 0); return IOU_OK; } int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync); if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in)) return -EINVAL; sync->flags = READ_ONCE(sqe->fsync_flags); if (unlikely(sync->flags & ~IORING_FSYNC_DATASYNC)) return -EINVAL; sync->off = READ_ONCE(sqe->off); sync->len = READ_ONCE(sqe->len); req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_fsync(struct io_kiocb *req, unsigned int issue_flags) { struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync); loff_t end = sync->off + sync->len; int ret; /* fsync always requires a blocking context */ WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = vfs_fsync_range(req->file, sync->off, end > 0 ? end : LLONG_MAX, sync->flags & IORING_FSYNC_DATASYNC); io_req_set_res(req, ret, 0); return IOU_OK; } int io_fallocate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync); if (sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in) return -EINVAL; sync->off = READ_ONCE(sqe->off); sync->len = READ_ONCE(sqe->addr); sync->mode = READ_ONCE(sqe->len); req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) { struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync); int ret; /* fallocate always requiring blocking context */ WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = vfs_fallocate(req->file, sync->mode, sync->off, sync->len); if (ret >= 0) fsnotify_modify(req->file); io_req_set_res(req, ret, 0); return IOU_OK; } |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2022-2023 NXP */ #include "common.h" #include "netlink.h" struct mm_req_info { struct ethnl_req_info base; }; struct mm_reply_data { struct ethnl_reply_data base; struct ethtool_mm_state state; struct ethtool_mm_stats stats; }; #define MM_REPDATA(__reply_base) \ container_of(__reply_base, struct mm_reply_data, base) #define ETHTOOL_MM_STAT_CNT \ (__ETHTOOL_A_MM_STAT_CNT - (ETHTOOL_A_MM_STAT_PAD + 1)) const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1] = { [ETHTOOL_A_MM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static int mm_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct mm_reply_data *data = MM_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_ops *ops; int ret; ops = dev->ethtool_ops; if (!ops->get_mm) return -EOPNOTSUPP; ethtool_stats_init((u64 *)&data->stats, sizeof(data->stats) / sizeof(u64)); ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = ops->get_mm(dev, &data->state); if (ret) goto out_complete; if (ops->get_mm_stats && (req_base->flags & ETHTOOL_FLAG_STATS)) ops->get_mm_stats(dev, &data->stats); out_complete: ethnl_ops_complete(dev); return ret; } static int mm_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { int len = 0; len += nla_total_size(sizeof(u8)); /* _MM_PMAC_ENABLED */ len += nla_total_size(sizeof(u8)); /* _MM_TX_ENABLED */ len += nla_total_size(sizeof(u8)); /* _MM_TX_ACTIVE */ len += nla_total_size(sizeof(u8)); /* _MM_VERIFY_ENABLED */ len += nla_total_size(sizeof(u8)); /* _MM_VERIFY_STATUS */ len += nla_total_size(sizeof(u32)); /* _MM_VERIFY_TIME */ len += nla_total_size(sizeof(u32)); /* _MM_MAX_VERIFY_TIME */ len += nla_total_size(sizeof(u32)); /* _MM_TX_MIN_FRAG_SIZE */ len += nla_total_size(sizeof(u32)); /* _MM_RX_MIN_FRAG_SIZE */ if (req_base->flags & ETHTOOL_FLAG_STATS) len += nla_total_size(0) + /* _MM_STATS */ nla_total_size_64bit(sizeof(u64)) * ETHTOOL_MM_STAT_CNT; return len; } static int mm_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) { if (val == ETHTOOL_STAT_NOT_SET) return 0; if (nla_put_u64_64bit(skb, attrtype, val, ETHTOOL_A_MM_STAT_PAD)) return -EMSGSIZE; return 0; } static int mm_put_stats(struct sk_buff *skb, const struct ethtool_mm_stats *stats) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_MM_STATS); if (!nest) return -EMSGSIZE; if (mm_put_stat(skb, stats->MACMergeFrameAssErrorCount, ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS) || mm_put_stat(skb, stats->MACMergeFrameSmdErrorCount, ETHTOOL_A_MM_STAT_SMD_ERRORS) || mm_put_stat(skb, stats->MACMergeFrameAssOkCount, ETHTOOL_A_MM_STAT_REASSEMBLY_OK) || mm_put_stat(skb, stats->MACMergeFragCountRx, ETHTOOL_A_MM_STAT_RX_FRAG_COUNT) || mm_put_stat(skb, stats->MACMergeFragCountTx, ETHTOOL_A_MM_STAT_TX_FRAG_COUNT) || mm_put_stat(skb, stats->MACMergeHoldCount, ETHTOOL_A_MM_STAT_HOLD_COUNT)) goto err_cancel; nla_nest_end(skb, nest); return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int mm_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct mm_reply_data *data = MM_REPDATA(reply_base); const struct ethtool_mm_state *state = &data->state; if (nla_put_u8(skb, ETHTOOL_A_MM_TX_ENABLED, state->tx_enabled) || nla_put_u8(skb, ETHTOOL_A_MM_TX_ACTIVE, state->tx_active) || nla_put_u8(skb, ETHTOOL_A_MM_PMAC_ENABLED, state->pmac_enabled) || nla_put_u8(skb, ETHTOOL_A_MM_VERIFY_ENABLED, state->verify_enabled) || nla_put_u8(skb, ETHTOOL_A_MM_VERIFY_STATUS, state->verify_status) || nla_put_u32(skb, ETHTOOL_A_MM_VERIFY_TIME, state->verify_time) || nla_put_u32(skb, ETHTOOL_A_MM_MAX_VERIFY_TIME, state->max_verify_time) || nla_put_u32(skb, ETHTOOL_A_MM_TX_MIN_FRAG_SIZE, state->tx_min_frag_size) || nla_put_u32(skb, ETHTOOL_A_MM_RX_MIN_FRAG_SIZE, state->rx_min_frag_size)) return -EMSGSIZE; if (req_base->flags & ETHTOOL_FLAG_STATS && mm_put_stats(skb, &data->stats)) return -EMSGSIZE; return 0; } const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1] = { [ETHTOOL_A_MM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_MM_VERIFY_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_MM_VERIFY_TIME] = NLA_POLICY_RANGE(NLA_U32, 1, 128), [ETHTOOL_A_MM_TX_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_MM_PMAC_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_MM_TX_MIN_FRAG_SIZE] = NLA_POLICY_RANGE(NLA_U32, 60, 252), }; static void mm_state_to_cfg(const struct ethtool_mm_state *state, struct ethtool_mm_cfg *cfg) { /* We could also compare state->verify_status against * ETHTOOL_MM_VERIFY_STATUS_DISABLED, but state->verify_enabled * is more like an administrative state which should be seen in * ETHTOOL_MSG_MM_GET replies. For example, a port with verification * disabled might be in the ETHTOOL_MM_VERIFY_STATUS_INITIAL * if it's down. */ cfg->verify_enabled = state->verify_enabled; cfg->verify_time = state->verify_time; cfg->tx_enabled = state->tx_enabled; cfg->pmac_enabled = state->pmac_enabled; cfg->tx_min_frag_size = state->tx_min_frag_size; } static int ethnl_set_mm_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_mm && ops->set_mm ? 1 : -EOPNOTSUPP; } static int ethnl_set_mm(struct ethnl_req_info *req_info, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct net_device *dev = req_info->dev; struct ethtool_mm_state state = {}; struct nlattr **tb = info->attrs; struct ethtool_mm_cfg cfg = {}; bool mod = false; int ret; ret = dev->ethtool_ops->get_mm(dev, &state); if (ret) return ret; mm_state_to_cfg(&state, &cfg); ethnl_update_bool(&cfg.verify_enabled, tb[ETHTOOL_A_MM_VERIFY_ENABLED], &mod); ethnl_update_u32(&cfg.verify_time, tb[ETHTOOL_A_MM_VERIFY_TIME], &mod); ethnl_update_bool(&cfg.tx_enabled, tb[ETHTOOL_A_MM_TX_ENABLED], &mod); ethnl_update_bool(&cfg.pmac_enabled, tb[ETHTOOL_A_MM_PMAC_ENABLED], &mod); ethnl_update_u32(&cfg.tx_min_frag_size, tb[ETHTOOL_A_MM_TX_MIN_FRAG_SIZE], &mod); if (!mod) return 0; if (cfg.verify_time > state.max_verify_time) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MM_VERIFY_TIME], "verifyTime exceeds device maximum"); return -ERANGE; } if (cfg.verify_enabled && !cfg.tx_enabled) { NL_SET_ERR_MSG(extack, "Verification requires TX enabled"); return -EINVAL; } if (cfg.tx_enabled && !cfg.pmac_enabled) { NL_SET_ERR_MSG(extack, "TX enabled requires pMAC enabled"); return -EINVAL; } ret = dev->ethtool_ops->set_mm(dev, &cfg, extack); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_mm_request_ops = { .request_cmd = ETHTOOL_MSG_MM_GET, .reply_cmd = ETHTOOL_MSG_MM_GET_REPLY, .hdr_attr = ETHTOOL_A_MM_HEADER, .req_info_size = sizeof(struct mm_req_info), .reply_data_size = sizeof(struct mm_reply_data), .prepare_data = mm_prepare_data, .reply_size = mm_reply_size, .fill_reply = mm_fill_reply, .set_validate = ethnl_set_mm_validate, .set = ethnl_set_mm, .set_ntf_cmd = ETHTOOL_MSG_MM_NTF, }; /* Returns whether a given device supports the MAC merge layer * (has an eMAC and a pMAC). Must be called under rtnl_lock() and * ethnl_ops_begin(). */ bool __ethtool_dev_mm_supported(struct net_device *dev) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_mm_state state = {}; int ret = -EOPNOTSUPP; if (ops && ops->get_mm) ret = ops->get_mm(dev, &state); return !ret; } bool ethtool_dev_mm_supported(struct net_device *dev) { const struct ethtool_ops *ops = dev->ethtool_ops; bool supported; int ret; ASSERT_RTNL(); if (!ops) return false; ret = ethnl_ops_begin(dev); if (ret < 0) return false; supported = __ethtool_dev_mm_supported(dev); ethnl_ops_complete(dev); return supported; } EXPORT_SYMBOL_GPL(ethtool_dev_mm_supported); |
| 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 414 414 2 8 8 8 8 8 8 8 4 4 1 4 4 4 4 4 4 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sunrpc/rpc_pipe.c * * Userland/kernel interface for rpcauth_gss. * Code shamelessly plagiarized from fs/nfsd/nfsctl.c * and fs/sysfs/inode.c * * Copyright (c) 2002, Trond Myklebust <trond.myklebust@fys.uio.no> * */ #include <linux/module.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/pagemap.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/namei.h> #include <linux/fsnotify.h> #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/utsname.h> #include <asm/ioctls.h> #include <linux/poll.h> #include <linux/wait.h> #include <linux/seq_file.h> #include <linux/sunrpc/clnt.h> #include <linux/workqueue.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/sunrpc/cache.h> #include <linux/nsproxy.h> #include <linux/notifier.h> #include "netns.h" #include "sunrpc.h" #define RPCDBG_FACILITY RPCDBG_DEBUG #define NET_NAME(net) ((net == &init_net) ? " (init_net)" : "") static struct file_system_type rpc_pipe_fs_type; static const struct rpc_pipe_ops gssd_dummy_pipe_ops; static struct kmem_cache *rpc_inode_cachep __read_mostly; #define RPC_UPCALL_TIMEOUT (30*HZ) static BLOCKING_NOTIFIER_HEAD(rpc_pipefs_notifier_list); int rpc_pipefs_notifier_register(struct notifier_block *nb) { return blocking_notifier_chain_register(&rpc_pipefs_notifier_list, nb); } EXPORT_SYMBOL_GPL(rpc_pipefs_notifier_register); void rpc_pipefs_notifier_unregister(struct notifier_block *nb) { blocking_notifier_chain_unregister(&rpc_pipefs_notifier_list, nb); } EXPORT_SYMBOL_GPL(rpc_pipefs_notifier_unregister); static void rpc_purge_list(wait_queue_head_t *waitq, struct list_head *head, void (*destroy_msg)(struct rpc_pipe_msg *), int err) { struct rpc_pipe_msg *msg; if (list_empty(head)) return; do { msg = list_entry(head->next, struct rpc_pipe_msg, list); list_del_init(&msg->list); msg->errno = err; destroy_msg(msg); } while (!list_empty(head)); if (waitq) wake_up(waitq); } static void rpc_timeout_upcall_queue(struct work_struct *work) { LIST_HEAD(free_list); struct rpc_pipe *pipe = container_of(work, struct rpc_pipe, queue_timeout.work); void (*destroy_msg)(struct rpc_pipe_msg *); struct dentry *dentry; spin_lock(&pipe->lock); destroy_msg = pipe->ops->destroy_msg; if (pipe->nreaders == 0) { list_splice_init(&pipe->pipe, &free_list); pipe->pipelen = 0; } dentry = dget(pipe->dentry); spin_unlock(&pipe->lock); rpc_purge_list(dentry ? &RPC_I(d_inode(dentry))->waitq : NULL, &free_list, destroy_msg, -ETIMEDOUT); dput(dentry); } ssize_t rpc_pipe_generic_upcall(struct file *filp, struct rpc_pipe_msg *msg, char __user *dst, size_t buflen) { char *data = (char *)msg->data + msg->copied; size_t mlen = min(msg->len - msg->copied, buflen); unsigned long left; left = copy_to_user(dst, data, mlen); if (left == mlen) { msg->errno = -EFAULT; return -EFAULT; } mlen -= left; msg->copied += mlen; msg->errno = 0; return mlen; } EXPORT_SYMBOL_GPL(rpc_pipe_generic_upcall); /** * rpc_queue_upcall - queue an upcall message to userspace * @pipe: upcall pipe on which to queue given message * @msg: message to queue * * Call with an @inode created by rpc_mkpipe() to queue an upcall. * A userspace process may then later read the upcall by performing a * read on an open file for this inode. It is up to the caller to * initialize the fields of @msg (other than @msg->list) appropriately. */ int rpc_queue_upcall(struct rpc_pipe *pipe, struct rpc_pipe_msg *msg) { int res = -EPIPE; struct dentry *dentry; spin_lock(&pipe->lock); if (pipe->nreaders) { list_add_tail(&msg->list, &pipe->pipe); pipe->pipelen += msg->len; res = 0; } else if (pipe->flags & RPC_PIPE_WAIT_FOR_OPEN) { if (list_empty(&pipe->pipe)) queue_delayed_work(rpciod_workqueue, &pipe->queue_timeout, RPC_UPCALL_TIMEOUT); list_add_tail(&msg->list, &pipe->pipe); pipe->pipelen += msg->len; res = 0; } dentry = dget(pipe->dentry); spin_unlock(&pipe->lock); if (dentry) { wake_up(&RPC_I(d_inode(dentry))->waitq); dput(dentry); } return res; } EXPORT_SYMBOL_GPL(rpc_queue_upcall); static inline void rpc_inode_setowner(struct inode *inode, void *private) { RPC_I(inode)->private = private; } static void rpc_close_pipes(struct inode *inode) { struct rpc_pipe *pipe = RPC_I(inode)->pipe; int need_release; LIST_HEAD(free_list); inode_lock(inode); spin_lock(&pipe->lock); need_release = pipe->nreaders != 0 || pipe->nwriters != 0; pipe->nreaders = 0; list_splice_init(&pipe->in_upcall, &free_list); list_splice_init(&pipe->pipe, &free_list); pipe->pipelen = 0; pipe->dentry = NULL; spin_unlock(&pipe->lock); rpc_purge_list(&RPC_I(inode)->waitq, &free_list, pipe->ops->destroy_msg, -EPIPE); pipe->nwriters = 0; if (need_release && pipe->ops->release_pipe) pipe->ops->release_pipe(inode); cancel_delayed_work_sync(&pipe->queue_timeout); rpc_inode_setowner(inode, NULL); RPC_I(inode)->pipe = NULL; inode_unlock(inode); } static struct inode * rpc_alloc_inode(struct super_block *sb) { struct rpc_inode *rpci; rpci = alloc_inode_sb(sb, rpc_inode_cachep, GFP_KERNEL); if (!rpci) return NULL; return &rpci->vfs_inode; } static void rpc_free_inode(struct inode *inode) { kmem_cache_free(rpc_inode_cachep, RPC_I(inode)); } static int rpc_pipe_open(struct inode *inode, struct file *filp) { struct rpc_pipe *pipe; int first_open; int res = -ENXIO; inode_lock(inode); pipe = RPC_I(inode)->pipe; if (pipe == NULL) goto out; first_open = pipe->nreaders == 0 && pipe->nwriters == 0; if (first_open && pipe->ops->open_pipe) { res = pipe->ops->open_pipe(inode); if (res) goto out; } if (filp->f_mode & FMODE_READ) pipe->nreaders++; if (filp->f_mode & FMODE_WRITE) pipe->nwriters++; res = 0; out: inode_unlock(inode); return res; } static int rpc_pipe_release(struct inode *inode, struct file *filp) { struct rpc_pipe *pipe; struct rpc_pipe_msg *msg; int last_close; inode_lock(inode); pipe = RPC_I(inode)->pipe; if (pipe == NULL) goto out; msg = filp->private_data; if (msg != NULL) { spin_lock(&pipe->lock); msg->errno = -EAGAIN; list_del_init(&msg->list); spin_unlock(&pipe->lock); pipe->ops->destroy_msg(msg); } if (filp->f_mode & FMODE_WRITE) pipe->nwriters --; if (filp->f_mode & FMODE_READ) { pipe->nreaders --; if (pipe->nreaders == 0) { LIST_HEAD(free_list); spin_lock(&pipe->lock); list_splice_init(&pipe->pipe, &free_list); pipe->pipelen = 0; spin_unlock(&pipe->lock); rpc_purge_list(&RPC_I(inode)->waitq, &free_list, pipe->ops->destroy_msg, -EAGAIN); } } last_close = pipe->nwriters == 0 && pipe->nreaders == 0; if (last_close && pipe->ops->release_pipe) pipe->ops->release_pipe(inode); out: inode_unlock(inode); return 0; } static ssize_t rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) { struct inode *inode = file_inode(filp); struct rpc_pipe *pipe; struct rpc_pipe_msg *msg; int res = 0; inode_lock(inode); pipe = RPC_I(inode)->pipe; if (pipe == NULL) { res = -EPIPE; goto out_unlock; } msg = filp->private_data; if (msg == NULL) { spin_lock(&pipe->lock); if (!list_empty(&pipe->pipe)) { msg = list_entry(pipe->pipe.next, struct rpc_pipe_msg, list); list_move(&msg->list, &pipe->in_upcall); pipe->pipelen -= msg->len; filp->private_data = msg; msg->copied = 0; } spin_unlock(&pipe->lock); if (msg == NULL) goto out_unlock; } /* NOTE: it is up to the callback to update msg->copied */ res = pipe->ops->upcall(filp, msg, buf, len); if (res < 0 || msg->len == msg->copied) { filp->private_data = NULL; spin_lock(&pipe->lock); list_del_init(&msg->list); spin_unlock(&pipe->lock); pipe->ops->destroy_msg(msg); } out_unlock: inode_unlock(inode); return res; } static ssize_t rpc_pipe_write(struct file *filp, const char __user *buf, size_t len, loff_t *offset) { struct inode *inode = file_inode(filp); int res; inode_lock(inode); res = -EPIPE; if (RPC_I(inode)->pipe != NULL) res = RPC_I(inode)->pipe->ops->downcall(filp, buf, len); inode_unlock(inode); return res; } static __poll_t rpc_pipe_poll(struct file *filp, struct poll_table_struct *wait) { struct inode *inode = file_inode(filp); struct rpc_inode *rpci = RPC_I(inode); __poll_t mask = EPOLLOUT | EPOLLWRNORM; poll_wait(filp, &rpci->waitq, wait); inode_lock(inode); if (rpci->pipe == NULL) mask |= EPOLLERR | EPOLLHUP; else if (filp->private_data || !list_empty(&rpci->pipe->pipe)) mask |= EPOLLIN | EPOLLRDNORM; inode_unlock(inode); return mask; } static long rpc_pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct rpc_pipe *pipe; int len; switch (cmd) { case FIONREAD: inode_lock(inode); pipe = RPC_I(inode)->pipe; if (pipe == NULL) { inode_unlock(inode); return -EPIPE; } spin_lock(&pipe->lock); len = pipe->pipelen; if (filp->private_data) { struct rpc_pipe_msg *msg; msg = filp->private_data; len += msg->len - msg->copied; } spin_unlock(&pipe->lock); inode_unlock(inode); return put_user(len, (int __user *)arg); default: return -EINVAL; } } static const struct file_operations rpc_pipe_fops = { .owner = THIS_MODULE, .llseek = no_llseek, .read = rpc_pipe_read, .write = rpc_pipe_write, .poll = rpc_pipe_poll, .unlocked_ioctl = rpc_pipe_ioctl, .open = rpc_pipe_open, .release = rpc_pipe_release, }; static int rpc_show_info(struct seq_file *m, void *v) { struct rpc_clnt *clnt = m->private; rcu_read_lock(); seq_printf(m, "RPC server: %s\n", rcu_dereference(clnt->cl_xprt)->servername); seq_printf(m, "service: %s (%d) version %d\n", clnt->cl_program->name, clnt->cl_prog, clnt->cl_vers); seq_printf(m, "address: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR)); seq_printf(m, "protocol: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_PROTO)); seq_printf(m, "port: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_PORT)); rcu_read_unlock(); return 0; } static int rpc_info_open(struct inode *inode, struct file *file) { struct rpc_clnt *clnt = NULL; int ret = single_open(file, rpc_show_info, NULL); if (!ret) { struct seq_file *m = file->private_data; spin_lock(&file->f_path.dentry->d_lock); if (!d_unhashed(file->f_path.dentry)) clnt = RPC_I(inode)->private; if (clnt != NULL && refcount_inc_not_zero(&clnt->cl_count)) { spin_unlock(&file->f_path.dentry->d_lock); m->private = clnt; } else { spin_unlock(&file->f_path.dentry->d_lock); single_release(inode, file); ret = -EINVAL; } } return ret; } static int rpc_info_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; struct rpc_clnt *clnt = (struct rpc_clnt *)m->private; if (clnt) rpc_release_client(clnt); return single_release(inode, file); } static const struct file_operations rpc_info_operations = { .owner = THIS_MODULE, .open = rpc_info_open, .read = seq_read, .llseek = seq_lseek, .release = rpc_info_release, }; /* * Description of fs contents. */ struct rpc_filelist { const char *name; const struct file_operations *i_fop; umode_t mode; }; static struct inode * rpc_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); if (!inode) return NULL; inode->i_ino = get_next_ino(); inode->i_mode = mode; simple_inode_init_ts(inode); switch (mode & S_IFMT) { case S_IFDIR: inode->i_fop = &simple_dir_operations; inode->i_op = &simple_dir_inode_operations; inc_nlink(inode); break; default: break; } return inode; } static int __rpc_create_common(struct inode *dir, struct dentry *dentry, umode_t mode, const struct file_operations *i_fop, void *private) { struct inode *inode; d_drop(dentry); inode = rpc_get_inode(dir->i_sb, mode); if (!inode) goto out_err; inode->i_ino = iunique(dir->i_sb, 100); if (i_fop) inode->i_fop = i_fop; if (private) rpc_inode_setowner(inode, private); d_add(dentry, inode); return 0; out_err: printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %pd\n", __FILE__, __func__, dentry); dput(dentry); return -ENOMEM; } static int __rpc_create(struct inode *dir, struct dentry *dentry, umode_t mode, const struct file_operations *i_fop, void *private) { int err; err = __rpc_create_common(dir, dentry, S_IFREG | mode, i_fop, private); if (err) return err; fsnotify_create(dir, dentry); return 0; } static int __rpc_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, const struct file_operations *i_fop, void *private) { int err; err = __rpc_create_common(dir, dentry, S_IFDIR | mode, i_fop, private); if (err) return err; inc_nlink(dir); fsnotify_mkdir(dir, dentry); return 0; } static void init_pipe(struct rpc_pipe *pipe) { pipe->nreaders = 0; pipe->nwriters = 0; INIT_LIST_HEAD(&pipe->in_upcall); INIT_LIST_HEAD(&pipe->in_downcall); INIT_LIST_HEAD(&pipe->pipe); pipe->pipelen = 0; INIT_DELAYED_WORK(&pipe->queue_timeout, rpc_timeout_upcall_queue); pipe->ops = NULL; spin_lock_init(&pipe->lock); pipe->dentry = NULL; } void rpc_destroy_pipe_data(struct rpc_pipe *pipe) { kfree(pipe); } EXPORT_SYMBOL_GPL(rpc_destroy_pipe_data); struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags) { struct rpc_pipe *pipe; pipe = kzalloc(sizeof(struct rpc_pipe), GFP_KERNEL); if (!pipe) return ERR_PTR(-ENOMEM); init_pipe(pipe); pipe->ops = ops; pipe->flags = flags; return pipe; } EXPORT_SYMBOL_GPL(rpc_mkpipe_data); static int __rpc_mkpipe_dentry(struct inode *dir, struct dentry *dentry, umode_t mode, const struct file_operations *i_fop, void *private, struct rpc_pipe *pipe) { struct rpc_inode *rpci; int err; err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private); if (err) return err; rpci = RPC_I(d_inode(dentry)); rpci->private = private; rpci->pipe = pipe; fsnotify_create(dir, dentry); return 0; } static int __rpc_rmdir(struct inode *dir, struct dentry *dentry) { int ret; dget(dentry); ret = simple_rmdir(dir, dentry); d_drop(dentry); if (!ret) fsnotify_rmdir(dir, dentry); dput(dentry); return ret; } static int __rpc_unlink(struct inode *dir, struct dentry *dentry) { int ret; dget(dentry); ret = simple_unlink(dir, dentry); d_drop(dentry); if (!ret) fsnotify_unlink(dir, dentry); dput(dentry); return ret; } static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); rpc_close_pipes(inode); return __rpc_unlink(dir, dentry); } static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent, const char *name) { struct qstr q = QSTR_INIT(name, strlen(name)); struct dentry *dentry = d_hash_and_lookup(parent, &q); if (!dentry) { dentry = d_alloc(parent, &q); if (!dentry) return ERR_PTR(-ENOMEM); } if (d_really_is_negative(dentry)) return dentry; dput(dentry); return ERR_PTR(-EEXIST); } /* * FIXME: This probably has races. */ static void __rpc_depopulate(struct dentry *parent, const struct rpc_filelist *files, int start, int eof) { struct inode *dir = d_inode(parent); struct dentry *dentry; struct qstr name; int i; for (i = start; i < eof; i++) { name.name = files[i].name; name.len = strlen(files[i].name); dentry = d_hash_and_lookup(parent, &name); if (dentry == NULL) continue; if (d_really_is_negative(dentry)) goto next; switch (d_inode(dentry)->i_mode & S_IFMT) { default: BUG(); case S_IFREG: __rpc_unlink(dir, dentry); break; case S_IFDIR: __rpc_rmdir(dir, dentry); } next: dput(dentry); } } static void rpc_depopulate(struct dentry *parent, const struct rpc_filelist *files, int start, int eof) { struct inode *dir = d_inode(parent); inode_lock_nested(dir, I_MUTEX_CHILD); __rpc_depopulate(parent, files, start, eof); inode_unlock(dir); } static int rpc_populate(struct dentry *parent, const struct rpc_filelist *files, int start, int eof, void *private) { struct inode *dir = d_inode(parent); struct dentry *dentry; int i, err; inode_lock(dir); for (i = start; i < eof; i++) { dentry = __rpc_lookup_create_exclusive(parent, files[i].name); err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_bad; switch (files[i].mode & S_IFMT) { default: BUG(); case S_IFREG: err = __rpc_create(dir, dentry, files[i].mode, files[i].i_fop, private); break; case S_IFDIR: err = __rpc_mkdir(dir, dentry, files[i].mode, NULL, private); } if (err != 0) goto out_bad; } inode_unlock(dir); return 0; out_bad: __rpc_depopulate(parent, files, start, eof); inode_unlock(dir); printk(KERN_WARNING "%s: %s failed to populate directory %pd\n", __FILE__, __func__, parent); return err; } static struct dentry *rpc_mkdir_populate(struct dentry *parent, const char *name, umode_t mode, void *private, int (*populate)(struct dentry *, void *), void *args_populate) { struct dentry *dentry; struct inode *dir = d_inode(parent); int error; inode_lock_nested(dir, I_MUTEX_PARENT); dentry = __rpc_lookup_create_exclusive(parent, name); if (IS_ERR(dentry)) goto out; error = __rpc_mkdir(dir, dentry, mode, NULL, private); if (error != 0) goto out_err; if (populate != NULL) { error = populate(dentry, args_populate); if (error) goto err_rmdir; } out: inode_unlock(dir); return dentry; err_rmdir: __rpc_rmdir(dir, dentry); out_err: dentry = ERR_PTR(error); goto out; } static int rpc_rmdir_depopulate(struct dentry *dentry, void (*depopulate)(struct dentry *)) { struct dentry *parent; struct inode *dir; int error; parent = dget_parent(dentry); dir = d_inode(parent); inode_lock_nested(dir, I_MUTEX_PARENT); if (depopulate != NULL) depopulate(dentry); error = __rpc_rmdir(dir, dentry); inode_unlock(dir); dput(parent); return error; } /** * rpc_mkpipe_dentry - make an rpc_pipefs file for kernel<->userspace * communication * @parent: dentry of directory to create new "pipe" in * @name: name of pipe * @private: private data to associate with the pipe, for the caller's use * @pipe: &rpc_pipe containing input parameters * * Data is made available for userspace to read by calls to * rpc_queue_upcall(). The actual reads will result in calls to * @ops->upcall, which will be called with the file pointer, * message, and userspace buffer to copy to. * * Writes can come at any time, and do not necessarily have to be * responses to upcalls. They will result in calls to @msg->downcall. * * The @private argument passed here will be available to all these methods * from the file pointer, via RPC_I(file_inode(file))->private. */ struct dentry *rpc_mkpipe_dentry(struct dentry *parent, const char *name, void *private, struct rpc_pipe *pipe) { struct dentry *dentry; struct inode *dir = d_inode(parent); umode_t umode = S_IFIFO | 0600; int err; if (pipe->ops->upcall == NULL) umode &= ~0444; if (pipe->ops->downcall == NULL) umode &= ~0222; inode_lock_nested(dir, I_MUTEX_PARENT); dentry = __rpc_lookup_create_exclusive(parent, name); if (IS_ERR(dentry)) goto out; err = __rpc_mkpipe_dentry(dir, dentry, umode, &rpc_pipe_fops, private, pipe); if (err) goto out_err; out: inode_unlock(dir); return dentry; out_err: dentry = ERR_PTR(err); printk(KERN_WARNING "%s: %s() failed to create pipe %pd/%s (errno = %d)\n", __FILE__, __func__, parent, name, err); goto out; } EXPORT_SYMBOL_GPL(rpc_mkpipe_dentry); /** * rpc_unlink - remove a pipe * @dentry: dentry for the pipe, as returned from rpc_mkpipe * * After this call, lookups will no longer find the pipe, and any * attempts to read or write using preexisting opens of the pipe will * return -EPIPE. */ int rpc_unlink(struct dentry *dentry) { struct dentry *parent; struct inode *dir; int error = 0; parent = dget_parent(dentry); dir = d_inode(parent); inode_lock_nested(dir, I_MUTEX_PARENT); error = __rpc_rmpipe(dir, dentry); inode_unlock(dir); dput(parent); return error; } EXPORT_SYMBOL_GPL(rpc_unlink); /** * rpc_init_pipe_dir_head - initialise a struct rpc_pipe_dir_head * @pdh: pointer to struct rpc_pipe_dir_head */ void rpc_init_pipe_dir_head(struct rpc_pipe_dir_head *pdh) { INIT_LIST_HEAD(&pdh->pdh_entries); pdh->pdh_dentry = NULL; } EXPORT_SYMBOL_GPL(rpc_init_pipe_dir_head); /** * rpc_init_pipe_dir_object - initialise a struct rpc_pipe_dir_object * @pdo: pointer to struct rpc_pipe_dir_object * @pdo_ops: pointer to const struct rpc_pipe_dir_object_ops * @pdo_data: pointer to caller-defined data */ void rpc_init_pipe_dir_object(struct rpc_pipe_dir_object *pdo, const struct rpc_pipe_dir_object_ops *pdo_ops, void *pdo_data) { INIT_LIST_HEAD(&pdo->pdo_head); pdo->pdo_ops = pdo_ops; pdo->pdo_data = pdo_data; } EXPORT_SYMBOL_GPL(rpc_init_pipe_dir_object); static int rpc_add_pipe_dir_object_locked(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo) { int ret = 0; if (pdh->pdh_dentry) ret = pdo->pdo_ops->create(pdh->pdh_dentry, pdo); if (ret == 0) list_add_tail(&pdo->pdo_head, &pdh->pdh_entries); return ret; } static void rpc_remove_pipe_dir_object_locked(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo) { if (pdh->pdh_dentry) pdo->pdo_ops->destroy(pdh->pdh_dentry, pdo); list_del_init(&pdo->pdo_head); } /** * rpc_add_pipe_dir_object - associate a rpc_pipe_dir_object to a directory * @net: pointer to struct net * @pdh: pointer to struct rpc_pipe_dir_head * @pdo: pointer to struct rpc_pipe_dir_object * */ int rpc_add_pipe_dir_object(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo) { int ret = 0; if (list_empty(&pdo->pdo_head)) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); mutex_lock(&sn->pipefs_sb_lock); ret = rpc_add_pipe_dir_object_locked(net, pdh, pdo); mutex_unlock(&sn->pipefs_sb_lock); } return ret; } EXPORT_SYMBOL_GPL(rpc_add_pipe_dir_object); /** * rpc_remove_pipe_dir_object - remove a rpc_pipe_dir_object from a directory * @net: pointer to struct net * @pdh: pointer to struct rpc_pipe_dir_head * @pdo: pointer to struct rpc_pipe_dir_object * */ void rpc_remove_pipe_dir_object(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo) { if (!list_empty(&pdo->pdo_head)) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); mutex_lock(&sn->pipefs_sb_lock); rpc_remove_pipe_dir_object_locked(net, pdh, pdo); mutex_unlock(&sn->pipefs_sb_lock); } } EXPORT_SYMBOL_GPL(rpc_remove_pipe_dir_object); /** * rpc_find_or_alloc_pipe_dir_object * @net: pointer to struct net * @pdh: pointer to struct rpc_pipe_dir_head * @match: match struct rpc_pipe_dir_object to data * @alloc: allocate a new struct rpc_pipe_dir_object * @data: user defined data for match() and alloc() * */ struct rpc_pipe_dir_object * rpc_find_or_alloc_pipe_dir_object(struct net *net, struct rpc_pipe_dir_head *pdh, int (*match)(struct rpc_pipe_dir_object *, void *), struct rpc_pipe_dir_object *(*alloc)(void *), void *data) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_pipe_dir_object *pdo; mutex_lock(&sn->pipefs_sb_lock); list_for_each_entry(pdo, &pdh->pdh_entries, pdo_head) { if (!match(pdo, data)) continue; goto out; } pdo = alloc(data); if (!pdo) goto out; rpc_add_pipe_dir_object_locked(net, pdh, pdo); out: mutex_unlock(&sn->pipefs_sb_lock); return pdo; } EXPORT_SYMBOL_GPL(rpc_find_or_alloc_pipe_dir_object); static void rpc_create_pipe_dir_objects(struct rpc_pipe_dir_head *pdh) { struct rpc_pipe_dir_object *pdo; struct dentry *dir = pdh->pdh_dentry; list_for_each_entry(pdo, &pdh->pdh_entries, pdo_head) pdo->pdo_ops->create(dir, pdo); } static void rpc_destroy_pipe_dir_objects(struct rpc_pipe_dir_head *pdh) { struct rpc_pipe_dir_object *pdo; struct dentry *dir = pdh->pdh_dentry; list_for_each_entry(pdo, &pdh->pdh_entries, pdo_head) pdo->pdo_ops->destroy(dir, pdo); } enum { RPCAUTH_info, RPCAUTH_EOF }; static const struct rpc_filelist authfiles[] = { [RPCAUTH_info] = { .name = "info", .i_fop = &rpc_info_operations, .mode = S_IFREG | 0400, }, }; static int rpc_clntdir_populate(struct dentry *dentry, void *private) { return rpc_populate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF, private); } static void rpc_clntdir_depopulate(struct dentry *dentry) { rpc_depopulate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF); } /** * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs * @dentry: the parent of new directory * @name: the name of new directory * @rpc_client: rpc client to associate with this directory * * This creates a directory at the given @path associated with * @rpc_clnt, which will contain a file named "info" with some basic * information about the client, together with any "pipes" that may * later be created using rpc_mkpipe(). */ struct dentry *rpc_create_client_dir(struct dentry *dentry, const char *name, struct rpc_clnt *rpc_client) { struct dentry *ret; ret = rpc_mkdir_populate(dentry, name, 0555, NULL, rpc_clntdir_populate, rpc_client); if (!IS_ERR(ret)) { rpc_client->cl_pipedir_objects.pdh_dentry = ret; rpc_create_pipe_dir_objects(&rpc_client->cl_pipedir_objects); } return ret; } /** * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir() * @rpc_client: rpc_client for the pipe */ int rpc_remove_client_dir(struct rpc_clnt *rpc_client) { struct dentry *dentry = rpc_client->cl_pipedir_objects.pdh_dentry; if (dentry == NULL) return 0; rpc_destroy_pipe_dir_objects(&rpc_client->cl_pipedir_objects); rpc_client->cl_pipedir_objects.pdh_dentry = NULL; return rpc_rmdir_depopulate(dentry, rpc_clntdir_depopulate); } static const struct rpc_filelist cache_pipefs_files[3] = { [0] = { .name = "channel", .i_fop = &cache_file_operations_pipefs, .mode = S_IFREG | 0600, }, [1] = { .name = "content", .i_fop = &content_file_operations_pipefs, .mode = S_IFREG | 0400, }, [2] = { .name = "flush", .i_fop = &cache_flush_operations_pipefs, .mode = S_IFREG | 0600, }, }; static int rpc_cachedir_populate(struct dentry *dentry, void *private) { return rpc_populate(dentry, cache_pipefs_files, 0, 3, private); } static void rpc_cachedir_depopulate(struct dentry *dentry) { rpc_depopulate(dentry, cache_pipefs_files, 0, 3); } struct dentry *rpc_create_cache_dir(struct dentry *parent, const char *name, umode_t umode, struct cache_detail *cd) { return rpc_mkdir_populate(parent, name, umode, NULL, rpc_cachedir_populate, cd); } void rpc_remove_cache_dir(struct dentry *dentry) { rpc_rmdir_depopulate(dentry, rpc_cachedir_depopulate); } /* * populate the filesystem */ static const struct super_operations s_ops = { .alloc_inode = rpc_alloc_inode, .free_inode = rpc_free_inode, .statfs = simple_statfs, }; #define RPCAUTH_GSSMAGIC 0x67596969 /* * We have a single directory with 1 node in it. */ enum { RPCAUTH_lockd, RPCAUTH_mount, RPCAUTH_nfs, RPCAUTH_portmap, RPCAUTH_statd, RPCAUTH_nfsd4_cb, RPCAUTH_cache, RPCAUTH_nfsd, RPCAUTH_gssd, RPCAUTH_RootEOF }; static const struct rpc_filelist files[] = { [RPCAUTH_lockd] = { .name = "lockd", .mode = S_IFDIR | 0555, }, [RPCAUTH_mount] = { .name = "mount", .mode = S_IFDIR | 0555, }, [RPCAUTH_nfs] = { .name = "nfs", .mode = S_IFDIR | 0555, }, [RPCAUTH_portmap] = { .name = "portmap", .mode = S_IFDIR | 0555, }, [RPCAUTH_statd] = { .name = "statd", .mode = S_IFDIR | 0555, }, [RPCAUTH_nfsd4_cb] = { .name = "nfsd4_cb", .mode = S_IFDIR | 0555, }, [RPCAUTH_cache] = { .name = "cache", .mode = S_IFDIR | 0555, }, [RPCAUTH_nfsd] = { .name = "nfsd", .mode = S_IFDIR | 0555, }, [RPCAUTH_gssd] = { .name = "gssd", .mode = S_IFDIR | 0555, }, }; /* * This call can be used only in RPC pipefs mount notification hooks. */ struct dentry *rpc_d_lookup_sb(const struct super_block *sb, const unsigned char *dir_name) { struct qstr dir = QSTR_INIT(dir_name, strlen(dir_name)); return d_hash_and_lookup(sb->s_root, &dir); } EXPORT_SYMBOL_GPL(rpc_d_lookup_sb); int rpc_pipefs_init_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); sn->gssd_dummy = rpc_mkpipe_data(&gssd_dummy_pipe_ops, 0); if (IS_ERR(sn->gssd_dummy)) return PTR_ERR(sn->gssd_dummy); mutex_init(&sn->pipefs_sb_lock); sn->pipe_version = -1; return 0; } void rpc_pipefs_exit_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); rpc_destroy_pipe_data(sn->gssd_dummy); } /* * This call will be used for per network namespace operations calls. * Note: Function will be returned with pipefs_sb_lock taken if superblock was * found. This lock have to be released by rpc_put_sb_net() when all operations * will be completed. */ struct super_block *rpc_get_sb_net(const struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); mutex_lock(&sn->pipefs_sb_lock); if (sn->pipefs_sb) return sn->pipefs_sb; mutex_unlock(&sn->pipefs_sb_lock); return NULL; } EXPORT_SYMBOL_GPL(rpc_get_sb_net); void rpc_put_sb_net(const struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); WARN_ON(sn->pipefs_sb == NULL); mutex_unlock(&sn->pipefs_sb_lock); } EXPORT_SYMBOL_GPL(rpc_put_sb_net); static const struct rpc_filelist gssd_dummy_clnt_dir[] = { [0] = { .name = "clntXX", .mode = S_IFDIR | 0555, }, }; static ssize_t dummy_downcall(struct file *filp, const char __user *src, size_t len) { return -EINVAL; } static const struct rpc_pipe_ops gssd_dummy_pipe_ops = { .upcall = rpc_pipe_generic_upcall, .downcall = dummy_downcall, }; /* * Here we present a bogus "info" file to keep rpc.gssd happy. We don't expect * that it will ever use this info to handle an upcall, but rpc.gssd expects * that this file will be there and have a certain format. */ static int rpc_dummy_info_show(struct seq_file *m, void *v) { seq_printf(m, "RPC server: %s\n", utsname()->nodename); seq_printf(m, "service: foo (1) version 0\n"); seq_printf(m, "address: 127.0.0.1\n"); seq_printf(m, "protocol: tcp\n"); seq_printf(m, "port: 0\n"); return 0; } DEFINE_SHOW_ATTRIBUTE(rpc_dummy_info); static const struct rpc_filelist gssd_dummy_info_file[] = { [0] = { .name = "info", .i_fop = &rpc_dummy_info_fops, .mode = S_IFREG | 0400, }, }; /** * rpc_gssd_dummy_populate - create a dummy gssd pipe * @root: root of the rpc_pipefs filesystem * @pipe_data: pipe data created when netns is initialized * * Create a dummy set of directories and a pipe that gssd can hold open to * indicate that it is up and running. */ static struct dentry * rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) { int ret = 0; struct dentry *gssd_dentry; struct dentry *clnt_dentry = NULL; struct dentry *pipe_dentry = NULL; struct qstr q = QSTR_INIT(files[RPCAUTH_gssd].name, strlen(files[RPCAUTH_gssd].name)); /* We should never get this far if "gssd" doesn't exist */ gssd_dentry = d_hash_and_lookup(root, &q); if (!gssd_dentry) return ERR_PTR(-ENOENT); ret = rpc_populate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1, NULL); if (ret) { pipe_dentry = ERR_PTR(ret); goto out; } q.name = gssd_dummy_clnt_dir[0].name; q.len = strlen(gssd_dummy_clnt_dir[0].name); clnt_dentry = d_hash_and_lookup(gssd_dentry, &q); if (!clnt_dentry) { __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); pipe_dentry = ERR_PTR(-ENOENT); goto out; } ret = rpc_populate(clnt_dentry, gssd_dummy_info_file, 0, 1, NULL); if (ret) { __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); pipe_dentry = ERR_PTR(ret); goto out; } pipe_dentry = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data); if (IS_ERR(pipe_dentry)) { __rpc_depopulate(clnt_dentry, gssd_dummy_info_file, 0, 1); __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); } out: dput(clnt_dentry); dput(gssd_dentry); return pipe_dentry; } static void rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry) { struct dentry *clnt_dir = pipe_dentry->d_parent; struct dentry *gssd_dir = clnt_dir->d_parent; dget(pipe_dentry); __rpc_rmpipe(d_inode(clnt_dir), pipe_dentry); __rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1); __rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1); dput(pipe_dentry); } static int rpc_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct dentry *root, *gssd_dentry; struct net *net = sb->s_fs_info; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); int err; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = RPCAUTH_GSSMAGIC; sb->s_op = &s_ops; sb->s_d_op = &simple_dentry_operations; sb->s_time_gran = 1; inode = rpc_get_inode(sb, S_IFDIR | 0555); sb->s_root = root = d_make_root(inode); if (!root) return -ENOMEM; if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL)) return -ENOMEM; gssd_dentry = rpc_gssd_dummy_populate(root, sn->gssd_dummy); if (IS_ERR(gssd_dentry)) { __rpc_depopulate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF); return PTR_ERR(gssd_dentry); } dprintk("RPC: sending pipefs MOUNT notification for net %x%s\n", net->ns.inum, NET_NAME(net)); mutex_lock(&sn->pipefs_sb_lock); sn->pipefs_sb = sb; err = blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_MOUNT, sb); if (err) goto err_depopulate; mutex_unlock(&sn->pipefs_sb_lock); return 0; err_depopulate: rpc_gssd_dummy_depopulate(gssd_dentry); blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_UMOUNT, sb); sn->pipefs_sb = NULL; __rpc_depopulate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF); mutex_unlock(&sn->pipefs_sb_lock); return err; } bool gssd_running(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_pipe *pipe = sn->gssd_dummy; return pipe->nreaders || pipe->nwriters; } EXPORT_SYMBOL_GPL(gssd_running); static int rpc_fs_get_tree(struct fs_context *fc) { return get_tree_keyed(fc, rpc_fill_super, get_net(fc->net_ns)); } static void rpc_fs_free_fc(struct fs_context *fc) { if (fc->s_fs_info) put_net(fc->s_fs_info); } static const struct fs_context_operations rpc_fs_context_ops = { .free = rpc_fs_free_fc, .get_tree = rpc_fs_get_tree, }; static int rpc_init_fs_context(struct fs_context *fc) { put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(fc->net_ns->user_ns); fc->ops = &rpc_fs_context_ops; return 0; } static void rpc_kill_sb(struct super_block *sb) { struct net *net = sb->s_fs_info; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); mutex_lock(&sn->pipefs_sb_lock); if (sn->pipefs_sb != sb) { mutex_unlock(&sn->pipefs_sb_lock); goto out; } sn->pipefs_sb = NULL; dprintk("RPC: sending pipefs UMOUNT notification for net %x%s\n", net->ns.inum, NET_NAME(net)); blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_UMOUNT, sb); mutex_unlock(&sn->pipefs_sb_lock); out: kill_litter_super(sb); put_net(net); } static struct file_system_type rpc_pipe_fs_type = { .owner = THIS_MODULE, .name = "rpc_pipefs", .init_fs_context = rpc_init_fs_context, .kill_sb = rpc_kill_sb, }; MODULE_ALIAS_FS("rpc_pipefs"); MODULE_ALIAS("rpc_pipefs"); static void init_once(void *foo) { struct rpc_inode *rpci = (struct rpc_inode *) foo; inode_init_once(&rpci->vfs_inode); rpci->private = NULL; rpci->pipe = NULL; init_waitqueue_head(&rpci->waitq); } int register_rpc_pipefs(void) { int err; rpc_inode_cachep = kmem_cache_create("rpc_inode_cache", sizeof(struct rpc_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (!rpc_inode_cachep) return -ENOMEM; err = rpc_clients_notifier_register(); if (err) goto err_notifier; err = register_filesystem(&rpc_pipe_fs_type); if (err) goto err_register; return 0; err_register: rpc_clients_notifier_unregister(); err_notifier: kmem_cache_destroy(rpc_inode_cachep); return err; } void unregister_rpc_pipefs(void) { rpc_clients_notifier_unregister(); unregister_filesystem(&rpc_pipe_fs_type); kmem_cache_destroy(rpc_inode_cachep); } |
| 76 76 18 18 28 28 2 1 1 1 1 1 1 1 2 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 | /* * net/tipc/monitor.c * * Copyright (c) 2016, Ericsson AB * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include <net/genetlink.h> #include "core.h" #include "addr.h" #include "monitor.h" #include "bearer.h" #define MAX_MON_DOMAIN 64 #define MON_TIMEOUT 120000 #define MAX_PEER_DOWN_EVENTS 4 /* struct tipc_mon_domain: domain record to be transferred between peers * @len: actual size of domain record * @gen: current generation of sender's domain * @ack_gen: most recent generation of self's domain acked by peer * @member_cnt: number of domain member nodes described in this record * @up_map: bit map indicating which of the members the sender considers up * @members: identity of the domain members */ struct tipc_mon_domain { u16 len; u16 gen; u16 ack_gen; u16 member_cnt; u64 up_map; u32 members[MAX_MON_DOMAIN]; }; /* struct tipc_peer: state of a peer node and its domain * @addr: tipc node identity of peer * @head_map: shows which other nodes currently consider peer 'up' * @domain: most recent domain record from peer * @hash: position in hashed lookup list * @list: position in linked list, in circular ascending order by 'addr' * @applied: number of reported domain members applied on this monitor list * @is_up: peer is up as seen from this node * @is_head: peer is assigned domain head as seen from this node * @is_local: peer is in local domain and should be continuously monitored * @down_cnt: - numbers of other peers which have reported this on lost */ struct tipc_peer { u32 addr; struct tipc_mon_domain *domain; struct hlist_node hash; struct list_head list; u8 applied; u8 down_cnt; bool is_up; bool is_head; bool is_local; }; struct tipc_monitor { struct hlist_head peers[NODE_HTABLE_SIZE]; int peer_cnt; struct tipc_peer *self; rwlock_t lock; struct tipc_mon_domain cache; u16 list_gen; u16 dom_gen; struct net *net; struct timer_list timer; unsigned long timer_intv; }; static struct tipc_monitor *tipc_monitor(struct net *net, int bearer_id) { return tipc_net(net)->monitors[bearer_id]; } const int tipc_max_domain_size = sizeof(struct tipc_mon_domain); static inline u16 mon_cpu_to_le16(u16 val) { return (__force __u16)htons(val); } static inline u32 mon_cpu_to_le32(u32 val) { return (__force __u32)htonl(val); } static inline u64 mon_cpu_to_le64(u64 val) { return (__force __u64)cpu_to_be64(val); } static inline u16 mon_le16_to_cpu(u16 val) { return ntohs((__force __be16)val); } static inline u32 mon_le32_to_cpu(u32 val) { return ntohl((__force __be32)val); } static inline u64 mon_le64_to_cpu(u64 val) { return be64_to_cpu((__force __be64)val); } /* dom_rec_len(): actual length of domain record for transport */ static int dom_rec_len(struct tipc_mon_domain *dom, u16 mcnt) { return (offsetof(struct tipc_mon_domain, members)) + (mcnt * sizeof(u32)); } /* dom_size() : calculate size of own domain based on number of peers */ static int dom_size(int peers) { int i = 0; while ((i * i) < peers) i++; return min(i, MAX_MON_DOMAIN); } static void map_set(u64 *up_map, int i, unsigned int v) { *up_map &= ~(1ULL << i); *up_map |= ((u64)v << i); } static int map_get(u64 up_map, int i) { return (up_map & (1ULL << i)) >> i; } static struct tipc_peer *peer_prev(struct tipc_peer *peer) { return list_last_entry(&peer->list, struct tipc_peer, list); } static struct tipc_peer *peer_nxt(struct tipc_peer *peer) { return list_first_entry(&peer->list, struct tipc_peer, list); } static struct tipc_peer *peer_head(struct tipc_peer *peer) { while (!peer->is_head) peer = peer_prev(peer); return peer; } static struct tipc_peer *get_peer(struct tipc_monitor *mon, u32 addr) { struct tipc_peer *peer; unsigned int thash = tipc_hashfn(addr); hlist_for_each_entry(peer, &mon->peers[thash], hash) { if (peer->addr == addr) return peer; } return NULL; } static struct tipc_peer *get_self(struct net *net, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); return mon->self; } static inline bool tipc_mon_is_active(struct net *net, struct tipc_monitor *mon) { struct tipc_net *tn = tipc_net(net); return mon->peer_cnt > tn->mon_threshold; } /* mon_identify_lost_members() : - identify amd mark potentially lost members */ static void mon_identify_lost_members(struct tipc_peer *peer, struct tipc_mon_domain *dom_bef, int applied_bef) { struct tipc_peer *member = peer; struct tipc_mon_domain *dom_aft = peer->domain; int applied_aft = peer->applied; int i; for (i = 0; i < applied_bef; i++) { member = peer_nxt(member); /* Do nothing if self or peer already see member as down */ if (!member->is_up || !map_get(dom_bef->up_map, i)) continue; /* Loss of local node must be detected by active probing */ if (member->is_local) continue; /* Start probing if member was removed from applied domain */ if (!applied_aft || (applied_aft < i)) { member->down_cnt = 1; continue; } /* Member loss is confirmed if it is still in applied domain */ if (!map_get(dom_aft->up_map, i)) member->down_cnt++; } } /* mon_apply_domain() : match a peer's domain record against monitor list */ static void mon_apply_domain(struct tipc_monitor *mon, struct tipc_peer *peer) { struct tipc_mon_domain *dom = peer->domain; struct tipc_peer *member; u32 addr; int i; if (!dom || !peer->is_up) return; /* Scan across domain members and match against monitor list */ peer->applied = 0; member = peer_nxt(peer); for (i = 0; i < dom->member_cnt; i++) { addr = dom->members[i]; if (addr != member->addr) return; peer->applied++; member = peer_nxt(member); } } /* mon_update_local_domain() : update after peer addition/removal/up/down */ static void mon_update_local_domain(struct tipc_monitor *mon) { struct tipc_peer *self = mon->self; struct tipc_mon_domain *cache = &mon->cache; struct tipc_mon_domain *dom = self->domain; struct tipc_peer *peer = self; u64 prev_up_map = dom->up_map; u16 member_cnt, i; bool diff; /* Update local domain size based on current size of cluster */ member_cnt = dom_size(mon->peer_cnt) - 1; self->applied = member_cnt; /* Update native and cached outgoing local domain records */ dom->len = dom_rec_len(dom, member_cnt); diff = dom->member_cnt != member_cnt; dom->member_cnt = member_cnt; for (i = 0; i < member_cnt; i++) { peer = peer_nxt(peer); diff |= dom->members[i] != peer->addr; dom->members[i] = peer->addr; map_set(&dom->up_map, i, peer->is_up); cache->members[i] = mon_cpu_to_le32(peer->addr); } diff |= dom->up_map != prev_up_map; if (!diff) return; dom->gen = ++mon->dom_gen; cache->len = mon_cpu_to_le16(dom->len); cache->gen = mon_cpu_to_le16(dom->gen); cache->member_cnt = mon_cpu_to_le16(member_cnt); cache->up_map = mon_cpu_to_le64(dom->up_map); mon_apply_domain(mon, self); } /* mon_update_neighbors() : update preceding neighbors of added/removed peer */ static void mon_update_neighbors(struct tipc_monitor *mon, struct tipc_peer *peer) { int dz, i; dz = dom_size(mon->peer_cnt); for (i = 0; i < dz; i++) { mon_apply_domain(mon, peer); peer = peer_prev(peer); } } /* mon_assign_roles() : reassign peer roles after a network change * The monitor list is consistent at this stage; i.e., each peer is monitoring * a set of domain members as matched between domain record and the monitor list */ static void mon_assign_roles(struct tipc_monitor *mon, struct tipc_peer *head) { struct tipc_peer *peer = peer_nxt(head); struct tipc_peer *self = mon->self; int i = 0; for (; peer != self; peer = peer_nxt(peer)) { peer->is_local = false; /* Update domain member */ if (i++ < head->applied) { peer->is_head = false; if (head == self) peer->is_local = true; continue; } /* Assign next domain head */ if (!peer->is_up) continue; if (peer->is_head) break; head = peer; head->is_head = true; i = 0; } mon->list_gen++; } void tipc_mon_remove_peer(struct net *net, u32 addr, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *self; struct tipc_peer *peer, *prev, *head; if (!mon) return; self = get_self(net, bearer_id); write_lock_bh(&mon->lock); peer = get_peer(mon, addr); if (!peer) goto exit; prev = peer_prev(peer); list_del(&peer->list); hlist_del(&peer->hash); kfree(peer->domain); kfree(peer); mon->peer_cnt--; head = peer_head(prev); if (head == self) mon_update_local_domain(mon); mon_update_neighbors(mon, prev); /* Revert to full-mesh monitoring if we reach threshold */ if (!tipc_mon_is_active(net, mon)) { list_for_each_entry(peer, &self->list, list) { kfree(peer->domain); peer->domain = NULL; peer->applied = 0; } } mon_assign_roles(mon, head); exit: write_unlock_bh(&mon->lock); } static bool tipc_mon_add_peer(struct tipc_monitor *mon, u32 addr, struct tipc_peer **peer) { struct tipc_peer *self = mon->self; struct tipc_peer *cur, *prev, *p; p = kzalloc(sizeof(*p), GFP_ATOMIC); *peer = p; if (!p) return false; p->addr = addr; /* Add new peer to lookup list */ INIT_LIST_HEAD(&p->list); hlist_add_head(&p->hash, &mon->peers[tipc_hashfn(addr)]); /* Sort new peer into iterator list, in ascending circular order */ prev = self; list_for_each_entry(cur, &self->list, list) { if ((addr > prev->addr) && (addr < cur->addr)) break; if (((addr < cur->addr) || (addr > prev->addr)) && (prev->addr > cur->addr)) break; prev = cur; } list_add_tail(&p->list, &cur->list); mon->peer_cnt++; mon_update_neighbors(mon, p); return true; } void tipc_mon_peer_up(struct net *net, u32 addr, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *self = get_self(net, bearer_id); struct tipc_peer *peer, *head; write_lock_bh(&mon->lock); peer = get_peer(mon, addr); if (!peer && !tipc_mon_add_peer(mon, addr, &peer)) goto exit; peer->is_up = true; head = peer_head(peer); if (head == self) mon_update_local_domain(mon); mon_assign_roles(mon, head); exit: write_unlock_bh(&mon->lock); } void tipc_mon_peer_down(struct net *net, u32 addr, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *self; struct tipc_peer *peer, *head; struct tipc_mon_domain *dom; int applied; if (!mon) return; self = get_self(net, bearer_id); write_lock_bh(&mon->lock); peer = get_peer(mon, addr); if (!peer) { pr_warn("Mon: unknown link %x/%u DOWN\n", addr, bearer_id); goto exit; } applied = peer->applied; peer->applied = 0; dom = peer->domain; peer->domain = NULL; if (peer->is_head) mon_identify_lost_members(peer, dom, applied); kfree(dom); peer->is_up = false; peer->is_head = false; peer->is_local = false; peer->down_cnt = 0; head = peer_head(peer); if (head == self) mon_update_local_domain(mon); mon_assign_roles(mon, head); exit: write_unlock_bh(&mon->lock); } /* tipc_mon_rcv - process monitor domain event message */ void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr, struct tipc_mon_state *state, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_mon_domain *arrv_dom = data; struct tipc_mon_domain dom_bef; struct tipc_mon_domain *dom; struct tipc_peer *peer; u16 new_member_cnt = mon_le16_to_cpu(arrv_dom->member_cnt); int new_dlen = dom_rec_len(arrv_dom, new_member_cnt); u16 new_gen = mon_le16_to_cpu(arrv_dom->gen); u16 acked_gen = mon_le16_to_cpu(arrv_dom->ack_gen); u16 arrv_dlen = mon_le16_to_cpu(arrv_dom->len); bool probing = state->probing; int i, applied_bef; state->probing = false; /* Sanity check received domain record */ if (new_member_cnt > MAX_MON_DOMAIN) return; if (dlen < dom_rec_len(arrv_dom, 0)) return; if (dlen != dom_rec_len(arrv_dom, new_member_cnt)) return; if (dlen < new_dlen || arrv_dlen != new_dlen) return; /* Synch generation numbers with peer if link just came up */ if (!state->synched) { state->peer_gen = new_gen - 1; state->acked_gen = acked_gen; state->synched = true; } if (more(acked_gen, state->acked_gen)) state->acked_gen = acked_gen; /* Drop duplicate unless we are waiting for a probe response */ if (!more(new_gen, state->peer_gen) && !probing) return; write_lock_bh(&mon->lock); peer = get_peer(mon, addr); if (!peer || !peer->is_up) goto exit; /* Peer is confirmed, stop any ongoing probing */ peer->down_cnt = 0; /* Task is done for duplicate record */ if (!more(new_gen, state->peer_gen)) goto exit; state->peer_gen = new_gen; /* Cache current domain record for later use */ dom_bef.member_cnt = 0; dom = peer->domain; if (dom) memcpy(&dom_bef, dom, dom->len); /* Transform and store received domain record */ if (!dom || (dom->len < new_dlen)) { kfree(dom); dom = kmalloc(new_dlen, GFP_ATOMIC); peer->domain = dom; if (!dom) goto exit; } dom->len = new_dlen; dom->gen = new_gen; dom->member_cnt = new_member_cnt; dom->up_map = mon_le64_to_cpu(arrv_dom->up_map); for (i = 0; i < new_member_cnt; i++) dom->members[i] = mon_le32_to_cpu(arrv_dom->members[i]); /* Update peers affected by this domain record */ applied_bef = peer->applied; mon_apply_domain(mon, peer); mon_identify_lost_members(peer, &dom_bef, applied_bef); mon_assign_roles(mon, peer_head(peer)); exit: write_unlock_bh(&mon->lock); } void tipc_mon_prep(struct net *net, void *data, int *dlen, struct tipc_mon_state *state, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_mon_domain *dom = data; u16 gen = mon->dom_gen; u16 len; /* Send invalid record if not active */ if (!tipc_mon_is_active(net, mon)) { dom->len = 0; return; } /* Send only a dummy record with ack if peer has acked our last sent */ if (likely(state->acked_gen == gen)) { len = dom_rec_len(dom, 0); *dlen = len; dom->len = mon_cpu_to_le16(len); dom->gen = mon_cpu_to_le16(gen); dom->ack_gen = mon_cpu_to_le16(state->peer_gen); dom->member_cnt = 0; return; } /* Send the full record */ read_lock_bh(&mon->lock); len = mon_le16_to_cpu(mon->cache.len); *dlen = len; memcpy(data, &mon->cache, len); read_unlock_bh(&mon->lock); dom->ack_gen = mon_cpu_to_le16(state->peer_gen); } void tipc_mon_get_state(struct net *net, u32 addr, struct tipc_mon_state *state, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *peer; if (!tipc_mon_is_active(net, mon)) { state->probing = false; state->monitoring = true; return; } /* Used cached state if table has not changed */ if (!state->probing && (state->list_gen == mon->list_gen) && (state->acked_gen == mon->dom_gen)) return; read_lock_bh(&mon->lock); peer = get_peer(mon, addr); if (peer) { state->probing = state->acked_gen != mon->dom_gen; state->probing |= peer->down_cnt; state->reset |= peer->down_cnt >= MAX_PEER_DOWN_EVENTS; state->monitoring = peer->is_local; state->monitoring |= peer->is_head; state->list_gen = mon->list_gen; } read_unlock_bh(&mon->lock); } static void mon_timeout(struct timer_list *t) { struct tipc_monitor *mon = from_timer(mon, t, timer); struct tipc_peer *self; int best_member_cnt = dom_size(mon->peer_cnt) - 1; write_lock_bh(&mon->lock); self = mon->self; if (self && (best_member_cnt != self->applied)) { mon_update_local_domain(mon); mon_assign_roles(mon, self); } write_unlock_bh(&mon->lock); mod_timer(&mon->timer, jiffies + mon->timer_intv); } int tipc_mon_create(struct net *net, int bearer_id) { struct tipc_net *tn = tipc_net(net); struct tipc_monitor *mon; struct tipc_peer *self; struct tipc_mon_domain *dom; if (tn->monitors[bearer_id]) return 0; mon = kzalloc(sizeof(*mon), GFP_ATOMIC); self = kzalloc(sizeof(*self), GFP_ATOMIC); dom = kzalloc(sizeof(*dom), GFP_ATOMIC); if (!mon || !self || !dom) { kfree(mon); kfree(self); kfree(dom); return -ENOMEM; } tn->monitors[bearer_id] = mon; rwlock_init(&mon->lock); mon->net = net; mon->peer_cnt = 1; mon->self = self; self->domain = dom; self->addr = tipc_own_addr(net); self->is_up = true; self->is_head = true; INIT_LIST_HEAD(&self->list); timer_setup(&mon->timer, mon_timeout, 0); mon->timer_intv = msecs_to_jiffies(MON_TIMEOUT + (tn->random & 0xffff)); mod_timer(&mon->timer, jiffies + mon->timer_intv); return 0; } void tipc_mon_delete(struct net *net, int bearer_id) { struct tipc_net *tn = tipc_net(net); struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *self; struct tipc_peer *peer, *tmp; if (!mon) return; self = get_self(net, bearer_id); write_lock_bh(&mon->lock); tn->monitors[bearer_id] = NULL; list_for_each_entry_safe(peer, tmp, &self->list, list) { list_del(&peer->list); hlist_del(&peer->hash); kfree(peer->domain); kfree(peer); } mon->self = NULL; write_unlock_bh(&mon->lock); timer_shutdown_sync(&mon->timer); kfree(self->domain); kfree(self); kfree(mon); } void tipc_mon_reinit_self(struct net *net) { struct tipc_monitor *mon; int bearer_id; for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { mon = tipc_monitor(net, bearer_id); if (!mon) continue; write_lock_bh(&mon->lock); mon->self->addr = tipc_own_addr(net); write_unlock_bh(&mon->lock); } } int tipc_nl_monitor_set_threshold(struct net *net, u32 cluster_size) { struct tipc_net *tn = tipc_net(net); if (cluster_size > TIPC_CLUSTER_SIZE) return -EINVAL; tn->mon_threshold = cluster_size; return 0; } int tipc_nl_monitor_get_threshold(struct net *net) { struct tipc_net *tn = tipc_net(net); return tn->mon_threshold; } static int __tipc_nl_add_monitor_peer(struct tipc_peer *peer, struct tipc_nl_msg *msg) { struct tipc_mon_domain *dom = peer->domain; struct nlattr *attrs; void *hdr; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_MON_PEER_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON_PEER); if (!attrs) goto msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_ADDR, peer->addr)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_APPLIED, peer->applied)) goto attr_msg_full; if (peer->is_up) if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_UP)) goto attr_msg_full; if (peer->is_local) if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_LOCAL)) goto attr_msg_full; if (peer->is_head) if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_HEAD)) goto attr_msg_full; if (dom) { if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_DOMGEN, dom->gen)) goto attr_msg_full; if (nla_put_u64_64bit(msg->skb, TIPC_NLA_MON_PEER_UPMAP, dom->up_map, TIPC_NLA_MON_PEER_PAD)) goto attr_msg_full; if (nla_put(msg->skb, TIPC_NLA_MON_PEER_MEMBERS, dom->member_cnt * sizeof(u32), &dom->members)) goto attr_msg_full; } nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg, u32 bearer_id, u32 *prev_node) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *peer; if (!mon) return -EINVAL; read_lock_bh(&mon->lock); peer = mon->self; do { if (*prev_node) { if (peer->addr == *prev_node) *prev_node = 0; else continue; } if (__tipc_nl_add_monitor_peer(peer, msg)) { *prev_node = peer->addr; read_unlock_bh(&mon->lock); return -EMSGSIZE; } } while ((peer = peer_nxt(peer)) != mon->self); read_unlock_bh(&mon->lock); return 0; } int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg, u32 bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); char bearer_name[TIPC_MAX_BEARER_NAME]; struct nlattr *attrs; void *hdr; int ret; ret = tipc_bearer_get_name(net, bearer_name, bearer_id); if (ret || !mon) return 0; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_MON_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON); if (!attrs) goto msg_full; read_lock_bh(&mon->lock); if (nla_put_u32(msg->skb, TIPC_NLA_MON_REF, bearer_id)) goto attr_msg_full; if (tipc_mon_is_active(net, mon)) if (nla_put_flag(msg->skb, TIPC_NLA_MON_ACTIVE)) goto attr_msg_full; if (nla_put_string(msg->skb, TIPC_NLA_MON_BEARER_NAME, bearer_name)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEERCNT, mon->peer_cnt)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_MON_LISTGEN, mon->list_gen)) goto attr_msg_full; read_unlock_bh(&mon->lock); nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; attr_msg_full: read_unlock_bh(&mon->lock); nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } |
| 44793 44808 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 | // SPDX-License-Identifier: GPL-2.0-only /* * x86 APERF/MPERF KHz calculation for * /sys/.../cpufreq/scaling_cur_freq * * Copyright (C) 2017 Intel Corp. * Author: Len Brown <len.brown@intel.com> */ #include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/ktime.h> #include <linux/math64.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/sched/isolation.h> #include <linux/sched/topology.h> #include <linux/smp.h> #include <linux/syscore_ops.h> #include <asm/cpu.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include "cpu.h" struct aperfmperf { seqcount_t seq; unsigned long last_update; u64 acnt; u64 mcnt; u64 aperf; u64 mperf; }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct aperfmperf, cpu_samples) = { .seq = SEQCNT_ZERO(cpu_samples.seq) }; static void init_counter_refs(void) { u64 aperf, mperf; rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); this_cpu_write(cpu_samples.aperf, aperf); this_cpu_write(cpu_samples.mperf, mperf); } #if defined(CONFIG_X86_64) && defined(CONFIG_SMP) /* * APERF/MPERF frequency ratio computation. * * The scheduler wants to do frequency invariant accounting and needs a <1 * ratio to account for the 'current' frequency, corresponding to * freq_curr / freq_max. * * Since the frequency freq_curr on x86 is controlled by micro-controller and * our P-state setting is little more than a request/hint, we need to observe * the effective frequency 'BusyMHz', i.e. the average frequency over a time * interval after discarding idle time. This is given by: * * BusyMHz = delta_APERF / delta_MPERF * freq_base * * where freq_base is the max non-turbo P-state. * * The freq_max term has to be set to a somewhat arbitrary value, because we * can't know which turbo states will be available at a given point in time: * it all depends on the thermal headroom of the entire package. We set it to * the turbo level with 4 cores active. * * Benchmarks show that's a good compromise between the 1C turbo ratio * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, * which would ignore the entire turbo range (a conspicuous part, making * freq_curr/freq_max always maxed out). * * An exception to the heuristic above is the Atom uarch, where we choose the * highest turbo level for freq_max since Atom's are generally oriented towards * power efficiency. * * Setting freq_max to anything less than the 1C turbo ratio makes the ratio * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. */ DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; void arch_set_max_freq_ratio(bool turbo_disabled) { arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : arch_turbo_freq_ratio; } EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); static bool __init turbo_disabled(void) { u64 misc_en; int err; err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en); if (err) return false; return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); } static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) { int err; err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq); if (err) return false; err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); if (err) return false; *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ return true; } #define X86_MATCH(vfm) \ X86_MATCH_VFM_FEATURE(vfm, X86_FEATURE_APERFMPERF, NULL) static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_XEON_PHI_KNL), X86_MATCH(INTEL_XEON_PHI_KNM), {} }; static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_SKYLAKE_X), {} }; static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_ATOM_GOLDMONT), X86_MATCH(INTEL_ATOM_GOLDMONT_D), X86_MATCH(INTEL_ATOM_GOLDMONT_PLUS), {} }; static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int num_delta_fratio) { int fratio, delta_fratio, found; int err, i; u64 msr; err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); if (err) return false; fratio = (msr >> 8) & 0xFF; i = 16; found = 0; do { if (found >= num_delta_fratio) { *turbo_freq = fratio; return true; } delta_fratio = (msr >> (i + 5)) & 0x7; if (delta_fratio) { found += 1; fratio -= delta_fratio; } i += 8; } while (i < 64); return true; } static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) { u64 ratios, counts; u32 group_size; int err, i; err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios); if (err) return false; err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts); if (err) return false; for (i = 0; i < 64; i += 8) { group_size = (counts >> i) & 0xFF; if (group_size >= size) { *turbo_freq = (ratios >> i) & 0xFF; return true; } } return false; } static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) { u64 msr; int err; err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ /* The CPU may have less than 4 cores */ if (!*turbo_freq) *turbo_freq = msr & 0xFF; /* 1C turbo */ return true; } static bool __init intel_set_max_freq_ratio(void) { u64 base_freq, turbo_freq; u64 turbo_ratio; if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) goto out; if (x86_match_cpu(has_glm_turbo_ratio_limits) && skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; if (x86_match_cpu(has_knl_turbo_ratio_limits) && knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; if (x86_match_cpu(has_skx_turbo_ratio_limits) && skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) goto out; if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) goto out; return false; out: /* * Some hypervisors advertise X86_FEATURE_APERFMPERF * but then fill all MSR's with zeroes. * Some CPUs have turbo boost but don't declare any turbo ratio * in MSR_TURBO_RATIO_LIMIT. */ if (!base_freq || !turbo_freq) { pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n"); return false; } turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); if (!turbo_ratio) { pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n"); return false; } arch_turbo_freq_ratio = turbo_ratio; arch_set_max_freq_ratio(turbo_disabled()); return true; } #ifdef CONFIG_PM_SLEEP static struct syscore_ops freq_invariance_syscore_ops = { .resume = init_counter_refs, }; static void register_freq_invariance_syscore_ops(void) { register_syscore_ops(&freq_invariance_syscore_ops); } #else static inline void register_freq_invariance_syscore_ops(void) {} #endif static void freq_invariance_enable(void) { if (static_branch_unlikely(&arch_scale_freq_key)) { WARN_ON_ONCE(1); return; } static_branch_enable_cpuslocked(&arch_scale_freq_key); register_freq_invariance_syscore_ops(); pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { arch_turbo_freq_ratio = ratio; arch_set_max_freq_ratio(turbo_disabled); freq_invariance_enable(); } static void __init bp_init_freq_invariance(void) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return; if (intel_set_max_freq_ratio()) { guard(cpus_read_lock)(); freq_invariance_enable(); } } static void disable_freq_invariance_workfn(struct work_struct *work) { int cpu; static_branch_disable(&arch_scale_freq_key); /* * Set arch_freq_scale to a default value on all cpus * This negates the effect of scaling */ for_each_possible_cpu(cpu) per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE; } static DECLARE_WORK(disable_freq_invariance_work, disable_freq_invariance_workfn); DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale); static DEFINE_STATIC_KEY_FALSE(arch_hybrid_cap_scale_key); struct arch_hybrid_cpu_scale { unsigned long capacity; unsigned long freq_ratio; }; static struct arch_hybrid_cpu_scale __percpu *arch_cpu_scale; /** * arch_enable_hybrid_capacity_scale() - Enable hybrid CPU capacity scaling * * Allocate memory for per-CPU data used by hybrid CPU capacity scaling, * initialize it and set the static key controlling its code paths. * * Must be called before arch_set_cpu_capacity(). */ bool arch_enable_hybrid_capacity_scale(void) { int cpu; if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) { WARN_ONCE(1, "Hybrid CPU capacity scaling already enabled"); return true; } arch_cpu_scale = alloc_percpu(struct arch_hybrid_cpu_scale); if (!arch_cpu_scale) return false; for_each_possible_cpu(cpu) { per_cpu_ptr(arch_cpu_scale, cpu)->capacity = SCHED_CAPACITY_SCALE; per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio = arch_max_freq_ratio; } static_branch_enable(&arch_hybrid_cap_scale_key); pr_info("Hybrid CPU capacity scaling enabled\n"); return true; } /** * arch_set_cpu_capacity() - Set scale-invariance parameters for a CPU * @cpu: Target CPU. * @cap: Capacity of @cpu at its maximum frequency, relative to @max_cap. * @max_cap: System-wide maximum CPU capacity. * @cap_freq: Frequency of @cpu corresponding to @cap. * @base_freq: Frequency of @cpu at which MPERF counts. * * The units in which @cap and @max_cap are expressed do not matter, so long * as they are consistent, because the former is effectively divided by the * latter. Analogously for @cap_freq and @base_freq. * * After calling this function for all CPUs, call arch_rebuild_sched_domains() * to let the scheduler know that capacity-aware scheduling can be used going * forward. */ void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long max_cap, unsigned long cap_freq, unsigned long base_freq) { if (static_branch_likely(&arch_hybrid_cap_scale_key)) { WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity, div_u64(cap << SCHED_CAPACITY_SHIFT, max_cap)); WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio, div_u64(cap_freq << SCHED_CAPACITY_SHIFT, base_freq)); } else { WARN_ONCE(1, "Hybrid CPU capacity scaling not enabled"); } } unsigned long arch_scale_cpu_capacity(int cpu) { if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) return READ_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity); return SCHED_CAPACITY_SCALE; } EXPORT_SYMBOL_GPL(arch_scale_cpu_capacity); static void scale_freq_tick(u64 acnt, u64 mcnt) { u64 freq_scale, freq_ratio; if (!arch_scale_freq_invariant()) return; if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) goto error; if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) freq_ratio = READ_ONCE(this_cpu_ptr(arch_cpu_scale)->freq_ratio); else freq_ratio = arch_max_freq_ratio; if (check_mul_overflow(mcnt, freq_ratio, &mcnt) || !mcnt) goto error; freq_scale = div64_u64(acnt, mcnt); if (!freq_scale) goto error; if (freq_scale > SCHED_CAPACITY_SCALE) freq_scale = SCHED_CAPACITY_SCALE; this_cpu_write(arch_freq_scale, freq_scale); return; error: pr_warn("Scheduler frequency invariance went wobbly, disabling!\n"); schedule_work(&disable_freq_invariance_work); } #else static inline void bp_init_freq_invariance(void) { } static inline void scale_freq_tick(u64 acnt, u64 mcnt) { } #endif /* CONFIG_X86_64 && CONFIG_SMP */ void arch_scale_freq_tick(void) { struct aperfmperf *s = this_cpu_ptr(&cpu_samples); u64 acnt, mcnt, aperf, mperf; if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) return; rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); acnt = aperf - s->aperf; mcnt = mperf - s->mperf; s->aperf = aperf; s->mperf = mperf; raw_write_seqcount_begin(&s->seq); s->last_update = jiffies; s->acnt = acnt; s->mcnt = mcnt; raw_write_seqcount_end(&s->seq); scale_freq_tick(acnt, mcnt); } /* * Discard samples older than the define maximum sample age of 20ms. There * is no point in sending IPIs in such a case. If the scheduler tick was * not running then the CPU is either idle or isolated. */ #define MAX_SAMPLE_AGE ((unsigned long)HZ / 50) unsigned int arch_freq_get_on_cpu(int cpu) { struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu); unsigned int seq, freq; unsigned long last; u64 acnt, mcnt; if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) goto fallback; do { seq = raw_read_seqcount_begin(&s->seq); last = s->last_update; acnt = s->acnt; mcnt = s->mcnt; } while (read_seqcount_retry(&s->seq, seq)); /* * Bail on invalid count and when the last update was too long ago, * which covers idle and NOHZ full CPUs. */ if (!mcnt || (jiffies - last) > MAX_SAMPLE_AGE) goto fallback; return div64_u64((cpu_khz * acnt), mcnt); fallback: freq = cpufreq_quick_get(cpu); return freq ? freq : cpu_khz; } static int __init bp_init_aperfmperf(void) { if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) return 0; init_counter_refs(); bp_init_freq_invariance(); return 0; } early_initcall(bp_init_aperfmperf); void ap_init_aperfmperf(void) { if (cpu_feature_enabled(X86_FEATURE_APERFMPERF)) init_counter_refs(); } |
| 9 10 10 1 5 4 10 10 10 10 10 10 10 9 10 9 5 10 2 2 1 1 10 12 5 12 12 12 3 12 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 | // SPDX-License-Identifier: GPL-2.0-or-later /* procfs files for key database enumeration * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/init.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <asm/errno.h> #include "internal.h" static void *proc_keys_start(struct seq_file *p, loff_t *_pos); static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos); static void proc_keys_stop(struct seq_file *p, void *v); static int proc_keys_show(struct seq_file *m, void *v); static const struct seq_operations proc_keys_ops = { .start = proc_keys_start, .next = proc_keys_next, .stop = proc_keys_stop, .show = proc_keys_show, }; static void *proc_key_users_start(struct seq_file *p, loff_t *_pos); static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos); static void proc_key_users_stop(struct seq_file *p, void *v); static int proc_key_users_show(struct seq_file *m, void *v); static const struct seq_operations proc_key_users_ops = { .start = proc_key_users_start, .next = proc_key_users_next, .stop = proc_key_users_stop, .show = proc_key_users_show, }; /* * Declare the /proc files. */ static int __init key_proc_init(void) { struct proc_dir_entry *p; p = proc_create_seq("keys", 0, NULL, &proc_keys_ops); if (!p) panic("Cannot create /proc/keys\n"); p = proc_create_seq("key-users", 0, NULL, &proc_key_users_ops); if (!p) panic("Cannot create /proc/key-users\n"); return 0; } __initcall(key_proc_init); /* * Implement "/proc/keys" to provide a list of the keys on the system that * grant View permission to the caller. */ static struct rb_node *key_serial_next(struct seq_file *p, struct rb_node *n) { struct user_namespace *user_ns = seq_user_ns(p); n = rb_next(n); while (n) { struct key *key = rb_entry(n, struct key, serial_node); if (kuid_has_mapping(user_ns, key->user->uid)) break; n = rb_next(n); } return n; } static struct key *find_ge_key(struct seq_file *p, key_serial_t id) { struct user_namespace *user_ns = seq_user_ns(p); struct rb_node *n = key_serial_tree.rb_node; struct key *minkey = NULL; while (n) { struct key *key = rb_entry(n, struct key, serial_node); if (id < key->serial) { if (!minkey || minkey->serial > key->serial) minkey = key; n = n->rb_left; } else if (id > key->serial) { n = n->rb_right; } else { minkey = key; break; } key = NULL; } if (!minkey) return NULL; for (;;) { if (kuid_has_mapping(user_ns, minkey->user->uid)) return minkey; n = rb_next(&minkey->serial_node); if (!n) return NULL; minkey = rb_entry(n, struct key, serial_node); } } static void *proc_keys_start(struct seq_file *p, loff_t *_pos) __acquires(key_serial_lock) { key_serial_t pos = *_pos; struct key *key; spin_lock(&key_serial_lock); if (*_pos > INT_MAX) return NULL; key = find_ge_key(p, pos); if (!key) return NULL; *_pos = key->serial; return &key->serial_node; } static inline key_serial_t key_node_serial(struct rb_node *n) { struct key *key = rb_entry(n, struct key, serial_node); return key->serial; } static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos) { struct rb_node *n; n = key_serial_next(p, v); if (n) *_pos = key_node_serial(n); else (*_pos)++; return n; } static void proc_keys_stop(struct seq_file *p, void *v) __releases(key_serial_lock) { spin_unlock(&key_serial_lock); } static int proc_keys_show(struct seq_file *m, void *v) { struct rb_node *_p = v; struct key *key = rb_entry(_p, struct key, serial_node); unsigned long flags; key_ref_t key_ref, skey_ref; time64_t now, expiry; char xbuf[16]; short state; u64 timo; int rc; struct keyring_search_context ctx = { .index_key = key->index_key, .cred = m->file->f_cred, .match_data.cmp = lookup_user_key_possessed, .match_data.raw_data = key, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .flags = (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_RECURSE), }; key_ref = make_key_ref(key, 0); /* determine if the key is possessed by this process (a test we can * skip if the key does not indicate the possessor can view it */ if (key->perm & KEY_POS_VIEW) { rcu_read_lock(); skey_ref = search_cred_keyrings_rcu(&ctx); rcu_read_unlock(); if (!IS_ERR(skey_ref)) { key_ref_put(skey_ref); key_ref = make_key_ref(key, 1); } } /* check whether the current task is allowed to view the key */ rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW); if (rc < 0) return 0; now = ktime_get_real_seconds(); rcu_read_lock(); /* come up with a suitable timeout value */ expiry = READ_ONCE(key->expiry); if (expiry == TIME64_MAX) { memcpy(xbuf, "perm", 5); } else if (now >= expiry) { memcpy(xbuf, "expd", 5); } else { timo = expiry - now; if (timo < 60) sprintf(xbuf, "%llus", timo); else if (timo < 60*60) sprintf(xbuf, "%llum", div_u64(timo, 60)); else if (timo < 60*60*24) sprintf(xbuf, "%lluh", div_u64(timo, 60 * 60)); else if (timo < 60*60*24*7) sprintf(xbuf, "%llud", div_u64(timo, 60 * 60 * 24)); else sprintf(xbuf, "%lluw", div_u64(timo, 60 * 60 * 24 * 7)); } state = key_read_state(key); #define showflag(FLAGS, LETTER, FLAG) \ ((FLAGS & (1 << FLAG)) ? LETTER : '-') flags = READ_ONCE(key->flags); seq_printf(m, "%08x %c%c%c%c%c%c%c %5d %4s %08x %5d %5d %-9.9s ", key->serial, state != KEY_IS_UNINSTANTIATED ? 'I' : '-', showflag(flags, 'R', KEY_FLAG_REVOKED), showflag(flags, 'D', KEY_FLAG_DEAD), showflag(flags, 'Q', KEY_FLAG_IN_QUOTA), showflag(flags, 'U', KEY_FLAG_USER_CONSTRUCT), state < 0 ? 'N' : '-', showflag(flags, 'i', KEY_FLAG_INVALIDATED), refcount_read(&key->usage), xbuf, key->perm, from_kuid_munged(seq_user_ns(m), key->uid), from_kgid_munged(seq_user_ns(m), key->gid), key->type->name); #undef showflag if (key->type->describe) key->type->describe(key, m); seq_putc(m, '\n'); rcu_read_unlock(); return 0; } static struct rb_node *__key_user_next(struct user_namespace *user_ns, struct rb_node *n) { while (n) { struct key_user *user = rb_entry(n, struct key_user, node); if (kuid_has_mapping(user_ns, user->uid)) break; n = rb_next(n); } return n; } static struct rb_node *key_user_next(struct user_namespace *user_ns, struct rb_node *n) { return __key_user_next(user_ns, rb_next(n)); } static struct rb_node *key_user_first(struct user_namespace *user_ns, struct rb_root *r) { struct rb_node *n = rb_first(r); return __key_user_next(user_ns, n); } static void *proc_key_users_start(struct seq_file *p, loff_t *_pos) __acquires(key_user_lock) { struct rb_node *_p; loff_t pos = *_pos; spin_lock(&key_user_lock); _p = key_user_first(seq_user_ns(p), &key_user_tree); while (pos > 0 && _p) { pos--; _p = key_user_next(seq_user_ns(p), _p); } return _p; } static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos) { (*_pos)++; return key_user_next(seq_user_ns(p), (struct rb_node *)v); } static void proc_key_users_stop(struct seq_file *p, void *v) __releases(key_user_lock) { spin_unlock(&key_user_lock); } static int proc_key_users_show(struct seq_file *m, void *v) { struct rb_node *_p = v; struct key_user *user = rb_entry(_p, struct key_user, node); unsigned maxkeys = uid_eq(user->uid, GLOBAL_ROOT_UID) ? key_quota_root_maxkeys : key_quota_maxkeys; unsigned maxbytes = uid_eq(user->uid, GLOBAL_ROOT_UID) ? key_quota_root_maxbytes : key_quota_maxbytes; seq_printf(m, "%5u: %5d %d/%d %d/%d %d/%d\n", from_kuid_munged(seq_user_ns(m), user->uid), refcount_read(&user->usage), atomic_read(&user->nkeys), atomic_read(&user->nikeys), user->qnkeys, maxkeys, user->qnbytes, maxbytes); return 0; } |
| 3 95 16 100 83 1774 113 480 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_WAIT_H #define _LINUX_WAIT_H /* * Linux wait queue related types and methods */ #include <linux/list.h> #include <linux/stddef.h> #include <linux/spinlock.h> #include <asm/current.h> typedef struct wait_queue_entry wait_queue_entry_t; typedef int (*wait_queue_func_t)(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key); /* wait_queue_entry::flags */ #define WQ_FLAG_EXCLUSIVE 0x01 #define WQ_FLAG_WOKEN 0x02 #define WQ_FLAG_CUSTOM 0x04 #define WQ_FLAG_DONE 0x08 #define WQ_FLAG_PRIORITY 0x10 /* * A single wait-queue entry structure: */ struct wait_queue_entry { unsigned int flags; void *private; wait_queue_func_t func; struct list_head entry; }; struct wait_queue_head { spinlock_t lock; struct list_head head; }; typedef struct wait_queue_head wait_queue_head_t; struct task_struct; /* * Macros for declaration and initialisaton of the datatypes */ #define __WAITQUEUE_INITIALIZER(name, tsk) { \ .private = tsk, \ .func = default_wake_function, \ .entry = { NULL, NULL } } #define DECLARE_WAITQUEUE(name, tsk) \ struct wait_queue_entry name = __WAITQUEUE_INITIALIZER(name, tsk) #define __WAIT_QUEUE_HEAD_INITIALIZER(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = LIST_HEAD_INIT(name.head) } #define DECLARE_WAIT_QUEUE_HEAD(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name) extern void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *); #define init_waitqueue_head(wq_head) \ do { \ static struct lock_class_key __key; \ \ __init_waitqueue_head((wq_head), #wq_head, &__key); \ } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ ({ init_waitqueue_head(&name); name; }) # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) \ struct wait_queue_head name = __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) #else # define DECLARE_WAIT_QUEUE_HEAD_ONSTACK(name) DECLARE_WAIT_QUEUE_HEAD(name) #endif static inline void init_waitqueue_entry(struct wait_queue_entry *wq_entry, struct task_struct *p) { wq_entry->flags = 0; wq_entry->private = p; wq_entry->func = default_wake_function; } static inline void init_waitqueue_func_entry(struct wait_queue_entry *wq_entry, wait_queue_func_t func) { wq_entry->flags = 0; wq_entry->private = NULL; wq_entry->func = func; } /** * waitqueue_active -- locklessly test for waiters on the queue * @wq_head: the waitqueue to test for waiters * * returns true if the wait list is not empty * * NOTE: this function is lockless and requires care, incorrect usage _will_ * lead to sporadic and non-obvious failure. * * Use either while holding wait_queue_head::lock or when used for wakeups * with an extra smp_mb() like:: * * CPU0 - waker CPU1 - waiter * * for (;;) { * @cond = true; prepare_to_wait(&wq_head, &wait, state); * smp_mb(); // smp_mb() from set_current_state() * if (waitqueue_active(wq_head)) if (@cond) * wake_up(wq_head); break; * schedule(); * } * finish_wait(&wq_head, &wait); * * Because without the explicit smp_mb() it's possible for the * waitqueue_active() load to get hoisted over the @cond store such that we'll * observe an empty wait list while the waiter might not observe @cond. * * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), * which (when the lock is uncontended) are of roughly equal cost. */ static inline int waitqueue_active(struct wait_queue_head *wq_head) { return !list_empty(&wq_head->head); } /** * wq_has_single_sleeper - check if there is only one sleeper * @wq_head: wait queue head * * Returns true of wq_head has only one sleeper on the list. * * Please refer to the comment for waitqueue_active. */ static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head) { return list_is_singular(&wq_head->head); } /** * wq_has_sleeper - check if there are any waiting processes * @wq_head: wait queue head * * Returns true if wq_head has waiting processes * * Please refer to the comment for waitqueue_active. */ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head) { /* * We need to be sure we are in sync with the * add_wait_queue modifications to the wait queue. * * This memory barrier should be paired with one on the * waiting side. */ smp_mb(); return waitqueue_active(wq_head); } extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { struct list_head *head = &wq_head->head; struct wait_queue_entry *wq; list_for_each_entry(wq, &wq_head->head, entry) { if (!(wq->flags & WQ_FLAG_PRIORITY)) break; head = &wq->entry; } list_add(&wq_entry->entry, head); } /* * Used for wake-one threads: */ static inline void __add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { wq_entry->flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq_head, wq_entry); } static inline void __add_wait_queue_entry_tail(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_add_tail(&wq_entry->entry, &wq_head->head); } static inline void __add_wait_queue_entry_tail_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { wq_entry->flags |= WQ_FLAG_EXCLUSIVE; __add_wait_queue_entry_tail(wq_head, wq_entry); } static inline void __remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry) { list_del(&wq_entry->entry); } int __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) #define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) #define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) #define wake_up_interruptible_all(x) __wake_up(x, TASK_INTERRUPTIBLE, 0, NULL) #define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE) /* * Wakeup macros to be used to report events to the targets. */ #define poll_to_key(m) ((void *)(__force uintptr_t)(__poll_t)(m)) #define key_to_poll(m) ((__force __poll_t)(uintptr_t)(void *)(m)) #define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, poll_to_key(m)) #define wake_up_poll_on_current_cpu(x, m) \ __wake_up_on_current_cpu(x, TASK_NORMAL, poll_to_key(m)) #define wake_up_locked_poll(x, m) \ __wake_up_locked_key((x), TASK_NORMAL, poll_to_key(m)) #define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, poll_to_key(m)) #define wake_up_interruptible_sync_poll(x, m) \ __wake_up_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) #define wake_up_interruptible_sync_poll_locked(x, m) \ __wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) /** * wake_up_pollfree - signal that a polled waitqueue is going away * @wq_head: the wait queue head * * In the very rare cases where a ->poll() implementation uses a waitqueue whose * lifetime is tied to a task rather than to the 'struct file' being polled, * this function must be called before the waitqueue is freed so that * non-blocking polls (e.g. epoll) are notified that the queue is going away. * * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU. */ static inline void wake_up_pollfree(struct wait_queue_head *wq_head) { /* * For performance reasons, we don't always take the queue lock here. * Therefore, we might race with someone removing the last entry from * the queue, and proceed while they still hold the queue lock. * However, rcu_read_lock() is required to be held in such cases, so we * can safely proceed with an RCU-delayed free. */ if (waitqueue_active(wq_head)) __wake_up_pollfree(wq_head); } #define ___wait_cond_timeout(condition) \ ({ \ bool __cond = (condition); \ if (__cond && !__ret) \ __ret = 1; \ __cond || !__ret; \ }) #define ___wait_is_interruptible(state) \ (!__builtin_constant_p(state) || \ (state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); /* * The below macro ___wait_event() has an explicit shadow of the __ret * variable when used from the wait_event_*() macros. * * This is so that both can use the ___wait_cond_timeout() construct * to wrap the condition. * * The type inconsistency of the wait_event_*() __ret variable is also * on purpose; we use long where we can return timeout values and int * otherwise. */ #define ___wait_event(wq_head, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ struct wait_queue_entry __wq_entry; \ long __ret = ret; /* explicit shadow */ \ \ init_wait_entry(&__wq_entry, exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ for (;;) { \ long __int = prepare_to_wait_event(&wq_head, &__wq_entry, state);\ \ if (condition) \ break; \ \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ goto __out; \ } \ \ cmd; \ } \ finish_wait(&wq_head, &__wq_entry); \ __out: __ret; \ }) #define __wait_event(wq_head, condition) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event(wq_head, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_event(wq_head, condition); \ } while (0) #define __io_wait_event(wq_head, condition) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ io_schedule()) /* * io_wait_event() -- like wait_event() but with io_schedule() */ #define io_wait_event(wq_head, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __io_wait_event(wq_head, condition); \ } while (0) #define __wait_event_freezable(wq_head, condition) \ ___wait_event(wq_head, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), \ 0, 0, schedule()) /** * wait_event_freezable - sleep (or freeze) until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute * to system load) until the @condition evaluates to true. The * @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event_freezable(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_freezable(wq_head, condition); \ __ret; \ }) #define __wait_event_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_freezable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 0, timeout, \ __ret = schedule_timeout(__ret)) /* * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid * increasing load and is freezable. */ #define wait_event_freezable_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_freezable_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 1, 0, \ cmd1; schedule(); cmd2) /* * Just like wait_event_cmd(), except it sets exclusive flag */ #define wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2) \ do { \ if (condition) \ break; \ __wait_event_exclusive_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) #define __wait_event_cmd(wq_head, condition, cmd1, cmd2) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ cmd1; schedule(); cmd2) /** * wait_event_cmd - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @cmd1: the command will be executed before sleep * @cmd2: the command will be executed after sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */ #define wait_event_cmd(wq_head, condition, cmd1, cmd2) \ do { \ if (condition) \ break; \ __wait_event_cmd(wq_head, condition, cmd1, cmd2); \ } while (0) #define __wait_event_interruptible(wq_head, condition) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) /** * wait_event_interruptible - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_interruptible(wq_head, condition); \ __ret; \ }) #define __wait_event_interruptible_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_INTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_interruptible_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a signal. */ #define wait_event_interruptible_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_interruptible_timeout(wq_head, \ condition, timeout); \ __ret; \ }) #define __wait_event_hrtimeout(wq_head, condition, timeout, state) \ ({ \ int __ret = 0; \ struct hrtimer_sleeper __t; \ \ hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ HRTIMER_MODE_REL); \ if ((timeout) != KTIME_MAX) { \ hrtimer_set_expires_range_ns(&__t.timer, timeout, \ current->timer_slack_ns); \ hrtimer_sleeper_start_expires(&__t, HRTIMER_MODE_REL); \ } \ \ __ret = ___wait_event(wq_head, condition, state, 0, 0, \ if (!__t.task) { \ __ret = -ETIME; \ break; \ } \ schedule()); \ \ hrtimer_cancel(&__t.timer); \ destroy_hrtimer_on_stack(&__t.timer); \ __ret; \ }) /** * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function returns 0 if @condition became true, or -ETIME if the timeout * elapsed. */ #define wait_event_hrtimeout(wq_head, condition, timeout) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_hrtimeout(wq_head, condition, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ }) /** * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, as a ktime_t * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function returns 0 if @condition became true, -ERESTARTSYS if it was * interrupted by a signal, or -ETIME if the timeout elapsed. */ #define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ ({ \ long __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_hrtimeout(wq, condition, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ }) #define __wait_event_interruptible_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ schedule()) #define wait_event_interruptible_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_interruptible_exclusive(wq, condition); \ __ret; \ }) #define __wait_event_killable_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ schedule()) #define wait_event_killable_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_killable_exclusive(wq, condition); \ __ret; \ }) #define __wait_event_freezable_exclusive(wq, condition) \ ___wait_event(wq, condition, (TASK_INTERRUPTIBLE|TASK_FREEZABLE), 1, 0,\ schedule()) #define wait_event_freezable_exclusive(wq, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_freezable_exclusive(wq, condition); \ __ret; \ }) /** * wait_event_idle - wait for a condition without contributing to system load * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * */ #define wait_event_idle(wq_head, condition) \ do { \ might_sleep(); \ if (!(condition)) \ ___wait_event(wq_head, condition, TASK_IDLE, 0, 0, schedule()); \ } while (0) /** * wait_event_idle_exclusive - wait for a condition with contributing to system load * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. * The @condition is checked each time the waitqueue @wq_head is woken up. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus if other processes wait on the same list, when this * process is woken further processes are not considered. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * */ #define wait_event_idle_exclusive(wq_head, condition) \ do { \ might_sleep(); \ if (!(condition)) \ ___wait_event(wq_head, condition, TASK_IDLE, 1, 0, schedule()); \ } while (0) #define __wait_event_idle_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_IDLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_idle_timeout - sleep without load until a condition becomes true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_idle_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_idle_timeout(wq_head, condition, timeout); \ __ret; \ }) #define __wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_IDLE, 1, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_idle_exclusive_timeout - sleep without load until a condition becomes true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_IDLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus if other processes wait on the same list, when this * process is woken further processes are not considered. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * or the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed. */ #define wait_event_idle_exclusive_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_idle_exclusive_timeout(wq_head, condition, timeout);\ __ret; \ }) extern int do_wait_intr(wait_queue_head_t *, wait_queue_entry_t *); extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); #define __wait_event_interruptible_locked(wq, condition, exclusive, fn) \ ({ \ int __ret; \ DEFINE_WAIT(__wait); \ if (exclusive) \ __wait.flags |= WQ_FLAG_EXCLUSIVE; \ do { \ __ret = fn(&(wq), &__wait); \ if (__ret) \ break; \ } while (!(condition)); \ __remove_wait_queue(&(wq), &__wait); \ __set_current_state(TASK_RUNNING); \ __ret; \ }) /** * wait_event_interruptible_locked - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock()/spin_unlock() * functions which must match the way they are locked/unlocked outside * of this macro. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_locked(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr)) /** * wait_event_interruptible_locked_irq - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq() * functions which must match the way they are locked/unlocked outside * of this macro. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_locked_irq(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 0, do_wait_intr_irq)) /** * wait_event_interruptible_exclusive_locked - sleep exclusively until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock()/spin_unlock() * functions which must match the way they are locked/unlocked outside * of this macro. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus when other process waits process on the list if this * process is awaken further processes are not considered. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_exclusive_locked(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr)) /** * wait_event_interruptible_exclusive_locked_irq - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq is woken up. * * It must be called with wq.lock being held. This spinlock is * unlocked while sleeping but @condition testing is done while lock * is held and when this macro exits the lock is held. * * The lock is locked/unlocked using spin_lock_irq()/spin_unlock_irq() * functions which must match the way they are locked/unlocked outside * of this macro. * * The process is put on the wait queue with an WQ_FLAG_EXCLUSIVE flag * set thus when other process waits process on the list if this * process is awaken further processes are not considered. * * wake_up_locked() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_interruptible_exclusive_locked_irq(wq, condition) \ ((condition) \ ? 0 : __wait_event_interruptible_locked(wq, condition, 1, do_wait_intr_irq)) #define __wait_event_killable(wq, condition) \ ___wait_event(wq, condition, TASK_KILLABLE, 0, 0, schedule()) /** * wait_event_killable - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a * signal and 0 if @condition evaluated to true. */ #define wait_event_killable(wq_head, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_killable(wq_head, condition); \ __ret; \ }) #define __wait_event_state(wq, condition, state) \ ___wait_event(wq, condition, state, 0, 0, schedule()) /** * wait_event_state - sleep until a condition gets true * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @state: state to sleep in * * The process is put to sleep (@state) until the @condition evaluates to true * or a signal is received (when allowed by @state). The @condition is checked * each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * The function will return -ERESTARTSYS if it was interrupted by a signal * (when allowed by @state) and 0 if @condition evaluated to true. */ #define wait_event_state(wq_head, condition, state) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_event_state(wq_head, condition, state); \ __ret; \ }) #define __wait_event_killable_timeout(wq_head, condition, timeout) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ TASK_KILLABLE, 0, timeout, \ __ret = schedule_timeout(__ret)) /** * wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_KILLABLE) until the * @condition evaluates to true or a kill signal is received. * The @condition is checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * Returns: * 0 if the @condition evaluated to %false after the @timeout elapsed, * 1 if the @condition evaluated to %true after the @timeout elapsed, * the remaining jiffies (at least 1) if the @condition evaluated * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was * interrupted by a kill signal. * * Only kill signals interrupt this process. */ #define wait_event_killable_timeout(wq_head, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_killable_timeout(wq_head, \ condition, timeout); \ __ret; \ }) #define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ spin_unlock_irq(&lock); \ cmd; \ schedule(); \ spin_lock_irq(&lock)) /** * wait_event_lock_irq_cmd - sleep until a condition gets true. The * condition is checked under the lock. This * is expected to be called with the lock * taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd * and schedule() and reacquired afterwards. * @cmd: a command which is invoked outside the critical section before * sleep * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. */ #define wait_event_lock_irq_cmd(wq_head, condition, lock, cmd) \ do { \ if (condition) \ break; \ __wait_event_lock_irq(wq_head, condition, lock, cmd); \ } while (0) /** * wait_event_lock_irq - sleep until a condition gets true. The * condition is checked under the lock. This * is expected to be called with the lock * taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. */ #define wait_event_lock_irq(wq_head, condition, lock) \ do { \ if (condition) \ break; \ __wait_event_lock_irq(wq_head, condition, lock, ); \ } while (0) #define __wait_event_interruptible_lock_irq(wq_head, condition, lock, cmd) \ ___wait_event(wq_head, condition, TASK_INTERRUPTIBLE, 0, 0, \ spin_unlock_irq(&lock); \ cmd; \ schedule(); \ spin_lock_irq(&lock)) /** * wait_event_interruptible_lock_irq_cmd - sleep until a condition gets true. * The condition is checked under the lock. This is expected to * be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before cmd and * schedule() and reacquired afterwards. * @cmd: a command which is invoked outside the critical section before * sleep * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or a signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before invoking the cmd and going to sleep and is reacquired * afterwards. * * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ #define wait_event_interruptible_lock_irq_cmd(wq_head, condition, lock, cmd) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = __wait_event_interruptible_lock_irq(wq_head, \ condition, lock, cmd); \ __ret; \ }) /** * wait_event_interruptible_lock_irq - sleep until a condition gets true. * The condition is checked under the lock. This is expected * to be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. * * The macro will return -ERESTARTSYS if it was interrupted by a signal * and 0 if @condition evaluated to true. */ #define wait_event_interruptible_lock_irq(wq_head, condition, lock) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = __wait_event_interruptible_lock_irq(wq_head, \ condition, lock,); \ __ret; \ }) #define __wait_event_lock_irq_timeout(wq_head, condition, lock, timeout, state) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ state, 0, timeout, \ spin_unlock_irq(&lock); \ __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); /** * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets * true or a timeout elapses. The condition is checked under * the lock. This is expected to be called with the lock taken. * @wq_head: the waitqueue to wait on * @condition: a C expression for the event to wait for * @lock: a locked spinlock_t, which will be released before schedule() * and reacquired afterwards. * @timeout: timeout, in jiffies * * The process is put to sleep (TASK_INTERRUPTIBLE) until the * @condition evaluates to true or signal is received. The @condition is * checked each time the waitqueue @wq_head is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. * * This is supposed to be called while holding the lock. The lock is * dropped before going to sleep and is reacquired afterwards. * * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it * was interrupted by a signal, and the remaining jiffies otherwise * if the condition evaluated to true before the timeout elapsed. */ #define wait_event_interruptible_lock_irq_timeout(wq_head, condition, lock, \ timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_lock_irq_timeout( \ wq_head, condition, lock, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ }) #define wait_event_lock_irq_timeout(wq_head, condition, lock, timeout) \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_event_lock_irq_timeout( \ wq_head, condition, lock, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ }) /* * Waitqueues which are removed from the waitqueue_head at wakeup time */ void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); #define DEFINE_WAIT_FUNC(name, function) \ struct wait_queue_entry name = { \ .private = current, \ .func = function, \ .entry = LIST_HEAD_INIT((name).entry), \ } #define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) #define init_wait(wait) \ do { \ (wait)->private = current; \ (wait)->func = autoremove_wake_function; \ INIT_LIST_HEAD(&(wait)->entry); \ (wait)->flags = 0; \ } while (0) typedef int (*task_call_f)(struct task_struct *p, void *arg); extern int task_call_func(struct task_struct *p, task_call_f func, void *arg); #endif /* _LINUX_WAIT_H */ |
| 1 105 105 105 20 4 4 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 | // SPDX-License-Identifier: GPL-2.0-only /* * This file contians vfs dentry ops for the 9P2000 protocol. * * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> */ #include <linux/module.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/namei.h> #include <linux/sched.h> #include <linux/slab.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include "v9fs.h" #include "v9fs_vfs.h" #include "fid.h" /** * v9fs_cached_dentry_delete - called when dentry refcount equals 0 * @dentry: dentry in question * */ static int v9fs_cached_dentry_delete(const struct dentry *dentry) { p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n", dentry, dentry); /* Don't cache negative dentries */ if (d_really_is_negative(dentry)) return 1; return 0; } /** * v9fs_dentry_release - called when dentry is going to be freed * @dentry: dentry that is being release * */ static void v9fs_dentry_release(struct dentry *dentry) { struct hlist_node *p, *n; struct hlist_head head; p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n", dentry, dentry); spin_lock(&dentry->d_lock); hlist_move_list((struct hlist_head *)&dentry->d_fsdata, &head); spin_unlock(&dentry->d_lock); hlist_for_each_safe(p, n, &head) p9_fid_put(hlist_entry(p, struct p9_fid, dlist)); } static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) { struct p9_fid *fid; struct inode *inode; struct v9fs_inode *v9inode; if (flags & LOOKUP_RCU) return -ECHILD; inode = d_inode(dentry); if (!inode) goto out_valid; v9inode = V9FS_I(inode); if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) { int retval; struct v9fs_session_info *v9ses; fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) return PTR_ERR(fid); v9ses = v9fs_inode2v9ses(inode); if (v9fs_proto_dotl(v9ses)) retval = v9fs_refresh_inode_dotl(fid, inode); else retval = v9fs_refresh_inode(fid, inode); p9_fid_put(fid); if (retval == -ENOENT) return 0; if (retval < 0) return retval; } out_valid: return 1; } const struct dentry_operations v9fs_cached_dentry_operations = { .d_revalidate = v9fs_lookup_revalidate, .d_weak_revalidate = v9fs_lookup_revalidate, .d_delete = v9fs_cached_dentry_delete, .d_release = v9fs_dentry_release, }; const struct dentry_operations v9fs_dentry_operations = { .d_delete = always_delete_dentry, .d_release = v9fs_dentry_release, }; |
| 502 328 96 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Authors: Lotsa people, from code originally in tcp */ #ifndef _INET6_HASHTABLES_H #define _INET6_HASHTABLES_H #if IS_ENABLED(CONFIG_IPV6) #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/types.h> #include <linux/jhash.h> #include <net/inet_sock.h> #include <net/ipv6.h> #include <net/netns/hash.h> struct inet_hashinfo; static inline unsigned int __inet6_ehashfn(const u32 lhash, const u16 lport, const u32 fhash, const __be16 fport, const u32 initval) { const u32 ports = (((u32)lport) << 16) | (__force u32)fport; return jhash_3words(lhash, fhash, ports, initval); } /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM * * The sockhash lock must be held as a reader here. */ struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif); typedef u32 (inet6_ehashfn_t)(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport); inet6_ehashfn_t inet6_ehashfn; INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, inet6_ehashfn_t *ehashfn); struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif); struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn); static inline struct sock *__inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif, bool *refcounted) { struct sock *sk = __inet6_lookup_established(net, hashinfo, saddr, sport, daddr, hnum, dif, sdif); *refcounted = true; if (sk) return sk; *refcounted = false; return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport, daddr, hnum, dif, sdif); } static inline struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, bool *refcounted, inet6_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool prefetched; sk = skb_steal_sock(skb, refcounted, &prefetched); if (!sk) return NULL; if (!prefetched || !sk_fullsock(sk)) return sk; if (sk->sk_protocol == IPPROTO_TCP) { if (sk->sk_state != TCP_LISTEN) return sk; } else if (sk->sk_protocol == IPPROTO_UDP) { if (sk->sk_state != TCP_CLOSE) return sk; } else { return sk; } reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, ntohs(dport), ehashfn); if (!reuse_sk) return sk; /* We've chosen a new reuseport sock which is never refcounted. This * implies that sk also isn't refcounted. */ WARN_ON_ONCE(*refcounted); return reuse_sk; } static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be16 sport, const __be16 dport, int iif, int sdif, bool *refcounted) { struct net *net = dev_net(skb_dst(skb)->dev); const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct sock *sk; sk = inet6_steal_sock(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, dport, refcounted, inet6_ehashfn); if (IS_ERR(sk)) return NULL; if (sk) return sk; return __inet6_lookup(net, hashinfo, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, ntohs(dport), iif, sdif, refcounted); } struct sock *inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif); int inet6_hash(struct sock *sk); static inline bool inet6_match(const struct net *net, const struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, const __portpair ports, const int dif, const int sdif) { if (!net_eq(sock_net(sk), net) || sk->sk_family != AF_INET6 || sk->sk_portpair != ports || !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return false; /* READ_ONCE() paired with WRITE_ONCE() in sock_bindtoindex_locked() */ return inet_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif, sdif); } #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _INET6_HASHTABLES_H */ |
| 388 56 57 57 330 331 422 2 409 38 83 3 195 1778 20 1769 640 640 639 641 1 638 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 library code, needed by static components when full IPv6 support is * not configured or static. These functions are needed by GSO/GRO implementation. */ #include <linux/export.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/addrconf.h> #include <net/secure_seq.h> #include <linux/netfilter.h> static u32 __ipv6_select_ident(struct net *net, const struct in6_addr *dst, const struct in6_addr *src) { return get_random_u32_above(0); } /* This function exists only for tap drivers that must support broken * clients requesting UFO without specifying an IPv6 fragment ID. * * This is similar to ipv6_select_ident() but we use an independent hash * seed to limit information leakage. * * The network header must be set before calling this. */ __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb) { struct in6_addr buf[2]; struct in6_addr *addrs; u32 id; addrs = skb_header_pointer(skb, skb_network_offset(skb) + offsetof(struct ipv6hdr, saddr), sizeof(buf), buf); if (!addrs) return 0; id = __ipv6_select_ident(net, &addrs[1], &addrs[0]); return htonl(id); } EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident); __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr) { u32 id; id = __ipv6_select_ident(net, daddr, saddr); return htonl(id); } EXPORT_SYMBOL(ipv6_select_ident); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) { unsigned int offset = sizeof(struct ipv6hdr); unsigned int packet_len = skb_tail_pointer(skb) - skb_network_header(skb); int found_rhdr = 0; *nexthdr = &ipv6_hdr(skb)->nexthdr; while (offset <= packet_len) { struct ipv6_opt_hdr *exthdr; switch (**nexthdr) { case NEXTHDR_HOP: break; case NEXTHDR_ROUTING: found_rhdr = 1; break; case NEXTHDR_DEST: #if IS_ENABLED(CONFIG_IPV6_MIP6) if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) break; #endif if (found_rhdr) return offset; break; default: return offset; } if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) return -EINVAL; exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); offset += ipv6_optlen(exthdr); if (offset > IPV6_MAXPLEN) return -EINVAL; *nexthdr = &exthdr->nexthdr; } return -EINVAL; } EXPORT_SYMBOL(ip6_find_1stfragopt); #if IS_ENABLED(CONFIG_IPV6) int ip6_dst_hoplimit(struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); if (hoplimit == 0) { struct net_device *dev = dst->dev; struct inet6_dev *idev; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) hoplimit = READ_ONCE(idev->cnf.hop_limit); else hoplimit = READ_ONCE(dev_net(dev)->ipv6.devconf_all->hop_limit); rcu_read_unlock(); } return hoplimit; } EXPORT_SYMBOL(ip6_dst_hoplimit); #endif int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int len; len = skb->len - sizeof(struct ipv6hdr); if (len > IPV6_MAXPLEN) len = 0; ipv6_hdr(skb)->payload_len = htons(len); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; skb->protocol = htons(ETH_P_IPV6); return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); } EXPORT_SYMBOL_GPL(__ip6_local_out); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = __ip6_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } EXPORT_SYMBOL_GPL(ip6_local_out); |
| 7200 36 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/linux/eventpoll.h ( Efficient event polling implementation ) * Copyright (C) 2001,...,2006 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> #include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ struct file; #ifdef CONFIG_EPOLL #ifdef CONFIG_KCMP struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); /* * This is called from inside fs/file_table.c:__fput() to unlink files * from the eventpoll interface. We need to have this facility to cleanup * correctly files that are closed without being removed from the eventpoll * interface. */ static inline void eventpoll_release(struct file *file) { /* * Fast check to avoid the get/release of the semaphore. Since * we're doing this outside the semaphore lock, it might return * false negatives, but we don't care. It'll help in 99.99% of cases * to avoid the semaphore lock. False positives simply cannot happen * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ if (likely(!file->f_ep)) return; /* * The file is being closed while it is still linked to an epoll * descriptor. We need to handle this by correctly unlinking it * from its containers. */ eventpoll_release_file(file); } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock); /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { return op != EPOLL_CTL_DEL; } #else static inline void eventpoll_release(struct file *file) {} #endif #if defined(CONFIG_ARM) && defined(CONFIG_OABI_COMPAT) /* ARM OABI has an incompatible struct layout and needs a special handler */ extern struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent); #else static inline struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent) { if (__put_user(revents, &uevent->events) || __put_user(data, &uevent->data)) return NULL; return uevent+1; } #endif #endif /* #ifndef _LINUX_EVENTPOLL_H */ |
| 15772 15808 219 219 6357 6365 30899 30961 12 12 238 239 27106 27132 16584 1526 16512 691 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 | // SPDX-License-Identifier: GPL-2.0-or-later /* bit search implementation * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Copyright (C) 2008 IBM Corporation * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au> * (Inspired by David Howell's find_next_bit implementation) * * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease * size and improve performance, 2015. */ #include <linux/bitops.h> #include <linux/bitmap.h> #include <linux/export.h> #include <linux/math.h> #include <linux/minmax.h> #include <linux/swab.h> /* * Common helper for find_bit() function family * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) * @MUNGE: The expression that post-processes a word containing found bit (may be empty) * @size: The bitmap size in bits */ #define FIND_FIRST_BIT(FETCH, MUNGE, size) \ ({ \ unsigned long idx, val, sz = (size); \ \ for (idx = 0; idx * BITS_PER_LONG < sz; idx++) { \ val = (FETCH); \ if (val) { \ sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(val)), sz); \ break; \ } \ } \ \ sz; \ }) /* * Common helper for find_next_bit() function family * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) * @MUNGE: The expression that post-processes a word containing found bit (may be empty) * @size: The bitmap size in bits * @start: The bitnumber to start searching at */ #define FIND_NEXT_BIT(FETCH, MUNGE, size, start) \ ({ \ unsigned long mask, idx, tmp, sz = (size), __start = (start); \ \ if (unlikely(__start >= sz)) \ goto out; \ \ mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start)); \ idx = __start / BITS_PER_LONG; \ \ for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) { \ if ((idx + 1) * BITS_PER_LONG >= sz) \ goto out; \ idx++; \ } \ \ sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz); \ out: \ sz; \ }) #define FIND_NTH_BIT(FETCH, size, num) \ ({ \ unsigned long sz = (size), nr = (num), idx, w, tmp; \ \ for (idx = 0; (idx + 1) * BITS_PER_LONG <= sz; idx++) { \ if (idx * BITS_PER_LONG + nr >= sz) \ goto out; \ \ tmp = (FETCH); \ w = hweight_long(tmp); \ if (w > nr) \ goto found; \ \ nr -= w; \ } \ \ if (sz % BITS_PER_LONG) \ tmp = (FETCH) & BITMAP_LAST_WORD_MASK(sz); \ found: \ sz = idx * BITS_PER_LONG + fns(tmp, nr); \ out: \ sz; \ }) #ifndef find_first_bit /* * Find the first set bit in a memory region. */ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) { return FIND_FIRST_BIT(addr[idx], /* nop */, size); } EXPORT_SYMBOL(_find_first_bit); #endif #ifndef find_first_and_bit /* * Find the first set bit in two memory regions. */ unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { return FIND_FIRST_BIT(addr1[idx] & addr2[idx], /* nop */, size); } EXPORT_SYMBOL(_find_first_and_bit); #endif /* * Find the first set bit in three memory regions. */ unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size) { return FIND_FIRST_BIT(addr1[idx] & addr2[idx] & addr3[idx], /* nop */, size); } EXPORT_SYMBOL(_find_first_and_and_bit); #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. */ unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size) { return FIND_FIRST_BIT(~addr[idx], /* nop */, size); } EXPORT_SYMBOL(_find_first_zero_bit); #endif #ifndef find_next_bit unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) { return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start); } EXPORT_SYMBOL(_find_next_bit); #endif unsigned long __find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) { return FIND_NTH_BIT(addr[idx], size, n); } EXPORT_SYMBOL(__find_nth_bit); unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { return FIND_NTH_BIT(addr1[idx] & addr2[idx], size, n); } EXPORT_SYMBOL(__find_nth_and_bit); unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { return FIND_NTH_BIT(addr1[idx] & ~addr2[idx], size, n); } EXPORT_SYMBOL(__find_nth_andnot_bit); unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, unsigned long size, unsigned long n) { return FIND_NTH_BIT(addr1[idx] & addr2[idx] & ~addr3[idx], size, n); } EXPORT_SYMBOL(__find_nth_and_andnot_bit); #ifndef find_next_and_bit unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start) { return FIND_NEXT_BIT(addr1[idx] & addr2[idx], /* nop */, nbits, start); } EXPORT_SYMBOL(_find_next_and_bit); #endif #ifndef find_next_andnot_bit unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start) { return FIND_NEXT_BIT(addr1[idx] & ~addr2[idx], /* nop */, nbits, start); } EXPORT_SYMBOL(_find_next_andnot_bit); #endif #ifndef find_next_or_bit unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start) { return FIND_NEXT_BIT(addr1[idx] | addr2[idx], /* nop */, nbits, start); } EXPORT_SYMBOL(_find_next_or_bit); #endif #ifndef find_next_zero_bit unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) { return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start); } EXPORT_SYMBOL(_find_next_zero_bit); #endif #ifndef find_last_bit unsigned long _find_last_bit(const unsigned long *addr, unsigned long size) { if (size) { unsigned long val = BITMAP_LAST_WORD_MASK(size); unsigned long idx = (size-1) / BITS_PER_LONG; do { val &= addr[idx]; if (val) return idx * BITS_PER_LONG + __fls(val); val = ~0ul; } while (idx--); } return size; } EXPORT_SYMBOL(_find_last_bit); #endif unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset) { offset = find_next_bit(addr, size, offset); if (offset == size) return size; offset = round_down(offset, 8); *clump = bitmap_get_value8(addr, offset); return offset; } EXPORT_SYMBOL(find_next_clump8); #ifdef __BIG_ENDIAN #ifndef find_first_zero_bit_le /* * Find the first cleared bit in an LE memory region. */ unsigned long _find_first_zero_bit_le(const unsigned long *addr, unsigned long size) { return FIND_FIRST_BIT(~addr[idx], swab, size); } EXPORT_SYMBOL(_find_first_zero_bit_le); #endif #ifndef find_next_zero_bit_le unsigned long _find_next_zero_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset) { return FIND_NEXT_BIT(~addr[idx], swab, size, offset); } EXPORT_SYMBOL(_find_next_zero_bit_le); #endif #ifndef find_next_bit_le unsigned long _find_next_bit_le(const unsigned long *addr, unsigned long size, unsigned long offset) { return FIND_NEXT_BIT(addr[idx], swab, size, offset); } EXPORT_SYMBOL(_find_next_bit_le); #endif #endif /* __BIG_ENDIAN */ |
| 8 7 7 2 2 2 2 8 4 4 8 10 10 4 2 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2008-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the list:set type */ #include <linux/module.h> #include <linux/ip.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_list.h> #define IPSET_TYPE_REV_MIN 0 /* 1 Counters support added */ /* 2 Comments support added */ #define IPSET_TYPE_REV_MAX 3 /* skbinfo support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("list:set", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_list:set"); /* Member elements */ struct set_elem { struct rcu_head rcu; struct list_head list; struct ip_set *set; /* Sigh, in order to cleanup reference */ ip_set_id_t id; } __aligned(__alignof__(u64)); struct set_adt_elem { ip_set_id_t id; ip_set_id_t refid; int before; }; /* Type structure */ struct list_set { u32 size; /* size of set list array */ struct timer_list gc; /* garbage collection */ struct ip_set *set; /* attached to this ip_set */ struct net *net; /* namespace */ struct list_head members; /* the set members */ }; static int list_set_ktest(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt, const struct ip_set_ext *ext) { struct list_set *map = set->data; struct ip_set_ext *mext = &opt->ext; struct set_elem *e; u32 flags = opt->cmdflags; int ret; /* Don't lookup sub-counters at all */ opt->cmdflags &= ~IPSET_FLAG_MATCH_COUNTERS; if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE) opt->cmdflags |= IPSET_FLAG_SKIP_COUNTER_UPDATE; list_for_each_entry_rcu(e, &map->members, list) { ret = ip_set_test(e->id, skb, par, opt); if (ret <= 0) continue; if (ip_set_match_extensions(set, ext, mext, flags, e)) return 1; } return 0; } static int list_set_kadd(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt, const struct ip_set_ext *ext) { struct list_set *map = set->data; struct set_elem *e; int ret; list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; ret = ip_set_add(e->id, skb, par, opt); if (ret == 0) return ret; } return 0; } static int list_set_kdel(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt, const struct ip_set_ext *ext) { struct list_set *map = set->data; struct set_elem *e; int ret; list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; ret = ip_set_del(e->id, skb, par, opt); if (ret == 0) return ret; } return 0; } static int list_set_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); int ret = -EINVAL; rcu_read_lock(); switch (adt) { case IPSET_TEST: ret = list_set_ktest(set, skb, par, opt, &ext); break; case IPSET_ADD: ret = list_set_kadd(set, skb, par, opt, &ext); break; case IPSET_DEL: ret = list_set_kdel(set, skb, par, opt, &ext); break; default: break; } rcu_read_unlock(); return ret; } /* Userspace interfaces: we are protected by the nfnl mutex */ static void __list_set_del_rcu(struct rcu_head * rcu) { struct set_elem *e = container_of(rcu, struct set_elem, rcu); struct ip_set *set = e->set; ip_set_ext_destroy(set, e); kfree(e); } static void list_set_del(struct ip_set *set, struct set_elem *e) { struct list_set *map = set->data; set->elements--; list_del_rcu(&e->list); ip_set_put_byindex(map->net, e->id); call_rcu(&e->rcu, __list_set_del_rcu); } static void list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old) { struct list_set *map = set->data; list_replace_rcu(&old->list, &e->list); ip_set_put_byindex(map->net, old->id); call_rcu(&old->rcu, __list_set_del_rcu); } static void set_cleanup_entries(struct ip_set *set) { struct list_set *map = set->data; struct set_elem *e, *n; list_for_each_entry_safe(e, n, &map->members, list) if (ip_set_timeout_expired(ext_timeout(e, set))) list_set_del(set, e); } static int list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct list_set *map = set->data; struct set_adt_elem *d = value; struct set_elem *e, *next, *prev = NULL; int ret = 0; rcu_read_lock(); list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; else if (e->id != d->id) { prev = e; continue; } if (d->before == 0) { ret = 1; goto out; } else if (d->before > 0) { next = list_next_entry(e, list); ret = !list_is_last(&e->list, &map->members) && next->id == d->refid; } else { ret = prev && prev->id == d->refid; } goto out; } out: rcu_read_unlock(); return ret; } static void list_set_init_extensions(struct ip_set *set, const struct ip_set_ext *ext, struct set_elem *e) { if (SET_WITH_COUNTER(set)) ip_set_init_counter(ext_counter(e, set), ext); if (SET_WITH_COMMENT(set)) ip_set_init_comment(set, ext_comment(e, set), ext); if (SET_WITH_SKBINFO(set)) ip_set_init_skbinfo(ext_skbinfo(e, set), ext); /* Update timeout last */ if (SET_WITH_TIMEOUT(set)) ip_set_timeout_set(ext_timeout(e, set), ext->timeout); } static int list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct list_set *map = set->data; struct set_adt_elem *d = value; struct set_elem *e, *n, *prev, *next; bool flag_exist = flags & IPSET_FLAG_EXIST; /* Find where to add the new entry */ n = prev = next = NULL; list_for_each_entry_rcu(e, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; else if (d->id == e->id) n = e; else if (d->before == 0 || e->id != d->refid) continue; else if (d->before > 0) next = e; else prev = e; } /* If before/after is used on an empty set */ if ((d->before > 0 && !next) || (d->before < 0 && !prev)) return -IPSET_ERR_REF_EXIST; /* Re-add already existing element */ if (n) { if (!flag_exist) return -IPSET_ERR_EXIST; /* Update extensions */ ip_set_ext_destroy(set, n); list_set_init_extensions(set, ext, n); /* Set is already added to the list */ ip_set_put_byindex(map->net, d->id); return 0; } /* Add new entry */ if (d->before == 0) { /* Append */ n = list_empty(&map->members) ? NULL : list_last_entry(&map->members, struct set_elem, list); } else if (d->before > 0) { /* Insert after next element */ if (!list_is_last(&next->list, &map->members)) n = list_next_entry(next, list); } else { /* Insert before prev element */ if (prev->list.prev != &map->members) n = list_prev_entry(prev, list); } /* Can we replace a timed out entry? */ if (n && !(SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(n, set)))) n = NULL; e = kzalloc(set->dsize, GFP_ATOMIC); if (!e) return -ENOMEM; e->id = d->id; e->set = set; INIT_LIST_HEAD(&e->list); list_set_init_extensions(set, ext, e); if (n) list_set_replace(set, e, n); else if (next) list_add_tail_rcu(&e->list, &next->list); else if (prev) list_add_rcu(&e->list, &prev->list); else list_add_tail_rcu(&e->list, &map->members); set->elements++; return 0; } static int list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct list_set *map = set->data; struct set_adt_elem *d = value; struct set_elem *e, *n, *next, *prev = NULL; list_for_each_entry_safe(e, n, &map->members, list) { if (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set))) continue; else if (e->id != d->id) { prev = e; continue; } if (d->before > 0) { next = list_next_entry(e, list); if (list_is_last(&e->list, &map->members) || next->id != d->refid) return -IPSET_ERR_REF_EXIST; } else if (d->before < 0) { if (!prev || prev->id != d->refid) return -IPSET_ERR_REF_EXIST; } list_set_del(set, e); return 0; } return d->before != 0 ? -IPSET_ERR_REF_EXIST : -IPSET_ERR_EXIST; } static int list_set_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct list_set *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct set_adt_elem e = { .refid = IPSET_INVALID_ID }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); struct ip_set *s; int ret = 0; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_NAME] || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; e.id = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAME]), &s); if (e.id == IPSET_INVALID_ID) return -IPSET_ERR_NAME; /* "Loop detection" */ if (s->type->features & IPSET_TYPE_NAME) { ret = -IPSET_ERR_LOOP; goto finish; } if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 f = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); e.before = f & IPSET_FLAG_BEFORE; } if (e.before && !tb[IPSET_ATTR_NAMEREF]) { ret = -IPSET_ERR_BEFORE; goto finish; } if (tb[IPSET_ATTR_NAMEREF]) { e.refid = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAMEREF]), &s); if (e.refid == IPSET_INVALID_ID) { ret = -IPSET_ERR_NAMEREF; goto finish; } if (!e.before) e.before = -1; } if (adt != IPSET_TEST && SET_WITH_TIMEOUT(set)) set_cleanup_entries(set); ret = adtfn(set, &e, &ext, &ext, flags); finish: if (e.refid != IPSET_INVALID_ID) ip_set_put_byindex(map->net, e.refid); if (adt != IPSET_ADD || ret) ip_set_put_byindex(map->net, e.id); return ip_set_eexist(ret, flags) ? 0 : ret; } static void list_set_flush(struct ip_set *set) { struct list_set *map = set->data; struct set_elem *e, *n; list_for_each_entry_safe(e, n, &map->members, list) list_set_del(set, e); set->elements = 0; set->ext_size = 0; } static void list_set_destroy(struct ip_set *set) { struct list_set *map = set->data; WARN_ON_ONCE(!list_empty(&map->members)); kfree(map); set->data = NULL; } /* Calculate the actual memory size of the set data */ static size_t list_set_memsize(const struct list_set *map, size_t dsize) { struct set_elem *e; u32 n = 0; rcu_read_lock(); list_for_each_entry_rcu(e, &map->members, list) n++; rcu_read_unlock(); return (sizeof(*map) + n * dsize); } static int list_set_head(struct ip_set *set, struct sk_buff *skb) { const struct list_set *map = set->data; struct nlattr *nested; size_t memsize = list_set_memsize(map, set->dsize) + set->ext_size; nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) || nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; nla_nest_end(skb, nested); return 0; nla_put_failure: return -EMSGSIZE; } static int list_set_list(const struct ip_set *set, struct sk_buff *skb, struct netlink_callback *cb) { const struct list_set *map = set->data; struct nlattr *atd, *nested; u32 i = 0, first = cb->args[IPSET_CB_ARG0]; char name[IPSET_MAXNAMELEN]; struct set_elem *e; int ret = 0; atd = nla_nest_start(skb, IPSET_ATTR_ADT); if (!atd) return -EMSGSIZE; rcu_read_lock(); list_for_each_entry_rcu(e, &map->members, list) { if (i < first || (SET_WITH_TIMEOUT(set) && ip_set_timeout_expired(ext_timeout(e, set)))) { i++; continue; } nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; ip_set_name_byindex(map->net, e->id, name); if (nla_put_string(skb, IPSET_ATTR_NAME, name)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; nla_nest_end(skb, nested); i++; } nla_nest_end(skb, atd); /* Set listing finished */ cb->args[IPSET_CB_ARG0] = 0; goto out; nla_put_failure: nla_nest_cancel(skb, nested); if (unlikely(i == first)) { nla_nest_cancel(skb, atd); cb->args[IPSET_CB_ARG0] = 0; ret = -EMSGSIZE; } else { cb->args[IPSET_CB_ARG0] = i; nla_nest_end(skb, atd); } out: rcu_read_unlock(); return ret; } static bool list_set_same_set(const struct ip_set *a, const struct ip_set *b) { const struct list_set *x = a->data; const struct list_set *y = b->data; return x->size == y->size && a->timeout == b->timeout && a->extensions == b->extensions; } static void list_set_cancel_gc(struct ip_set *set) { struct list_set *map = set->data; if (SET_WITH_TIMEOUT(set)) timer_shutdown_sync(&map->gc); /* Flush list to drop references to other ipsets */ list_set_flush(set); } static const struct ip_set_type_variant set_variant = { .kadt = list_set_kadt, .uadt = list_set_uadt, .adt = { [IPSET_ADD] = list_set_uadd, [IPSET_DEL] = list_set_udel, [IPSET_TEST] = list_set_utest, }, .destroy = list_set_destroy, .flush = list_set_flush, .head = list_set_head, .list = list_set_list, .same_set = list_set_same_set, .cancel_gc = list_set_cancel_gc, }; static void list_set_gc(struct timer_list *t) { struct list_set *map = from_timer(map, t, gc); struct ip_set *set = map->set; spin_lock_bh(&set->lock); set_cleanup_entries(set); spin_unlock_bh(&set->lock); map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; add_timer(&map->gc); } static void list_set_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) { struct list_set *map = set->data; timer_setup(&map->gc, gc, 0); mod_timer(&map->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); } /* Create list:set type of sets */ static bool init_list_set(struct net *net, struct ip_set *set, u32 size) { struct list_set *map; map = kzalloc(sizeof(*map), GFP_KERNEL); if (!map) return false; map->size = size; map->net = net; map->set = set; INIT_LIST_HEAD(&map->members); set->data = map; return true; } static int list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) { u32 size = IP_SET_LIST_DEFAULT_SIZE; if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_SIZE) || !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (tb[IPSET_ATTR_SIZE]) size = ip_set_get_h32(tb[IPSET_ATTR_SIZE]); if (size < IP_SET_LIST_MIN_SIZE) size = IP_SET_LIST_MIN_SIZE; set->variant = &set_variant; set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem), __alignof__(struct set_elem)); if (!init_list_set(net, set, size)) return -ENOMEM; if (tb[IPSET_ATTR_TIMEOUT]) { set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); list_set_gc_init(set, list_set_gc); } return 0; } static struct ip_set_type list_set_type __read_mostly = { .name = "list:set", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_NAME | IPSET_DUMP_LAST, .dimension = IPSET_DIM_ONE, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create = list_set_create, .create_policy = { [IPSET_ATTR_SIZE] = { .type = NLA_U32 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_NAME] = { .type = NLA_STRING, .len = IPSET_MAXNAMELEN }, [IPSET_ATTR_NAMEREF] = { .type = NLA_STRING, .len = IPSET_MAXNAMELEN }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init list_set_init(void) { return ip_set_type_register(&list_set_type); } static void __exit list_set_fini(void) { rcu_barrier(); ip_set_type_unregister(&list_set_type); } module_init(list_set_init); module_exit(list_set_fini); |
| 425 363 456 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM page_pool #if !defined(_TRACE_PAGE_POOL_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGE_POOL_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> #include <net/page_pool/types.h> TRACE_EVENT(page_pool_release, TP_PROTO(const struct page_pool *pool, s32 inflight, u32 hold, u32 release), TP_ARGS(pool, inflight, hold, release), TP_STRUCT__entry( __field(const struct page_pool *, pool) __field(s32, inflight) __field(u32, hold) __field(u32, release) __field(u64, cnt) ), TP_fast_assign( __entry->pool = pool; __entry->inflight = inflight; __entry->hold = hold; __entry->release = release; __entry->cnt = pool->destroy_cnt; ), TP_printk("page_pool=%p inflight=%d hold=%u release=%u cnt=%llu", __entry->pool, __entry->inflight, __entry->hold, __entry->release, __entry->cnt) ); TRACE_EVENT(page_pool_state_release, TP_PROTO(const struct page_pool *pool, netmem_ref netmem, u32 release), TP_ARGS(pool, netmem, release), TP_STRUCT__entry( __field(const struct page_pool *, pool) __field(unsigned long, netmem) __field(u32, release) __field(unsigned long, pfn) ), TP_fast_assign( __entry->pool = pool; __entry->netmem = (__force unsigned long)netmem; __entry->release = release; __entry->pfn = netmem_pfn_trace(netmem); ), TP_printk("page_pool=%p netmem=%p is_net_iov=%lu pfn=0x%lx release=%u", __entry->pool, (void *)__entry->netmem, __entry->netmem & NET_IOV, __entry->pfn, __entry->release) ); TRACE_EVENT(page_pool_state_hold, TP_PROTO(const struct page_pool *pool, netmem_ref netmem, u32 hold), TP_ARGS(pool, netmem, hold), TP_STRUCT__entry( __field(const struct page_pool *, pool) __field(unsigned long, netmem) __field(u32, hold) __field(unsigned long, pfn) ), TP_fast_assign( __entry->pool = pool; __entry->netmem = (__force unsigned long)netmem; __entry->hold = hold; __entry->pfn = netmem_pfn_trace(netmem); ), TP_printk("page_pool=%p netmem=%p is_net_iov=%lu, pfn=0x%lx hold=%u", __entry->pool, (void *)__entry->netmem, __entry->netmem & NET_IOV, __entry->pfn, __entry->hold) ); TRACE_EVENT(page_pool_update_nid, TP_PROTO(const struct page_pool *pool, int new_nid), TP_ARGS(pool, new_nid), TP_STRUCT__entry( __field(const struct page_pool *, pool) __field(int, pool_nid) __field(int, new_nid) ), TP_fast_assign( __entry->pool = pool; __entry->pool_nid = pool->p.nid; __entry->new_nid = new_nid; ), TP_printk("page_pool=%p pool_nid=%d new_nid=%d", __entry->pool, __entry->pool_nid, __entry->new_nid) ); #endif /* _TRACE_PAGE_POOL_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 52 52 52 5599 5595 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 | // SPDX-License-Identifier: GPL-2.0 /* * Block rq-qos policy for assigning an I/O priority class to requests. * * Using an rq-qos policy for assigning I/O priority class has two advantages * over using the ioprio_set() system call: * * - This policy is cgroup based so it has all the advantages of cgroups. * - While ioprio_set() does not affect page cache writeback I/O, this rq-qos * controller affects page cache writeback I/O for filesystems that support * assiociating a cgroup with writeback I/O. See also * Documentation/admin-guide/cgroup-v2.rst. */ #include <linux/blk-mq.h> #include <linux/blk_types.h> #include <linux/kernel.h> #include <linux/module.h> #include "blk-cgroup.h" #include "blk-ioprio.h" #include "blk-rq-qos.h" /** * enum prio_policy - I/O priority class policy. * @POLICY_NO_CHANGE: (default) do not modify the I/O priority class. * @POLICY_PROMOTE_TO_RT: modify no-IOPRIO_CLASS_RT to IOPRIO_CLASS_RT. * @POLICY_RESTRICT_TO_BE: modify IOPRIO_CLASS_NONE and IOPRIO_CLASS_RT into * IOPRIO_CLASS_BE. * @POLICY_ALL_TO_IDLE: change the I/O priority class into IOPRIO_CLASS_IDLE. * @POLICY_NONE_TO_RT: an alias for POLICY_PROMOTE_TO_RT. * * See also <linux/ioprio.h>. */ enum prio_policy { POLICY_NO_CHANGE = 0, POLICY_PROMOTE_TO_RT = 1, POLICY_RESTRICT_TO_BE = 2, POLICY_ALL_TO_IDLE = 3, POLICY_NONE_TO_RT = 4, }; static const char *policy_name[] = { [POLICY_NO_CHANGE] = "no-change", [POLICY_PROMOTE_TO_RT] = "promote-to-rt", [POLICY_RESTRICT_TO_BE] = "restrict-to-be", [POLICY_ALL_TO_IDLE] = "idle", [POLICY_NONE_TO_RT] = "none-to-rt", }; static struct blkcg_policy ioprio_policy; /** * struct ioprio_blkcg - Per cgroup data. * @cpd: blkcg_policy_data structure. * @prio_policy: One of the IOPRIO_CLASS_* values. See also <linux/ioprio.h>. */ struct ioprio_blkcg { struct blkcg_policy_data cpd; enum prio_policy prio_policy; }; static struct ioprio_blkcg *blkcg_to_ioprio_blkcg(struct blkcg *blkcg) { return container_of(blkcg_to_cpd(blkcg, &ioprio_policy), struct ioprio_blkcg, cpd); } static struct ioprio_blkcg * ioprio_blkcg_from_css(struct cgroup_subsys_state *css) { return blkcg_to_ioprio_blkcg(css_to_blkcg(css)); } static int ioprio_show_prio_policy(struct seq_file *sf, void *v) { struct ioprio_blkcg *blkcg = ioprio_blkcg_from_css(seq_css(sf)); seq_printf(sf, "%s\n", policy_name[blkcg->prio_policy]); return 0; } static ssize_t ioprio_set_prio_policy(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct ioprio_blkcg *blkcg = ioprio_blkcg_from_css(of_css(of)); int ret; if (off != 0) return -EIO; /* kernfs_fop_write_iter() terminates 'buf' with '\0'. */ ret = sysfs_match_string(policy_name, buf); if (ret < 0) return ret; blkcg->prio_policy = ret; return nbytes; } static struct blkcg_policy_data *ioprio_alloc_cpd(gfp_t gfp) { struct ioprio_blkcg *blkcg; blkcg = kzalloc(sizeof(*blkcg), gfp); if (!blkcg) return NULL; blkcg->prio_policy = POLICY_NO_CHANGE; return &blkcg->cpd; } static void ioprio_free_cpd(struct blkcg_policy_data *cpd) { struct ioprio_blkcg *blkcg = container_of(cpd, typeof(*blkcg), cpd); kfree(blkcg); } #define IOPRIO_ATTRS \ { \ .name = "prio.class", \ .seq_show = ioprio_show_prio_policy, \ .write = ioprio_set_prio_policy, \ }, \ { } /* sentinel */ /* cgroup v2 attributes */ static struct cftype ioprio_files[] = { IOPRIO_ATTRS }; /* cgroup v1 attributes */ static struct cftype ioprio_legacy_files[] = { IOPRIO_ATTRS }; static struct blkcg_policy ioprio_policy = { .dfl_cftypes = ioprio_files, .legacy_cftypes = ioprio_legacy_files, .cpd_alloc_fn = ioprio_alloc_cpd, .cpd_free_fn = ioprio_free_cpd, }; void blkcg_set_ioprio(struct bio *bio) { struct ioprio_blkcg *blkcg = blkcg_to_ioprio_blkcg(bio->bi_blkg->blkcg); u16 prio; if (!blkcg || blkcg->prio_policy == POLICY_NO_CHANGE) return; if (blkcg->prio_policy == POLICY_PROMOTE_TO_RT || blkcg->prio_policy == POLICY_NONE_TO_RT) { /* * For RT threads, the default priority level is 4 because * task_nice is 0. By promoting non-RT io-priority to RT-class * and default level 4, those requests that are already * RT-class but need a higher io-priority can use ioprio_set() * to achieve this. */ if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) != IOPRIO_CLASS_RT) bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 4); return; } /* * Except for IOPRIO_CLASS_NONE, higher I/O priority numbers * correspond to a lower priority. Hence, the max_t() below selects * the lower priority of bi_ioprio and the cgroup I/O priority class. * If the bio I/O priority equals IOPRIO_CLASS_NONE, the cgroup I/O * priority is assigned to the bio. */ prio = max_t(u16, bio->bi_ioprio, IOPRIO_PRIO_VALUE(blkcg->prio_policy, 0)); if (prio > bio->bi_ioprio) bio->bi_ioprio = prio; } static int __init ioprio_init(void) { return blkcg_policy_register(&ioprio_policy); } static void __exit ioprio_exit(void) { blkcg_policy_unregister(&ioprio_policy); } module_init(ioprio_init); module_exit(ioprio_exit); |
| 4180 4181 1355 414 414 414 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 | // SPDX-License-Identifier: GPL-2.0-or-later /* * vrf.c: device driver to encapsulate a VRF space * * Copyright (c) 2015 Cumulus Networks. All rights reserved. * Copyright (c) 2015 Shrijeet Mukherjee <shm@cumulusnetworks.com> * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> * * Based on dummy, team and ipvlan drivers */ #include <linux/ethtool.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ip.h> #include <linux/init.h> #include <linux/moduleparam.h> #include <linux/netfilter.h> #include <linux/rtnetlink.h> #include <net/rtnetlink.h> #include <linux/u64_stats_sync.h> #include <linux/hashtable.h> #include <linux/spinlock_types.h> #include <linux/inetdevice.h> #include <net/arp.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/route.h> #include <net/addrconf.h> #include <net/l3mdev.h> #include <net/fib_rules.h> #include <net/sch_generic.h> #include <net/netns/generic.h> #include <net/netfilter/nf_conntrack.h> #include <net/inet_dscp.h> #define DRV_NAME "vrf" #define DRV_VERSION "1.1" #define FIB_RULE_PREF 1000 /* default preference for FIB rules */ #define HT_MAP_BITS 4 #define HASH_INITVAL ((u32)0xcafef00d) struct vrf_map { DECLARE_HASHTABLE(ht, HT_MAP_BITS); spinlock_t vmap_lock; /* shared_tables: * count how many distinct tables do not comply with the strict mode * requirement. * shared_tables value must be 0 in order to enable the strict mode. * * example of the evolution of shared_tables: * | time * add vrf0 --> table 100 shared_tables = 0 | t0 * add vrf1 --> table 101 shared_tables = 0 | t1 * add vrf2 --> table 100 shared_tables = 1 | t2 * add vrf3 --> table 100 shared_tables = 1 | t3 * add vrf4 --> table 101 shared_tables = 2 v t4 * * shared_tables is a "step function" (or "staircase function") * and it is increased by one when the second vrf is associated to a * table. * * at t2, vrf0 and vrf2 are bound to table 100: shared_tables = 1. * * at t3, another dev (vrf3) is bound to the same table 100 but the * value of shared_tables is still 1. * This means that no matter how many new vrfs will register on the * table 100, the shared_tables will not increase (considering only * table 100). * * at t4, vrf4 is bound to table 101, and shared_tables = 2. * * Looking at the value of shared_tables we can immediately know if * the strict_mode can or cannot be enforced. Indeed, strict_mode * can be enforced iff shared_tables = 0. * * Conversely, shared_tables is decreased when a vrf is de-associated * from a table with exactly two associated vrfs. */ u32 shared_tables; bool strict_mode; }; struct vrf_map_elem { struct hlist_node hnode; struct list_head vrf_list; /* VRFs registered to this table */ u32 table_id; int users; int ifindex; }; static unsigned int vrf_net_id; /* per netns vrf data */ struct netns_vrf { /* protected by rtnl lock */ bool add_fib_rules; struct vrf_map vmap; struct ctl_table_header *ctl_hdr; }; struct net_vrf { struct rtable __rcu *rth; struct rt6_info __rcu *rt6; #if IS_ENABLED(CONFIG_IPV6) struct fib6_table *fib6_table; #endif u32 tb_id; struct list_head me_list; /* entry in vrf_map_elem */ int ifindex; }; static void vrf_rx_stats(struct net_device *dev, int len) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_inc(&dstats->rx_packets); u64_stats_add(&dstats->rx_bytes, len); u64_stats_update_end(&dstats->syncp); } static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb) { vrf_dev->stats.tx_errors++; kfree_skb(skb); } static struct vrf_map *netns_vrf_map(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); return &nn_vrf->vmap; } static struct vrf_map *netns_vrf_map_by_dev(struct net_device *dev) { return netns_vrf_map(dev_net(dev)); } static int vrf_map_elem_get_vrf_ifindex(struct vrf_map_elem *me) { struct list_head *me_head = &me->vrf_list; struct net_vrf *vrf; if (list_empty(me_head)) return -ENODEV; vrf = list_first_entry(me_head, struct net_vrf, me_list); return vrf->ifindex; } static struct vrf_map_elem *vrf_map_elem_alloc(gfp_t flags) { struct vrf_map_elem *me; me = kmalloc(sizeof(*me), flags); if (!me) return NULL; return me; } static void vrf_map_elem_free(struct vrf_map_elem *me) { kfree(me); } static void vrf_map_elem_init(struct vrf_map_elem *me, int table_id, int ifindex, int users) { me->table_id = table_id; me->ifindex = ifindex; me->users = users; INIT_LIST_HEAD(&me->vrf_list); } static struct vrf_map_elem *vrf_map_lookup_elem(struct vrf_map *vmap, u32 table_id) { struct vrf_map_elem *me; u32 key; key = jhash_1word(table_id, HASH_INITVAL); hash_for_each_possible(vmap->ht, me, hnode, key) { if (me->table_id == table_id) return me; } return NULL; } static void vrf_map_add_elem(struct vrf_map *vmap, struct vrf_map_elem *me) { u32 table_id = me->table_id; u32 key; key = jhash_1word(table_id, HASH_INITVAL); hash_add(vmap->ht, &me->hnode, key); } static void vrf_map_del_elem(struct vrf_map_elem *me) { hash_del(&me->hnode); } static void vrf_map_lock(struct vrf_map *vmap) __acquires(&vmap->vmap_lock) { spin_lock(&vmap->vmap_lock); } static void vrf_map_unlock(struct vrf_map *vmap) __releases(&vmap->vmap_lock) { spin_unlock(&vmap->vmap_lock); } /* called with rtnl lock held */ static int vrf_map_register_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vrf_map *vmap = netns_vrf_map_by_dev(dev); struct net_vrf *vrf = netdev_priv(dev); struct vrf_map_elem *new_me, *me; u32 table_id = vrf->tb_id; bool free_new_me = false; int users; int res; /* we pre-allocate elements used in the spin-locked section (so that we * keep the spinlock as short as possible). */ new_me = vrf_map_elem_alloc(GFP_KERNEL); if (!new_me) return -ENOMEM; vrf_map_elem_init(new_me, table_id, dev->ifindex, 0); vrf_map_lock(vmap); me = vrf_map_lookup_elem(vmap, table_id); if (!me) { me = new_me; vrf_map_add_elem(vmap, me); goto link_vrf; } /* we already have an entry in the vrf_map, so it means there is (at * least) a vrf registered on the specific table. */ free_new_me = true; if (vmap->strict_mode) { /* vrfs cannot share the same table */ NL_SET_ERR_MSG(extack, "Table is used by another VRF"); res = -EBUSY; goto unlock; } link_vrf: users = ++me->users; if (users == 2) ++vmap->shared_tables; list_add(&vrf->me_list, &me->vrf_list); res = 0; unlock: vrf_map_unlock(vmap); /* clean-up, if needed */ if (free_new_me) vrf_map_elem_free(new_me); return res; } /* called with rtnl lock held */ static void vrf_map_unregister_dev(struct net_device *dev) { struct vrf_map *vmap = netns_vrf_map_by_dev(dev); struct net_vrf *vrf = netdev_priv(dev); u32 table_id = vrf->tb_id; struct vrf_map_elem *me; int users; vrf_map_lock(vmap); me = vrf_map_lookup_elem(vmap, table_id); if (!me) goto unlock; list_del(&vrf->me_list); users = --me->users; if (users == 1) { --vmap->shared_tables; } else if (users == 0) { vrf_map_del_elem(me); /* no one will refer to this element anymore */ vrf_map_elem_free(me); } unlock: vrf_map_unlock(vmap); } /* return the vrf device index associated with the table_id */ static int vrf_ifindex_lookup_by_table_id(struct net *net, u32 table_id) { struct vrf_map *vmap = netns_vrf_map(net); struct vrf_map_elem *me; int ifindex; vrf_map_lock(vmap); if (!vmap->strict_mode) { ifindex = -EPERM; goto unlock; } me = vrf_map_lookup_elem(vmap, table_id); if (!me) { ifindex = -ENODEV; goto unlock; } ifindex = vrf_map_elem_get_vrf_ifindex(me); unlock: vrf_map_unlock(vmap); return ifindex; } /* by default VRF devices do not have a qdisc and are expected * to be created with only a single queue. */ static bool qdisc_tx_is_default(const struct net_device *dev) { struct netdev_queue *txq; struct Qdisc *qdisc; if (dev->num_tx_queues > 1) return false; txq = netdev_get_tx_queue(dev, 0); qdisc = rcu_access_pointer(txq->qdisc); return !qdisc->enqueue; } /* Local traffic destined to local address. Reinsert the packet to rx * path, similar to loopback handling. */ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, struct dst_entry *dst) { int len = skb->len; skb_orphan(skb); skb_dst_set(skb, dst); /* set pkt_type to avoid skb hitting packet taps twice - * once on Tx and again in Rx processing */ skb->pkt_type = PACKET_LOOPBACK; skb->protocol = eth_type_trans(skb, dev); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { vrf_rx_stats(dev, len); } else { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_inc(&dstats->rx_drops); u64_stats_update_end(&dstats->syncp); } return NETDEV_TX_OK; } static void vrf_nf_set_untracked(struct sk_buff *skb) { if (skb_get_nfct(skb) == 0) nf_ct_set(skb, NULL, IP_CT_UNTRACKED); } static void vrf_nf_reset_ct(struct sk_buff *skb) { if (skb_get_nfct(skb) == IP_CT_UNTRACKED) nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) static int vrf_ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; vrf_nf_reset_ct(skb); err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { const struct ipv6hdr *iph; struct net *net = dev_net(skb->dev); struct flowi6 fl6; int ret = NET_XMIT_DROP; struct dst_entry *dst; struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) goto err; iph = ipv6_hdr(skb); memset(&fl6, 0, sizeof(fl6)); /* needed to match OIF rule */ fl6.flowi6_l3mdev = dev->ifindex; fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; fl6.flowlabel = ip6_flowinfo(iph); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = iph->nexthdr; dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst) || dst == dst_null) goto err; skb_dst_drop(skb); /* if dst.dev is the VRF device again this is locally originated traffic * destined to a local address. Short circuit to Rx path. */ if (dst->dev == dev) return vrf_local_xmit(skb, dev, dst); skb_dst_set(skb, dst); /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); ret = vrf_ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(ret))) dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; return ret; err: vrf_tx_error(dev, skb); return NET_XMIT_DROP; } #else static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { vrf_tx_error(dev, skb); return NET_XMIT_DROP; } #endif /* based on ip_local_out; can't use it b/c the dst is switched pointing to us */ static int vrf_ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; vrf_nf_reset_ct(skb); err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, struct net_device *vrf_dev) { struct iphdr *ip4h; int ret = NET_XMIT_DROP; struct flowi4 fl4; struct net *net = dev_net(vrf_dev); struct rtable *rt; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) goto err; ip4h = ip_hdr(skb); memset(&fl4, 0, sizeof(fl4)); /* needed to match OIF rule */ fl4.flowi4_l3mdev = vrf_dev->ifindex; fl4.flowi4_iif = LOOPBACK_IFINDEX; fl4.flowi4_tos = ip4h->tos & INET_DSCP_MASK; fl4.flowi4_flags = FLOWI_FLAG_ANYSRC; fl4.flowi4_proto = ip4h->protocol; fl4.daddr = ip4h->daddr; fl4.saddr = ip4h->saddr; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; skb_dst_drop(skb); /* if dst.dev is the VRF device again this is locally originated traffic * destined to a local address. Short circuit to Rx path. */ if (rt->dst.dev == vrf_dev) return vrf_local_xmit(skb, vrf_dev, &rt->dst); skb_dst_set(skb, &rt->dst); /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); if (!ip4h->saddr) { ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0, RT_SCOPE_LINK); } memset(IPCB(skb), 0, sizeof(*IPCB(skb))); ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); if (unlikely(net_xmit_eval(ret))) vrf_dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; out: return ret; err: vrf_tx_error(vrf_dev, skb); goto out; } static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) { switch (skb->protocol) { case htons(ETH_P_IP): return vrf_process_v4_outbound(skb, dev); case htons(ETH_P_IPV6): return vrf_process_v6_outbound(skb, dev); default: vrf_tx_error(dev, skb); return NET_XMIT_DROP; } } static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); int len = skb->len; netdev_tx_t ret = is_ip_tx_frame(skb, dev); u64_stats_update_begin(&dstats->syncp); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { u64_stats_inc(&dstats->tx_packets); u64_stats_add(&dstats->tx_bytes, len); } else { u64_stats_inc(&dstats->tx_drops); } u64_stats_update_end(&dstats->syncp); return ret; } static void vrf_finish_direct(struct sk_buff *skb) { struct net_device *vrf_dev = skb->dev; if (!list_empty(&vrf_dev->ptype_all) && likely(skb_headroom(skb) >= ETH_HLEN)) { struct ethhdr *eth = skb_push(skb, ETH_HLEN); ether_addr_copy(eth->h_source, vrf_dev->dev_addr); eth_zero_addr(eth->h_dest); eth->h_proto = skb->protocol; dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, ETH_HLEN); } vrf_nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) /* modelled after ip6_finish_output2 */ static int vrf_finish_output6(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; const struct in6_addr *nexthop; struct neighbour *neigh; int ret; vrf_nf_reset_ct(skb); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; rcu_read_lock(); nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); if (!IS_ERR(neigh)) { sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); rcu_read_unlock(); return ret; } rcu_read_unlock(); IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } /* modelled after ip6_output */ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, vrf_finish_output6, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } /* set dst on skb to send packet to us via dev_xmit path. Allows * packet to go through device based features such as qdisc, netfilter * hooks and packet sockets with skb->dev set to vrf device. */ static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_vrf *vrf = netdev_priv(vrf_dev); struct dst_entry *dst = NULL; struct rt6_info *rt6; rcu_read_lock(); rt6 = rcu_dereference(vrf->rt6); if (likely(rt6)) { dst = &rt6->dst; dst_hold(dst); } rcu_read_unlock(); if (unlikely(!dst)) { vrf_tx_error(vrf_dev, skb); return NULL; } skb_dst_drop(skb); skb_dst_set(skb, dst); return skb; } static int vrf_output6_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { vrf_finish_direct(skb); return vrf_ip6_local_out(net, sk, skb); } static int vrf_output6_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { int err = 1; skb->protocol = htons(ETH_P_IPV6); if (!(IPCB(skb)->flags & IPSKB_REROUTED)) err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, vrf_output6_direct_finish); if (likely(err == 1)) vrf_finish_direct(skb); return err; } static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = vrf_output6_direct(net, sk, skb); if (likely(err == 1)) err = vrf_ip6_local_out(net, sk, skb); return err; } static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(vrf_dev); int err; skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip6_out_direct_finish); if (likely(err == 1)) err = vrf_output6_direct(net, sk, skb); if (likely(err == 1)) return skb; return NULL; } static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { /* don't divert link scope packets */ if (rt6_need_strict(&ipv6_hdr(skb)->daddr)) return skb; vrf_nf_set_untracked(skb); if (qdisc_tx_is_default(vrf_dev) || IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return vrf_ip6_out_direct(vrf_dev, sk, skb); return vrf_ip6_out_redirect(vrf_dev, skb); } /* holding rtnl */ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) { struct rt6_info *rt6 = rtnl_dereference(vrf->rt6); struct net *net = dev_net(dev); struct dst_entry *dst; RCU_INIT_POINTER(vrf->rt6, NULL); synchronize_rcu(); /* move dev in dst's to loopback so this VRF device can be deleted * - based on dst_ifdown */ if (rt6) { dst = &rt6->dst; netdev_ref_replace(dst->dev, net->loopback_dev, &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } } static int vrf_rt6_create(struct net_device *dev) { int flags = DST_NOPOLICY | DST_NOXFRM; struct net_vrf *vrf = netdev_priv(dev); struct net *net = dev_net(dev); struct rt6_info *rt6; int rc = -ENOMEM; /* IPv6 can be CONFIG enabled and then disabled runtime */ if (!ipv6_mod_enabled()) return 0; vrf->fib6_table = fib6_new_table(net, vrf->tb_id); if (!vrf->fib6_table) goto out; /* create a dst for routing packets out a VRF device */ rt6 = ip6_dst_alloc(net, dev, flags); if (!rt6) goto out; rt6->dst.output = vrf_output6; rcu_assign_pointer(vrf->rt6, rt6); rc = 0; out: return rc; } #else static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { return skb; } static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) { } static int vrf_rt6_create(struct net_device *dev) { return 0; } #endif /* modelled after ip_finish_output2 */ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = dst_rtable(dst); struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; vrf_nf_reset_ct(skb); /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) { dev->stats.tx_errors++; return -ENOMEM; } } rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int ret; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ ret = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock(); return ret; } rcu_read_unlock(); vrf_tx_error(skb->dev, skb); return -EINVAL; } static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, vrf_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } /* set dst on skb to send packet to us via dev_xmit path. Allows * packet to go through device based features such as qdisc, netfilter * hooks and packet sockets with skb->dev set to vrf device. */ static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_vrf *vrf = netdev_priv(vrf_dev); struct dst_entry *dst = NULL; struct rtable *rth; rcu_read_lock(); rth = rcu_dereference(vrf->rth); if (likely(rth)) { dst = &rth->dst; dst_hold(dst); } rcu_read_unlock(); if (unlikely(!dst)) { vrf_tx_error(vrf_dev, skb); return NULL; } skb_dst_drop(skb); skb_dst_set(skb, dst); return skb; } static int vrf_output_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { vrf_finish_direct(skb); return vrf_ip_local_out(net, sk, skb); } static int vrf_output_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { int err = 1; skb->protocol = htons(ETH_P_IP); if (!(IPCB(skb)->flags & IPSKB_REROUTED)) err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, vrf_output_direct_finish); if (likely(err == 1)) vrf_finish_direct(skb); return err; } static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = vrf_output_direct(net, sk, skb); if (likely(err == 1)) err = vrf_ip_local_out(net, sk, skb); return err; } static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(vrf_dev); int err; skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip_out_direct_finish); if (likely(err == 1)) err = vrf_output_direct(net, sk, skb); if (likely(err == 1)) return skb; return NULL; } static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { /* don't divert multicast or local broadcast */ if (ipv4_is_multicast(ip_hdr(skb)->daddr) || ipv4_is_lbcast(ip_hdr(skb)->daddr)) return skb; vrf_nf_set_untracked(skb); if (qdisc_tx_is_default(vrf_dev) || IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return vrf_ip_out_direct(vrf_dev, sk, skb); return vrf_ip_out_redirect(vrf_dev, skb); } /* called with rcu lock held */ static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb, u16 proto) { switch (proto) { case AF_INET: return vrf_ip_out(vrf_dev, sk, skb); case AF_INET6: return vrf_ip6_out(vrf_dev, sk, skb); } return skb; } /* holding rtnl */ static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf) { struct rtable *rth = rtnl_dereference(vrf->rth); struct net *net = dev_net(dev); struct dst_entry *dst; RCU_INIT_POINTER(vrf->rth, NULL); synchronize_rcu(); /* move dev in dst's to loopback so this VRF device can be deleted * - based on dst_ifdown */ if (rth) { dst = &rth->dst; netdev_ref_replace(dst->dev, net->loopback_dev, &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } } static int vrf_rtable_create(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); struct rtable *rth; if (!fib_new_table(dev_net(dev), vrf->tb_id)) return -ENOMEM; /* create a dst for routing packets out through a VRF device */ rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1); if (!rth) return -ENOMEM; rth->dst.output = vrf_output; rcu_assign_pointer(vrf->rth, rth); return 0; } /**************************** device handling ********************/ /* cycle interface to flush neighbor cache and move routes across tables */ static void cycle_netdev(struct net_device *dev, struct netlink_ext_ack *extack) { unsigned int flags = dev->flags; int ret; if (!netif_running(dev)) return; ret = dev_change_flags(dev, flags & ~IFF_UP, extack); if (ret >= 0) ret = dev_change_flags(dev, flags, extack); if (ret < 0) { netdev_err(dev, "Failed to cycle device %s; route tables might be wrong!\n", dev->name); } } static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { int ret; /* do not allow loopback device to be enslaved to a VRF. * The vrf device acts as the loopback for the vrf. */ if (port_dev == dev_net(dev)->loopback_dev) { NL_SET_ERR_MSG(extack, "Can not enslave loopback device to a VRF"); return -EOPNOTSUPP; } port_dev->priv_flags |= IFF_L3MDEV_SLAVE; ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack); if (ret < 0) goto err; cycle_netdev(port_dev, extack); return 0; err: port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; return ret; } static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { if (netif_is_l3_master(port_dev)) { NL_SET_ERR_MSG(extack, "Can not enslave an L3 master device to a VRF"); return -EINVAL; } if (netif_is_l3_slave(port_dev)) return -EINVAL; return do_vrf_add_slave(dev, port_dev, extack); } /* inverse of do_vrf_add_slave */ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { netdev_upper_dev_unlink(port_dev, dev); port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; cycle_netdev(port_dev, NULL); return 0; } static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { return do_vrf_del_slave(dev, port_dev); } static void vrf_dev_uninit(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); vrf_rtable_release(dev, vrf); vrf_rt6_release(dev, vrf); } static int vrf_dev_init(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); /* create the default dst which points back to us */ if (vrf_rtable_create(dev) != 0) goto out_nomem; if (vrf_rt6_create(dev) != 0) goto out_rth; dev->flags = IFF_MASTER | IFF_NOARP; /* similarly, oper state is irrelevant; set to up to avoid confusion */ dev->operstate = IF_OPER_UP; netdev_lockdep_set_classes(dev); return 0; out_rth: vrf_rtable_release(dev, vrf); out_nomem: return -ENOMEM; } static const struct net_device_ops vrf_netdev_ops = { .ndo_init = vrf_dev_init, .ndo_uninit = vrf_dev_uninit, .ndo_start_xmit = vrf_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_add_slave = vrf_add_slave, .ndo_del_slave = vrf_del_slave, }; static u32 vrf_fib_table(const struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); return vrf->tb_id; } static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook, struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1) skb = NULL; /* kfree_skb(skb) handled by nf code */ return skb; } static int vrf_prepare_mac_header(struct sk_buff *skb, struct net_device *vrf_dev, u16 proto) { struct ethhdr *eth; int err; /* in general, we do not know if there is enough space in the head of * the packet for hosting the mac header. */ err = skb_cow_head(skb, LL_RESERVED_SPACE(vrf_dev)); if (unlikely(err)) /* no space in the skb head */ return -ENOBUFS; __skb_push(skb, ETH_HLEN); eth = (struct ethhdr *)skb->data; skb_reset_mac_header(skb); skb_reset_mac_len(skb); /* we set the ethernet destination and the source addresses to the * address of the VRF device. */ ether_addr_copy(eth->h_dest, vrf_dev->dev_addr); ether_addr_copy(eth->h_source, vrf_dev->dev_addr); eth->h_proto = htons(proto); /* the destination address of the Ethernet frame corresponds to the * address set on the VRF interface; therefore, the packet is intended * to be processed locally. */ skb->protocol = eth->h_proto; skb->pkt_type = PACKET_HOST; skb_postpush_rcsum(skb, skb->data, ETH_HLEN); skb_pull_inline(skb, ETH_HLEN); return 0; } /* prepare and add the mac header to the packet if it was not set previously. * In this way, packet sniffers such as tcpdump can parse the packet correctly. * If the mac header was already set, the original mac header is left * untouched and the function returns immediately. */ static int vrf_add_mac_header_if_unset(struct sk_buff *skb, struct net_device *vrf_dev, u16 proto, struct net_device *orig_dev) { if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev)) return 0; return vrf_prepare_mac_header(skb, vrf_dev, proto); } #if IS_ENABLED(CONFIG_IPV6) /* neighbor handling is done with actual device; do not want * to flip skb->dev for those ndisc packets. This really fails * for multiple next protocols (e.g., NEXTHDR_HOP). But it is * a start. */ static bool ipv6_ndisc_frame(const struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); bool rc = false; if (iph->nexthdr == NEXTHDR_ICMP) { const struct icmp6hdr *icmph; struct icmp6hdr _icmph; icmph = skb_header_pointer(skb, sizeof(*iph), sizeof(_icmph), &_icmph); if (!icmph) goto out; switch (icmph->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: rc = true; break; } } out: return rc; } static struct rt6_info *vrf_ip6_route_lookup(struct net *net, const struct net_device *dev, struct flowi6 *fl6, int ifindex, const struct sk_buff *skb, int flags) { struct net_vrf *vrf = netdev_priv(dev); return ip6_pol_route(net, vrf->fib6_table, ifindex, fl6, skb, flags); } static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev, int ifindex) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct flowi6 fl6 = { .flowi6_iif = ifindex, .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), }; struct net *net = dev_net(vrf_dev); struct rt6_info *rt6; rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb, RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE); if (unlikely(!rt6)) return; if (unlikely(&rt6->dst == &net->ipv6.ip6_null_entry->dst)) return; skb_dst_set(skb, &rt6->dst); } static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { int orig_iif = skb->skb_iif; bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); bool is_ndisc = ipv6_ndisc_frame(skb); /* loopback, multicast & non-ND link-local traffic; do not push through * packet taps again. Reset pkt_type for upper layers to process skb. * For non-loopback strict packets, determine the dst using the original * ifindex. */ if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IP6CB(skb)->flags |= IP6SKB_L3SLAVE; if (skb->pkt_type == PACKET_LOOPBACK) skb->pkt_type = PACKET_HOST; else vrf_ip6_input_dst(skb, vrf_dev, orig_iif); goto out; } /* if packet is NDISC then keep the ingress interface */ if (!is_ndisc) { struct net_device *orig_dev = skb->dev; vrf_rx_stats(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; if (!list_empty(&vrf_dev->ptype_all)) { int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IPV6, orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, skb->mac_len); } } IP6CB(skb)->flags |= IP6SKB_L3SLAVE; } if (need_strict) vrf_ip6_input_dst(skb, vrf_dev, orig_iif); skb = vrf_rcv_nfhook(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, vrf_dev); out: return skb; } #else static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { return skb; } #endif static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_device *orig_dev = skb->dev; skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IPCB(skb)->flags |= IPSKB_L3SLAVE; if (ipv4_is_multicast(ip_hdr(skb)->daddr)) goto out; /* loopback traffic; do not push through packet taps again. * Reset pkt_type for upper layers to process skb */ if (skb->pkt_type == PACKET_LOOPBACK) { skb->pkt_type = PACKET_HOST; goto out; } vrf_rx_stats(vrf_dev, skb->len); if (!list_empty(&vrf_dev->ptype_all)) { int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP, orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, skb->mac_len); } } skb = vrf_rcv_nfhook(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, vrf_dev); out: return skb; } /* called with rcu lock held */ static struct sk_buff *vrf_l3_rcv(struct net_device *vrf_dev, struct sk_buff *skb, u16 proto) { switch (proto) { case AF_INET: return vrf_ip_rcv(vrf_dev, skb); case AF_INET6: return vrf_ip6_rcv(vrf_dev, skb); } return skb; } #if IS_ENABLED(CONFIG_IPV6) /* send to link-local or multicast address via interface enslaved to * VRF device. Force lookup to VRF table without changing flow struct * Note: Caller to this function must hold rcu_read_lock() and no refcnt * is taken on the dst by this function. */ static struct dst_entry *vrf_link_scope_lookup(const struct net_device *dev, struct flowi6 *fl6) { struct net *net = dev_net(dev); int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_DST_NOREF; struct dst_entry *dst = NULL; struct rt6_info *rt; /* VRF device does not have a link-local address and * sending packets to link-local or mcast addresses over * a VRF device does not make sense */ if (fl6->flowi6_oif == dev->ifindex) { dst = &net->ipv6.ip6_null_entry->dst; return dst; } if (!ipv6_addr_any(&fl6->saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, NULL, flags); if (rt) dst = &rt->dst; return dst; } #endif static const struct l3mdev_ops vrf_l3mdev_ops = { .l3mdev_fib_table = vrf_fib_table, .l3mdev_l3_rcv = vrf_l3_rcv, .l3mdev_l3_out = vrf_l3_out, #if IS_ENABLED(CONFIG_IPV6) .l3mdev_link_scope_lookup = vrf_link_scope_lookup, #endif }; static void vrf_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); } static const struct ethtool_ops vrf_ethtool_ops = { .get_drvinfo = vrf_get_drvinfo, }; static inline size_t vrf_fib_rule_nl_size(void) { size_t sz; sz = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)); sz += nla_total_size(sizeof(u8)); /* FRA_L3MDEV */ sz += nla_total_size(sizeof(u32)); /* FRA_PRIORITY */ sz += nla_total_size(sizeof(u8)); /* FRA_PROTOCOL */ return sz; } static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) { struct fib_rule_hdr *frh; struct nlmsghdr *nlh; struct sk_buff *skb; int err; if ((family == AF_INET6 || family == RTNL_FAMILY_IP6MR) && !ipv6_mod_enabled()) return 0; skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL); if (!skb) return -ENOMEM; nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*frh), 0); if (!nlh) goto nla_put_failure; /* rule only needs to appear once */ nlh->nlmsg_flags |= NLM_F_EXCL; frh = nlmsg_data(nlh); memset(frh, 0, sizeof(*frh)); frh->family = family; frh->action = FR_ACT_TO_TBL; if (nla_put_u8(skb, FRA_PROTOCOL, RTPROT_KERNEL)) goto nla_put_failure; if (nla_put_u8(skb, FRA_L3MDEV, 1)) goto nla_put_failure; if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF)) goto nla_put_failure; nlmsg_end(skb, nlh); /* fib_nl_{new,del}rule handling looks for net from skb->sk */ skb->sk = dev_net(dev)->rtnl; if (add_it) { err = fib_nl_newrule(skb, nlh, NULL); if (err == -EEXIST) err = 0; } else { err = fib_nl_delrule(skb, nlh, NULL); if (err == -ENOENT) err = 0; } nlmsg_free(skb); return err; nla_put_failure: nlmsg_free(skb); return -EMSGSIZE; } static int vrf_add_fib_rules(const struct net_device *dev) { int err; err = vrf_fib_rule(dev, AF_INET, true); if (err < 0) goto out_err; err = vrf_fib_rule(dev, AF_INET6, true); if (err < 0) goto ipv6_err; #if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES) err = vrf_fib_rule(dev, RTNL_FAMILY_IPMR, true); if (err < 0) goto ipmr_err; #endif #if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES) err = vrf_fib_rule(dev, RTNL_FAMILY_IP6MR, true); if (err < 0) goto ip6mr_err; #endif return 0; #if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES) ip6mr_err: vrf_fib_rule(dev, RTNL_FAMILY_IPMR, false); #endif #if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES) ipmr_err: vrf_fib_rule(dev, AF_INET6, false); #endif ipv6_err: vrf_fib_rule(dev, AF_INET, false); out_err: netdev_err(dev, "Failed to add FIB rules.\n"); return err; } static void vrf_setup(struct net_device *dev) { ether_setup(dev); /* Initialize the device structure. */ dev->netdev_ops = &vrf_netdev_ops; dev->l3mdev_ops = &vrf_l3mdev_ops; dev->ethtool_ops = &vrf_ethtool_ops; dev->needs_free_netdev = true; /* Fill in device structure with ethernet-generic values. */ eth_hw_addr_random(dev); /* don't acquire vrf device's netif_tx_lock when transmitting */ dev->lltx = true; /* don't allow vrf devices to change network namespaces. */ dev->netns_local = true; /* does not make sense for a VLAN to be added to a vrf device */ dev->features |= NETIF_F_VLAN_CHALLENGED; /* enable offload features */ dev->features |= NETIF_F_GSO_SOFTWARE; dev->features |= NETIF_F_RXCSUM | NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC; dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA; dev->hw_features = dev->features; dev->hw_enc_features = dev->features; /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_NO_RX_HANDLER; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* VRF devices do not care about MTU, but if the MTU is set * too low then the ipv4 and ipv6 protocols are disabled * which breaks networking. */ dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU; dev->mtu = dev->max_mtu; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG(extack, "Invalid hardware address"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG(extack, "Invalid hardware address"); return -EADDRNOTAVAIL; } } return 0; } static void vrf_dellink(struct net_device *dev, struct list_head *head) { struct net_device *port_dev; struct list_head *iter; netdev_for_each_lower_dev(dev, port_dev, iter) vrf_del_slave(dev, port_dev); vrf_map_unregister_dev(dev); unregister_netdevice_queue(dev, head); } static int vrf_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_vrf *vrf = netdev_priv(dev); struct netns_vrf *nn_vrf; bool *add_fib_rules; struct net *net; int err; if (!data || !data[IFLA_VRF_TABLE]) { NL_SET_ERR_MSG(extack, "VRF table id is missing"); return -EINVAL; } vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]); if (vrf->tb_id == RT_TABLE_UNSPEC) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VRF_TABLE], "Invalid VRF table id"); return -EINVAL; } dev->priv_flags |= IFF_L3MDEV_MASTER; err = register_netdevice(dev); if (err) goto out; /* mapping between table_id and vrf; * note: such binding could not be done in the dev init function * because dev->ifindex id is not available yet. */ vrf->ifindex = dev->ifindex; err = vrf_map_register_dev(dev, extack); if (err) { unregister_netdevice(dev); goto out; } net = dev_net(dev); nn_vrf = net_generic(net, vrf_net_id); add_fib_rules = &nn_vrf->add_fib_rules; if (*add_fib_rules) { err = vrf_add_fib_rules(dev); if (err) { vrf_map_unregister_dev(dev); unregister_netdevice(dev); goto out; } *add_fib_rules = false; } out: return err; } static size_t vrf_nl_getsize(const struct net_device *dev) { return nla_total_size(sizeof(u32)); /* IFLA_VRF_TABLE */ } static int vrf_fillinfo(struct sk_buff *skb, const struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); return nla_put_u32(skb, IFLA_VRF_TABLE, vrf->tb_id); } static size_t vrf_get_slave_size(const struct net_device *bond_dev, const struct net_device *slave_dev) { return nla_total_size(sizeof(u32)); /* IFLA_VRF_PORT_TABLE */ } static int vrf_fill_slave_info(struct sk_buff *skb, const struct net_device *vrf_dev, const struct net_device *slave_dev) { struct net_vrf *vrf = netdev_priv(vrf_dev); if (nla_put_u32(skb, IFLA_VRF_PORT_TABLE, vrf->tb_id)) return -EMSGSIZE; return 0; } static const struct nla_policy vrf_nl_policy[IFLA_VRF_MAX + 1] = { [IFLA_VRF_TABLE] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vrf_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct net_vrf), .get_size = vrf_nl_getsize, .policy = vrf_nl_policy, .validate = vrf_validate, .fill_info = vrf_fillinfo, .get_slave_size = vrf_get_slave_size, .fill_slave_info = vrf_fill_slave_info, .newlink = vrf_newlink, .dellink = vrf_dellink, .setup = vrf_setup, .maxtype = IFLA_VRF_MAX, }; static int vrf_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* only care about unregister events to drop slave references */ if (event == NETDEV_UNREGISTER) { struct net_device *vrf_dev; if (!netif_is_l3_slave(dev)) goto out; vrf_dev = netdev_master_upper_dev_get(dev); vrf_del_slave(vrf_dev, dev); } out: return NOTIFY_DONE; } static struct notifier_block vrf_notifier_block __read_mostly = { .notifier_call = vrf_device_event, }; static int vrf_map_init(struct vrf_map *vmap) { spin_lock_init(&vmap->vmap_lock); hash_init(vmap->ht); vmap->strict_mode = false; return 0; } #ifdef CONFIG_SYSCTL static bool vrf_strict_mode(struct vrf_map *vmap) { bool strict_mode; vrf_map_lock(vmap); strict_mode = vmap->strict_mode; vrf_map_unlock(vmap); return strict_mode; } static int vrf_strict_mode_change(struct vrf_map *vmap, bool new_mode) { bool *cur_mode; int res = 0; vrf_map_lock(vmap); cur_mode = &vmap->strict_mode; if (*cur_mode == new_mode) goto unlock; if (*cur_mode) { /* disable strict mode */ *cur_mode = false; } else { if (vmap->shared_tables) { /* we cannot allow strict_mode because there are some * vrfs that share one or more tables. */ res = -EBUSY; goto unlock; } /* no tables are shared among vrfs, so we can go back * to 1:1 association between a vrf with its table. */ *cur_mode = true; } unlock: vrf_map_unlock(vmap); return res; } static int vrf_shared_table_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)table->extra1; struct vrf_map *vmap = netns_vrf_map(net); int proc_strict_mode = 0; struct ctl_table tmp = { .procname = table->procname, .data = &proc_strict_mode, .maxlen = sizeof(int), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }; int ret; if (!write) proc_strict_mode = vrf_strict_mode(vmap); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) ret = vrf_strict_mode_change(vmap, (bool)proc_strict_mode); return ret; } static const struct ctl_table vrf_table[] = { { .procname = "strict_mode", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = vrf_shared_table_handler, /* set by the vrf_netns_init */ .extra1 = NULL, }, }; static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { struct ctl_table *table; table = kmemdup(vrf_table, sizeof(vrf_table), GFP_KERNEL); if (!table) return -ENOMEM; /* init the extra1 parameter with the reference to current netns */ table[0].extra1 = net; nn_vrf->ctl_hdr = register_net_sysctl_sz(net, "net/vrf", table, ARRAY_SIZE(vrf_table)); if (!nn_vrf->ctl_hdr) { kfree(table); return -ENOMEM; } return 0; } static void vrf_netns_exit_sysctl(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); const struct ctl_table *table; table = nn_vrf->ctl_hdr->ctl_table_arg; unregister_net_sysctl_table(nn_vrf->ctl_hdr); kfree(table); } #else static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { return 0; } static void vrf_netns_exit_sysctl(struct net *net) { } #endif /* Initialize per network namespace state */ static int __net_init vrf_netns_init(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); nn_vrf->add_fib_rules = true; vrf_map_init(&nn_vrf->vmap); return vrf_netns_init_sysctl(net, nn_vrf); } static void __net_exit vrf_netns_exit(struct net *net) { vrf_netns_exit_sysctl(net); } static struct pernet_operations vrf_net_ops __net_initdata = { .init = vrf_netns_init, .exit = vrf_netns_exit, .id = &vrf_net_id, .size = sizeof(struct netns_vrf), }; static int __init vrf_init_module(void) { int rc; register_netdevice_notifier(&vrf_notifier_block); rc = register_pernet_subsys(&vrf_net_ops); if (rc < 0) goto error; rc = l3mdev_table_lookup_register(L3MDEV_TYPE_VRF, vrf_ifindex_lookup_by_table_id); if (rc < 0) goto unreg_pernet; rc = rtnl_link_register(&vrf_link_ops); if (rc < 0) goto table_lookup_unreg; return 0; table_lookup_unreg: l3mdev_table_lookup_unregister(L3MDEV_TYPE_VRF, vrf_ifindex_lookup_by_table_id); unreg_pernet: unregister_pernet_subsys(&vrf_net_ops); error: unregister_netdevice_notifier(&vrf_notifier_block); return rc; } module_init(vrf_init_module); MODULE_AUTHOR("Shrijeet Mukherjee, David Ahern"); MODULE_DESCRIPTION("Device driver to instantiate VRF domains"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); MODULE_VERSION(DRV_VERSION); |
| 2 16 1 9 6 15 3 9 12 8 8 8 8 7 1 7 2 2 5 7 14 15 16 9 7 16 1 12 15 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 | // SPDX-License-Identifier: GPL-2.0-or-later /* * udp_diag.c Module for monitoring UDP transport protocols sockets. * * Authors: Pavel Emelyanov, <xemul@parallels.com> */ #include <linux/module.h> #include <linux/inet_diag.h> #include <linux/udp.h> #include <net/udp.h> #include <net/udplite.h> #include <linux/sock_diag.h> static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *req, struct nlattr *bc, bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; return inet_sk_diag_fill(sk, NULL, skb, cb, req, NLM_F_MULTI, net_admin); } static int udp_dump_one(struct udp_table *tbl, struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { struct sk_buff *in_skb = cb->skb; int err; struct sock *sk = NULL; struct sk_buff *rep; struct net *net = sock_net(in_skb->sk); rcu_read_lock(); if (req->sdiag_family == AF_INET) /* src and dst are swapped for historical reasons */ sk = __udp4_lib_lookup(net, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_if, 0, tbl, NULL); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) sk = __udp6_lib_lookup(net, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, req->id.idiag_if, 0, tbl, NULL); #endif if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); err = -ENOENT; if (!sk) goto out_nosk; err = sock_diag_check_cookie(sk, req->id.idiag_cookie); if (err) goto out; err = -ENOMEM; rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + inet_diag_msg_attrs_size() + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) goto out; err = inet_sk_diag_fill(sk, NULL, rep, cb, req, 0, netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(rep); goto out; } err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); out: if (sk) sock_put(sk); out_nosk: return err; } static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct net *net = sock_net(skb->sk); struct inet_diag_dump_data *cb_data; int num, s_num, slot, s_slot; struct nlattr *bc; cb_data = cb->data; bc = cb_data->inet_diag_nla_bc; s_slot = cb->args[0]; num = s_num = cb->args[1]; for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) { struct udp_hslot *hslot = &table->hash[slot]; struct sock *sk; num = 0; if (hlist_empty(&hslot->head)) continue; spin_lock_bh(&hslot->lock); sk_for_each(sk, &hslot->head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) goto next; if (!(r->idiag_states & (1 << sk->sk_state))) goto next; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next; if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next; if (r->id.idiag_dport != inet->inet_dport && r->id.idiag_dport) goto next; if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) { spin_unlock_bh(&hslot->lock); goto done; } next: num++; } spin_unlock_bh(&hslot->lock); } done: cb->args[0] = slot; cb->args[1] = num; } static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { udp_dump(sock_net(cb->skb->sk)->ipv4.udp_table, skb, cb, r); } static int udp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { return udp_dump_one(sock_net(cb->skb->sk)->ipv4.udp_table, cb, req); } static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, void *info) { r->idiag_rqueue = udp_rqueue_get(sk); r->idiag_wqueue = sk_wmem_alloc_get(sk); } #ifdef CONFIG_INET_DIAG_DESTROY static int __udp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req, struct udp_table *tbl) { struct net *net = sock_net(in_skb->sk); struct sock *sk; int err; rcu_read_lock(); if (req->sdiag_family == AF_INET) sk = __udp4_lib_lookup(net, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if, 0, tbl, NULL); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) { if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) sk = __udp4_lib_lookup(net, req->id.idiag_dst[3], req->id.idiag_dport, req->id.idiag_src[3], req->id.idiag_sport, req->id.idiag_if, 0, tbl, NULL); else sk = __udp6_lib_lookup(net, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, req->id.idiag_if, 0, tbl, NULL); } #endif else { rcu_read_unlock(); return -EINVAL; } if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); if (!sk) return -ENOENT; if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { sock_put(sk); return -ENOENT; } err = sock_diag_destroy(sk, ECONNABORTED); sock_put(sk); return err; } static int udp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { return __udp_diag_destroy(in_skb, req, sock_net(in_skb->sk)->ipv4.udp_table); } static int udplite_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { return __udp_diag_destroy(in_skb, req, &udplite_table); } #endif static const struct inet_diag_handler udp_diag_handler = { .owner = THIS_MODULE, .dump = udp_diag_dump, .dump_one = udp_diag_dump_one, .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDP, .idiag_info_size = 0, #ifdef CONFIG_INET_DIAG_DESTROY .destroy = udp_diag_destroy, #endif }; static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { udp_dump(&udplite_table, skb, cb, r); } static int udplite_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { return udp_dump_one(&udplite_table, cb, req); } static const struct inet_diag_handler udplite_diag_handler = { .owner = THIS_MODULE, .dump = udplite_diag_dump, .dump_one = udplite_diag_dump_one, .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDPLITE, .idiag_info_size = 0, #ifdef CONFIG_INET_DIAG_DESTROY .destroy = udplite_diag_destroy, #endif }; static int __init udp_diag_init(void) { int err; err = inet_diag_register(&udp_diag_handler); if (err) goto out; err = inet_diag_register(&udplite_diag_handler); if (err) goto out_lite; out: return err; out_lite: inet_diag_unregister(&udp_diag_handler); goto out; } static void __exit udp_diag_exit(void) { inet_diag_unregister(&udplite_diag_handler); inet_diag_unregister(&udp_diag_handler); } module_init(udp_diag_init); module_exit(udp_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("UDP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-17 /* AF_INET - IPPROTO_UDP */); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-136 /* AF_INET - IPPROTO_UDPLITE */); |
| 97 97 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 | // SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/async.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/delay.h> #include <linux/string.h> #include <linux/dirent.h> #include <linux/syscalls.h> #include <linux/utime.h> #include <linux/file.h> #include <linux/kstrtox.h> #include <linux/memblock.h> #include <linux/mm.h> #include <linux/namei.h> #include <linux/init_syscalls.h> #include <linux/umh.h> #include <linux/security.h> #include "do_mounts.h" static __initdata bool csum_present; static __initdata u32 io_csum; static ssize_t __init xwrite(struct file *file, const unsigned char *p, size_t count, loff_t *pos) { ssize_t out = 0; /* sys_write only can write MAX_RW_COUNT aka 2G-4K bytes at most */ while (count) { ssize_t rv = kernel_write(file, p, count, pos); if (rv < 0) { if (rv == -EINTR || rv == -EAGAIN) continue; return out ? out : rv; } else if (rv == 0) break; if (csum_present) { ssize_t i; for (i = 0; i < rv; i++) io_csum += p[i]; } p += rv; out += rv; count -= rv; } return out; } static __initdata char *message; static void __init error(char *x) { if (!message) message = x; } #define panic_show_mem(fmt, ...) \ ({ show_mem(); panic(fmt, ##__VA_ARGS__); }) /* link hash */ #define N_ALIGN(len) ((((len) + 1) & ~3) + 2) static __initdata struct hash { int ino, minor, major; umode_t mode; struct hash *next; char name[N_ALIGN(PATH_MAX)]; } *head[32]; static inline int hash(int major, int minor, int ino) { unsigned long tmp = ino + minor + (major << 3); tmp += tmp >> 5; return tmp & 31; } static char __init *find_link(int major, int minor, int ino, umode_t mode, char *name) { struct hash **p, *q; for (p = head + hash(major, minor, ino); *p; p = &(*p)->next) { if ((*p)->ino != ino) continue; if ((*p)->minor != minor) continue; if ((*p)->major != major) continue; if (((*p)->mode ^ mode) & S_IFMT) continue; return (*p)->name; } q = kmalloc(sizeof(struct hash), GFP_KERNEL); if (!q) panic_show_mem("can't allocate link hash entry"); q->major = major; q->minor = minor; q->ino = ino; q->mode = mode; strcpy(q->name, name); q->next = NULL; *p = q; return NULL; } static void __init free_hash(void) { struct hash **p, *q; for (p = head; p < head + 32; p++) { while (*p) { q = *p; *p = q->next; kfree(q); } } } #ifdef CONFIG_INITRAMFS_PRESERVE_MTIME static void __init do_utime(char *filename, time64_t mtime) { struct timespec64 t[2] = { { .tv_sec = mtime }, { .tv_sec = mtime } }; init_utimes(filename, t); } static void __init do_utime_path(const struct path *path, time64_t mtime) { struct timespec64 t[2] = { { .tv_sec = mtime }, { .tv_sec = mtime } }; vfs_utimes(path, t); } static __initdata LIST_HEAD(dir_list); struct dir_entry { struct list_head list; time64_t mtime; char name[]; }; static void __init dir_add(const char *name, time64_t mtime) { size_t nlen = strlen(name) + 1; struct dir_entry *de; de = kmalloc(sizeof(struct dir_entry) + nlen, GFP_KERNEL); if (!de) panic_show_mem("can't allocate dir_entry buffer"); INIT_LIST_HEAD(&de->list); strscpy(de->name, name, nlen); de->mtime = mtime; list_add(&de->list, &dir_list); } static void __init dir_utime(void) { struct dir_entry *de, *tmp; list_for_each_entry_safe(de, tmp, &dir_list, list) { list_del(&de->list); do_utime(de->name, de->mtime); kfree(de); } } #else static void __init do_utime(char *filename, time64_t mtime) {} static void __init do_utime_path(const struct path *path, time64_t mtime) {} static void __init dir_add(const char *name, time64_t mtime) {} static void __init dir_utime(void) {} #endif static __initdata time64_t mtime; /* cpio header parsing */ static __initdata unsigned long ino, major, minor, nlink; static __initdata umode_t mode; static __initdata unsigned long body_len, name_len; static __initdata uid_t uid; static __initdata gid_t gid; static __initdata unsigned rdev; static __initdata u32 hdr_csum; static void __init parse_header(char *s) { unsigned long parsed[13]; char buf[9]; int i; buf[8] = '\0'; for (i = 0, s += 6; i < 13; i++, s += 8) { memcpy(buf, s, 8); parsed[i] = simple_strtoul(buf, NULL, 16); } ino = parsed[0]; mode = parsed[1]; uid = parsed[2]; gid = parsed[3]; nlink = parsed[4]; mtime = parsed[5]; /* breaks in y2106 */ body_len = parsed[6]; major = parsed[7]; minor = parsed[8]; rdev = new_encode_dev(MKDEV(parsed[9], parsed[10])); name_len = parsed[11]; hdr_csum = parsed[12]; } /* FSM */ static __initdata enum state { Start, Collect, GotHeader, SkipIt, GotName, CopyFile, GotSymlink, Reset } state, next_state; static __initdata char *victim; static unsigned long byte_count __initdata; static __initdata loff_t this_header, next_header; static inline void __init eat(unsigned n) { victim += n; this_header += n; byte_count -= n; } static __initdata char *collected; static long remains __initdata; static __initdata char *collect; static void __init read_into(char *buf, unsigned size, enum state next) { if (byte_count >= size) { collected = victim; eat(size); state = next; } else { collect = collected = buf; remains = size; next_state = next; state = Collect; } } static __initdata char *header_buf, *symlink_buf, *name_buf; static int __init do_start(void) { read_into(header_buf, 110, GotHeader); return 0; } static int __init do_collect(void) { unsigned long n = remains; if (byte_count < n) n = byte_count; memcpy(collect, victim, n); eat(n); collect += n; if ((remains -= n) != 0) return 1; state = next_state; return 0; } static int __init do_header(void) { if (!memcmp(collected, "070701", 6)) { csum_present = false; } else if (!memcmp(collected, "070702", 6)) { csum_present = true; } else { if (memcmp(collected, "070707", 6) == 0) error("incorrect cpio method used: use -H newc option"); else error("no cpio magic"); return 1; } parse_header(collected); next_header = this_header + N_ALIGN(name_len) + body_len; next_header = (next_header + 3) & ~3; state = SkipIt; if (name_len <= 0 || name_len > PATH_MAX) return 0; if (S_ISLNK(mode)) { if (body_len > PATH_MAX) return 0; collect = collected = symlink_buf; remains = N_ALIGN(name_len) + body_len; next_state = GotSymlink; state = Collect; return 0; } if (S_ISREG(mode) || !body_len) read_into(name_buf, N_ALIGN(name_len), GotName); return 0; } static int __init do_skip(void) { if (this_header + byte_count < next_header) { eat(byte_count); return 1; } else { eat(next_header - this_header); state = next_state; return 0; } } static int __init do_reset(void) { while (byte_count && *victim == '\0') eat(1); if (byte_count && (this_header & 3)) error("broken padding"); return 1; } static void __init clean_path(char *path, umode_t fmode) { struct kstat st; if (!init_stat(path, &st, AT_SYMLINK_NOFOLLOW) && (st.mode ^ fmode) & S_IFMT) { if (S_ISDIR(st.mode)) init_rmdir(path); else init_unlink(path); } } static int __init maybe_link(void) { if (nlink >= 2) { char *old = find_link(major, minor, ino, mode, collected); if (old) { clean_path(collected, 0); return (init_link(old, collected) < 0) ? -1 : 1; } } return 0; } static __initdata struct file *wfile; static __initdata loff_t wfile_pos; static int __init do_name(void) { state = SkipIt; next_state = Reset; if (strcmp(collected, "TRAILER!!!") == 0) { free_hash(); return 0; } clean_path(collected, mode); if (S_ISREG(mode)) { int ml = maybe_link(); if (ml >= 0) { int openflags = O_WRONLY|O_CREAT|O_LARGEFILE; if (ml != 1) openflags |= O_TRUNC; wfile = filp_open(collected, openflags, mode); if (IS_ERR(wfile)) return 0; wfile_pos = 0; io_csum = 0; vfs_fchown(wfile, uid, gid); vfs_fchmod(wfile, mode); if (body_len) vfs_truncate(&wfile->f_path, body_len); state = CopyFile; } } else if (S_ISDIR(mode)) { init_mkdir(collected, mode); init_chown(collected, uid, gid, 0); init_chmod(collected, mode); dir_add(collected, mtime); } else if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) { if (maybe_link() == 0) { init_mknod(collected, mode, rdev); init_chown(collected, uid, gid, 0); init_chmod(collected, mode); do_utime(collected, mtime); } } return 0; } static int __init do_copy(void) { if (byte_count >= body_len) { if (xwrite(wfile, victim, body_len, &wfile_pos) != body_len) error("write error"); do_utime_path(&wfile->f_path, mtime); fput(wfile); if (csum_present && io_csum != hdr_csum) error("bad data checksum"); eat(body_len); state = SkipIt; return 0; } else { if (xwrite(wfile, victim, byte_count, &wfile_pos) != byte_count) error("write error"); body_len -= byte_count; eat(byte_count); return 1; } } static int __init do_symlink(void) { collected[N_ALIGN(name_len) + body_len] = '\0'; clean_path(collected, 0); init_symlink(collected + N_ALIGN(name_len), collected); init_chown(collected, uid, gid, AT_SYMLINK_NOFOLLOW); do_utime(collected, mtime); state = SkipIt; next_state = Reset; return 0; } static __initdata int (*actions[])(void) = { [Start] = do_start, [Collect] = do_collect, [GotHeader] = do_header, [SkipIt] = do_skip, [GotName] = do_name, [CopyFile] = do_copy, [GotSymlink] = do_symlink, [Reset] = do_reset, }; static long __init write_buffer(char *buf, unsigned long len) { byte_count = len; victim = buf; while (!actions[state]()) ; return len - byte_count; } static long __init flush_buffer(void *bufv, unsigned long len) { char *buf = bufv; long written; long origLen = len; if (message) return -1; while ((written = write_buffer(buf, len)) < len && !message) { char c = buf[written]; if (c == '0') { buf += written; len -= written; state = Start; } else if (c == 0) { buf += written; len -= written; state = Reset; } else error("junk within compressed archive"); } return origLen; } static unsigned long my_inptr __initdata; /* index of next byte to be processed in inbuf */ #include <linux/decompress/generic.h> static char * __init unpack_to_rootfs(char *buf, unsigned long len) { long written; decompress_fn decompress; const char *compress_name; static __initdata char msg_buf[64]; header_buf = kmalloc(110, GFP_KERNEL); symlink_buf = kmalloc(PATH_MAX + N_ALIGN(PATH_MAX) + 1, GFP_KERNEL); name_buf = kmalloc(N_ALIGN(PATH_MAX), GFP_KERNEL); if (!header_buf || !symlink_buf || !name_buf) panic_show_mem("can't allocate buffers"); state = Start; this_header = 0; message = NULL; while (!message && len) { loff_t saved_offset = this_header; if (*buf == '0' && !(this_header & 3)) { state = Start; written = write_buffer(buf, len); buf += written; len -= written; continue; } if (!*buf) { buf++; len--; this_header++; continue; } this_header = 0; decompress = decompress_method(buf, len, &compress_name); pr_debug("Detected %s compressed data\n", compress_name); if (decompress) { int res = decompress(buf, len, NULL, flush_buffer, NULL, &my_inptr, error); if (res) error("decompressor failed"); } else if (compress_name) { if (!message) { snprintf(msg_buf, sizeof msg_buf, "compression method %s not configured", compress_name); message = msg_buf; } } else error("invalid magic at start of compressed archive"); if (state != Reset) error("junk at the end of compressed archive"); this_header = saved_offset + my_inptr; buf += my_inptr; len -= my_inptr; } dir_utime(); kfree(name_buf); kfree(symlink_buf); kfree(header_buf); return message; } static int __initdata do_retain_initrd; static int __init retain_initrd_param(char *str) { if (*str) return 0; do_retain_initrd = 1; return 1; } __setup("retain_initrd", retain_initrd_param); #ifdef CONFIG_ARCH_HAS_KEEPINITRD static int __init keepinitrd_setup(char *__unused) { do_retain_initrd = 1; return 1; } __setup("keepinitrd", keepinitrd_setup); #endif static bool __initdata initramfs_async = true; static int __init initramfs_async_setup(char *str) { return kstrtobool(str, &initramfs_async) == 0; } __setup("initramfs_async=", initramfs_async_setup); extern char __initramfs_start[]; extern unsigned long __initramfs_size; #include <linux/initrd.h> #include <linux/kexec.h> static BIN_ATTR(initrd, 0440, sysfs_bin_attr_simple_read, NULL, 0); void __init reserve_initrd_mem(void) { phys_addr_t start; unsigned long size; /* Ignore the virtul address computed during device tree parsing */ initrd_start = initrd_end = 0; if (!phys_initrd_size) return; /* * Round the memory region to page boundaries as per free_initrd_mem() * This allows us to detect whether the pages overlapping the initrd * are in use, but more importantly, reserves the entire set of pages * as we don't want these pages allocated for other purposes. */ start = round_down(phys_initrd_start, PAGE_SIZE); size = phys_initrd_size + (phys_initrd_start - start); size = round_up(size, PAGE_SIZE); if (!memblock_is_region_memory(start, size)) { pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region", (u64)start, size); goto disable; } if (memblock_is_region_reserved(start, size)) { pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n", (u64)start, size); goto disable; } memblock_reserve(start, size); /* Now convert initrd to virtual addresses */ initrd_start = (unsigned long)__va(phys_initrd_start); initrd_end = initrd_start + phys_initrd_size; initrd_below_start_ok = 1; return; disable: pr_cont(" - disabling initrd\n"); initrd_start = 0; initrd_end = 0; } void __weak __init free_initrd_mem(unsigned long start, unsigned long end) { #ifdef CONFIG_ARCH_KEEP_MEMBLOCK unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE); unsigned long aligned_end = ALIGN(end, PAGE_SIZE); memblock_free((void *)aligned_start, aligned_end - aligned_start); #endif free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, "initrd"); } #ifdef CONFIG_CRASH_RESERVE static bool __init kexec_free_initrd(void) { unsigned long crashk_start = (unsigned long)__va(crashk_res.start); unsigned long crashk_end = (unsigned long)__va(crashk_res.end); /* * If the initrd region is overlapped with crashkernel reserved region, * free only memory that is not part of crashkernel region. */ if (initrd_start >= crashk_end || initrd_end <= crashk_start) return false; /* * Initialize initrd memory region since the kexec boot does not do. */ memset((void *)initrd_start, 0, initrd_end - initrd_start); if (initrd_start < crashk_start) free_initrd_mem(initrd_start, crashk_start); if (initrd_end > crashk_end) free_initrd_mem(crashk_end, initrd_end); return true; } #else static inline bool kexec_free_initrd(void) { return false; } #endif /* CONFIG_KEXEC_CORE */ #ifdef CONFIG_BLK_DEV_RAM static void __init populate_initrd_image(char *err) { ssize_t written; struct file *file; loff_t pos = 0; printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n", err); file = filp_open("/initrd.image", O_WRONLY|O_CREAT|O_LARGEFILE, 0700); if (IS_ERR(file)) return; written = xwrite(file, (char *)initrd_start, initrd_end - initrd_start, &pos); if (written != initrd_end - initrd_start) pr_err("/initrd.image: incomplete write (%zd != %ld)\n", written, initrd_end - initrd_start); fput(file); } #endif /* CONFIG_BLK_DEV_RAM */ static void __init do_populate_rootfs(void *unused, async_cookie_t cookie) { /* Load the built in initramfs */ char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size); if (err) panic_show_mem("%s", err); /* Failed to decompress INTERNAL initramfs */ if (!initrd_start || IS_ENABLED(CONFIG_INITRAMFS_FORCE)) goto done; if (IS_ENABLED(CONFIG_BLK_DEV_RAM)) printk(KERN_INFO "Trying to unpack rootfs image as initramfs...\n"); else printk(KERN_INFO "Unpacking initramfs...\n"); err = unpack_to_rootfs((char *)initrd_start, initrd_end - initrd_start); if (err) { #ifdef CONFIG_BLK_DEV_RAM populate_initrd_image(err); #else printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err); #endif } done: security_initramfs_populated(); /* * If the initrd region is overlapped with crashkernel reserved region, * free only memory that is not part of crashkernel region. */ if (!do_retain_initrd && initrd_start && !kexec_free_initrd()) { free_initrd_mem(initrd_start, initrd_end); } else if (do_retain_initrd && initrd_start) { bin_attr_initrd.size = initrd_end - initrd_start; bin_attr_initrd.private = (void *)initrd_start; if (sysfs_create_bin_file(firmware_kobj, &bin_attr_initrd)) pr_err("Failed to create initrd sysfs file"); } initrd_start = 0; initrd_end = 0; init_flush_fput(); } static ASYNC_DOMAIN_EXCLUSIVE(initramfs_domain); static async_cookie_t initramfs_cookie; void wait_for_initramfs(void) { if (!initramfs_cookie) { /* * Something before rootfs_initcall wants to access * the filesystem/initramfs. Probably a bug. Make a * note, avoid deadlocking the machine, and let the * caller's access fail as it used to. */ pr_warn_once("wait_for_initramfs() called before rootfs_initcalls\n"); return; } async_synchronize_cookie_domain(initramfs_cookie + 1, &initramfs_domain); } EXPORT_SYMBOL_GPL(wait_for_initramfs); static int __init populate_rootfs(void) { initramfs_cookie = async_schedule_domain(do_populate_rootfs, NULL, &initramfs_domain); usermodehelper_enable(); if (!initramfs_async) wait_for_initramfs(); return 0; } rootfs_initcall(populate_rootfs); |
| 30 30 31 18 30 30 25 25 25 25 25 29 29 29 29 25 24 5 24 24 24 24 25 25 24 24 24 24 24 24 28 6 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 | // SPDX-License-Identifier: GPL-2.0-or-later /* * RTC class driver for "CMOS RTC": PCs, ACPI, etc * * Copyright (C) 1996 Paul Gortmaker (drivers/char/rtc.c) * Copyright (C) 2006 David Brownell (convert to new framework) */ /* * The original "cmos clock" chip was an MC146818 chip, now obsolete. * That defined the register interface now provided by all PCs, some * non-PC systems, and incorporated into ACPI. Modern PC chipsets * integrate an MC146818 clone in their southbridge, and boards use * that instead of discrete clones like the DS12887 or M48T86. There * are also clones that connect using the LPC bus. * * That register API is also used directly by various other drivers * (notably for integrated NVRAM), infrastructure (x86 has code to * bypass the RTC framework, directly reading the RTC during boot * and updating minutes/seconds for systems using NTP synch) and * utilities (like userspace 'hwclock', if no /dev node exists). * * So **ALL** calls to CMOS_READ and CMOS_WRITE must be done with * interrupts disabled, holding the global rtc_lock, to exclude those * other drivers and utilities on correctly configured systems. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/platform_device.h> #include <linux/log2.h> #include <linux/pm.h> #include <linux/of.h> #include <linux/of_platform.h> #ifdef CONFIG_X86 #include <asm/i8259.h> #include <asm/processor.h> #include <linux/dmi.h> #endif /* this is for "generic access to PC-style RTC" using CMOS_READ/CMOS_WRITE */ #include <linux/mc146818rtc.h> #ifdef CONFIG_ACPI /* * Use ACPI SCI to replace HPET interrupt for RTC Alarm event * * If cleared, ACPI SCI is only used to wake up the system from suspend * * If set, ACPI SCI is used to handle UIE/AIE and system wakeup */ static bool use_acpi_alarm; module_param(use_acpi_alarm, bool, 0444); static inline int cmos_use_acpi_alarm(void) { return use_acpi_alarm; } #else /* !CONFIG_ACPI */ static inline int cmos_use_acpi_alarm(void) { return 0; } #endif struct cmos_rtc { struct rtc_device *rtc; struct device *dev; int irq; struct resource *iomem; time64_t alarm_expires; void (*wake_on)(struct device *); void (*wake_off)(struct device *); u8 enabled_wake; u8 suspend_ctrl; /* newer hardware extends the original register set */ u8 day_alrm; u8 mon_alrm; u8 century; struct rtc_wkalrm saved_wkalrm; }; /* both platform and pnp busses use negative numbers for invalid irqs */ #define is_valid_irq(n) ((n) > 0) static const char driver_name[] = "rtc_cmos"; /* The RTC_INTR register may have e.g. RTC_PF set even if RTC_PIE is clear; * always mask it against the irq enable bits in RTC_CONTROL. Bit values * are the same: PF==PIE, AF=AIE, UF=UIE; so RTC_IRQMASK works with both. */ #define RTC_IRQMASK (RTC_PF | RTC_AF | RTC_UF) static inline int is_intr(u8 rtc_intr) { if (!(rtc_intr & RTC_IRQF)) return 0; return rtc_intr & RTC_IRQMASK; } /*----------------------------------------------------------------*/ /* Much modern x86 hardware has HPETs (10+ MHz timers) which, because * many BIOS programmers don't set up "sane mode" IRQ routing, are mostly * used in a broken "legacy replacement" mode. The breakage includes * HPET #1 hijacking the IRQ for this RTC, and being unavailable for * other (better) use. * * When that broken mode is in use, platform glue provides a partial * emulation of hardware RTC IRQ facilities using HPET #1. We don't * want to use HPET for anything except those IRQs though... */ #ifdef CONFIG_HPET_EMULATE_RTC #include <asm/hpet.h> #else static inline int is_hpet_enabled(void) { return 0; } static inline int hpet_mask_rtc_irq_bit(unsigned long mask) { return 0; } static inline int hpet_set_rtc_irq_bit(unsigned long mask) { return 0; } static inline int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec) { return 0; } static inline int hpet_set_periodic_freq(unsigned long freq) { return 0; } static inline int hpet_rtc_dropped_irq(void) { return 0; } static inline int hpet_rtc_timer_init(void) { return 0; } extern irq_handler_t hpet_rtc_interrupt; static inline int hpet_register_irq_handler(irq_handler_t handler) { return 0; } static inline int hpet_unregister_irq_handler(irq_handler_t handler) { return 0; } #endif /* Don't use HPET for RTC Alarm event if ACPI Fixed event is used */ static inline int use_hpet_alarm(void) { return is_hpet_enabled() && !cmos_use_acpi_alarm(); } /*----------------------------------------------------------------*/ #ifdef RTC_PORT /* Most newer x86 systems have two register banks, the first used * for RTC and NVRAM and the second only for NVRAM. Caller must * own rtc_lock ... and we won't worry about access during NMI. */ #define can_bank2 true static inline unsigned char cmos_read_bank2(unsigned char addr) { outb(addr, RTC_PORT(2)); return inb(RTC_PORT(3)); } static inline void cmos_write_bank2(unsigned char val, unsigned char addr) { outb(addr, RTC_PORT(2)); outb(val, RTC_PORT(3)); } #else #define can_bank2 false static inline unsigned char cmos_read_bank2(unsigned char addr) { return 0; } static inline void cmos_write_bank2(unsigned char val, unsigned char addr) { } #endif /*----------------------------------------------------------------*/ static int cmos_read_time(struct device *dev, struct rtc_time *t) { int ret; /* * If pm_trace abused the RTC for storage, set the timespec to 0, * which tells the caller that this RTC value is unusable. */ if (!pm_trace_rtc_valid()) return -EIO; ret = mc146818_get_time(t, 1000); if (ret < 0) { dev_err_ratelimited(dev, "unable to read current time\n"); return ret; } return 0; } static int cmos_set_time(struct device *dev, struct rtc_time *t) { /* NOTE: this ignores the issue whereby updating the seconds * takes effect exactly 500ms after we write the register. * (Also queueing and other delays before we get this far.) */ return mc146818_set_time(t); } struct cmos_read_alarm_callback_param { struct cmos_rtc *cmos; struct rtc_time *time; unsigned char rtc_control; }; static void cmos_read_alarm_callback(unsigned char __always_unused seconds, void *param_in) { struct cmos_read_alarm_callback_param *p = (struct cmos_read_alarm_callback_param *)param_in; struct rtc_time *time = p->time; time->tm_sec = CMOS_READ(RTC_SECONDS_ALARM); time->tm_min = CMOS_READ(RTC_MINUTES_ALARM); time->tm_hour = CMOS_READ(RTC_HOURS_ALARM); if (p->cmos->day_alrm) { /* ignore upper bits on readback per ACPI spec */ time->tm_mday = CMOS_READ(p->cmos->day_alrm) & 0x3f; if (!time->tm_mday) time->tm_mday = -1; if (p->cmos->mon_alrm) { time->tm_mon = CMOS_READ(p->cmos->mon_alrm); if (!time->tm_mon) time->tm_mon = -1; } } p->rtc_control = CMOS_READ(RTC_CONTROL); } static int cmos_read_alarm(struct device *dev, struct rtc_wkalrm *t) { struct cmos_rtc *cmos = dev_get_drvdata(dev); struct cmos_read_alarm_callback_param p = { .cmos = cmos, .time = &t->time, }; /* This not only a rtc_op, but also called directly */ if (!is_valid_irq(cmos->irq)) return -ETIMEDOUT; /* Basic alarms only support hour, minute, and seconds fields. * Some also support day and month, for alarms up to a year in * the future. */ /* Some Intel chipsets disconnect the alarm registers when the clock * update is in progress - during this time reads return bogus values * and writes may fail silently. See for example "7th Generation Intel® * Processor Family I/O for U/Y Platforms [...] Datasheet", section * 27.7.1 * * Use the mc146818_avoid_UIP() function to avoid this. */ if (!mc146818_avoid_UIP(cmos_read_alarm_callback, 10, &p)) return -EIO; if (!(p.rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { if (((unsigned)t->time.tm_sec) < 0x60) t->time.tm_sec = bcd2bin(t->time.tm_sec); else t->time.tm_sec = -1; if (((unsigned)t->time.tm_min) < 0x60) t->time.tm_min = bcd2bin(t->time.tm_min); else t->time.tm_min = -1; if (((unsigned)t->time.tm_hour) < 0x24) t->time.tm_hour = bcd2bin(t->time.tm_hour); else t->time.tm_hour = -1; if (cmos->day_alrm) { if (((unsigned)t->time.tm_mday) <= 0x31) t->time.tm_mday = bcd2bin(t->time.tm_mday); else t->time.tm_mday = -1; if (cmos->mon_alrm) { if (((unsigned)t->time.tm_mon) <= 0x12) t->time.tm_mon = bcd2bin(t->time.tm_mon)-1; else t->time.tm_mon = -1; } } } t->enabled = !!(p.rtc_control & RTC_AIE); t->pending = 0; return 0; } static void cmos_checkintr(struct cmos_rtc *cmos, unsigned char rtc_control) { unsigned char rtc_intr; /* NOTE after changing RTC_xIE bits we always read INTR_FLAGS; * allegedly some older rtcs need that to handle irqs properly */ rtc_intr = CMOS_READ(RTC_INTR_FLAGS); if (use_hpet_alarm()) return; rtc_intr &= (rtc_control & RTC_IRQMASK) | RTC_IRQF; if (is_intr(rtc_intr)) rtc_update_irq(cmos->rtc, 1, rtc_intr); } static void cmos_irq_enable(struct cmos_rtc *cmos, unsigned char mask) { unsigned char rtc_control; /* flush any pending IRQ status, notably for update irqs, * before we enable new IRQs */ rtc_control = CMOS_READ(RTC_CONTROL); cmos_checkintr(cmos, rtc_control); rtc_control |= mask; CMOS_WRITE(rtc_control, RTC_CONTROL); if (use_hpet_alarm()) hpet_set_rtc_irq_bit(mask); if ((mask & RTC_AIE) && cmos_use_acpi_alarm()) { if (cmos->wake_on) cmos->wake_on(cmos->dev); } cmos_checkintr(cmos, rtc_control); } static void cmos_irq_disable(struct cmos_rtc *cmos, unsigned char mask) { unsigned char rtc_control; rtc_control = CMOS_READ(RTC_CONTROL); rtc_control &= ~mask; CMOS_WRITE(rtc_control, RTC_CONTROL); if (use_hpet_alarm()) hpet_mask_rtc_irq_bit(mask); if ((mask & RTC_AIE) && cmos_use_acpi_alarm()) { if (cmos->wake_off) cmos->wake_off(cmos->dev); } cmos_checkintr(cmos, rtc_control); } static int cmos_validate_alarm(struct device *dev, struct rtc_wkalrm *t) { struct cmos_rtc *cmos = dev_get_drvdata(dev); struct rtc_time now; cmos_read_time(dev, &now); if (!cmos->day_alrm) { time64_t t_max_date; time64_t t_alrm; t_max_date = rtc_tm_to_time64(&now); t_max_date += 24 * 60 * 60 - 1; t_alrm = rtc_tm_to_time64(&t->time); if (t_alrm > t_max_date) { dev_err(dev, "Alarms can be up to one day in the future\n"); return -EINVAL; } } else if (!cmos->mon_alrm) { struct rtc_time max_date = now; time64_t t_max_date; time64_t t_alrm; int max_mday; if (max_date.tm_mon == 11) { max_date.tm_mon = 0; max_date.tm_year += 1; } else { max_date.tm_mon += 1; } max_mday = rtc_month_days(max_date.tm_mon, max_date.tm_year); if (max_date.tm_mday > max_mday) max_date.tm_mday = max_mday; t_max_date = rtc_tm_to_time64(&max_date); t_max_date -= 1; t_alrm = rtc_tm_to_time64(&t->time); if (t_alrm > t_max_date) { dev_err(dev, "Alarms can be up to one month in the future\n"); return -EINVAL; } } else { struct rtc_time max_date = now; time64_t t_max_date; time64_t t_alrm; int max_mday; max_date.tm_year += 1; max_mday = rtc_month_days(max_date.tm_mon, max_date.tm_year); if (max_date.tm_mday > max_mday) max_date.tm_mday = max_mday; t_max_date = rtc_tm_to_time64(&max_date); t_max_date -= 1; t_alrm = rtc_tm_to_time64(&t->time); if (t_alrm > t_max_date) { dev_err(dev, "Alarms can be up to one year in the future\n"); return -EINVAL; } } return 0; } struct cmos_set_alarm_callback_param { struct cmos_rtc *cmos; unsigned char mon, mday, hrs, min, sec; struct rtc_wkalrm *t; }; /* Note: this function may be executed by mc146818_avoid_UIP() more then * once */ static void cmos_set_alarm_callback(unsigned char __always_unused seconds, void *param_in) { struct cmos_set_alarm_callback_param *p = (struct cmos_set_alarm_callback_param *)param_in; /* next rtc irq must not be from previous alarm setting */ cmos_irq_disable(p->cmos, RTC_AIE); /* update alarm */ CMOS_WRITE(p->hrs, RTC_HOURS_ALARM); CMOS_WRITE(p->min, RTC_MINUTES_ALARM); CMOS_WRITE(p->sec, RTC_SECONDS_ALARM); /* the system may support an "enhanced" alarm */ if (p->cmos->day_alrm) { CMOS_WRITE(p->mday, p->cmos->day_alrm); if (p->cmos->mon_alrm) CMOS_WRITE(p->mon, p->cmos->mon_alrm); } if (use_hpet_alarm()) { /* * FIXME the HPET alarm glue currently ignores day_alrm * and mon_alrm ... */ hpet_set_alarm_time(p->t->time.tm_hour, p->t->time.tm_min, p->t->time.tm_sec); } if (p->t->enabled) cmos_irq_enable(p->cmos, RTC_AIE); } static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t) { struct cmos_rtc *cmos = dev_get_drvdata(dev); struct cmos_set_alarm_callback_param p = { .cmos = cmos, .t = t }; unsigned char rtc_control; int ret; /* This not only a rtc_op, but also called directly */ if (!is_valid_irq(cmos->irq)) return -EIO; ret = cmos_validate_alarm(dev, t); if (ret < 0) return ret; p.mon = t->time.tm_mon + 1; p.mday = t->time.tm_mday; p.hrs = t->time.tm_hour; p.min = t->time.tm_min; p.sec = t->time.tm_sec; spin_lock_irq(&rtc_lock); rtc_control = CMOS_READ(RTC_CONTROL); spin_unlock_irq(&rtc_lock); if (!(rtc_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { /* Writing 0xff means "don't care" or "match all". */ p.mon = (p.mon <= 12) ? bin2bcd(p.mon) : 0xff; p.mday = (p.mday >= 1 && p.mday <= 31) ? bin2bcd(p.mday) : 0xff; p.hrs = (p.hrs < 24) ? bin2bcd(p.hrs) : 0xff; p.min = (p.min < 60) ? bin2bcd(p.min) : 0xff; p.sec = (p.sec < 60) ? bin2bcd(p.sec) : 0xff; } /* * Some Intel chipsets disconnect the alarm registers when the clock * update is in progress - during this time writes fail silently. * * Use mc146818_avoid_UIP() to avoid this. */ if (!mc146818_avoid_UIP(cmos_set_alarm_callback, 10, &p)) return -ETIMEDOUT; cmos->alarm_expires = rtc_tm_to_time64(&t->time); return 0; } static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct cmos_rtc *cmos = dev_get_drvdata(dev); unsigned long flags; spin_lock_irqsave(&rtc_lock, flags); if (enabled) cmos_irq_enable(cmos, RTC_AIE); else cmos_irq_disable(cmos, RTC_AIE); spin_unlock_irqrestore(&rtc_lock, flags); return 0; } #if IS_ENABLED(CONFIG_RTC_INTF_PROC) static int cmos_procfs(struct device *dev, struct seq_file *seq) { struct cmos_rtc *cmos = dev_get_drvdata(dev); unsigned char rtc_control, valid; spin_lock_irq(&rtc_lock); rtc_control = CMOS_READ(RTC_CONTROL); valid = CMOS_READ(RTC_VALID); spin_unlock_irq(&rtc_lock); /* NOTE: at least ICH6 reports battery status using a different * (non-RTC) bit; and SQWE is ignored on many current systems. */ seq_printf(seq, "periodic_IRQ\t: %s\n" "update_IRQ\t: %s\n" "HPET_emulated\t: %s\n" // "square_wave\t: %s\n" "BCD\t\t: %s\n" "DST_enable\t: %s\n" "periodic_freq\t: %d\n" "batt_status\t: %s\n", (rtc_control & RTC_PIE) ? "yes" : "no", (rtc_control & RTC_UIE) ? "yes" : "no", use_hpet_alarm() ? "yes" : "no", // (rtc_control & RTC_SQWE) ? "yes" : "no", (rtc_control & RTC_DM_BINARY) ? "no" : "yes", (rtc_control & RTC_DST_EN) ? "yes" : "no", cmos->rtc->irq_freq, (valid & RTC_VRT) ? "okay" : "dead"); return 0; } #else #define cmos_procfs NULL #endif static const struct rtc_class_ops cmos_rtc_ops = { .read_time = cmos_read_time, .set_time = cmos_set_time, .read_alarm = cmos_read_alarm, .set_alarm = cmos_set_alarm, .proc = cmos_procfs, .alarm_irq_enable = cmos_alarm_irq_enable, }; /*----------------------------------------------------------------*/ /* * All these chips have at least 64 bytes of address space, shared by * RTC registers and NVRAM. Most of those bytes of NVRAM are used * by boot firmware. Modern chips have 128 or 256 bytes. */ #define NVRAM_OFFSET (RTC_REG_D + 1) static int cmos_nvram_read(void *priv, unsigned int off, void *val, size_t count) { unsigned char *buf = val; off += NVRAM_OFFSET; spin_lock_irq(&rtc_lock); for (; count; count--, off++) { if (off < 128) *buf++ = CMOS_READ(off); else if (can_bank2) *buf++ = cmos_read_bank2(off); else break; } spin_unlock_irq(&rtc_lock); return count ? -EIO : 0; } static int cmos_nvram_write(void *priv, unsigned int off, void *val, size_t count) { struct cmos_rtc *cmos = priv; unsigned char *buf = val; /* NOTE: on at least PCs and Ataris, the boot firmware uses a * checksum on part of the NVRAM data. That's currently ignored * here. If userspace is smart enough to know what fields of * NVRAM to update, updating checksums is also part of its job. */ off += NVRAM_OFFSET; spin_lock_irq(&rtc_lock); for (; count; count--, off++) { /* don't trash RTC registers */ if (off == cmos->day_alrm || off == cmos->mon_alrm || off == cmos->century) buf++; else if (off < 128) CMOS_WRITE(*buf++, off); else if (can_bank2) cmos_write_bank2(*buf++, off); else break; } spin_unlock_irq(&rtc_lock); return count ? -EIO : 0; } /*----------------------------------------------------------------*/ static struct cmos_rtc cmos_rtc; static irqreturn_t cmos_interrupt(int irq, void *p) { u8 irqstat; u8 rtc_control; spin_lock(&rtc_lock); /* When the HPET interrupt handler calls us, the interrupt * status is passed as arg1 instead of the irq number. But * always clear irq status, even when HPET is in the way. * * Note that HPET and RTC are almost certainly out of phase, * giving different IRQ status ... */ irqstat = CMOS_READ(RTC_INTR_FLAGS); rtc_control = CMOS_READ(RTC_CONTROL); if (use_hpet_alarm()) irqstat = (unsigned long)irq & 0xF0; /* If we were suspended, RTC_CONTROL may not be accurate since the * bios may have cleared it. */ if (!cmos_rtc.suspend_ctrl) irqstat &= (rtc_control & RTC_IRQMASK) | RTC_IRQF; else irqstat &= (cmos_rtc.suspend_ctrl & RTC_IRQMASK) | RTC_IRQF; /* All Linux RTC alarms should be treated as if they were oneshot. * Similar code may be needed in system wakeup paths, in case the * alarm woke the system. */ if (irqstat & RTC_AIE) { cmos_rtc.suspend_ctrl &= ~RTC_AIE; rtc_control &= ~RTC_AIE; CMOS_WRITE(rtc_control, RTC_CONTROL); if (use_hpet_alarm()) hpet_mask_rtc_irq_bit(RTC_AIE); CMOS_READ(RTC_INTR_FLAGS); } spin_unlock(&rtc_lock); if (is_intr(irqstat)) { rtc_update_irq(p, 1, irqstat); return IRQ_HANDLED; } else return IRQ_NONE; } #ifdef CONFIG_ACPI #include <linux/acpi.h> static u32 rtc_handler(void *context) { struct device *dev = context; struct cmos_rtc *cmos = dev_get_drvdata(dev); unsigned char rtc_control = 0; unsigned char rtc_intr; unsigned long flags; /* * Always update rtc irq when ACPI is used as RTC Alarm. * Or else, ACPI SCI is enabled during suspend/resume only, * update rtc irq in that case. */ if (cmos_use_acpi_alarm()) cmos_interrupt(0, (void *)cmos->rtc); else { /* Fix me: can we use cmos_interrupt() here as well? */ spin_lock_irqsave(&rtc_lock, flags); if (cmos_rtc.suspend_ctrl) rtc_control = CMOS_READ(RTC_CONTROL); if (rtc_control & RTC_AIE) { cmos_rtc.suspend_ctrl &= ~RTC_AIE; CMOS_WRITE(rtc_control, RTC_CONTROL); rtc_intr = CMOS_READ(RTC_INTR_FLAGS); rtc_update_irq(cmos->rtc, 1, rtc_intr); } spin_unlock_irqrestore(&rtc_lock, flags); } pm_wakeup_hard_event(dev); acpi_clear_event(ACPI_EVENT_RTC); acpi_disable_event(ACPI_EVENT_RTC, 0); return ACPI_INTERRUPT_HANDLED; } static void acpi_rtc_event_setup(struct device *dev) { if (acpi_disabled) return; acpi_install_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler, dev); /* * After the RTC handler is installed, the Fixed_RTC event should * be disabled. Only when the RTC alarm is set will it be enabled. */ acpi_clear_event(ACPI_EVENT_RTC); acpi_disable_event(ACPI_EVENT_RTC, 0); } static void acpi_rtc_event_cleanup(void) { if (acpi_disabled) return; acpi_remove_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler); } static void rtc_wake_on(struct device *dev) { acpi_clear_event(ACPI_EVENT_RTC); acpi_enable_event(ACPI_EVENT_RTC, 0); } static void rtc_wake_off(struct device *dev) { acpi_disable_event(ACPI_EVENT_RTC, 0); } #ifdef CONFIG_X86 static void use_acpi_alarm_quirks(void) { switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: if (dmi_get_bios_year() < 2015) return; break; case X86_VENDOR_AMD: case X86_VENDOR_HYGON: if (dmi_get_bios_year() < 2021) return; break; default: return; } if (!is_hpet_enabled()) return; use_acpi_alarm = true; } #else static inline void use_acpi_alarm_quirks(void) { } #endif static void acpi_cmos_wake_setup(struct device *dev) { if (acpi_disabled) return; use_acpi_alarm_quirks(); cmos_rtc.wake_on = rtc_wake_on; cmos_rtc.wake_off = rtc_wake_off; /* ACPI tables bug workaround. */ if (acpi_gbl_FADT.month_alarm && !acpi_gbl_FADT.day_alarm) { dev_dbg(dev, "bogus FADT month_alarm (%d)\n", acpi_gbl_FADT.month_alarm); acpi_gbl_FADT.month_alarm = 0; } cmos_rtc.day_alrm = acpi_gbl_FADT.day_alarm; cmos_rtc.mon_alrm = acpi_gbl_FADT.month_alarm; cmos_rtc.century = acpi_gbl_FADT.century; if (acpi_gbl_FADT.flags & ACPI_FADT_S4_RTC_WAKE) dev_info(dev, "RTC can wake from S4\n"); /* RTC always wakes from S1/S2/S3, and often S4/STD */ device_init_wakeup(dev, 1); } static void cmos_check_acpi_rtc_status(struct device *dev, unsigned char *rtc_control) { struct cmos_rtc *cmos = dev_get_drvdata(dev); acpi_event_status rtc_status; acpi_status status; if (acpi_gbl_FADT.flags & ACPI_FADT_FIXED_RTC) return; status = acpi_get_event_status(ACPI_EVENT_RTC, &rtc_status); if (ACPI_FAILURE(status)) { dev_err(dev, "Could not get RTC status\n"); } else if (rtc_status & ACPI_EVENT_FLAG_SET) { unsigned char mask; *rtc_control &= ~RTC_AIE; CMOS_WRITE(*rtc_control, RTC_CONTROL); mask = CMOS_READ(RTC_INTR_FLAGS); rtc_update_irq(cmos->rtc, 1, mask); } } #else /* !CONFIG_ACPI */ static inline void acpi_rtc_event_setup(struct device *dev) { } static inline void acpi_rtc_event_cleanup(void) { } static inline void acpi_cmos_wake_setup(struct device *dev) { } static inline void cmos_check_acpi_rtc_status(struct device *dev, unsigned char *rtc_control) { } #endif /* CONFIG_ACPI */ #ifdef CONFIG_PNP #define INITSECTION #else #define INITSECTION __init #endif #define SECS_PER_DAY (24 * 60 * 60) #define SECS_PER_MONTH (28 * SECS_PER_DAY) #define SECS_PER_YEAR (365 * SECS_PER_DAY) static int INITSECTION cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) { struct cmos_rtc_board_info *info = dev_get_platdata(dev); int retval = 0; unsigned char rtc_control; unsigned address_space; u32 flags = 0; struct nvmem_config nvmem_cfg = { .name = "cmos_nvram", .word_size = 1, .stride = 1, .reg_read = cmos_nvram_read, .reg_write = cmos_nvram_write, .priv = &cmos_rtc, }; /* there can be only one ... */ if (cmos_rtc.dev) return -EBUSY; if (!ports) return -ENODEV; /* Claim I/O ports ASAP, minimizing conflict with legacy driver. * * REVISIT non-x86 systems may instead use memory space resources * (needing ioremap etc), not i/o space resources like this ... */ if (RTC_IOMAPPED) ports = request_region(ports->start, resource_size(ports), driver_name); else ports = request_mem_region(ports->start, resource_size(ports), driver_name); if (!ports) { dev_dbg(dev, "i/o registers already in use\n"); return -EBUSY; } cmos_rtc.irq = rtc_irq; cmos_rtc.iomem = ports; /* Heuristic to deduce NVRAM size ... do what the legacy NVRAM * driver did, but don't reject unknown configs. Old hardware * won't address 128 bytes. Newer chips have multiple banks, * though they may not be listed in one I/O resource. */ #if defined(CONFIG_ATARI) address_space = 64; #elif defined(__i386__) || defined(__x86_64__) || defined(__arm__) \ || defined(__sparc__) || defined(__mips__) \ || defined(__powerpc__) address_space = 128; #else #warning Assuming 128 bytes of RTC+NVRAM address space, not 64 bytes. address_space = 128; #endif if (can_bank2 && ports->end > (ports->start + 1)) address_space = 256; /* For ACPI systems extension info comes from the FADT. On others, * board specific setup provides it as appropriate. Systems where * the alarm IRQ isn't automatically a wakeup IRQ (like ACPI, and * some almost-clones) can provide hooks to make that behave. * * Note that ACPI doesn't preclude putting these registers into * "extended" areas of the chip, including some that we won't yet * expect CMOS_READ and friends to handle. */ if (info) { if (info->flags) flags = info->flags; if (info->address_space) address_space = info->address_space; cmos_rtc.day_alrm = info->rtc_day_alarm; cmos_rtc.mon_alrm = info->rtc_mon_alarm; cmos_rtc.century = info->rtc_century; if (info->wake_on && info->wake_off) { cmos_rtc.wake_on = info->wake_on; cmos_rtc.wake_off = info->wake_off; } } else { acpi_cmos_wake_setup(dev); } if (cmos_rtc.day_alrm >= 128) cmos_rtc.day_alrm = 0; if (cmos_rtc.mon_alrm >= 128) cmos_rtc.mon_alrm = 0; if (cmos_rtc.century >= 128) cmos_rtc.century = 0; cmos_rtc.dev = dev; dev_set_drvdata(dev, &cmos_rtc); cmos_rtc.rtc = devm_rtc_allocate_device(dev); if (IS_ERR(cmos_rtc.rtc)) { retval = PTR_ERR(cmos_rtc.rtc); goto cleanup0; } if (cmos_rtc.mon_alrm) cmos_rtc.rtc->alarm_offset_max = SECS_PER_YEAR - 1; else if (cmos_rtc.day_alrm) cmos_rtc.rtc->alarm_offset_max = SECS_PER_MONTH - 1; else cmos_rtc.rtc->alarm_offset_max = SECS_PER_DAY - 1; rename_region(ports, dev_name(&cmos_rtc.rtc->dev)); if (!mc146818_does_rtc_work()) { dev_warn(dev, "broken or not accessible\n"); retval = -ENXIO; goto cleanup1; } spin_lock_irq(&rtc_lock); if (!(flags & CMOS_RTC_FLAGS_NOFREQ)) { /* force periodic irq to CMOS reset default of 1024Hz; * * REVISIT it's been reported that at least one x86_64 ALI * mobo doesn't use 32KHz here ... for portability we might * need to do something about other clock frequencies. */ cmos_rtc.rtc->irq_freq = 1024; if (use_hpet_alarm()) hpet_set_periodic_freq(cmos_rtc.rtc->irq_freq); CMOS_WRITE(RTC_REF_CLCK_32KHZ | 0x06, RTC_FREQ_SELECT); } /* disable irqs */ if (is_valid_irq(rtc_irq)) cmos_irq_disable(&cmos_rtc, RTC_PIE | RTC_AIE | RTC_UIE); rtc_control = CMOS_READ(RTC_CONTROL); spin_unlock_irq(&rtc_lock); if (is_valid_irq(rtc_irq) && !(rtc_control & RTC_24H)) { dev_warn(dev, "only 24-hr supported\n"); retval = -ENXIO; goto cleanup1; } if (use_hpet_alarm()) hpet_rtc_timer_init(); if (is_valid_irq(rtc_irq)) { irq_handler_t rtc_cmos_int_handler; if (use_hpet_alarm()) { rtc_cmos_int_handler = hpet_rtc_interrupt; retval = hpet_register_irq_handler(cmos_interrupt); if (retval) { hpet_mask_rtc_irq_bit(RTC_IRQMASK); dev_warn(dev, "hpet_register_irq_handler " " failed in rtc_init()."); goto cleanup1; } } else rtc_cmos_int_handler = cmos_interrupt; retval = request_irq(rtc_irq, rtc_cmos_int_handler, 0, dev_name(&cmos_rtc.rtc->dev), cmos_rtc.rtc); if (retval < 0) { dev_dbg(dev, "IRQ %d is already in use\n", rtc_irq); goto cleanup1; } } else { clear_bit(RTC_FEATURE_ALARM, cmos_rtc.rtc->features); } cmos_rtc.rtc->ops = &cmos_rtc_ops; retval = devm_rtc_register_device(cmos_rtc.rtc); if (retval) goto cleanup2; /* Set the sync offset for the periodic 11min update correct */ cmos_rtc.rtc->set_offset_nsec = NSEC_PER_SEC / 2; /* export at least the first block of NVRAM */ nvmem_cfg.size = address_space - NVRAM_OFFSET; devm_rtc_nvmem_register(cmos_rtc.rtc, &nvmem_cfg); /* * Everything has gone well so far, so by default register a handler for * the ACPI RTC fixed event. */ if (!info) acpi_rtc_event_setup(dev); dev_info(dev, "%s%s, %d bytes nvram%s\n", !is_valid_irq(rtc_irq) ? "no alarms" : cmos_rtc.mon_alrm ? "alarms up to one year" : cmos_rtc.day_alrm ? "alarms up to one month" : "alarms up to one day", cmos_rtc.century ? ", y3k" : "", nvmem_cfg.size, use_hpet_alarm() ? ", hpet irqs" : ""); return 0; cleanup2: if (is_valid_irq(rtc_irq)) free_irq(rtc_irq, cmos_rtc.rtc); cleanup1: cmos_rtc.dev = NULL; cleanup0: if (RTC_IOMAPPED) release_region(ports->start, resource_size(ports)); else release_mem_region(ports->start, resource_size(ports)); return retval; } static void cmos_do_shutdown(int rtc_irq) { spin_lock_irq(&rtc_lock); if (is_valid_irq(rtc_irq)) cmos_irq_disable(&cmos_rtc, RTC_IRQMASK); spin_unlock_irq(&rtc_lock); } static void cmos_do_remove(struct device *dev) { struct cmos_rtc *cmos = dev_get_drvdata(dev); struct resource *ports; cmos_do_shutdown(cmos->irq); if (is_valid_irq(cmos->irq)) { free_irq(cmos->irq, cmos->rtc); if (use_hpet_alarm()) hpet_unregister_irq_handler(cmos_interrupt); } if (!dev_get_platdata(dev)) acpi_rtc_event_cleanup(); cmos->rtc = NULL; ports = cmos->iomem; if (RTC_IOMAPPED) release_region(ports->start, resource_size(ports)); else release_mem_region(ports->start, resource_size(ports)); cmos->iomem = NULL; cmos->dev = NULL; } static int cmos_aie_poweroff(struct device *dev) { struct cmos_rtc *cmos = dev_get_drvdata(dev); struct rtc_time now; time64_t t_now; int retval = 0; unsigned char rtc_control; if (!cmos->alarm_expires) return -EINVAL; spin_lock_irq(&rtc_lock); rtc_control = CMOS_READ(RTC_CONTROL); spin_unlock_irq(&rtc_lock); /* We only care about the situation where AIE is disabled. */ if (rtc_control & RTC_AIE) return -EBUSY; cmos_read_time(dev, &now); t_now = rtc_tm_to_time64(&now); /* * When enabling "RTC wake-up" in BIOS setup, the machine reboots * automatically right after shutdown on some buggy boxes. * This automatic rebooting issue won't happen when the alarm * time is larger than now+1 seconds. * * If the alarm time is equal to now+1 seconds, the issue can be * prevented by cancelling the alarm. */ if (cmos->alarm_expires == t_now + 1) { struct rtc_wkalrm alarm; /* Cancel the AIE timer by configuring the past time. */ rtc_time64_to_tm(t_now - 1, &alarm.time); alarm.enabled = 0; retval = cmos_set_alarm(dev, &alarm); } else if (cmos->alarm_expires > t_now + 1) { retval = -EBUSY; } return retval; } static int cmos_suspend(struct device *dev) { struct cmos_rtc *cmos = dev_get_drvdata(dev); unsigned char tmp; /* only the alarm might be a wakeup event source */ spin_lock_irq(&rtc_lock); cmos->suspend_ctrl = tmp = CMOS_READ(RTC_CONTROL); if (tmp & (RTC_PIE|RTC_AIE|RTC_UIE)) { unsigned char mask; if (device_may_wakeup(dev)) mask = RTC_IRQMASK & ~RTC_AIE; else mask = RTC_IRQMASK; tmp &= ~mask; CMOS_WRITE(tmp, RTC_CONTROL); if (use_hpet_alarm()) hpet_mask_rtc_irq_bit(mask); cmos_checkintr(cmos, tmp); } spin_unlock_irq(&rtc_lock); if ((tmp & RTC_AIE) && !cmos_use_acpi_alarm()) { cmos->enabled_wake = 1; if (cmos->wake_on) cmos->wake_on(dev); else enable_irq_wake(cmos->irq); } memset(&cmos->saved_wkalrm, 0, sizeof(struct rtc_wkalrm)); cmos_read_alarm(dev, &cmos->saved_wkalrm); dev_dbg(dev, "suspend%s, ctrl %02x\n", (tmp & RTC_AIE) ? ", alarm may wake" : "", tmp); return 0; } /* We want RTC alarms to wake us from e.g. ACPI G2/S5 "soft off", even * after a detour through G3 "mechanical off", although the ACPI spec * says wakeup should only work from G1/S4 "hibernate". To most users, * distinctions between S4 and S5 are pointless. So when the hardware * allows, don't draw that distinction. */ static inline int cmos_poweroff(struct device *dev) { if (!IS_ENABLED(CONFIG_PM)) return -ENOSYS; return cmos_suspend(dev); } static void cmos_check_wkalrm(struct device *dev) { struct cmos_rtc *cmos = dev_get_drvdata(dev); struct rtc_wkalrm current_alarm; time64_t t_now; time64_t t_current_expires; time64_t t_saved_expires; struct rtc_time now; /* Check if we have RTC Alarm armed */ if (!(cmos->suspend_ctrl & RTC_AIE)) return; cmos_read_time(dev, &now); t_now = rtc_tm_to_time64(&now); /* * ACPI RTC wake event is cleared after resume from STR, * ACK the rtc irq here */ if (t_now >= cmos->alarm_expires && cmos_use_acpi_alarm()) { local_irq_disable(); cmos_interrupt(0, (void *)cmos->rtc); local_irq_enable(); return; } memset(¤t_alarm, 0, sizeof(struct rtc_wkalrm)); cmos_read_alarm(dev, ¤t_alarm); t_current_expires = rtc_tm_to_time64(¤t_alarm.time); t_saved_expires = rtc_tm_to_time64(&cmos->saved_wkalrm.time); if (t_current_expires != t_saved_expires || cmos->saved_wkalrm.enabled != current_alarm.enabled) { cmos_set_alarm(dev, &cmos->saved_wkalrm); } } static int __maybe_unused cmos_resume(struct device *dev) { struct cmos_rtc *cmos = dev_get_drvdata(dev); unsigned char tmp; if (cmos->enabled_wake && !cmos_use_acpi_alarm()) { if (cmos->wake_off) cmos->wake_off(dev); else disable_irq_wake(cmos->irq); cmos->enabled_wake = 0; } /* The BIOS might have changed the alarm, restore it */ cmos_check_wkalrm(dev); spin_lock_irq(&rtc_lock); tmp = cmos->suspend_ctrl; cmos->suspend_ctrl = 0; /* re-enable any irqs previously active */ if (tmp & RTC_IRQMASK) { unsigned char mask; if (device_may_wakeup(dev) && use_hpet_alarm()) hpet_rtc_timer_init(); do { CMOS_WRITE(tmp, RTC_CONTROL); if (use_hpet_alarm()) hpet_set_rtc_irq_bit(tmp & RTC_IRQMASK); mask = CMOS_READ(RTC_INTR_FLAGS); mask &= (tmp & RTC_IRQMASK) | RTC_IRQF; if (!use_hpet_alarm() || !is_intr(mask)) break; /* force one-shot behavior if HPET blocked * the wake alarm's irq */ rtc_update_irq(cmos->rtc, 1, mask); tmp &= ~RTC_AIE; hpet_mask_rtc_irq_bit(RTC_AIE); } while (mask & RTC_AIE); if (tmp & RTC_AIE) cmos_check_acpi_rtc_status(dev, &tmp); } spin_unlock_irq(&rtc_lock); dev_dbg(dev, "resume, ctrl %02x\n", tmp); return 0; } static SIMPLE_DEV_PM_OPS(cmos_pm_ops, cmos_suspend, cmos_resume); /*----------------------------------------------------------------*/ /* On non-x86 systems, a "CMOS" RTC lives most naturally on platform_bus. * ACPI systems always list these as PNPACPI devices, and pre-ACPI PCs * probably list them in similar PNPBIOS tables; so PNP is more common. * * We don't use legacy "poke at the hardware" probing. Ancient PCs that * predate even PNPBIOS should set up platform_bus devices. */ #ifdef CONFIG_PNP #include <linux/pnp.h> static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) { int irq; if (pnp_port_start(pnp, 0) == 0x70 && !pnp_irq_valid(pnp, 0)) { irq = 0; #ifdef CONFIG_X86 /* Some machines contain a PNP entry for the RTC, but * don't define the IRQ. It should always be safe to * hardcode it on systems with a legacy PIC. */ if (nr_legacy_irqs()) irq = RTC_IRQ; #endif } else { irq = pnp_irq(pnp, 0); } return cmos_do_probe(&pnp->dev, pnp_get_resource(pnp, IORESOURCE_IO, 0), irq); } static void cmos_pnp_remove(struct pnp_dev *pnp) { cmos_do_remove(&pnp->dev); } static void cmos_pnp_shutdown(struct pnp_dev *pnp) { struct device *dev = &pnp->dev; struct cmos_rtc *cmos = dev_get_drvdata(dev); if (system_state == SYSTEM_POWER_OFF) { int retval = cmos_poweroff(dev); if (cmos_aie_poweroff(dev) < 0 && !retval) return; } cmos_do_shutdown(cmos->irq); } static const struct pnp_device_id rtc_ids[] = { { .id = "PNP0b00", }, { .id = "PNP0b01", }, { .id = "PNP0b02", }, { }, }; MODULE_DEVICE_TABLE(pnp, rtc_ids); static struct pnp_driver cmos_pnp_driver = { .name = driver_name, .id_table = rtc_ids, .probe = cmos_pnp_probe, .remove = cmos_pnp_remove, .shutdown = cmos_pnp_shutdown, /* flag ensures resume() gets called, and stops syslog spam */ .flags = PNP_DRIVER_RES_DO_NOT_CHANGE, .driver = { .pm = &cmos_pm_ops, }, }; #endif /* CONFIG_PNP */ #ifdef CONFIG_OF static const struct of_device_id of_cmos_match[] = { { .compatible = "motorola,mc146818", }, { }, }; MODULE_DEVICE_TABLE(of, of_cmos_match); static __init void cmos_of_init(struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; const __be32 *val; if (!node) return; val = of_get_property(node, "ctrl-reg", NULL); if (val) CMOS_WRITE(be32_to_cpup(val), RTC_CONTROL); val = of_get_property(node, "freq-reg", NULL); if (val) CMOS_WRITE(be32_to_cpup(val), RTC_FREQ_SELECT); } #else static inline void cmos_of_init(struct platform_device *pdev) {} #endif /*----------------------------------------------------------------*/ /* Platform setup should have set up an RTC device, when PNP is * unavailable ... this could happen even on (older) PCs. */ static int __init cmos_platform_probe(struct platform_device *pdev) { struct resource *resource; int irq; cmos_of_init(pdev); if (RTC_IOMAPPED) resource = platform_get_resource(pdev, IORESOURCE_IO, 0); else resource = platform_get_resource(pdev, IORESOURCE_MEM, 0); irq = platform_get_irq(pdev, 0); if (irq < 0) irq = -1; return cmos_do_probe(&pdev->dev, resource, irq); } static void cmos_platform_remove(struct platform_device *pdev) { cmos_do_remove(&pdev->dev); } static void cmos_platform_shutdown(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct cmos_rtc *cmos = dev_get_drvdata(dev); if (system_state == SYSTEM_POWER_OFF) { int retval = cmos_poweroff(dev); if (cmos_aie_poweroff(dev) < 0 && !retval) return; } cmos_do_shutdown(cmos->irq); } /* work with hotplug and coldplug */ MODULE_ALIAS("platform:rtc_cmos"); static struct platform_driver cmos_platform_driver = { .remove_new = cmos_platform_remove, .shutdown = cmos_platform_shutdown, .driver = { .name = driver_name, .pm = &cmos_pm_ops, .of_match_table = of_match_ptr(of_cmos_match), } }; #ifdef CONFIG_PNP static bool pnp_driver_registered; #endif static bool platform_driver_registered; static int __init cmos_init(void) { int retval = 0; #ifdef CONFIG_PNP retval = pnp_register_driver(&cmos_pnp_driver); if (retval == 0) pnp_driver_registered = true; #endif if (!cmos_rtc.dev) { retval = platform_driver_probe(&cmos_platform_driver, cmos_platform_probe); if (retval == 0) platform_driver_registered = true; } if (retval == 0) return 0; #ifdef CONFIG_PNP if (pnp_driver_registered) pnp_unregister_driver(&cmos_pnp_driver); #endif return retval; } module_init(cmos_init); static void __exit cmos_exit(void) { #ifdef CONFIG_PNP if (pnp_driver_registered) pnp_unregister_driver(&cmos_pnp_driver); #endif if (platform_driver_registered) platform_driver_unregister(&cmos_platform_driver); } module_exit(cmos_exit); MODULE_AUTHOR("David Brownell"); MODULE_DESCRIPTION("Driver for PC-style 'CMOS' RTCs"); MODULE_LICENSE("GPL"); |
| 572 14 183 420 57 457 1455 99 1 46 1 1217 2439 65 121 41 498 49 146 102 44 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 | // SPDX-License-Identifier: GPL-2.0+ /* * ext4_jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 * * Copyright 1998--1999 Red Hat corp --- All Rights Reserved * * Ext4-specific journaling extensions. */ #ifndef _EXT4_JBD2_H #define _EXT4_JBD2_H #include <linux/fs.h> #include <linux/jbd2.h> #include "ext4.h" #define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) /* Define the number of blocks we need to account to a transaction to * modify one block of data. * * We may have to touch one inode, one bitmap buffer, up to three * indirection blocks, the group and superblock summaries, and the data * block to complete the transaction. * * For extents-enabled fs we may have to allocate and modify up to * 5 levels of tree, data block (for each of these we need bitmap + group * summaries), root which is stored in the inode, sb */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ (ext4_has_feature_extents(sb) ? 20U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode * and the superblock, which are already accounted for. */ #define EXT4_XATTR_TRANS_BLOCKS 6U /* Define the minimum size for a transaction which modifies data. This * needs to take into account the fact that we may end up modifying two * quota files too (one for the group, one for the user quota). The * superblock only gets updated once, of course, so don't bother * counting that again for the quota updates. */ #define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ EXT4_XATTR_TRANS_BLOCKS - 2 + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* * Define the number of metadata blocks we need to account to modify data. * * This include super block, inode block, quota blocks and xattr blocks */ #define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* Define an arbitrary limit for the amount of data we will anticipate * writing to any given transaction. For unbounded transactions such as * write(2) and truncate(2) we can write more than this, but we always * start off at the maximum transaction size and grow the transaction * optimistically as we go. */ #define EXT4_MAX_TRANS_DATA 64U /* We break up a large truncate or write transaction once the handle's * buffer credits gets this low, we need either to extend the * transaction or to start a new one. Reserve enough space here for * inode, bitmap, superblock, group and indirection updates for at least * one block, plus two quota updates. Quota allocations are not * needed. */ #define EXT4_RESERVE_TRANS_BLOCKS 12U /* * Number of credits needed if we need to insert an entry into a * directory. For each new index block, we need 4 blocks (old index * block, new index block, bitmap block, bg summary). For normal * htree directories there are 2 levels; if the largedir feature * enabled it's 3 levels. */ #define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ #define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_INIT_REWRITE) : 0) #define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0 #endif #define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb)) #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) /* * Ext4 handle operation types -- for logging purposes */ #define EXT4_HT_MISC 0 #define EXT4_HT_INODE 1 #define EXT4_HT_WRITE_PAGE 2 #define EXT4_HT_MAP_BLOCKS 3 #define EXT4_HT_DIR 4 #define EXT4_HT_TRUNCATE 5 #define EXT4_HT_QUOTA 6 #define EXT4_HT_RESIZE 7 #define EXT4_HT_MIGRATE 8 #define EXT4_HT_MOVE_EXTENTS 9 #define EXT4_HT_XATTR 10 #define EXT4_HT_EXT_CONVERT 11 #define EXT4_HT_MAX 12 /** * struct ext4_journal_cb_entry - Base structure for callback information. * * This struct is a 'seed' structure for a using with your own callback * structs. If you are using callbacks you must allocate one of these * or another struct of your own definition which has this struct * as it's first element and pass it to ext4_journal_callback_add(). */ struct ext4_journal_cb_entry { /* list information for other callbacks attached to the same handle */ struct list_head jce_list; /* Function to call with this callback structure */ void (*jce_func)(struct super_block *sb, struct ext4_journal_cb_entry *jce, int error); /* user data goes here */ }; /** * ext4_journal_callback_add: add a function to call after transaction commit * @handle: active journal transaction handle to register callback on * @func: callback function to call after the transaction has committed: * @sb: superblock of current filesystem for transaction * @jce: returned journal callback data * @rc: journal state at commit (0 = transaction committed properly) * @jce: journal callback data (internal and function private data struct) * * The registered function will be called in the context of the journal thread * after the transaction for which the handle was created has completed. * * No locks are held when the callback function is called, so it is safe to * call blocking functions from within the callback, but the callback should * not block or run for too long, or the filesystem will be blocked waiting for * the next transaction to commit. No journaling functions can be used, or * there is a risk of deadlock. * * There is no guaranteed calling order of multiple registered callbacks on * the same transaction. */ static inline void _ext4_journal_callback_add(handle_t *handle, struct ext4_journal_cb_entry *jce) { /* Add the jce to transaction's private list */ list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list); } static inline void ext4_journal_callback_add(handle_t *handle, void (*func)(struct super_block *sb, struct ext4_journal_cb_entry *jce, int rc), struct ext4_journal_cb_entry *jce) { struct ext4_sb_info *sbi = EXT4_SB(handle->h_transaction->t_journal->j_private); /* Add the jce to transaction's private list */ jce->jce_func = func; spin_lock(&sbi->s_md_lock); _ext4_journal_callback_add(handle, jce); spin_unlock(&sbi->s_md_lock); } /** * ext4_journal_callback_del: delete a registered callback * @handle: active journal transaction handle on which callback was registered * @jce: registered journal callback entry to unregister * Return true if object was successfully removed */ static inline bool ext4_journal_callback_try_del(handle_t *handle, struct ext4_journal_cb_entry *jce) { bool deleted; struct ext4_sb_info *sbi = EXT4_SB(handle->h_transaction->t_journal->j_private); spin_lock(&sbi->s_md_lock); deleted = !list_empty(&jce->jce_list); list_del_init(&jce->jce_list); spin_unlock(&sbi->s_md_lock); return deleted; } int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); /* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); #define ext4_mark_inode_dirty(__h, __i) \ __ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__) int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, const char *func, unsigned int line); int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc); /* * Wrapper functions with which ext4 calls into JBD. */ int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_forget(const char *where, unsigned int line, handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr); int __ext4_journal_get_create_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh); #define ext4_journal_get_write_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \ __ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \ (bh), (block_nr)) #define ext4_journal_get_create_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_create_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096) /* Note: Do not use this for NULL handles. This is only to determine if * a properly allocated handle is using a journal or not. */ static inline int ext4_handle_valid(handle_t *handle) { if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT) return 0; return 1; } static inline void ext4_handle_sync(handle_t *handle) { if (ext4_handle_valid(handle)) handle->h_sync = 1; } static inline int ext4_handle_is_aborted(handle_t *handle) { if (ext4_handle_valid(handle)) return is_handle_aborted(handle); return 0; } static inline int ext4_free_metadata_revoke_credits(struct super_block *sb, int blocks) { /* Freeing each metadata block can result in freeing one cluster */ return blocks * EXT4_SB(sb)->s_cluster_ratio; } static inline int ext4_trans_default_revoke_credits(struct super_block *sb) { return ext4_free_metadata_revoke_credits(sb, 8); } #define ext4_journal_start_sb(sb, type, nblocks) \ __ext4_journal_start_sb(NULL, (sb), __LINE__, (type), (nblocks), 0,\ ext4_trans_default_revoke_credits(sb)) #define ext4_journal_start(inode, type, nblocks) \ __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0, \ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\ __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \ __ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \ (revoke_creds)) static inline handle_t *__ext4_journal_start(struct inode *inode, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds) { return __ext4_journal_start_sb(inode, inode->i_sb, line, type, blocks, rsv_blocks, revoke_creds); } #define ext4_journal_stop(handle) \ __ext4_journal_stop(__func__, __LINE__, (handle)) #define ext4_journal_start_reserved(handle, type) \ __ext4_journal_start_reserved((handle), __LINE__, (type)) handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, int type); static inline handle_t *ext4_journal_current_handle(void) { return journal_current_handle(); } static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2_journal_extend(handle, nblocks, revoke); return 0; } static inline int ext4_journal_restart(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS); return 0; } int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, int extend_cred, int revoke_cred); /* * Ensure @handle has at least @check_creds credits available. If not, * transaction will be extended or restarted to contain at least @extend_cred * credits. Before restarting transaction @fn is executed to allow for cleanup * before the transaction is restarted. * * The return value is < 0 in case of error, 0 in case the handle has enough * credits or transaction extension succeeded, 1 in case transaction had to be * restarted. */ #define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred, \ revoke_cred, fn) \ ({ \ __label__ __ensure_end; \ int err = __ext4_journal_ensure_credits((handle), (check_cred), \ (extend_cred), (revoke_cred)); \ \ if (err <= 0) \ goto __ensure_end; \ err = (fn); \ if (err < 0) \ goto __ensure_end; \ err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \ if (err == 0) \ err = 1; \ __ensure_end: \ err; \ }) /* * Ensure given handle has at least requested amount of credits available, * possibly restarting transaction if needed. We also make sure the transaction * has space for at least ext4_trans_default_revoke_credits(sb) revoke records * as freeing one or two blocks is very common pattern and requesting this is * very cheap. */ static inline int ext4_journal_ensure_credits(handle_t *handle, int credits, int revoke_creds) { return ext4_journal_ensure_credits_fn(handle, credits, credits, revoke_creds, 0); } static inline int ext4_journal_blocks_per_page(struct inode *inode) { if (EXT4_JOURNAL(inode) != NULL) return jbd2_journal_blocks_per_page(inode); return 0; } static inline int ext4_journal_force_commit(journal_t *journal) { if (journal) return jbd2_journal_force_commit(journal); return 0; } static inline int ext4_jbd2_inode_add_write(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_write(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline int ext4_jbd2_inode_add_wait(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_wait(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline void ext4_update_inode_fsync_trans(handle_t *handle, struct inode *inode, int datasync) { struct ext4_inode_info *ei = EXT4_I(inode); if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) { ei->i_sync_tid = handle->h_transaction->t_tid; if (datasync) ei->i_datasync_tid = handle->h_transaction->t_tid; } } /* super.c */ int ext4_force_commit(struct super_block *sb); /* * Ext4 inode journal modes */ #define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */ #define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */ #define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */ int ext4_inode_journal_mode(struct inode *inode); static inline int ext4_should_journal_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE; } static inline int ext4_should_order_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE; } static inline int ext4_should_writeback_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE; } static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks) { if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) return 0; if (!ext4_should_journal_data(inode)) return 0; /* * Data blocks in one extent are contiguous, just account for partial * clusters at extent boundaries */ return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1); } /* * This function controls whether or not we should try to go down the * dioread_nolock code paths, which makes it safe to avoid taking * i_rwsem for direct I/O reads. This only works for extent-based * files, and it doesn't work if data journaling is enabled, since the * dioread_nolock code uses b_private to pass information back to the * I/O completion handler, and this conflicts with the jbd's use of * b_private. */ static inline int ext4_should_dioread_nolock(struct inode *inode) { if (!test_opt(inode->i_sb, DIOREAD_NOLOCK)) return 0; if (!S_ISREG(inode->i_mode)) return 0; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return 0; if (ext4_should_journal_data(inode)) return 0; /* temporary fix to prevent generic/422 test failures */ if (!test_opt(inode->i_sb, DELALLOC)) return 0; return 1; } #endif /* _EXT4_JBD2_H */ |
| 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_QUEUE_H #define _NF_QUEUE_H #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/jhash.h> #include <linux/netfilter.h> #include <linux/skbuff.h> /* Each queued (to userspace) skbuff has one of these. */ struct nf_queue_entry { struct list_head list; struct sk_buff *skb; unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct net_device *physin; struct net_device *physout; #endif struct nf_hook_state state; u16 size; /* sizeof(entry) + saved route keys */ /* extra space to store route keys */ }; #define nf_queue_entry_reroute(x) ((void *)x + sizeof(struct nf_queue_entry)) /* Packet queuing */ struct nf_queue_handler { int (*outfn)(struct nf_queue_entry *entry, unsigned int queuenum); void (*nf_hook_drop)(struct net *net); }; void nf_register_queue_handler(const struct nf_queue_handler *qh); void nf_unregister_queue_handler(void); bool nf_queue_entry_get_refs(struct nf_queue_entry *entry); void nf_queue_entry_free(struct nf_queue_entry *entry); static inline void init_hashrandom(u32 *jhash_initval) { while (*jhash_initval == 0) *jhash_initval = get_random_u32(); } static inline u32 hash_v4(const struct iphdr *iph, u32 initval) { /* packets in either direction go into same queue */ if ((__force u32)iph->saddr < (__force u32)iph->daddr) return jhash_3words((__force u32)iph->saddr, (__force u32)iph->daddr, iph->protocol, initval); return jhash_3words((__force u32)iph->daddr, (__force u32)iph->saddr, iph->protocol, initval); } static inline u32 hash_v6(const struct ipv6hdr *ip6h, u32 initval) { u32 a, b, c; if ((__force u32)ip6h->saddr.s6_addr32[3] < (__force u32)ip6h->daddr.s6_addr32[3]) { a = (__force u32) ip6h->saddr.s6_addr32[3]; b = (__force u32) ip6h->daddr.s6_addr32[3]; } else { b = (__force u32) ip6h->saddr.s6_addr32[3]; a = (__force u32) ip6h->daddr.s6_addr32[3]; } if ((__force u32)ip6h->saddr.s6_addr32[1] < (__force u32)ip6h->daddr.s6_addr32[1]) c = (__force u32) ip6h->saddr.s6_addr32[1]; else c = (__force u32) ip6h->daddr.s6_addr32[1]; return jhash_3words(a, b, c, initval); } static inline u32 hash_bridge(const struct sk_buff *skb, u32 initval) { struct ipv6hdr *ip6h, _ip6h; struct iphdr *iph, _iph; switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), &_iph); if (iph) return hash_v4(iph, initval); break; case htons(ETH_P_IPV6): ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h), &_ip6h); if (ip6h) return hash_v6(ip6h, initval); break; } return 0; } static inline u32 nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family, u32 initval) { switch (family) { case NFPROTO_IPV4: queue += reciprocal_scale(hash_v4(ip_hdr(skb), initval), queues_total); break; case NFPROTO_IPV6: queue += reciprocal_scale(hash_v6(ipv6_hdr(skb), initval), queues_total); break; case NFPROTO_BRIDGE: queue += reciprocal_scale(hash_bridge(skb, initval), queues_total); break; } return queue; } int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, unsigned int index, unsigned int verdict); #endif /* _NF_QUEUE_H */ |
| 125 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2011 Instituto Nokia de Tecnologia * Copyright (C) 2014 Marvell International Ltd. * * Authors: * Lauro Ramos Venancio <lauro.venancio@openbossa.org> * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> */ #ifndef __NET_NFC_H #define __NET_NFC_H #include <linux/nfc.h> #include <linux/device.h> #include <linux/skbuff.h> #define nfc_dbg(dev, fmt, ...) dev_dbg((dev), "NFC: " fmt, ##__VA_ARGS__) #define nfc_info(dev, fmt, ...) dev_info((dev), "NFC: " fmt, ##__VA_ARGS__) #define nfc_err(dev, fmt, ...) dev_err((dev), "NFC: " fmt, ##__VA_ARGS__) struct nfc_phy_ops { int (*write)(void *dev_id, struct sk_buff *skb); int (*enable)(void *dev_id); void (*disable)(void *dev_id); }; struct nfc_dev; /** * data_exchange_cb_t - Definition of nfc_data_exchange callback * * @context: nfc_data_exchange cb_context parameter * @skb: response data * @err: If an error has occurred during data exchange, it is the * error number. Zero means no error. * * When a rx or tx package is lost or corrupted or the target gets out * of the operating field, err is -EIO. */ typedef void (*data_exchange_cb_t)(void *context, struct sk_buff *skb, int err); typedef void (*se_io_cb_t)(void *context, u8 *apdu, size_t apdu_len, int err); struct nfc_target; struct nfc_ops { int (*dev_up)(struct nfc_dev *dev); int (*dev_down)(struct nfc_dev *dev); int (*start_poll)(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols); void (*stop_poll)(struct nfc_dev *dev); int (*dep_link_up)(struct nfc_dev *dev, struct nfc_target *target, u8 comm_mode, u8 *gb, size_t gb_len); int (*dep_link_down)(struct nfc_dev *dev); int (*activate_target)(struct nfc_dev *dev, struct nfc_target *target, u32 protocol); void (*deactivate_target)(struct nfc_dev *dev, struct nfc_target *target, u8 mode); int (*im_transceive)(struct nfc_dev *dev, struct nfc_target *target, struct sk_buff *skb, data_exchange_cb_t cb, void *cb_context); int (*tm_send)(struct nfc_dev *dev, struct sk_buff *skb); int (*check_presence)(struct nfc_dev *dev, struct nfc_target *target); int (*fw_download)(struct nfc_dev *dev, const char *firmware_name); /* Secure Element API */ int (*discover_se)(struct nfc_dev *dev); int (*enable_se)(struct nfc_dev *dev, u32 se_idx); int (*disable_se)(struct nfc_dev *dev, u32 se_idx); int (*se_io) (struct nfc_dev *dev, u32 se_idx, u8 *apdu, size_t apdu_length, se_io_cb_t cb, void *cb_context); }; #define NFC_TARGET_IDX_ANY -1 #define NFC_MAX_GT_LEN 48 #define NFC_ATR_RES_GT_OFFSET 15 #define NFC_ATR_REQ_GT_OFFSET 14 /** * struct nfc_target - NFC target description * * @sens_res: 2 bytes describing the target SENS_RES response, if the target * is a type A one. The %sens_res most significant byte must be byte 2 * as described by the NFC Forum digital specification (i.e. the platform * configuration one) while %sens_res least significant byte is byte 1. */ struct nfc_target { u32 idx; u32 supported_protocols; u16 sens_res; u8 sel_res; u8 nfcid1_len; u8 nfcid1[NFC_NFCID1_MAXSIZE]; u8 nfcid2_len; u8 nfcid2[NFC_NFCID2_MAXSIZE]; u8 sensb_res_len; u8 sensb_res[NFC_SENSB_RES_MAXSIZE]; u8 sensf_res_len; u8 sensf_res[NFC_SENSF_RES_MAXSIZE]; u8 hci_reader_gate; u8 logical_idx; u8 is_iso15693; u8 iso15693_dsfid; u8 iso15693_uid[NFC_ISO15693_UID_MAXSIZE]; }; /** * nfc_se - A structure for NFC accessible secure elements. * * @idx: The secure element index. User space will enable or * disable a secure element by its index. * @type: The secure element type. It can be SE_UICC or * SE_EMBEDDED. * @state: The secure element state, either enabled or disabled. * */ struct nfc_se { struct list_head list; u32 idx; u16 type; u16 state; }; /** * nfc_evt_transaction - A struct for NFC secure element event transaction. * * @aid: The application identifier triggering the event * * @aid_len: The application identifier length [5:16] * * @params: The application parameters transmitted during the transaction * * @params_len: The applications parameters length [0:255] * */ #define NFC_MIN_AID_LENGTH 5 #define NFC_MAX_AID_LENGTH 16 #define NFC_MAX_PARAMS_LENGTH 255 #define NFC_EVT_TRANSACTION_AID_TAG 0x81 #define NFC_EVT_TRANSACTION_PARAMS_TAG 0x82 struct nfc_evt_transaction { u32 aid_len; u8 aid[NFC_MAX_AID_LENGTH]; u8 params_len; u8 params[]; } __packed; struct nfc_genl_data { u32 poll_req_portid; struct mutex genl_data_mutex; }; struct nfc_vendor_cmd { __u32 vendor_id; __u32 subcmd; int (*doit)(struct nfc_dev *dev, void *data, size_t data_len); }; struct nfc_dev { int idx; u32 target_next_idx; struct nfc_target *targets; int n_targets; int targets_generation; struct device dev; bool dev_up; bool fw_download_in_progress; u8 rf_mode; bool polling; struct nfc_target *active_target; bool dep_link_up; struct nfc_genl_data genl_data; u32 supported_protocols; struct list_head secure_elements; int tx_headroom; int tx_tailroom; struct timer_list check_pres_timer; struct work_struct check_pres_work; bool shutting_down; struct rfkill *rfkill; const struct nfc_vendor_cmd *vendor_cmds; int n_vendor_cmds; const struct nfc_ops *ops; struct genl_info *cur_cmd_info; }; #define to_nfc_dev(_dev) container_of(_dev, struct nfc_dev, dev) extern const struct class nfc_class; struct nfc_dev *nfc_allocate_device(const struct nfc_ops *ops, u32 supported_protocols, int tx_headroom, int tx_tailroom); /** * nfc_free_device - free nfc device * * @dev: The nfc device to free */ static inline void nfc_free_device(struct nfc_dev *dev) { put_device(&dev->dev); } int nfc_register_device(struct nfc_dev *dev); void nfc_unregister_device(struct nfc_dev *dev); /** * nfc_set_parent_dev - set the parent device * * @nfc_dev: The nfc device whose parent is being set * @dev: The parent device */ static inline void nfc_set_parent_dev(struct nfc_dev *nfc_dev, struct device *dev) { nfc_dev->dev.parent = dev; } /** * nfc_set_drvdata - set driver specific data * * @dev: The nfc device * @data: Pointer to driver specific data */ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) { dev_set_drvdata(&dev->dev, data); } /** * nfc_get_drvdata - get driver specific data * * @dev: The nfc device */ static inline void *nfc_get_drvdata(const struct nfc_dev *dev) { return dev_get_drvdata(&dev->dev); } /** * nfc_device_name - get the nfc device name * * @dev: The nfc device whose name to return */ static inline const char *nfc_device_name(const struct nfc_dev *dev) { return dev_name(&dev->dev); } struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk, unsigned int flags, unsigned int size, unsigned int *err); struct sk_buff *nfc_alloc_recv_skb(unsigned int size, gfp_t gfp); int nfc_set_remote_general_bytes(struct nfc_dev *dev, const u8 *gt, u8 gt_len); u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len); int nfc_fw_download_done(struct nfc_dev *dev, const char *firmware_name, u32 result); int nfc_targets_found(struct nfc_dev *dev, struct nfc_target *targets, int ntargets); int nfc_target_lost(struct nfc_dev *dev, u32 target_idx); int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, const u8 *gb, size_t gb_len); int nfc_tm_deactivated(struct nfc_dev *dev); int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb); void nfc_driver_failure(struct nfc_dev *dev, int err); int nfc_se_transaction(struct nfc_dev *dev, u8 se_idx, struct nfc_evt_transaction *evt_transaction); int nfc_se_connectivity(struct nfc_dev *dev, u8 se_idx); int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type); int nfc_remove_se(struct nfc_dev *dev, u32 se_idx); struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx); void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb, u8 payload_type, u8 direction); static inline int nfc_set_vendor_cmds(struct nfc_dev *dev, const struct nfc_vendor_cmd *cmds, int n_cmds) { if (dev->vendor_cmds || dev->n_vendor_cmds) return -EINVAL; dev->vendor_cmds = cmds; dev->n_vendor_cmds = n_cmds; return 0; } struct sk_buff *__nfc_alloc_vendor_cmd_reply_skb(struct nfc_dev *dev, enum nfc_attrs attr, u32 oui, u32 subcmd, int approxlen); int nfc_vendor_cmd_reply(struct sk_buff *skb); /** * nfc_vendor_cmd_alloc_reply_skb - allocate vendor command reply * @dev: nfc device * @oui: vendor oui * @approxlen: an upper bound of the length of the data that will * be put into the skb * * This function allocates and pre-fills an skb for a reply to * a vendor command. Since it is intended for a reply, calling * it outside of a vendor command's doit() operation is invalid. * * The returned skb is pre-filled with some identifying data in * a way that any data that is put into the skb (with skb_put(), * nla_put() or similar) will end up being within the * %NFC_ATTR_VENDOR_DATA attribute, so all that needs to be done * with the skb is adding data for the corresponding userspace tool * which can then read that data out of the vendor data attribute. * You must not modify the skb in any other way. * * When done, call nfc_vendor_cmd_reply() with the skb and return * its error code as the result of the doit() operation. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * nfc_vendor_cmd_alloc_reply_skb(struct nfc_dev *dev, u32 oui, u32 subcmd, int approxlen) { return __nfc_alloc_vendor_cmd_reply_skb(dev, NFC_ATTR_VENDOR_DATA, oui, subcmd, approxlen); } #endif /* __NET_NFC_H */ |
| 1 18 15 19 7 16 1 2 2 58 7 29 6 1 17 43 6 53 79 117 104 92 4 29 2 1 61 53 2 28 25 4 22 22 84 24 413 279 176 75 42 54 1 160 29 24 40 38 6 2 37 40 40 14 15 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 | // SPDX-License-Identifier: GPL-2.0-or-later /* scm.c - Socket level control messages processing. * * Author: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Alignment and value checking mods by Craig Metz */ #include <linux/module.h> #include <linux/signal.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/sched/user.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/net.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/security.h> #include <linux/pid_namespace.h> #include <linux/pid.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/errqueue.h> #include <linux/io_uring.h> #include <linux/uaccess.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/compat.h> #include <net/scm.h> #include <net/cls_cgroup.h> #include <net/af_unix.h> /* * Only allow a user to send credentials, that they could set with * setu(g)id. */ static __inline__ int scm_check_creds(struct ucred *creds) { const struct cred *cred = current_cred(); kuid_t uid = make_kuid(cred->user_ns, creds->uid); kgid_t gid = make_kgid(cred->user_ns, creds->gid); if (!uid_valid(uid) || !gid_valid(gid)) return -EINVAL; if ((creds->pid == task_tgid_vnr(current) || ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) && ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || uid_eq(uid, cred->suid)) || ns_capable(cred->user_ns, CAP_SETUID)) && ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || gid_eq(gid, cred->sgid)) || ns_capable(cred->user_ns, CAP_SETGID))) { return 0; } return -EPERM; } static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) { int *fdp = (int*)CMSG_DATA(cmsg); struct scm_fp_list *fpl = *fplp; struct file **fpp; int i, num; num = (cmsg->cmsg_len - sizeof(struct cmsghdr))/sizeof(int); if (num <= 0) return 0; if (num > SCM_MAX_FD) return -EINVAL; if (!fpl) { fpl = kmalloc(sizeof(struct scm_fp_list), GFP_KERNEL_ACCOUNT); if (!fpl) return -ENOMEM; *fplp = fpl; fpl->count = 0; fpl->count_unix = 0; fpl->max = SCM_MAX_FD; fpl->user = NULL; #if IS_ENABLED(CONFIG_UNIX) fpl->inflight = false; fpl->dead = false; fpl->edges = NULL; INIT_LIST_HEAD(&fpl->vertices); #endif } fpp = &fpl->fp[fpl->count]; if (fpl->count + num > fpl->max) return -EINVAL; /* * Verify the descriptors and increment the usage count. */ for (i=0; i< num; i++) { int fd = fdp[i]; struct file *file; if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; /* don't allow io_uring files */ if (io_is_uring_fops(file)) { fput(file); return -EINVAL; } if (unix_get_socket(file)) fpl->count_unix++; *fpp++ = file; fpl->count++; } if (!fpl->user) fpl->user = get_uid(current_user()); return num; } void __scm_destroy(struct scm_cookie *scm) { struct scm_fp_list *fpl = scm->fp; int i; if (fpl) { scm->fp = NULL; for (i=fpl->count-1; i>=0; i--) fput(fpl->fp[i]); free_uid(fpl->user); kfree(fpl); } } EXPORT_SYMBOL(__scm_destroy); int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) { const struct proto_ops *ops = READ_ONCE(sock->ops); struct cmsghdr *cmsg; int err; for_each_cmsghdr(cmsg, msg) { err = -EINVAL; /* Verify that cmsg_len is at least sizeof(struct cmsghdr) */ /* The first check was omitted in <= 2.2.5. The reasoning was that parser checks cmsg_len in any case, so that additional check would be work duplication. But if cmsg_level is not SOL_SOCKET, we do not check for too short ancillary data object at all! Oops. OK, let's add it... */ if (!CMSG_OK(msg, cmsg)) goto error; if (cmsg->cmsg_level != SOL_SOCKET) continue; switch (cmsg->cmsg_type) { case SCM_RIGHTS: if (!ops || ops->family != PF_UNIX) goto error; err=scm_fp_copy(cmsg, &p->fp); if (err<0) goto error; break; case SCM_CREDENTIALS: { struct ucred creds; kuid_t uid; kgid_t gid; if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct ucred))) goto error; memcpy(&creds, CMSG_DATA(cmsg), sizeof(struct ucred)); err = scm_check_creds(&creds); if (err) goto error; p->creds.pid = creds.pid; if (!p->pid || pid_vnr(p->pid) != creds.pid) { struct pid *pid; err = -ESRCH; pid = find_get_pid(creds.pid); if (!pid) goto error; put_pid(p->pid); p->pid = pid; } err = -EINVAL; uid = make_kuid(current_user_ns(), creds.uid); gid = make_kgid(current_user_ns(), creds.gid); if (!uid_valid(uid) || !gid_valid(gid)) goto error; p->creds.uid = uid; p->creds.gid = gid; break; } default: goto error; } } if (p->fp && !p->fp->count) { kfree(p->fp); p->fp = NULL; } return 0; error: scm_destroy(p); return err; } EXPORT_SYMBOL(__scm_send); int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data) { int cmlen = CMSG_LEN(len); if (msg->msg_flags & MSG_CMSG_COMPAT) return put_cmsg_compat(msg, level, type, len, data); if (!msg->msg_control || msg->msg_controllen < sizeof(struct cmsghdr)) { msg->msg_flags |= MSG_CTRUNC; return 0; /* XXX: return error? check spec. */ } if (msg->msg_controllen < cmlen) { msg->msg_flags |= MSG_CTRUNC; cmlen = msg->msg_controllen; } if (msg->msg_control_is_user) { struct cmsghdr __user *cm = msg->msg_control_user; check_object_size(data, cmlen - sizeof(*cm), true); if (!user_write_access_begin(cm, cmlen)) goto efault; unsafe_put_user(cmlen, &cm->cmsg_len, efault_end); unsafe_put_user(level, &cm->cmsg_level, efault_end); unsafe_put_user(type, &cm->cmsg_type, efault_end); unsafe_copy_to_user(CMSG_USER_DATA(cm), data, cmlen - sizeof(*cm), efault_end); user_write_access_end(); } else { struct cmsghdr *cm = msg->msg_control; cm->cmsg_level = level; cm->cmsg_type = type; cm->cmsg_len = cmlen; memcpy(CMSG_DATA(cm), data, cmlen - sizeof(*cm)); } cmlen = min(CMSG_SPACE(len), msg->msg_controllen); if (msg->msg_control_is_user) msg->msg_control_user += cmlen; else msg->msg_control += cmlen; msg->msg_controllen -= cmlen; return 0; efault_end: user_write_access_end(); efault: return -EFAULT; } EXPORT_SYMBOL(put_cmsg); void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) { struct scm_timestamping64 tss; int i; for (i = 0; i < ARRAY_SIZE(tss.ts); i++) { tss.ts[i].tv_sec = tss_internal->ts[i].tv_sec; tss.ts[i].tv_nsec = tss_internal->ts[i].tv_nsec; } put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_NEW, sizeof(tss), &tss); } EXPORT_SYMBOL(put_cmsg_scm_timestamping64); void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) { struct scm_timestamping tss; int i; for (i = 0; i < ARRAY_SIZE(tss.ts); i++) { tss.ts[i].tv_sec = tss_internal->ts[i].tv_sec; tss.ts[i].tv_nsec = tss_internal->ts[i].tv_nsec; } put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_OLD, sizeof(tss), &tss); } EXPORT_SYMBOL(put_cmsg_scm_timestamping); static int scm_max_fds(struct msghdr *msg) { if (msg->msg_controllen <= sizeof(struct cmsghdr)) return 0; return (msg->msg_controllen - sizeof(struct cmsghdr)) / sizeof(int); } void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) { struct cmsghdr __user *cm = (__force struct cmsghdr __user *)msg->msg_control_user; unsigned int o_flags = (msg->msg_flags & MSG_CMSG_CLOEXEC) ? O_CLOEXEC : 0; int fdmax = min_t(int, scm_max_fds(msg), scm->fp->count); int __user *cmsg_data = CMSG_USER_DATA(cm); int err = 0, i; /* no use for FD passing from kernel space callers */ if (WARN_ON_ONCE(!msg->msg_control_is_user)) return; if (msg->msg_flags & MSG_CMSG_COMPAT) { scm_detach_fds_compat(msg, scm); return; } for (i = 0; i < fdmax; i++) { err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); if (err < 0) break; } if (i > 0) { int cmlen = CMSG_LEN(i * sizeof(int)); err = put_user(SOL_SOCKET, &cm->cmsg_level); if (!err) err = put_user(SCM_RIGHTS, &cm->cmsg_type); if (!err) err = put_user(cmlen, &cm->cmsg_len); if (!err) { cmlen = CMSG_SPACE(i * sizeof(int)); if (msg->msg_controllen < cmlen) cmlen = msg->msg_controllen; msg->msg_control_user += cmlen; msg->msg_controllen -= cmlen; } } if (i < scm->fp->count || (scm->fp->count && fdmax <= 0)) msg->msg_flags |= MSG_CTRUNC; /* * All of the files that fit in the message have had their usage counts * incremented, so we just free the list. */ __scm_destroy(scm); } EXPORT_SYMBOL(scm_detach_fds); struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) { struct scm_fp_list *new_fpl; int i; if (!fpl) return NULL; new_fpl = kmemdup(fpl, offsetof(struct scm_fp_list, fp[fpl->count]), GFP_KERNEL_ACCOUNT); if (new_fpl) { for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); new_fpl->max = new_fpl->count; new_fpl->user = get_uid(fpl->user); #if IS_ENABLED(CONFIG_UNIX) new_fpl->inflight = false; new_fpl->edges = NULL; INIT_LIST_HEAD(&new_fpl->vertices); #endif } return new_fpl; } EXPORT_SYMBOL(scm_fp_dup); |
| 13 13 11 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2008, Intel Corporation. * * Author: Alexander Duyck <alexander.h.duyck@intel.com> */ #ifndef __NET_TC_SKBEDIT_H #define __NET_TC_SKBEDIT_H #include <net/act_api.h> #include <linux/tc_act/tc_skbedit.h> struct tcf_skbedit_params { u32 flags; u32 priority; u32 mark; u32 mask; u16 queue_mapping; u16 mapping_mod; u16 ptype; struct rcu_head rcu; }; struct tcf_skbedit { struct tc_action common; struct tcf_skbedit_params __rcu *params; }; #define to_skbedit(a) ((struct tcf_skbedit *)a) /* Return true iff action is the one identified by FLAG. */ static inline bool is_tcf_skbedit_with_flag(const struct tc_action *a, u32 flag) { #ifdef CONFIG_NET_CLS_ACT u32 flags; if (a->ops && a->ops->id == TCA_ID_SKBEDIT) { rcu_read_lock(); flags = rcu_dereference(to_skbedit(a)->params)->flags; rcu_read_unlock(); return flags == flag; } #endif return false; } /* Return true iff action is mark */ static inline bool is_tcf_skbedit_mark(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_MARK); } static inline u32 tcf_skbedit_mark(const struct tc_action *a) { u32 mark; rcu_read_lock(); mark = rcu_dereference(to_skbedit(a)->params)->mark; rcu_read_unlock(); return mark; } /* Return true iff action is ptype */ static inline bool is_tcf_skbedit_ptype(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_PTYPE); } static inline u32 tcf_skbedit_ptype(const struct tc_action *a) { u16 ptype; rcu_read_lock(); ptype = rcu_dereference(to_skbedit(a)->params)->ptype; rcu_read_unlock(); return ptype; } /* Return true iff action is priority */ static inline bool is_tcf_skbedit_priority(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_PRIORITY); } static inline u32 tcf_skbedit_priority(const struct tc_action *a) { u32 priority; rcu_read_lock(); priority = rcu_dereference(to_skbedit(a)->params)->priority; rcu_read_unlock(); return priority; } static inline u16 tcf_skbedit_rx_queue_mapping(const struct tc_action *a) { u16 rx_queue; rcu_read_lock(); rx_queue = rcu_dereference(to_skbedit(a)->params)->queue_mapping; rcu_read_unlock(); return rx_queue; } /* Return true iff action is queue_mapping */ static inline bool is_tcf_skbedit_queue_mapping(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_QUEUE_MAPPING); } /* Return true if action is on ingress traffic */ static inline bool is_tcf_skbedit_ingress(u32 flags) { return flags & TCA_ACT_FLAGS_AT_INGRESS; } static inline bool is_tcf_skbedit_tx_queue_mapping(const struct tc_action *a) { return is_tcf_skbedit_queue_mapping(a) && !is_tcf_skbedit_ingress(a->tcfa_flags); } static inline bool is_tcf_skbedit_rx_queue_mapping(const struct tc_action *a) { return is_tcf_skbedit_queue_mapping(a) && is_tcf_skbedit_ingress(a->tcfa_flags); } /* Return true iff action is inheritdsfield */ static inline bool is_tcf_skbedit_inheritdsfield(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_INHERITDSFIELD); } #endif /* __NET_TC_SKBEDIT_H */ |
| 8 13 2 2 1 7 1 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 | // SPDX-License-Identifier: GPL-2.0-only /* * Xtables module to match the process control group. * * Might be used to implement individual "per-application" firewall * policies in contrast to global policies based on control groups. * Matching is based upon processes tagged to net_cls' classid marker. * * (C) 2013 Daniel Borkmann <dborkman@redhat.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/skbuff.h> #include <linux/module.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_cgroup.h> #include <net/sock.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); MODULE_DESCRIPTION("Xtables: process control group matching"); MODULE_ALIAS("ipt_cgroup"); MODULE_ALIAS("ip6t_cgroup"); static int cgroup_mt_check_v0(const struct xt_mtchk_param *par) { struct xt_cgroup_info_v0 *info = par->matchinfo; if (info->invert & ~1) return -EINVAL; return 0; } static int cgroup_mt_check_v1(const struct xt_mtchk_param *par) { struct xt_cgroup_info_v1 *info = par->matchinfo; struct cgroup *cgrp; if ((info->invert_path & ~1) || (info->invert_classid & ~1)) return -EINVAL; if (!info->has_path && !info->has_classid) { pr_info("xt_cgroup: no path or classid specified\n"); return -EINVAL; } if (info->has_path && info->has_classid) { pr_info_ratelimited("path and classid specified\n"); return -EINVAL; } info->priv = NULL; if (info->has_path) { cgrp = cgroup_get_from_path(info->path); if (IS_ERR(cgrp)) { pr_info_ratelimited("invalid path, errno=%ld\n", PTR_ERR(cgrp)); return -EINVAL; } info->priv = cgrp; } return 0; } static int cgroup_mt_check_v2(const struct xt_mtchk_param *par) { struct xt_cgroup_info_v2 *info = par->matchinfo; struct cgroup *cgrp; if ((info->invert_path & ~1) || (info->invert_classid & ~1)) return -EINVAL; if (!info->has_path && !info->has_classid) { pr_info("xt_cgroup: no path or classid specified\n"); return -EINVAL; } if (info->has_path && info->has_classid) { pr_info_ratelimited("path and classid specified\n"); return -EINVAL; } info->priv = NULL; if (info->has_path) { cgrp = cgroup_get_from_path(info->path); if (IS_ERR(cgrp)) { pr_info_ratelimited("invalid path, errno=%ld\n", PTR_ERR(cgrp)); return -EINVAL; } info->priv = cgrp; } return 0; } static bool cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_cgroup_info_v0 *info = par->matchinfo; struct sock *sk = skb->sk; if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; return (info->id == sock_cgroup_classid(&skb->sk->sk_cgrp_data)) ^ info->invert; } static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_cgroup_info_v1 *info = par->matchinfo; struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data; struct cgroup *ancestor = info->priv; struct sock *sk = skb->sk; if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; if (ancestor) return cgroup_is_descendant(sock_cgroup_ptr(skcd), ancestor) ^ info->invert_path; else return (info->classid == sock_cgroup_classid(skcd)) ^ info->invert_classid; } static bool cgroup_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_cgroup_info_v2 *info = par->matchinfo; struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data; struct cgroup *ancestor = info->priv; struct sock *sk = skb->sk; if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; if (ancestor) return cgroup_is_descendant(sock_cgroup_ptr(skcd), ancestor) ^ info->invert_path; else return (info->classid == sock_cgroup_classid(skcd)) ^ info->invert_classid; } static void cgroup_mt_destroy_v1(const struct xt_mtdtor_param *par) { struct xt_cgroup_info_v1 *info = par->matchinfo; if (info->priv) cgroup_put(info->priv); } static void cgroup_mt_destroy_v2(const struct xt_mtdtor_param *par) { struct xt_cgroup_info_v2 *info = par->matchinfo; if (info->priv) cgroup_put(info->priv); } static struct xt_match cgroup_mt_reg[] __read_mostly = { { .name = "cgroup", .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = cgroup_mt_check_v0, .match = cgroup_mt_v0, .matchsize = sizeof(struct xt_cgroup_info_v0), .me = THIS_MODULE, .hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN), }, { .name = "cgroup", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = cgroup_mt_check_v1, .match = cgroup_mt_v1, .matchsize = sizeof(struct xt_cgroup_info_v1), .usersize = offsetof(struct xt_cgroup_info_v1, priv), .destroy = cgroup_mt_destroy_v1, .me = THIS_MODULE, .hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN), }, { .name = "cgroup", .revision = 2, .family = NFPROTO_UNSPEC, .checkentry = cgroup_mt_check_v2, .match = cgroup_mt_v2, .matchsize = sizeof(struct xt_cgroup_info_v2), .usersize = offsetof(struct xt_cgroup_info_v2, priv), .destroy = cgroup_mt_destroy_v2, .me = THIS_MODULE, .hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN), }, }; static int __init cgroup_mt_init(void) { return xt_register_matches(cgroup_mt_reg, ARRAY_SIZE(cgroup_mt_reg)); } static void __exit cgroup_mt_exit(void) { xt_unregister_matches(cgroup_mt_reg, ARRAY_SIZE(cgroup_mt_reg)); } module_init(cgroup_mt_init); module_exit(cgroup_mt_exit); |
| 263 72 2 19 1 9 15 38 107 5 84 2452 2 3 1 1 1 1 1 1 1 79 81 79 74 119 2124 23 181 181 179 2 9 9 181 120 89 253 81 78 81 81 2 16 78 81 81 48 39 81 81 3 59 78 78 34 56 56 56 78 8 8 7 77 77 99 99 99 77 53 20 2 2 341 28 72 3 3 36 36 36 1 100 255 15 3 89 3 1 1 5 1 3 3 2307 2305 1 42 3 17 1554 2136 1772 1892 2 3 2279 14 2308 244 51 193 3 16 242 16 2 17 18 1 17 17 18 25 5 132 48 235 21 237 229 8 249 251 253 252 237 22 236 22 253 248 7 253 234 22 253 252 1 146 116 250 252 143 118 118 118 14 105 81 21 17 48 81 19 22 22 22 18 92 92 91 34 2 56 82 82 11 4 4 4 14 15 45 45 33 45 55 1912 1913 97 42 136 107 92 92 47 84 13 8 3 83 81 19 20 39 23 23 1 2 14 27 19 101 1 100 1 66 36 1 35 313 12 27 306 330 8 9 2 6 315 8 254 5 55 306 90 254 7 23 26 303 2 2 253 2 2 2 1 81 305 27 323 322 332 332 192 44 5 7 2 136 130 49 49 4 144 81 80 81 70 51 1 17 67 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 | // SPDX-License-Identifier: GPL-2.0-or-later /* * fs/eventpoll.c (Efficient event retrieval implementation) * Copyright (C) 2001,...,2009 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/signal.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/string.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/rbtree.h> #include <linux/wait.h> #include <linux/eventpoll.h> #include <linux/mount.h> #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/anon_inodes.h> #include <linux/device.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/mman.h> #include <linux/atomic.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/compat.h> #include <linux/rculist.h> #include <linux/capability.h> #include <net/busy_poll.h> /* * LOCKING: * There are three level of locking required by epoll : * * 1) epnested_mutex (mutex) * 2) ep->mtx (mutex) * 3) ep->lock (rwlock) * * The acquire order is the one listed above, from 1 to 3. * We need a rwlock (ep->lock) because we manipulate objects * from inside the poll callback, that might be triggered from * a wake_up() that in turn might be called from IRQ context. * So we can't sleep inside the poll callback and hence we need * a spinlock. During the event transfer loop (from kernel to * user space) we could end up sleeping due a copy_to_user(), so * we need a lock that will allow us to sleep. This lock is a * mutex (ep->mtx). It is acquired during the event transfer loop, * during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file(). * The epnested_mutex is acquired when inserting an epoll fd onto another * epoll fd. We do this so that we walk the epoll tree and ensure that this * insertion does not create a cycle of epoll file descriptors, which * could lead to deadlock. We need a global mutex to prevent two * simultaneous inserts (A into B and B into A) from racing and * constructing a cycle without either insert observing that it is * going to. * It is necessary to acquire multiple "ep->mtx"es at once in the * case when one epoll fd is added to another. In this case, we * always acquire the locks in the order of nesting (i.e. after * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired * before e2->mtx). Since we disallow cycles of epoll file * descriptors, this ensures that the mutexes are well-ordered. In * order to communicate this nesting to lockdep, when walking a tree * of epoll file descriptors, we use the current recursion depth as * the lockdep subkey. * It is possible to drop the "ep->mtx" and to use the global * mutex "epnested_mutex" (together with "ep->lock") to have it working, * but having "ep->mtx" will make the interface more scalable. * Events that require holding "epnested_mutex" are very rare, while for * normal operations the epoll private "ep->mtx" will guarantee * a better scalability. */ /* Epoll private bits inside the event mask */ #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE) #define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT) #define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \ EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE) /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 #define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) #define EP_UNACTIVE_PTR ((void *) -1L) #define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry)) struct epoll_filefd { struct file *file; int fd; } __packed; /* Wait structure used by the poll hooks */ struct eppoll_entry { /* List header used to link this structure to the "struct epitem" */ struct eppoll_entry *next; /* The "base" pointer is set to the container "struct epitem" */ struct epitem *base; /* * Wait queue item that will be linked to the target file wait * queue head. */ wait_queue_entry_t wait; /* The wait queue head that linked the "wait" wait queue item */ wait_queue_head_t *whead; }; /* * Each file descriptor added to the eventpoll interface will * have an entry of this type linked to the "rbr" RB tree. * Avoid increasing the size of this struct, there can be many thousands * of these on a server and we do not want this to take another cache line. */ struct epitem { union { /* RB tree node links this structure to the eventpoll RB tree */ struct rb_node rbn; /* Used to free the struct epitem */ struct rcu_head rcu; }; /* List header used to link this structure to the eventpoll ready list */ struct list_head rdllink; /* * Works together "struct eventpoll"->ovflist in keeping the * single linked chain of items. */ struct epitem *next; /* The file descriptor information this item refers to */ struct epoll_filefd ffd; /* * Protected by file->f_lock, true for to-be-released epitem already * removed from the "struct file" items list; together with * eventpoll->refcount orchestrates "struct eventpoll" disposal */ bool dying; /* List containing poll wait queues */ struct eppoll_entry *pwqlist; /* The "container" of this item */ struct eventpoll *ep; /* List header used to link this item to the "struct file" items list */ struct hlist_node fllink; /* wakeup_source used when EPOLLWAKEUP is set */ struct wakeup_source __rcu *ws; /* The structure that describe the interested events and the source fd */ struct epoll_event event; }; /* * This structure is stored inside the "private_data" member of the file * structure and represents the main data structure for the eventpoll * interface. */ struct eventpoll { /* * This mutex is used to ensure that files are not removed * while epoll is using them. This is held during the event * collection loop, the file cleanup path, the epoll file exit * code and the ctl operations. */ struct mutex mtx; /* Wait queue used by sys_epoll_wait() */ wait_queue_head_t wq; /* Wait queue used by file->poll() */ wait_queue_head_t poll_wait; /* List of ready file descriptors */ struct list_head rdllist; /* Lock which protects rdllist and ovflist */ rwlock_t lock; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; /* * This is a single linked list that chains all the "struct epitem" that * happened while transferring ready events to userspace w/out * holding ->lock. */ struct epitem *ovflist; /* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */ struct wakeup_source *ws; /* The user that created the eventpoll descriptor */ struct user_struct *user; struct file *file; /* used to optimize loop detection check */ u64 gen; struct hlist_head refs; /* * usage count, used together with epitem->dying to * orchestrate the disposal of this struct */ refcount_t refcount; #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ unsigned int napi_id; /* busy poll timeout */ u32 busy_poll_usecs; /* busy poll packet budget */ u16 busy_poll_budget; bool prefer_busy_poll; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC /* tracks wakeup nests for lockdep validation */ u8 nests; #endif }; /* Wrapper struct used by poll queueing */ struct ep_pqueue { poll_table pt; struct epitem *epi; }; /* * Configuration options available inside /proc/sys/fs/epoll/ */ /* Maximum number of epoll watched descriptors, per user */ static long max_user_watches __read_mostly; /* Used for cycles detection */ static DEFINE_MUTEX(epnested_mutex); static u64 loop_check_gen = 0; /* Used to check for epoll file descriptor inclusion loops */ static struct eventpoll *inserting_into; /* Slab cache used to allocate "struct epitem" */ static struct kmem_cache *epi_cache __ro_after_init; /* Slab cache used to allocate "struct eppoll_entry" */ static struct kmem_cache *pwq_cache __ro_after_init; /* * List of files with newly added links, where we may need to limit the number * of emanating paths. Protected by the epnested_mutex. */ struct epitems_head { struct hlist_head epitems; struct epitems_head *next; }; static struct epitems_head *tfile_check_list = EP_UNACTIVE_PTR; static struct kmem_cache *ephead_cache __ro_after_init; static inline void free_ephead(struct epitems_head *head) { if (head) kmem_cache_free(ephead_cache, head); } static void list_file(struct file *file) { struct epitems_head *head; head = container_of(file->f_ep, struct epitems_head, epitems); if (!head->next) { head->next = tfile_check_list; tfile_check_list = head; } } static void unlist_file(struct epitems_head *head) { struct epitems_head *to_free = head; struct hlist_node *p = rcu_dereference(hlist_first_rcu(&head->epitems)); if (p) { struct epitem *epi= container_of(p, struct epitem, fllink); spin_lock(&epi->ffd.file->f_lock); if (!hlist_empty(&head->epitems)) to_free = NULL; head->next = NULL; spin_unlock(&epi->ffd.file->f_lock); } free_ephead(to_free); } #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static long long_zero; static long long_max = LONG_MAX; static struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, .maxlen = sizeof(max_user_watches), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &long_zero, .extra2 = &long_max, }, }; static void __init epoll_sysctls_init(void) { register_sysctl("fs/epoll", epoll_table); } #else #define epoll_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static const struct file_operations eventpoll_fops; static inline int is_file_epoll(struct file *f) { return f->f_op == &eventpoll_fops; } /* Setup the structure that is used as key for the RB tree */ static inline void ep_set_ffd(struct epoll_filefd *ffd, struct file *file, int fd) { ffd->file = file; ffd->fd = fd; } /* Compare RB tree keys */ static inline int ep_cmp_ffd(struct epoll_filefd *p1, struct epoll_filefd *p2) { return (p1->file > p2->file ? +1: (p1->file < p2->file ? -1 : p1->fd - p2->fd)); } /* Tells us if the item is currently linked */ static inline int ep_is_linked(struct epitem *epi) { return !list_empty(&epi->rdllink); } static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait); } /* Get the "struct epitem" from a wait queue pointer */ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait)->base; } /** * ep_events_available - Checks if ready events might be available. * * @ep: Pointer to the eventpoll context. * * Return: a value different than %zero if ready events are available, * or %zero otherwise. */ static inline int ep_events_available(struct eventpoll *ep) { return !list_empty_careful(&ep->rdllist) || READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR; } #ifdef CONFIG_NET_RX_BUSY_POLL /** * busy_loop_ep_timeout - check if busy poll has timed out. The timeout value * from the epoll instance ep is preferred, but if it is not set fallback to * the system-wide global via busy_loop_timeout. * * @start_time: The start time used to compute the remaining time until timeout. * @ep: Pointer to the eventpoll context. * * Return: true if the timeout has expired, false otherwise. */ static bool busy_loop_ep_timeout(unsigned long start_time, struct eventpoll *ep) { unsigned long bp_usec = READ_ONCE(ep->busy_poll_usecs); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } else { return busy_loop_timeout(start_time); } } static bool ep_busy_loop_on(struct eventpoll *ep) { return !!READ_ONCE(ep->busy_poll_usecs) || net_busy_loop_on(); } static bool ep_busy_loop_end(void *p, unsigned long start_time) { struct eventpoll *ep = p; return ep_events_available(ep) || busy_loop_ep_timeout(start_time, ep); } /* * Busy poll if globally on and supporting sockets found && no events, * busy loop will return if need_resched or ep_events_available. * * we must do our busy polling with irqs enabled */ static bool ep_busy_loop(struct eventpoll *ep, int nonblock) { unsigned int napi_id = READ_ONCE(ep->napi_id); u16 budget = READ_ONCE(ep->busy_poll_budget); bool prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (!budget) budget = BUSY_POLL_BUDGET; if (napi_id >= MIN_NAPI_ID && ep_busy_loop_on(ep)) { napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, prefer_busy_poll, budget); if (ep_events_available(ep)) return true; /* * Busy poll timed out. Drop NAPI ID for now, we can add * it back in when we have moved a socket with a valid NAPI * ID onto the ready list. */ ep->napi_id = 0; return false; } return false; } /* * Set epoll busy poll NAPI ID from sk. */ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { struct eventpoll *ep = epi->ep; unsigned int napi_id; struct socket *sock; struct sock *sk; if (!ep_busy_loop_on(ep)) return; sock = sock_from_file(epi->ffd.file); if (!sock) return; sk = sock->sk; if (!sk) return; napi_id = READ_ONCE(sk->sk_napi_id); /* Non-NAPI IDs can be rejected * or * Nothing to do if we already have this ID */ if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id) return; /* record NAPI ID for use in next busy poll */ ep->napi_id = napi_id; } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct eventpoll *ep = file->private_data; void __user *uarg = (void __user *)arg; struct epoll_params epoll_params; switch (cmd) { case EPIOCSPARAMS: if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params))) return -EFAULT; /* pad byte must be zero */ if (epoll_params.__pad) return -EINVAL; if (epoll_params.busy_poll_usecs > S32_MAX) return -EINVAL; if (epoll_params.prefer_busy_poll > 1) return -EINVAL; if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT && !capable(CAP_NET_ADMIN)) return -EPERM; WRITE_ONCE(ep->busy_poll_usecs, epoll_params.busy_poll_usecs); WRITE_ONCE(ep->busy_poll_budget, epoll_params.busy_poll_budget); WRITE_ONCE(ep->prefer_busy_poll, epoll_params.prefer_busy_poll); return 0; case EPIOCGPARAMS: memset(&epoll_params, 0, sizeof(epoll_params)); epoll_params.busy_poll_usecs = READ_ONCE(ep->busy_poll_usecs); epoll_params.busy_poll_budget = READ_ONCE(ep->busy_poll_budget); epoll_params.prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params))) return -EFAULT; return 0; default: return -ENOIOCTLCMD; } } #else static inline bool ep_busy_loop(struct eventpoll *ep, int nonblock) { return false; } static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } #endif /* CONFIG_NET_RX_BUSY_POLL */ /* * As described in commit 0ccf831cb lockdep: annotate epoll * the use of wait queues used by epoll is done in a very controlled * manner. Wake ups can nest inside each other, but are never done * with the same locking. For example: * * dfd = socket(...); * efd1 = epoll_create(); * efd2 = epoll_create(); * epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...); * epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...); * * When a packet arrives to the device underneath "dfd", the net code will * issue a wake_up() on its poll wake list. Epoll (efd1) has installed a * callback wakeup entry on that queue, and the wake_up() performed by the * "dfd" net code will end up in ep_poll_callback(). At this point epoll * (efd1) notices that it may have some event ready, so it needs to wake up * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake() * that ends up in another wake_up(), after having checked about the * recursion constraints. That are, no more than EP_MAX_NESTS, to avoid * stack blasting. * * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle * this special case of epoll. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, unsigned pollflags) { struct eventpoll *ep_src; unsigned long flags; u8 nests = 0; /* * To set the subclass or nesting level for spin_lock_irqsave_nested() * it might be natural to create a per-cpu nest count. However, since * we can recurse on ep->poll_wait.lock, and a non-raw spinlock can * schedule() in the -rt kernel, the per-cpu variable are no longer * protected. Thus, we are introducing a per eventpoll nest field. * If we are not being call from ep_poll_callback(), epi is NULL and * we are at the first level of nesting, 0. Otherwise, we are being * called from ep_poll_callback() and if a previous wakeup source is * not an epoll file itself, we are at depth 1 since the wakeup source * is depth 0. If the wakeup source is a previous epoll file in the * wakeup chain then we use its nests value and record ours as * nests + 1. The previous epoll file nests value is stable since its * already holding its own poll_wait.lock. */ if (epi) { if ((is_file_epoll(epi->ffd.file))) { ep_src = epi->ffd.file->private_data; nests = ep_src->nests; } else { nests = 1; } } spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests); ep->nests = nests + 1; wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags); ep->nests = 0; spin_unlock_irqrestore(&ep->poll_wait.lock, flags); } #else static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, __poll_t pollflags) { wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } #endif static void ep_remove_wait_queue(struct eppoll_entry *pwq) { wait_queue_head_t *whead; rcu_read_lock(); /* * If it is cleared by POLLFREE, it should be rcu-safe. * If we read NULL we need a barrier paired with * smp_store_release() in ep_poll_callback(), otherwise * we rely on whead->lock. */ whead = smp_load_acquire(&pwq->whead); if (whead) remove_wait_queue(whead, &pwq->wait); rcu_read_unlock(); } /* * This function unregisters poll callbacks from the associated file * descriptor. Must be called with "mtx" held. */ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) { struct eppoll_entry **p = &epi->pwqlist; struct eppoll_entry *pwq; while ((pwq = *p) != NULL) { *p = pwq->next; ep_remove_wait_queue(pwq); kmem_cache_free(pwq_cache, pwq); } } /* call only when ep->mtx is held */ static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi) { return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx)); } /* call only when ep->mtx is held */ static inline void ep_pm_stay_awake(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); if (ws) __pm_stay_awake(ws); } static inline bool ep_has_wakeup_source(struct epitem *epi) { return rcu_access_pointer(epi->ws) ? true : false; } /* call when ep->mtx cannot be held (ep_poll_callback) */ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) { struct wakeup_source *ws; rcu_read_lock(); ws = rcu_dereference(epi->ws); if (ws) __pm_stay_awake(ws); rcu_read_unlock(); } /* * ep->mutex needs to be held because we could be hit by * eventpoll_release_file() and epoll_ctl(). */ static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist) { /* * Steal the ready list, and re-init the original one to the * empty list. Also, set ep->ovflist to NULL so that events * happening while looping w/out locks, are not lost. We cannot * have the poll callback to queue directly on ep->rdllist, * because we want the "sproc" callback to be able to do it * in a lockless way. */ lockdep_assert_irqs_enabled(); write_lock_irq(&ep->lock); list_splice_init(&ep->rdllist, txlist); WRITE_ONCE(ep->ovflist, NULL); write_unlock_irq(&ep->lock); } static void ep_done_scan(struct eventpoll *ep, struct list_head *txlist) { struct epitem *epi, *nepi; write_lock_irq(&ep->lock); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. * We re-insert them inside the main ready-list here. */ for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL; nepi = epi->next, epi->next = EP_UNACTIVE_PTR) { /* * We need to check if the item is already in the list. * During the "sproc" callback execution time, items are * queued into ->ovflist but the "txlist" might already * contain them, and the list_splice() below takes care of them. */ if (!ep_is_linked(epi)) { /* * ->ovflist is LIFO, so we have to reverse it in order * to keep in FIFO. */ list_add(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } /* * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after * releasing the lock, events will be queued in the normal way inside * ep->rdllist. */ WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR); /* * Quickly re-inject items left on "txlist". */ list_splice(txlist, &ep->rdllist); __pm_relax(ep->ws); if (!list_empty(&ep->rdllist)) { if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); } write_unlock_irq(&ep->lock); } static void ep_get(struct eventpoll *ep) { refcount_inc(&ep->refcount); } /* * Returns true if the event poll can be disposed */ static bool ep_refcount_dec_and_test(struct eventpoll *ep) { if (!refcount_dec_and_test(&ep->refcount)) return false; WARN_ON_ONCE(!RB_EMPTY_ROOT(&ep->rbr.rb_root)); return true; } static void ep_free(struct eventpoll *ep) { mutex_destroy(&ep->mtx); free_uid(ep->user); wakeup_source_unregister(ep->ws); kfree(ep); } /* * Removes a "struct epitem" from the eventpoll RB tree and deallocates * all the associated resources. Must be called with "mtx" held. * If the dying flag is set, do the removal only if force is true. * This prevents ep_clear_and_put() from dropping all the ep references * while running concurrently with eventpoll_release_file(). * Returns true if the eventpoll can be disposed. */ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) { struct file *file = epi->ffd.file; struct epitems_head *to_free; struct hlist_head *head; lockdep_assert_irqs_enabled(); /* * Removes poll wait queue hooks. */ ep_unregister_pollwait(ep, epi); /* Remove the current item from the list of epoll hooks */ spin_lock(&file->f_lock); if (epi->dying && !force) { spin_unlock(&file->f_lock); return false; } to_free = NULL; head = file->f_ep; if (head->first == &epi->fllink && !epi->fllink.next) { file->f_ep = NULL; if (!is_file_epoll(file)) { struct epitems_head *v; v = container_of(head, struct epitems_head, epitems); if (!smp_load_acquire(&v->next)) to_free = v; } } hlist_del_rcu(&epi->fllink); spin_unlock(&file->f_lock); free_ephead(to_free); rb_erase_cached(&epi->rbn, &ep->rbr); write_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); write_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* * At this point it is safe to free the eventpoll item. Use the union * field epi->rcu, since we are trying to minimize the size of * 'struct epitem'. The 'rbn' field is no longer in use. Protected by * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make * use of the rbn field. */ kfree_rcu(epi, rcu); percpu_counter_dec(&ep->user->epoll_watches); return ep_refcount_dec_and_test(ep); } /* * ep_remove variant for callers owing an additional reference to the ep */ static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi) { WARN_ON_ONCE(__ep_remove(ep, epi, false)); } static void ep_clear_and_put(struct eventpoll *ep) { struct rb_node *rbp, *next; struct epitem *epi; bool dispose; /* We need to release all tasks waiting for these file */ if (waitqueue_active(&ep->poll_wait)) ep_poll_safewake(ep, NULL, 0); mutex_lock(&ep->mtx); /* * Walks through the whole tree by unregistering poll callbacks. */ for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); ep_unregister_pollwait(ep, epi); cond_resched(); } /* * Walks through the whole tree and try to free each "struct epitem". * Note that ep_remove_safe() will not remove the epitem in case of a * racing eventpoll_release_file(); the latter will do the removal. * At this point we are sure no poll callbacks will be lingering around. * Since we still own a reference to the eventpoll struct, the loop can't * dispose it. */ for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = next) { next = rb_next(rbp); epi = rb_entry(rbp, struct epitem, rbn); ep_remove_safe(ep, epi); cond_resched(); } dispose = ep_refcount_dec_and_test(ep); mutex_unlock(&ep->mtx); if (dispose) ep_free(ep); } static long ep_eventpoll_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { int ret; if (!is_file_epoll(file)) return -EINVAL; switch (cmd) { case EPIOCSPARAMS: case EPIOCGPARAMS: ret = ep_eventpoll_bp_ioctl(file, cmd, arg); break; default: ret = -EINVAL; break; } return ret; } static int ep_eventpoll_release(struct inode *inode, struct file *file) { struct eventpoll *ep = file->private_data; if (ep) ep_clear_and_put(ep); return 0; } static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth); static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth) { struct eventpoll *ep = file->private_data; LIST_HEAD(txlist); struct epitem *epi, *tmp; poll_table pt; __poll_t res = 0; init_poll_funcptr(&pt, NULL); /* Insert inside our poll wait queue */ poll_wait(file, &ep->poll_wait, wait); /* * Proceed to find out if wanted events are really available inside * the ready list. */ mutex_lock_nested(&ep->mtx, depth); ep_start_scan(ep, &txlist); list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { if (ep_item_poll(epi, &pt, depth + 1)) { res = EPOLLIN | EPOLLRDNORM; break; } else { /* * Item has been dropped into the ready list by the poll * callback, but it's not actually ready, as far as * caller requested events goes. We can remove it here. */ __pm_relax(ep_wakeup_source(epi)); list_del_init(&epi->rdllink); } } ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); return res; } /* * The ffd.file pointer may be in the process of being torn down due to * being closed, but we may not have finished eventpoll_release() yet. * * Normally, even with the atomic_long_inc_not_zero, the file may have * been free'd and then gotten re-allocated to something else (since * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU). * * But for epoll, users hold the ep->mtx mutex, and as such any file in * the process of being free'd will block in eventpoll_release_file() * and thus the underlying file allocation will not be free'd, and the * file re-use cannot happen. * * For the same reason we can avoid a rcu_read_lock() around the * operation - 'ffd.file' cannot go away even if the refcount has * reached zero (but we must still not call out to ->poll() functions * etc). */ static struct file *epi_fget(const struct epitem *epi) { struct file *file; file = epi->ffd.file; if (!atomic_long_inc_not_zero(&file->f_count)) file = NULL; return file; } /* * Differs from ep_eventpoll_poll() in that internal callers already have * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested() * is correctly annotated. */ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth) { struct file *file = epi_fget(epi); __poll_t res; /* * We could return EPOLLERR | EPOLLHUP or something, but let's * treat this more as "file doesn't exist, poll didn't happen". */ if (!file) return 0; pt->_key = epi->event.events; if (!is_file_epoll(file)) res = vfs_poll(file, pt); else res = __ep_eventpoll_poll(file, pt, depth); fput(file); return res & epi->event.events; } static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait) { return __ep_eventpoll_poll(file, wait, 0); } #ifdef CONFIG_PROC_FS static void ep_show_fdinfo(struct seq_file *m, struct file *f) { struct eventpoll *ep = f->private_data; struct rb_node *rbp; mutex_lock(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); struct inode *inode = file_inode(epi->ffd.file); seq_printf(m, "tfd: %8d events: %8x data: %16llx " " pos:%lli ino:%lx sdev:%x\n", epi->ffd.fd, epi->event.events, (long long)epi->event.data, (long long)epi->ffd.file->f_pos, inode->i_ino, inode->i_sb->s_dev); if (seq_has_overflowed(m)) break; } mutex_unlock(&ep->mtx); } #endif /* File callbacks that implement the eventpoll file behaviour */ static const struct file_operations eventpoll_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = ep_show_fdinfo, #endif .release = ep_eventpoll_release, .poll = ep_eventpoll_poll, .llseek = noop_llseek, .unlocked_ioctl = ep_eventpoll_ioctl, .compat_ioctl = compat_ptr_ioctl, }; /* * This is called from eventpoll_release() to unlink files from the eventpoll * interface. We need to have this facility to cleanup correctly files that are * closed without being removed from the eventpoll interface. */ void eventpoll_release_file(struct file *file) { struct eventpoll *ep; struct epitem *epi; bool dispose; /* * Use the 'dying' flag to prevent a concurrent ep_clear_and_put() from * touching the epitems list before eventpoll_release_file() can access * the ep->mtx. */ again: spin_lock(&file->f_lock); if (file->f_ep && file->f_ep->first) { epi = hlist_entry(file->f_ep->first, struct epitem, fllink); epi->dying = true; spin_unlock(&file->f_lock); /* * ep access is safe as we still own a reference to the ep * struct */ ep = epi->ep; mutex_lock(&ep->mtx); dispose = __ep_remove(ep, epi, true); mutex_unlock(&ep->mtx); if (dispose) ep_free(ep); goto again; } spin_unlock(&file->f_lock); } static int ep_alloc(struct eventpoll **pep) { struct eventpoll *ep; ep = kzalloc(sizeof(*ep), GFP_KERNEL); if (unlikely(!ep)) return -ENOMEM; mutex_init(&ep->mtx); rwlock_init(&ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); ep->rbr = RB_ROOT_CACHED; ep->ovflist = EP_UNACTIVE_PTR; ep->user = get_current_user(); refcount_set(&ep->refcount, 1); *pep = ep; return 0; } /* * Search the file inside the eventpoll tree. The RB tree operations * are protected by the "mtx" mutex, and ep_find() must be called with * "mtx" held. */ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) { int kcmp; struct rb_node *rbp; struct epitem *epi, *epir = NULL; struct epoll_filefd ffd; ep_set_ffd(&ffd, file, fd); for (rbp = ep->rbr.rb_root.rb_node; rbp; ) { epi = rb_entry(rbp, struct epitem, rbn); kcmp = ep_cmp_ffd(&ffd, &epi->ffd); if (kcmp > 0) rbp = rbp->rb_right; else if (kcmp < 0) rbp = rbp->rb_left; else { epir = epi; break; } } return epir; } #ifdef CONFIG_KCMP static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) { struct rb_node *rbp; struct epitem *epi; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (epi->ffd.fd == tfd) { if (toff == 0) return epi; else toff--; } cond_resched(); } return NULL; } struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff) { struct file *file_raw; struct eventpoll *ep; struct epitem *epi; if (!is_file_epoll(file)) return ERR_PTR(-EINVAL); ep = file->private_data; mutex_lock(&ep->mtx); epi = ep_find_tfd(ep, tfd, toff); if (epi) file_raw = epi->ffd.file; else file_raw = ERR_PTR(-ENOENT); mutex_unlock(&ep->mtx); return file_raw; } #endif /* CONFIG_KCMP */ /* * Adds a new entry to the tail of the list in a lockless way, i.e. * multiple CPUs are allowed to call this function concurrently. * * Beware: it is necessary to prevent any other modifications of the * existing list until all changes are completed, in other words * concurrent list_add_tail_lockless() calls should be protected * with a read lock, where write lock acts as a barrier which * makes sure all list_add_tail_lockless() calls are fully * completed. * * Also an element can be locklessly added to the list only in one * direction i.e. either to the tail or to the head, otherwise * concurrent access will corrupt the list. * * Return: %false if element has been already added to the list, %true * otherwise. */ static inline bool list_add_tail_lockless(struct list_head *new, struct list_head *head) { struct list_head *prev; /* * This is simple 'new->next = head' operation, but cmpxchg() * is used in order to detect that same element has been just * added to the list from another CPU: the winner observes * new->next == new. */ if (!try_cmpxchg(&new->next, &new, head)) return false; /* * Initially ->next of a new element must be updated with the head * (we are inserting to the tail) and only then pointers are atomically * exchanged. XCHG guarantees memory ordering, thus ->next should be * updated before pointers are actually swapped and pointers are * swapped before prev->next is updated. */ prev = xchg(&head->prev, new); /* * It is safe to modify prev->next and new->prev, because a new element * is added only to the tail and new->next is updated before XCHG. */ prev->next = new; new->prev = prev; return true; } /* * Chains a new epi entry to the tail of the ep->ovflist in a lockless way, * i.e. multiple CPUs are allowed to call this function concurrently. * * Return: %false if epi element has been already chained, %true otherwise. */ static inline bool chain_epi_lockless(struct epitem *epi) { struct eventpoll *ep = epi->ep; /* Fast preliminary check */ if (epi->next != EP_UNACTIVE_PTR) return false; /* Check that the same epi has not been just chained from another CPU */ if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) return false; /* Atomically exchange tail */ epi->next = xchg(&ep->ovflist, epi); return true; } /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. * * This callback takes a read lock in order not to contend with concurrent * events from another file descriptor, thus all modifications to ->rdllist * or ->ovflist are lockless. Read lock is paired with the write lock from * ep_start/done_scan(), which stops all list modifications and guarantees * that lists state is seen correctly. * * Another thing worth to mention is that ep_poll_callback() can be called * concurrently for the same @epi from different CPUs if poll table was inited * with several wait queues entries. Plural wakeup from different CPUs of a * single wait queue is serialized by wq.lock, but the case when multiple wait * queues are used should be detected accordingly. This is detected using * cmpxchg() operation. */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int pwake = 0; struct epitem *epi = ep_item_from_wait(wait); struct eventpoll *ep = epi->ep; __poll_t pollflags = key_to_poll(key); unsigned long flags; int ewake = 0; read_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); /* * If the event mask does not contain any poll(2) event, we consider the * descriptor to be disabled. This condition is likely the effect of the * EPOLLONESHOT bit that disables the descriptor when an event is received, * until the next EPOLL_CTL_MOD will be issued. */ if (!(epi->event.events & ~EP_PRIVATE_BITS)) goto out_unlock; /* * Check the events coming with the callback. At this stage, not * every device reports the events in the "key" parameter of the * callback. We need to be able to handle both cases here, hence the * test for "key" != NULL before the event match test. */ if (pollflags && !(pollflags & epi->event.events)) goto out_unlock; /* * If we are transferring events to userspace, we can hold no locks * (because we're accessing user memory, and because of linux f_op->poll() * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { if (chain_epi_lockless(epi)) ep_pm_stay_awake_rcu(epi); } else if (!ep_is_linked(epi)) { /* In the usual case, add event to ready list. */ if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) ep_pm_stay_awake_rcu(epi); } /* * Wake up ( if active ) both the eventpoll wait list and the ->poll() * wait list. */ if (waitqueue_active(&ep->wq)) { if ((epi->event.events & EPOLLEXCLUSIVE) && !(pollflags & POLLFREE)) { switch (pollflags & EPOLLINOUT_BITS) { case EPOLLIN: if (epi->event.events & EPOLLIN) ewake = 1; break; case EPOLLOUT: if (epi->event.events & EPOLLOUT) ewake = 1; break; case 0: ewake = 1; break; } } wake_up(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) pwake++; out_unlock: read_unlock_irqrestore(&ep->lock, flags); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; if (pollflags & POLLFREE) { /* * If we race with ep_remove_wait_queue() it can miss * ->whead = NULL and do another remove_wait_queue() after * us, so we can't use __remove_wait_queue(). */ list_del_init(&wait->entry); /* * ->whead != NULL protects us from the race with * ep_clear_and_put() or ep_remove(), ep_remove_wait_queue() * takes whead->lock held by the caller. Once we nullify it, * nothing protects ep/epi or even wait. */ smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); } return ewake; } /* * This is the callback that is used to add our wait queue to the * target file wakeup lists. */ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, poll_table *pt) { struct ep_pqueue *epq = container_of(pt, struct ep_pqueue, pt); struct epitem *epi = epq->epi; struct eppoll_entry *pwq; if (unlikely(!epi)) // an earlier allocation has failed return; pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL); if (unlikely(!pwq)) { epq->epi = NULL; return; } init_waitqueue_func_entry(&pwq->wait, ep_poll_callback); pwq->whead = whead; pwq->base = epi; if (epi->event.events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(whead, &pwq->wait); else add_wait_queue(whead, &pwq->wait); pwq->next = epi->pwqlist; epi->pwqlist = pwq; } static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) { int kcmp; struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL; struct epitem *epic; bool leftmost = true; while (*p) { parent = *p; epic = rb_entry(parent, struct epitem, rbn); kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd); if (kcmp > 0) { p = &parent->rb_right; leftmost = false; } else p = &parent->rb_left; } rb_link_node(&epi->rbn, parent, p); rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost); } #define PATH_ARR_SIZE 5 /* * These are the number paths of length 1 to 5, that we are allowing to emanate * from a single file of interest. For example, we allow 1000 paths of length * 1, to emanate from each file of interest. This essentially represents the * potential wakeup paths, which need to be limited in order to avoid massive * uncontrolled wakeup storms. The common use case should be a single ep which * is connected to n file sources. In this case each file source has 1 path * of length 1. Thus, the numbers below should be more than sufficient. These * path limits are enforced during an EPOLL_CTL_ADD operation, since a modify * and delete can't add additional paths. Protected by the epnested_mutex. */ static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 }; static int path_count[PATH_ARR_SIZE]; static int path_count_inc(int nests) { /* Allow an arbitrary number of depth 1 paths */ if (nests == 0) return 0; if (++path_count[nests] > path_limits[nests]) return -1; return 0; } static void path_count_init(void) { int i; for (i = 0; i < PATH_ARR_SIZE; i++) path_count[i] = 0; } static int reverse_path_check_proc(struct hlist_head *refs, int depth) { int error = 0; struct epitem *epi; if (depth > EP_MAX_NESTS) /* too deep nesting */ return -1; /* CTL_DEL can remove links here, but that can't increase our count */ hlist_for_each_entry_rcu(epi, refs, fllink) { struct hlist_head *refs = &epi->ep->refs; if (hlist_empty(refs)) error = path_count_inc(depth); else error = reverse_path_check_proc(refs, depth + 1); if (error != 0) break; } return error; } /** * reverse_path_check - The tfile_check_list is list of epitem_head, which have * links that are proposed to be newly added. We need to * make sure that those added links don't add too many * paths such that we will spend all our time waking up * eventpoll objects. * * Return: %zero if the proposed links don't create too many paths, * %-1 otherwise. */ static int reverse_path_check(void) { struct epitems_head *p; for (p = tfile_check_list; p != EP_UNACTIVE_PTR; p = p->next) { int error; path_count_init(); rcu_read_lock(); error = reverse_path_check_proc(&p->epitems, 0); rcu_read_unlock(); if (error) return error; } return 0; } static int ep_create_wakeup_source(struct epitem *epi) { struct name_snapshot n; struct wakeup_source *ws; if (!epi->ep->ws) { epi->ep->ws = wakeup_source_register(NULL, "eventpoll"); if (!epi->ep->ws) return -ENOMEM; } take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry); ws = wakeup_source_register(NULL, n.name.name); release_dentry_name_snapshot(&n); if (!ws) return -ENOMEM; rcu_assign_pointer(epi->ws, ws); return 0; } /* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */ static noinline void ep_destroy_wakeup_source(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); RCU_INIT_POINTER(epi->ws, NULL); /* * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is * used internally by wakeup_source_remove, too (called by * wakeup_source_unregister), so we cannot use call_rcu */ synchronize_rcu(); wakeup_source_unregister(ws); } static int attach_epitem(struct file *file, struct epitem *epi) { struct epitems_head *to_free = NULL; struct hlist_head *head = NULL; struct eventpoll *ep = NULL; if (is_file_epoll(file)) ep = file->private_data; if (ep) { head = &ep->refs; } else if (!READ_ONCE(file->f_ep)) { allocate: to_free = kmem_cache_zalloc(ephead_cache, GFP_KERNEL); if (!to_free) return -ENOMEM; head = &to_free->epitems; } spin_lock(&file->f_lock); if (!file->f_ep) { if (unlikely(!head)) { spin_unlock(&file->f_lock); goto allocate; } file->f_ep = head; to_free = NULL; } hlist_add_head_rcu(&epi->fllink, file->f_ep); spin_unlock(&file->f_lock); free_ephead(to_free); return 0; } /* * Must be called with "mtx" held. */ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, struct file *tfile, int fd, int full_check) { int error, pwake = 0; __poll_t revents; struct epitem *epi; struct ep_pqueue epq; struct eventpoll *tep = NULL; if (is_file_epoll(tfile)) tep = tfile->private_data; lockdep_assert_irqs_enabled(); if (unlikely(percpu_counter_compare(&ep->user->epoll_watches, max_user_watches) >= 0)) return -ENOSPC; percpu_counter_inc(&ep->user->epoll_watches); if (!(epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL))) { percpu_counter_dec(&ep->user->epoll_watches); return -ENOMEM; } /* Item initialization follow here ... */ INIT_LIST_HEAD(&epi->rdllink); epi->ep = ep; ep_set_ffd(&epi->ffd, tfile, fd); epi->event = *event; epi->next = EP_UNACTIVE_PTR; if (tep) mutex_lock_nested(&tep->mtx, 1); /* Add the current item to the list of active epoll hook for this file */ if (unlikely(attach_epitem(tfile, epi) < 0)) { if (tep) mutex_unlock(&tep->mtx); kmem_cache_free(epi_cache, epi); percpu_counter_dec(&ep->user->epoll_watches); return -ENOMEM; } if (full_check && !tep) list_file(tfile); /* * Add the current item to the RB tree. All RB tree operations are * protected by "mtx", and ep_insert() is called with "mtx" held. */ ep_rbtree_insert(ep, epi); if (tep) mutex_unlock(&tep->mtx); /* * ep_remove_safe() calls in the later error paths can't lead to * ep_free() as the ep file itself still holds an ep reference. */ ep_get(ep); /* now check if we've created too many backpaths */ if (unlikely(full_check && reverse_path_check())) { ep_remove_safe(ep, epi); return -EINVAL; } if (epi->event.events & EPOLLWAKEUP) { error = ep_create_wakeup_source(epi); if (error) { ep_remove_safe(ep, epi); return error; } } /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); /* * Attach the item to the poll hooks and get current event bits. * We can safely use the file* here because its usage count has * been increased by the caller of this function. Note that after * this operation completes, the poll callback can start hitting * the new item. */ revents = ep_item_poll(epi, &epq.pt, 1); /* * We have to check if something went wrong during the poll wait queue * install process. Namely an allocation for a wait queue failed due * high memory pressure. */ if (unlikely(!epq.epi)) { ep_remove_safe(ep, epi); return -ENOMEM; } /* We have to drop the new item inside our item list to keep track of it */ write_lock_irq(&ep->lock); /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); /* If the file is already "ready" we drop it inside the ready list */ if (revents && !ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } write_unlock_irq(&ep->lock); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } /* * Modify the interest event mask by dropping an event if the new mask * has a match in the current file status. Must be called with "mtx" held. */ static int ep_modify(struct eventpoll *ep, struct epitem *epi, const struct epoll_event *event) { int pwake = 0; poll_table pt; lockdep_assert_irqs_enabled(); init_poll_funcptr(&pt, NULL); /* * Set the new event interest mask before calling f_op->poll(); * otherwise we might miss an event that happens between the * f_op->poll() call and the new event set registering. */ epi->event.events = event->events; /* need barrier below */ epi->event.data = event->data; /* protected by mtx */ if (epi->event.events & EPOLLWAKEUP) { if (!ep_has_wakeup_source(epi)) ep_create_wakeup_source(epi); } else if (ep_has_wakeup_source(epi)) { ep_destroy_wakeup_source(epi); } /* * The following barrier has two effects: * * 1) Flush epi changes above to other CPUs. This ensures * we do not miss events from ep_poll_callback if an * event occurs immediately after we call f_op->poll(). * We need this because we did not take ep->lock while * changing epi above (but ep_poll_callback does take * ep->lock). * * 2) We also need to ensure we do not miss _past_ events * when calling f_op->poll(). This barrier also * pairs with the barrier in wq_has_sleeper (see * comments for wq_has_sleeper). * * This barrier will now guarantee ep_poll_callback or f_op->poll * (or both) will notice the readiness of an item. */ smp_mb(); /* * Get current event bits. We can safely use the file* here because * its usage count has been increased by the caller of this function. * If the item is "hot" and it is not registered inside the ready * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { write_lock_irq(&ep->lock); if (!ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } write_unlock_irq(&ep->lock); } /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { struct epitem *epi, *tmp; LIST_HEAD(txlist); poll_table pt; int res = 0; /* * Always short-circuit for fatal signals to allow threads to make a * timely exit without the chance of finding more events available and * fetching repeatedly. */ if (fatal_signal_pending(current)) return -EINTR; init_poll_funcptr(&pt, NULL); mutex_lock(&ep->mtx); ep_start_scan(ep, &txlist); /* * We can loop without lock because we are passed a task private list. * Items cannot vanish during the loop we are holding ep->mtx. */ list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { struct wakeup_source *ws; __poll_t revents; if (res >= maxevents) break; /* * Activate ep->ws before deactivating epi->ws to prevent * triggering auto-suspend here (in case we reactive epi->ws * below). * * This could be rearranged to delay the deactivation of epi->ws * instead, but then epi->ws would temporarily be out of sync * with ep_is_linked(). */ ws = ep_wakeup_source(epi); if (ws) { if (ws->active) __pm_stay_awake(ep->ws); __pm_relax(ws); } list_del_init(&epi->rdllink); /* * If the event mask intersect the caller-requested one, * deliver the event to userspace. Again, we are holding ep->mtx, * so no operations coming from userspace can change the item. */ revents = ep_item_poll(epi, &pt, 1); if (!revents) continue; events = epoll_put_uevent(revents, epi->event.data, events); if (!events) { list_add(&epi->rdllink, &txlist); ep_pm_stay_awake(epi); if (!res) res = -EFAULT; break; } res++; if (epi->event.events & EPOLLONESHOT) epi->event.events &= EP_PRIVATE_BITS; else if (!(epi->event.events & EPOLLET)) { /* * If this file has been added with Level * Trigger mode, we need to insert back inside * the ready list, so that the next call to * epoll_wait() will check again the events * availability. At this point, no one can insert * into ep->rdllist besides us. The epoll_ctl() * callers are locked out by * ep_send_events() holding "mtx" and the * poll callback will queue them in ep->ovflist. */ list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); return res; } static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms) { struct timespec64 now; if (ms < 0) return NULL; if (!ms) { to->tv_sec = 0; to->tv_nsec = 0; return to; } to->tv_sec = ms / MSEC_PER_SEC; to->tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC); ktime_get_ts64(&now); *to = timespec64_add_safe(now, *to); return to; } /* * autoremove_wake_function, but remove even on failure to wake up, because we * know that default_wake_function/ttwu will only fail if the thread is already * woken, and in that case the ep_poll loop will remove the entry anyways, not * try to reuse it. */ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode, int sync, void *key) { int ret = default_wake_function(wq_entry, mode, sync, key); /* * Pairs with list_empty_careful in ep_poll, and ensures future loop * iterations see the cause of this wakeup. */ list_del_init_careful(&wq_entry->entry); return ret; } /** * ep_poll - Retrieves ready events, and delivers them to the caller-supplied * event buffer. * * @ep: Pointer to the eventpoll context. * @events: Pointer to the userspace buffer where the ready events should be * stored. * @maxevents: Size (in terms of number of events) of the caller event buffer. * @timeout: Maximum timeout for the ready events fetch operation, in * timespec. If the timeout is zero, the function will not block, * while if the @timeout ptr is NULL, the function will block * until at least one event has been retrieved (or an error * occurred). * * Return: the number of ready events which have been fetched, or an * error code, in case of error. */ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout) { int res, eavail, timed_out = 0; u64 slack = 0; wait_queue_entry_t wait; ktime_t expires, *to = NULL; lockdep_assert_irqs_enabled(); if (timeout && (timeout->tv_sec | timeout->tv_nsec)) { slack = select_estimate_accuracy(timeout); to = &expires; *to = timespec64_to_ktime(*timeout); } else if (timeout) { /* * Avoid the unnecessary trip to the wait queue loop, if the * caller specified a non blocking operation. */ timed_out = 1; } /* * This call is racy: We may or may not see events that are being added * to the ready list under the lock (e.g., in IRQ callbacks). For cases * with a non-zero timeout, this thread will check the ready list under * lock and will add to the wait queue. For cases with a zero * timeout, the user by definition should not care and will have to * recheck again. */ eavail = ep_events_available(ep); while (1) { if (eavail) { /* * Try to transfer events to user space. In case we get * 0 events and there's still timeout left over, we go * trying again in search of more luck. */ res = ep_send_events(ep, events, maxevents); if (res) return res; } if (timed_out) return 0; eavail = ep_busy_loop(ep, timed_out); if (eavail) continue; if (signal_pending(current)) return -EINTR; /* * Internally init_wait() uses autoremove_wake_function(), * thus wait entry is removed from the wait queue on each * wakeup. Why it is important? In case of several waiters * each new wakeup will hit the next waiter, giving it the * chance to harvest new event. Otherwise wakeup can be * lost. This is also good performance-wise, because on * normal wakeup path no need to call __remove_wait_queue() * explicitly, thus ep->lock is not taken, which halts the * event delivery. * * In fact, we now use an even more aggressive function that * unconditionally removes, because we don't reuse the wait * entry between loop iterations. This lets us also avoid the * performance issue if a process is killed, causing all of its * threads to wake up without being removed normally. */ init_wait(&wait); wait.func = ep_autoremove_wake_function; write_lock_irq(&ep->lock); /* * Barrierless variant, waitqueue_active() is called under * the same lock on wakeup ep_poll_callback() side, so it * is safe to avoid an explicit barrier. */ __set_current_state(TASK_INTERRUPTIBLE); /* * Do the final check under the lock. ep_start/done_scan() * plays with two lists (->rdllist and ->ovflist) and there * is always a race when both lists are empty for short * period of time although events are pending, so lock is * important. */ eavail = ep_events_available(ep); if (!eavail) __add_wait_queue_exclusive(&ep->wq, &wait); write_unlock_irq(&ep->lock); if (!eavail) timed_out = !schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * We were woken up, thus go and try to harvest some events. * If timed out and still on the wait queue, recheck eavail * carefully under lock, below. */ eavail = 1; if (!list_empty_careful(&wait.entry)) { write_lock_irq(&ep->lock); /* * If the thread timed out and is not on the wait queue, * it means that the thread was woken up after its * timeout expired before it could reacquire the lock. * Thus, when wait.entry is empty, it needs to harvest * events. */ if (timed_out) eavail = list_empty(&wait.entry); __remove_wait_queue(&ep->wq, &wait); write_unlock_irq(&ep->lock); } } } /** * ep_loop_check_proc - verify that adding an epoll file inside another * epoll structure does not violate the constraints, in * terms of closed loops, or too deep chains (which can * result in excessive stack usage). * * @ep: the &struct eventpoll to be currently checked. * @depth: Current depth of the path being checked. * * Return: %zero if adding the epoll @file inside current epoll * structure @ep does not violate the constraints, or %-1 otherwise. */ static int ep_loop_check_proc(struct eventpoll *ep, int depth) { int error = 0; struct rb_node *rbp; struct epitem *epi; mutex_lock_nested(&ep->mtx, depth + 1); ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { struct eventpoll *ep_tovisit; ep_tovisit = epi->ffd.file->private_data; if (ep_tovisit->gen == loop_check_gen) continue; if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS) error = -1; else error = ep_loop_check_proc(ep_tovisit, depth + 1); if (error != 0) break; } else { /* * If we've reached a file that is not associated with * an ep, then we need to check if the newly added * links are going to add too many wakeup paths. We do * this by adding it to the tfile_check_list, if it's * not already there, and calling reverse_path_check() * during ep_insert(). */ list_file(epi->ffd.file); } } mutex_unlock(&ep->mtx); return error; } /** * ep_loop_check - Performs a check to verify that adding an epoll file (@to) * into another epoll file (represented by @ep) does not create * closed loops or too deep chains. * * @ep: Pointer to the epoll we are inserting into. * @to: Pointer to the epoll to be inserted. * * Return: %zero if adding the epoll @to inside the epoll @from * does not violate the constraints, or %-1 otherwise. */ static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to) { inserting_into = ep; return ep_loop_check_proc(to, 0); } static void clear_tfile_check_list(void) { rcu_read_lock(); while (tfile_check_list != EP_UNACTIVE_PTR) { struct epitems_head *head = tfile_check_list; tfile_check_list = head->next; unlist_file(head); } rcu_read_unlock(); } /* * Open an eventpoll file descriptor. */ static int do_epoll_create(int flags) { int error, fd; struct eventpoll *ep = NULL; struct file *file; /* Check the EPOLL_* constant for consistency. */ BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC); if (flags & ~EPOLL_CLOEXEC) return -EINVAL; /* * Create the internal data structure ("struct eventpoll"). */ error = ep_alloc(&ep); if (error < 0) return error; /* * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC)); if (fd < 0) { error = fd; goto out_free_ep; } file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep, O_RDWR | (flags & O_CLOEXEC)); if (IS_ERR(file)) { error = PTR_ERR(file); goto out_free_fd; } ep->file = file; fd_install(fd, file); return fd; out_free_fd: put_unused_fd(fd); out_free_ep: ep_clear_and_put(ep); return error; } SYSCALL_DEFINE1(epoll_create1, int, flags) { return do_epoll_create(flags); } SYSCALL_DEFINE1(epoll_create, int, size) { if (size <= 0) return -EINVAL; return do_epoll_create(0); } #ifdef CONFIG_PM_SLEEP static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) epev->events &= ~EPOLLWAKEUP; } #else static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { epev->events &= ~EPOLLWAKEUP; } #endif static inline int epoll_mutex_lock(struct mutex *mutex, int depth, bool nonblock) { if (!nonblock) { mutex_lock_nested(mutex, depth); return 0; } if (mutex_trylock(mutex)) return 0; return -EAGAIN; } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock) { int error; int full_check = 0; struct fd f, tf; struct eventpoll *ep; struct epitem *epi; struct eventpoll *tep = NULL; error = -EBADF; f = fdget(epfd); if (!f.file) goto error_return; /* Get the "struct file *" for the target file */ tf = fdget(fd); if (!tf.file) goto error_fput; /* The target file descriptor must support poll */ error = -EPERM; if (!file_can_poll(tf.file)) goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ if (ep_op_has_event(op)) ep_take_care_of_epollwakeup(epds); /* * We have to check that the file structure underneath the file descriptor * the user passed to us _is_ an eventpoll file. And also we do not permit * adding an epoll file descriptor inside itself. */ error = -EINVAL; if (f.file == tf.file || !is_file_epoll(f.file)) goto error_tgt_fput; /* * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only, * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation. * Also, we do not currently supported nested exclusive wakeups. */ if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) { if (op == EPOLL_CTL_MOD) goto error_tgt_fput; if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) || (epds->events & ~EPOLLEXCLUSIVE_OK_BITS))) goto error_tgt_fput; } /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = f.file->private_data; /* * When we insert an epoll file descriptor inside another epoll file * descriptor, there is the chance of creating closed loops, which are * better be handled here, than in more critical paths. While we are * checking for loops we also determine the list of files reachable * and hang them on the tfile_check_list, so we can check that we * haven't created too many possible wakeup paths. * * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when * the epoll file descriptor is attaching directly to a wakeup source, * unless the epoll file descriptor is nested. The purpose of taking the * 'epnested_mutex' on add is to prevent complex toplogies such as loops and * deep wakeup paths from forming in parallel through multiple * EPOLL_CTL_ADD operations. */ error = epoll_mutex_lock(&ep->mtx, 0, nonblock); if (error) goto error_tgt_fput; if (op == EPOLL_CTL_ADD) { if (READ_ONCE(f.file->f_ep) || ep->gen == loop_check_gen || is_file_epoll(tf.file)) { mutex_unlock(&ep->mtx); error = epoll_mutex_lock(&epnested_mutex, 0, nonblock); if (error) goto error_tgt_fput; loop_check_gen++; full_check = 1; if (is_file_epoll(tf.file)) { tep = tf.file->private_data; error = -ELOOP; if (ep_loop_check(ep, tep) != 0) goto error_tgt_fput; } error = epoll_mutex_lock(&ep->mtx, 0, nonblock); if (error) goto error_tgt_fput; } } /* * Try to lookup the file inside our RB tree. Since we grabbed "mtx" * above, we can be sure to be able to use the item looked up by * ep_find() till we release the mutex. */ epi = ep_find(ep, tf.file, fd); error = -EINVAL; switch (op) { case EPOLL_CTL_ADD: if (!epi) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_insert(ep, epds, tf.file, fd, full_check); } else error = -EEXIST; break; case EPOLL_CTL_DEL: if (epi) { /* * The eventpoll itself is still alive: the refcount * can't go to zero here. */ ep_remove_safe(ep, epi); error = 0; } else { error = -ENOENT; } break; case EPOLL_CTL_MOD: if (epi) { if (!(epi->event.events & EPOLLEXCLUSIVE)) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_modify(ep, epi, epds); } } else error = -ENOENT; break; } mutex_unlock(&ep->mtx); error_tgt_fput: if (full_check) { clear_tfile_check_list(); loop_check_gen++; mutex_unlock(&epnested_mutex); } fdput(tf); error_fput: fdput(f); error_return: return error; } /* * The following function implements the controller interface for * the eventpoll file that enables the insertion/removal/change of * file descriptors inside the interest set. */ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event) { struct epoll_event epds; if (ep_op_has_event(op) && copy_from_user(&epds, event, sizeof(struct epoll_event))) return -EFAULT; return do_epoll_ctl(epfd, op, fd, &epds, false); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_wait(2). */ static int do_epoll_wait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to) { int error; struct fd f; struct eventpoll *ep; /* The maximum number of event must be greater than zero */ if (maxevents <= 0 || maxevents > EP_MAX_EVENTS) return -EINVAL; /* Verify that the area passed by the user is writeable */ if (!access_ok(events, maxevents * sizeof(struct epoll_event))) return -EFAULT; /* Get the "struct file *" for the eventpoll file */ f = fdget(epfd); if (!f.file) return -EBADF; /* * We have to check that the file structure underneath the fd * the user passed to us _is_ an eventpoll file. */ error = -EINVAL; if (!is_file_epoll(f.file)) goto error_fput; /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = f.file->private_data; /* Time to fish for events ... */ error = ep_poll(ep, events, maxevents, to); error_fput: fdput(f); return error; } SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout) { struct timespec64 to; return do_epoll_wait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout)); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). */ static int do_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to, const sigset_t __user *sigmask, size_t sigsetsize) { int error; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ error = set_user_sigmask(sigmask, sigsetsize); if (error) return error; error = do_epoll_wait(epfd, events, maxevents, to); restore_saved_sigmask_unless(error == -EINTR); return error; } SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 to; return do_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #ifdef CONFIG_COMPAT static int do_compat_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize) { long err; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ err = set_compat_user_sigmask(sigmask, sigsetsize); if (err) return err; err = do_epoll_wait(epfd, events, maxevents, timeout); restore_saved_sigmask_unless(err == -EINTR); return err; } COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 to; return do_compat_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } COMPAT_SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_compat_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #endif static int __init eventpoll_init(void) { struct sysinfo si; si_meminfo(&si); /* * Allows top 4% of lomem to be allocated for epoll watches (per user). */ max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; BUG_ON(max_user_watches < 0); /* * We can have many thousands of epitems, so prevent this from * using an extra cache line on 64-bit (and smaller) CPUs */ BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128); /* Allocates slab cache used to allocate "struct epitem" items */ epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Allocates slab cache used to allocate "struct eppoll_entry" */ pwq_cache = kmem_cache_create("eventpoll_pwq", sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); epoll_sysctls_init(); ephead_cache = kmem_cache_create("ep_head", sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); return 0; } fs_initcall(eventpoll_init); |
| 92 92 5894 1066 4934 589 5447 5893 5895 5896 5891 434 435 137 138 137 116 897 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 | // SPDX-License-Identifier: GPL-2.0 /* * Tag allocation using scalable bitmaps. Uses active queue tracking to support * fairer distribution of tags between multiple submitters when a shared tag map * is used. * * Copyright (C) 2013-2014 Jens Axboe */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/delay.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-sched.h" /* * Recalculate wakeup batch when tag is shared by hctx. */ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, unsigned int users) { if (!users) return; sbitmap_queue_recalculate_wake_batch(&tags->bitmap_tags, users); sbitmap_queue_recalculate_wake_batch(&tags->breserved_tags, users); } /* * If a previously inactive queue goes active, bump the active user count. * We need to do this before try to allocate driver tag, then even if fail * to get tag when first time, the other shared-tag users could reserve * budget for it. */ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; unsigned long flags; struct blk_mq_tags *tags = hctx->tags; /* * calling test_bit() prior to test_and_set_bit() is intentional, * it avoids dirtying the cacheline if the queue is already active. */ if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) || test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; } else { if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) || test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; } spin_lock_irqsave(&tags->lock, flags); users = tags->active_queues + 1; WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); spin_unlock_irqrestore(&tags->lock, flags); } /* * Wakeup all potentially sleeping on tags */ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve) { sbitmap_queue_wake_all(&tags->bitmap_tags); if (include_reserve) sbitmap_queue_wake_all(&tags->breserved_tags); } /* * If a previously busy queue goes inactive, potential waiters could now * be allowed to queue. Wake them up and check. */ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->tags; unsigned int users; if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; } else { if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; } spin_lock_irq(&tags->lock); users = tags->active_queues - 1; WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); spin_unlock_irq(&tags->lock); blk_mq_tag_wakeup_all(tags, false); } static int __blk_mq_get_tag(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt) { if (!data->q->elevator && !(data->flags & BLK_MQ_REQ_RESERVED) && !hctx_may_queue(data->hctx, bt)) return BLK_MQ_NO_TAG; if (data->shallow_depth) return sbitmap_queue_get_shallow(bt, data->shallow_depth); else return __sbitmap_queue_get(bt); } unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags, unsigned int *offset) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct sbitmap_queue *bt = &tags->bitmap_tags; unsigned long ret; if (data->shallow_depth ||data->flags & BLK_MQ_REQ_RESERVED || data->hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) return 0; ret = __sbitmap_queue_get_batch(bt, nr_tags, offset); *offset += tags->nr_reserved_tags; return ret; } unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) { struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct sbitmap_queue *bt; struct sbq_wait_state *ws; DEFINE_SBQ_WAIT(wait); unsigned int tag_offset; int tag; if (data->flags & BLK_MQ_REQ_RESERVED) { if (unlikely(!tags->nr_reserved_tags)) { WARN_ON_ONCE(1); return BLK_MQ_NO_TAG; } bt = &tags->breserved_tags; tag_offset = 0; } else { bt = &tags->bitmap_tags; tag_offset = tags->nr_reserved_tags; } tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) goto found_tag; if (data->flags & BLK_MQ_REQ_NOWAIT) return BLK_MQ_NO_TAG; ws = bt_wait_ptr(bt, data->hctx); do { struct sbitmap_queue *bt_prev; /* * We're out of tags on this hardware queue, kick any * pending IO submits before going to sleep waiting for * some to complete. */ blk_mq_run_hw_queue(data->hctx, false); /* * Retry tag allocation after running the hardware queue, * as running the queue may also have found completions. */ tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) break; sbitmap_prepare_to_wait(bt, ws, &wait, TASK_UNINTERRUPTIBLE); tag = __blk_mq_get_tag(data, bt); if (tag != BLK_MQ_NO_TAG) break; bt_prev = bt; io_schedule(); sbitmap_finish_wait(bt, ws, &wait); data->ctx = blk_mq_get_ctx(data->q); data->hctx = blk_mq_map_queue(data->q, data->cmd_flags, data->ctx); tags = blk_mq_tags_from_data(data); if (data->flags & BLK_MQ_REQ_RESERVED) bt = &tags->breserved_tags; else bt = &tags->bitmap_tags; /* * If destination hw queue is changed, fake wake up on * previous queue for compensating the wake up miss, so * other allocations on previous queue won't be starved. */ if (bt != bt_prev) sbitmap_queue_wake_up(bt_prev, 1); ws = bt_wait_ptr(bt, data->hctx); } while (1); sbitmap_finish_wait(bt, ws, &wait); found_tag: /* * Give up this allocation if the hctx is inactive. The caller will * retry on an active hctx. */ if (unlikely(test_bit(BLK_MQ_S_INACTIVE, &data->hctx->state))) { blk_mq_put_tag(tags, data->ctx, tag + tag_offset); return BLK_MQ_NO_TAG; } return tag + tag_offset; } void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag) { if (!blk_mq_tag_is_reserved(tags, tag)) { const int real_tag = tag - tags->nr_reserved_tags; BUG_ON(real_tag >= tags->nr_tags); sbitmap_queue_clear(&tags->bitmap_tags, real_tag, ctx->cpu); } else { sbitmap_queue_clear(&tags->breserved_tags, tag, ctx->cpu); } } void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags) { sbitmap_queue_clear_batch(&tags->bitmap_tags, tags->nr_reserved_tags, tag_array, nr_tags); } struct bt_iter_data { struct blk_mq_hw_ctx *hctx; struct request_queue *q; busy_tag_iter_fn *fn; void *data; bool reserved; }; static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, unsigned int bitnr) { struct request *rq; unsigned long flags; spin_lock_irqsave(&tags->lock, flags); rq = tags->rqs[bitnr]; if (!rq || rq->tag != bitnr || !req_ref_inc_not_zero(rq)) rq = NULL; spin_unlock_irqrestore(&tags->lock, flags); return rq; } static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_iter_data *iter_data = data; struct blk_mq_hw_ctx *hctx = iter_data->hctx; struct request_queue *q = iter_data->q; struct blk_mq_tag_set *set = q->tag_set; struct blk_mq_tags *tags; struct request *rq; bool ret = true; if (blk_mq_is_shared_tags(set->flags)) tags = set->shared_tags; else tags = hctx->tags; if (!iter_data->reserved) bitnr += tags->nr_reserved_tags; /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; if (rq->q == q && (!hctx || rq->mq_hctx == hctx)) ret = iter_data->fn(rq, iter_data->data); blk_mq_put_rq_ref(rq); return ret; } /** * bt_for_each - iterate over the requests associated with a hardware queue * @hctx: Hardware queue to examine. * @q: Request queue to examine. * @bt: sbitmap to examine. This is either the breserved_tags member * or the bitmap_tags member of struct blk_mq_tags. * @fn: Pointer to the function that will be called for each request * associated with @hctx that has been assigned a driver tag. * @fn will be called as follows: @fn(@hctx, rq, @data, @reserved) * where rq is a pointer to a request. Return true to continue * iterating tags, false to stop. * @data: Will be passed as third argument to @fn. * @reserved: Indicates whether @bt is the breserved_tags member or the * bitmap_tags member of struct blk_mq_tags. */ static void bt_for_each(struct blk_mq_hw_ctx *hctx, struct request_queue *q, struct sbitmap_queue *bt, busy_tag_iter_fn *fn, void *data, bool reserved) { struct bt_iter_data iter_data = { .hctx = hctx, .fn = fn, .data = data, .reserved = reserved, .q = q, }; sbitmap_for_each_set(&bt->sb, bt_iter, &iter_data); } struct bt_tags_iter_data { struct blk_mq_tags *tags; busy_tag_iter_fn *fn; void *data; unsigned int flags; }; #define BT_TAG_ITER_RESERVED (1 << 0) #define BT_TAG_ITER_STARTED (1 << 1) #define BT_TAG_ITER_STATIC_RQS (1 << 2) static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_tags_iter_data *iter_data = data; struct blk_mq_tags *tags = iter_data->tags; struct request *rq; bool ret = true; bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS); if (!(iter_data->flags & BT_TAG_ITER_RESERVED)) bitnr += tags->nr_reserved_tags; /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ if (iter_static_rqs) rq = tags->static_rqs[bitnr]; else rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; if (!(iter_data->flags & BT_TAG_ITER_STARTED) || blk_mq_request_started(rq)) ret = iter_data->fn(rq, iter_data->data); if (!iter_static_rqs) blk_mq_put_rq_ref(rq); return ret; } /** * bt_tags_for_each - iterate over the requests in a tag map * @tags: Tag map to iterate over. * @bt: sbitmap to examine. This is either the breserved_tags member * or the bitmap_tags member of struct blk_mq_tags. * @fn: Pointer to the function that will be called for each started * request. @fn will be called as follows: @fn(rq, @data, * @reserved) where rq is a pointer to a request. Return true * to continue iterating tags, false to stop. * @data: Will be passed as second argument to @fn. * @flags: BT_TAG_ITER_* */ static void bt_tags_for_each(struct blk_mq_tags *tags, struct sbitmap_queue *bt, busy_tag_iter_fn *fn, void *data, unsigned int flags) { struct bt_tags_iter_data iter_data = { .tags = tags, .fn = fn, .data = data, .flags = flags, }; if (tags->rqs) sbitmap_for_each_set(&bt->sb, bt_tags_iter, &iter_data); } static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv, unsigned int flags) { WARN_ON_ONCE(flags & BT_TAG_ITER_RESERVED); if (tags->nr_reserved_tags) bt_tags_for_each(tags, &tags->breserved_tags, fn, priv, flags | BT_TAG_ITER_RESERVED); bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, flags); } /** * blk_mq_all_tag_iter - iterate over all requests in a tag map * @tags: Tag map to iterate over. * @fn: Pointer to the function that will be called for each * request. @fn will be called as follows: @fn(rq, @priv, * reserved) where rq is a pointer to a request. 'reserved' * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. * * Caller has to pass the tag map from which requests are allocated. */ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv) { __blk_mq_all_tag_iter(tags, fn, priv, BT_TAG_ITER_STATIC_RQS); } /** * blk_mq_tagset_busy_iter - iterate over all started requests in a tag set * @tagset: Tag set to iterate over. * @fn: Pointer to the function that will be called for each started * request. @fn will be called as follows: @fn(rq, @priv, * reserved) where rq is a pointer to a request. 'reserved' * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. * * We grab one request reference before calling @fn and release it after * @fn returns. */ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv) { unsigned int flags = tagset->flags; int i, nr_tags; nr_tags = blk_mq_is_shared_tags(flags) ? 1 : tagset->nr_hw_queues; for (i = 0; i < nr_tags; i++) { if (tagset->tags && tagset->tags[i]) __blk_mq_all_tag_iter(tagset->tags[i], fn, priv, BT_TAG_ITER_STARTED); } } EXPORT_SYMBOL(blk_mq_tagset_busy_iter); static bool blk_mq_tagset_count_completed_rqs(struct request *rq, void *data) { unsigned *count = data; if (blk_mq_request_completed(rq)) (*count)++; return true; } /** * blk_mq_tagset_wait_completed_request - Wait until all scheduled request * completions have finished. * @tagset: Tag set to drain completed request * * Note: This function has to be run after all IO queues are shutdown */ void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset) { while (true) { unsigned count = 0; blk_mq_tagset_busy_iter(tagset, blk_mq_tagset_count_completed_rqs, &count); if (!count) break; msleep(5); } } EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request); /** * blk_mq_queue_tag_busy_iter - iterate over all requests with a driver tag * @q: Request queue to examine. * @fn: Pointer to the function that will be called for each request * on @q. @fn will be called as follows: @fn(hctx, rq, @priv, * reserved) where rq is a pointer to a request and hctx points * to the hardware queue associated with the request. 'reserved' * indicates whether or not @rq is a reserved request. * @priv: Will be passed as third argument to @fn. * * Note: if @q->tag_set is shared with other request queues then @fn will be * called for all requests on all queues that share that tag set and not only * for requests associated with @q. */ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn, void *priv) { /* * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and hctx_table * while the queue is frozen. So we can use q_usage_counter to avoid * racing with it. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; if (blk_mq_is_shared_tags(q->tag_set->flags)) { struct blk_mq_tags *tags = q->tag_set->shared_tags; struct sbitmap_queue *bresv = &tags->breserved_tags; struct sbitmap_queue *btags = &tags->bitmap_tags; if (tags->nr_reserved_tags) bt_for_each(NULL, q, bresv, fn, priv, true); bt_for_each(NULL, q, btags, fn, priv, false); } else { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) { struct blk_mq_tags *tags = hctx->tags; struct sbitmap_queue *bresv = &tags->breserved_tags; struct sbitmap_queue *btags = &tags->bitmap_tags; /* * If no software queues are currently mapped to this * hardware queue, there's nothing to check */ if (!blk_mq_hw_queue_mapped(hctx)) continue; if (tags->nr_reserved_tags) bt_for_each(hctx, q, bresv, fn, priv, true); bt_for_each(hctx, q, btags, fn, priv, false); } } blk_queue_exit(q); } static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, bool round_robin, int node) { return sbitmap_queue_init_node(bt, depth, -1, round_robin, GFP_KERNEL, node); } int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, struct sbitmap_queue *breserved_tags, unsigned int queue_depth, unsigned int reserved, int node, int alloc_policy) { unsigned int depth = queue_depth - reserved; bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; if (bt_alloc(bitmap_tags, depth, round_robin, node)) return -ENOMEM; if (bt_alloc(breserved_tags, reserved, round_robin, node)) goto free_bitmap_tags; return 0; free_bitmap_tags: sbitmap_queue_free(bitmap_tags); return -ENOMEM; } struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, unsigned int reserved_tags, int node, int alloc_policy) { struct blk_mq_tags *tags; if (total_tags > BLK_MQ_TAG_MAX) { pr_err("blk-mq: tag depth too large\n"); return NULL; } tags = kzalloc_node(sizeof(*tags), GFP_KERNEL, node); if (!tags) return NULL; tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; spin_lock_init(&tags->lock); if (blk_mq_init_bitmaps(&tags->bitmap_tags, &tags->breserved_tags, total_tags, reserved_tags, node, alloc_policy) < 0) { kfree(tags); return NULL; } return tags; } void blk_mq_free_tags(struct blk_mq_tags *tags) { sbitmap_queue_free(&tags->bitmap_tags); sbitmap_queue_free(&tags->breserved_tags); kfree(tags); } int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tagsptr, unsigned int tdepth, bool can_grow) { struct blk_mq_tags *tags = *tagsptr; if (tdepth <= tags->nr_reserved_tags) return -EINVAL; /* * If we are allowed to grow beyond the original size, allocate * a new set of tags before freeing the old one. */ if (tdepth > tags->nr_tags) { struct blk_mq_tag_set *set = hctx->queue->tag_set; struct blk_mq_tags *new; if (!can_grow) return -EINVAL; /* * We need some sort of upper limit, set it high enough that * no valid use cases should require more. */ if (tdepth > MAX_SCHED_RQ) return -EINVAL; /* * Only the sbitmap needs resizing since we allocated the max * initially. */ if (blk_mq_is_shared_tags(set->flags)) return 0; new = blk_mq_alloc_map_and_rqs(set, hctx->queue_num, tdepth); if (!new) return -ENOMEM; blk_mq_free_map_and_rqs(set, *tagsptr, hctx->queue_num); *tagsptr = new; } else { /* * Don't need (or can't) update reserved tags here, they * remain static and should never need resizing. */ sbitmap_queue_resize(&tags->bitmap_tags, tdepth - tags->nr_reserved_tags); } return 0; } void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, unsigned int size) { struct blk_mq_tags *tags = set->shared_tags; sbitmap_queue_resize(&tags->bitmap_tags, size - set->reserved_tags); } void blk_mq_tag_update_sched_shared_tags(struct request_queue *q) { sbitmap_queue_resize(&q->sched_shared_tags->bitmap_tags, q->nr_requests - q->tag_set->reserved_tags); } /** * blk_mq_unique_tag() - return a tag that is unique queue-wide * @rq: request for which to compute a unique tag * * The tag field in struct request is unique per hardware queue but not over * all hardware queues. Hence this function that returns a tag with the * hardware context index in the upper bits and the per hardware queue tag in * the lower bits. * * Note: When called for a request that is queued on a non-multiqueue request * queue, the hardware context index is set to zero. */ u32 blk_mq_unique_tag(struct request *rq) { return (rq->mq_hctx->queue_num << BLK_MQ_UNIQUE_TAG_BITS) | (rq->tag & BLK_MQ_UNIQUE_TAG_MASK); } EXPORT_SYMBOL(blk_mq_unique_tag); |
| 4 4 649 650 8 294 293 1142 1143 266 266 413 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> #include <linux/rhashtable.h> #include <linux/netdevice.h> #include <net/ip.h> #include <net/ip6_route.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_tuple.h> static DEFINE_MUTEX(flowtable_lock); static LIST_HEAD(flowtables); static void flow_offload_fill_dir(struct flow_offload *flow, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple; struct nf_conntrack_tuple *ctt = &flow->ct->tuplehash[dir].tuple; ft->dir = dir; switch (ctt->src.l3num) { case NFPROTO_IPV4: ft->src_v4 = ctt->src.u3.in; ft->dst_v4 = ctt->dst.u3.in; break; case NFPROTO_IPV6: ft->src_v6 = ctt->src.u3.in6; ft->dst_v6 = ctt->dst.u3.in6; break; } ft->l3proto = ctt->src.l3num; ft->l4proto = ctt->dst.protonum; switch (ctt->dst.protonum) { case IPPROTO_TCP: case IPPROTO_UDP: ft->src_port = ctt->src.u.tcp.port; ft->dst_port = ctt->dst.u.tcp.port; break; } } struct flow_offload *flow_offload_alloc(struct nf_conn *ct) { struct flow_offload *flow; if (unlikely(nf_ct_is_dying(ct))) return NULL; flow = kzalloc(sizeof(*flow), GFP_ATOMIC); if (!flow) return NULL; refcount_inc(&ct->ct_general.use); flow->ct = ct; flow_offload_fill_dir(flow, FLOW_OFFLOAD_DIR_ORIGINAL); flow_offload_fill_dir(flow, FLOW_OFFLOAD_DIR_REPLY); if (ct->status & IPS_SRC_NAT) __set_bit(NF_FLOW_SNAT, &flow->flags); if (ct->status & IPS_DST_NAT) __set_bit(NF_FLOW_DNAT, &flow->flags); return flow; } EXPORT_SYMBOL_GPL(flow_offload_alloc); static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple) { if (flow_tuple->l3proto == NFPROTO_IPV6) return rt6_get_cookie(dst_rt6_info(flow_tuple->dst_cache)); return 0; } static struct dst_entry *nft_route_dst_fetch(struct nf_flow_route *route, enum flow_offload_tuple_dir dir) { struct dst_entry *dst = route->tuple[dir].dst; route->tuple[dir].dst = NULL; return dst; } static int flow_offload_fill_route(struct flow_offload *flow, struct nf_flow_route *route, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; struct dst_entry *dst = nft_route_dst_fetch(route, dir); int i, j = 0; switch (flow_tuple->l3proto) { case NFPROTO_IPV4: flow_tuple->mtu = ip_dst_mtu_maybe_forward(dst, true); break; case NFPROTO_IPV6: flow_tuple->mtu = ip6_dst_mtu_maybe_forward(dst, true); break; } flow_tuple->iifidx = route->tuple[dir].in.ifindex; for (i = route->tuple[dir].in.num_encaps - 1; i >= 0; i--) { flow_tuple->encap[j].id = route->tuple[dir].in.encap[i].id; flow_tuple->encap[j].proto = route->tuple[dir].in.encap[i].proto; if (route->tuple[dir].in.ingress_vlans & BIT(i)) flow_tuple->in_vlan_ingress |= BIT(j); j++; } flow_tuple->encap_num = route->tuple[dir].in.num_encaps; switch (route->tuple[dir].xmit_type) { case FLOW_OFFLOAD_XMIT_DIRECT: memcpy(flow_tuple->out.h_dest, route->tuple[dir].out.h_dest, ETH_ALEN); memcpy(flow_tuple->out.h_source, route->tuple[dir].out.h_source, ETH_ALEN); flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex; dst_release(dst); break; case FLOW_OFFLOAD_XMIT_XFRM: case FLOW_OFFLOAD_XMIT_NEIGH: flow_tuple->dst_cache = dst; flow_tuple->dst_cookie = flow_offload_dst_cookie(flow_tuple); break; default: WARN_ON_ONCE(1); break; } flow_tuple->xmit_type = route->tuple[dir].xmit_type; return 0; } static void nft_flow_dst_release(struct flow_offload *flow, enum flow_offload_tuple_dir dir) { if (flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM) dst_release(flow->tuplehash[dir].tuple.dst_cache); } void flow_offload_route_init(struct flow_offload *flow, struct nf_flow_route *route) { flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); flow->type = NF_FLOW_OFFLOAD_ROUTE; } EXPORT_SYMBOL_GPL(flow_offload_route_init); static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) { tcp->seen[0].td_maxwin = 0; tcp->seen[1].td_maxwin = 0; } static void flow_offload_fixup_ct(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); s32 timeout; if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); flow_offload_fixup_tcp(&ct->proto.tcp); timeout = tn->timeouts[ct->proto.tcp.state]; timeout -= tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); enum udp_conntrack state = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? UDP_CT_REPLIED : UDP_CT_UNREPLIED; timeout = tn->timeouts[state]; timeout -= tn->offload_timeout; } else { return; } if (timeout < 0) timeout = 0; if (nf_flow_timeout_delta(READ_ONCE(ct->timeout)) > (__s32)timeout) WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout); } static void flow_offload_route_release(struct flow_offload *flow) { nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_REPLY); } void flow_offload_free(struct flow_offload *flow) { switch (flow->type) { case NF_FLOW_OFFLOAD_ROUTE: flow_offload_route_release(flow); break; default: break; } nf_ct_put(flow->ct); kfree_rcu(flow, rcu_head); } EXPORT_SYMBOL_GPL(flow_offload_free); static u32 flow_offload_hash(const void *data, u32 len, u32 seed) { const struct flow_offload_tuple *tuple = data; return jhash(tuple, offsetof(struct flow_offload_tuple, __hash), seed); } static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed) { const struct flow_offload_tuple_rhash *tuplehash = data; return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, __hash), seed); } static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct flow_offload_tuple *tuple = arg->key; const struct flow_offload_tuple_rhash *x = ptr; if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, __hash))) return 1; return 0; } static const struct rhashtable_params nf_flow_offload_rhash_params = { .head_offset = offsetof(struct flow_offload_tuple_rhash, node), .hashfn = flow_offload_hash, .obj_hashfn = flow_offload_hash_obj, .obj_cmpfn = flow_offload_hash_cmp, .automatic_shrinking = true, }; unsigned long flow_offload_get_timeout(struct flow_offload *flow) { unsigned long timeout = NF_FLOW_TIMEOUT; struct net *net = nf_ct_net(flow->ct); int l4num = nf_ct_protonum(flow->ct); if (l4num == IPPROTO_TCP) { struct nf_tcp_net *tn = nf_tcp_pernet(net); timeout = tn->offload_timeout; } else if (l4num == IPPROTO_UDP) { struct nf_udp_net *tn = nf_udp_pernet(net); timeout = tn->offload_timeout; } return timeout; } int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) { int err; flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); err = rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[0].node, nf_flow_offload_rhash_params); if (err < 0) return err; err = rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[1].node, nf_flow_offload_rhash_params); if (err < 0) { rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[0].node, nf_flow_offload_rhash_params); return err; } nf_ct_offload_timeout(flow->ct); if (nf_flowtable_hw_offload(flow_table)) { __set_bit(NF_FLOW_HW, &flow->flags); nf_flow_offload_add(flow_table, flow); } return 0; } EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, struct flow_offload *flow, bool force) { u32 timeout; timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); if (force || timeout - READ_ONCE(flow->timeout) > HZ) WRITE_ONCE(flow->timeout, timeout); else return; if (likely(!nf_flowtable_hw_offload(flow_table))) return; nf_flow_offload_add(flow_table, flow); } EXPORT_SYMBOL_GPL(flow_offload_refresh); static inline bool nf_flow_has_expired(const struct flow_offload *flow) { return nf_flow_timeout_delta(flow->timeout) <= 0; } static void flow_offload_del(struct nf_flowtable *flow_table, struct flow_offload *flow) { rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node, nf_flow_offload_rhash_params); rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, nf_flow_offload_rhash_params); flow_offload_free(flow); } void flow_offload_teardown(struct flow_offload *flow) { clear_bit(IPS_OFFLOAD_BIT, &flow->ct->status); set_bit(NF_FLOW_TEARDOWN, &flow->flags); flow_offload_fixup_ct(flow->ct); } EXPORT_SYMBOL_GPL(flow_offload_teardown); struct flow_offload_tuple_rhash * flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple) { struct flow_offload_tuple_rhash *tuplehash; struct flow_offload *flow; int dir; tuplehash = rhashtable_lookup(&flow_table->rhashtable, tuple, nf_flow_offload_rhash_params); if (!tuplehash) return NULL; dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) return NULL; if (unlikely(nf_ct_is_dying(flow->ct))) return NULL; return tuplehash; } EXPORT_SYMBOL_GPL(flow_offload_lookup); static int nf_flow_table_iterate(struct nf_flowtable *flow_table, void (*iter)(struct nf_flowtable *flowtable, struct flow_offload *flow, void *data), void *data) { struct flow_offload_tuple_rhash *tuplehash; struct rhashtable_iter hti; struct flow_offload *flow; int err = 0; rhashtable_walk_enter(&flow_table->rhashtable, &hti); rhashtable_walk_start(&hti); while ((tuplehash = rhashtable_walk_next(&hti))) { if (IS_ERR(tuplehash)) { if (PTR_ERR(tuplehash) != -EAGAIN) { err = PTR_ERR(tuplehash); break; } continue; } if (tuplehash->tuple.dir) continue; flow = container_of(tuplehash, struct flow_offload, tuplehash[0]); iter(flow_table, flow, data); } rhashtable_walk_stop(&hti); rhashtable_walk_exit(&hti); return err; } static bool nf_flow_custom_gc(struct nf_flowtable *flow_table, const struct flow_offload *flow) { return flow_table->type->gc && flow_table->type->gc(flow); } static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || nf_flow_custom_gc(flow_table, flow)) flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { if (test_bit(NF_FLOW_HW, &flow->flags)) { if (!test_bit(NF_FLOW_HW_DYING, &flow->flags)) nf_flow_offload_del(flow_table, flow); else if (test_bit(NF_FLOW_HW_DEAD, &flow->flags)) flow_offload_del(flow_table, flow); } else { flow_offload_del(flow_table, flow); } } else if (test_bit(NF_FLOW_HW, &flow->flags)) { nf_flow_offload_stats(flow_table, flow); } } void nf_flow_table_gc_run(struct nf_flowtable *flow_table) { nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, NULL); } static void nf_flow_offload_work_gc(struct work_struct *work) { struct nf_flowtable *flow_table; flow_table = container_of(work, struct nf_flowtable, gc_work.work); nf_flow_table_gc_run(flow_table); queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } static void nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, __be16 port, __be16 new_port) { struct tcphdr *tcph; tcph = (void *)(skb_network_header(skb) + thoff); inet_proto_csum_replace2(&tcph->check, skb, port, new_port, false); } static void nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff, __be16 port, __be16 new_port) { struct udphdr *udph; udph = (void *)(skb_network_header(skb) + thoff); if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace2(&udph->check, skb, port, new_port, false); if (!udph->check) udph->check = CSUM_MANGLED_0; } } static void nf_flow_nat_port(struct sk_buff *skb, unsigned int thoff, u8 protocol, __be16 port, __be16 new_port) { switch (protocol) { case IPPROTO_TCP: nf_flow_nat_port_tcp(skb, thoff, port, new_port); break; case IPPROTO_UDP: nf_flow_nat_port_udp(skb, thoff, port, new_port); break; } } void nf_flow_snat_port(const struct flow_offload *flow, struct sk_buff *skb, unsigned int thoff, u8 protocol, enum flow_offload_tuple_dir dir) { struct flow_ports *hdr; __be16 port, new_port; hdr = (void *)(skb_network_header(skb) + thoff); switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: port = hdr->source; new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; hdr->source = new_port; break; case FLOW_OFFLOAD_DIR_REPLY: port = hdr->dest; new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; hdr->dest = new_port; break; } nf_flow_nat_port(skb, thoff, protocol, port, new_port); } EXPORT_SYMBOL_GPL(nf_flow_snat_port); void nf_flow_dnat_port(const struct flow_offload *flow, struct sk_buff *skb, unsigned int thoff, u8 protocol, enum flow_offload_tuple_dir dir) { struct flow_ports *hdr; __be16 port, new_port; hdr = (void *)(skb_network_header(skb) + thoff); switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: port = hdr->dest; new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port; hdr->dest = new_port; break; case FLOW_OFFLOAD_DIR_REPLY: port = hdr->source; new_port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port; hdr->source = new_port; break; } nf_flow_nat_port(skb, thoff, protocol, port, new_port); } EXPORT_SYMBOL_GPL(nf_flow_dnat_port); int nf_flow_table_init(struct nf_flowtable *flowtable) { int err; INIT_DELAYED_WORK(&flowtable->gc_work, nf_flow_offload_work_gc); flow_block_init(&flowtable->flow_block); init_rwsem(&flowtable->flow_block_lock); err = rhashtable_init(&flowtable->rhashtable, &nf_flow_offload_rhash_params); if (err < 0) return err; queue_delayed_work(system_power_efficient_wq, &flowtable->gc_work, HZ); mutex_lock(&flowtable_lock); list_add(&flowtable->list, &flowtables); mutex_unlock(&flowtable_lock); return 0; } EXPORT_SYMBOL_GPL(nf_flow_table_init); static void nf_flow_table_do_cleanup(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { struct net_device *dev = data; if (!dev) { flow_offload_teardown(flow); return; } if (net_eq(nf_ct_net(flow->ct), dev_net(dev)) && (flow->tuplehash[0].tuple.iifidx == dev->ifindex || flow->tuplehash[1].tuple.iifidx == dev->ifindex)) flow_offload_teardown(flow); } void nf_flow_table_gc_cleanup(struct nf_flowtable *flowtable, struct net_device *dev) { nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev); flush_delayed_work(&flowtable->gc_work); nf_flow_table_offload_flush(flowtable); } void nf_flow_table_cleanup(struct net_device *dev) { struct nf_flowtable *flowtable; mutex_lock(&flowtable_lock); list_for_each_entry(flowtable, &flowtables, list) nf_flow_table_gc_cleanup(flowtable, dev); mutex_unlock(&flowtable_lock); } EXPORT_SYMBOL_GPL(nf_flow_table_cleanup); void nf_flow_table_free(struct nf_flowtable *flow_table) { mutex_lock(&flowtable_lock); list_del(&flow_table->list); mutex_unlock(&flowtable_lock); cancel_delayed_work_sync(&flow_table->gc_work); nf_flow_table_offload_flush(flow_table); /* ... no more pending work after this stage ... */ nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL); nf_flow_table_gc_run(flow_table); nf_flow_table_offload_flush_cleanup(flow_table); rhashtable_destroy(&flow_table->rhashtable); } EXPORT_SYMBOL_GPL(nf_flow_table_free); static int nf_flow_table_init_net(struct net *net) { net->ft.stat = alloc_percpu(struct nf_flow_table_stat); return net->ft.stat ? 0 : -ENOMEM; } static void nf_flow_table_fini_net(struct net *net) { free_percpu(net->ft.stat); } static int nf_flow_table_pernet_init(struct net *net) { int ret; ret = nf_flow_table_init_net(net); if (ret < 0) return ret; ret = nf_flow_table_init_proc(net); if (ret < 0) goto out_proc; return 0; out_proc: nf_flow_table_fini_net(net); return ret; } static void nf_flow_table_pernet_exit(struct list_head *net_exit_list) { struct net *net; list_for_each_entry(net, net_exit_list, exit_list) { nf_flow_table_fini_proc(net); nf_flow_table_fini_net(net); } } static struct pernet_operations nf_flow_table_net_ops = { .init = nf_flow_table_pernet_init, .exit_batch = nf_flow_table_pernet_exit, }; static int __init nf_flow_table_module_init(void) { int ret; ret = register_pernet_subsys(&nf_flow_table_net_ops); if (ret < 0) return ret; ret = nf_flow_table_offload_init(); if (ret) goto out_offload; ret = nf_flow_register_bpf(); if (ret) goto out_bpf; return 0; out_bpf: nf_flow_table_offload_exit(); out_offload: unregister_pernet_subsys(&nf_flow_table_net_ops); return ret; } static void __exit nf_flow_table_module_exit(void) { nf_flow_table_offload_exit(); unregister_pernet_subsys(&nf_flow_table_net_ops); } module_init(nf_flow_table_module_init); module_exit(nf_flow_table_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("Netfilter flow table module"); |
| 2 2 14 116 130 108 20 2 135 2 131 2 22 81 29 99 4 5 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C)2002 USAGI/WIDE Project * * Authors * * Mitsuru KANDA @USAGI : IPv6 Support * Kazunori MIYAZAWA @USAGI : * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * * This file is derived from net/ipv4/esp.c */ #define pr_fmt(fmt) "IPv6: " fmt #include <crypto/aead.h> #include <crypto/authenc.h> #include <linux/err.h> #include <linux/module.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/esp.h> #include <linux/scatterlist.h> #include <linux/kernel.h> #include <linux/pfkeyv2.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/ip6_checksum.h> #include <net/ip6_route.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/udp.h> #include <linux/icmpv6.h> #include <net/tcp.h> #include <net/espintcp.h> #include <net/inet6_hashtables.h> #include <linux/skbuff_ref.h> #include <linux/highmem.h> struct esp_skb_cb { struct xfrm_skb_cb xfrm; void *tmp; }; struct esp_output_extra { __be32 seqhi; u32 esphoff; }; #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0])) /* * Allocate an AEAD request structure with extra space for SG and IV. * * For alignment considerations the upper 32 bits of the sequence number are * placed at the front, if present. Followed by the IV, the request and finally * the SG list. * * TODO: Use spare space in skb for this where possible. */ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqihlen) { unsigned int len; len = seqihlen; len += crypto_aead_ivsize(aead); if (len) { len += crypto_aead_alignmask(aead) & ~(crypto_tfm_ctx_alignment() - 1); len = ALIGN(len, crypto_tfm_ctx_alignment()); } len += sizeof(struct aead_request) + crypto_aead_reqsize(aead); len = ALIGN(len, __alignof__(struct scatterlist)); len += sizeof(struct scatterlist) * nfrags; return kmalloc(len, GFP_ATOMIC); } static inline void *esp_tmp_extra(void *tmp) { return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra)); } static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen) { return crypto_aead_ivsize(aead) ? PTR_ALIGN((u8 *)tmp + seqhilen, crypto_aead_alignmask(aead) + 1) : tmp + seqhilen; } static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv) { struct aead_request *req; req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead), crypto_tfm_ctx_alignment()); aead_request_set_tfm(req, aead); return req; } static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead, struct aead_request *req) { return (void *)ALIGN((unsigned long)(req + 1) + crypto_aead_reqsize(aead), __alignof__(struct scatterlist)); } static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) { struct crypto_aead *aead = x->data; int extralen = 0; u8 *iv; struct aead_request *req; struct scatterlist *sg; if (x->props.flags & XFRM_STATE_ESN) extralen += sizeof(struct esp_output_extra); iv = esp_tmp_iv(aead, tmp, extralen); req = esp_tmp_req(aead, iv); /* Unref skb_frag_pages in the src scatterlist if necessary. * Skip the first sg which comes from skb->data. */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) skb_page_unref(page_to_netmem(sg_page(sg)), skb->pp_recycle); } #ifdef CONFIG_INET6_ESPINTCP struct esp_tcp_sk { struct sock *sk; struct rcu_head rcu; }; static void esp_free_tcp_sk(struct rcu_head *head) { struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); sock_put(esk->sk); kfree(esk); } static struct sock *esp6_find_tcp_sk(struct xfrm_state *x) { struct xfrm_encap_tmpl *encap = x->encap; struct net *net = xs_net(x); struct esp_tcp_sk *esk; __be16 sport, dport; struct sock *nsk; struct sock *sk; sk = rcu_dereference(x->encap_sk); if (sk && sk->sk_state == TCP_ESTABLISHED) return sk; spin_lock_bh(&x->lock); sport = encap->encap_sport; dport = encap->encap_dport; nsk = rcu_dereference_protected(x->encap_sk, lockdep_is_held(&x->lock)); if (sk && sk == nsk) { esk = kmalloc(sizeof(*esk), GFP_ATOMIC); if (!esk) { spin_unlock_bh(&x->lock); return ERR_PTR(-ENOMEM); } RCU_INIT_POINTER(x->encap_sk, NULL); esk->sk = sk; call_rcu(&esk->rcu, esp_free_tcp_sk); } spin_unlock_bh(&x->lock); sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6, dport, &x->props.saddr.in6, ntohs(sport), 0, 0); if (!sk) return ERR_PTR(-ENOENT); if (!tcp_is_ulp_esp(sk)) { sock_put(sk); return ERR_PTR(-EINVAL); } spin_lock_bh(&x->lock); nsk = rcu_dereference_protected(x->encap_sk, lockdep_is_held(&x->lock)); if (encap->encap_sport != sport || encap->encap_dport != dport) { sock_put(sk); sk = nsk ?: ERR_PTR(-EREMCHG); } else if (sk == nsk) { sock_put(sk); } else { rcu_assign_pointer(x->encap_sk, sk); } spin_unlock_bh(&x->lock); return sk; } static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) { struct sock *sk; int err; rcu_read_lock(); sk = esp6_find_tcp_sk(x); err = PTR_ERR_OR_ZERO(sk); if (err) goto out; bh_lock_sock(sk); if (sock_owned_by_user(sk)) err = espintcp_queue_out(sk, skb); else err = espintcp_push_skb(sk, skb); bh_unlock_sock(sk); out: rcu_read_unlock(); return err; } static int esp_output_tcp_encap_cb(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; return esp_output_tcp_finish(x, skb); } static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) { int err; local_bh_disable(); err = xfrm_trans_queue_net(xs_net(x), skb, esp_output_tcp_encap_cb); local_bh_enable(); /* EINPROGRESS just happens to do the right thing. It * actually means that the skb has been consumed and * isn't coming back. */ return err ?: -EINPROGRESS; } #else static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) { WARN_ON(1); return -EOPNOTSUPP; } #endif static void esp_output_encap_csum(struct sk_buff *skb) { /* UDP encap with IPv6 requires a valid checksum */ if (*skb_mac_header(skb) == IPPROTO_UDP) { struct udphdr *uh = udp_hdr(skb); struct ipv6hdr *ip6h = ipv6_hdr(skb); int len = ntohs(uh->len); unsigned int offset = skb_transport_offset(skb); __wsum csum = skb_checksum(skb, offset, skb->len - offset, 0); uh->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, len, IPPROTO_UDP, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } } static void esp_output_done(void *data, int err) { struct sk_buff *skb = data; struct xfrm_offload *xo = xfrm_offload(skb); void *tmp; struct xfrm_state *x; if (xo && (xo->flags & XFRM_DEV_RESUME)) { struct sec_path *sp = skb_sec_path(skb); x = sp->xvec[sp->len - 1]; } else { x = skb_dst(skb)->xfrm; } tmp = ESP_SKB_CB(skb)->tmp; esp_ssg_unref(x, tmp, skb); kfree(tmp); esp_output_encap_csum(skb); if (xo && (xo->flags & XFRM_DEV_RESUME)) { if (err) { XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); kfree_skb(skb); return; } skb_push(skb, skb->data - skb_mac_header(skb)); secpath_reset(skb); xfrm_dev_resume(skb); } else { if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else xfrm_output_resume(skb->sk, skb, err); } } /* Move ESP header back into place. */ static void esp_restore_header(struct sk_buff *skb, unsigned int offset) { struct ip_esp_hdr *esph = (void *)(skb->data + offset); void *tmp = ESP_SKB_CB(skb)->tmp; __be32 *seqhi = esp_tmp_extra(tmp); esph->seq_no = esph->spi; esph->spi = *seqhi; } static void esp_output_restore_header(struct sk_buff *skb) { void *tmp = ESP_SKB_CB(skb)->tmp; struct esp_output_extra *extra = esp_tmp_extra(tmp); esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff - sizeof(__be32)); } static struct ip_esp_hdr *esp_output_set_esn(struct sk_buff *skb, struct xfrm_state *x, struct ip_esp_hdr *esph, struct esp_output_extra *extra) { /* For ESN we move the header forward by 4 bytes to * accommodate the high bits. We will move it back after * encryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { __u32 seqhi; struct xfrm_offload *xo = xfrm_offload(skb); if (xo) seqhi = xo->seq.hi; else seqhi = XFRM_SKB_CB(skb)->seq.output.hi; extra->esphoff = (unsigned char *)esph - skb_transport_header(skb); esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4); extra->seqhi = esph->spi; esph->seq_no = htonl(seqhi); } esph->spi = x->id.spi; return esph; } static void esp_output_done_esn(void *data, int err) { struct sk_buff *skb = data; esp_output_restore_header(skb); esp_output_done(data, err); } static struct ip_esp_hdr *esp6_output_udp_encap(struct sk_buff *skb, int encap_type, struct esp_info *esp, __be16 sport, __be16 dport) { struct udphdr *uh; unsigned int len; len = skb->len + esp->tailen - skb_transport_offset(skb); if (len > U16_MAX) return ERR_PTR(-EMSGSIZE); uh = (struct udphdr *)esp->esph; uh->source = sport; uh->dest = dport; uh->len = htons(len); uh->check = 0; *skb_mac_header(skb) = IPPROTO_UDP; return (struct ip_esp_hdr *)(uh + 1); } #ifdef CONFIG_INET6_ESPINTCP static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) { __be16 *lenp = (void *)esp->esph; struct ip_esp_hdr *esph; unsigned int len; struct sock *sk; len = skb->len + esp->tailen - skb_transport_offset(skb); if (len > IP_MAX_MTU) return ERR_PTR(-EMSGSIZE); rcu_read_lock(); sk = esp6_find_tcp_sk(x); rcu_read_unlock(); if (IS_ERR(sk)) return ERR_CAST(sk); *lenp = htons(len); esph = (struct ip_esp_hdr *)(lenp + 1); return esph; } #else static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) { return ERR_PTR(-EOPNOTSUPP); } #endif static int esp6_output_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) { struct xfrm_encap_tmpl *encap = x->encap; struct ip_esp_hdr *esph; __be16 sport, dport; int encap_type; spin_lock_bh(&x->lock); sport = encap->encap_sport; dport = encap->encap_dport; encap_type = encap->encap_type; spin_unlock_bh(&x->lock); switch (encap_type) { default: case UDP_ENCAP_ESPINUDP: esph = esp6_output_udp_encap(skb, encap_type, esp, sport, dport); break; case TCP_ENCAP_ESPINTCP: esph = esp6_output_tcp_encap(x, skb, esp); break; } if (IS_ERR(esph)) return PTR_ERR(esph); esp->esph = esph; return 0; } int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) { u8 *tail; int nfrags; int esph_offset; struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; if (x->encap) { int err = esp6_output_encap(x, skb, esp); if (err < 0) return err; } if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { if (tailen <= skb_tailroom(skb)) { nfrags = 1; trailer = skb; tail = skb_tail_pointer(trailer); goto skip_cow; } else if ((skb_shinfo(skb)->nr_frags < MAX_SKB_FRAGS) && !skb_has_frag_list(skb)) { int allocsize; struct sock *sk = skb->sk; struct page_frag *pfrag = &x->xfrag; esp->inplace = false; allocsize = ALIGN(tailen, L1_CACHE_BYTES); spin_lock_bh(&x->lock); if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) { spin_unlock_bh(&x->lock); goto cow; } page = pfrag->page; get_page(page); tail = page_address(page) + pfrag->offset; esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto); nfrags = skb_shinfo(skb)->nr_frags; __skb_fill_page_desc(skb, nfrags, page, pfrag->offset, tailen); skb_shinfo(skb)->nr_frags = ++nfrags; pfrag->offset = pfrag->offset + allocsize; spin_unlock_bh(&x->lock); nfrags++; skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; } } cow: esph_offset = (unsigned char *)esp->esph - skb_transport_header(skb); nfrags = skb_cow_data(skb, tailen, &trailer); if (nfrags < 0) goto out; tail = skb_tail_pointer(trailer); esp->esph = (struct ip_esp_hdr *)(skb_transport_header(skb) + esph_offset); skip_cow: esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto); pskb_put(skb, trailer, tailen); out: return nfrags; } EXPORT_SYMBOL_GPL(esp6_output_head); int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) { u8 *iv; int alen; void *tmp; int ivlen; int assoclen; int extralen; struct page *page; struct ip_esp_hdr *esph; struct aead_request *req; struct crypto_aead *aead; struct scatterlist *sg, *dsg; struct esp_output_extra *extra; int err = -ENOMEM; assoclen = sizeof(struct ip_esp_hdr); extralen = 0; if (x->props.flags & XFRM_STATE_ESN) { extralen += sizeof(*extra); assoclen += sizeof(__be32); } aead = x->data; alen = crypto_aead_authsize(aead); ivlen = crypto_aead_ivsize(aead); tmp = esp_alloc_tmp(aead, esp->nfrags + 2, extralen); if (!tmp) goto error; extra = esp_tmp_extra(tmp); iv = esp_tmp_iv(aead, tmp, extralen); req = esp_tmp_req(aead, iv); sg = esp_req_sg(aead, req); if (esp->inplace) dsg = sg; else dsg = &sg[esp->nfrags]; esph = esp_output_set_esn(skb, x, esp->esph, extra); esp->esph = esph; sg_init_table(sg, esp->nfrags); err = skb_to_sgvec(skb, sg, (unsigned char *)esph - skb->data, assoclen + ivlen + esp->clen + alen); if (unlikely(err < 0)) goto error_free; if (!esp->inplace) { int allocsize; struct page_frag *pfrag = &x->xfrag; allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES); spin_lock_bh(&x->lock); if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) { spin_unlock_bh(&x->lock); goto error_free; } skb_shinfo(skb)->nr_frags = 1; page = pfrag->page; get_page(page); /* replace page frags in skb with new page */ __skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len); pfrag->offset = pfrag->offset + allocsize; spin_unlock_bh(&x->lock); sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1); err = skb_to_sgvec(skb, dsg, (unsigned char *)esph - skb->data, assoclen + ivlen + esp->clen + alen); if (unlikely(err < 0)) goto error_free; } if ((x->props.flags & XFRM_STATE_ESN)) aead_request_set_callback(req, 0, esp_output_done_esn, skb); else aead_request_set_callback(req, 0, esp_output_done, skb); aead_request_set_crypt(req, sg, dsg, ivlen + esp->clen, iv); aead_request_set_ad(req, assoclen); memset(iv, 0, ivlen); memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&esp->seqno + 8 - min(ivlen, 8), min(ivlen, 8)); ESP_SKB_CB(skb)->tmp = tmp; err = crypto_aead_encrypt(req); switch (err) { case -EINPROGRESS: goto error; case -ENOSPC: err = NET_XMIT_DROP; break; case 0: if ((x->props.flags & XFRM_STATE_ESN)) esp_output_restore_header(skb); esp_output_encap_csum(skb); } if (sg != dsg) esp_ssg_unref(x, tmp, skb); if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) err = esp_output_tail_tcp(x, skb); error_free: kfree(tmp); error: return err; } EXPORT_SYMBOL_GPL(esp6_output_tail); static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) { int alen; int blksize; struct ip_esp_hdr *esph; struct crypto_aead *aead; struct esp_info esp; esp.inplace = true; esp.proto = *skb_mac_header(skb); *skb_mac_header(skb) = IPPROTO_ESP; /* skb is pure payload to encrypt */ aead = x->data; alen = crypto_aead_authsize(aead); esp.tfclen = 0; if (x->tfcpad) { struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } blksize = ALIGN(crypto_aead_blocksize(aead), 4); esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize); esp.plen = esp.clen - skb->len - esp.tfclen; esp.tailen = esp.tfclen + esp.plen + alen; esp.esph = ip_esp_hdr(skb); esp.nfrags = esp6_output_head(x, skb, &esp); if (esp.nfrags < 0) return esp.nfrags; esph = esp.esph; esph->spi = x->id.spi; esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); esp.seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low + ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32)); skb_push(skb, -skb_network_offset(skb)); return esp6_output_tail(x, skb, &esp); } static inline int esp_remove_trailer(struct sk_buff *skb) { struct xfrm_state *x = xfrm_input_state(skb); struct crypto_aead *aead = x->data; int alen, hlen, elen; int padlen, trimlen; __wsum csumdiff; u8 nexthdr[2]; int ret; alen = crypto_aead_authsize(aead); hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); elen = skb->len - hlen; ret = skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2); BUG_ON(ret); ret = -EINVAL; padlen = nexthdr[0]; if (padlen + 2 + alen >= elen) { net_dbg_ratelimited("ipsec esp packet is garbage padlen=%d, elen=%d\n", padlen + 2, elen - alen); goto out; } trimlen = alen + padlen + 2; if (skb->ip_summed == CHECKSUM_COMPLETE) { csumdiff = skb_checksum(skb, skb->len - trimlen, trimlen, 0); skb->csum = csum_block_sub(skb->csum, csumdiff, skb->len - trimlen); } ret = pskb_trim(skb, skb->len - trimlen); if (unlikely(ret)) return ret; ret = nexthdr[1]; out: return ret; } int esp6_input_done2(struct sk_buff *skb, int err) { struct xfrm_state *x = xfrm_input_state(skb); struct xfrm_offload *xo = xfrm_offload(skb); struct crypto_aead *aead = x->data; int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); int hdr_len = skb_network_header_len(skb); if (!xo || !(xo->flags & CRYPTO_DONE)) kfree(ESP_SKB_CB(skb)->tmp); if (unlikely(err)) goto out; err = esp_remove_trailer(skb); if (unlikely(err < 0)) goto out; if (x->encap) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); int offset = skb_network_offset(skb) + sizeof(*ip6h); struct xfrm_encap_tmpl *encap = x->encap; u8 nexthdr = ip6h->nexthdr; __be16 frag_off, source; struct udphdr *uh; struct tcphdr *th; offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset == -1) { err = -EINVAL; goto out; } uh = (void *)(skb->data + offset); th = (void *)(skb->data + offset); hdr_len += offset; switch (x->encap->encap_type) { case TCP_ENCAP_ESPINTCP: source = th->source; break; case UDP_ENCAP_ESPINUDP: source = uh->source; break; default: WARN_ON_ONCE(1); err = -EINVAL; goto out; } /* * 1) if the NAT-T peer's IP or port changed then * advertise the change to the keying daemon. * This is an inbound SA, so just compare * SRC ports. */ if (!ipv6_addr_equal(&ip6h->saddr, &x->props.saddr.in6) || source != encap->encap_sport) { xfrm_address_t ipaddr; memcpy(&ipaddr.a6, &ip6h->saddr.s6_addr, sizeof(ipaddr.a6)); km_new_mapping(x, &ipaddr, source); /* XXX: perhaps add an extra * policy check here, to see * if we should allow or * reject a packet from a * different source * address/port. */ } /* * 2) ignore UDP/TCP checksums in case * of NAT-T in Transport Mode, or * perform other post-processing fixes * as per draft-ietf-ipsec-udp-encaps-06, * section 3.1.2 */ if (x->props.mode == XFRM_MODE_TRANSPORT) skb->ip_summed = CHECKSUM_UNNECESSARY; } skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); skb_pull_rcsum(skb, hlen); if (x->props.mode == XFRM_MODE_TUNNEL) skb_reset_transport_header(skb); else skb_set_transport_header(skb, -hdr_len); /* RFC4303: Drop dummy packets without any error */ if (err == IPPROTO_NONE) err = -EINVAL; out: return err; } EXPORT_SYMBOL_GPL(esp6_input_done2); static void esp_input_done(void *data, int err) { struct sk_buff *skb = data; xfrm_input_resume(skb, esp6_input_done2(skb, err)); } static void esp_input_restore_header(struct sk_buff *skb) { esp_restore_header(skb, 0); __skb_pull(skb, 4); } static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi) { struct xfrm_state *x = xfrm_input_state(skb); /* For ESN we move the header forward by 4 bytes to * accommodate the high bits. We will move it back after * decryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { struct ip_esp_hdr *esph = skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; } } static void esp_input_done_esn(void *data, int err) { struct sk_buff *skb = data; esp_input_restore_header(skb); esp_input_done(data, err); } static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) { struct crypto_aead *aead = x->data; struct aead_request *req; struct sk_buff *trailer; int ivlen = crypto_aead_ivsize(aead); int elen = skb->len - sizeof(struct ip_esp_hdr) - ivlen; int nfrags; int assoclen; int seqhilen; int ret = 0; void *tmp; __be32 *seqhi; u8 *iv; struct scatterlist *sg; if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + ivlen)) { ret = -EINVAL; goto out; } if (elen <= 0) { ret = -EINVAL; goto out; } assoclen = sizeof(struct ip_esp_hdr); seqhilen = 0; if (x->props.flags & XFRM_STATE_ESN) { seqhilen += sizeof(__be32); assoclen += seqhilen; } if (!skb_cloned(skb)) { if (!skb_is_nonlinear(skb)) { nfrags = 1; goto skip_cow; } else if (!skb_has_frag_list(skb)) { nfrags = skb_shinfo(skb)->nr_frags; nfrags++; goto skip_cow; } } nfrags = skb_cow_data(skb, 0, &trailer); if (nfrags < 0) { ret = -EINVAL; goto out; } skip_cow: ret = -ENOMEM; tmp = esp_alloc_tmp(aead, nfrags, seqhilen); if (!tmp) goto out; ESP_SKB_CB(skb)->tmp = tmp; seqhi = esp_tmp_extra(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); req = esp_tmp_req(aead, iv); sg = esp_req_sg(aead, req); esp_input_set_header(skb, seqhi); sg_init_table(sg, nfrags); ret = skb_to_sgvec(skb, sg, 0, skb->len); if (unlikely(ret < 0)) { kfree(tmp); goto out; } skb->ip_summed = CHECKSUM_NONE; if ((x->props.flags & XFRM_STATE_ESN)) aead_request_set_callback(req, 0, esp_input_done_esn, skb); else aead_request_set_callback(req, 0, esp_input_done, skb); aead_request_set_crypt(req, sg, sg, elen + ivlen, iv); aead_request_set_ad(req, assoclen); ret = crypto_aead_decrypt(req); if (ret == -EINPROGRESS) goto out; if ((x->props.flags & XFRM_STATE_ESN)) esp_input_restore_header(skb); ret = esp6_input_done2(skb, ret); out: return ret; } static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset); struct xfrm_state *x; if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return 0; x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); xfrm_state_put(x); return 0; } static void esp6_destroy(struct xfrm_state *x) { struct crypto_aead *aead = x->data; if (!aead) return; crypto_free_aead(aead); } static int esp_init_aead(struct xfrm_state *x, struct netlink_ext_ack *extack) { char aead_name[CRYPTO_MAX_ALG_NAME]; struct crypto_aead *aead; int err; if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)", x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME) { NL_SET_ERR_MSG(extack, "Algorithm name is too long"); return -ENAMETOOLONG; } aead = crypto_alloc_aead(aead_name, 0, 0); err = PTR_ERR(aead); if (IS_ERR(aead)) goto error; x->data = aead; err = crypto_aead_setkey(aead, x->aead->alg_key, (x->aead->alg_key_len + 7) / 8); if (err) goto error; err = crypto_aead_setauthsize(aead, x->aead->alg_icv_len / 8); if (err) goto error; return 0; error: NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); return err; } static int esp_init_authenc(struct xfrm_state *x, struct netlink_ext_ack *extack) { struct crypto_aead *aead; struct crypto_authenc_key_param *param; struct rtattr *rta; char *key; char *p; char authenc_name[CRYPTO_MAX_ALG_NAME]; unsigned int keylen; int err; err = -ENAMETOOLONG; if ((x->props.flags & XFRM_STATE_ESN)) { if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, "%s%sauthencesn(%s,%s)%s", x->geniv ?: "", x->geniv ? "(" : "", x->aalg ? x->aalg->alg_name : "digest_null", x->ealg->alg_name, x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) { NL_SET_ERR_MSG(extack, "Algorithm name is too long"); goto error; } } else { if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME, "%s%sauthenc(%s,%s)%s", x->geniv ?: "", x->geniv ? "(" : "", x->aalg ? x->aalg->alg_name : "digest_null", x->ealg->alg_name, x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME) { NL_SET_ERR_MSG(extack, "Algorithm name is too long"); goto error; } } aead = crypto_alloc_aead(authenc_name, 0, 0); err = PTR_ERR(aead); if (IS_ERR(aead)) { NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); goto error; } x->data = aead; keylen = (x->aalg ? (x->aalg->alg_key_len + 7) / 8 : 0) + (x->ealg->alg_key_len + 7) / 8 + RTA_SPACE(sizeof(*param)); err = -ENOMEM; key = kmalloc(keylen, GFP_KERNEL); if (!key) goto error; p = key; rta = (void *)p; rta->rta_type = CRYPTO_AUTHENC_KEYA_PARAM; rta->rta_len = RTA_LENGTH(sizeof(*param)); param = RTA_DATA(rta); p += RTA_SPACE(sizeof(*param)); if (x->aalg) { struct xfrm_algo_desc *aalg_desc; memcpy(p, x->aalg->alg_key, (x->aalg->alg_key_len + 7) / 8); p += (x->aalg->alg_key_len + 7) / 8; aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0); BUG_ON(!aalg_desc); err = -EINVAL; if (aalg_desc->uinfo.auth.icv_fullbits / 8 != crypto_aead_authsize(aead)) { NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); goto free_key; } err = crypto_aead_setauthsize( aead, x->aalg->alg_trunc_len / 8); if (err) { NL_SET_ERR_MSG(extack, "Kernel was unable to initialize cryptographic operations"); goto free_key; } } param->enckeylen = cpu_to_be32((x->ealg->alg_key_len + 7) / 8); memcpy(p, x->ealg->alg_key, (x->ealg->alg_key_len + 7) / 8); err = crypto_aead_setkey(aead, key, keylen); free_key: kfree(key); error: return err; } static int esp6_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { struct crypto_aead *aead; u32 align; int err; x->data = NULL; if (x->aead) { err = esp_init_aead(x, extack); } else if (x->ealg) { err = esp_init_authenc(x, extack); } else { NL_SET_ERR_MSG(extack, "ESP: AEAD or CRYPT must be provided"); err = -EINVAL; } if (err) goto error; aead = x->data; x->props.header_len = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead); switch (x->props.mode) { case XFRM_MODE_BEET: if (x->sel.family != AF_INET6) x->props.header_len += IPV4_BEET_PHMAXLEN + (sizeof(struct ipv6hdr) - sizeof(struct iphdr)); break; default: case XFRM_MODE_TRANSPORT: break; case XFRM_MODE_TUNNEL: x->props.header_len += sizeof(struct ipv6hdr); break; } if (x->encap) { struct xfrm_encap_tmpl *encap = x->encap; switch (encap->encap_type) { default: NL_SET_ERR_MSG(extack, "Unsupported encapsulation type for ESP"); err = -EINVAL; goto error; case UDP_ENCAP_ESPINUDP: x->props.header_len += sizeof(struct udphdr); break; #ifdef CONFIG_INET6_ESPINTCP case TCP_ENCAP_ESPINTCP: /* only the length field, TCP encap is done by * the socket */ x->props.header_len += 2; break; #endif } } align = ALIGN(crypto_aead_blocksize(aead), 4); x->props.trailer_len = align + 1 + crypto_aead_authsize(aead); error: return err; } static int esp6_rcv_cb(struct sk_buff *skb, int err) { return 0; } static const struct xfrm_type esp6_type = { .owner = THIS_MODULE, .proto = IPPROTO_ESP, .flags = XFRM_TYPE_REPLAY_PROT, .init_state = esp6_init_state, .destructor = esp6_destroy, .input = esp6_input, .output = esp6_output, }; static struct xfrm6_protocol esp6_protocol = { .handler = xfrm6_rcv, .input_handler = xfrm_input, .cb_handler = esp6_rcv_cb, .err_handler = esp6_err, .priority = 0, }; static int __init esp6_init(void) { if (xfrm_register_type(&esp6_type, AF_INET6) < 0) { pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } if (xfrm6_protocol_register(&esp6_protocol, IPPROTO_ESP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&esp6_type, AF_INET6); return -EAGAIN; } return 0; } static void __exit esp6_fini(void) { if (xfrm6_protocol_deregister(&esp6_protocol, IPPROTO_ESP) < 0) pr_info("%s: can't remove protocol\n", __func__); xfrm_unregister_type(&esp6_type, AF_INET6); } module_init(esp6_init); module_exit(esp6_fini); MODULE_DESCRIPTION("IPv6 ESP transformation helpers"); MODULE_LICENSE("GPL"); MODULE_ALIAS_XFRM_TYPE(AF_INET6, XFRM_PROTO_ESP); |
| 414 2 2 2 2 2 2 2 414 414 414 414 414 414 414 2 2 414 414 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sunrpc/cache.c * * Generic code for various authentication-related caches * used by sunrpc clients and servers. * * Copyright (C) 2002 Neil Brown <neilb@cse.unsw.edu.au> */ #include <linux/types.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/string_helpers.h> #include <linux/uaccess.h> #include <linux/poll.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/net.h> #include <linux/workqueue.h> #include <linux/mutex.h> #include <linux/pagemap.h> #include <asm/ioctls.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/cache.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <trace/events/sunrpc.h> #include "netns.h" #include "fail.h" #define RPCDBG_FACILITY RPCDBG_CACHE static bool cache_defer_req(struct cache_req *req, struct cache_head *item); static void cache_revisit_request(struct cache_head *item); static void cache_init(struct cache_head *h, struct cache_detail *detail) { time64_t now = seconds_since_boot(); INIT_HLIST_NODE(&h->cache_list); h->flags = 0; kref_init(&h->ref); h->expiry_time = now + CACHE_NEW_EXPIRY; if (now <= detail->flush_time) /* ensure it isn't already expired */ now = detail->flush_time + 1; h->last_refresh = now; } static void cache_fresh_unlocked(struct cache_head *head, struct cache_detail *detail); static struct cache_head *sunrpc_cache_find_rcu(struct cache_detail *detail, struct cache_head *key, int hash) { struct hlist_head *head = &detail->hash_table[hash]; struct cache_head *tmp; rcu_read_lock(); hlist_for_each_entry_rcu(tmp, head, cache_list) { if (!detail->match(tmp, key)) continue; if (test_bit(CACHE_VALID, &tmp->flags) && cache_is_expired(detail, tmp)) continue; tmp = cache_get_rcu(tmp); rcu_read_unlock(); return tmp; } rcu_read_unlock(); return NULL; } static void sunrpc_begin_cache_remove_entry(struct cache_head *ch, struct cache_detail *cd) { /* Must be called under cd->hash_lock */ hlist_del_init_rcu(&ch->cache_list); set_bit(CACHE_CLEANED, &ch->flags); cd->entries --; } static void sunrpc_end_cache_remove_entry(struct cache_head *ch, struct cache_detail *cd) { cache_fresh_unlocked(ch, cd); cache_put(ch, cd); } static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, struct cache_head *key, int hash) { struct cache_head *new, *tmp, *freeme = NULL; struct hlist_head *head = &detail->hash_table[hash]; new = detail->alloc(); if (!new) return NULL; /* must fully initialise 'new', else * we might get lose if we need to * cache_put it soon. */ cache_init(new, detail); detail->init(new, key); spin_lock(&detail->hash_lock); /* check if entry appeared while we slept */ hlist_for_each_entry_rcu(tmp, head, cache_list, lockdep_is_held(&detail->hash_lock)) { if (!detail->match(tmp, key)) continue; if (test_bit(CACHE_VALID, &tmp->flags) && cache_is_expired(detail, tmp)) { sunrpc_begin_cache_remove_entry(tmp, detail); trace_cache_entry_expired(detail, tmp); freeme = tmp; break; } cache_get(tmp); spin_unlock(&detail->hash_lock); cache_put(new, detail); return tmp; } hlist_add_head_rcu(&new->cache_list, head); detail->entries++; cache_get(new); spin_unlock(&detail->hash_lock); if (freeme) sunrpc_end_cache_remove_entry(freeme, detail); return new; } struct cache_head *sunrpc_cache_lookup_rcu(struct cache_detail *detail, struct cache_head *key, int hash) { struct cache_head *ret; ret = sunrpc_cache_find_rcu(detail, key, hash); if (ret) return ret; /* Didn't find anything, insert an empty entry */ return sunrpc_cache_add_entry(detail, key, hash); } EXPORT_SYMBOL_GPL(sunrpc_cache_lookup_rcu); static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch); static void cache_fresh_locked(struct cache_head *head, time64_t expiry, struct cache_detail *detail) { time64_t now = seconds_since_boot(); if (now <= detail->flush_time) /* ensure it isn't immediately treated as expired */ now = detail->flush_time + 1; head->expiry_time = expiry; head->last_refresh = now; smp_wmb(); /* paired with smp_rmb() in cache_is_valid() */ set_bit(CACHE_VALID, &head->flags); } static void cache_fresh_unlocked(struct cache_head *head, struct cache_detail *detail) { if (test_and_clear_bit(CACHE_PENDING, &head->flags)) { cache_revisit_request(head); cache_dequeue(detail, head); } } static void cache_make_negative(struct cache_detail *detail, struct cache_head *h) { set_bit(CACHE_NEGATIVE, &h->flags); trace_cache_entry_make_negative(detail, h); } static void cache_entry_update(struct cache_detail *detail, struct cache_head *h, struct cache_head *new) { if (!test_bit(CACHE_NEGATIVE, &new->flags)) { detail->update(h, new); trace_cache_entry_update(detail, h); } else { cache_make_negative(detail, h); } } struct cache_head *sunrpc_cache_update(struct cache_detail *detail, struct cache_head *new, struct cache_head *old, int hash) { /* The 'old' entry is to be replaced by 'new'. * If 'old' is not VALID, we update it directly, * otherwise we need to replace it */ struct cache_head *tmp; if (!test_bit(CACHE_VALID, &old->flags)) { spin_lock(&detail->hash_lock); if (!test_bit(CACHE_VALID, &old->flags)) { cache_entry_update(detail, old, new); cache_fresh_locked(old, new->expiry_time, detail); spin_unlock(&detail->hash_lock); cache_fresh_unlocked(old, detail); return old; } spin_unlock(&detail->hash_lock); } /* We need to insert a new entry */ tmp = detail->alloc(); if (!tmp) { cache_put(old, detail); return NULL; } cache_init(tmp, detail); detail->init(tmp, old); spin_lock(&detail->hash_lock); cache_entry_update(detail, tmp, new); hlist_add_head(&tmp->cache_list, &detail->hash_table[hash]); detail->entries++; cache_get(tmp); cache_fresh_locked(tmp, new->expiry_time, detail); cache_fresh_locked(old, 0, detail); spin_unlock(&detail->hash_lock); cache_fresh_unlocked(tmp, detail); cache_fresh_unlocked(old, detail); cache_put(old, detail); return tmp; } EXPORT_SYMBOL_GPL(sunrpc_cache_update); static inline int cache_is_valid(struct cache_head *h) { if (!test_bit(CACHE_VALID, &h->flags)) return -EAGAIN; else { /* entry is valid */ if (test_bit(CACHE_NEGATIVE, &h->flags)) return -ENOENT; else { /* * In combination with write barrier in * sunrpc_cache_update, ensures that anyone * using the cache entry after this sees the * updated contents: */ smp_rmb(); return 0; } } } static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h) { int rv; spin_lock(&detail->hash_lock); rv = cache_is_valid(h); if (rv == -EAGAIN) { cache_make_negative(detail, h); cache_fresh_locked(h, seconds_since_boot()+CACHE_NEW_EXPIRY, detail); rv = -ENOENT; } spin_unlock(&detail->hash_lock); cache_fresh_unlocked(h, detail); return rv; } /* * This is the generic cache management routine for all * the authentication caches. * It checks the currency of a cache item and will (later) * initiate an upcall to fill it if needed. * * * Returns 0 if the cache_head can be used, or cache_puts it and returns * -EAGAIN if upcall is pending and request has been queued * -ETIMEDOUT if upcall failed or request could not be queue or * upcall completed but item is still invalid (implying that * the cache item has been replaced with a newer one). * -ENOENT if cache entry was negative */ int cache_check(struct cache_detail *detail, struct cache_head *h, struct cache_req *rqstp) { int rv; time64_t refresh_age, age; /* First decide return status as best we can */ rv = cache_is_valid(h); /* now see if we want to start an upcall */ refresh_age = (h->expiry_time - h->last_refresh); age = seconds_since_boot() - h->last_refresh; if (rqstp == NULL) { if (rv == -EAGAIN) rv = -ENOENT; } else if (rv == -EAGAIN || (h->expiry_time != 0 && age > refresh_age/2)) { dprintk("RPC: Want update, refage=%lld, age=%lld\n", refresh_age, age); switch (detail->cache_upcall(detail, h)) { case -EINVAL: rv = try_to_negate_entry(detail, h); break; case -EAGAIN: cache_fresh_unlocked(h, detail); break; } } if (rv == -EAGAIN) { if (!cache_defer_req(rqstp, h)) { /* * Request was not deferred; handle it as best * we can ourselves: */ rv = cache_is_valid(h); if (rv == -EAGAIN) rv = -ETIMEDOUT; } } if (rv) cache_put(h, detail); return rv; } EXPORT_SYMBOL_GPL(cache_check); /* * caches need to be periodically cleaned. * For this we maintain a list of cache_detail and * a current pointer into that list and into the table * for that entry. * * Each time cache_clean is called it finds the next non-empty entry * in the current table and walks the list in that entry * looking for entries that can be removed. * * An entry gets removed if: * - The expiry is before current time * - The last_refresh time is before the flush_time for that cache * * later we might drop old entries with non-NEVER expiry if that table * is getting 'full' for some definition of 'full' * * The question of "how often to scan a table" is an interesting one * and is answered in part by the use of the "nextcheck" field in the * cache_detail. * When a scan of a table begins, the nextcheck field is set to a time * that is well into the future. * While scanning, if an expiry time is found that is earlier than the * current nextcheck time, nextcheck is set to that expiry time. * If the flush_time is ever set to a time earlier than the nextcheck * time, the nextcheck time is then set to that flush_time. * * A table is then only scanned if the current time is at least * the nextcheck time. * */ static LIST_HEAD(cache_list); static DEFINE_SPINLOCK(cache_list_lock); static struct cache_detail *current_detail; static int current_index; static void do_cache_clean(struct work_struct *work); static struct delayed_work cache_cleaner; void sunrpc_init_cache_detail(struct cache_detail *cd) { spin_lock_init(&cd->hash_lock); INIT_LIST_HEAD(&cd->queue); spin_lock(&cache_list_lock); cd->nextcheck = 0; cd->entries = 0; atomic_set(&cd->writers, 0); cd->last_close = 0; cd->last_warn = -1; list_add(&cd->others, &cache_list); spin_unlock(&cache_list_lock); /* start the cleaning process */ queue_delayed_work(system_power_efficient_wq, &cache_cleaner, 0); } EXPORT_SYMBOL_GPL(sunrpc_init_cache_detail); void sunrpc_destroy_cache_detail(struct cache_detail *cd) { cache_purge(cd); spin_lock(&cache_list_lock); spin_lock(&cd->hash_lock); if (current_detail == cd) current_detail = NULL; list_del_init(&cd->others); spin_unlock(&cd->hash_lock); spin_unlock(&cache_list_lock); if (list_empty(&cache_list)) { /* module must be being unloaded so its safe to kill the worker */ cancel_delayed_work_sync(&cache_cleaner); } } EXPORT_SYMBOL_GPL(sunrpc_destroy_cache_detail); /* clean cache tries to find something to clean * and cleans it. * It returns 1 if it cleaned something, * 0 if it didn't find anything this time * -1 if it fell off the end of the list. */ static int cache_clean(void) { int rv = 0; struct list_head *next; spin_lock(&cache_list_lock); /* find a suitable table if we don't already have one */ while (current_detail == NULL || current_index >= current_detail->hash_size) { if (current_detail) next = current_detail->others.next; else next = cache_list.next; if (next == &cache_list) { current_detail = NULL; spin_unlock(&cache_list_lock); return -1; } current_detail = list_entry(next, struct cache_detail, others); if (current_detail->nextcheck > seconds_since_boot()) current_index = current_detail->hash_size; else { current_index = 0; current_detail->nextcheck = seconds_since_boot()+30*60; } } /* find a non-empty bucket in the table */ while (current_detail && current_index < current_detail->hash_size && hlist_empty(¤t_detail->hash_table[current_index])) current_index++; /* find a cleanable entry in the bucket and clean it, or set to next bucket */ if (current_detail && current_index < current_detail->hash_size) { struct cache_head *ch = NULL; struct cache_detail *d; struct hlist_head *head; struct hlist_node *tmp; spin_lock(¤t_detail->hash_lock); /* Ok, now to clean this strand */ head = ¤t_detail->hash_table[current_index]; hlist_for_each_entry_safe(ch, tmp, head, cache_list) { if (current_detail->nextcheck > ch->expiry_time) current_detail->nextcheck = ch->expiry_time+1; if (!cache_is_expired(current_detail, ch)) continue; sunrpc_begin_cache_remove_entry(ch, current_detail); trace_cache_entry_expired(current_detail, ch); rv = 1; break; } spin_unlock(¤t_detail->hash_lock); d = current_detail; if (!ch) current_index ++; spin_unlock(&cache_list_lock); if (ch) sunrpc_end_cache_remove_entry(ch, d); } else spin_unlock(&cache_list_lock); return rv; } /* * We want to regularly clean the cache, so we need to schedule some work ... */ static void do_cache_clean(struct work_struct *work) { int delay; if (list_empty(&cache_list)) return; if (cache_clean() == -1) delay = round_jiffies_relative(30*HZ); else delay = 5; queue_delayed_work(system_power_efficient_wq, &cache_cleaner, delay); } /* * Clean all caches promptly. This just calls cache_clean * repeatedly until we are sure that every cache has had a chance to * be fully cleaned */ void cache_flush(void) { while (cache_clean() != -1) cond_resched(); while (cache_clean() != -1) cond_resched(); } EXPORT_SYMBOL_GPL(cache_flush); void cache_purge(struct cache_detail *detail) { struct cache_head *ch = NULL; struct hlist_head *head = NULL; int i = 0; spin_lock(&detail->hash_lock); if (!detail->entries) { spin_unlock(&detail->hash_lock); return; } dprintk("RPC: %d entries in %s cache\n", detail->entries, detail->name); for (i = 0; i < detail->hash_size; i++) { head = &detail->hash_table[i]; while (!hlist_empty(head)) { ch = hlist_entry(head->first, struct cache_head, cache_list); sunrpc_begin_cache_remove_entry(ch, detail); spin_unlock(&detail->hash_lock); sunrpc_end_cache_remove_entry(ch, detail); spin_lock(&detail->hash_lock); } } spin_unlock(&detail->hash_lock); } EXPORT_SYMBOL_GPL(cache_purge); /* * Deferral and Revisiting of Requests. * * If a cache lookup finds a pending entry, we * need to defer the request and revisit it later. * All deferred requests are stored in a hash table, * indexed by "struct cache_head *". * As it may be wasteful to store a whole request * structure, we allow the request to provide a * deferred form, which must contain a * 'struct cache_deferred_req' * This cache_deferred_req contains a method to allow * it to be revisited when cache info is available */ #define DFR_HASHSIZE (PAGE_SIZE/sizeof(struct list_head)) #define DFR_HASH(item) ((((long)item)>>4 ^ (((long)item)>>13)) % DFR_HASHSIZE) #define DFR_MAX 300 /* ??? */ static DEFINE_SPINLOCK(cache_defer_lock); static LIST_HEAD(cache_defer_list); static struct hlist_head cache_defer_hash[DFR_HASHSIZE]; static int cache_defer_cnt; static void __unhash_deferred_req(struct cache_deferred_req *dreq) { hlist_del_init(&dreq->hash); if (!list_empty(&dreq->recent)) { list_del_init(&dreq->recent); cache_defer_cnt--; } } static void __hash_deferred_req(struct cache_deferred_req *dreq, struct cache_head *item) { int hash = DFR_HASH(item); INIT_LIST_HEAD(&dreq->recent); hlist_add_head(&dreq->hash, &cache_defer_hash[hash]); } static void setup_deferral(struct cache_deferred_req *dreq, struct cache_head *item, int count_me) { dreq->item = item; spin_lock(&cache_defer_lock); __hash_deferred_req(dreq, item); if (count_me) { cache_defer_cnt++; list_add(&dreq->recent, &cache_defer_list); } spin_unlock(&cache_defer_lock); } struct thread_deferred_req { struct cache_deferred_req handle; struct completion completion; }; static void cache_restart_thread(struct cache_deferred_req *dreq, int too_many) { struct thread_deferred_req *dr = container_of(dreq, struct thread_deferred_req, handle); complete(&dr->completion); } static void cache_wait_req(struct cache_req *req, struct cache_head *item) { struct thread_deferred_req sleeper; struct cache_deferred_req *dreq = &sleeper.handle; sleeper.completion = COMPLETION_INITIALIZER_ONSTACK(sleeper.completion); dreq->revisit = cache_restart_thread; setup_deferral(dreq, item, 0); if (!test_bit(CACHE_PENDING, &item->flags) || wait_for_completion_interruptible_timeout( &sleeper.completion, req->thread_wait) <= 0) { /* The completion wasn't completed, so we need * to clean up */ spin_lock(&cache_defer_lock); if (!hlist_unhashed(&sleeper.handle.hash)) { __unhash_deferred_req(&sleeper.handle); spin_unlock(&cache_defer_lock); } else { /* cache_revisit_request already removed * this from the hash table, but hasn't * called ->revisit yet. It will very soon * and we need to wait for it. */ spin_unlock(&cache_defer_lock); wait_for_completion(&sleeper.completion); } } } static void cache_limit_defers(void) { /* Make sure we haven't exceed the limit of allowed deferred * requests. */ struct cache_deferred_req *discard = NULL; if (cache_defer_cnt <= DFR_MAX) return; spin_lock(&cache_defer_lock); /* Consider removing either the first or the last */ if (cache_defer_cnt > DFR_MAX) { if (get_random_u32_below(2)) discard = list_entry(cache_defer_list.next, struct cache_deferred_req, recent); else discard = list_entry(cache_defer_list.prev, struct cache_deferred_req, recent); __unhash_deferred_req(discard); } spin_unlock(&cache_defer_lock); if (discard) discard->revisit(discard, 1); } #if IS_ENABLED(CONFIG_FAIL_SUNRPC) static inline bool cache_defer_immediately(void) { return !fail_sunrpc.ignore_cache_wait && should_fail(&fail_sunrpc.attr, 1); } #else static inline bool cache_defer_immediately(void) { return false; } #endif /* Return true if and only if a deferred request is queued. */ static bool cache_defer_req(struct cache_req *req, struct cache_head *item) { struct cache_deferred_req *dreq; if (!cache_defer_immediately()) { cache_wait_req(req, item); if (!test_bit(CACHE_PENDING, &item->flags)) return false; } dreq = req->defer(req); if (dreq == NULL) return false; setup_deferral(dreq, item, 1); if (!test_bit(CACHE_PENDING, &item->flags)) /* Bit could have been cleared before we managed to * set up the deferral, so need to revisit just in case */ cache_revisit_request(item); cache_limit_defers(); return true; } static void cache_revisit_request(struct cache_head *item) { struct cache_deferred_req *dreq; struct list_head pending; struct hlist_node *tmp; int hash = DFR_HASH(item); INIT_LIST_HEAD(&pending); spin_lock(&cache_defer_lock); hlist_for_each_entry_safe(dreq, tmp, &cache_defer_hash[hash], hash) if (dreq->item == item) { __unhash_deferred_req(dreq); list_add(&dreq->recent, &pending); } spin_unlock(&cache_defer_lock); while (!list_empty(&pending)) { dreq = list_entry(pending.next, struct cache_deferred_req, recent); list_del_init(&dreq->recent); dreq->revisit(dreq, 0); } } void cache_clean_deferred(void *owner) { struct cache_deferred_req *dreq, *tmp; struct list_head pending; INIT_LIST_HEAD(&pending); spin_lock(&cache_defer_lock); list_for_each_entry_safe(dreq, tmp, &cache_defer_list, recent) { if (dreq->owner == owner) { __unhash_deferred_req(dreq); list_add(&dreq->recent, &pending); } } spin_unlock(&cache_defer_lock); while (!list_empty(&pending)) { dreq = list_entry(pending.next, struct cache_deferred_req, recent); list_del_init(&dreq->recent); dreq->revisit(dreq, 1); } } /* * communicate with user-space * * We have a magic /proc file - /proc/net/rpc/<cachename>/channel. * On read, you get a full request, or block. * On write, an update request is processed. * Poll works if anything to read, and always allows write. * * Implemented by linked list of requests. Each open file has * a ->private that also exists in this list. New requests are added * to the end and may wakeup and preceding readers. * New readers are added to the head. If, on read, an item is found with * CACHE_UPCALLING clear, we free it from the list. * */ static DEFINE_SPINLOCK(queue_lock); struct cache_queue { struct list_head list; int reader; /* if 0, then request */ }; struct cache_request { struct cache_queue q; struct cache_head *item; char * buf; int len; int readers; }; struct cache_reader { struct cache_queue q; int offset; /* if non-0, we have a refcnt on next request */ }; static int cache_request(struct cache_detail *detail, struct cache_request *crq) { char *bp = crq->buf; int len = PAGE_SIZE; detail->cache_request(detail, crq->item, &bp, &len); if (len < 0) return -E2BIG; return PAGE_SIZE - len; } static ssize_t cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; struct cache_request *rq; struct inode *inode = file_inode(filp); int err; if (count == 0) return 0; inode_lock(inode); /* protect against multiple concurrent * readers on this file */ again: spin_lock(&queue_lock); /* need to find next request */ while (rp->q.list.next != &cd->queue && list_entry(rp->q.list.next, struct cache_queue, list) ->reader) { struct list_head *next = rp->q.list.next; list_move(&rp->q.list, next); } if (rp->q.list.next == &cd->queue) { spin_unlock(&queue_lock); inode_unlock(inode); WARN_ON_ONCE(rp->offset); return 0; } rq = container_of(rp->q.list.next, struct cache_request, q.list); WARN_ON_ONCE(rq->q.reader); if (rp->offset == 0) rq->readers++; spin_unlock(&queue_lock); if (rq->len == 0) { err = cache_request(cd, rq); if (err < 0) goto out; rq->len = err; } if (rp->offset == 0 && !test_bit(CACHE_PENDING, &rq->item->flags)) { err = -EAGAIN; spin_lock(&queue_lock); list_move(&rp->q.list, &rq->q.list); spin_unlock(&queue_lock); } else { if (rp->offset + count > rq->len) count = rq->len - rp->offset; err = -EFAULT; if (copy_to_user(buf, rq->buf + rp->offset, count)) goto out; rp->offset += count; if (rp->offset >= rq->len) { rp->offset = 0; spin_lock(&queue_lock); list_move(&rp->q.list, &rq->q.list); spin_unlock(&queue_lock); } err = 0; } out: if (rp->offset == 0) { /* need to release rq */ spin_lock(&queue_lock); rq->readers--; if (rq->readers == 0 && !test_bit(CACHE_PENDING, &rq->item->flags)) { list_del(&rq->q.list); spin_unlock(&queue_lock); cache_put(rq->item, cd); kfree(rq->buf); kfree(rq); } else spin_unlock(&queue_lock); } if (err == -EAGAIN) goto again; inode_unlock(inode); return err ? err : count; } static ssize_t cache_do_downcall(char *kaddr, const char __user *buf, size_t count, struct cache_detail *cd) { ssize_t ret; if (count == 0) return -EINVAL; if (copy_from_user(kaddr, buf, count)) return -EFAULT; kaddr[count] = '\0'; ret = cd->cache_parse(cd, kaddr, count); if (!ret) ret = count; return ret; } static ssize_t cache_downcall(struct address_space *mapping, const char __user *buf, size_t count, struct cache_detail *cd) { char *write_buf; ssize_t ret = -ENOMEM; if (count >= 32768) { /* 32k is max userland buffer, lets check anyway */ ret = -EINVAL; goto out; } write_buf = kvmalloc(count + 1, GFP_KERNEL); if (!write_buf) goto out; ret = cache_do_downcall(write_buf, buf, count, cd); kvfree(write_buf); out: return ret; } static ssize_t cache_write(struct file *filp, const char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { struct address_space *mapping = filp->f_mapping; struct inode *inode = file_inode(filp); ssize_t ret = -EINVAL; if (!cd->cache_parse) goto out; inode_lock(inode); ret = cache_downcall(mapping, buf, count, cd); inode_unlock(inode); out: return ret; } static DECLARE_WAIT_QUEUE_HEAD(queue_wait); static __poll_t cache_poll(struct file *filp, poll_table *wait, struct cache_detail *cd) { __poll_t mask; struct cache_reader *rp = filp->private_data; struct cache_queue *cq; poll_wait(filp, &queue_wait, wait); /* alway allow write */ mask = EPOLLOUT | EPOLLWRNORM; if (!rp) return mask; spin_lock(&queue_lock); for (cq= &rp->q; &cq->list != &cd->queue; cq = list_entry(cq->list.next, struct cache_queue, list)) if (!cq->reader) { mask |= EPOLLIN | EPOLLRDNORM; break; } spin_unlock(&queue_lock); return mask; } static int cache_ioctl(struct inode *ino, struct file *filp, unsigned int cmd, unsigned long arg, struct cache_detail *cd) { int len = 0; struct cache_reader *rp = filp->private_data; struct cache_queue *cq; if (cmd != FIONREAD || !rp) return -EINVAL; spin_lock(&queue_lock); /* only find the length remaining in current request, * or the length of the next request */ for (cq= &rp->q; &cq->list != &cd->queue; cq = list_entry(cq->list.next, struct cache_queue, list)) if (!cq->reader) { struct cache_request *cr = container_of(cq, struct cache_request, q); len = cr->len - rp->offset; break; } spin_unlock(&queue_lock); return put_user(len, (int __user *)arg); } static int cache_open(struct inode *inode, struct file *filp, struct cache_detail *cd) { struct cache_reader *rp = NULL; if (!cd || !try_module_get(cd->owner)) return -EACCES; nonseekable_open(inode, filp); if (filp->f_mode & FMODE_READ) { rp = kmalloc(sizeof(*rp), GFP_KERNEL); if (!rp) { module_put(cd->owner); return -ENOMEM; } rp->offset = 0; rp->q.reader = 1; spin_lock(&queue_lock); list_add(&rp->q.list, &cd->queue); spin_unlock(&queue_lock); } if (filp->f_mode & FMODE_WRITE) atomic_inc(&cd->writers); filp->private_data = rp; return 0; } static int cache_release(struct inode *inode, struct file *filp, struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; if (rp) { spin_lock(&queue_lock); if (rp->offset) { struct cache_queue *cq; for (cq= &rp->q; &cq->list != &cd->queue; cq = list_entry(cq->list.next, struct cache_queue, list)) if (!cq->reader) { container_of(cq, struct cache_request, q) ->readers--; break; } rp->offset = 0; } list_del(&rp->q.list); spin_unlock(&queue_lock); filp->private_data = NULL; kfree(rp); } if (filp->f_mode & FMODE_WRITE) { atomic_dec(&cd->writers); cd->last_close = seconds_since_boot(); } module_put(cd->owner); return 0; } static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch) { struct cache_queue *cq, *tmp; struct cache_request *cr; struct list_head dequeued; INIT_LIST_HEAD(&dequeued); spin_lock(&queue_lock); list_for_each_entry_safe(cq, tmp, &detail->queue, list) if (!cq->reader) { cr = container_of(cq, struct cache_request, q); if (cr->item != ch) continue; if (test_bit(CACHE_PENDING, &ch->flags)) /* Lost a race and it is pending again */ break; if (cr->readers != 0) continue; list_move(&cr->q.list, &dequeued); } spin_unlock(&queue_lock); while (!list_empty(&dequeued)) { cr = list_entry(dequeued.next, struct cache_request, q.list); list_del(&cr->q.list); cache_put(cr->item, detail); kfree(cr->buf); kfree(cr); } } /* * Support routines for text-based upcalls. * Fields are separated by spaces. * Fields are either mangled to quote space tab newline slosh with slosh * or a hexified with a leading \x * Record is terminated with newline. * */ void qword_add(char **bpp, int *lp, char *str) { char *bp = *bpp; int len = *lp; int ret; if (len < 0) return; ret = string_escape_str(str, bp, len, ESCAPE_OCTAL, "\\ \n\t"); if (ret >= len) { bp += len; len = -1; } else { bp += ret; len -= ret; *bp++ = ' '; len--; } *bpp = bp; *lp = len; } EXPORT_SYMBOL_GPL(qword_add); void qword_addhex(char **bpp, int *lp, char *buf, int blen) { char *bp = *bpp; int len = *lp; if (len < 0) return; if (len > 2) { *bp++ = '\\'; *bp++ = 'x'; len -= 2; while (blen && len >= 2) { bp = hex_byte_pack(bp, *buf++); len -= 2; blen--; } } if (blen || len<1) len = -1; else { *bp++ = ' '; len--; } *bpp = bp; *lp = len; } EXPORT_SYMBOL_GPL(qword_addhex); static void warn_no_listener(struct cache_detail *detail) { if (detail->last_warn != detail->last_close) { detail->last_warn = detail->last_close; if (detail->warn_no_listener) detail->warn_no_listener(detail, detail->last_close != 0); } } static bool cache_listeners_exist(struct cache_detail *detail) { if (atomic_read(&detail->writers)) return true; if (detail->last_close == 0) /* This cache was never opened */ return false; if (detail->last_close < seconds_since_boot() - 30) /* * We allow for the possibility that someone might * restart a userspace daemon without restarting the * server; but after 30 seconds, we give up. */ return false; return true; } /* * register an upcall request to user-space and queue it up for read() by the * upcall daemon. * * Each request is at most one page long. */ static int cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h) { char *buf; struct cache_request *crq; int ret = 0; if (test_bit(CACHE_CLEANED, &h->flags)) /* Too late to make an upcall */ return -EAGAIN; buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!buf) return -EAGAIN; crq = kmalloc(sizeof (*crq), GFP_KERNEL); if (!crq) { kfree(buf); return -EAGAIN; } crq->q.reader = 0; crq->buf = buf; crq->len = 0; crq->readers = 0; spin_lock(&queue_lock); if (test_bit(CACHE_PENDING, &h->flags)) { crq->item = cache_get(h); list_add_tail(&crq->q.list, &detail->queue); trace_cache_entry_upcall(detail, h); } else /* Lost a race, no longer PENDING, so don't enqueue */ ret = -EAGAIN; spin_unlock(&queue_lock); wake_up(&queue_wait); if (ret == -EAGAIN) { kfree(buf); kfree(crq); } return ret; } int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h) { if (test_and_set_bit(CACHE_PENDING, &h->flags)) return 0; return cache_pipe_upcall(detail, h); } EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall); int sunrpc_cache_pipe_upcall_timeout(struct cache_detail *detail, struct cache_head *h) { if (!cache_listeners_exist(detail)) { warn_no_listener(detail); trace_cache_entry_no_listener(detail, h); return -EINVAL; } return sunrpc_cache_pipe_upcall(detail, h); } EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall_timeout); /* * parse a message from user-space and pass it * to an appropriate cache * Messages are, like requests, separated into fields by * spaces and dequotes as \xHEXSTRING or embedded \nnn octal * * Message is * reply cachename expiry key ... content.... * * key and content are both parsed by cache */ int qword_get(char **bpp, char *dest, int bufsize) { /* return bytes copied, or -1 on error */ char *bp = *bpp; int len = 0; while (*bp == ' ') bp++; if (bp[0] == '\\' && bp[1] == 'x') { /* HEX STRING */ bp += 2; while (len < bufsize - 1) { int h, l; h = hex_to_bin(bp[0]); if (h < 0) break; l = hex_to_bin(bp[1]); if (l < 0) break; *dest++ = (h << 4) | l; bp += 2; len++; } } else { /* text with \nnn octal quoting */ while (*bp != ' ' && *bp != '\n' && *bp && len < bufsize-1) { if (*bp == '\\' && isodigit(bp[1]) && (bp[1] <= '3') && isodigit(bp[2]) && isodigit(bp[3])) { int byte = (*++bp -'0'); bp++; byte = (byte << 3) | (*bp++ - '0'); byte = (byte << 3) | (*bp++ - '0'); *dest++ = byte; len++; } else { *dest++ = *bp++; len++; } } } if (*bp != ' ' && *bp != '\n' && *bp != '\0') return -1; while (*bp == ' ') bp++; *bpp = bp; *dest = '\0'; return len; } EXPORT_SYMBOL_GPL(qword_get); /* * support /proc/net/rpc/$CACHENAME/content * as a seqfile. * We call ->cache_show passing NULL for the item to * get a header, then pass each real item in the cache */ static void *__cache_seq_start(struct seq_file *m, loff_t *pos) { loff_t n = *pos; unsigned int hash, entry; struct cache_head *ch; struct cache_detail *cd = m->private; if (!n--) return SEQ_START_TOKEN; hash = n >> 32; entry = n & ((1LL<<32) - 1); hlist_for_each_entry_rcu(ch, &cd->hash_table[hash], cache_list) if (!entry--) return ch; n &= ~((1LL<<32) - 1); do { hash++; n += 1LL<<32; } while(hash < cd->hash_size && hlist_empty(&cd->hash_table[hash])); if (hash >= cd->hash_size) return NULL; *pos = n+1; return hlist_entry_safe(rcu_dereference_raw( hlist_first_rcu(&cd->hash_table[hash])), struct cache_head, cache_list); } static void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos) { struct cache_head *ch = p; int hash = (*pos >> 32); struct cache_detail *cd = m->private; if (p == SEQ_START_TOKEN) hash = 0; else if (ch->cache_list.next == NULL) { hash++; *pos += 1LL<<32; } else { ++*pos; return hlist_entry_safe(rcu_dereference_raw( hlist_next_rcu(&ch->cache_list)), struct cache_head, cache_list); } *pos &= ~((1LL<<32) - 1); while (hash < cd->hash_size && hlist_empty(&cd->hash_table[hash])) { hash++; *pos += 1LL<<32; } if (hash >= cd->hash_size) return NULL; ++*pos; return hlist_entry_safe(rcu_dereference_raw( hlist_first_rcu(&cd->hash_table[hash])), struct cache_head, cache_list); } void *cache_seq_start_rcu(struct seq_file *m, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return __cache_seq_start(m, pos); } EXPORT_SYMBOL_GPL(cache_seq_start_rcu); void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos) { return cache_seq_next(file, p, pos); } EXPORT_SYMBOL_GPL(cache_seq_next_rcu); void cache_seq_stop_rcu(struct seq_file *m, void *p) __releases(RCU) { rcu_read_unlock(); } EXPORT_SYMBOL_GPL(cache_seq_stop_rcu); static int c_show(struct seq_file *m, void *p) { struct cache_head *cp = p; struct cache_detail *cd = m->private; if (p == SEQ_START_TOKEN) return cd->cache_show(m, cd, NULL); ifdebug(CACHE) seq_printf(m, "# expiry=%lld refcnt=%d flags=%lx\n", convert_to_wallclock(cp->expiry_time), kref_read(&cp->ref), cp->flags); cache_get(cp); if (cache_check(cd, cp, NULL)) /* cache_check does a cache_put on failure */ seq_puts(m, "# "); else { if (cache_is_expired(cd, cp)) seq_puts(m, "# "); cache_put(cp, cd); } return cd->cache_show(m, cd, cp); } static const struct seq_operations cache_content_op = { .start = cache_seq_start_rcu, .next = cache_seq_next_rcu, .stop = cache_seq_stop_rcu, .show = c_show, }; static int content_open(struct inode *inode, struct file *file, struct cache_detail *cd) { struct seq_file *seq; int err; if (!cd || !try_module_get(cd->owner)) return -EACCES; err = seq_open(file, &cache_content_op); if (err) { module_put(cd->owner); return err; } seq = file->private_data; seq->private = cd; return 0; } static int content_release(struct inode *inode, struct file *file, struct cache_detail *cd) { int ret = seq_release(inode, file); module_put(cd->owner); return ret; } static int open_flush(struct inode *inode, struct file *file, struct cache_detail *cd) { if (!cd || !try_module_get(cd->owner)) return -EACCES; return nonseekable_open(inode, file); } static int release_flush(struct inode *inode, struct file *file, struct cache_detail *cd) { module_put(cd->owner); return 0; } static ssize_t read_flush(struct file *file, char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { char tbuf[22]; size_t len; len = snprintf(tbuf, sizeof(tbuf), "%llu\n", convert_to_wallclock(cd->flush_time)); return simple_read_from_buffer(buf, count, ppos, tbuf, len); } static ssize_t write_flush(struct file *file, const char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { char tbuf[20]; char *ep; time64_t now; if (*ppos || count > sizeof(tbuf)-1) return -EINVAL; if (copy_from_user(tbuf, buf, count)) return -EFAULT; tbuf[count] = 0; simple_strtoul(tbuf, &ep, 0); if (*ep && *ep != '\n') return -EINVAL; /* Note that while we check that 'buf' holds a valid number, * we always ignore the value and just flush everything. * Making use of the number leads to races. */ now = seconds_since_boot(); /* Always flush everything, so behave like cache_purge() * Do this by advancing flush_time to the current time, * or by one second if it has already reached the current time. * Newly added cache entries will always have ->last_refresh greater * that ->flush_time, so they don't get flushed prematurely. */ if (cd->flush_time >= now) now = cd->flush_time + 1; cd->flush_time = now; cd->nextcheck = now; cache_flush(); if (cd->flush) cd->flush(); *ppos += count; return count; } static ssize_t cache_read_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = pde_data(file_inode(filp)); return cache_read(filp, buf, count, ppos, cd); } static ssize_t cache_write_procfs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = pde_data(file_inode(filp)); return cache_write(filp, buf, count, ppos, cd); } static __poll_t cache_poll_procfs(struct file *filp, poll_table *wait) { struct cache_detail *cd = pde_data(file_inode(filp)); return cache_poll(filp, wait, cd); } static long cache_ioctl_procfs(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct cache_detail *cd = pde_data(inode); return cache_ioctl(inode, filp, cmd, arg, cd); } static int cache_open_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return cache_open(inode, filp, cd); } static int cache_release_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return cache_release(inode, filp, cd); } static const struct proc_ops cache_channel_proc_ops = { .proc_lseek = no_llseek, .proc_read = cache_read_procfs, .proc_write = cache_write_procfs, .proc_poll = cache_poll_procfs, .proc_ioctl = cache_ioctl_procfs, /* for FIONREAD */ .proc_open = cache_open_procfs, .proc_release = cache_release_procfs, }; static int content_open_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return content_open(inode, filp, cd); } static int content_release_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return content_release(inode, filp, cd); } static const struct proc_ops content_proc_ops = { .proc_open = content_open_procfs, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = content_release_procfs, }; static int open_flush_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return open_flush(inode, filp, cd); } static int release_flush_procfs(struct inode *inode, struct file *filp) { struct cache_detail *cd = pde_data(inode); return release_flush(inode, filp, cd); } static ssize_t read_flush_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = pde_data(file_inode(filp)); return read_flush(filp, buf, count, ppos, cd); } static ssize_t write_flush_procfs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = pde_data(file_inode(filp)); return write_flush(filp, buf, count, ppos, cd); } static const struct proc_ops cache_flush_proc_ops = { .proc_open = open_flush_procfs, .proc_read = read_flush_procfs, .proc_write = write_flush_procfs, .proc_release = release_flush_procfs, .proc_lseek = no_llseek, }; static void remove_cache_proc_entries(struct cache_detail *cd) { if (cd->procfs) { proc_remove(cd->procfs); cd->procfs = NULL; } } #ifdef CONFIG_PROC_FS static int create_cache_proc_entries(struct cache_detail *cd, struct net *net) { struct proc_dir_entry *p; struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); cd->procfs = proc_mkdir(cd->name, sn->proc_net_rpc); if (cd->procfs == NULL) goto out_nomem; p = proc_create_data("flush", S_IFREG | 0600, cd->procfs, &cache_flush_proc_ops, cd); if (p == NULL) goto out_nomem; if (cd->cache_request || cd->cache_parse) { p = proc_create_data("channel", S_IFREG | 0600, cd->procfs, &cache_channel_proc_ops, cd); if (p == NULL) goto out_nomem; } if (cd->cache_show) { p = proc_create_data("content", S_IFREG | 0400, cd->procfs, &content_proc_ops, cd); if (p == NULL) goto out_nomem; } return 0; out_nomem: remove_cache_proc_entries(cd); return -ENOMEM; } #else /* CONFIG_PROC_FS */ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net) { return 0; } #endif void __init cache_initialize(void) { INIT_DEFERRABLE_WORK(&cache_cleaner, do_cache_clean); } int cache_register_net(struct cache_detail *cd, struct net *net) { int ret; sunrpc_init_cache_detail(cd); ret = create_cache_proc_entries(cd, net); if (ret) sunrpc_destroy_cache_detail(cd); return ret; } EXPORT_SYMBOL_GPL(cache_register_net); void cache_unregister_net(struct cache_detail *cd, struct net *net) { remove_cache_proc_entries(cd); sunrpc_destroy_cache_detail(cd); } EXPORT_SYMBOL_GPL(cache_unregister_net); struct cache_detail *cache_create_net(const struct cache_detail *tmpl, struct net *net) { struct cache_detail *cd; int i; cd = kmemdup(tmpl, sizeof(struct cache_detail), GFP_KERNEL); if (cd == NULL) return ERR_PTR(-ENOMEM); cd->hash_table = kcalloc(cd->hash_size, sizeof(struct hlist_head), GFP_KERNEL); if (cd->hash_table == NULL) { kfree(cd); return ERR_PTR(-ENOMEM); } for (i = 0; i < cd->hash_size; i++) INIT_HLIST_HEAD(&cd->hash_table[i]); cd->net = net; return cd; } EXPORT_SYMBOL_GPL(cache_create_net); void cache_destroy_net(struct cache_detail *cd, struct net *net) { kfree(cd->hash_table); kfree(cd); } EXPORT_SYMBOL_GPL(cache_destroy_net); static ssize_t cache_read_pipefs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = RPC_I(file_inode(filp))->private; return cache_read(filp, buf, count, ppos, cd); } static ssize_t cache_write_pipefs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = RPC_I(file_inode(filp))->private; return cache_write(filp, buf, count, ppos, cd); } static __poll_t cache_poll_pipefs(struct file *filp, poll_table *wait) { struct cache_detail *cd = RPC_I(file_inode(filp))->private; return cache_poll(filp, wait, cd); } static long cache_ioctl_pipefs(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct cache_detail *cd = RPC_I(inode)->private; return cache_ioctl(inode, filp, cmd, arg, cd); } static int cache_open_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return cache_open(inode, filp, cd); } static int cache_release_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return cache_release(inode, filp, cd); } const struct file_operations cache_file_operations_pipefs = { .owner = THIS_MODULE, .llseek = no_llseek, .read = cache_read_pipefs, .write = cache_write_pipefs, .poll = cache_poll_pipefs, .unlocked_ioctl = cache_ioctl_pipefs, /* for FIONREAD */ .open = cache_open_pipefs, .release = cache_release_pipefs, }; static int content_open_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return content_open(inode, filp, cd); } static int content_release_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return content_release(inode, filp, cd); } const struct file_operations content_file_operations_pipefs = { .open = content_open_pipefs, .read = seq_read, .llseek = seq_lseek, .release = content_release_pipefs, }; static int open_flush_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return open_flush(inode, filp, cd); } static int release_flush_pipefs(struct inode *inode, struct file *filp) { struct cache_detail *cd = RPC_I(inode)->private; return release_flush(inode, filp, cd); } static ssize_t read_flush_pipefs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = RPC_I(file_inode(filp))->private; return read_flush(filp, buf, count, ppos, cd); } static ssize_t write_flush_pipefs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { struct cache_detail *cd = RPC_I(file_inode(filp))->private; return write_flush(filp, buf, count, ppos, cd); } const struct file_operations cache_flush_operations_pipefs = { .open = open_flush_pipefs, .read = read_flush_pipefs, .write = write_flush_pipefs, .release = release_flush_pipefs, .llseek = no_llseek, }; int sunrpc_cache_register_pipefs(struct dentry *parent, const char *name, umode_t umode, struct cache_detail *cd) { struct dentry *dir = rpc_create_cache_dir(parent, name, umode, cd); if (IS_ERR(dir)) return PTR_ERR(dir); cd->pipefs = dir; return 0; } EXPORT_SYMBOL_GPL(sunrpc_cache_register_pipefs); void sunrpc_cache_unregister_pipefs(struct cache_detail *cd) { if (cd->pipefs) { rpc_remove_cache_dir(cd->pipefs); cd->pipefs = NULL; } } EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs); void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h) { spin_lock(&cd->hash_lock); if (!hlist_unhashed(&h->cache_list)){ sunrpc_begin_cache_remove_entry(h, cd); spin_unlock(&cd->hash_lock); sunrpc_end_cache_remove_entry(h, cd); } else spin_unlock(&cd->hash_lock); } EXPORT_SYMBOL_GPL(sunrpc_cache_unhash); |
| 1212 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 | // SPDX-License-Identifier: GPL-2.0 struct io_tctx_node { struct list_head ctx_node; struct task_struct *task; struct io_ring_ctx *ctx; }; int io_uring_alloc_task_context(struct task_struct *task, struct io_ring_ctx *ctx); void io_uring_del_tctx_node(unsigned long index); int __io_uring_add_tctx_node(struct io_ring_ctx *ctx); int __io_uring_add_tctx_node_from_submit(struct io_ring_ctx *ctx); void io_uring_clean_tctx(struct io_uring_task *tctx); void io_uring_unreg_ringfd(void); int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, unsigned nr_args); int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, unsigned nr_args); /* * Note that this task has used io_uring. We use it for cancelation purposes. */ static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; if (likely(tctx && tctx->last == ctx)) return 0; return __io_uring_add_tctx_node_from_submit(ctx); } |
| 381 1841 661 1800 211 7496 1844 321 171 121 121 21 121 121 121 120 121 121 119 3 5 917 121 1315 1312 879 15 441 166 896 4 2 50 12 18 51 52 52 50 52 557 7 1845 1844 1842 212 142 253 107 1905 1821 321 274 49 321 1090 816 1846 16 1843 1847 1850 1315 3208 3216 9 279 1316 1625 86 85 7110 7113 78 3241 280 3106 57 426 425 15 23 119 7 119 120 120 111 10 8 11 93 110 1 14 48 19 2 27 620 1 425 4 198 191 549 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * High-resolution kernel timers * * In contrast to the low-resolution timeout API, aka timer wheel, * hrtimers provide finer resolution and accuracy depending on system * configuration and capabilities. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * Based on the original timer wheel code * * Help, testing, suggestions, bugfixes, improvements were * provided by: * * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel * et. al. */ #include <linux/cpu.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/hrtimer.h> #include <linux/notifier.h> #include <linux/syscalls.h> #include <linux/interrupt.h> #include <linux/tick.h> #include <linux/err.h> #include <linux/debugobjects.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/sched/deadline.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <trace/events/timer.h> #include "tick-internal.h" /* * Masks for selecting the soft and hard context timers from * cpu_base->active */ #define MASK_SHIFT (HRTIMER_BASE_MONOTONIC_SOFT) #define HRTIMER_ACTIVE_HARD ((1U << MASK_SHIFT) - 1) #define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT) #define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD) /* * The timer bases: * * There are more clockids than hrtimer bases. Thus, we index * into the timer bases by the hrtimer_base_type enum. When trying * to reach a base using a clockid, hrtimer_clockid_to_base() * is used to convert from clockid to the proper hrtimer_base_type. */ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), .clock_base = { { .index = HRTIMER_BASE_MONOTONIC, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, { .index = HRTIMER_BASE_MONOTONIC_SOFT, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME_SOFT, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME_SOFT, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, } }; static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { /* Make sure we catch unsupported clockids */ [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES, [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; /* * Functions and macros which are different for UP/SMP systems are kept in a * single place */ #ifdef CONFIG_SMP /* * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base() * such that hrtimer_callback_running() can unconditionally dereference * timer->base->cpu_base */ static struct hrtimer_cpu_base migration_cpu_base = { .clock_base = { { .cpu_base = &migration_cpu_base, .seq = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq, &migration_cpu_base.lock), }, }, }; #define migration_base migration_cpu_base.clock_base[0] static inline bool is_migration_base(struct hrtimer_clock_base *base) { return base == &migration_base; } /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are * locked, and the base itself is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found on the lists/queues. * * When the timer's base is locked, and the timer removed from list, it is * possible to set timer->base = &migration_base and drop the lock: the timer * remains locked. */ static struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->lock) { struct hrtimer_clock_base *base; for (;;) { base = READ_ONCE(timer->base); if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; /* The timer has migrated to another CPU: */ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags); } cpu_relax(); } } /* * We do not migrate the timer when it is expiring before the next * event on the target cpu. When high resolution is enabled, we cannot * reprogram the target cpu hardware and we would cause it to fire * late. To keep it simple, we handle the high resolution enabled and * disabled case similar. * * Called with cpu_base->lock of target cpu held. */ static int hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base) { ktime_t expires; expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); return expires < new_base->cpu_base->expires_next; } static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target()); #endif return base; } /* * We switch the timer base to a power-optimized selected CPU target, * if: * - NO_HZ_COMMON is enabled * - timer migration is enabled * - the timer callback is not running * - the timer is not the first expiring timer on the new target * * If one of the above requirements is not fulfilled we move the timer * to the current CPU or leave it on the previously assigned CPU if * the timer callback is currently running. */ static inline struct hrtimer_clock_base * switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, int pinned) { struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base; struct hrtimer_clock_base *new_base; int basenum = base->index; this_cpu_base = this_cpu_ptr(&hrtimer_bases); new_cpu_base = get_target_base(this_cpu_base, pinned); again: new_base = &new_cpu_base->clock_base[basenum]; if (base != new_base) { /* * We are trying to move timer to new_base. * However we can't change timer's base while it is running, * so we keep it on the same CPU. No hassle vs. reprogramming * the event source in the high resolution case. The softirq * code will take care of this when the timer function has * completed. There is no conflict as we hold the lock until * the timer is enqueued. */ if (unlikely(hrtimer_callback_running(timer))) return base; /* See the comment in lock_hrtimer_base() */ WRITE_ONCE(timer->base, &migration_base); raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); if (new_cpu_base != this_cpu_base && hrtimer_check_target(timer, new_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; WRITE_ONCE(timer->base, base); goto again; } WRITE_ONCE(timer->base, new_base); } else { if (new_cpu_base != this_cpu_base && hrtimer_check_target(timer, new_base)) { new_cpu_base = this_cpu_base; goto again; } } return new_base; } #else /* CONFIG_SMP */ static inline bool is_migration_base(struct hrtimer_clock_base *base) { return false; } static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->cpu_base->lock) { struct hrtimer_clock_base *base = timer->base; raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); return base; } # define switch_hrtimer_base(t, b, p) (b) #endif /* !CONFIG_SMP */ /* * Functions for the union type storage format of ktime_t which are * too large for inlining: */ #if BITS_PER_LONG < 64 /* * Divide a ktime value by a nanosecond value */ s64 __ktime_divns(const ktime_t kt, s64 div) { int sft = 0; s64 dclc; u64 tmp; dclc = ktime_to_ns(kt); tmp = dclc < 0 ? -dclc : dclc; /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; div >>= 1; } tmp >>= sft; do_div(tmp, (u32) div); return dclc < 0 ? -tmp : tmp; } EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* * Add two ktime values and do a safety check for overflow: */ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) { ktime_t res = ktime_add_unsafe(lhs, rhs); /* * We use KTIME_SEC_MAX here, the maximum timeout which we can * return to user space in a timespec: */ if (res < 0 || res < lhs || res < rhs) res = ktime_set(KTIME_SEC_MAX, 0); return res; } EXPORT_SYMBOL_GPL(ktime_add_safe); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr hrtimer_debug_descr; static void *hrtimer_debug_hint(void *addr) { return ((struct hrtimer *) addr)->function; } /* * fixup_init is called when: * - an active object is initialized */ static bool hrtimer_fixup_init(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_init(timer, &hrtimer_debug_descr); return true; default: return false; } } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) { switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool hrtimer_fixup_free(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_free(timer, &hrtimer_debug_descr); return true; default: return false; } } static const struct debug_obj_descr hrtimer_debug_descr = { .name = "hrtimer", .debug_hint = hrtimer_debug_hint, .fixup_init = hrtimer_fixup_init, .fixup_activate = hrtimer_fixup_activate, .fixup_free = hrtimer_fixup_free, }; static inline void debug_hrtimer_init(struct hrtimer *timer) { debug_object_init(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_object_activate(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { debug_object_deactivate(timer, &hrtimer_debug_descr); } static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode); void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { debug_object_init_on_stack(timer, &hrtimer_debug_descr); __hrtimer_init(timer, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr); __hrtimer_init_sleeper(sl, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } #endif static inline void debug_init(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init(timer); trace_hrtimer_init(timer, clockid, mode); } static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_hrtimer_activate(timer, mode); trace_hrtimer_start(timer, mode); } static inline void debug_deactivate(struct hrtimer *timer) { debug_hrtimer_deactivate(timer); trace_hrtimer_cancel(timer); } static struct hrtimer_clock_base * __next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active) { unsigned int idx; if (!*active) return NULL; idx = __ffs(*active); *active &= ~(1U << idx); return &cpu_base->clock_base[idx]; } #define for_each_active_base(base, cpu_base, active) \ while ((base = __next_base((cpu_base), &(active)))) static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base, const struct hrtimer *exclude, unsigned int active, ktime_t expires_next) { struct hrtimer_clock_base *base; ktime_t expires; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; struct hrtimer *timer; next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); if (timer == exclude) { /* Get to the next timer in the queue. */ next = timerqueue_iterate_next(next); if (!next) continue; timer = container_of(next, struct hrtimer, node); } expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires < expires_next) { expires_next = expires; /* Skip cpu_base update if a timer is being excluded. */ if (exclude) continue; if (timer->is_soft) cpu_base->softirq_next_timer = timer; else cpu_base->next_timer = timer; } } /* * clock_was_set() might have changed base->offset of any of * the clock bases so the result might be negative. Fix it up * to prevent a false positive in clockevents_program_event(). */ if (expires_next < 0) expires_next = 0; return expires_next; } /* * Recomputes cpu_base::*next_timer and returns the earliest expires_next * but does not set cpu_base::*expires_next, that is done by * hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating * cpu_base::*expires_next right away, reprogramming logic would no longer * work. * * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases, * those timers will get run whenever the softirq gets handled, at the end of * hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases. * * Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases. * The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual * softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD. * * @active_mask must be one of: * - HRTIMER_ACTIVE_ALL, * - HRTIMER_ACTIVE_SOFT, or * - HRTIMER_ACTIVE_HARD. */ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask) { unsigned int active; struct hrtimer *next_timer = NULL; ktime_t expires_next = KTIME_MAX; if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; cpu_base->softirq_next_timer = NULL; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, KTIME_MAX); next_timer = cpu_base->softirq_next_timer; } if (active_mask & HRTIMER_ACTIVE_HARD) { active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; cpu_base->next_timer = next_timer; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, expires_next); } return expires_next; } static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base) { ktime_t expires_next, soft = KTIME_MAX; /* * If the soft interrupt has already been activated, ignore the * soft bases. They will be handled in the already raised soft * interrupt. */ if (!cpu_base->softirq_activated) { soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * Update the soft expiry time. clock_settime() might have * affected it. */ cpu_base->softirq_expires_next = soft; } expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD); /* * If a softirq timer is expiring first, update cpu_base->next_timer * and program the hardware with the soft expiry time. */ if (expires_next > soft) { cpu_base->next_timer = cpu_base->softirq_next_timer; expires_next = soft; } return expires_next; } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; } /* * Is the high resolution mode active ? */ static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? cpu_base->hres_active : 0; } static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, struct hrtimer *next_timer, ktime_t expires_next) { cpu_base->expires_next = expires_next; /* * If hres is not active, hardware does not have to be * reprogrammed yet. * * If a hang was detected in the last timer interrupt then we * leave the hang delay active in the hardware. We want the * system to make progress. That also prevents the following * scenario: * T1 expires 50ms from now * T2 expires 5s from now * * T1 is removed, so this code is called and would reprogram * the hardware to 5s from now. Any hrtimer_start after that * will not reprogram the hardware due to hang_detected being * set. So we'd effectively block all timers until the T2 event * fires. */ if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) return; tick_program_event(expires_next, 1); } /* * Reprogram the event source with checking both queues for the * next event * Called with interrupts disabled and base->lock held */ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { ktime_t expires_next; expires_next = hrtimer_update_next_event(cpu_base); if (skip_equal && expires_next == cpu_base->expires_next) return; __hrtimer_reprogram(cpu_base, cpu_base->next_timer, expires_next); } /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer enabled ? */ static bool hrtimer_hres_enabled __read_mostly = true; unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; EXPORT_SYMBOL_GPL(hrtimer_resolution); /* * Enable / Disable high resolution mode */ static int __init setup_hrtimer_hres(char *str) { return (kstrtobool(str, &hrtimer_hres_enabled) == 0); } __setup("highres=", setup_hrtimer_hres); /* * hrtimer_high_res_enabled - query, if the highres mode is enabled */ static inline int hrtimer_is_hres_enabled(void) { return hrtimer_hres_enabled; } static void retrigger_next_event(void *arg); /* * Switch to high resolution mode */ static void hrtimer_switch_to_hres(void) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { pr_warn("Could not switch to high resolution mode on CPU %u\n", base->cpu); return; } base->hres_active = 1; hrtimer_resolution = HIGH_RES_NSEC; tick_setup_sched_timer(true); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); } #else static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline void hrtimer_switch_to_hres(void) { } #endif /* CONFIG_HIGH_RES_TIMERS */ /* * Retrigger next event is called after clock was set with interrupts * disabled through an SMP function call or directly from low level * resume code. * * This is only invoked when: * - CONFIG_HIGH_RES_TIMERS is enabled. * - CONFIG_NOHZ_COMMON is enabled * * For the other cases this function is empty and because the call sites * are optimized out it vanishes as well, i.e. no need for lots of * #ifdeffery. */ static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); /* * When high resolution mode or nohz is active, then the offsets of * CLOCK_REALTIME/TAI/BOOTTIME have to be updated. Otherwise the * next tick will take care of that. * * If high resolution mode is active then the next expiring timer * must be reevaluated and the clock event device reprogrammed if * necessary. * * In the NOHZ case the update of the offset and the reevaluation * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. */ if (!hrtimer_hres_active(base) && !tick_nohz_active) return; raw_spin_lock(&base->lock); hrtimer_update_base(base); if (hrtimer_hres_active(base)) hrtimer_force_reprogram(base, 0); else hrtimer_update_next_event(base); raw_spin_unlock(&base->lock); } /* * When a timer is enqueued and expires earlier than the already enqueued * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * * Called with interrupts disabled and base->cpu_base.lock held */ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *base = timer->base; ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* * CLOCK_REALTIME timer might be requested with an absolute * expiry time which is less than base->offset. Set it to 0. */ if (expires < 0) expires = 0; if (timer->is_soft) { /* * soft hrtimer could be started on a remote CPU. In this * case softirq_expires_next needs to be updated on the * remote CPU. The soft hrtimer will not expire before the * first hard hrtimer on the remote CPU - * hrtimer_check_target() prevents this case. */ struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base; if (timer_cpu_base->softirq_activated) return; if (!ktime_before(expires, timer_cpu_base->softirq_expires_next)) return; timer_cpu_base->softirq_next_timer = timer; timer_cpu_base->softirq_expires_next = expires; if (!ktime_before(expires, timer_cpu_base->expires_next) || !reprogram) return; } /* * If the timer is not on the current cpu, we cannot reprogram * the other cpus clock event device. */ if (base->cpu_base != cpu_base) return; if (expires >= cpu_base->expires_next) return; /* * If the hrtimer interrupt is running, then it will reevaluate the * clock bases and reprogram the clock event device. */ if (cpu_base->in_hrtirq) return; cpu_base->next_timer = timer; __hrtimer_reprogram(cpu_base, timer, expires); } static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, unsigned int active) { struct hrtimer_clock_base *base; unsigned int seq; ktime_t expires; /* * Update the base offsets unconditionally so the following * checks whether the SMP function call is required works. * * The update is safe even when the remote CPU is in the hrtimer * interrupt or the hrtimer soft interrupt and expiring affected * bases. Either it will see the update before handling a base or * it will see it when it finishes the processing and reevaluates * the next expiring timer. */ seq = cpu_base->clock_was_set_seq; hrtimer_update_base(cpu_base); /* * If the sequence did not change over the update then the * remote CPU already handled it. */ if (seq == cpu_base->clock_was_set_seq) return false; /* * If the remote CPU is currently handling an hrtimer interrupt, it * will reevaluate the first expiring timer of all clock bases * before reprogramming. Nothing to do here. */ if (cpu_base->in_hrtirq) return false; /* * Walk the affected clock bases and check whether the first expiring * timer in a clock base is moving ahead of the first expiring timer of * @cpu_base. If so, the IPI must be invoked because per CPU clock * event devices cannot be remotely reprogrammed. */ active &= cpu_base->active_bases; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; next = timerqueue_getnext(&base->active); expires = ktime_sub(next->expires, base->offset); if (expires < cpu_base->expires_next) return true; /* Extra check for softirq clock bases */ if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; if (expires < cpu_base->softirq_expires_next) return true; } return false; } /* * Clock was set. This might affect CLOCK_REALTIME, CLOCK_TAI and * CLOCK_BOOTTIME (for late sleep time injection). * * This requires to update the offsets for these clocks * vs. CLOCK_MONOTONIC. When high resolution timers are enabled, then this * also requires to eventually reprogram the per CPU clock event devices * when the change moves an affected timer ahead of the first expiring * timer on that CPU. Obviously remote per CPU clock event devices cannot * be reprogrammed. The other reason why an IPI has to be sent is when the * system is in !HIGH_RES and NOHZ mode. The NOHZ mode updates the offsets * in the tick, which obviously might be stopped, so this has to bring out * the remote CPU which might sleep in idle to get this sorted. */ void clock_was_set(unsigned int bases) { struct hrtimer_cpu_base *cpu_base = raw_cpu_ptr(&hrtimer_bases); cpumask_var_t mask; int cpu; if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active) goto out_timerfd; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { on_each_cpu(retrigger_next_event, NULL, 1); goto out_timerfd; } /* Avoid interrupting CPUs if possible */ cpus_read_lock(); for_each_online_cpu(cpu) { unsigned long flags; cpu_base = &per_cpu(hrtimer_bases, cpu); raw_spin_lock_irqsave(&cpu_base->lock, flags); if (update_needs_ipi(cpu_base, bases)) cpumask_set_cpu(cpu, mask); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } preempt_disable(); smp_call_function_many(mask, retrigger_next_event, NULL, 1); preempt_enable(); cpus_read_unlock(); free_cpumask_var(mask); out_timerfd: timerfd_clock_was_set(); } static void clock_was_set_work(struct work_struct *work) { clock_was_set(CLOCK_SET_WALL); } static DECLARE_WORK(hrtimer_work, clock_was_set_work); /* * Called from timekeeping code to reprogram the hrtimer interrupt device * on all cpus and to notify timerfd. */ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } /* * Called during resume either directly from via timekeeping_resume() * or in the case of s2idle from tick_unfreeze() to ensure that the * hrtimers are up to date. */ void hrtimers_resume_local(void) { lockdep_assert_irqs_disabled(); /* Retrigger on the local CPU */ retrigger_next_event(NULL); } /* * Counterpart to lock_hrtimer_base above: */ static inline void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __releases(&timer->base->cpu_base->lock) { raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); } /** * hrtimer_forward() - forward the timer expiry * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward * * Forward the timer expiry so it will expire in the future. * * .. note:: * This only updates the timer expiry value and does not requeue the timer. * * There is also a variant of the function hrtimer_forward_now(). * * Context: Can be safely called from the callback function of @timer. If called * from other contexts @timer must neither be enqueued nor running the * callback and the caller needs to take care of serialization. * * Return: The number of overruns are returned. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { u64 orun = 1; ktime_t delta; delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta < 0) return 0; if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED)) return 0; if (interval < hrtimer_resolution) interval = hrtimer_resolution; if (unlikely(delta >= interval)) { s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); hrtimer_add_expires_ns(timer, incr * orun); if (hrtimer_get_expires_tv64(timer) > now) return orun; /* * This (and the ktime_add() below) is the * correction for exact: */ orun++; } hrtimer_add_expires(timer, interval); return orun; } EXPORT_SYMBOL_GPL(hrtimer_forward); /* * enqueue_hrtimer - internal function to (re)start a timer * * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. * * Returns 1 when the new timer is the leftmost timer in the tree. */ static int enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, enum hrtimer_mode mode) { debug_activate(timer, mode); WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } /* * __remove_hrtimer - internal function to remove a timer * * Caller must hold the base lock. * * High resolution timer mode reprograms the clock event device when the * timer is the one which expires next. The caller can disable this by setting * reprogram to zero. This is useful, when the context does a reprogramming * anyway (e.g. timer interrupt) */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; if (!timerqueue_del(&base->active, &timer->node)) cpu_base->active_bases &= ~(1 << base->index); /* * Note: If reprogram is false we do not update * cpu_base->next_timer. This happens when we remove the first * timer on a remote cpu. No harm as we never dereference * cpu_base->next_timer. So the worst thing what can happen is * an superfluous call to hrtimer_force_reprogram() on the * remote cpu later on if the same timer gets enqueued again. */ if (reprogram && timer == cpu_base->next_timer) hrtimer_force_reprogram(cpu_base, 1); } /* * remove hrtimer, called with base lock held */ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart, bool keep_local) { u8 state = timer->state; if (state & HRTIMER_STATE_ENQUEUED) { bool reprogram; /* * Remove the timer and force reprogramming when high * resolution mode is active and the timer is on the current * CPU. If we remove a timer on another CPU, reprogramming is * skipped. The interrupt event on this CPU is fired and * reprogramming happens in the interrupt handler. This is a * rare case and less expensive than a smp call. */ debug_deactivate(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); /* * If the timer is not restarted then reprogramming is * required if the timer is local. If it is local and about * to be restarted, avoid programming it twice (on removal * and a moment later when it's requeued). */ if (!restart) state = HRTIMER_STATE_INACTIVE; else reprogram &= !keep_local; __remove_hrtimer(timer, base, state, reprogram); return 1; } return 0; } static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { #ifdef CONFIG_TIME_LOW_RES /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution * (i.e. one jiffy) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) tim = ktime_add_safe(tim, hrtimer_resolution); #endif return tim; } static void hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram) { ktime_t expires; /* * Find the next SOFT expiration. */ expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * reprogramming needs to be triggered, even if the next soft * hrtimer expires at the same time than the next hard * hrtimer. cpu_base->softirq_expires_next needs to be updated! */ if (expires == KTIME_MAX) return; /* * cpu_base->*next_timer is recomputed by __hrtimer_get_next_event() * cpu_base->*expires_next is only set by hrtimer_reprogram() */ hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram); } static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode, struct hrtimer_clock_base *base) { struct hrtimer_clock_base *new_base; bool force_local, first; /* * If the timer is on the local cpu base and is the first expiring * timer then this might end up reprogramming the hardware twice * (on removal and on enqueue). To avoid that by prevent the * reprogram on removal, keep the timer local to the current CPU * and enforce reprogramming after it is queued no matter whether * it is the new first expiring timer again or not. */ force_local = base->cpu_base == this_cpu_ptr(&hrtimer_bases); force_local &= base->cpu_base->next_timer == timer; /* * Remove an active timer from the queue. In case it is not queued * on the current CPU, make sure that remove_hrtimer() updates the * remote data correctly. * * If it's on the current CPU and the first expiring timer, then * skip reprogramming, keep the timer local and enforce * reprogramming later if it was the first expiring timer. This * avoids programming the underlying clock event twice (once at * removal and once after enqueue). */ remove_hrtimer(timer, base, true, force_local); if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); /* Switch the timer base, if necessary: */ if (!force_local) { new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); } else { new_base = base; } first = enqueue_hrtimer(timer, new_base, mode); if (!force_local) return first; /* * Timer was forced to stay on the current CPU to avoid * reprogramming on removal and enqueue. Force reprogram the * hardware by evaluating the new first expiring timer. */ hrtimer_force_reprogram(new_base->cpu_base, 1); return 0; } /** * hrtimer_start_range_ns - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @delta_ns: "slack" range for the timer * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base; unsigned long flags; if (WARN_ON_ONCE(!timer->function)) return; /* * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard * expiry mode because unmarked timers are moved to softirq expiry. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); else WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard); base = lock_hrtimer_base(timer, &flags); if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base)) hrtimer_reprogram(timer, true); unlock_hrtimer_base(timer, &flags); } EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop * * Returns: * * * 0 when the timer was not active * * 1 when the timer was active * * -1 when the timer is currently executing the callback function and * cannot be stopped */ int hrtimer_try_to_cancel(struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned long flags; int ret = -1; /* * Check lockless first. If the timer is not active (neither * enqueued nor running the callback, nothing to do here. The * base lock does not serialize against a concurrent enqueue, * so we can avoid taking it. */ if (!hrtimer_active(timer)) return 0; base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) ret = remove_hrtimer(timer, base, false, false); unlock_hrtimer_base(timer, &flags); return ret; } EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); #ifdef CONFIG_PREEMPT_RT static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { spin_lock_init(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) __acquires(&base->softirq_expiry_lock) { spin_lock(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) __releases(&base->softirq_expiry_lock) { spin_unlock(&base->softirq_expiry_lock); } /* * The counterpart to hrtimer_cancel_wait_running(). * * If there is a waiter for cpu_base->expiry_lock, then it was waiting for * the timer callback to finish. Drop expiry_lock and reacquire it. That * allows the waiter to acquire the lock and make progress. */ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, unsigned long flags) { if (atomic_read(&cpu_base->timer_waiters)) { raw_spin_unlock_irqrestore(&cpu_base->lock, flags); spin_unlock(&cpu_base->softirq_expiry_lock); spin_lock(&cpu_base->softirq_expiry_lock); raw_spin_lock_irq(&cpu_base->lock); } } /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion: if the soft irq thread is preempted * in the middle of a timer callback, then calling del_timer_sync() can * lead to two issues: * * - If the caller is on a remote CPU then it has to spin wait for the timer * handler to complete. This can result in unbound priority inversion. * * - If the caller originates from the task which preempted the timer * handler on the same CPU, then spin waiting for the timer handler to * complete is never going to end. */ void hrtimer_cancel_wait_running(const struct hrtimer *timer) { /* Lockless read. Prevent the compiler from reloading it below */ struct hrtimer_clock_base *base = READ_ONCE(timer->base); /* * Just relax if the timer expires in hard interrupt context or if * it is currently on the migration base. */ if (!timer->is_soft || is_migration_base(base)) { cpu_relax(); return; } /* * Mark the base as contended and grab the expiry lock, which is * held by the softirq across the timer callback. Drop the lock * immediately so the softirq can expire the next timer. In theory * the timer could already be running again, but that's more than * unlikely and just causes another wait loop. */ atomic_inc(&base->cpu_base->timer_waiters); spin_lock_bh(&base->cpu_base->softirq_expiry_lock); atomic_dec(&base->cpu_base->timer_waiters); spin_unlock_bh(&base->cpu_base->softirq_expiry_lock); } #else static inline void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_sync_wait_running(struct hrtimer_cpu_base *base, unsigned long flags) { } #endif /** * hrtimer_cancel - cancel a timer and wait for the handler to finish. * @timer: the timer to be cancelled * * Returns: * 0 when the timer was not active * 1 when the timer was active */ int hrtimer_cancel(struct hrtimer *timer) { int ret; do { ret = hrtimer_try_to_cancel(timer); if (ret < 0) hrtimer_cancel_wait_running(timer); } while (ret < 0); return ret; } EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * __hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) rem = hrtimer_expires_remaining_adjusted(timer); else rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** * hrtimer_get_next_event - get the time until next expiry event * * Returns the next expiry time or KTIME_MAX if no timer is pending. */ u64 hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (!hrtimer_hres_active(cpu_base)) expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } /** * hrtimer_next_event_without - time until next expiry event w/o one timer * @exclude: timer to exclude * * Returns the next expiry time over all timers except for the @exclude one or * KTIME_MAX if none of them is pending. */ u64 hrtimer_next_event_without(const struct hrtimer *exclude) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (hrtimer_hres_active(cpu_base)) { unsigned int active; if (!cpu_base->softirq_activated) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; expires = __hrtimer_next_event_base(cpu_base, exclude, active, KTIME_MAX); } active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; expires = __hrtimer_next_event_base(cpu_base, exclude, active, expires); } raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } #endif static inline int hrtimer_clockid_to_base(clockid_t clock_id) { if (likely(clock_id < MAX_CLOCKS)) { int base = hrtimer_clock_to_base_table[clock_id]; if (likely(base != HRTIMER_MAX_CLOCK_BASES)) return base; } WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); return HRTIMER_BASE_MONOTONIC; } static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { bool softtimer = !!(mode & HRTIMER_MODE_SOFT); struct hrtimer_cpu_base *cpu_base; int base; /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context for latency reasons and because the callbacks * can invoke functions which might sleep on RT, e.g. spin_lock(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(mode & HRTIMER_MODE_HARD)) softtimer = true; memset(timer, 0, sizeof(struct hrtimer)); cpu_base = raw_cpu_ptr(&hrtimer_bases); /* * POSIX magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they needs to become CLOCK_MONOTONIC to * ensure POSIX compliance. */ if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC; base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; base += hrtimer_clockid_to_base(clock_id); timer->is_soft = softtimer; timer->is_hard = !!(mode & HRTIMER_MODE_HARD); timer->base = &cpu_base->clock_base[base]; timerqueue_init(&timer->node); } /** * hrtimer_init - initialize a timer to the given clock * @timer: the timer to be initialized * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { debug_init(timer, clock_id, mode); __hrtimer_init(timer, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init); /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated * to another cpu. * * It is important for this function to not return a false negative. */ bool hrtimer_active(const struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned int seq; do { base = READ_ONCE(timer->base); seq = raw_read_seqcount_begin(&base->seq); if (timer->state != HRTIMER_STATE_INACTIVE || base->running == timer) return true; } while (read_seqcount_retry(&base->seq, seq) || base != READ_ONCE(timer->base)); return false; } EXPORT_SYMBOL_GPL(hrtimer_active); /* * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3 * distinct sections: * * - queued: the timer is queued * - callback: the timer is being ran * - post: the timer is inactive or (re)queued * * On the read side we ensure we observe timer->state and cpu_base->running * from the same section, if anything changed while we looked at it, we retry. * This includes timer->base changing because sequence numbers alone are * insufficient for that. * * The sequence numbers are required because otherwise we could still observe * a false negative if the read side got smeared over multiple consecutive * __run_hrtimer() invocations. */ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, struct hrtimer_clock_base *base, struct hrtimer *timer, ktime_t *now, unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); bool expires_in_hardirq; int restart; lockdep_assert_held(&cpu_base->lock); debug_deactivate(timer); base->running = timer; /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); fn = timer->function; /* * Clear the 'is relative' flag for the TIME_LOW_RES case. If the * timer is restarted with a period then it becomes an absolute * timer. If its not restarted it does not matter. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES)) timer->is_rel = false; /* * The timer is marked as running in the CPU base, so it is * protected against migration to a different CPU even if the lock * is dropped. */ raw_spin_unlock_irqrestore(&cpu_base->lock, flags); trace_hrtimer_expire_entry(timer, now); expires_in_hardirq = lockdep_hrtimer_enter(timer); restart = fn(timer); lockdep_hrtimer_exit(expires_in_hardirq); trace_hrtimer_expire_exit(timer); raw_spin_lock_irq(&cpu_base->lock); /* * Note: We clear the running state after enqueue_hrtimer and * we do not reprogram the event hardware. Happens either in * hrtimer_start_range_ns() or in hrtimer_interrupt() * * Note: Because we dropped the cpu_base->lock above, * hrtimer_start_range_ns() can have popped in and enqueued the timer * for us already. */ if (restart != HRTIMER_NORESTART && !(timer->state & HRTIMER_STATE_ENQUEUED)) enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS); /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running.timer == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); WARN_ON_ONCE(base->running != timer); base->running = NULL; } static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, unsigned long flags, unsigned int active_mask) { struct hrtimer_clock_base *base; unsigned int active = cpu_base->active_bases & active_mask; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *node; ktime_t basenow; basenow = ktime_add(now, base->offset); while ((node = timerqueue_getnext(&base->active))) { struct hrtimer *timer; timer = container_of(node, struct hrtimer, node); /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the * earliest interrupt after their soft expiration. * This allows us to avoid using a Priority Search * Tree, which can answer a stabbing query for * overlapping intervals and instead use the simple * BST we already have. * We don't add extra wakeups by delaying timers that * are right-of a not yet expired timer, because that * timer will have to trigger a wakeup anyway. */ if (basenow < hrtimer_get_softexpires_tv64(timer)) break; __run_hrtimer(cpu_base, base, timer, &basenow, flags); if (active_mask == HRTIMER_ACTIVE_SOFT) hrtimer_sync_wait_running(cpu_base, flags); } } } static __latent_entropy void hrtimer_run_softirq(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; hrtimer_cpu_base_lock_expiry(cpu_base); raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT); cpu_base->softirq_activated = 0; hrtimer_update_softirq_timer(cpu_base, true); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); hrtimer_cpu_base_unlock_expiry(cpu_base); } #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer interrupt * Called with interrupts disabled */ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); ktime_t expires_next, now, entry_time, delta; unsigned long flags; int retries = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; dev->next_event = KTIME_MAX; raw_spin_lock_irqsave(&cpu_base->lock, flags); entry_time = now = hrtimer_update_base(cpu_base); retry: cpu_base->in_hrtirq = 1; /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via * the migration code. This does not affect enqueueing of * timers which run their callback and need to be requeued on * this CPU. */ cpu_base->expires_next = KTIME_MAX; if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_softirq_irqoff(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); /* Reevaluate the clock bases for the [soft] next expiry */ expires_next = hrtimer_update_next_event(cpu_base); /* * Store the new expiry value so the migration code can verify * against it. */ cpu_base->expires_next = expires_next; cpu_base->in_hrtirq = 0; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); /* Reprogramming necessary ? */ if (!tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; return; } /* * The next timer was already expired due to: * - tracing * - long lasting callbacks * - being scheduled away when running in a VM * * We need to prevent that we loop forever in the hrtimer * interrupt routine. We give it 3 attempts to avoid * overreacting on some spurious event. * * Acquire base lock for updating the offsets and retrieving * the current time. */ raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); cpu_base->nr_retries++; if (++retries < 3) goto retry; /* * Give the system a chance to do something else than looping * here. We stored the entry time, so we know exactly how long * we spent here. We schedule the next event this amount of * time away. */ cpu_base->nr_hangs++; cpu_base->hang_detected = 1; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); delta = ktime_sub(now, entry_time); if ((unsigned int)delta > cpu_base->max_hang_time) cpu_base->max_hang_time = (unsigned int) delta; /* * Limit it to a sensible value as we enforce a longer * delay. Give the CPU at least 100ms to catch up. */ if (delta > 100 * NSEC_PER_MSEC) expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC); else expires_next = ktime_add(now, delta); tick_program_event(expires_next, 1); pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } #endif /* !CONFIG_HIGH_RES_TIMERS */ /* * Called from run_local_timers in hardirq context every jiffy */ void hrtimer_run_queues(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; if (hrtimer_hres_active(cpu_base)) return; /* * This _is_ ugly: We have to check periodically, whether we * can switch to highres and / or nohz mode. The clocksource * switch happens with xtime_lock held. Notification from * there only sets the check bit in the tick_oneshot code, * otherwise we might deadlock vs. xtime_lock. */ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) { hrtimer_switch_to_hres(); return; } raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_softirq_irqoff(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } /* * Sleep related functions: */ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) { struct hrtimer_sleeper *t = container_of(timer, struct hrtimer_sleeper, timer); struct task_struct *task = t->task; t->task = NULL; if (task) wake_up_process(task); return HRTIMER_NORESTART; } /** * hrtimer_sleeper_start_expires - Start a hrtimer sleeper timer * @sl: sleeper to be started * @mode: timer mode abs/rel * * Wrapper around hrtimer_start_expires() for hrtimer_sleeper based timers * to allow PREEMPT_RT to tweak the delivery mode (soft/hardirq context) */ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode) { /* * Make the enqueue delivery mode check work on RT. If the sleeper * was initialized for hard interrupt delivery, force the mode bit. * This is a special case for hrtimer_sleepers because * hrtimer_init_sleeper() determines the delivery mode on RT so the * fiddling with this decision is avoided at the call sites. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) mode |= HRTIMER_MODE_HARD; hrtimer_start_expires(&sl->timer, mode); } EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires); static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context either for latency reasons or because the * hrtimer callback takes regular spinlocks or invokes other * functions which are not suitable for hard interrupt context on * PREEMPT_RT. * * The hrtimer_sleeper callback is RT compatible in hard interrupt * context, but there is a latency concern: Untrusted userspace can * spawn many threads which arm timers for the same expiry time on * the same CPU. That causes a latency spike due to the wakeup of * a gazillion threads. * * OTOH, privileged real-time user space applications rely on the * low latency of hard interrupt wakeups. If the current task is in * a real-time scheduling class, mark the mode for hard interrupt * expiry. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) { if (task_is_realtime(current) && !(mode & HRTIMER_MODE_SOFT)) mode |= HRTIMER_MODE_HARD; } __hrtimer_init(&sl->timer, clock_id, mode); sl->timer.function = hrtimer_wakeup; sl->task = current; } /** * hrtimer_init_sleeper - initialize sleeper to the given clock * @sl: sleeper to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel */ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { debug_init(&sl->timer, clock_id, mode); __hrtimer_init_sleeper(sl, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { #ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; break; #endif case TT_NATIVE: if (put_timespec64(ts, restart->nanosleep.rmtp)) return -EFAULT; break; default: BUG(); } return -ERESTART_RESTARTBLOCK; } static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { struct restart_block *restart; do { set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); hrtimer_sleeper_start_expires(t, mode); if (likely(t->task)) schedule(); hrtimer_cancel(&t->timer); mode = HRTIMER_MODE_ABS; } while (t->task && !signal_pending(current)); __set_current_state(TASK_RUNNING); if (!t->task) return 0; restart = ¤t->restart_block; if (restart->nanosleep.type != TT_NONE) { ktime_t rem = hrtimer_expires_remaining(&t->timer); struct timespec64 rmt; if (rem <= 0) return 0; rmt = ktime_to_timespec64(rem); return nanosleep_copyout(restart, &rmt); } return -ERESTART_RESTARTBLOCK; } static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) { struct hrtimer_sleeper t; int ret; hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; } long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid) { struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; hrtimer_init_sleeper_on_stack(&t, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; /* Absolute timers do not update the rmtp value and restart: */ if (mode == HRTIMER_MODE_ABS) { ret = -ERESTARTNOHAND; goto out; } restart = ¤t->restart_block; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); set_restart_fn(restart, hrtimer_nanosleep_restart); out: destroy_hrtimer_on_stack(&t.timer); return ret; } #ifdef CONFIG_64BIT SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, struct __kernel_timespec __user *, rmtp) { struct timespec64 tu; if (get_timespec64(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { struct timespec64 tu; if (get_old_timespec32(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif /* * Functions related to boot-time initialization: */ int hrtimers_prepare_cpu(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i]; clock_b->cpu_base = cpu_base; seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock); timerqueue_init_head(&clock_b->active); } cpu_base->cpu = cpu; cpu_base->active_bases = 0; cpu_base->hres_active = 0; cpu_base->hang_detected = 0; cpu_base->next_timer = NULL; cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->online = 1; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } #ifdef CONFIG_HOTPLUG_CPU static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, struct hrtimer_clock_base *new_base) { struct hrtimer *timer; struct timerqueue_node *node; while ((node = timerqueue_getnext(&old_base->active))) { timer = container_of(node, struct hrtimer, node); BUG_ON(hrtimer_callback_running(timer)); debug_deactivate(timer); /* * Mark it as ENQUEUED not INACTIVE otherwise the * timer could be seen as !active and just vanish away * under us on another CPU */ __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0); timer->base = new_base; /* * Enqueue the timers on the new cpu. This does not * reprogram the event device in case the timer * expires before the earliest on this CPU, but we run * hrtimer_interrupt after we migrated everything to * sort out already expired timers and reprogram the * event device. */ enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS); } } int hrtimers_cpu_dying(unsigned int dying_cpu) { int i, ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER)); struct hrtimer_cpu_base *old_base, *new_base; old_base = this_cpu_ptr(&hrtimer_bases); new_base = &per_cpu(hrtimer_bases, ncpu); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock(&old_base->lock); raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], &new_base->clock_base[i]); } /* * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); old_base->online = 0; raw_spin_unlock(&old_base->lock); return 0; } #endif /* CONFIG_HOTPLUG_CPU */ void __init hrtimers_init(void) { hrtimers_prepare_cpu(smp_processor_id()); open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq); } /** * schedule_hrtimeout_range_clock - sleep until timeout * @expires: timeout value (ktime_t) * @delta: slack in expires timeout (ktime_t) * @mode: timer mode * @clock_id: timer clock to be used */ int __sched schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, const enum hrtimer_mode mode, clockid_t clock_id) { struct hrtimer_sleeper t; /* * Optimize when a zero timeout value is given. It does not * matter whether this is an absolute or a relative time. */ if (expires && *expires == 0) { __set_current_state(TASK_RUNNING); return 0; } /* * A NULL parameter means "infinite" */ if (!expires) { schedule(); return -EINTR; } hrtimer_init_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); hrtimer_sleeper_start_expires(&t, mode); if (likely(t.task)) schedule(); hrtimer_cancel(&t.timer); destroy_hrtimer_on_stack(&t.timer); __set_current_state(TASK_RUNNING); return !t.task ? 0 : -EINTR; } EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); /** * schedule_hrtimeout_range - sleep until timeout * @expires: timeout value (ktime_t) * @delta: slack in expires timeout (ktime_t) * @mode: timer mode * * Make the current task sleep until the given expiry time has * elapsed. The routine will return immediately unless * the current task state has been set (see set_current_state()). * * The @delta argument gives the kernel the freedom to schedule the * actual wakeup to a time that is both power and performance friendly * for regular (non RT/DL) tasks. * The kernel give the normal best effort behavior for "@expires+@delta", * but may decide to fire the timer earlier, but no earlier than @expires. * * You can set the task state as follows - * * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be TASK_RUNNING when this * routine returns. * * Returns 0 when the timer has expired. If the task was woken before the * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or * by an explicit wakeup, it returns -EINTR. */ int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode) { return schedule_hrtimeout_range_clock(expires, delta, mode, CLOCK_MONOTONIC); } EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); /** * schedule_hrtimeout - sleep until timeout * @expires: timeout value (ktime_t) * @mode: timer mode * * Make the current task sleep until the given expiry time has * elapsed. The routine will return immediately unless * the current task state has been set (see set_current_state()). * * You can set the task state as follows - * * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be TASK_RUNNING when this * routine returns. * * Returns 0 when the timer has expired. If the task was woken before the * timer expired by a signal (only possible in state TASK_INTERRUPTIBLE) or * by an explicit wakeup, it returns -EINTR. */ int __sched schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode) { return schedule_hrtimeout_range(expires, 0, mode); } EXPORT_SYMBOL_GPL(schedule_hrtimeout); |
| 370 369 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/lockdep.h> #include <linux/sysfs.h> #include <linux/kobject.h> #include <linux/memory.h> #include <linux/memory-tiers.h> #include <linux/notifier.h> #include "internal.h" struct memory_tier { /* hierarchy of memory tiers */ struct list_head list; /* list of all memory types part of this tier */ struct list_head memory_types; /* * start value of abstract distance. memory tier maps * an abstract distance range, * adistance_start .. adistance_start + MEMTIER_CHUNK_SIZE */ int adistance_start; struct device dev; /* All the nodes that are part of all the lower memory tiers. */ nodemask_t lower_tier_mask; }; struct demotion_nodes { nodemask_t preferred; }; struct node_memory_type_map { struct memory_dev_type *memtype; int map_count; }; static DEFINE_MUTEX(memory_tier_lock); static LIST_HEAD(memory_tiers); /* * The list is used to store all memory types that are not created * by a device driver. */ static LIST_HEAD(default_memory_types); static struct node_memory_type_map node_memory_types[MAX_NUMNODES]; struct memory_dev_type *default_dram_type; nodemask_t default_dram_nodes __initdata = NODE_MASK_NONE; static const struct bus_type memory_tier_subsys = { .name = "memory_tiering", .dev_name = "memory_tier", }; #ifdef CONFIG_MIGRATION static int top_tier_adistance; /* * node_demotion[] examples: * * Example 1: * * Node 0 & 1 are CPU + DRAM nodes, node 2 & 3 are PMEM nodes. * * node distances: * node 0 1 2 3 * 0 10 20 30 40 * 1 20 10 40 30 * 2 30 40 10 40 * 3 40 30 40 10 * * memory_tiers0 = 0-1 * memory_tiers1 = 2-3 * * node_demotion[0].preferred = 2 * node_demotion[1].preferred = 3 * node_demotion[2].preferred = <empty> * node_demotion[3].preferred = <empty> * * Example 2: * * Node 0 & 1 are CPU + DRAM nodes, node 2 is memory-only DRAM node. * * node distances: * node 0 1 2 * 0 10 20 30 * 1 20 10 30 * 2 30 30 10 * * memory_tiers0 = 0-2 * * node_demotion[0].preferred = <empty> * node_demotion[1].preferred = <empty> * node_demotion[2].preferred = <empty> * * Example 3: * * Node 0 is CPU + DRAM nodes, Node 1 is HBM node, node 2 is PMEM node. * * node distances: * node 0 1 2 * 0 10 20 30 * 1 20 10 40 * 2 30 40 10 * * memory_tiers0 = 1 * memory_tiers1 = 0 * memory_tiers2 = 2 * * node_demotion[0].preferred = 2 * node_demotion[1].preferred = 0 * node_demotion[2].preferred = <empty> * */ static struct demotion_nodes *node_demotion __read_mostly; #endif /* CONFIG_MIGRATION */ static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms); /* The lock is used to protect `default_dram_perf*` info and nid. */ static DEFINE_MUTEX(default_dram_perf_lock); static bool default_dram_perf_error; static struct access_coordinate default_dram_perf; static int default_dram_perf_ref_nid = NUMA_NO_NODE; static const char *default_dram_perf_ref_source; static inline struct memory_tier *to_memory_tier(struct device *device) { return container_of(device, struct memory_tier, dev); } static __always_inline nodemask_t get_memtier_nodemask(struct memory_tier *memtier) { nodemask_t nodes = NODE_MASK_NONE; struct memory_dev_type *memtype; list_for_each_entry(memtype, &memtier->memory_types, tier_sibling) nodes_or(nodes, nodes, memtype->nodes); return nodes; } static void memory_tier_device_release(struct device *dev) { struct memory_tier *tier = to_memory_tier(dev); /* * synchronize_rcu in clear_node_memory_tier makes sure * we don't have rcu access to this memory tier. */ kfree(tier); } static ssize_t nodelist_show(struct device *dev, struct device_attribute *attr, char *buf) { int ret; nodemask_t nmask; mutex_lock(&memory_tier_lock); nmask = get_memtier_nodemask(to_memory_tier(dev)); ret = sysfs_emit(buf, "%*pbl\n", nodemask_pr_args(&nmask)); mutex_unlock(&memory_tier_lock); return ret; } static DEVICE_ATTR_RO(nodelist); static struct attribute *memtier_dev_attrs[] = { &dev_attr_nodelist.attr, NULL }; static const struct attribute_group memtier_dev_group = { .attrs = memtier_dev_attrs, }; static const struct attribute_group *memtier_dev_groups[] = { &memtier_dev_group, NULL }; static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memtype) { int ret; bool found_slot = false; struct memory_tier *memtier, *new_memtier; int adistance = memtype->adistance; unsigned int memtier_adistance_chunk_size = MEMTIER_CHUNK_SIZE; lockdep_assert_held_once(&memory_tier_lock); adistance = round_down(adistance, memtier_adistance_chunk_size); /* * If the memtype is already part of a memory tier, * just return that. */ if (!list_empty(&memtype->tier_sibling)) { list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) return memtier; } WARN_ON(1); return ERR_PTR(-EINVAL); } list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) { goto link_memtype; } else if (adistance < memtier->adistance_start) { found_slot = true; break; } } new_memtier = kzalloc(sizeof(struct memory_tier), GFP_KERNEL); if (!new_memtier) return ERR_PTR(-ENOMEM); new_memtier->adistance_start = adistance; INIT_LIST_HEAD(&new_memtier->list); INIT_LIST_HEAD(&new_memtier->memory_types); if (found_slot) list_add_tail(&new_memtier->list, &memtier->list); else list_add_tail(&new_memtier->list, &memory_tiers); new_memtier->dev.id = adistance >> MEMTIER_CHUNK_BITS; new_memtier->dev.bus = &memory_tier_subsys; new_memtier->dev.release = memory_tier_device_release; new_memtier->dev.groups = memtier_dev_groups; ret = device_register(&new_memtier->dev); if (ret) { list_del(&new_memtier->list); put_device(&new_memtier->dev); return ERR_PTR(ret); } memtier = new_memtier; link_memtype: list_add(&memtype->tier_sibling, &memtier->memory_types); return memtier; } static struct memory_tier *__node_get_memory_tier(int node) { pg_data_t *pgdat; pgdat = NODE_DATA(node); if (!pgdat) return NULL; /* * Since we hold memory_tier_lock, we can avoid * RCU read locks when accessing the details. No * parallel updates are possible here. */ return rcu_dereference_check(pgdat->memtier, lockdep_is_held(&memory_tier_lock)); } #ifdef CONFIG_MIGRATION bool node_is_toptier(int node) { bool toptier; pg_data_t *pgdat; struct memory_tier *memtier; pgdat = NODE_DATA(node); if (!pgdat) return false; rcu_read_lock(); memtier = rcu_dereference(pgdat->memtier); if (!memtier) { toptier = true; goto out; } if (memtier->adistance_start <= top_tier_adistance) toptier = true; else toptier = false; out: rcu_read_unlock(); return toptier; } void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets) { struct memory_tier *memtier; /* * pg_data_t.memtier updates includes a synchronize_rcu() * which ensures that we either find NULL or a valid memtier * in NODE_DATA. protect the access via rcu_read_lock(); */ rcu_read_lock(); memtier = rcu_dereference(pgdat->memtier); if (memtier) *targets = memtier->lower_tier_mask; else *targets = NODE_MASK_NONE; rcu_read_unlock(); } /** * next_demotion_node() - Get the next node in the demotion path * @node: The starting node to lookup the next node * * Return: node id for next memory node in the demotion path hierarchy * from @node; NUMA_NO_NODE if @node is terminal. This does not keep * @node online or guarantee that it *continues* to be the next demotion * target. */ int next_demotion_node(int node) { struct demotion_nodes *nd; int target; if (!node_demotion) return NUMA_NO_NODE; nd = &node_demotion[node]; /* * node_demotion[] is updated without excluding this * function from running. * * Make sure to use RCU over entire code blocks if * node_demotion[] reads need to be consistent. */ rcu_read_lock(); /* * If there are multiple target nodes, just select one * target node randomly. * * In addition, we can also use round-robin to select * target node, but we should introduce another variable * for node_demotion[] to record last selected target node, * that may cause cache ping-pong due to the changing of * last target node. Or introducing per-cpu data to avoid * caching issue, which seems more complicated. So selecting * target node randomly seems better until now. */ target = node_random(&nd->preferred); rcu_read_unlock(); return target; } static void disable_all_demotion_targets(void) { struct memory_tier *memtier; int node; for_each_node_state(node, N_MEMORY) { node_demotion[node].preferred = NODE_MASK_NONE; /* * We are holding memory_tier_lock, it is safe * to access pgda->memtier. */ memtier = __node_get_memory_tier(node); if (memtier) memtier->lower_tier_mask = NODE_MASK_NONE; } /* * Ensure that the "disable" is visible across the system. * Readers will see either a combination of before+disable * state or disable+after. They will never see before and * after state together. */ synchronize_rcu(); } static void dump_demotion_targets(void) { int node; for_each_node_state(node, N_MEMORY) { struct memory_tier *memtier = __node_get_memory_tier(node); nodemask_t preferred = node_demotion[node].preferred; if (!memtier) continue; if (nodes_empty(preferred)) pr_info("Demotion targets for Node %d: null\n", node); else pr_info("Demotion targets for Node %d: preferred: %*pbl, fallback: %*pbl\n", node, nodemask_pr_args(&preferred), nodemask_pr_args(&memtier->lower_tier_mask)); } } /* * Find an automatic demotion target for all memory * nodes. Failing here is OK. It might just indicate * being at the end of a chain. */ static void establish_demotion_targets(void) { struct memory_tier *memtier; struct demotion_nodes *nd; int target = NUMA_NO_NODE, node; int distance, best_distance; nodemask_t tier_nodes, lower_tier; lockdep_assert_held_once(&memory_tier_lock); if (!node_demotion) return; disable_all_demotion_targets(); for_each_node_state(node, N_MEMORY) { best_distance = -1; nd = &node_demotion[node]; memtier = __node_get_memory_tier(node); if (!memtier || list_is_last(&memtier->list, &memory_tiers)) continue; /* * Get the lower memtier to find the demotion node list. */ memtier = list_next_entry(memtier, list); tier_nodes = get_memtier_nodemask(memtier); /* * find_next_best_node, use 'used' nodemask as a skip list. * Add all memory nodes except the selected memory tier * nodelist to skip list so that we find the best node from the * memtier nodelist. */ nodes_andnot(tier_nodes, node_states[N_MEMORY], tier_nodes); /* * Find all the nodes in the memory tier node list of same best distance. * add them to the preferred mask. We randomly select between nodes * in the preferred mask when allocating pages during demotion. */ do { target = find_next_best_node(node, &tier_nodes); if (target == NUMA_NO_NODE) break; distance = node_distance(node, target); if (distance == best_distance || best_distance == -1) { best_distance = distance; node_set(target, nd->preferred); } else { break; } } while (1); } /* * Promotion is allowed from a memory tier to higher * memory tier only if the memory tier doesn't include * compute. We want to skip promotion from a memory tier, * if any node that is part of the memory tier have CPUs. * Once we detect such a memory tier, we consider that tier * as top tiper from which promotion is not allowed. */ list_for_each_entry_reverse(memtier, &memory_tiers, list) { tier_nodes = get_memtier_nodemask(memtier); nodes_and(tier_nodes, node_states[N_CPU], tier_nodes); if (!nodes_empty(tier_nodes)) { /* * abstract distance below the max value of this memtier * is considered toptier. */ top_tier_adistance = memtier->adistance_start + MEMTIER_CHUNK_SIZE - 1; break; } } /* * Now build the lower_tier mask for each node collecting node mask from * all memory tier below it. This allows us to fallback demotion page * allocation to a set of nodes that is closer the above selected * preferred node. */ lower_tier = node_states[N_MEMORY]; list_for_each_entry(memtier, &memory_tiers, list) { /* * Keep removing current tier from lower_tier nodes, * This will remove all nodes in current and above * memory tier from the lower_tier mask. */ tier_nodes = get_memtier_nodemask(memtier); nodes_andnot(lower_tier, lower_tier, tier_nodes); memtier->lower_tier_mask = lower_tier; } dump_demotion_targets(); } #else static inline void establish_demotion_targets(void) {} #endif /* CONFIG_MIGRATION */ static inline void __init_node_memory_type(int node, struct memory_dev_type *memtype) { if (!node_memory_types[node].memtype) node_memory_types[node].memtype = memtype; /* * for each device getting added in the same NUMA node * with this specific memtype, bump the map count. We * Only take memtype device reference once, so that * changing a node memtype can be done by droping the * only reference count taken here. */ if (node_memory_types[node].memtype == memtype) { if (!node_memory_types[node].map_count++) kref_get(&memtype->kref); } } static struct memory_tier *set_node_memory_tier(int node) { struct memory_tier *memtier; struct memory_dev_type *memtype = default_dram_type; int adist = MEMTIER_ADISTANCE_DRAM; pg_data_t *pgdat = NODE_DATA(node); lockdep_assert_held_once(&memory_tier_lock); if (!node_state(node, N_MEMORY)) return ERR_PTR(-EINVAL); mt_calc_adistance(node, &adist); if (!node_memory_types[node].memtype) { memtype = mt_find_alloc_memory_type(adist, &default_memory_types); if (IS_ERR(memtype)) { memtype = default_dram_type; pr_info("Failed to allocate a memory type. Fall back.\n"); } } __init_node_memory_type(node, memtype); memtype = node_memory_types[node].memtype; node_set(node, memtype->nodes); memtier = find_create_memory_tier(memtype); if (!IS_ERR(memtier)) rcu_assign_pointer(pgdat->memtier, memtier); return memtier; } static void destroy_memory_tier(struct memory_tier *memtier) { list_del(&memtier->list); device_unregister(&memtier->dev); } static bool clear_node_memory_tier(int node) { bool cleared = false; pg_data_t *pgdat; struct memory_tier *memtier; pgdat = NODE_DATA(node); if (!pgdat) return false; /* * Make sure that anybody looking at NODE_DATA who finds * a valid memtier finds memory_dev_types with nodes still * linked to the memtier. We achieve this by waiting for * rcu read section to finish using synchronize_rcu. * This also enables us to free the destroyed memory tier * with kfree instead of kfree_rcu */ memtier = __node_get_memory_tier(node); if (memtier) { struct memory_dev_type *memtype; rcu_assign_pointer(pgdat->memtier, NULL); synchronize_rcu(); memtype = node_memory_types[node].memtype; node_clear(node, memtype->nodes); if (nodes_empty(memtype->nodes)) { list_del_init(&memtype->tier_sibling); if (list_empty(&memtier->memory_types)) destroy_memory_tier(memtier); } cleared = true; } return cleared; } static void release_memtype(struct kref *kref) { struct memory_dev_type *memtype; memtype = container_of(kref, struct memory_dev_type, kref); kfree(memtype); } struct memory_dev_type *alloc_memory_type(int adistance) { struct memory_dev_type *memtype; memtype = kmalloc(sizeof(*memtype), GFP_KERNEL); if (!memtype) return ERR_PTR(-ENOMEM); memtype->adistance = adistance; INIT_LIST_HEAD(&memtype->tier_sibling); memtype->nodes = NODE_MASK_NONE; kref_init(&memtype->kref); return memtype; } EXPORT_SYMBOL_GPL(alloc_memory_type); void put_memory_type(struct memory_dev_type *memtype) { kref_put(&memtype->kref, release_memtype); } EXPORT_SYMBOL_GPL(put_memory_type); void init_node_memory_type(int node, struct memory_dev_type *memtype) { mutex_lock(&memory_tier_lock); __init_node_memory_type(node, memtype); mutex_unlock(&memory_tier_lock); } EXPORT_SYMBOL_GPL(init_node_memory_type); void clear_node_memory_type(int node, struct memory_dev_type *memtype) { mutex_lock(&memory_tier_lock); if (node_memory_types[node].memtype == memtype || !memtype) node_memory_types[node].map_count--; /* * If we umapped all the attached devices to this node, * clear the node memory type. */ if (!node_memory_types[node].map_count) { memtype = node_memory_types[node].memtype; node_memory_types[node].memtype = NULL; put_memory_type(memtype); } mutex_unlock(&memory_tier_lock); } EXPORT_SYMBOL_GPL(clear_node_memory_type); struct memory_dev_type *mt_find_alloc_memory_type(int adist, struct list_head *memory_types) { struct memory_dev_type *mtype; list_for_each_entry(mtype, memory_types, list) if (mtype->adistance == adist) return mtype; mtype = alloc_memory_type(adist); if (IS_ERR(mtype)) return mtype; list_add(&mtype->list, memory_types); return mtype; } EXPORT_SYMBOL_GPL(mt_find_alloc_memory_type); void mt_put_memory_types(struct list_head *memory_types) { struct memory_dev_type *mtype, *mtn; list_for_each_entry_safe(mtype, mtn, memory_types, list) { list_del(&mtype->list); put_memory_type(mtype); } } EXPORT_SYMBOL_GPL(mt_put_memory_types); /* * This is invoked via `late_initcall()` to initialize memory tiers for * memory nodes, both with and without CPUs. After the initialization of * firmware and devices, adistance algorithms are expected to be provided. */ static int __init memory_tier_late_init(void) { int nid; struct memory_tier *memtier; get_online_mems(); guard(mutex)(&memory_tier_lock); /* Assign each uninitialized N_MEMORY node to a memory tier. */ for_each_node_state(nid, N_MEMORY) { /* * Some device drivers may have initialized * memory tiers, potentially bringing memory nodes * online and configuring memory tiers. * Exclude them here. */ if (node_memory_types[nid].memtype) continue; memtier = set_node_memory_tier(nid); if (IS_ERR(memtier)) continue; } establish_demotion_targets(); put_online_mems(); return 0; } late_initcall(memory_tier_late_init); static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix) { pr_info( "%sread_latency: %u, write_latency: %u, read_bandwidth: %u, write_bandwidth: %u\n", prefix, coord->read_latency, coord->write_latency, coord->read_bandwidth, coord->write_bandwidth); } int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, const char *source) { guard(mutex)(&default_dram_perf_lock); if (default_dram_perf_error) return -EIO; if (perf->read_latency + perf->write_latency == 0 || perf->read_bandwidth + perf->write_bandwidth == 0) return -EINVAL; if (default_dram_perf_ref_nid == NUMA_NO_NODE) { default_dram_perf = *perf; default_dram_perf_ref_nid = nid; default_dram_perf_ref_source = kstrdup(source, GFP_KERNEL); return 0; } /* * The performance of all default DRAM nodes is expected to be * same (that is, the variation is less than 10%). And it * will be used as base to calculate the abstract distance of * other memory nodes. */ if (abs(perf->read_latency - default_dram_perf.read_latency) * 10 > default_dram_perf.read_latency || abs(perf->write_latency - default_dram_perf.write_latency) * 10 > default_dram_perf.write_latency || abs(perf->read_bandwidth - default_dram_perf.read_bandwidth) * 10 > default_dram_perf.read_bandwidth || abs(perf->write_bandwidth - default_dram_perf.write_bandwidth) * 10 > default_dram_perf.write_bandwidth) { pr_info( "memory-tiers: the performance of DRAM node %d mismatches that of the reference\n" "DRAM node %d.\n", nid, default_dram_perf_ref_nid); pr_info(" performance of reference DRAM node %d:\n", default_dram_perf_ref_nid); dump_hmem_attrs(&default_dram_perf, " "); pr_info(" performance of DRAM node %d:\n", nid); dump_hmem_attrs(perf, " "); pr_info( " disable default DRAM node performance based abstract distance algorithm.\n"); default_dram_perf_error = true; return -EINVAL; } return 0; } int mt_perf_to_adistance(struct access_coordinate *perf, int *adist) { guard(mutex)(&default_dram_perf_lock); if (default_dram_perf_error) return -EIO; if (perf->read_latency + perf->write_latency == 0 || perf->read_bandwidth + perf->write_bandwidth == 0) return -EINVAL; if (default_dram_perf_ref_nid == NUMA_NO_NODE) return -ENOENT; /* * The abstract distance of a memory node is in direct proportion to * its memory latency (read + write) and inversely proportional to its * memory bandwidth (read + write). The abstract distance, memory * latency, and memory bandwidth of the default DRAM nodes are used as * the base. */ *adist = MEMTIER_ADISTANCE_DRAM * (perf->read_latency + perf->write_latency) / (default_dram_perf.read_latency + default_dram_perf.write_latency) * (default_dram_perf.read_bandwidth + default_dram_perf.write_bandwidth) / (perf->read_bandwidth + perf->write_bandwidth); return 0; } EXPORT_SYMBOL_GPL(mt_perf_to_adistance); /** * register_mt_adistance_algorithm() - Register memory tiering abstract distance algorithm * @nb: The notifier block which describe the algorithm * * Return: 0 on success, errno on error. * * Every memory tiering abstract distance algorithm provider needs to * register the algorithm with register_mt_adistance_algorithm(). To * calculate the abstract distance for a specified memory node, the * notifier function will be called unless some high priority * algorithm has provided result. The prototype of the notifier * function is as follows, * * int (*algorithm_notifier)(struct notifier_block *nb, * unsigned long nid, void *data); * * Where "nid" specifies the memory node, "data" is the pointer to the * returned abstract distance (that is, "int *adist"). If the * algorithm provides the result, NOTIFY_STOP should be returned. * Otherwise, return_value & %NOTIFY_STOP_MASK == 0 to allow the next * algorithm in the chain to provide the result. */ int register_mt_adistance_algorithm(struct notifier_block *nb) { return blocking_notifier_chain_register(&mt_adistance_algorithms, nb); } EXPORT_SYMBOL_GPL(register_mt_adistance_algorithm); /** * unregister_mt_adistance_algorithm() - Unregister memory tiering abstract distance algorithm * @nb: the notifier block which describe the algorithm * * Return: 0 on success, errno on error. */ int unregister_mt_adistance_algorithm(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&mt_adistance_algorithms, nb); } EXPORT_SYMBOL_GPL(unregister_mt_adistance_algorithm); /** * mt_calc_adistance() - Calculate abstract distance with registered algorithms * @node: the node to calculate abstract distance for * @adist: the returned abstract distance * * Return: if return_value & %NOTIFY_STOP_MASK != 0, then some * abstract distance algorithm provides the result, and return it via * @adist. Otherwise, no algorithm can provide the result and @adist * will be kept as it is. */ int mt_calc_adistance(int node, int *adist) { return blocking_notifier_call_chain(&mt_adistance_algorithms, node, adist); } EXPORT_SYMBOL_GPL(mt_calc_adistance); static int __meminit memtier_hotplug_callback(struct notifier_block *self, unsigned long action, void *_arg) { struct memory_tier *memtier; struct memory_notify *arg = _arg; /* * Only update the node migration order when a node is * changing status, like online->offline. */ if (arg->status_change_nid < 0) return notifier_from_errno(0); switch (action) { case MEM_OFFLINE: mutex_lock(&memory_tier_lock); if (clear_node_memory_tier(arg->status_change_nid)) establish_demotion_targets(); mutex_unlock(&memory_tier_lock); break; case MEM_ONLINE: mutex_lock(&memory_tier_lock); memtier = set_node_memory_tier(arg->status_change_nid); if (!IS_ERR(memtier)) establish_demotion_targets(); mutex_unlock(&memory_tier_lock); break; } return notifier_from_errno(0); } static int __init memory_tier_init(void) { int ret; ret = subsys_virtual_register(&memory_tier_subsys, NULL); if (ret) panic("%s() failed to register memory tier subsystem\n", __func__); #ifdef CONFIG_MIGRATION node_demotion = kcalloc(nr_node_ids, sizeof(struct demotion_nodes), GFP_KERNEL); WARN_ON(!node_demotion); #endif guard(mutex)(&memory_tier_lock); /* * For now we can have 4 faster memory tiers with smaller adistance * than default DRAM tier. */ default_dram_type = mt_find_alloc_memory_type(MEMTIER_ADISTANCE_DRAM, &default_memory_types); if (IS_ERR(default_dram_type)) panic("%s() failed to allocate default DRAM tier\n", __func__); /* Record nodes with memory and CPU to set default DRAM performance. */ nodes_and(default_dram_nodes, node_states[N_MEMORY], node_states[N_CPU]); hotplug_memory_notifier(memtier_hotplug_callback, MEMTIER_HOTPLUG_PRI); return 0; } subsys_initcall(memory_tier_init); bool numa_demotion_enabled = false; #ifdef CONFIG_MIGRATION #ifdef CONFIG_SYSFS static ssize_t demotion_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", numa_demotion_enabled ? "true" : "false"); } static ssize_t demotion_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { ssize_t ret; ret = kstrtobool(buf, &numa_demotion_enabled); if (ret) return ret; return count; } static struct kobj_attribute numa_demotion_enabled_attr = __ATTR_RW(demotion_enabled); static struct attribute *numa_attrs[] = { &numa_demotion_enabled_attr.attr, NULL, }; static const struct attribute_group numa_attr_group = { .attrs = numa_attrs, }; static int __init numa_init_sysfs(void) { int err; struct kobject *numa_kobj; numa_kobj = kobject_create_and_add("numa", mm_kobj); if (!numa_kobj) { pr_err("failed to create numa kobject\n"); return -ENOMEM; } err = sysfs_create_group(numa_kobj, &numa_attr_group); if (err) { pr_err("failed to register numa group\n"); goto delete_obj; } return 0; delete_obj: kobject_put(numa_kobj); return err; } subsys_initcall(numa_init_sysfs); #endif /* CONFIG_SYSFS */ #endif |
| 52 52 52 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 | /* SPDX-License-Identifier: GPL-2.0 * * IO cost model based controller. * * Copyright (C) 2019 Tejun Heo <tj@kernel.org> * Copyright (C) 2019 Andy Newell <newella@fb.com> * Copyright (C) 2019 Facebook * * One challenge of controlling IO resources is the lack of trivially * observable cost metric. This is distinguished from CPU and memory where * wallclock time and the number of bytes can serve as accurate enough * approximations. * * Bandwidth and iops are the most commonly used metrics for IO devices but * depending on the type and specifics of the device, different IO patterns * easily lead to multiple orders of magnitude variations rendering them * useless for the purpose of IO capacity distribution. While on-device * time, with a lot of clutches, could serve as a useful approximation for * non-queued rotational devices, this is no longer viable with modern * devices, even the rotational ones. * * While there is no cost metric we can trivially observe, it isn't a * complete mystery. For example, on a rotational device, seek cost * dominates while a contiguous transfer contributes a smaller amount * proportional to the size. If we can characterize at least the relative * costs of these different types of IOs, it should be possible to * implement a reasonable work-conserving proportional IO resource * distribution. * * 1. IO Cost Model * * IO cost model estimates the cost of an IO given its basic parameters and * history (e.g. the end sector of the last IO). The cost is measured in * device time. If a given IO is estimated to cost 10ms, the device should * be able to process ~100 of those IOs in a second. * * Currently, there's only one builtin cost model - linear. Each IO is * classified as sequential or random and given a base cost accordingly. * On top of that, a size cost proportional to the length of the IO is * added. While simple, this model captures the operational * characteristics of a wide varienty of devices well enough. Default * parameters for several different classes of devices are provided and the * parameters can be configured from userspace via * /sys/fs/cgroup/io.cost.model. * * If needed, tools/cgroup/iocost_coef_gen.py can be used to generate * device-specific coefficients. * * 2. Control Strategy * * The device virtual time (vtime) is used as the primary control metric. * The control strategy is composed of the following three parts. * * 2-1. Vtime Distribution * * When a cgroup becomes active in terms of IOs, its hierarchical share is * calculated. Please consider the following hierarchy where the numbers * inside parentheses denote the configured weights. * * root * / \ * A (w:100) B (w:300) * / \ * A0 (w:100) A1 (w:100) * * If B is idle and only A0 and A1 are actively issuing IOs, as the two are * of equal weight, each gets 50% share. If then B starts issuing IOs, B * gets 300/(100+300) or 75% share, and A0 and A1 equally splits the rest, * 12.5% each. The distribution mechanism only cares about these flattened * shares. They're called hweights (hierarchical weights) and always add * upto 1 (WEIGHT_ONE). * * A given cgroup's vtime runs slower in inverse proportion to its hweight. * For example, with 12.5% weight, A0's time runs 8 times slower (100/12.5) * against the device vtime - an IO which takes 10ms on the underlying * device is considered to take 80ms on A0. * * This constitutes the basis of IO capacity distribution. Each cgroup's * vtime is running at a rate determined by its hweight. A cgroup tracks * the vtime consumed by past IOs and can issue a new IO if doing so * wouldn't outrun the current device vtime. Otherwise, the IO is * suspended until the vtime has progressed enough to cover it. * * 2-2. Vrate Adjustment * * It's unrealistic to expect the cost model to be perfect. There are too * many devices and even on the same device the overall performance * fluctuates depending on numerous factors such as IO mixture and device * internal garbage collection. The controller needs to adapt dynamically. * * This is achieved by adjusting the overall IO rate according to how busy * the device is. If the device becomes overloaded, we're sending down too * many IOs and should generally slow down. If there are waiting issuers * but the device isn't saturated, we're issuing too few and should * generally speed up. * * To slow down, we lower the vrate - the rate at which the device vtime * passes compared to the wall clock. For example, if the vtime is running * at the vrate of 75%, all cgroups added up would only be able to issue * 750ms worth of IOs per second, and vice-versa for speeding up. * * Device business is determined using two criteria - rq wait and * completion latencies. * * When a device gets saturated, the on-device and then the request queues * fill up and a bio which is ready to be issued has to wait for a request * to become available. When this delay becomes noticeable, it's a clear * indication that the device is saturated and we lower the vrate. This * saturation signal is fairly conservative as it only triggers when both * hardware and software queues are filled up, and is used as the default * busy signal. * * As devices can have deep queues and be unfair in how the queued commands * are executed, solely depending on rq wait may not result in satisfactory * control quality. For a better control quality, completion latency QoS * parameters can be configured so that the device is considered saturated * if N'th percentile completion latency rises above the set point. * * The completion latency requirements are a function of both the * underlying device characteristics and the desired IO latency quality of * service. There is an inherent trade-off - the tighter the latency QoS, * the higher the bandwidth lossage. Latency QoS is disabled by default * and can be set through /sys/fs/cgroup/io.cost.qos. * * 2-3. Work Conservation * * Imagine two cgroups A and B with equal weights. A is issuing a small IO * periodically while B is sending out enough parallel IOs to saturate the * device on its own. Let's say A's usage amounts to 100ms worth of IO * cost per second, i.e., 10% of the device capacity. The naive * distribution of half and half would lead to 60% utilization of the * device, a significant reduction in the total amount of work done * compared to free-for-all competition. This is too high a cost to pay * for IO control. * * To conserve the total amount of work done, we keep track of how much * each active cgroup is actually using and yield part of its weight if * there are other cgroups which can make use of it. In the above case, * A's weight will be lowered so that it hovers above the actual usage and * B would be able to use the rest. * * As we don't want to penalize a cgroup for donating its weight, the * surplus weight adjustment factors in a margin and has an immediate * snapback mechanism in case the cgroup needs more IO vtime for itself. * * Note that adjusting down surplus weights has the same effects as * accelerating vtime for other cgroups and work conservation can also be * implemented by adjusting vrate dynamically. However, squaring who can * donate and should take back how much requires hweight propagations * anyway making it easier to implement and understand as a separate * mechanism. * * 3. Monitoring * * Instead of debugfs or other clumsy monitoring mechanisms, this * controller uses a drgn based monitoring script - * tools/cgroup/iocost_monitor.py. For details on drgn, please see * https://github.com/osandov/drgn. The output looks like the following. * * sdb RUN per=300ms cur_per=234.218:v203.695 busy= +1 vrate= 62.12% * active weight hweight% inflt% dbt delay usages% * test/a * 50/ 50 33.33/ 33.33 27.65 2 0*041 033:033:033 * test/b * 100/ 100 66.67/ 66.67 17.56 0 0*000 066:079:077 * * - per : Timer period * - cur_per : Internal wall and device vtime clock * - vrate : Device virtual time rate against wall clock * - weight : Surplus-adjusted and configured weights * - hweight : Surplus-adjusted and configured hierarchical weights * - inflt : The percentage of in-flight IO cost at the end of last period * - del_ms : Deferred issuer delay induction level and duration * - usages : Usage history */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/time64.h> #include <linux/parser.h> #include <linux/sched/signal.h> #include <asm/local.h> #include <asm/local64.h> #include "blk-rq-qos.h" #include "blk-stat.h" #include "blk-wbt.h" #include "blk-cgroup.h" #ifdef CONFIG_TRACEPOINTS /* copied from TRACE_CGROUP_PATH, see cgroup-internal.h */ #define TRACE_IOCG_PATH_LEN 1024 static DEFINE_SPINLOCK(trace_iocg_path_lock); static char trace_iocg_path[TRACE_IOCG_PATH_LEN]; #define TRACE_IOCG_PATH(type, iocg, ...) \ do { \ unsigned long flags; \ if (trace_iocost_##type##_enabled()) { \ spin_lock_irqsave(&trace_iocg_path_lock, flags); \ cgroup_path(iocg_to_blkg(iocg)->blkcg->css.cgroup, \ trace_iocg_path, TRACE_IOCG_PATH_LEN); \ trace_iocost_##type(iocg, trace_iocg_path, \ ##__VA_ARGS__); \ spin_unlock_irqrestore(&trace_iocg_path_lock, flags); \ } \ } while (0) #else /* CONFIG_TRACE_POINTS */ #define TRACE_IOCG_PATH(type, iocg, ...) do { } while (0) #endif /* CONFIG_TRACE_POINTS */ enum { MILLION = 1000000, /* timer period is calculated from latency requirements, bound it */ MIN_PERIOD = USEC_PER_MSEC, MAX_PERIOD = USEC_PER_SEC, /* * iocg->vtime is targeted at 50% behind the device vtime, which * serves as its IO credit buffer. Surplus weight adjustment is * immediately canceled if the vtime margin runs below 10%. */ MARGIN_MIN_PCT = 10, MARGIN_LOW_PCT = 20, MARGIN_TARGET_PCT = 50, INUSE_ADJ_STEP_PCT = 25, /* Have some play in timer operations */ TIMER_SLACK_PCT = 1, /* 1/64k is granular enough and can easily be handled w/ u32 */ WEIGHT_ONE = 1 << 16, }; enum { /* * As vtime is used to calculate the cost of each IO, it needs to * be fairly high precision. For example, it should be able to * represent the cost of a single page worth of discard with * suffificient accuracy. At the same time, it should be able to * represent reasonably long enough durations to be useful and * convenient during operation. * * 1s worth of vtime is 2^37. This gives us both sub-nanosecond * granularity and days of wrap-around time even at extreme vrates. */ VTIME_PER_SEC_SHIFT = 37, VTIME_PER_SEC = 1LLU << VTIME_PER_SEC_SHIFT, VTIME_PER_USEC = VTIME_PER_SEC / USEC_PER_SEC, VTIME_PER_NSEC = VTIME_PER_SEC / NSEC_PER_SEC, /* bound vrate adjustments within two orders of magnitude */ VRATE_MIN_PPM = 10000, /* 1% */ VRATE_MAX_PPM = 100000000, /* 10000% */ VRATE_MIN = VTIME_PER_USEC * VRATE_MIN_PPM / MILLION, VRATE_CLAMP_ADJ_PCT = 4, /* switch iff the conditions are met for longer than this */ AUTOP_CYCLE_NSEC = 10LLU * NSEC_PER_SEC, }; enum { /* if IOs end up waiting for requests, issue less */ RQ_WAIT_BUSY_PCT = 5, /* unbusy hysterisis */ UNBUSY_THR_PCT = 75, /* * The effect of delay is indirect and non-linear and a huge amount of * future debt can accumulate abruptly while unthrottled. Linearly scale * up delay as debt is going up and then let it decay exponentially. * This gives us quick ramp ups while delay is accumulating and long * tails which can help reducing the frequency of debt explosions on * unthrottle. The parameters are experimentally determined. * * The delay mechanism provides adequate protection and behavior in many * cases. However, this is far from ideal and falls shorts on both * fronts. The debtors are often throttled too harshly costing a * significant level of fairness and possibly total work while the * protection against their impacts on the system can be choppy and * unreliable. * * The shortcoming primarily stems from the fact that, unlike for page * cache, the kernel doesn't have well-defined back-pressure propagation * mechanism and policies for anonymous memory. Fully addressing this * issue will likely require substantial improvements in the area. */ MIN_DELAY_THR_PCT = 500, MAX_DELAY_THR_PCT = 25000, MIN_DELAY = 250, MAX_DELAY = 250 * USEC_PER_MSEC, /* halve debts if avg usage over 100ms is under 50% */ DFGV_USAGE_PCT = 50, DFGV_PERIOD = 100 * USEC_PER_MSEC, /* don't let cmds which take a very long time pin lagging for too long */ MAX_LAGGING_PERIODS = 10, /* * Count IO size in 4k pages. The 12bit shift helps keeping * size-proportional components of cost calculation in closer * numbers of digits to per-IO cost components. */ IOC_PAGE_SHIFT = 12, IOC_PAGE_SIZE = 1 << IOC_PAGE_SHIFT, IOC_SECT_TO_PAGE_SHIFT = IOC_PAGE_SHIFT - SECTOR_SHIFT, /* if apart further than 16M, consider randio for linear model */ LCOEF_RANDIO_PAGES = 4096, }; enum ioc_running { IOC_IDLE, IOC_RUNNING, IOC_STOP, }; /* io.cost.qos controls including per-dev enable of the whole controller */ enum { QOS_ENABLE, QOS_CTRL, NR_QOS_CTRL_PARAMS, }; /* io.cost.qos params */ enum { QOS_RPPM, QOS_RLAT, QOS_WPPM, QOS_WLAT, QOS_MIN, QOS_MAX, NR_QOS_PARAMS, }; /* io.cost.model controls */ enum { COST_CTRL, COST_MODEL, NR_COST_CTRL_PARAMS, }; /* builtin linear cost model coefficients */ enum { I_LCOEF_RBPS, I_LCOEF_RSEQIOPS, I_LCOEF_RRANDIOPS, I_LCOEF_WBPS, I_LCOEF_WSEQIOPS, I_LCOEF_WRANDIOPS, NR_I_LCOEFS, }; enum { LCOEF_RPAGE, LCOEF_RSEQIO, LCOEF_RRANDIO, LCOEF_WPAGE, LCOEF_WSEQIO, LCOEF_WRANDIO, NR_LCOEFS, }; enum { AUTOP_INVALID, AUTOP_HDD, AUTOP_SSD_QD1, AUTOP_SSD_DFL, AUTOP_SSD_FAST, }; struct ioc_params { u32 qos[NR_QOS_PARAMS]; u64 i_lcoefs[NR_I_LCOEFS]; u64 lcoefs[NR_LCOEFS]; u32 too_fast_vrate_pct; u32 too_slow_vrate_pct; }; struct ioc_margins { s64 min; s64 low; s64 target; }; struct ioc_missed { local_t nr_met; local_t nr_missed; u32 last_met; u32 last_missed; }; struct ioc_pcpu_stat { struct ioc_missed missed[2]; local64_t rq_wait_ns; u64 last_rq_wait_ns; }; /* per device */ struct ioc { struct rq_qos rqos; bool enabled; struct ioc_params params; struct ioc_margins margins; u32 period_us; u32 timer_slack_ns; u64 vrate_min; u64 vrate_max; spinlock_t lock; struct timer_list timer; struct list_head active_iocgs; /* active cgroups */ struct ioc_pcpu_stat __percpu *pcpu_stat; enum ioc_running running; atomic64_t vtime_rate; u64 vtime_base_rate; s64 vtime_err; seqcount_spinlock_t period_seqcount; u64 period_at; /* wallclock starttime */ u64 period_at_vtime; /* vtime starttime */ atomic64_t cur_period; /* inc'd each period */ int busy_level; /* saturation history */ bool weights_updated; atomic_t hweight_gen; /* for lazy hweights */ /* debt forgivness */ u64 dfgv_period_at; u64 dfgv_period_rem; u64 dfgv_usage_us_sum; u64 autop_too_fast_at; u64 autop_too_slow_at; int autop_idx; bool user_qos_params:1; bool user_cost_model:1; }; struct iocg_pcpu_stat { local64_t abs_vusage; }; struct iocg_stat { u64 usage_us; u64 wait_us; u64 indebt_us; u64 indelay_us; }; /* per device-cgroup pair */ struct ioc_gq { struct blkg_policy_data pd; struct ioc *ioc; /* * A iocg can get its weight from two sources - an explicit * per-device-cgroup configuration or the default weight of the * cgroup. `cfg_weight` is the explicit per-device-cgroup * configuration. `weight` is the effective considering both * sources. * * When an idle cgroup becomes active its `active` goes from 0 to * `weight`. `inuse` is the surplus adjusted active weight. * `active` and `inuse` are used to calculate `hweight_active` and * `hweight_inuse`. * * `last_inuse` remembers `inuse` while an iocg is idle to persist * surplus adjustments. * * `inuse` may be adjusted dynamically during period. `saved_*` are used * to determine and track adjustments. */ u32 cfg_weight; u32 weight; u32 active; u32 inuse; u32 last_inuse; s64 saved_margin; sector_t cursor; /* to detect randio */ /* * `vtime` is this iocg's vtime cursor which progresses as IOs are * issued. If lagging behind device vtime, the delta represents * the currently available IO budget. If running ahead, the * overage. * * `vtime_done` is the same but progressed on completion rather * than issue. The delta behind `vtime` represents the cost of * currently in-flight IOs. */ atomic64_t vtime; atomic64_t done_vtime; u64 abs_vdebt; /* current delay in effect and when it started */ u64 delay; u64 delay_at; /* * The period this iocg was last active in. Used for deactivation * and invalidating `vtime`. */ atomic64_t active_period; struct list_head active_list; /* see __propagate_weights() and current_hweight() for details */ u64 child_active_sum; u64 child_inuse_sum; u64 child_adjusted_sum; int hweight_gen; u32 hweight_active; u32 hweight_inuse; u32 hweight_donating; u32 hweight_after_donation; struct list_head walk_list; struct list_head surplus_list; struct wait_queue_head waitq; struct hrtimer waitq_timer; /* timestamp at the latest activation */ u64 activated_at; /* statistics */ struct iocg_pcpu_stat __percpu *pcpu_stat; struct iocg_stat stat; struct iocg_stat last_stat; u64 last_stat_abs_vusage; u64 usage_delta_us; u64 wait_since; u64 indebt_since; u64 indelay_since; /* this iocg's depth in the hierarchy and ancestors including self */ int level; struct ioc_gq *ancestors[]; }; /* per cgroup */ struct ioc_cgrp { struct blkcg_policy_data cpd; unsigned int dfl_weight; }; struct ioc_now { u64 now_ns; u64 now; u64 vnow; }; struct iocg_wait { struct wait_queue_entry wait; struct bio *bio; u64 abs_cost; bool committed; }; struct iocg_wake_ctx { struct ioc_gq *iocg; u32 hw_inuse; s64 vbudget; }; static const struct ioc_params autop[] = { [AUTOP_HDD] = { .qos = { [QOS_RLAT] = 250000, /* 250ms */ [QOS_WLAT] = 250000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 174019176, [I_LCOEF_RSEQIOPS] = 41708, [I_LCOEF_RRANDIOPS] = 370, [I_LCOEF_WBPS] = 178075866, [I_LCOEF_WSEQIOPS] = 42705, [I_LCOEF_WRANDIOPS] = 378, }, }, [AUTOP_SSD_QD1] = { .qos = { [QOS_RLAT] = 25000, /* 25ms */ [QOS_WLAT] = 25000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 245855193, [I_LCOEF_RSEQIOPS] = 61575, [I_LCOEF_RRANDIOPS] = 6946, [I_LCOEF_WBPS] = 141365009, [I_LCOEF_WSEQIOPS] = 33716, [I_LCOEF_WRANDIOPS] = 26796, }, }, [AUTOP_SSD_DFL] = { .qos = { [QOS_RLAT] = 25000, /* 25ms */ [QOS_WLAT] = 25000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 488636629, [I_LCOEF_RSEQIOPS] = 8932, [I_LCOEF_RRANDIOPS] = 8518, [I_LCOEF_WBPS] = 427891549, [I_LCOEF_WSEQIOPS] = 28755, [I_LCOEF_WRANDIOPS] = 21940, }, .too_fast_vrate_pct = 500, }, [AUTOP_SSD_FAST] = { .qos = { [QOS_RLAT] = 5000, /* 5ms */ [QOS_WLAT] = 5000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 3102524156LLU, [I_LCOEF_RSEQIOPS] = 724816, [I_LCOEF_RRANDIOPS] = 778122, [I_LCOEF_WBPS] = 1742780862LLU, [I_LCOEF_WSEQIOPS] = 425702, [I_LCOEF_WRANDIOPS] = 443193, }, .too_slow_vrate_pct = 10, }, }; /* * vrate adjust percentages indexed by ioc->busy_level. We adjust up on * vtime credit shortage and down on device saturation. */ static const u32 vrate_adj_pct[] = { 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8, 8, 8, 16 }; static struct blkcg_policy blkcg_policy_iocost; /* accessors and helpers */ static struct ioc *rqos_to_ioc(struct rq_qos *rqos) { return container_of(rqos, struct ioc, rqos); } static struct ioc *q_to_ioc(struct request_queue *q) { return rqos_to_ioc(rq_qos_id(q, RQ_QOS_COST)); } static const char __maybe_unused *ioc_name(struct ioc *ioc) { struct gendisk *disk = ioc->rqos.disk; if (!disk) return "<unknown>"; return disk->disk_name; } static struct ioc_gq *pd_to_iocg(struct blkg_policy_data *pd) { return pd ? container_of(pd, struct ioc_gq, pd) : NULL; } static struct ioc_gq *blkg_to_iocg(struct blkcg_gq *blkg) { return pd_to_iocg(blkg_to_pd(blkg, &blkcg_policy_iocost)); } static struct blkcg_gq *iocg_to_blkg(struct ioc_gq *iocg) { return pd_to_blkg(&iocg->pd); } static struct ioc_cgrp *blkcg_to_iocc(struct blkcg *blkcg) { return container_of(blkcg_to_cpd(blkcg, &blkcg_policy_iocost), struct ioc_cgrp, cpd); } /* * Scale @abs_cost to the inverse of @hw_inuse. The lower the hierarchical * weight, the more expensive each IO. Must round up. */ static u64 abs_cost_to_cost(u64 abs_cost, u32 hw_inuse) { return DIV64_U64_ROUND_UP(abs_cost * WEIGHT_ONE, hw_inuse); } /* * The inverse of abs_cost_to_cost(). Must round up. */ static u64 cost_to_abs_cost(u64 cost, u32 hw_inuse) { return DIV64_U64_ROUND_UP(cost * hw_inuse, WEIGHT_ONE); } static void iocg_commit_bio(struct ioc_gq *iocg, struct bio *bio, u64 abs_cost, u64 cost) { struct iocg_pcpu_stat *gcs; bio->bi_iocost_cost = cost; atomic64_add(cost, &iocg->vtime); gcs = get_cpu_ptr(iocg->pcpu_stat); local64_add(abs_cost, &gcs->abs_vusage); put_cpu_ptr(gcs); } static void iocg_lock(struct ioc_gq *iocg, bool lock_ioc, unsigned long *flags) { if (lock_ioc) { spin_lock_irqsave(&iocg->ioc->lock, *flags); spin_lock(&iocg->waitq.lock); } else { spin_lock_irqsave(&iocg->waitq.lock, *flags); } } static void iocg_unlock(struct ioc_gq *iocg, bool unlock_ioc, unsigned long *flags) { if (unlock_ioc) { spin_unlock(&iocg->waitq.lock); spin_unlock_irqrestore(&iocg->ioc->lock, *flags); } else { spin_unlock_irqrestore(&iocg->waitq.lock, *flags); } } #define CREATE_TRACE_POINTS #include <trace/events/iocost.h> static void ioc_refresh_margins(struct ioc *ioc) { struct ioc_margins *margins = &ioc->margins; u32 period_us = ioc->period_us; u64 vrate = ioc->vtime_base_rate; margins->min = (period_us * MARGIN_MIN_PCT / 100) * vrate; margins->low = (period_us * MARGIN_LOW_PCT / 100) * vrate; margins->target = (period_us * MARGIN_TARGET_PCT / 100) * vrate; } /* latency Qos params changed, update period_us and all the dependent params */ static void ioc_refresh_period_us(struct ioc *ioc) { u32 ppm, lat, multi, period_us; lockdep_assert_held(&ioc->lock); /* pick the higher latency target */ if (ioc->params.qos[QOS_RLAT] >= ioc->params.qos[QOS_WLAT]) { ppm = ioc->params.qos[QOS_RPPM]; lat = ioc->params.qos[QOS_RLAT]; } else { ppm = ioc->params.qos[QOS_WPPM]; lat = ioc->params.qos[QOS_WLAT]; } /* * We want the period to be long enough to contain a healthy number * of IOs while short enough for granular control. Define it as a * multiple of the latency target. Ideally, the multiplier should * be scaled according to the percentile so that it would nominally * contain a certain number of requests. Let's be simpler and * scale it linearly so that it's 2x >= pct(90) and 10x at pct(50). */ if (ppm) multi = max_t(u32, (MILLION - ppm) / 50000, 2); else multi = 2; period_us = multi * lat; period_us = clamp_t(u32, period_us, MIN_PERIOD, MAX_PERIOD); /* calculate dependent params */ ioc->period_us = period_us; ioc->timer_slack_ns = div64_u64( (u64)period_us * NSEC_PER_USEC * TIMER_SLACK_PCT, 100); ioc_refresh_margins(ioc); } /* * ioc->rqos.disk isn't initialized when this function is called from * the init path. */ static int ioc_autop_idx(struct ioc *ioc, struct gendisk *disk) { int idx = ioc->autop_idx; const struct ioc_params *p = &autop[idx]; u32 vrate_pct; u64 now_ns; /* rotational? */ if (!blk_queue_nonrot(disk->queue)) return AUTOP_HDD; /* handle SATA SSDs w/ broken NCQ */ if (blk_queue_depth(disk->queue) == 1) return AUTOP_SSD_QD1; /* use one of the normal ssd sets */ if (idx < AUTOP_SSD_DFL) return AUTOP_SSD_DFL; /* if user is overriding anything, maintain what was there */ if (ioc->user_qos_params || ioc->user_cost_model) return idx; /* step up/down based on the vrate */ vrate_pct = div64_u64(ioc->vtime_base_rate * 100, VTIME_PER_USEC); now_ns = blk_time_get_ns(); if (p->too_fast_vrate_pct && p->too_fast_vrate_pct <= vrate_pct) { if (!ioc->autop_too_fast_at) ioc->autop_too_fast_at = now_ns; if (now_ns - ioc->autop_too_fast_at >= AUTOP_CYCLE_NSEC) return idx + 1; } else { ioc->autop_too_fast_at = 0; } if (p->too_slow_vrate_pct && p->too_slow_vrate_pct >= vrate_pct) { if (!ioc->autop_too_slow_at) ioc->autop_too_slow_at = now_ns; if (now_ns - ioc->autop_too_slow_at >= AUTOP_CYCLE_NSEC) return idx - 1; } else { ioc->autop_too_slow_at = 0; } return idx; } /* * Take the followings as input * * @bps maximum sequential throughput * @seqiops maximum sequential 4k iops * @randiops maximum random 4k iops * * and calculate the linear model cost coefficients. * * *@page per-page cost 1s / (@bps / 4096) * *@seqio base cost of a seq IO max((1s / @seqiops) - *@page, 0) * @randiops base cost of a rand IO max((1s / @randiops) - *@page, 0) */ static void calc_lcoefs(u64 bps, u64 seqiops, u64 randiops, u64 *page, u64 *seqio, u64 *randio) { u64 v; *page = *seqio = *randio = 0; if (bps) { u64 bps_pages = DIV_ROUND_UP_ULL(bps, IOC_PAGE_SIZE); if (bps_pages) *page = DIV64_U64_ROUND_UP(VTIME_PER_SEC, bps_pages); else *page = 1; } if (seqiops) { v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, seqiops); if (v > *page) *seqio = v - *page; } if (randiops) { v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, randiops); if (v > *page) *randio = v - *page; } } static void ioc_refresh_lcoefs(struct ioc *ioc) { u64 *u = ioc->params.i_lcoefs; u64 *c = ioc->params.lcoefs; calc_lcoefs(u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS], &c[LCOEF_RPAGE], &c[LCOEF_RSEQIO], &c[LCOEF_RRANDIO]); calc_lcoefs(u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS], &c[LCOEF_WPAGE], &c[LCOEF_WSEQIO], &c[LCOEF_WRANDIO]); } /* * struct gendisk is required as an argument because ioc->rqos.disk * is not properly initialized when called from the init path. */ static bool ioc_refresh_params_disk(struct ioc *ioc, bool force, struct gendisk *disk) { const struct ioc_params *p; int idx; lockdep_assert_held(&ioc->lock); idx = ioc_autop_idx(ioc, disk); p = &autop[idx]; if (idx == ioc->autop_idx && !force) return false; if (idx != ioc->autop_idx) { atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC); ioc->vtime_base_rate = VTIME_PER_USEC; } ioc->autop_idx = idx; ioc->autop_too_fast_at = 0; ioc->autop_too_slow_at = 0; if (!ioc->user_qos_params) memcpy(ioc->params.qos, p->qos, sizeof(p->qos)); if (!ioc->user_cost_model) memcpy(ioc->params.i_lcoefs, p->i_lcoefs, sizeof(p->i_lcoefs)); ioc_refresh_period_us(ioc); ioc_refresh_lcoefs(ioc); ioc->vrate_min = DIV64_U64_ROUND_UP((u64)ioc->params.qos[QOS_MIN] * VTIME_PER_USEC, MILLION); ioc->vrate_max = DIV64_U64_ROUND_UP((u64)ioc->params.qos[QOS_MAX] * VTIME_PER_USEC, MILLION); return true; } static bool ioc_refresh_params(struct ioc *ioc, bool force) { return ioc_refresh_params_disk(ioc, force, ioc->rqos.disk); } /* * When an iocg accumulates too much vtime or gets deactivated, we throw away * some vtime, which lowers the overall device utilization. As the exact amount * which is being thrown away is known, we can compensate by accelerating the * vrate accordingly so that the extra vtime generated in the current period * matches what got lost. */ static void ioc_refresh_vrate(struct ioc *ioc, struct ioc_now *now) { s64 pleft = ioc->period_at + ioc->period_us - now->now; s64 vperiod = ioc->period_us * ioc->vtime_base_rate; s64 vcomp, vcomp_min, vcomp_max; lockdep_assert_held(&ioc->lock); /* we need some time left in this period */ if (pleft <= 0) goto done; /* * Calculate how much vrate should be adjusted to offset the error. * Limit the amount of adjustment and deduct the adjusted amount from * the error. */ vcomp = -div64_s64(ioc->vtime_err, pleft); vcomp_min = -(ioc->vtime_base_rate >> 1); vcomp_max = ioc->vtime_base_rate; vcomp = clamp(vcomp, vcomp_min, vcomp_max); ioc->vtime_err += vcomp * pleft; atomic64_set(&ioc->vtime_rate, ioc->vtime_base_rate + vcomp); done: /* bound how much error can accumulate */ ioc->vtime_err = clamp(ioc->vtime_err, -vperiod, vperiod); } static void ioc_adjust_base_vrate(struct ioc *ioc, u32 rq_wait_pct, int nr_lagging, int nr_shortages, int prev_busy_level, u32 *missed_ppm) { u64 vrate = ioc->vtime_base_rate; u64 vrate_min = ioc->vrate_min, vrate_max = ioc->vrate_max; if (!ioc->busy_level || (ioc->busy_level < 0 && nr_lagging)) { if (ioc->busy_level != prev_busy_level || nr_lagging) trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages); return; } /* * If vrate is out of bounds, apply clamp gradually as the * bounds can change abruptly. Otherwise, apply busy_level * based adjustment. */ if (vrate < vrate_min) { vrate = div64_u64(vrate * (100 + VRATE_CLAMP_ADJ_PCT), 100); vrate = min(vrate, vrate_min); } else if (vrate > vrate_max) { vrate = div64_u64(vrate * (100 - VRATE_CLAMP_ADJ_PCT), 100); vrate = max(vrate, vrate_max); } else { int idx = min_t(int, abs(ioc->busy_level), ARRAY_SIZE(vrate_adj_pct) - 1); u32 adj_pct = vrate_adj_pct[idx]; if (ioc->busy_level > 0) adj_pct = 100 - adj_pct; else adj_pct = 100 + adj_pct; vrate = clamp(DIV64_U64_ROUND_UP(vrate * adj_pct, 100), vrate_min, vrate_max); } trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages); ioc->vtime_base_rate = vrate; ioc_refresh_margins(ioc); } /* take a snapshot of the current [v]time and vrate */ static void ioc_now(struct ioc *ioc, struct ioc_now *now) { unsigned seq; u64 vrate; now->now_ns = blk_time_get_ns(); now->now = ktime_to_us(now->now_ns); vrate = atomic64_read(&ioc->vtime_rate); /* * The current vtime is * * vtime at period start + (wallclock time since the start) * vrate * * As a consistent snapshot of `period_at_vtime` and `period_at` is * needed, they're seqcount protected. */ do { seq = read_seqcount_begin(&ioc->period_seqcount); now->vnow = ioc->period_at_vtime + (now->now - ioc->period_at) * vrate; } while (read_seqcount_retry(&ioc->period_seqcount, seq)); } static void ioc_start_period(struct ioc *ioc, struct ioc_now *now) { WARN_ON_ONCE(ioc->running != IOC_RUNNING); write_seqcount_begin(&ioc->period_seqcount); ioc->period_at = now->now; ioc->period_at_vtime = now->vnow; write_seqcount_end(&ioc->period_seqcount); ioc->timer.expires = jiffies + usecs_to_jiffies(ioc->period_us); add_timer(&ioc->timer); } /* * Update @iocg's `active` and `inuse` to @active and @inuse, update level * weight sums and propagate upwards accordingly. If @save, the current margin * is saved to be used as reference for later inuse in-period adjustments. */ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, bool save, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; int lvl; lockdep_assert_held(&ioc->lock); /* * For an active leaf node, its inuse shouldn't be zero or exceed * @active. An active internal node's inuse is solely determined by the * inuse to active ratio of its children regardless of @inuse. */ if (list_empty(&iocg->active_list) && iocg->child_active_sum) { inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum, iocg->child_active_sum); } else { inuse = clamp_t(u32, inuse, 1, active); } iocg->last_inuse = iocg->inuse; if (save) iocg->saved_margin = now->vnow - atomic64_read(&iocg->vtime); if (active == iocg->active && inuse == iocg->inuse) return; for (lvl = iocg->level - 1; lvl >= 0; lvl--) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; u32 parent_active = 0, parent_inuse = 0; /* update the level sums */ parent->child_active_sum += (s32)(active - child->active); parent->child_inuse_sum += (s32)(inuse - child->inuse); /* apply the updates */ child->active = active; child->inuse = inuse; /* * The delta between inuse and active sums indicates that * much of weight is being given away. Parent's inuse * and active should reflect the ratio. */ if (parent->child_active_sum) { parent_active = parent->weight; parent_inuse = DIV64_U64_ROUND_UP( parent_active * parent->child_inuse_sum, parent->child_active_sum); } /* do we need to keep walking up? */ if (parent_active == parent->active && parent_inuse == parent->inuse) break; active = parent_active; inuse = parent_inuse; } ioc->weights_updated = true; } static void commit_weights(struct ioc *ioc) { lockdep_assert_held(&ioc->lock); if (ioc->weights_updated) { /* paired with rmb in current_hweight(), see there */ smp_wmb(); atomic_inc(&ioc->hweight_gen); ioc->weights_updated = false; } } static void propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, bool save, struct ioc_now *now) { __propagate_weights(iocg, active, inuse, save, now); commit_weights(iocg->ioc); } static void current_hweight(struct ioc_gq *iocg, u32 *hw_activep, u32 *hw_inusep) { struct ioc *ioc = iocg->ioc; int lvl; u32 hwa, hwi; int ioc_gen; /* hot path - if uptodate, use cached */ ioc_gen = atomic_read(&ioc->hweight_gen); if (ioc_gen == iocg->hweight_gen) goto out; /* * Paired with wmb in commit_weights(). If we saw the updated * hweight_gen, all the weight updates from __propagate_weights() are * visible too. * * We can race with weight updates during calculation and get it * wrong. However, hweight_gen would have changed and a future * reader will recalculate and we're guaranteed to discard the * wrong result soon. */ smp_rmb(); hwa = hwi = WEIGHT_ONE; for (lvl = 0; lvl <= iocg->level - 1; lvl++) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; u64 active_sum = READ_ONCE(parent->child_active_sum); u64 inuse_sum = READ_ONCE(parent->child_inuse_sum); u32 active = READ_ONCE(child->active); u32 inuse = READ_ONCE(child->inuse); /* we can race with deactivations and either may read as zero */ if (!active_sum || !inuse_sum) continue; active_sum = max_t(u64, active, active_sum); hwa = div64_u64((u64)hwa * active, active_sum); inuse_sum = max_t(u64, inuse, inuse_sum); hwi = div64_u64((u64)hwi * inuse, inuse_sum); } iocg->hweight_active = max_t(u32, hwa, 1); iocg->hweight_inuse = max_t(u32, hwi, 1); iocg->hweight_gen = ioc_gen; out: if (hw_activep) *hw_activep = iocg->hweight_active; if (hw_inusep) *hw_inusep = iocg->hweight_inuse; } /* * Calculate the hweight_inuse @iocg would get with max @inuse assuming all the * other weights stay unchanged. */ static u32 current_hweight_max(struct ioc_gq *iocg) { u32 hwm = WEIGHT_ONE; u32 inuse = iocg->active; u64 child_inuse_sum; int lvl; lockdep_assert_held(&iocg->ioc->lock); for (lvl = iocg->level - 1; lvl >= 0; lvl--) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; child_inuse_sum = parent->child_inuse_sum + inuse - child->inuse; hwm = div64_u64((u64)hwm * inuse, child_inuse_sum); inuse = DIV64_U64_ROUND_UP(parent->active * child_inuse_sum, parent->child_active_sum); } return max_t(u32, hwm, 1); } static void weight_updated(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); struct ioc_cgrp *iocc = blkcg_to_iocc(blkg->blkcg); u32 weight; lockdep_assert_held(&ioc->lock); weight = iocg->cfg_weight ?: iocc->dfl_weight; if (weight != iocg->weight && iocg->active) propagate_weights(iocg, weight, iocg->inuse, true, now); iocg->weight = weight; } static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 __maybe_unused last_period, cur_period; u64 vtime, vtarget; int i; /* * If seem to be already active, just update the stamp to tell the * timer that we're still active. We don't mind occassional races. */ if (!list_empty(&iocg->active_list)) { ioc_now(ioc, now); cur_period = atomic64_read(&ioc->cur_period); if (atomic64_read(&iocg->active_period) != cur_period) atomic64_set(&iocg->active_period, cur_period); return true; } /* racy check on internal node IOs, treat as root level IOs */ if (iocg->child_active_sum) return false; spin_lock_irq(&ioc->lock); ioc_now(ioc, now); /* update period */ cur_period = atomic64_read(&ioc->cur_period); last_period = atomic64_read(&iocg->active_period); atomic64_set(&iocg->active_period, cur_period); /* already activated or breaking leaf-only constraint? */ if (!list_empty(&iocg->active_list)) goto succeed_unlock; for (i = iocg->level - 1; i > 0; i--) if (!list_empty(&iocg->ancestors[i]->active_list)) goto fail_unlock; if (iocg->child_active_sum) goto fail_unlock; /* * Always start with the target budget. On deactivation, we throw away * anything above it. */ vtarget = now->vnow - ioc->margins.target; vtime = atomic64_read(&iocg->vtime); atomic64_add(vtarget - vtime, &iocg->vtime); atomic64_add(vtarget - vtime, &iocg->done_vtime); vtime = vtarget; /* * Activate, propagate weight and start period timer if not * running. Reset hweight_gen to avoid accidental match from * wrapping. */ iocg->hweight_gen = atomic_read(&ioc->hweight_gen) - 1; list_add(&iocg->active_list, &ioc->active_iocgs); propagate_weights(iocg, iocg->weight, iocg->last_inuse ?: iocg->weight, true, now); TRACE_IOCG_PATH(iocg_activate, iocg, now, last_period, cur_period, vtime); iocg->activated_at = now->now; if (ioc->running == IOC_IDLE) { ioc->running = IOC_RUNNING; ioc->dfgv_period_at = now->now; ioc->dfgv_period_rem = 0; ioc_start_period(ioc, now); } succeed_unlock: spin_unlock_irq(&ioc->lock); return true; fail_unlock: spin_unlock_irq(&ioc->lock); return false; } static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); u64 tdelta, delay, new_delay, shift; s64 vover, vover_pct; u32 hwa; lockdep_assert_held(&iocg->waitq.lock); /* * If the delay is set by another CPU, we may be in the past. No need to * change anything if so. This avoids decay calculation underflow. */ if (time_before64(now->now, iocg->delay_at)) return false; /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; shift = div64_u64(tdelta, USEC_PER_SEC); if (iocg->delay && shift < BITS_PER_LONG) delay = iocg->delay >> shift; else delay = 0; /* calculate the new delay from the debt amount */ current_hweight(iocg, &hwa, NULL); vover = atomic64_read(&iocg->vtime) + abs_cost_to_cost(iocg->abs_vdebt, hwa) - now->vnow; vover_pct = div64_s64(100 * vover, ioc->period_us * ioc->vtime_base_rate); if (vover_pct <= MIN_DELAY_THR_PCT) new_delay = 0; else if (vover_pct >= MAX_DELAY_THR_PCT) new_delay = MAX_DELAY; else new_delay = MIN_DELAY + div_u64((MAX_DELAY - MIN_DELAY) * (vover_pct - MIN_DELAY_THR_PCT), MAX_DELAY_THR_PCT - MIN_DELAY_THR_PCT); /* pick the higher one and apply */ if (new_delay > delay) { iocg->delay = new_delay; iocg->delay_at = now->now; delay = new_delay; } if (delay >= MIN_DELAY) { if (!iocg->indelay_since) iocg->indelay_since = now->now; blkcg_set_delay(blkg, delay * NSEC_PER_USEC); return true; } else { if (iocg->indelay_since) { iocg->stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = 0; } iocg->delay = 0; blkcg_clear_delay(blkg); return false; } } static void iocg_incur_debt(struct ioc_gq *iocg, u64 abs_cost, struct ioc_now *now) { struct iocg_pcpu_stat *gcs; lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); WARN_ON_ONCE(list_empty(&iocg->active_list)); /* * Once in debt, debt handling owns inuse. @iocg stays at the minimum * inuse donating all of it share to others until its debt is paid off. */ if (!iocg->abs_vdebt && abs_cost) { iocg->indebt_since = now->now; propagate_weights(iocg, iocg->active, 0, false, now); } iocg->abs_vdebt += abs_cost; gcs = get_cpu_ptr(iocg->pcpu_stat); local64_add(abs_cost, &gcs->abs_vusage); put_cpu_ptr(gcs); } static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay, struct ioc_now *now) { lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); /* * make sure that nobody messed with @iocg. Check iocg->pd.online * to avoid warn when removing blkcg or disk. */ WARN_ON_ONCE(list_empty(&iocg->active_list) && iocg->pd.online); WARN_ON_ONCE(iocg->inuse > 1); iocg->abs_vdebt -= min(abs_vpay, iocg->abs_vdebt); /* if debt is paid in full, restore inuse */ if (!iocg->abs_vdebt) { iocg->stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = 0; propagate_weights(iocg, iocg->active, iocg->last_inuse, false, now); } } static int iocg_wake_fn(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key) { struct iocg_wait *wait = container_of(wq_entry, struct iocg_wait, wait); struct iocg_wake_ctx *ctx = key; u64 cost = abs_cost_to_cost(wait->abs_cost, ctx->hw_inuse); ctx->vbudget -= cost; if (ctx->vbudget < 0) return -1; iocg_commit_bio(ctx->iocg, wait->bio, wait->abs_cost, cost); wait->committed = true; /* * autoremove_wake_function() removes the wait entry only when it * actually changed the task state. We want the wait always removed. * Remove explicitly and use default_wake_function(). Note that the * order of operations is important as finish_wait() tests whether * @wq_entry is removed without grabbing the lock. */ default_wake_function(wq_entry, mode, flags, key); list_del_init_careful(&wq_entry->entry); return 0; } /* * Calculate the accumulated budget, pay debt if @pay_debt and wake up waiters * accordingly. When @pay_debt is %true, the caller must be holding ioc->lock in * addition to iocg->waitq.lock. */ static void iocg_kick_waitq(struct ioc_gq *iocg, bool pay_debt, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct iocg_wake_ctx ctx = { .iocg = iocg }; u64 vshortage, expires, oexpires; s64 vbudget; u32 hwa; lockdep_assert_held(&iocg->waitq.lock); current_hweight(iocg, &hwa, NULL); vbudget = now->vnow - atomic64_read(&iocg->vtime); /* pay off debt */ if (pay_debt && iocg->abs_vdebt && vbudget > 0) { u64 abs_vbudget = cost_to_abs_cost(vbudget, hwa); u64 abs_vpay = min_t(u64, abs_vbudget, iocg->abs_vdebt); u64 vpay = abs_cost_to_cost(abs_vpay, hwa); lockdep_assert_held(&ioc->lock); atomic64_add(vpay, &iocg->vtime); atomic64_add(vpay, &iocg->done_vtime); iocg_pay_debt(iocg, abs_vpay, now); vbudget -= vpay; } if (iocg->abs_vdebt || iocg->delay) iocg_kick_delay(iocg, now); /* * Debt can still be outstanding if we haven't paid all yet or the * caller raced and called without @pay_debt. Shouldn't wake up waiters * under debt. Make sure @vbudget reflects the outstanding amount and is * not positive. */ if (iocg->abs_vdebt) { s64 vdebt = abs_cost_to_cost(iocg->abs_vdebt, hwa); vbudget = min_t(s64, 0, vbudget - vdebt); } /* * Wake up the ones which are due and see how much vtime we'll need for * the next one. As paying off debt restores hw_inuse, it must be read * after the above debt payment. */ ctx.vbudget = vbudget; current_hweight(iocg, NULL, &ctx.hw_inuse); __wake_up_locked_key(&iocg->waitq, TASK_NORMAL, &ctx); if (!waitqueue_active(&iocg->waitq)) { if (iocg->wait_since) { iocg->stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = 0; } return; } if (!iocg->wait_since) iocg->wait_since = now->now; if (WARN_ON_ONCE(ctx.vbudget >= 0)) return; /* determine next wakeup, add a timer margin to guarantee chunking */ vshortage = -ctx.vbudget; expires = now->now_ns + DIV64_U64_ROUND_UP(vshortage, ioc->vtime_base_rate) * NSEC_PER_USEC; expires += ioc->timer_slack_ns; /* if already active and close enough, don't bother */ oexpires = ktime_to_ns(hrtimer_get_softexpires(&iocg->waitq_timer)); if (hrtimer_is_queued(&iocg->waitq_timer) && abs(oexpires - expires) <= ioc->timer_slack_ns) return; hrtimer_start_range_ns(&iocg->waitq_timer, ns_to_ktime(expires), ioc->timer_slack_ns, HRTIMER_MODE_ABS); } static enum hrtimer_restart iocg_waitq_timer_fn(struct hrtimer *timer) { struct ioc_gq *iocg = container_of(timer, struct ioc_gq, waitq_timer); bool pay_debt = READ_ONCE(iocg->abs_vdebt); struct ioc_now now; unsigned long flags; ioc_now(iocg->ioc, &now); iocg_lock(iocg, pay_debt, &flags); iocg_kick_waitq(iocg, pay_debt, &now); iocg_unlock(iocg, pay_debt, &flags); return HRTIMER_NORESTART; } static void ioc_lat_stat(struct ioc *ioc, u32 *missed_ppm_ar, u32 *rq_wait_pct_p) { u32 nr_met[2] = { }; u32 nr_missed[2] = { }; u64 rq_wait_ns = 0; int cpu, rw; for_each_online_cpu(cpu) { struct ioc_pcpu_stat *stat = per_cpu_ptr(ioc->pcpu_stat, cpu); u64 this_rq_wait_ns; for (rw = READ; rw <= WRITE; rw++) { u32 this_met = local_read(&stat->missed[rw].nr_met); u32 this_missed = local_read(&stat->missed[rw].nr_missed); nr_met[rw] += this_met - stat->missed[rw].last_met; nr_missed[rw] += this_missed - stat->missed[rw].last_missed; stat->missed[rw].last_met = this_met; stat->missed[rw].last_missed = this_missed; } this_rq_wait_ns = local64_read(&stat->rq_wait_ns); rq_wait_ns += this_rq_wait_ns - stat->last_rq_wait_ns; stat->last_rq_wait_ns = this_rq_wait_ns; } for (rw = READ; rw <= WRITE; rw++) { if (nr_met[rw] + nr_missed[rw]) missed_ppm_ar[rw] = DIV64_U64_ROUND_UP((u64)nr_missed[rw] * MILLION, nr_met[rw] + nr_missed[rw]); else missed_ppm_ar[rw] = 0; } *rq_wait_pct_p = div64_u64(rq_wait_ns * 100, ioc->period_us * NSEC_PER_USEC); } /* was iocg idle this period? */ static bool iocg_is_idle(struct ioc_gq *iocg) { struct ioc *ioc = iocg->ioc; /* did something get issued this period? */ if (atomic64_read(&iocg->active_period) == atomic64_read(&ioc->cur_period)) return false; /* is something in flight? */ if (atomic64_read(&iocg->done_vtime) != atomic64_read(&iocg->vtime)) return false; return true; } /* * Call this function on the target leaf @iocg's to build pre-order traversal * list of all the ancestors in @inner_walk. The inner nodes are linked through * ->walk_list and the caller is responsible for dissolving the list after use. */ static void iocg_build_inner_walk(struct ioc_gq *iocg, struct list_head *inner_walk) { int lvl; WARN_ON_ONCE(!list_empty(&iocg->walk_list)); /* find the first ancestor which hasn't been visited yet */ for (lvl = iocg->level - 1; lvl >= 0; lvl--) { if (!list_empty(&iocg->ancestors[lvl]->walk_list)) break; } /* walk down and visit the inner nodes to get pre-order traversal */ while (++lvl <= iocg->level - 1) { struct ioc_gq *inner = iocg->ancestors[lvl]; /* record traversal order */ list_add_tail(&inner->walk_list, inner_walk); } } /* propagate the deltas to the parent */ static void iocg_flush_stat_upward(struct ioc_gq *iocg) { if (iocg->level > 0) { struct iocg_stat *parent_stat = &iocg->ancestors[iocg->level - 1]->stat; parent_stat->usage_us += iocg->stat.usage_us - iocg->last_stat.usage_us; parent_stat->wait_us += iocg->stat.wait_us - iocg->last_stat.wait_us; parent_stat->indebt_us += iocg->stat.indebt_us - iocg->last_stat.indebt_us; parent_stat->indelay_us += iocg->stat.indelay_us - iocg->last_stat.indelay_us; } iocg->last_stat = iocg->stat; } /* collect per-cpu counters and propagate the deltas to the parent */ static void iocg_flush_stat_leaf(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 abs_vusage = 0; u64 vusage_delta; int cpu; lockdep_assert_held(&iocg->ioc->lock); /* collect per-cpu counters */ for_each_possible_cpu(cpu) { abs_vusage += local64_read( per_cpu_ptr(&iocg->pcpu_stat->abs_vusage, cpu)); } vusage_delta = abs_vusage - iocg->last_stat_abs_vusage; iocg->last_stat_abs_vusage = abs_vusage; iocg->usage_delta_us = div64_u64(vusage_delta, ioc->vtime_base_rate); iocg->stat.usage_us += iocg->usage_delta_us; iocg_flush_stat_upward(iocg); } /* get stat counters ready for reading on all active iocgs */ static void iocg_flush_stat(struct list_head *target_iocgs, struct ioc_now *now) { LIST_HEAD(inner_walk); struct ioc_gq *iocg, *tiocg; /* flush leaves and build inner node walk list */ list_for_each_entry(iocg, target_iocgs, active_list) { iocg_flush_stat_leaf(iocg, now); iocg_build_inner_walk(iocg, &inner_walk); } /* keep flushing upwards by walking the inner list backwards */ list_for_each_entry_safe_reverse(iocg, tiocg, &inner_walk, walk_list) { iocg_flush_stat_upward(iocg); list_del_init(&iocg->walk_list); } } /* * Determine what @iocg's hweight_inuse should be after donating unused * capacity. @hwm is the upper bound and used to signal no donation. This * function also throws away @iocg's excess budget. */ static u32 hweight_after_donation(struct ioc_gq *iocg, u32 old_hwi, u32 hwm, u32 usage, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 vtime = atomic64_read(&iocg->vtime); s64 excess, delta, target, new_hwi; /* debt handling owns inuse for debtors */ if (iocg->abs_vdebt) return 1; /* see whether minimum margin requirement is met */ if (waitqueue_active(&iocg->waitq) || time_after64(vtime, now->vnow - ioc->margins.min)) return hwm; /* throw away excess above target */ excess = now->vnow - vtime - ioc->margins.target; if (excess > 0) { atomic64_add(excess, &iocg->vtime); atomic64_add(excess, &iocg->done_vtime); vtime += excess; ioc->vtime_err -= div64_u64(excess * old_hwi, WEIGHT_ONE); } /* * Let's say the distance between iocg's and device's vtimes as a * fraction of period duration is delta. Assuming that the iocg will * consume the usage determined above, we want to determine new_hwi so * that delta equals MARGIN_TARGET at the end of the next period. * * We need to execute usage worth of IOs while spending the sum of the * new budget (1 - MARGIN_TARGET) and the leftover from the last period * (delta): * * usage = (1 - MARGIN_TARGET + delta) * new_hwi * * Therefore, the new_hwi is: * * new_hwi = usage / (1 - MARGIN_TARGET + delta) */ delta = div64_s64(WEIGHT_ONE * (now->vnow - vtime), now->vnow - ioc->period_at_vtime); target = WEIGHT_ONE * MARGIN_TARGET_PCT / 100; new_hwi = div64_s64(WEIGHT_ONE * usage, WEIGHT_ONE - target + delta); return clamp_t(s64, new_hwi, 1, hwm); } /* * For work-conservation, an iocg which isn't using all of its share should * donate the leftover to other iocgs. There are two ways to achieve this - 1. * bumping up vrate accordingly 2. lowering the donating iocg's inuse weight. * * #1 is mathematically simpler but has the drawback of requiring synchronous * global hweight_inuse updates when idle iocg's get activated or inuse weights * change due to donation snapbacks as it has the possibility of grossly * overshooting what's allowed by the model and vrate. * * #2 is inherently safe with local operations. The donating iocg can easily * snap back to higher weights when needed without worrying about impacts on * other nodes as the impacts will be inherently correct. This also makes idle * iocg activations safe. The only effect activations have is decreasing * hweight_inuse of others, the right solution to which is for those iocgs to * snap back to higher weights. * * So, we go with #2. The challenge is calculating how each donating iocg's * inuse should be adjusted to achieve the target donation amounts. This is done * using Andy's method described in the following pdf. * * https://drive.google.com/file/d/1PsJwxPFtjUnwOY1QJ5AeICCcsL7BM3bo * * Given the weights and target after-donation hweight_inuse values, Andy's * method determines how the proportional distribution should look like at each * sibling level to maintain the relative relationship between all non-donating * pairs. To roughly summarize, it divides the tree into donating and * non-donating parts, calculates global donation rate which is used to * determine the target hweight_inuse for each node, and then derives per-level * proportions. * * The following pdf shows that global distribution calculated this way can be * achieved by scaling inuse weights of donating leaves and propagating the * adjustments upwards proportionally. * * https://drive.google.com/file/d/1vONz1-fzVO7oY5DXXsLjSxEtYYQbOvsE * * Combining the above two, we can determine how each leaf iocg's inuse should * be adjusted to achieve the target donation. * * https://drive.google.com/file/d/1WcrltBOSPN0qXVdBgnKm4mdp9FhuEFQN * * The inline comments use symbols from the last pdf. * * b is the sum of the absolute budgets in the subtree. 1 for the root node. * f is the sum of the absolute budgets of non-donating nodes in the subtree. * t is the sum of the absolute budgets of donating nodes in the subtree. * w is the weight of the node. w = w_f + w_t * w_f is the non-donating portion of w. w_f = w * f / b * w_b is the donating portion of w. w_t = w * t / b * s is the sum of all sibling weights. s = Sum(w) for siblings * s_f and s_t are the non-donating and donating portions of s. * * Subscript p denotes the parent's counterpart and ' the adjusted value - e.g. * w_pt is the donating portion of the parent's weight and w'_pt the same value * after adjustments. Subscript r denotes the root node's values. */ static void transfer_surpluses(struct list_head *surpluses, struct ioc_now *now) { LIST_HEAD(over_hwa); LIST_HEAD(inner_walk); struct ioc_gq *iocg, *tiocg, *root_iocg; u32 after_sum, over_sum, over_target, gamma; /* * It's pretty unlikely but possible for the total sum of * hweight_after_donation's to be higher than WEIGHT_ONE, which will * confuse the following calculations. If such condition is detected, * scale down everyone over its full share equally to keep the sum below * WEIGHT_ONE. */ after_sum = 0; over_sum = 0; list_for_each_entry(iocg, surpluses, surplus_list) { u32 hwa; current_hweight(iocg, &hwa, NULL); after_sum += iocg->hweight_after_donation; if (iocg->hweight_after_donation > hwa) { over_sum += iocg->hweight_after_donation; list_add(&iocg->walk_list, &over_hwa); } } if (after_sum >= WEIGHT_ONE) { /* * The delta should be deducted from the over_sum, calculate * target over_sum value. */ u32 over_delta = after_sum - (WEIGHT_ONE - 1); WARN_ON_ONCE(over_sum <= over_delta); over_target = over_sum - over_delta; } else { over_target = 0; } list_for_each_entry_safe(iocg, tiocg, &over_hwa, walk_list) { if (over_target) iocg->hweight_after_donation = div_u64((u64)iocg->hweight_after_donation * over_target, over_sum); list_del_init(&iocg->walk_list); } /* * Build pre-order inner node walk list and prepare for donation * adjustment calculations. */ list_for_each_entry(iocg, surpluses, surplus_list) { iocg_build_inner_walk(iocg, &inner_walk); } root_iocg = list_first_entry(&inner_walk, struct ioc_gq, walk_list); WARN_ON_ONCE(root_iocg->level > 0); list_for_each_entry(iocg, &inner_walk, walk_list) { iocg->child_adjusted_sum = 0; iocg->hweight_donating = 0; iocg->hweight_after_donation = 0; } /* * Propagate the donating budget (b_t) and after donation budget (b'_t) * up the hierarchy. */ list_for_each_entry(iocg, surpluses, surplus_list) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; parent->hweight_donating += iocg->hweight_donating; parent->hweight_after_donation += iocg->hweight_after_donation; } list_for_each_entry_reverse(iocg, &inner_walk, walk_list) { if (iocg->level > 0) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; parent->hweight_donating += iocg->hweight_donating; parent->hweight_after_donation += iocg->hweight_after_donation; } } /* * Calculate inner hwa's (b) and make sure the donation values are * within the accepted ranges as we're doing low res calculations with * roundups. */ list_for_each_entry(iocg, &inner_walk, walk_list) { if (iocg->level) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; iocg->hweight_active = DIV64_U64_ROUND_UP( (u64)parent->hweight_active * iocg->active, parent->child_active_sum); } iocg->hweight_donating = min(iocg->hweight_donating, iocg->hweight_active); iocg->hweight_after_donation = min(iocg->hweight_after_donation, iocg->hweight_donating - 1); if (WARN_ON_ONCE(iocg->hweight_active <= 1 || iocg->hweight_donating <= 1 || iocg->hweight_after_donation == 0)) { pr_warn("iocg: invalid donation weights in "); pr_cont_cgroup_path(iocg_to_blkg(iocg)->blkcg->css.cgroup); pr_cont(": active=%u donating=%u after=%u\n", iocg->hweight_active, iocg->hweight_donating, iocg->hweight_after_donation); } } /* * Calculate the global donation rate (gamma) - the rate to adjust * non-donating budgets by. * * No need to use 64bit multiplication here as the first operand is * guaranteed to be smaller than WEIGHT_ONE (1<<16). * * We know that there are beneficiary nodes and the sum of the donating * hweights can't be whole; however, due to the round-ups during hweight * calculations, root_iocg->hweight_donating might still end up equal to * or greater than whole. Limit the range when calculating the divider. * * gamma = (1 - t_r') / (1 - t_r) */ gamma = DIV_ROUND_UP( (WEIGHT_ONE - root_iocg->hweight_after_donation) * WEIGHT_ONE, WEIGHT_ONE - min_t(u32, root_iocg->hweight_donating, WEIGHT_ONE - 1)); /* * Calculate adjusted hwi, child_adjusted_sum and inuse for the inner * nodes. */ list_for_each_entry(iocg, &inner_walk, walk_list) { struct ioc_gq *parent; u32 inuse, wpt, wptp; u64 st, sf; if (iocg->level == 0) { /* adjusted weight sum for 1st level: s' = s * b_pf / b'_pf */ iocg->child_adjusted_sum = DIV64_U64_ROUND_UP( iocg->child_active_sum * (WEIGHT_ONE - iocg->hweight_donating), WEIGHT_ONE - iocg->hweight_after_donation); continue; } parent = iocg->ancestors[iocg->level - 1]; /* b' = gamma * b_f + b_t' */ iocg->hweight_inuse = DIV64_U64_ROUND_UP( (u64)gamma * (iocg->hweight_active - iocg->hweight_donating), WEIGHT_ONE) + iocg->hweight_after_donation; /* w' = s' * b' / b'_p */ inuse = DIV64_U64_ROUND_UP( (u64)parent->child_adjusted_sum * iocg->hweight_inuse, parent->hweight_inuse); /* adjusted weight sum for children: s' = s_f + s_t * w'_pt / w_pt */ st = DIV64_U64_ROUND_UP( iocg->child_active_sum * iocg->hweight_donating, iocg->hweight_active); sf = iocg->child_active_sum - st; wpt = DIV64_U64_ROUND_UP( (u64)iocg->active * iocg->hweight_donating, iocg->hweight_active); wptp = DIV64_U64_ROUND_UP( (u64)inuse * iocg->hweight_after_donation, iocg->hweight_inuse); iocg->child_adjusted_sum = sf + DIV64_U64_ROUND_UP(st * wptp, wpt); } /* * All inner nodes now have ->hweight_inuse and ->child_adjusted_sum and * we can finally determine leaf adjustments. */ list_for_each_entry(iocg, surpluses, surplus_list) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; u32 inuse; /* * In-debt iocgs participated in the donation calculation with * the minimum target hweight_inuse. Configuring inuse * accordingly would work fine but debt handling expects * @iocg->inuse stay at the minimum and we don't wanna * interfere. */ if (iocg->abs_vdebt) { WARN_ON_ONCE(iocg->inuse > 1); continue; } /* w' = s' * b' / b'_p, note that b' == b'_t for donating leaves */ inuse = DIV64_U64_ROUND_UP( parent->child_adjusted_sum * iocg->hweight_after_donation, parent->hweight_inuse); TRACE_IOCG_PATH(inuse_transfer, iocg, now, iocg->inuse, inuse, iocg->hweight_inuse, iocg->hweight_after_donation); __propagate_weights(iocg, iocg->active, inuse, true, now); } /* walk list should be dissolved after use */ list_for_each_entry_safe(iocg, tiocg, &inner_walk, walk_list) list_del_init(&iocg->walk_list); } /* * A low weight iocg can amass a large amount of debt, for example, when * anonymous memory gets reclaimed aggressively. If the system has a lot of * memory paired with a slow IO device, the debt can span multiple seconds or * more. If there are no other subsequent IO issuers, the in-debt iocg may end * up blocked paying its debt while the IO device is idle. * * The following protects against such cases. If the device has been * sufficiently idle for a while, the debts are halved and delays are * recalculated. */ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors, struct ioc_now *now) { struct ioc_gq *iocg; u64 dur, usage_pct, nr_cycles, nr_cycles_shift; /* if no debtor, reset the cycle */ if (!nr_debtors) { ioc->dfgv_period_at = now->now; ioc->dfgv_period_rem = 0; ioc->dfgv_usage_us_sum = 0; return; } /* * Debtors can pass through a lot of writes choking the device and we * don't want to be forgiving debts while the device is struggling from * write bursts. If we're missing latency targets, consider the device * fully utilized. */ if (ioc->busy_level > 0) usage_us_sum = max_t(u64, usage_us_sum, ioc->period_us); ioc->dfgv_usage_us_sum += usage_us_sum; if (time_before64(now->now, ioc->dfgv_period_at + DFGV_PERIOD)) return; /* * At least DFGV_PERIOD has passed since the last period. Calculate the * average usage and reset the period counters. */ dur = now->now - ioc->dfgv_period_at; usage_pct = div64_u64(100 * ioc->dfgv_usage_us_sum, dur); ioc->dfgv_period_at = now->now; ioc->dfgv_usage_us_sum = 0; /* if was too busy, reset everything */ if (usage_pct > DFGV_USAGE_PCT) { ioc->dfgv_period_rem = 0; return; } /* * Usage is lower than threshold. Let's forgive some debts. Debt * forgiveness runs off of the usual ioc timer but its period usually * doesn't match ioc's. Compensate the difference by performing the * reduction as many times as would fit in the duration since the last * run and carrying over the left-over duration in @ioc->dfgv_period_rem * - if ioc period is 75% of DFGV_PERIOD, one out of three consecutive * reductions is doubled. */ nr_cycles = dur + ioc->dfgv_period_rem; ioc->dfgv_period_rem = do_div(nr_cycles, DFGV_PERIOD); list_for_each_entry(iocg, &ioc->active_iocgs, active_list) { u64 __maybe_unused old_debt, __maybe_unused old_delay; if (!iocg->abs_vdebt && !iocg->delay) continue; spin_lock(&iocg->waitq.lock); old_debt = iocg->abs_vdebt; old_delay = iocg->delay; nr_cycles_shift = min_t(u64, nr_cycles, BITS_PER_LONG - 1); if (iocg->abs_vdebt) iocg->abs_vdebt = iocg->abs_vdebt >> nr_cycles_shift ?: 1; if (iocg->delay) iocg->delay = iocg->delay >> nr_cycles_shift ?: 1; iocg_kick_waitq(iocg, true, now); TRACE_IOCG_PATH(iocg_forgive_debt, iocg, now, usage_pct, old_debt, iocg->abs_vdebt, old_delay, iocg->delay); spin_unlock(&iocg->waitq.lock); } } /* * Check the active iocgs' state to avoid oversleeping and deactive * idle iocgs. * * Since waiters determine the sleep durations based on the vrate * they saw at the time of sleep, if vrate has increased, some * waiters could be sleeping for too long. Wake up tardy waiters * which should have woken up in the last period and expire idle * iocgs. */ static int ioc_check_iocgs(struct ioc *ioc, struct ioc_now *now) { int nr_debtors = 0; struct ioc_gq *iocg, *tiocg; list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) { if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && !iocg->delay && !iocg_is_idle(iocg)) continue; spin_lock(&iocg->waitq.lock); /* flush wait and indebt stat deltas */ if (iocg->wait_since) { iocg->stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = now->now; } if (iocg->indebt_since) { iocg->stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = now->now; } if (iocg->indelay_since) { iocg->stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = now->now; } if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt || iocg->delay) { /* might be oversleeping vtime / hweight changes, kick */ iocg_kick_waitq(iocg, true, now); if (iocg->abs_vdebt || iocg->delay) nr_debtors++; } else if (iocg_is_idle(iocg)) { /* no waiter and idle, deactivate */ u64 vtime = atomic64_read(&iocg->vtime); s64 excess; /* * @iocg has been inactive for a full duration and will * have a high budget. Account anything above target as * error and throw away. On reactivation, it'll start * with the target budget. */ excess = now->vnow - vtime - ioc->margins.target; if (excess > 0) { u32 old_hwi; current_hweight(iocg, NULL, &old_hwi); ioc->vtime_err -= div64_u64(excess * old_hwi, WEIGHT_ONE); } TRACE_IOCG_PATH(iocg_idle, iocg, now, atomic64_read(&iocg->active_period), atomic64_read(&ioc->cur_period), vtime); __propagate_weights(iocg, 0, 0, false, now); list_del_init(&iocg->active_list); } spin_unlock(&iocg->waitq.lock); } commit_weights(ioc); return nr_debtors; } static void ioc_timer_fn(struct timer_list *timer) { struct ioc *ioc = container_of(timer, struct ioc, timer); struct ioc_gq *iocg, *tiocg; struct ioc_now now; LIST_HEAD(surpluses); int nr_debtors, nr_shortages = 0, nr_lagging = 0; u64 usage_us_sum = 0; u32 ppm_rthr; u32 ppm_wthr; u32 missed_ppm[2], rq_wait_pct; u64 period_vtime; int prev_busy_level; /* how were the latencies during the period? */ ioc_lat_stat(ioc, missed_ppm, &rq_wait_pct); /* take care of active iocgs */ spin_lock_irq(&ioc->lock); ppm_rthr = MILLION - ioc->params.qos[QOS_RPPM]; ppm_wthr = MILLION - ioc->params.qos[QOS_WPPM]; ioc_now(ioc, &now); period_vtime = now.vnow - ioc->period_at_vtime; if (WARN_ON_ONCE(!period_vtime)) { spin_unlock_irq(&ioc->lock); return; } nr_debtors = ioc_check_iocgs(ioc, &now); /* * Wait and indebt stat are flushed above and the donation calculation * below needs updated usage stat. Let's bring stat up-to-date. */ iocg_flush_stat(&ioc->active_iocgs, &now); /* calc usage and see whether some weights need to be moved around */ list_for_each_entry(iocg, &ioc->active_iocgs, active_list) { u64 vdone, vtime, usage_us; u32 hw_active, hw_inuse; /* * Collect unused and wind vtime closer to vnow to prevent * iocgs from accumulating a large amount of budget. */ vdone = atomic64_read(&iocg->done_vtime); vtime = atomic64_read(&iocg->vtime); current_hweight(iocg, &hw_active, &hw_inuse); /* * Latency QoS detection doesn't account for IOs which are * in-flight for longer than a period. Detect them by * comparing vdone against period start. If lagging behind * IOs from past periods, don't increase vrate. */ if ((ppm_rthr != MILLION || ppm_wthr != MILLION) && !atomic_read(&iocg_to_blkg(iocg)->use_delay) && time_after64(vtime, vdone) && time_after64(vtime, now.vnow - MAX_LAGGING_PERIODS * period_vtime) && time_before64(vdone, now.vnow - period_vtime)) nr_lagging++; /* * Determine absolute usage factoring in in-flight IOs to avoid * high-latency completions appearing as idle. */ usage_us = iocg->usage_delta_us; usage_us_sum += usage_us; /* see whether there's surplus vtime */ WARN_ON_ONCE(!list_empty(&iocg->surplus_list)); if (hw_inuse < hw_active || (!waitqueue_active(&iocg->waitq) && time_before64(vtime, now.vnow - ioc->margins.low))) { u32 hwa, old_hwi, hwm, new_hwi, usage; u64 usage_dur; if (vdone != vtime) { u64 inflight_us = DIV64_U64_ROUND_UP( cost_to_abs_cost(vtime - vdone, hw_inuse), ioc->vtime_base_rate); usage_us = max(usage_us, inflight_us); } /* convert to hweight based usage ratio */ if (time_after64(iocg->activated_at, ioc->period_at)) usage_dur = max_t(u64, now.now - iocg->activated_at, 1); else usage_dur = max_t(u64, now.now - ioc->period_at, 1); usage = clamp_t(u32, DIV64_U64_ROUND_UP(usage_us * WEIGHT_ONE, usage_dur), 1, WEIGHT_ONE); /* * Already donating or accumulated enough to start. * Determine the donation amount. */ current_hweight(iocg, &hwa, &old_hwi); hwm = current_hweight_max(iocg); new_hwi = hweight_after_donation(iocg, old_hwi, hwm, usage, &now); /* * Donation calculation assumes hweight_after_donation * to be positive, a condition that a donor w/ hwa < 2 * can't meet. Don't bother with donation if hwa is * below 2. It's not gonna make a meaningful difference * anyway. */ if (new_hwi < hwm && hwa >= 2) { iocg->hweight_donating = hwa; iocg->hweight_after_donation = new_hwi; list_add(&iocg->surplus_list, &surpluses); } else if (!iocg->abs_vdebt) { /* * @iocg doesn't have enough to donate. Reset * its inuse to active. * * Don't reset debtors as their inuse's are * owned by debt handling. This shouldn't affect * donation calculuation in any meaningful way * as @iocg doesn't have a meaningful amount of * share anyway. */ TRACE_IOCG_PATH(inuse_shortage, iocg, &now, iocg->inuse, iocg->active, iocg->hweight_inuse, new_hwi); __propagate_weights(iocg, iocg->active, iocg->active, true, &now); nr_shortages++; } } else { /* genuinely short on vtime */ nr_shortages++; } } if (!list_empty(&surpluses) && nr_shortages) transfer_surpluses(&surpluses, &now); commit_weights(ioc); /* surplus list should be dissolved after use */ list_for_each_entry_safe(iocg, tiocg, &surpluses, surplus_list) list_del_init(&iocg->surplus_list); /* * If q is getting clogged or we're missing too much, we're issuing * too much IO and should lower vtime rate. If we're not missing * and experiencing shortages but not surpluses, we're too stingy * and should increase vtime rate. */ prev_busy_level = ioc->busy_level; if (rq_wait_pct > RQ_WAIT_BUSY_PCT || missed_ppm[READ] > ppm_rthr || missed_ppm[WRITE] > ppm_wthr) { /* clearly missing QoS targets, slow down vrate */ ioc->busy_level = max(ioc->busy_level, 0); ioc->busy_level++; } else if (rq_wait_pct <= RQ_WAIT_BUSY_PCT * UNBUSY_THR_PCT / 100 && missed_ppm[READ] <= ppm_rthr * UNBUSY_THR_PCT / 100 && missed_ppm[WRITE] <= ppm_wthr * UNBUSY_THR_PCT / 100) { /* QoS targets are being met with >25% margin */ if (nr_shortages) { /* * We're throttling while the device has spare * capacity. If vrate was being slowed down, stop. */ ioc->busy_level = min(ioc->busy_level, 0); /* * If there are IOs spanning multiple periods, wait * them out before pushing the device harder. */ if (!nr_lagging) ioc->busy_level--; } else { /* * Nobody is being throttled and the users aren't * issuing enough IOs to saturate the device. We * simply don't know how close the device is to * saturation. Coast. */ ioc->busy_level = 0; } } else { /* inside the hysterisis margin, we're good */ ioc->busy_level = 0; } ioc->busy_level = clamp(ioc->busy_level, -1000, 1000); ioc_adjust_base_vrate(ioc, rq_wait_pct, nr_lagging, nr_shortages, prev_busy_level, missed_ppm); ioc_refresh_params(ioc, false); ioc_forgive_debts(ioc, usage_us_sum, nr_debtors, &now); /* * This period is done. Move onto the next one. If nothing's * going on with the device, stop the timer. */ atomic64_inc(&ioc->cur_period); if (ioc->running != IOC_STOP) { if (!list_empty(&ioc->active_iocgs)) { ioc_start_period(ioc, &now); } else { ioc->busy_level = 0; ioc->vtime_err = 0; ioc->running = IOC_IDLE; } ioc_refresh_vrate(ioc, &now); } spin_unlock_irq(&ioc->lock); } static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, u64 abs_cost, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct ioc_margins *margins = &ioc->margins; u32 __maybe_unused old_inuse = iocg->inuse, __maybe_unused old_hwi; u32 hwi, adj_step; s64 margin; u64 cost, new_inuse; unsigned long flags; current_hweight(iocg, NULL, &hwi); old_hwi = hwi; cost = abs_cost_to_cost(abs_cost, hwi); margin = now->vnow - vtime - cost; /* debt handling owns inuse for debtors */ if (iocg->abs_vdebt) return cost; /* * We only increase inuse during period and do so if the margin has * deteriorated since the previous adjustment. */ if (margin >= iocg->saved_margin || margin >= margins->low || iocg->inuse == iocg->active) return cost; spin_lock_irqsave(&ioc->lock, flags); /* we own inuse only when @iocg is in the normal active state */ if (iocg->abs_vdebt || list_empty(&iocg->active_list)) { spin_unlock_irqrestore(&ioc->lock, flags); return cost; } /* * Bump up inuse till @abs_cost fits in the existing budget. * adj_step must be determined after acquiring ioc->lock - we might * have raced and lost to another thread for activation and could * be reading 0 iocg->active before ioc->lock which will lead to * infinite loop. */ new_inuse = iocg->inuse; adj_step = DIV_ROUND_UP(iocg->active * INUSE_ADJ_STEP_PCT, 100); do { new_inuse = new_inuse + adj_step; propagate_weights(iocg, iocg->active, new_inuse, true, now); current_hweight(iocg, NULL, &hwi); cost = abs_cost_to_cost(abs_cost, hwi); } while (time_after64(vtime + cost, now->vnow) && iocg->inuse != iocg->active); spin_unlock_irqrestore(&ioc->lock, flags); TRACE_IOCG_PATH(inuse_adjust, iocg, now, old_inuse, iocg->inuse, old_hwi, hwi); return cost; } static void calc_vtime_cost_builtin(struct bio *bio, struct ioc_gq *iocg, bool is_merge, u64 *costp) { struct ioc *ioc = iocg->ioc; u64 coef_seqio, coef_randio, coef_page; u64 pages = max_t(u64, bio_sectors(bio) >> IOC_SECT_TO_PAGE_SHIFT, 1); u64 seek_pages = 0; u64 cost = 0; /* Can't calculate cost for empty bio */ if (!bio->bi_iter.bi_size) goto out; switch (bio_op(bio)) { case REQ_OP_READ: coef_seqio = ioc->params.lcoefs[LCOEF_RSEQIO]; coef_randio = ioc->params.lcoefs[LCOEF_RRANDIO]; coef_page = ioc->params.lcoefs[LCOEF_RPAGE]; break; case REQ_OP_WRITE: coef_seqio = ioc->params.lcoefs[LCOEF_WSEQIO]; coef_randio = ioc->params.lcoefs[LCOEF_WRANDIO]; coef_page = ioc->params.lcoefs[LCOEF_WPAGE]; break; default: goto out; } if (iocg->cursor) { seek_pages = abs(bio->bi_iter.bi_sector - iocg->cursor); seek_pages >>= IOC_SECT_TO_PAGE_SHIFT; } if (!is_merge) { if (seek_pages > LCOEF_RANDIO_PAGES) { cost += coef_randio; } else { cost += coef_seqio; } } cost += pages * coef_page; out: *costp = cost; } static u64 calc_vtime_cost(struct bio *bio, struct ioc_gq *iocg, bool is_merge) { u64 cost; calc_vtime_cost_builtin(bio, iocg, is_merge, &cost); return cost; } static void calc_size_vtime_cost_builtin(struct request *rq, struct ioc *ioc, u64 *costp) { unsigned int pages = blk_rq_stats_sectors(rq) >> IOC_SECT_TO_PAGE_SHIFT; switch (req_op(rq)) { case REQ_OP_READ: *costp = pages * ioc->params.lcoefs[LCOEF_RPAGE]; break; case REQ_OP_WRITE: *costp = pages * ioc->params.lcoefs[LCOEF_WPAGE]; break; default: *costp = 0; } } static u64 calc_size_vtime_cost(struct request *rq, struct ioc *ioc) { u64 cost; calc_size_vtime_cost_builtin(rq, ioc, &cost); return cost; } static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; struct ioc *ioc = rqos_to_ioc(rqos); struct ioc_gq *iocg = blkg_to_iocg(blkg); struct ioc_now now; struct iocg_wait wait; u64 abs_cost, cost, vtime; bool use_debt, ioc_locked; unsigned long flags; /* bypass IOs if disabled, still initializing, or for root cgroup */ if (!ioc->enabled || !iocg || !iocg->level) return; /* calculate the absolute vtime cost */ abs_cost = calc_vtime_cost(bio, iocg, false); if (!abs_cost) return; if (!iocg_activate(iocg, &now)) return; iocg->cursor = bio_end_sector(bio); vtime = atomic64_read(&iocg->vtime); cost = adjust_inuse_and_calc_cost(iocg, vtime, abs_cost, &now); /* * If no one's waiting and within budget, issue right away. The * tests are racy but the races aren't systemic - we only miss once * in a while which is fine. */ if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && time_before_eq64(vtime + cost, now.vnow)) { iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * We're over budget. This can be handled in two ways. IOs which may * cause priority inversions are punted to @ioc->aux_iocg and charged as * debt. Otherwise, the issuer is blocked on @iocg->waitq. Debt handling * requires @ioc->lock, waitq handling @iocg->waitq.lock. Determine * whether debt handling is needed and acquire locks accordingly. */ use_debt = bio_issue_as_root_blkg(bio) || fatal_signal_pending(current); ioc_locked = use_debt || READ_ONCE(iocg->abs_vdebt); retry_lock: iocg_lock(iocg, ioc_locked, &flags); /* * @iocg must stay activated for debt and waitq handling. Deactivation * is synchronized against both ioc->lock and waitq.lock and we won't * get deactivated as long as we're waiting or has debt, so we're good * if we're activated here. In the unlikely cases that we aren't, just * issue the IO. */ if (unlikely(list_empty(&iocg->active_list))) { iocg_unlock(iocg, ioc_locked, &flags); iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * We're over budget. If @bio has to be issued regardless, remember * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay * off the debt before waking more IOs. * * This way, the debt is continuously paid off each period with the * actual budget available to the cgroup. If we just wound vtime, we * would incorrectly use the current hw_inuse for the entire amount * which, for example, can lead to the cgroup staying blocked for a * long time even with substantially raised hw_inuse. * * An iocg with vdebt should stay online so that the timer can keep * deducting its vdebt and [de]activate use_delay mechanism * accordingly. We don't want to race against the timer trying to * clear them and leave @iocg inactive w/ dangling use_delay heavily * penalizing the cgroup and its descendants. */ if (use_debt) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) blkcg_schedule_throttle(rqos->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); iocg_unlock(iocg, ioc_locked, &flags); return; } /* guarantee that iocgs w/ waiters have maximum inuse */ if (!iocg->abs_vdebt && iocg->inuse != iocg->active) { if (!ioc_locked) { iocg_unlock(iocg, false, &flags); ioc_locked = true; goto retry_lock; } propagate_weights(iocg, iocg->active, iocg->active, true, &now); } /* * Append self to the waitq and schedule the wakeup timer if we're * the first waiter. The timer duration is calculated based on the * current vrate. vtime and hweight changes can make it too short * or too long. Each wait entry records the absolute cost it's * waiting for to allow re-evaluation using a custom wait entry. * * If too short, the timer simply reschedules itself. If too long, * the period timer will notice and trigger wakeups. * * All waiters are on iocg->waitq and the wait states are * synchronized using waitq.lock. */ init_waitqueue_func_entry(&wait.wait, iocg_wake_fn); wait.wait.private = current; wait.bio = bio; wait.abs_cost = abs_cost; wait.committed = false; /* will be set true by waker */ __add_wait_queue_entry_tail(&iocg->waitq, &wait.wait); iocg_kick_waitq(iocg, ioc_locked, &now); iocg_unlock(iocg, ioc_locked, &flags); while (true) { set_current_state(TASK_UNINTERRUPTIBLE); if (wait.committed) break; io_schedule(); } /* waker already committed us, proceed */ finish_wait(&iocg->waitq, &wait.wait); } static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio) { struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg); struct ioc *ioc = rqos_to_ioc(rqos); sector_t bio_end = bio_end_sector(bio); struct ioc_now now; u64 vtime, abs_cost, cost; unsigned long flags; /* bypass if disabled, still initializing, or for root cgroup */ if (!ioc->enabled || !iocg || !iocg->level) return; abs_cost = calc_vtime_cost(bio, iocg, true); if (!abs_cost) return; ioc_now(ioc, &now); vtime = atomic64_read(&iocg->vtime); cost = adjust_inuse_and_calc_cost(iocg, vtime, abs_cost, &now); /* update cursor if backmerging into the request at the cursor */ if (blk_rq_pos(rq) < bio_end && blk_rq_pos(rq) + blk_rq_sectors(rq) == iocg->cursor) iocg->cursor = bio_end; /* * Charge if there's enough vtime budget and the existing request has * cost assigned. */ if (rq->bio && rq->bio->bi_iocost_cost && time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) { iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * Otherwise, account it as debt if @iocg is online, which it should * be for the vast majority of cases. See debt handling in * ioc_rqos_throttle() for details. */ spin_lock_irqsave(&ioc->lock, flags); spin_lock(&iocg->waitq.lock); if (likely(!list_empty(&iocg->active_list))) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) blkcg_schedule_throttle(rqos->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); } else { iocg_commit_bio(iocg, bio, abs_cost, cost); } spin_unlock(&iocg->waitq.lock); spin_unlock_irqrestore(&ioc->lock, flags); } static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio) { struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg); if (iocg && bio->bi_iocost_cost) atomic64_add(bio->bi_iocost_cost, &iocg->done_vtime); } static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq) { struct ioc *ioc = rqos_to_ioc(rqos); struct ioc_pcpu_stat *ccs; u64 on_q_ns, rq_wait_ns, size_nsec; int pidx, rw; if (!ioc->enabled || !rq->alloc_time_ns || !rq->start_time_ns) return; switch (req_op(rq)) { case REQ_OP_READ: pidx = QOS_RLAT; rw = READ; break; case REQ_OP_WRITE: pidx = QOS_WLAT; rw = WRITE; break; default: return; } on_q_ns = blk_time_get_ns() - rq->alloc_time_ns; rq_wait_ns = rq->start_time_ns - rq->alloc_time_ns; size_nsec = div64_u64(calc_size_vtime_cost(rq, ioc), VTIME_PER_NSEC); ccs = get_cpu_ptr(ioc->pcpu_stat); if (on_q_ns <= size_nsec || on_q_ns - size_nsec <= ioc->params.qos[pidx] * NSEC_PER_USEC) local_inc(&ccs->missed[rw].nr_met); else local_inc(&ccs->missed[rw].nr_missed); local64_add(rq_wait_ns, &ccs->rq_wait_ns); put_cpu_ptr(ccs); } static void ioc_rqos_queue_depth_changed(struct rq_qos *rqos) { struct ioc *ioc = rqos_to_ioc(rqos); spin_lock_irq(&ioc->lock); ioc_refresh_params(ioc, false); spin_unlock_irq(&ioc->lock); } static void ioc_rqos_exit(struct rq_qos *rqos) { struct ioc *ioc = rqos_to_ioc(rqos); blkcg_deactivate_policy(rqos->disk, &blkcg_policy_iocost); spin_lock_irq(&ioc->lock); ioc->running = IOC_STOP; spin_unlock_irq(&ioc->lock); timer_shutdown_sync(&ioc->timer); free_percpu(ioc->pcpu_stat); kfree(ioc); } static const struct rq_qos_ops ioc_rqos_ops = { .throttle = ioc_rqos_throttle, .merge = ioc_rqos_merge, .done_bio = ioc_rqos_done_bio, .done = ioc_rqos_done, .queue_depth_changed = ioc_rqos_queue_depth_changed, .exit = ioc_rqos_exit, }; static int blk_iocost_init(struct gendisk *disk) { struct ioc *ioc; int i, cpu, ret; ioc = kzalloc(sizeof(*ioc), GFP_KERNEL); if (!ioc) return -ENOMEM; ioc->pcpu_stat = alloc_percpu(struct ioc_pcpu_stat); if (!ioc->pcpu_stat) { kfree(ioc); return -ENOMEM; } for_each_possible_cpu(cpu) { struct ioc_pcpu_stat *ccs = per_cpu_ptr(ioc->pcpu_stat, cpu); for (i = 0; i < ARRAY_SIZE(ccs->missed); i++) { local_set(&ccs->missed[i].nr_met, 0); local_set(&ccs->missed[i].nr_missed, 0); } local64_set(&ccs->rq_wait_ns, 0); } spin_lock_init(&ioc->lock); timer_setup(&ioc->timer, ioc_timer_fn, 0); INIT_LIST_HEAD(&ioc->active_iocgs); ioc->running = IOC_IDLE; ioc->vtime_base_rate = VTIME_PER_USEC; atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC); seqcount_spinlock_init(&ioc->period_seqcount, &ioc->lock); ioc->period_at = ktime_to_us(blk_time_get()); atomic64_set(&ioc->cur_period, 0); atomic_set(&ioc->hweight_gen, 0); spin_lock_irq(&ioc->lock); ioc->autop_idx = AUTOP_INVALID; ioc_refresh_params_disk(ioc, true, disk); spin_unlock_irq(&ioc->lock); /* * rqos must be added before activation to allow ioc_pd_init() to * lookup the ioc from q. This means that the rqos methods may get * called before policy activation completion, can't assume that the * target bio has an iocg associated and need to test for NULL iocg. */ ret = rq_qos_add(&ioc->rqos, disk, RQ_QOS_COST, &ioc_rqos_ops); if (ret) goto err_free_ioc; ret = blkcg_activate_policy(disk, &blkcg_policy_iocost); if (ret) goto err_del_qos; return 0; err_del_qos: rq_qos_del(&ioc->rqos); err_free_ioc: free_percpu(ioc->pcpu_stat); kfree(ioc); return ret; } static struct blkcg_policy_data *ioc_cpd_alloc(gfp_t gfp) { struct ioc_cgrp *iocc; iocc = kzalloc(sizeof(struct ioc_cgrp), gfp); if (!iocc) return NULL; iocc->dfl_weight = CGROUP_WEIGHT_DFL * WEIGHT_ONE; return &iocc->cpd; } static void ioc_cpd_free(struct blkcg_policy_data *cpd) { kfree(container_of(cpd, struct ioc_cgrp, cpd)); } static struct blkg_policy_data *ioc_pd_alloc(struct gendisk *disk, struct blkcg *blkcg, gfp_t gfp) { int levels = blkcg->css.cgroup->level + 1; struct ioc_gq *iocg; iocg = kzalloc_node(struct_size(iocg, ancestors, levels), gfp, disk->node_id); if (!iocg) return NULL; iocg->pcpu_stat = alloc_percpu_gfp(struct iocg_pcpu_stat, gfp); if (!iocg->pcpu_stat) { kfree(iocg); return NULL; } return &iocg->pd; } static void ioc_pd_init(struct blkg_policy_data *pd) { struct ioc_gq *iocg = pd_to_iocg(pd); struct blkcg_gq *blkg = pd_to_blkg(&iocg->pd); struct ioc *ioc = q_to_ioc(blkg->q); struct ioc_now now; struct blkcg_gq *tblkg; unsigned long flags; ioc_now(ioc, &now); iocg->ioc = ioc; atomic64_set(&iocg->vtime, now.vnow); atomic64_set(&iocg->done_vtime, now.vnow); atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period)); INIT_LIST_HEAD(&iocg->active_list); INIT_LIST_HEAD(&iocg->walk_list); INIT_LIST_HEAD(&iocg->surplus_list); iocg->hweight_active = WEIGHT_ONE; iocg->hweight_inuse = WEIGHT_ONE; init_waitqueue_head(&iocg->waitq); hrtimer_init(&iocg->waitq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); iocg->waitq_timer.function = iocg_waitq_timer_fn; iocg->level = blkg->blkcg->css.cgroup->level; for (tblkg = blkg; tblkg; tblkg = tblkg->parent) { struct ioc_gq *tiocg = blkg_to_iocg(tblkg); iocg->ancestors[tiocg->level] = tiocg; } spin_lock_irqsave(&ioc->lock, flags); weight_updated(iocg, &now); spin_unlock_irqrestore(&ioc->lock, flags); } static void ioc_pd_free(struct blkg_policy_data *pd) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; unsigned long flags; if (ioc) { spin_lock_irqsave(&ioc->lock, flags); if (!list_empty(&iocg->active_list)) { struct ioc_now now; ioc_now(ioc, &now); propagate_weights(iocg, 0, 0, false, &now); list_del_init(&iocg->active_list); } WARN_ON_ONCE(!list_empty(&iocg->walk_list)); WARN_ON_ONCE(!list_empty(&iocg->surplus_list)); spin_unlock_irqrestore(&ioc->lock, flags); hrtimer_cancel(&iocg->waitq_timer); } free_percpu(iocg->pcpu_stat); kfree(iocg); } static void ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; if (!ioc->enabled) return; if (iocg->level == 0) { unsigned vp10k = DIV64_U64_ROUND_CLOSEST( ioc->vtime_base_rate * 10000, VTIME_PER_USEC); seq_printf(s, " cost.vrate=%u.%02u", vp10k / 100, vp10k % 100); } seq_printf(s, " cost.usage=%llu", iocg->last_stat.usage_us); if (blkcg_debug_stats) seq_printf(s, " cost.wait=%llu cost.indebt=%llu cost.indelay=%llu", iocg->last_stat.wait_us, iocg->last_stat.indebt_us, iocg->last_stat.indelay_us); } static u64 ioc_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc_gq *iocg = pd_to_iocg(pd); if (dname && iocg->cfg_weight) seq_printf(sf, "%s %u\n", dname, iocg->cfg_weight / WEIGHT_ONE); return 0; } static int ioc_weight_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct ioc_cgrp *iocc = blkcg_to_iocc(blkcg); seq_printf(sf, "default %u\n", iocc->dfl_weight / WEIGHT_ONE); blkcg_print_blkgs(sf, blkcg, ioc_weight_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct blkcg *blkcg = css_to_blkcg(of_css(of)); struct ioc_cgrp *iocc = blkcg_to_iocc(blkcg); struct blkg_conf_ctx ctx; struct ioc_now now; struct ioc_gq *iocg; u32 v; int ret; if (!strchr(buf, ':')) { struct blkcg_gq *blkg; if (!sscanf(buf, "default %u", &v) && !sscanf(buf, "%u", &v)) return -EINVAL; if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX) return -EINVAL; spin_lock_irq(&blkcg->lock); iocc->dfl_weight = v * WEIGHT_ONE; hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { struct ioc_gq *iocg = blkg_to_iocg(blkg); if (iocg) { spin_lock(&iocg->ioc->lock); ioc_now(iocg->ioc, &now); weight_updated(iocg, &now); spin_unlock(&iocg->ioc->lock); } } spin_unlock_irq(&blkcg->lock); return nbytes; } blkg_conf_init(&ctx, buf); ret = blkg_conf_prep(blkcg, &blkcg_policy_iocost, &ctx); if (ret) goto err; iocg = blkg_to_iocg(ctx.blkg); if (!strncmp(ctx.body, "default", 7)) { v = 0; } else { if (!sscanf(ctx.body, "%u", &v)) goto einval; if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX) goto einval; } spin_lock(&iocg->ioc->lock); iocg->cfg_weight = v * WEIGHT_ONE; ioc_now(iocg->ioc, &now); weight_updated(iocg, &now); spin_unlock(&iocg->ioc->lock); blkg_conf_exit(&ctx); return nbytes; einval: ret = -EINVAL; err: blkg_conf_exit(&ctx); return ret; } static u64 ioc_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc *ioc = pd_to_iocg(pd)->ioc; if (!dname) return 0; spin_lock_irq(&ioc->lock); seq_printf(sf, "%s enable=%d ctrl=%s rpct=%u.%02u rlat=%u wpct=%u.%02u wlat=%u min=%u.%02u max=%u.%02u\n", dname, ioc->enabled, ioc->user_qos_params ? "user" : "auto", ioc->params.qos[QOS_RPPM] / 10000, ioc->params.qos[QOS_RPPM] % 10000 / 100, ioc->params.qos[QOS_RLAT], ioc->params.qos[QOS_WPPM] / 10000, ioc->params.qos[QOS_WPPM] % 10000 / 100, ioc->params.qos[QOS_WLAT], ioc->params.qos[QOS_MIN] / 10000, ioc->params.qos[QOS_MIN] % 10000 / 100, ioc->params.qos[QOS_MAX] / 10000, ioc->params.qos[QOS_MAX] % 10000 / 100); spin_unlock_irq(&ioc->lock); return 0; } static int ioc_qos_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); blkcg_print_blkgs(sf, blkcg, ioc_qos_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static const match_table_t qos_ctrl_tokens = { { QOS_ENABLE, "enable=%u" }, { QOS_CTRL, "ctrl=%s" }, { NR_QOS_CTRL_PARAMS, NULL }, }; static const match_table_t qos_tokens = { { QOS_RPPM, "rpct=%s" }, { QOS_RLAT, "rlat=%u" }, { QOS_WPPM, "wpct=%s" }, { QOS_WLAT, "wlat=%u" }, { QOS_MIN, "min=%s" }, { QOS_MAX, "max=%s" }, { NR_QOS_PARAMS, NULL }, }; static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, size_t nbytes, loff_t off) { struct blkg_conf_ctx ctx; struct gendisk *disk; struct ioc *ioc; u32 qos[NR_QOS_PARAMS]; bool enable, user; char *body, *p; int ret; blkg_conf_init(&ctx, input); ret = blkg_conf_open_bdev(&ctx); if (ret) goto err; body = ctx.body; disk = ctx.bdev->bd_disk; if (!queue_is_mq(disk->queue)) { ret = -EOPNOTSUPP; goto err; } ioc = q_to_ioc(disk->queue); if (!ioc) { ret = blk_iocost_init(disk); if (ret) goto err; ioc = q_to_ioc(disk->queue); } blk_mq_freeze_queue(disk->queue); blk_mq_quiesce_queue(disk->queue); spin_lock_irq(&ioc->lock); memcpy(qos, ioc->params.qos, sizeof(qos)); enable = ioc->enabled; user = ioc->user_qos_params; while ((p = strsep(&body, " \t\n"))) { substring_t args[MAX_OPT_ARGS]; char buf[32]; int tok; s64 v; if (!*p) continue; switch (match_token(p, qos_ctrl_tokens, args)) { case QOS_ENABLE: if (match_u64(&args[0], &v)) goto einval; enable = v; continue; case QOS_CTRL: match_strlcpy(buf, &args[0], sizeof(buf)); if (!strcmp(buf, "auto")) user = false; else if (!strcmp(buf, "user")) user = true; else goto einval; continue; } tok = match_token(p, qos_tokens, args); switch (tok) { case QOS_RPPM: case QOS_WPPM: if (match_strlcpy(buf, &args[0], sizeof(buf)) >= sizeof(buf)) goto einval; if (cgroup_parse_float(buf, 2, &v)) goto einval; if (v < 0 || v > 10000) goto einval; qos[tok] = v * 100; break; case QOS_RLAT: case QOS_WLAT: if (match_u64(&args[0], &v)) goto einval; qos[tok] = v; break; case QOS_MIN: case QOS_MAX: if (match_strlcpy(buf, &args[0], sizeof(buf)) >= sizeof(buf)) goto einval; if (cgroup_parse_float(buf, 2, &v)) goto einval; if (v < 0) goto einval; qos[tok] = clamp_t(s64, v * 100, VRATE_MIN_PPM, VRATE_MAX_PPM); break; default: goto einval; } user = true; } if (qos[QOS_MIN] > qos[QOS_MAX]) goto einval; if (enable && !ioc->enabled) { blk_stat_enable_accounting(disk->queue); blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = true; } else if (!enable && ioc->enabled) { blk_stat_disable_accounting(disk->queue); blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = false; } if (user) { memcpy(ioc->params.qos, qos, sizeof(qos)); ioc->user_qos_params = true; } else { ioc->user_qos_params = false; } ioc_refresh_params(ioc, true); spin_unlock_irq(&ioc->lock); if (enable) wbt_disable_default(disk); else wbt_enable_default(disk); blk_mq_unquiesce_queue(disk->queue); blk_mq_unfreeze_queue(disk->queue); blkg_conf_exit(&ctx); return nbytes; einval: spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(disk->queue); blk_mq_unfreeze_queue(disk->queue); ret = -EINVAL; err: blkg_conf_exit(&ctx); return ret; } static u64 ioc_cost_model_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc *ioc = pd_to_iocg(pd)->ioc; u64 *u = ioc->params.i_lcoefs; if (!dname) return 0; spin_lock_irq(&ioc->lock); seq_printf(sf, "%s ctrl=%s model=linear " "rbps=%llu rseqiops=%llu rrandiops=%llu " "wbps=%llu wseqiops=%llu wrandiops=%llu\n", dname, ioc->user_cost_model ? "user" : "auto", u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS], u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS]); spin_unlock_irq(&ioc->lock); return 0; } static int ioc_cost_model_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); blkcg_print_blkgs(sf, blkcg, ioc_cost_model_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static const match_table_t cost_ctrl_tokens = { { COST_CTRL, "ctrl=%s" }, { COST_MODEL, "model=%s" }, { NR_COST_CTRL_PARAMS, NULL }, }; static const match_table_t i_lcoef_tokens = { { I_LCOEF_RBPS, "rbps=%u" }, { I_LCOEF_RSEQIOPS, "rseqiops=%u" }, { I_LCOEF_RRANDIOPS, "rrandiops=%u" }, { I_LCOEF_WBPS, "wbps=%u" }, { I_LCOEF_WSEQIOPS, "wseqiops=%u" }, { I_LCOEF_WRANDIOPS, "wrandiops=%u" }, { NR_I_LCOEFS, NULL }, }; static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, size_t nbytes, loff_t off) { struct blkg_conf_ctx ctx; struct request_queue *q; struct ioc *ioc; u64 u[NR_I_LCOEFS]; bool user; char *body, *p; int ret; blkg_conf_init(&ctx, input); ret = blkg_conf_open_bdev(&ctx); if (ret) goto err; body = ctx.body; q = bdev_get_queue(ctx.bdev); if (!queue_is_mq(q)) { ret = -EOPNOTSUPP; goto err; } ioc = q_to_ioc(q); if (!ioc) { ret = blk_iocost_init(ctx.bdev->bd_disk); if (ret) goto err; ioc = q_to_ioc(q); } blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); spin_lock_irq(&ioc->lock); memcpy(u, ioc->params.i_lcoefs, sizeof(u)); user = ioc->user_cost_model; while ((p = strsep(&body, " \t\n"))) { substring_t args[MAX_OPT_ARGS]; char buf[32]; int tok; u64 v; if (!*p) continue; switch (match_token(p, cost_ctrl_tokens, args)) { case COST_CTRL: match_strlcpy(buf, &args[0], sizeof(buf)); if (!strcmp(buf, "auto")) user = false; else if (!strcmp(buf, "user")) user = true; else goto einval; continue; case COST_MODEL: match_strlcpy(buf, &args[0], sizeof(buf)); if (strcmp(buf, "linear")) goto einval; continue; } tok = match_token(p, i_lcoef_tokens, args); if (tok == NR_I_LCOEFS) goto einval; if (match_u64(&args[0], &v)) goto einval; u[tok] = v; user = true; } if (user) { memcpy(ioc->params.i_lcoefs, u, sizeof(u)); ioc->user_cost_model = true; } else { ioc->user_cost_model = false; } ioc_refresh_params(ioc, true); spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(q); blk_mq_unfreeze_queue(q); blkg_conf_exit(&ctx); return nbytes; einval: spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(q); blk_mq_unfreeze_queue(q); ret = -EINVAL; err: blkg_conf_exit(&ctx); return ret; } static struct cftype ioc_files[] = { { .name = "weight", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = ioc_weight_show, .write = ioc_weight_write, }, { .name = "cost.qos", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = ioc_qos_show, .write = ioc_qos_write, }, { .name = "cost.model", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = ioc_cost_model_show, .write = ioc_cost_model_write, }, {} }; static struct blkcg_policy blkcg_policy_iocost = { .dfl_cftypes = ioc_files, .cpd_alloc_fn = ioc_cpd_alloc, .cpd_free_fn = ioc_cpd_free, .pd_alloc_fn = ioc_pd_alloc, .pd_init_fn = ioc_pd_init, .pd_free_fn = ioc_pd_free, .pd_stat_fn = ioc_pd_stat, }; static int __init ioc_init(void) { return blkcg_policy_register(&blkcg_policy_iocost); } static void __exit ioc_exit(void) { blkcg_policy_unregister(&blkcg_policy_iocost); } module_init(ioc_init); module_exit(ioc_exit); |
| 28 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/module.h> #include <net/ip.h> #include <linux/ipv6.h> #include <linux/icmp.h> #include <net/ipv6.h> #include <net/tcp.h> #include <net/udp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_tcpudp.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> MODULE_DESCRIPTION("Xtables: TCP, UDP and UDP-Lite match"); MODULE_LICENSE("GPL"); MODULE_ALIAS("xt_tcp"); MODULE_ALIAS("xt_udp"); MODULE_ALIAS("ipt_udp"); MODULE_ALIAS("ipt_tcp"); MODULE_ALIAS("ip6t_udp"); MODULE_ALIAS("ip6t_tcp"); MODULE_ALIAS("ipt_icmp"); MODULE_ALIAS("ip6t_icmp6"); /* Returns 1 if the port is matched by the range, 0 otherwise */ static inline bool port_match(u_int16_t min, u_int16_t max, u_int16_t port, bool invert) { return (port >= min && port <= max) ^ invert; } static bool tcp_find_option(u_int8_t option, const struct sk_buff *skb, unsigned int protoff, unsigned int optlen, bool invert, bool *hotdrop) { /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ const u_int8_t *op; u_int8_t _opt[60 - sizeof(struct tcphdr)]; unsigned int i; pr_debug("finding option\n"); if (!optlen) return invert; /* If we don't have the whole header, drop packet. */ op = skb_header_pointer(skb, protoff + sizeof(struct tcphdr), optlen, _opt); if (op == NULL) { *hotdrop = true; return false; } for (i = 0; i < optlen; ) { if (op[i] == option) return !invert; if (op[i] < 2) i++; else i += op[i+1]?:1; } return invert; } static bool tcp_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct tcphdr *th; struct tcphdr _tcph; const struct xt_tcp *tcpinfo = par->matchinfo; if (par->fragoff != 0) { /* To quote Alan: Don't allow a fragment of TCP 8 bytes in. Nobody normal causes this. Its a cracker trying to break in by doing a flag overwrite to pass the direction checks. */ if (par->fragoff == 1) { pr_debug("Dropping evil TCP offset=1 frag.\n"); par->hotdrop = true; } /* Must not be a fragment. */ return false; } th = skb_header_pointer(skb, par->thoff, sizeof(_tcph), &_tcph); if (th == NULL) { /* We've been asked to examine this packet, and we can't. Hence, no choice but to drop. */ pr_debug("Dropping evil TCP offset=0 tinygram.\n"); par->hotdrop = true; return false; } if (!port_match(tcpinfo->spts[0], tcpinfo->spts[1], ntohs(th->source), !!(tcpinfo->invflags & XT_TCP_INV_SRCPT))) return false; if (!port_match(tcpinfo->dpts[0], tcpinfo->dpts[1], ntohs(th->dest), !!(tcpinfo->invflags & XT_TCP_INV_DSTPT))) return false; if (!NF_INVF(tcpinfo, XT_TCP_INV_FLAGS, (((unsigned char *)th)[13] & tcpinfo->flg_mask) == tcpinfo->flg_cmp)) return false; if (tcpinfo->option) { if (th->doff * 4 < sizeof(_tcph)) { par->hotdrop = true; return false; } if (!tcp_find_option(tcpinfo->option, skb, par->thoff, th->doff*4 - sizeof(_tcph), tcpinfo->invflags & XT_TCP_INV_OPTION, &par->hotdrop)) return false; } return true; } static int tcp_mt_check(const struct xt_mtchk_param *par) { const struct xt_tcp *tcpinfo = par->matchinfo; /* Must specify no unknown invflags */ return (tcpinfo->invflags & ~XT_TCP_INV_MASK) ? -EINVAL : 0; } static bool udp_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct udphdr *uh; struct udphdr _udph; const struct xt_udp *udpinfo = par->matchinfo; /* Must not be a fragment. */ if (par->fragoff != 0) return false; uh = skb_header_pointer(skb, par->thoff, sizeof(_udph), &_udph); if (uh == NULL) { /* We've been asked to examine this packet, and we can't. Hence, no choice but to drop. */ pr_debug("Dropping evil UDP tinygram.\n"); par->hotdrop = true; return false; } return port_match(udpinfo->spts[0], udpinfo->spts[1], ntohs(uh->source), !!(udpinfo->invflags & XT_UDP_INV_SRCPT)) && port_match(udpinfo->dpts[0], udpinfo->dpts[1], ntohs(uh->dest), !!(udpinfo->invflags & XT_UDP_INV_DSTPT)); } static int udp_mt_check(const struct xt_mtchk_param *par) { const struct xt_udp *udpinfo = par->matchinfo; /* Must specify no unknown invflags */ return (udpinfo->invflags & ~XT_UDP_INV_MASK) ? -EINVAL : 0; } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ static bool type_code_in_range(u8 test_type, u8 min_code, u8 max_code, u8 type, u8 code) { return type == test_type && code >= min_code && code <= max_code; } static bool icmp_type_code_match(u8 test_type, u8 min_code, u8 max_code, u8 type, u8 code, bool invert) { return (test_type == 0xFF || type_code_in_range(test_type, min_code, max_code, type, code)) ^ invert; } static bool icmp6_type_code_match(u8 test_type, u8 min_code, u8 max_code, u8 type, u8 code, bool invert) { return type_code_in_range(test_type, min_code, max_code, type, code) ^ invert; } static bool icmp_match(const struct sk_buff *skb, struct xt_action_param *par) { const struct icmphdr *ic; struct icmphdr _icmph; const struct ipt_icmp *icmpinfo = par->matchinfo; /* Must not be a fragment. */ if (par->fragoff != 0) return false; ic = skb_header_pointer(skb, par->thoff, sizeof(_icmph), &_icmph); if (!ic) { /* We've been asked to examine this packet, and we * can't. Hence, no choice but to drop. */ par->hotdrop = true; return false; } return icmp_type_code_match(icmpinfo->type, icmpinfo->code[0], icmpinfo->code[1], ic->type, ic->code, !!(icmpinfo->invflags & IPT_ICMP_INV)); } static bool icmp6_match(const struct sk_buff *skb, struct xt_action_param *par) { const struct icmp6hdr *ic; struct icmp6hdr _icmph; const struct ip6t_icmp *icmpinfo = par->matchinfo; /* Must not be a fragment. */ if (par->fragoff != 0) return false; ic = skb_header_pointer(skb, par->thoff, sizeof(_icmph), &_icmph); if (!ic) { /* We've been asked to examine this packet, and we * can't. Hence, no choice but to drop. */ par->hotdrop = true; return false; } return icmp6_type_code_match(icmpinfo->type, icmpinfo->code[0], icmpinfo->code[1], ic->icmp6_type, ic->icmp6_code, !!(icmpinfo->invflags & IP6T_ICMP_INV)); } static int icmp_checkentry(const struct xt_mtchk_param *par) { const struct ipt_icmp *icmpinfo = par->matchinfo; return (icmpinfo->invflags & ~IPT_ICMP_INV) ? -EINVAL : 0; } static int icmp6_checkentry(const struct xt_mtchk_param *par) { const struct ip6t_icmp *icmpinfo = par->matchinfo; return (icmpinfo->invflags & ~IP6T_ICMP_INV) ? -EINVAL : 0; } static struct xt_match tcpudp_mt_reg[] __read_mostly = { { .name = "tcp", .family = NFPROTO_IPV4, .checkentry = tcp_mt_check, .match = tcp_mt, .matchsize = sizeof(struct xt_tcp), .proto = IPPROTO_TCP, .me = THIS_MODULE, }, { .name = "tcp", .family = NFPROTO_IPV6, .checkentry = tcp_mt_check, .match = tcp_mt, .matchsize = sizeof(struct xt_tcp), .proto = IPPROTO_TCP, .me = THIS_MODULE, }, { .name = "udp", .family = NFPROTO_IPV4, .checkentry = udp_mt_check, .match = udp_mt, .matchsize = sizeof(struct xt_udp), .proto = IPPROTO_UDP, .me = THIS_MODULE, }, { .name = "udp", .family = NFPROTO_IPV6, .checkentry = udp_mt_check, .match = udp_mt, .matchsize = sizeof(struct xt_udp), .proto = IPPROTO_UDP, .me = THIS_MODULE, }, { .name = "udplite", .family = NFPROTO_IPV4, .checkentry = udp_mt_check, .match = udp_mt, .matchsize = sizeof(struct xt_udp), .proto = IPPROTO_UDPLITE, .me = THIS_MODULE, }, { .name = "udplite", .family = NFPROTO_IPV6, .checkentry = udp_mt_check, .match = udp_mt, .matchsize = sizeof(struct xt_udp), .proto = IPPROTO_UDPLITE, .me = THIS_MODULE, }, { .name = "icmp", .match = icmp_match, .matchsize = sizeof(struct ipt_icmp), .checkentry = icmp_checkentry, .proto = IPPROTO_ICMP, .family = NFPROTO_IPV4, .me = THIS_MODULE, }, { .name = "icmp6", .match = icmp6_match, .matchsize = sizeof(struct ip6t_icmp), .checkentry = icmp6_checkentry, .proto = IPPROTO_ICMPV6, .family = NFPROTO_IPV6, .me = THIS_MODULE, }, }; static int __init tcpudp_mt_init(void) { return xt_register_matches(tcpudp_mt_reg, ARRAY_SIZE(tcpudp_mt_reg)); } static void __exit tcpudp_mt_exit(void) { xt_unregister_matches(tcpudp_mt_reg, ARRAY_SIZE(tcpudp_mt_reg)); } module_init(tcpudp_mt_init); module_exit(tcpudp_mt_exit); |
| 39 34 39 9 190 190 190 189 149 149 149 149 117 9 139 107 107 107 49 57 149 44 35 45 7 1 1 11 8 15 7 7 175 81 81 81 176 176 224 198 140 224 182 259 259 40 175 193 81 259 1 259 107 258 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dccp/options.c * * An implementation of the DCCP protocol * Copyright (c) 2005 Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org> * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net> * Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz> */ #include <linux/dccp.h> #include <linux/module.h> #include <linux/types.h> #include <asm/unaligned.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include "ackvec.h" #include "ccid.h" #include "dccp.h" #include "feat.h" u64 dccp_decode_value_var(const u8 *bf, const u8 len) { u64 value = 0; if (len >= DCCP_OPTVAL_MAXLEN) value += ((u64)*bf++) << 40; if (len > 4) value += ((u64)*bf++) << 32; if (len > 3) value += ((u64)*bf++) << 24; if (len > 2) value += ((u64)*bf++) << 16; if (len > 1) value += ((u64)*bf++) << 8; if (len > 0) value += *bf; return value; } /** * dccp_parse_options - Parse DCCP options present in @skb * @sk: client|server|listening dccp socket (when @dreq != NULL) * @dreq: request socket to use during connection setup, or NULL * @skb: frame to parse */ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); const struct dccp_hdr *dh = dccp_hdr(skb); const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type; unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb); unsigned char *opt_ptr = options; const unsigned char *opt_end = (unsigned char *)dh + (dh->dccph_doff * 4); struct dccp_options_received *opt_recv = &dp->dccps_options_received; unsigned char opt, len; unsigned char *value; u32 elapsed_time; __be32 opt_val; int rc; int mandatory = 0; memset(opt_recv, 0, sizeof(*opt_recv)); opt = len = 0; while (opt_ptr != opt_end) { opt = *opt_ptr++; len = 0; value = NULL; /* Check if this isn't a single byte option */ if (opt > DCCPO_MAX_RESERVED) { if (opt_ptr == opt_end) goto out_nonsensical_length; len = *opt_ptr++; if (len < 2) goto out_nonsensical_length; /* * Remove the type and len fields, leaving * just the value size */ len -= 2; value = opt_ptr; opt_ptr += len; if (opt_ptr > opt_end) goto out_nonsensical_length; } /* * CCID-specific options are ignored during connection setup, as * negotiation may still be in progress (see RFC 4340, 10.3). * The same applies to Ack Vectors, as these depend on the CCID. */ if (dreq != NULL && (opt >= DCCPO_MIN_RX_CCID_SPECIFIC || opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1)) goto ignore_option; switch (opt) { case DCCPO_PADDING: break; case DCCPO_MANDATORY: if (mandatory) goto out_invalid_option; if (pkt_type != DCCP_PKT_DATA) mandatory = 1; break; case DCCPO_NDP_COUNT: if (len > 6) goto out_invalid_option; opt_recv->dccpor_ndp = dccp_decode_value_var(value, len); dccp_pr_debug("%s opt: NDP count=%llu\n", dccp_role(sk), (unsigned long long)opt_recv->dccpor_ndp); break; case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R: if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */ break; if (len == 0) goto out_invalid_option; rc = dccp_feat_parse_options(sk, dreq, mandatory, opt, *value, value + 1, len - 1); if (rc) goto out_featneg_failed; break; case DCCPO_TIMESTAMP: if (len != 4) goto out_invalid_option; /* * RFC 4340 13.1: "The precise time corresponding to * Timestamp Value zero is not specified". We use * zero to indicate absence of a meaningful timestamp. */ opt_val = get_unaligned((__be32 *)value); if (unlikely(opt_val == 0)) { DCCP_WARN("Timestamp with zero value\n"); break; } if (dreq != NULL) { dreq->dreq_timestamp_echo = ntohl(opt_val); dreq->dreq_timestamp_time = dccp_timestamp(); } else { opt_recv->dccpor_timestamp = dp->dccps_timestamp_echo = ntohl(opt_val); dp->dccps_timestamp_time = dccp_timestamp(); } dccp_pr_debug("%s rx opt: TIMESTAMP=%u, ackno=%llu\n", dccp_role(sk), ntohl(opt_val), (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq); /* schedule an Ack in case this sender is quiescent */ inet_csk_schedule_ack(sk); break; case DCCPO_TIMESTAMP_ECHO: if (len != 4 && len != 6 && len != 8) goto out_invalid_option; opt_val = get_unaligned((__be32 *)value); opt_recv->dccpor_timestamp_echo = ntohl(opt_val); dccp_pr_debug("%s rx opt: TIMESTAMP_ECHO=%u, len=%d, " "ackno=%llu", dccp_role(sk), opt_recv->dccpor_timestamp_echo, len + 2, (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq); value += 4; if (len == 4) { /* no elapsed time included */ dccp_pr_debug_cat("\n"); break; } if (len == 6) { /* 2-byte elapsed time */ __be16 opt_val2 = get_unaligned((__be16 *)value); elapsed_time = ntohs(opt_val2); } else { /* 4-byte elapsed time */ opt_val = get_unaligned((__be32 *)value); elapsed_time = ntohl(opt_val); } dccp_pr_debug_cat(", ELAPSED_TIME=%u\n", elapsed_time); /* Give precedence to the biggest ELAPSED_TIME */ if (elapsed_time > opt_recv->dccpor_elapsed_time) opt_recv->dccpor_elapsed_time = elapsed_time; break; case DCCPO_ELAPSED_TIME: if (dccp_packet_without_ack(skb)) /* RFC 4340, 13.2 */ break; if (len == 2) { __be16 opt_val2 = get_unaligned((__be16 *)value); elapsed_time = ntohs(opt_val2); } else if (len == 4) { opt_val = get_unaligned((__be32 *)value); elapsed_time = ntohl(opt_val); } else { goto out_invalid_option; } if (elapsed_time > opt_recv->dccpor_elapsed_time) opt_recv->dccpor_elapsed_time = elapsed_time; dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n", dccp_role(sk), elapsed_time); break; case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC: if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk, pkt_type, opt, value, len)) goto out_invalid_option; break; case DCCPO_ACK_VECTOR_0: case DCCPO_ACK_VECTOR_1: if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */ break; /* * Ack vectors are processed by the TX CCID if it is * interested. The RX CCID need not parse Ack Vectors, * since it is only interested in clearing old state. */ fallthrough; case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, pkt_type, opt, value, len)) goto out_invalid_option; break; default: DCCP_CRIT("DCCP(%p): option %d(len=%d) not " "implemented, ignoring", sk, opt, len); break; } ignore_option: if (opt != DCCPO_MANDATORY) mandatory = 0; } /* mandatory was the last byte in option list -> reset connection */ if (mandatory) goto out_invalid_option; out_nonsensical_length: /* RFC 4340, 5.8: ignore option and all remaining option space */ return 0; out_invalid_option: DCCP_INC_STATS(DCCP_MIB_INVALIDOPT); rc = DCCP_RESET_CODE_OPTION_ERROR; out_featneg_failed: DCCP_WARN("DCCP(%p): Option %d (len=%d) error=%u\n", sk, opt, len, rc); DCCP_SKB_CB(skb)->dccpd_reset_code = rc; DCCP_SKB_CB(skb)->dccpd_reset_data[0] = opt; DCCP_SKB_CB(skb)->dccpd_reset_data[1] = len > 0 ? value[0] : 0; DCCP_SKB_CB(skb)->dccpd_reset_data[2] = len > 1 ? value[1] : 0; return -1; } EXPORT_SYMBOL_GPL(dccp_parse_options); void dccp_encode_value_var(const u64 value, u8 *to, const u8 len) { if (len >= DCCP_OPTVAL_MAXLEN) *to++ = (value & 0xFF0000000000ull) >> 40; if (len > 4) *to++ = (value & 0xFF00000000ull) >> 32; if (len > 3) *to++ = (value & 0xFF000000) >> 24; if (len > 2) *to++ = (value & 0xFF0000) >> 16; if (len > 1) *to++ = (value & 0xFF00) >> 8; if (len > 0) *to++ = (value & 0xFF); } static inline u8 dccp_ndp_len(const u64 ndp) { if (likely(ndp <= 0xFF)) return 1; return likely(ndp <= USHRT_MAX) ? 2 : (ndp <= UINT_MAX ? 4 : 6); } int dccp_insert_option(struct sk_buff *skb, const unsigned char option, const void *value, const unsigned char len) { unsigned char *to; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 2 > DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len + 2; to = skb_push(skb, len + 2); *to++ = option; *to++ = len + 2; memcpy(to, value, len); return 0; } EXPORT_SYMBOL_GPL(dccp_insert_option); static int dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); u64 ndp = dp->dccps_ndp_count; if (dccp_non_data_packet(skb)) ++dp->dccps_ndp_count; else dp->dccps_ndp_count = 0; if (ndp > 0) { unsigned char *ptr; const int ndp_len = dccp_ndp_len(ndp); const int len = ndp_len + 2; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; ptr = skb_push(skb, len); *ptr++ = DCCPO_NDP_COUNT; *ptr++ = len; dccp_encode_value_var(ndp, ptr, ndp_len); } return 0; } static inline int dccp_elapsed_time_len(const u32 elapsed_time) { return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4; } static int dccp_insert_option_timestamp(struct sk_buff *skb) { __be32 now = htonl(dccp_timestamp()); /* yes this will overflow but that is the point as we want a * 10 usec 32 bit timer which mean it wraps every 11.9 hours */ return dccp_insert_option(skb, DCCPO_TIMESTAMP, &now, sizeof(now)); } static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp, struct dccp_request_sock *dreq, struct sk_buff *skb) { __be32 tstamp_echo; unsigned char *to; u32 elapsed_time, elapsed_time_len, len; if (dreq != NULL) { elapsed_time = dccp_timestamp() - dreq->dreq_timestamp_time; tstamp_echo = htonl(dreq->dreq_timestamp_echo); dreq->dreq_timestamp_echo = 0; } else { elapsed_time = dccp_timestamp() - dp->dccps_timestamp_time; tstamp_echo = htonl(dp->dccps_timestamp_echo); dp->dccps_timestamp_echo = 0; } elapsed_time_len = dccp_elapsed_time_len(elapsed_time); len = 6 + elapsed_time_len; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len += len; to = skb_push(skb, len); *to++ = DCCPO_TIMESTAMP_ECHO; *to++ = len; memcpy(to, &tstamp_echo, 4); to += 4; if (elapsed_time_len == 2) { const __be16 var16 = htons((u16)elapsed_time); memcpy(to, &var16, 2); } else if (elapsed_time_len == 4) { const __be32 var32 = htonl(elapsed_time); memcpy(to, &var32, 4); } return 0; } static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); const u16 buflen = dccp_ackvec_buflen(av); /* Figure out how many options do we need to represent the ackvec */ const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN); u16 len = buflen + 2 * nr_opts; u8 i, nonce = 0; const unsigned char *tail, *from; unsigned char *to; if (dcb->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) { DCCP_WARN("Lacking space for %u bytes on %s packet\n", len, dccp_packet_name(dcb->dccpd_type)); return -1; } /* * Since Ack Vectors are variable-length, we can not always predict * their size. To catch exception cases where the space is running out * on the skb, a separate Sync is scheduled to carry the Ack Vector. */ if (len > DCCPAV_MIN_OPTLEN && len + dcb->dccpd_opt_len + skb->len > dp->dccps_mss_cache) { DCCP_WARN("No space left for Ack Vector (%u) on skb (%u+%u), " "MPS=%u ==> reduce payload size?\n", len, skb->len, dcb->dccpd_opt_len, dp->dccps_mss_cache); dp->dccps_sync_scheduled = 1; return 0; } dcb->dccpd_opt_len += len; to = skb_push(skb, len); len = buflen; from = av->av_buf + av->av_buf_head; tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; for (i = 0; i < nr_opts; ++i) { int copylen = len; if (len > DCCP_SINGLE_OPT_MAXLEN) copylen = DCCP_SINGLE_OPT_MAXLEN; /* * RFC 4340, 12.2: Encode the Nonce Echo for this Ack Vector via * its type; ack_nonce is the sum of all individual buf_nonce's. */ nonce ^= av->av_buf_nonce[i]; *to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i]; *to++ = copylen + 2; /* Check if buf_head wraps */ if (from + copylen > tail) { const u16 tailsize = tail - from; memcpy(to, from, tailsize); to += tailsize; len -= tailsize; copylen -= tailsize; from = av->av_buf; } memcpy(to, from, copylen); from += copylen; to += copylen; len -= copylen; } /* * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340. */ if (dccp_ackvec_update_records(av, dcb->dccpd_seq, nonce)) return -ENOBUFS; return 0; } /** * dccp_insert_option_mandatory - Mandatory option (5.8.2) * @skb: frame into which to insert option * * Note that since we are using skb_push, this function needs to be called * _after_ inserting the option it is supposed to influence (stack order). */ int dccp_insert_option_mandatory(struct sk_buff *skb) { if (DCCP_SKB_CB(skb)->dccpd_opt_len >= DCCP_MAX_OPT_LEN) return -1; DCCP_SKB_CB(skb)->dccpd_opt_len++; *(u8 *)skb_push(skb, 1) = DCCPO_MANDATORY; return 0; } /** * dccp_insert_fn_opt - Insert single Feature-Negotiation option into @skb * @skb: frame to insert feature negotiation option into * @type: %DCCPO_CHANGE_L, %DCCPO_CHANGE_R, %DCCPO_CONFIRM_L, %DCCPO_CONFIRM_R * @feat: one out of %dccp_feature_numbers * @val: NN value or SP array (preferred element first) to copy * @len: true length of @val in bytes (excluding first element repetition) * @repeat_first: whether to copy the first element of @val twice * * The last argument is used to construct Confirm options, where the preferred * value and the preference list appear separately (RFC 4340, 6.3.1). Preference * lists are kept such that the preferred entry is always first, so we only need * to copy twice, and avoid the overhead of cloning into a bigger array. */ int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat, u8 *val, u8 len, bool repeat_first) { u8 tot_len, *to; /* take the `Feature' field and possible repetition into account */ if (len > (DCCP_SINGLE_OPT_MAXLEN - 2)) { DCCP_WARN("length %u for feature %u too large\n", len, feat); return -1; } if (unlikely(val == NULL || len == 0)) len = repeat_first = false; tot_len = 3 + repeat_first + len; if (DCCP_SKB_CB(skb)->dccpd_opt_len + tot_len > DCCP_MAX_OPT_LEN) { DCCP_WARN("packet too small for feature %d option!\n", feat); return -1; } DCCP_SKB_CB(skb)->dccpd_opt_len += tot_len; to = skb_push(skb, tot_len); *to++ = type; *to++ = tot_len; *to++ = feat; if (repeat_first) *to++ = *val; if (len) memcpy(to, val, len); return 0; } /* The length of all options needs to be a multiple of 4 (5.8) */ static void dccp_insert_option_padding(struct sk_buff *skb) { int padding = DCCP_SKB_CB(skb)->dccpd_opt_len % 4; if (padding != 0) { padding = 4 - padding; memset(skb_push(skb, padding), 0, padding); DCCP_SKB_CB(skb)->dccpd_opt_len += padding; } } int dccp_insert_options(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); DCCP_SKB_CB(skb)->dccpd_opt_len = 0; if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb)) return -1; if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) { /* Feature Negotiation */ if (dccp_feat_insert_opts(dp, NULL, skb)) return -1; if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST) { /* * Obtain RTT sample from Request/Response exchange. * This is currently used for TFRC initialisation. */ if (dccp_insert_option_timestamp(skb)) return -1; } else if (dccp_ackvec_pending(sk) && dccp_insert_option_ackvec(sk, skb)) { return -1; } } if (dp->dccps_hc_rx_insert_options) { if (ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb)) return -1; dp->dccps_hc_rx_insert_options = 0; } if (dp->dccps_timestamp_echo != 0 && dccp_insert_option_timestamp_echo(dp, NULL, skb)) return -1; dccp_insert_option_padding(skb); return 0; } int dccp_insert_options_rsk(struct dccp_request_sock *dreq, struct sk_buff *skb) { DCCP_SKB_CB(skb)->dccpd_opt_len = 0; if (dccp_feat_insert_opts(NULL, dreq, skb)) return -1; /* Obtain RTT sample from Response/Ack exchange (used by TFRC). */ if (dccp_insert_option_timestamp(skb)) return -1; if (dreq->dreq_timestamp_echo != 0 && dccp_insert_option_timestamp_echo(NULL, dreq, skb)) return -1; dccp_insert_option_padding(skb); return 0; } |
| 275 6 271 28 28 28 28 28 521 838 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright Red Hat Inc. 2017 * * This file is part of the SCTP kernel implementation * * These functions implement sctp stream message interleaving, mostly * including I-DATA and I-FORWARD-TSN chunks process. * * Please send any bug reports or fixes you make to the * email addresched(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * Xin Long <lucien.xin@gmail.com> */ #include <net/busy_poll.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/ulpevent.h> #include <linux/sctp.h> static struct sctp_chunk *sctp_make_idatafrag_empty( const struct sctp_association *asoc, const struct sctp_sndrcvinfo *sinfo, int len, __u8 flags, gfp_t gfp) { struct sctp_chunk *retval; struct sctp_idatahdr dp; memset(&dp, 0, sizeof(dp)); dp.stream = htons(sinfo->sinfo_stream); if (sinfo->sinfo_flags & SCTP_UNORDERED) flags |= SCTP_DATA_UNORDERED; retval = sctp_make_idata(asoc, flags, sizeof(dp) + len, gfp); if (!retval) return NULL; retval->subh.idata_hdr = sctp_addto_chunk(retval, sizeof(dp), &dp); memcpy(&retval->sinfo, sinfo, sizeof(struct sctp_sndrcvinfo)); return retval; } static void sctp_chunk_assign_mid(struct sctp_chunk *chunk) { struct sctp_stream *stream; struct sctp_chunk *lchunk; __u32 cfsn = 0; __u16 sid; if (chunk->has_mid) return; sid = sctp_chunk_stream_no(chunk); stream = &chunk->asoc->stream; list_for_each_entry(lchunk, &chunk->msg->chunks, frag_list) { struct sctp_idatahdr *hdr; __u32 mid; lchunk->has_mid = 1; hdr = lchunk->subh.idata_hdr; if (lchunk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG) hdr->ppid = lchunk->sinfo.sinfo_ppid; else hdr->fsn = htonl(cfsn++); if (lchunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) { mid = lchunk->chunk_hdr->flags & SCTP_DATA_LAST_FRAG ? sctp_mid_uo_next(stream, out, sid) : sctp_mid_uo_peek(stream, out, sid); } else { mid = lchunk->chunk_hdr->flags & SCTP_DATA_LAST_FRAG ? sctp_mid_next(stream, out, sid) : sctp_mid_peek(stream, out, sid); } hdr->mid = htonl(mid); } } static bool sctp_validate_data(struct sctp_chunk *chunk) { struct sctp_stream *stream; __u16 sid, ssn; if (chunk->chunk_hdr->type != SCTP_CID_DATA) return false; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) return true; stream = &chunk->asoc->stream; sid = sctp_chunk_stream_no(chunk); ssn = ntohs(chunk->subh.data_hdr->ssn); return !SSN_lt(ssn, sctp_ssn_peek(stream, in, sid)); } static bool sctp_validate_idata(struct sctp_chunk *chunk) { struct sctp_stream *stream; __u32 mid; __u16 sid; if (chunk->chunk_hdr->type != SCTP_CID_I_DATA) return false; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) return true; stream = &chunk->asoc->stream; sid = sctp_chunk_stream_no(chunk); mid = ntohl(chunk->subh.idata_hdr->mid); return !MID_lt(mid, sctp_mid_peek(stream, in, sid)); } static void sctp_intl_store_reasm(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_ulpevent *cevent; struct sk_buff *pos, *loc; pos = skb_peek_tail(&ulpq->reasm); if (!pos) { __skb_queue_tail(&ulpq->reasm, sctp_event2skb(event)); return; } cevent = sctp_skb2event(pos); if (event->stream == cevent->stream && event->mid == cevent->mid && (cevent->msg_flags & SCTP_DATA_FIRST_FRAG || (!(event->msg_flags & SCTP_DATA_FIRST_FRAG) && event->fsn > cevent->fsn))) { __skb_queue_tail(&ulpq->reasm, sctp_event2skb(event)); return; } if ((event->stream == cevent->stream && MID_lt(cevent->mid, event->mid)) || event->stream > cevent->stream) { __skb_queue_tail(&ulpq->reasm, sctp_event2skb(event)); return; } loc = NULL; skb_queue_walk(&ulpq->reasm, pos) { cevent = sctp_skb2event(pos); if (event->stream < cevent->stream || (event->stream == cevent->stream && MID_lt(event->mid, cevent->mid))) { loc = pos; break; } if (event->stream == cevent->stream && event->mid == cevent->mid && !(cevent->msg_flags & SCTP_DATA_FIRST_FRAG) && (event->msg_flags & SCTP_DATA_FIRST_FRAG || event->fsn < cevent->fsn)) { loc = pos; break; } } if (!loc) __skb_queue_tail(&ulpq->reasm, sctp_event2skb(event)); else __skb_queue_before(&ulpq->reasm, loc, sctp_event2skb(event)); } static struct sctp_ulpevent *sctp_intl_retrieve_partial( struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sk_buff *first_frag = NULL; struct sk_buff *last_frag = NULL; struct sctp_ulpevent *retval; struct sctp_stream_in *sin; struct sk_buff *pos; __u32 next_fsn = 0; int is_last = 0; sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); if (cevent->stream < event->stream) continue; if (cevent->stream > event->stream || cevent->mid != sin->mid) break; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: goto out; case SCTP_DATA_MIDDLE_FRAG: if (!first_frag) { if (cevent->fsn == sin->fsn) { first_frag = pos; last_frag = pos; next_fsn = cevent->fsn + 1; } } else if (cevent->fsn == next_fsn) { last_frag = pos; next_fsn++; } else { goto out; } break; case SCTP_DATA_LAST_FRAG: if (!first_frag) { if (cevent->fsn == sin->fsn) { first_frag = pos; last_frag = pos; next_fsn = 0; is_last = 1; } } else if (cevent->fsn == next_fsn) { last_frag = pos; next_fsn = 0; is_last = 1; } goto out; default: goto out; } } out: if (!first_frag) return NULL; retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm, first_frag, last_frag); if (retval) { sin->fsn = next_fsn; if (is_last) { retval->msg_flags |= MSG_EOR; sin->pd_mode = 0; } } return retval; } static struct sctp_ulpevent *sctp_intl_retrieve_reassembled( struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_association *asoc = ulpq->asoc; struct sk_buff *pos, *first_frag = NULL; struct sctp_ulpevent *retval = NULL; struct sk_buff *pd_first = NULL; struct sk_buff *pd_last = NULL; struct sctp_stream_in *sin; __u32 next_fsn = 0; __u32 pd_point = 0; __u32 pd_len = 0; __u32 mid = 0; sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); if (cevent->stream < event->stream) continue; if (cevent->stream > event->stream) break; if (MID_lt(cevent->mid, event->mid)) continue; if (MID_lt(event->mid, cevent->mid)) break; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: if (cevent->mid == sin->mid) { pd_first = pos; pd_last = pos; pd_len = pos->len; } first_frag = pos; next_fsn = 0; mid = cevent->mid; break; case SCTP_DATA_MIDDLE_FRAG: if (first_frag && cevent->mid == mid && cevent->fsn == next_fsn) { next_fsn++; if (pd_first) { pd_last = pos; pd_len += pos->len; } } else { first_frag = NULL; } break; case SCTP_DATA_LAST_FRAG: if (first_frag && cevent->mid == mid && cevent->fsn == next_fsn) goto found; else first_frag = NULL; break; } } if (!pd_first) goto out; pd_point = sctp_sk(asoc->base.sk)->pd_point; if (pd_point && pd_point <= pd_len) { retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm, pd_first, pd_last); if (retval) { sin->fsn = next_fsn; sin->pd_mode = 1; } } goto out; found: retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm, first_frag, pos); if (retval) retval->msg_flags |= MSG_EOR; out: return retval; } static struct sctp_ulpevent *sctp_intl_reasm(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_ulpevent *retval = NULL; struct sctp_stream_in *sin; if (SCTP_DATA_NOT_FRAG == (event->msg_flags & SCTP_DATA_FRAG_MASK)) { event->msg_flags |= MSG_EOR; return event; } sctp_intl_store_reasm(ulpq, event); sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); if (sin->pd_mode && event->mid == sin->mid && event->fsn == sin->fsn) retval = sctp_intl_retrieve_partial(ulpq, event); if (!retval) retval = sctp_intl_retrieve_reassembled(ulpq, event); return retval; } static void sctp_intl_store_ordered(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_ulpevent *cevent; struct sk_buff *pos, *loc; pos = skb_peek_tail(&ulpq->lobby); if (!pos) { __skb_queue_tail(&ulpq->lobby, sctp_event2skb(event)); return; } cevent = (struct sctp_ulpevent *)pos->cb; if (event->stream == cevent->stream && MID_lt(cevent->mid, event->mid)) { __skb_queue_tail(&ulpq->lobby, sctp_event2skb(event)); return; } if (event->stream > cevent->stream) { __skb_queue_tail(&ulpq->lobby, sctp_event2skb(event)); return; } loc = NULL; skb_queue_walk(&ulpq->lobby, pos) { cevent = (struct sctp_ulpevent *)pos->cb; if (cevent->stream > event->stream) { loc = pos; break; } if (cevent->stream == event->stream && MID_lt(event->mid, cevent->mid)) { loc = pos; break; } } if (!loc) __skb_queue_tail(&ulpq->lobby, sctp_event2skb(event)); else __skb_queue_before(&ulpq->lobby, loc, sctp_event2skb(event)); } static void sctp_intl_retrieve_ordered(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sk_buff_head *event_list; struct sctp_stream *stream; struct sk_buff *pos, *tmp; __u16 sid = event->stream; stream = &ulpq->asoc->stream; event_list = (struct sk_buff_head *)sctp_event2skb(event)->prev; sctp_skb_for_each(pos, &ulpq->lobby, tmp) { struct sctp_ulpevent *cevent = (struct sctp_ulpevent *)pos->cb; if (cevent->stream > sid) break; if (cevent->stream < sid) continue; if (cevent->mid != sctp_mid_peek(stream, in, sid)) break; sctp_mid_next(stream, in, sid); __skb_unlink(pos, &ulpq->lobby); __skb_queue_tail(event_list, pos); } } static struct sctp_ulpevent *sctp_intl_order(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_stream *stream; __u16 sid; stream = &ulpq->asoc->stream; sid = event->stream; if (event->mid != sctp_mid_peek(stream, in, sid)) { sctp_intl_store_ordered(ulpq, event); return NULL; } sctp_mid_next(stream, in, sid); sctp_intl_retrieve_ordered(ulpq, event); return event; } static int sctp_enqueue_event(struct sctp_ulpq *ulpq, struct sk_buff_head *skb_list) { struct sock *sk = ulpq->asoc->base.sk; struct sctp_sock *sp = sctp_sk(sk); struct sctp_ulpevent *event; struct sk_buff *skb; skb = __skb_peek(skb_list); event = sctp_skb2event(skb); if (sk->sk_shutdown & RCV_SHUTDOWN && (sk->sk_shutdown & SEND_SHUTDOWN || !sctp_ulpevent_is_notification(event))) goto out_free; if (!sctp_ulpevent_is_notification(event)) { sk_mark_napi_id(sk, skb); sk_incoming_cpu_update(sk); } if (!sctp_ulpevent_is_enabled(event, ulpq->asoc->subscribe)) goto out_free; skb_queue_splice_tail_init(skb_list, &sk->sk_receive_queue); if (!sp->data_ready_signalled) { sp->data_ready_signalled = 1; sk->sk_data_ready(sk); } return 1; out_free: sctp_queue_purge_ulpevents(skb_list); return 0; } static void sctp_intl_store_reasm_uo(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_ulpevent *cevent; struct sk_buff *pos; pos = skb_peek_tail(&ulpq->reasm_uo); if (!pos) { __skb_queue_tail(&ulpq->reasm_uo, sctp_event2skb(event)); return; } cevent = sctp_skb2event(pos); if (event->stream == cevent->stream && event->mid == cevent->mid && (cevent->msg_flags & SCTP_DATA_FIRST_FRAG || (!(event->msg_flags & SCTP_DATA_FIRST_FRAG) && event->fsn > cevent->fsn))) { __skb_queue_tail(&ulpq->reasm_uo, sctp_event2skb(event)); return; } if ((event->stream == cevent->stream && MID_lt(cevent->mid, event->mid)) || event->stream > cevent->stream) { __skb_queue_tail(&ulpq->reasm_uo, sctp_event2skb(event)); return; } skb_queue_walk(&ulpq->reasm_uo, pos) { cevent = sctp_skb2event(pos); if (event->stream < cevent->stream || (event->stream == cevent->stream && MID_lt(event->mid, cevent->mid))) break; if (event->stream == cevent->stream && event->mid == cevent->mid && !(cevent->msg_flags & SCTP_DATA_FIRST_FRAG) && (event->msg_flags & SCTP_DATA_FIRST_FRAG || event->fsn < cevent->fsn)) break; } __skb_queue_before(&ulpq->reasm_uo, pos, sctp_event2skb(event)); } static struct sctp_ulpevent *sctp_intl_retrieve_partial_uo( struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sk_buff *first_frag = NULL; struct sk_buff *last_frag = NULL; struct sctp_ulpevent *retval; struct sctp_stream_in *sin; struct sk_buff *pos; __u32 next_fsn = 0; int is_last = 0; sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); if (cevent->stream < event->stream) continue; if (cevent->stream > event->stream) break; if (MID_lt(cevent->mid, sin->mid_uo)) continue; if (MID_lt(sin->mid_uo, cevent->mid)) break; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: goto out; case SCTP_DATA_MIDDLE_FRAG: if (!first_frag) { if (cevent->fsn == sin->fsn_uo) { first_frag = pos; last_frag = pos; next_fsn = cevent->fsn + 1; } } else if (cevent->fsn == next_fsn) { last_frag = pos; next_fsn++; } else { goto out; } break; case SCTP_DATA_LAST_FRAG: if (!first_frag) { if (cevent->fsn == sin->fsn_uo) { first_frag = pos; last_frag = pos; next_fsn = 0; is_last = 1; } } else if (cevent->fsn == next_fsn) { last_frag = pos; next_fsn = 0; is_last = 1; } goto out; default: goto out; } } out: if (!first_frag) return NULL; retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm_uo, first_frag, last_frag); if (retval) { sin->fsn_uo = next_fsn; if (is_last) { retval->msg_flags |= MSG_EOR; sin->pd_mode_uo = 0; } } return retval; } static struct sctp_ulpevent *sctp_intl_retrieve_reassembled_uo( struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_association *asoc = ulpq->asoc; struct sk_buff *pos, *first_frag = NULL; struct sctp_ulpevent *retval = NULL; struct sk_buff *pd_first = NULL; struct sk_buff *pd_last = NULL; struct sctp_stream_in *sin; __u32 next_fsn = 0; __u32 pd_point = 0; __u32 pd_len = 0; __u32 mid = 0; sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); if (cevent->stream < event->stream) continue; if (cevent->stream > event->stream) break; if (MID_lt(cevent->mid, event->mid)) continue; if (MID_lt(event->mid, cevent->mid)) break; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: if (!sin->pd_mode_uo) { sin->mid_uo = cevent->mid; pd_first = pos; pd_last = pos; pd_len = pos->len; } first_frag = pos; next_fsn = 0; mid = cevent->mid; break; case SCTP_DATA_MIDDLE_FRAG: if (first_frag && cevent->mid == mid && cevent->fsn == next_fsn) { next_fsn++; if (pd_first) { pd_last = pos; pd_len += pos->len; } } else { first_frag = NULL; } break; case SCTP_DATA_LAST_FRAG: if (first_frag && cevent->mid == mid && cevent->fsn == next_fsn) goto found; else first_frag = NULL; break; } } if (!pd_first) goto out; pd_point = sctp_sk(asoc->base.sk)->pd_point; if (pd_point && pd_point <= pd_len) { retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm_uo, pd_first, pd_last); if (retval) { sin->fsn_uo = next_fsn; sin->pd_mode_uo = 1; } } goto out; found: retval = sctp_make_reassembled_event(asoc->base.net, &ulpq->reasm_uo, first_frag, pos); if (retval) retval->msg_flags |= MSG_EOR; out: return retval; } static struct sctp_ulpevent *sctp_intl_reasm_uo(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sctp_ulpevent *retval = NULL; struct sctp_stream_in *sin; if (SCTP_DATA_NOT_FRAG == (event->msg_flags & SCTP_DATA_FRAG_MASK)) { event->msg_flags |= MSG_EOR; return event; } sctp_intl_store_reasm_uo(ulpq, event); sin = sctp_stream_in(&ulpq->asoc->stream, event->stream); if (sin->pd_mode_uo && event->mid == sin->mid_uo && event->fsn == sin->fsn_uo) retval = sctp_intl_retrieve_partial_uo(ulpq, event); if (!retval) retval = sctp_intl_retrieve_reassembled_uo(ulpq, event); return retval; } static struct sctp_ulpevent *sctp_intl_retrieve_first_uo(struct sctp_ulpq *ulpq) { struct sctp_stream_in *csin, *sin = NULL; struct sk_buff *first_frag = NULL; struct sk_buff *last_frag = NULL; struct sctp_ulpevent *retval; struct sk_buff *pos; __u32 next_fsn = 0; __u16 sid = 0; skb_queue_walk(&ulpq->reasm_uo, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); csin = sctp_stream_in(&ulpq->asoc->stream, cevent->stream); if (csin->pd_mode_uo) continue; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: if (first_frag) goto out; first_frag = pos; last_frag = pos; next_fsn = 0; sin = csin; sid = cevent->stream; sin->mid_uo = cevent->mid; break; case SCTP_DATA_MIDDLE_FRAG: if (!first_frag) break; if (cevent->stream == sid && cevent->mid == sin->mid_uo && cevent->fsn == next_fsn) { next_fsn++; last_frag = pos; } else { goto out; } break; case SCTP_DATA_LAST_FRAG: if (first_frag) goto out; break; default: break; } } if (!first_frag) return NULL; out: retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm_uo, first_frag, last_frag); if (retval) { sin->fsn_uo = next_fsn; sin->pd_mode_uo = 1; } return retval; } static int sctp_ulpevent_idata(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, gfp_t gfp) { struct sctp_ulpevent *event; struct sk_buff_head temp; int event_eor = 0; event = sctp_ulpevent_make_rcvmsg(chunk->asoc, chunk, gfp); if (!event) return -ENOMEM; event->mid = ntohl(chunk->subh.idata_hdr->mid); if (event->msg_flags & SCTP_DATA_FIRST_FRAG) event->ppid = chunk->subh.idata_hdr->ppid; else event->fsn = ntohl(chunk->subh.idata_hdr->fsn); if (!(event->msg_flags & SCTP_DATA_UNORDERED)) { event = sctp_intl_reasm(ulpq, event); if (event) { skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); if (event->msg_flags & MSG_EOR) event = sctp_intl_order(ulpq, event); } } else { event = sctp_intl_reasm_uo(ulpq, event); if (event) { skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); } } if (event) { event_eor = (event->msg_flags & MSG_EOR) ? 1 : 0; sctp_enqueue_event(ulpq, &temp); } return event_eor; } static struct sctp_ulpevent *sctp_intl_retrieve_first(struct sctp_ulpq *ulpq) { struct sctp_stream_in *csin, *sin = NULL; struct sk_buff *first_frag = NULL; struct sk_buff *last_frag = NULL; struct sctp_ulpevent *retval; struct sk_buff *pos; __u32 next_fsn = 0; __u16 sid = 0; skb_queue_walk(&ulpq->reasm, pos) { struct sctp_ulpevent *cevent = sctp_skb2event(pos); csin = sctp_stream_in(&ulpq->asoc->stream, cevent->stream); if (csin->pd_mode) continue; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { case SCTP_DATA_FIRST_FRAG: if (first_frag) goto out; if (cevent->mid == csin->mid) { first_frag = pos; last_frag = pos; next_fsn = 0; sin = csin; sid = cevent->stream; } break; case SCTP_DATA_MIDDLE_FRAG: if (!first_frag) break; if (cevent->stream == sid && cevent->mid == sin->mid && cevent->fsn == next_fsn) { next_fsn++; last_frag = pos; } else { goto out; } break; case SCTP_DATA_LAST_FRAG: if (first_frag) goto out; break; default: break; } } if (!first_frag) return NULL; out: retval = sctp_make_reassembled_event(ulpq->asoc->base.net, &ulpq->reasm, first_frag, last_frag); if (retval) { sin->fsn = next_fsn; sin->pd_mode = 1; } return retval; } static void sctp_intl_start_pd(struct sctp_ulpq *ulpq, gfp_t gfp) { struct sctp_ulpevent *event; struct sk_buff_head temp; if (!skb_queue_empty(&ulpq->reasm)) { do { event = sctp_intl_retrieve_first(ulpq); if (event) { skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); sctp_enqueue_event(ulpq, &temp); } } while (event); } if (!skb_queue_empty(&ulpq->reasm_uo)) { do { event = sctp_intl_retrieve_first_uo(ulpq); if (event) { skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); sctp_enqueue_event(ulpq, &temp); } } while (event); } } static void sctp_renege_events(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, gfp_t gfp) { struct sctp_association *asoc = ulpq->asoc; __u32 freed = 0; __u16 needed; needed = ntohs(chunk->chunk_hdr->length) - sizeof(struct sctp_idata_chunk); if (skb_queue_empty(&asoc->base.sk->sk_receive_queue)) { freed = sctp_ulpq_renege_list(ulpq, &ulpq->lobby, needed); if (freed < needed) freed += sctp_ulpq_renege_list(ulpq, &ulpq->reasm, needed); if (freed < needed) freed += sctp_ulpq_renege_list(ulpq, &ulpq->reasm_uo, needed); } if (freed >= needed && sctp_ulpevent_idata(ulpq, chunk, gfp) <= 0) sctp_intl_start_pd(ulpq, gfp); } static void sctp_intl_stream_abort_pd(struct sctp_ulpq *ulpq, __u16 sid, __u32 mid, __u16 flags, gfp_t gfp) { struct sock *sk = ulpq->asoc->base.sk; struct sctp_ulpevent *ev = NULL; if (!sctp_ulpevent_type_enabled(ulpq->asoc->subscribe, SCTP_PARTIAL_DELIVERY_EVENT)) return; ev = sctp_ulpevent_make_pdapi(ulpq->asoc, SCTP_PARTIAL_DELIVERY_ABORTED, sid, mid, flags, gfp); if (ev) { struct sctp_sock *sp = sctp_sk(sk); __skb_queue_tail(&sk->sk_receive_queue, sctp_event2skb(ev)); if (!sp->data_ready_signalled) { sp->data_ready_signalled = 1; sk->sk_data_ready(sk); } } } static void sctp_intl_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid) { struct sctp_stream *stream = &ulpq->asoc->stream; struct sctp_ulpevent *cevent, *event = NULL; struct sk_buff_head *lobby = &ulpq->lobby; struct sk_buff *pos, *tmp; struct sk_buff_head temp; __u16 csid; __u32 cmid; skb_queue_head_init(&temp); sctp_skb_for_each(pos, lobby, tmp) { cevent = (struct sctp_ulpevent *)pos->cb; csid = cevent->stream; cmid = cevent->mid; if (csid > sid) break; if (csid < sid) continue; if (!MID_lt(cmid, sctp_mid_peek(stream, in, csid))) break; __skb_unlink(pos, lobby); if (!event) event = sctp_skb2event(pos); __skb_queue_tail(&temp, pos); } if (!event && pos != (struct sk_buff *)lobby) { cevent = (struct sctp_ulpevent *)pos->cb; csid = cevent->stream; cmid = cevent->mid; if (csid == sid && cmid == sctp_mid_peek(stream, in, csid)) { sctp_mid_next(stream, in, csid); __skb_unlink(pos, lobby); __skb_queue_tail(&temp, pos); event = sctp_skb2event(pos); } } if (event) { sctp_intl_retrieve_ordered(ulpq, event); sctp_enqueue_event(ulpq, &temp); } } static void sctp_intl_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp) { struct sctp_stream *stream = &ulpq->asoc->stream; __u16 sid; for (sid = 0; sid < stream->incnt; sid++) { struct sctp_stream_in *sin = SCTP_SI(stream, sid); __u32 mid; if (sin->pd_mode_uo) { sin->pd_mode_uo = 0; mid = sin->mid_uo; sctp_intl_stream_abort_pd(ulpq, sid, mid, 0x1, gfp); } if (sin->pd_mode) { sin->pd_mode = 0; mid = sin->mid; sctp_intl_stream_abort_pd(ulpq, sid, mid, 0, gfp); sctp_mid_skip(stream, in, sid, mid); sctp_intl_reap_ordered(ulpq, sid); } } /* intl abort pd happens only when all data needs to be cleaned */ sctp_ulpq_flush(ulpq); } static inline int sctp_get_skip_pos(struct sctp_ifwdtsn_skip *skiplist, int nskips, __be16 stream, __u8 flags) { int i; for (i = 0; i < nskips; i++) if (skiplist[i].stream == stream && skiplist[i].flags == flags) return i; return i; } #define SCTP_FTSN_U_BIT 0x1 static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) { struct sctp_ifwdtsn_skip ftsn_skip_arr[10]; struct sctp_association *asoc = q->asoc; struct sctp_chunk *ftsn_chunk = NULL; struct list_head *lchunk, *temp; int nskips = 0, skip_pos; struct sctp_chunk *chunk; __u32 tsn; if (!asoc->peer.prsctp_capable) return; if (TSN_lt(asoc->adv_peer_ack_point, ctsn)) asoc->adv_peer_ack_point = ctsn; list_for_each_safe(lchunk, temp, &q->abandoned) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); tsn = ntohl(chunk->subh.data_hdr->tsn); if (TSN_lte(tsn, ctsn)) { list_del_init(lchunk); sctp_chunk_free(chunk); } else if (TSN_lte(tsn, asoc->adv_peer_ack_point + 1)) { __be16 sid = chunk->subh.idata_hdr->stream; __be32 mid = chunk->subh.idata_hdr->mid; __u8 flags = 0; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) flags |= SCTP_FTSN_U_BIT; asoc->adv_peer_ack_point = tsn; skip_pos = sctp_get_skip_pos(&ftsn_skip_arr[0], nskips, sid, flags); ftsn_skip_arr[skip_pos].stream = sid; ftsn_skip_arr[skip_pos].reserved = 0; ftsn_skip_arr[skip_pos].flags = flags; ftsn_skip_arr[skip_pos].mid = mid; if (skip_pos == nskips) nskips++; if (nskips == 10) break; } else { break; } } if (asoc->adv_peer_ack_point > ctsn) ftsn_chunk = sctp_make_ifwdtsn(asoc, asoc->adv_peer_ack_point, nskips, &ftsn_skip_arr[0]); if (ftsn_chunk) { list_add_tail(&ftsn_chunk->list, &q->control_chunk_list); SCTP_INC_STATS(asoc->base.net, SCTP_MIB_OUTCTRLCHUNKS); } } #define _sctp_walk_ifwdtsn(pos, chunk, end) \ for (pos = (void *)(chunk->subh.ifwdtsn_hdr + 1); \ (void *)pos <= (void *)(chunk->subh.ifwdtsn_hdr + 1) + (end) - \ sizeof(struct sctp_ifwdtsn_skip); pos++) #define sctp_walk_ifwdtsn(pos, ch) \ _sctp_walk_ifwdtsn((pos), (ch), ntohs((ch)->chunk_hdr->length) - \ sizeof(struct sctp_ifwdtsn_chunk)) static bool sctp_validate_fwdtsn(struct sctp_chunk *chunk) { struct sctp_fwdtsn_skip *skip; __u16 incnt; if (chunk->chunk_hdr->type != SCTP_CID_FWD_TSN) return false; incnt = chunk->asoc->stream.incnt; sctp_walk_fwdtsn(skip, chunk) if (ntohs(skip->stream) >= incnt) return false; return true; } static bool sctp_validate_iftsn(struct sctp_chunk *chunk) { struct sctp_ifwdtsn_skip *skip; __u16 incnt; if (chunk->chunk_hdr->type != SCTP_CID_I_FWD_TSN) return false; incnt = chunk->asoc->stream.incnt; sctp_walk_ifwdtsn(skip, chunk) if (ntohs(skip->stream) >= incnt) return false; return true; } static void sctp_report_fwdtsn(struct sctp_ulpq *ulpq, __u32 ftsn) { /* Move the Cumulattive TSN Ack ahead. */ sctp_tsnmap_skip(&ulpq->asoc->peer.tsn_map, ftsn); /* purge the fragmentation queue */ sctp_ulpq_reasm_flushtsn(ulpq, ftsn); /* Abort any in progress partial delivery. */ sctp_ulpq_abort_pd(ulpq, GFP_ATOMIC); } static void sctp_intl_reasm_flushtsn(struct sctp_ulpq *ulpq, __u32 ftsn) { struct sk_buff *pos, *tmp; skb_queue_walk_safe(&ulpq->reasm, pos, tmp) { struct sctp_ulpevent *event = sctp_skb2event(pos); __u32 tsn = event->tsn; if (TSN_lte(tsn, ftsn)) { __skb_unlink(pos, &ulpq->reasm); sctp_ulpevent_free(event); } } skb_queue_walk_safe(&ulpq->reasm_uo, pos, tmp) { struct sctp_ulpevent *event = sctp_skb2event(pos); __u32 tsn = event->tsn; if (TSN_lte(tsn, ftsn)) { __skb_unlink(pos, &ulpq->reasm_uo); sctp_ulpevent_free(event); } } } static void sctp_report_iftsn(struct sctp_ulpq *ulpq, __u32 ftsn) { /* Move the Cumulattive TSN Ack ahead. */ sctp_tsnmap_skip(&ulpq->asoc->peer.tsn_map, ftsn); /* purge the fragmentation queue */ sctp_intl_reasm_flushtsn(ulpq, ftsn); /* abort only when it's for all data */ if (ftsn == sctp_tsnmap_get_max_tsn_seen(&ulpq->asoc->peer.tsn_map)) sctp_intl_abort_pd(ulpq, GFP_ATOMIC); } static void sctp_handle_fwdtsn(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk) { struct sctp_fwdtsn_skip *skip; /* Walk through all the skipped SSNs */ sctp_walk_fwdtsn(skip, chunk) sctp_ulpq_skip(ulpq, ntohs(skip->stream), ntohs(skip->ssn)); } static void sctp_intl_skip(struct sctp_ulpq *ulpq, __u16 sid, __u32 mid, __u8 flags) { struct sctp_stream_in *sin = sctp_stream_in(&ulpq->asoc->stream, sid); struct sctp_stream *stream = &ulpq->asoc->stream; if (flags & SCTP_FTSN_U_BIT) { if (sin->pd_mode_uo && MID_lt(sin->mid_uo, mid)) { sin->pd_mode_uo = 0; sctp_intl_stream_abort_pd(ulpq, sid, mid, 0x1, GFP_ATOMIC); } return; } if (MID_lt(mid, sctp_mid_peek(stream, in, sid))) return; if (sin->pd_mode) { sin->pd_mode = 0; sctp_intl_stream_abort_pd(ulpq, sid, mid, 0x0, GFP_ATOMIC); } sctp_mid_skip(stream, in, sid, mid); sctp_intl_reap_ordered(ulpq, sid); } static void sctp_handle_iftsn(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk) { struct sctp_ifwdtsn_skip *skip; /* Walk through all the skipped MIDs and abort stream pd if possible */ sctp_walk_ifwdtsn(skip, chunk) sctp_intl_skip(ulpq, ntohs(skip->stream), ntohl(skip->mid), skip->flags); } static int do_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sk_buff_head temp; skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); return sctp_ulpq_tail_event(ulpq, &temp); } static struct sctp_stream_interleave sctp_stream_interleave_0 = { .data_chunk_len = sizeof(struct sctp_data_chunk), .ftsn_chunk_len = sizeof(struct sctp_fwdtsn_chunk), /* DATA process functions */ .make_datafrag = sctp_make_datafrag_empty, .assign_number = sctp_chunk_assign_ssn, .validate_data = sctp_validate_data, .ulpevent_data = sctp_ulpq_tail_data, .enqueue_event = do_ulpq_tail_event, .renege_events = sctp_ulpq_renege, .start_pd = sctp_ulpq_partial_delivery, .abort_pd = sctp_ulpq_abort_pd, /* FORWARD-TSN process functions */ .generate_ftsn = sctp_generate_fwdtsn, .validate_ftsn = sctp_validate_fwdtsn, .report_ftsn = sctp_report_fwdtsn, .handle_ftsn = sctp_handle_fwdtsn, }; static int do_sctp_enqueue_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event) { struct sk_buff_head temp; skb_queue_head_init(&temp); __skb_queue_tail(&temp, sctp_event2skb(event)); return sctp_enqueue_event(ulpq, &temp); } static struct sctp_stream_interleave sctp_stream_interleave_1 = { .data_chunk_len = sizeof(struct sctp_idata_chunk), .ftsn_chunk_len = sizeof(struct sctp_ifwdtsn_chunk), /* I-DATA process functions */ .make_datafrag = sctp_make_idatafrag_empty, .assign_number = sctp_chunk_assign_mid, .validate_data = sctp_validate_idata, .ulpevent_data = sctp_ulpevent_idata, .enqueue_event = do_sctp_enqueue_event, .renege_events = sctp_renege_events, .start_pd = sctp_intl_start_pd, .abort_pd = sctp_intl_abort_pd, /* I-FORWARD-TSN process functions */ .generate_ftsn = sctp_generate_iftsn, .validate_ftsn = sctp_validate_iftsn, .report_ftsn = sctp_report_iftsn, .handle_ftsn = sctp_handle_iftsn, }; void sctp_stream_interleave_init(struct sctp_stream *stream) { struct sctp_association *asoc; asoc = container_of(stream, struct sctp_association, stream); stream->si = asoc->peer.intl_capable ? &sctp_stream_interleave_1 : &sctp_stream_interleave_0; } |
| 246 127 190 239 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 | /* * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/random.h> #include <linux/export.h> #include "rds.h" /* * All of connection management is simplified by serializing it through * work queues that execute in a connection managing thread. * * TCP wants to send acks through sendpage() in response to data_ready(), * but it needs a process context to do so. * * The receive paths need to allocate but can't drop packets (!) so we have * a thread around to block allocating if the receive fast path sees an * allocation failure. */ /* Grand Unified Theory of connection life cycle: * At any point in time, the connection can be in one of these states: * DOWN, CONNECTING, UP, DISCONNECTING, ERROR * * The following transitions are possible: * ANY -> ERROR * UP -> DISCONNECTING * ERROR -> DISCONNECTING * DISCONNECTING -> DOWN * DOWN -> CONNECTING * CONNECTING -> UP * * Transition to state DISCONNECTING/DOWN: * - Inside the shutdown worker; synchronizes with xmit path * through RDS_IN_XMIT, and with connection management callbacks * via c_cm_lock. * * For receive callbacks, we rely on the underlying transport * (TCP, IB/RDMA) to provide the necessary synchronisation. */ struct workqueue_struct *rds_wq; EXPORT_SYMBOL_GPL(rds_wq); void rds_connect_path_complete(struct rds_conn_path *cp, int curr) { if (!rds_conn_path_transition(cp, curr, RDS_CONN_UP)) { printk(KERN_WARNING "%s: Cannot transition to state UP, " "current state is %d\n", __func__, atomic_read(&cp->cp_state)); rds_conn_path_drop(cp, false); return; } rdsdebug("conn %p for %pI6c to %pI6c complete\n", cp->cp_conn, &cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr); cp->cp_reconnect_jiffies = 0; set_bit(0, &cp->cp_conn->c_map_queued); rcu_read_lock(); if (!rds_destroy_pending(cp->cp_conn)) { queue_delayed_work(rds_wq, &cp->cp_send_w, 0); queue_delayed_work(rds_wq, &cp->cp_recv_w, 0); } rcu_read_unlock(); cp->cp_conn->c_proposed_version = RDS_PROTOCOL_VERSION; } EXPORT_SYMBOL_GPL(rds_connect_path_complete); void rds_connect_complete(struct rds_connection *conn) { rds_connect_path_complete(&conn->c_path[0], RDS_CONN_CONNECTING); } EXPORT_SYMBOL_GPL(rds_connect_complete); /* * This random exponential backoff is relied on to eventually resolve racing * connects. * * If connect attempts race then both parties drop both connections and come * here to wait for a random amount of time before trying again. Eventually * the backoff range will be so much greater than the time it takes to * establish a connection that one of the pair will establish the connection * before the other's random delay fires. * * Connection attempts that arrive while a connection is already established * are also considered to be racing connects. This lets a connection from * a rebooted machine replace an existing stale connection before the transport * notices that the connection has failed. * * We should *always* start with a random backoff; otherwise a broken connection * will always take several iterations to be re-established. */ void rds_queue_reconnect(struct rds_conn_path *cp) { unsigned long rand; struct rds_connection *conn = cp->cp_conn; rdsdebug("conn %p for %pI6c to %pI6c reconnect jiffies %lu\n", conn, &conn->c_laddr, &conn->c_faddr, cp->cp_reconnect_jiffies); /* let peer with smaller addr initiate reconnect, to avoid duels */ if (conn->c_trans->t_type == RDS_TRANS_TCP && rds_addr_cmp(&conn->c_laddr, &conn->c_faddr) >= 0) return; set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); if (cp->cp_reconnect_jiffies == 0) { cp->cp_reconnect_jiffies = rds_sysctl_reconnect_min_jiffies; rcu_read_lock(); if (!rds_destroy_pending(cp->cp_conn)) queue_delayed_work(rds_wq, &cp->cp_conn_w, 0); rcu_read_unlock(); return; } get_random_bytes(&rand, sizeof(rand)); rdsdebug("%lu delay %lu ceil conn %p for %pI6c -> %pI6c\n", rand % cp->cp_reconnect_jiffies, cp->cp_reconnect_jiffies, conn, &conn->c_laddr, &conn->c_faddr); rcu_read_lock(); if (!rds_destroy_pending(cp->cp_conn)) queue_delayed_work(rds_wq, &cp->cp_conn_w, rand % cp->cp_reconnect_jiffies); rcu_read_unlock(); cp->cp_reconnect_jiffies = min(cp->cp_reconnect_jiffies * 2, rds_sysctl_reconnect_max_jiffies); } void rds_connect_worker(struct work_struct *work) { struct rds_conn_path *cp = container_of(work, struct rds_conn_path, cp_conn_w.work); struct rds_connection *conn = cp->cp_conn; int ret; if (cp->cp_index > 0 && rds_addr_cmp(&cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr) >= 0) return; clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING); if (ret) { ret = conn->c_trans->conn_path_connect(cp); rdsdebug("conn %p for %pI6c to %pI6c dispatched, ret %d\n", conn, &conn->c_laddr, &conn->c_faddr, ret); if (ret) { if (rds_conn_path_transition(cp, RDS_CONN_CONNECTING, RDS_CONN_DOWN)) rds_queue_reconnect(cp); else rds_conn_path_error(cp, "connect failed\n"); } } } void rds_send_worker(struct work_struct *work) { struct rds_conn_path *cp = container_of(work, struct rds_conn_path, cp_send_w.work); int ret; if (rds_conn_path_state(cp) == RDS_CONN_UP) { clear_bit(RDS_LL_SEND_FULL, &cp->cp_flags); ret = rds_send_xmit(cp); cond_resched(); rdsdebug("conn %p ret %d\n", cp->cp_conn, ret); switch (ret) { case -EAGAIN: rds_stats_inc(s_send_immediate_retry); queue_delayed_work(rds_wq, &cp->cp_send_w, 0); break; case -ENOMEM: rds_stats_inc(s_send_delayed_retry); queue_delayed_work(rds_wq, &cp->cp_send_w, 2); break; default: break; } } } void rds_recv_worker(struct work_struct *work) { struct rds_conn_path *cp = container_of(work, struct rds_conn_path, cp_recv_w.work); int ret; if (rds_conn_path_state(cp) == RDS_CONN_UP) { ret = cp->cp_conn->c_trans->recv_path(cp); rdsdebug("conn %p ret %d\n", cp->cp_conn, ret); switch (ret) { case -EAGAIN: rds_stats_inc(s_recv_immediate_retry); queue_delayed_work(rds_wq, &cp->cp_recv_w, 0); break; case -ENOMEM: rds_stats_inc(s_recv_delayed_retry); queue_delayed_work(rds_wq, &cp->cp_recv_w, 2); break; default: break; } } } void rds_shutdown_worker(struct work_struct *work) { struct rds_conn_path *cp = container_of(work, struct rds_conn_path, cp_down_w); rds_conn_shutdown(cp); } void rds_threads_exit(void) { destroy_workqueue(rds_wq); } int rds_threads_init(void) { rds_wq = create_singlethread_workqueue("krdsd"); if (!rds_wq) return -ENOMEM; return 0; } /* Compare two IPv6 addresses. Return 0 if the two addresses are equal. * Return 1 if the first is greater. Return -1 if the second is greater. */ int rds_addr_cmp(const struct in6_addr *addr1, const struct in6_addr *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const __be64 *a1, *a2; u64 x, y; a1 = (__be64 *)addr1; a2 = (__be64 *)addr2; if (*a1 != *a2) { if (be64_to_cpu(*a1) < be64_to_cpu(*a2)) return -1; else return 1; } else { x = be64_to_cpu(*++a1); y = be64_to_cpu(*++a2); if (x < y) return -1; else if (x > y) return 1; else return 0; } #else u32 a, b; int i; for (i = 0; i < 4; i++) { if (addr1->s6_addr32[i] != addr2->s6_addr32[i]) { a = ntohl(addr1->s6_addr32[i]); b = ntohl(addr2->s6_addr32[i]); if (a < b) return -1; else if (a > b) return 1; } } return 0; #endif } EXPORT_SYMBOL_GPL(rds_addr_cmp); |
| 1 17 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2013 Trond Myklebust <Trond.Myklebust@netapp.com> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM nfs #if !defined(_TRACE_NFS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NFS_H #include <linux/tracepoint.h> #include <linux/iversion.h> #include <trace/misc/fs.h> #include <trace/misc/nfs.h> #include <trace/misc/sunrpc.h> #define nfs_show_cache_validity(v) \ __print_flags(v, "|", \ { NFS_INO_INVALID_DATA, "INVALID_DATA" }, \ { NFS_INO_INVALID_ATIME, "INVALID_ATIME" }, \ { NFS_INO_INVALID_ACCESS, "INVALID_ACCESS" }, \ { NFS_INO_INVALID_ACL, "INVALID_ACL" }, \ { NFS_INO_REVAL_FORCED, "REVAL_FORCED" }, \ { NFS_INO_INVALID_LABEL, "INVALID_LABEL" }, \ { NFS_INO_INVALID_CHANGE, "INVALID_CHANGE" }, \ { NFS_INO_INVALID_CTIME, "INVALID_CTIME" }, \ { NFS_INO_INVALID_MTIME, "INVALID_MTIME" }, \ { NFS_INO_INVALID_SIZE, "INVALID_SIZE" }, \ { NFS_INO_INVALID_OTHER, "INVALID_OTHER" }, \ { NFS_INO_DATA_INVAL_DEFER, "DATA_INVAL_DEFER" }, \ { NFS_INO_INVALID_BLOCKS, "INVALID_BLOCKS" }, \ { NFS_INO_INVALID_XATTR, "INVALID_XATTR" }, \ { NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \ { NFS_INO_INVALID_MODE, "INVALID_MODE" }) #define nfs_show_nfsi_flags(v) \ __print_flags(v, "|", \ { BIT(NFS_INO_STALE), "STALE" }, \ { BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \ { BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \ { BIT(NFS_INO_LAYOUTCOMMIT), "NEED_LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTCOMMITTING), "LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTSTATS), "LAYOUTSTATS" }, \ { BIT(NFS_INO_ODIRECT), "ODIRECT" }) DECLARE_EVENT_CLASS(nfs_inode_event, TP_PROTO( const struct inode *inode ), TP_ARGS(inode), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (unsigned long long)__entry->version ) ); DECLARE_EVENT_CLASS(nfs_inode_event_done, TP_PROTO( const struct inode *inode, int error ), TP_ARGS(inode, error), TP_STRUCT__entry( __field(unsigned long, error) __field(dev_t, dev) __field(u32, fhandle) __field(unsigned char, type) __field(u64, fileid) __field(u64, version) __field(loff_t, size) __field(unsigned long, nfsi_flags) __field(unsigned long, cache_validity) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->error = error < 0 ? -error : 0; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->type = nfs_umode_to_dtype(inode->i_mode); __entry->version = inode_peek_iversion_raw(inode); __entry->size = i_size_read(inode); __entry->nfsi_flags = nfsi->flags; __entry->cache_validity = nfsi->cache_validity; ), TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "type=%u (%s) version=%llu size=%lld " "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s)", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->type, show_fs_dirent_type(__entry->type), (unsigned long long)__entry->version, (long long)__entry->size, __entry->cache_validity, nfs_show_cache_validity(__entry->cache_validity), __entry->nfsi_flags, nfs_show_nfsi_flags(__entry->nfsi_flags) ) ); #define DEFINE_NFS_INODE_EVENT(name) \ DEFINE_EVENT(nfs_inode_event, name, \ TP_PROTO( \ const struct inode *inode \ ), \ TP_ARGS(inode)) #define DEFINE_NFS_INODE_EVENT_DONE(name) \ DEFINE_EVENT(nfs_inode_event_done, name, \ TP_PROTO( \ const struct inode *inode, \ int error \ ), \ TP_ARGS(inode, error)) DEFINE_NFS_INODE_EVENT(nfs_set_inode_stale); DEFINE_NFS_INODE_EVENT(nfs_refresh_inode_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_refresh_inode_exit); DEFINE_NFS_INODE_EVENT(nfs_revalidate_inode_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_revalidate_inode_exit); DEFINE_NFS_INODE_EVENT(nfs_invalidate_mapping_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_invalidate_mapping_exit); DEFINE_NFS_INODE_EVENT(nfs_getattr_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_getattr_exit); DEFINE_NFS_INODE_EVENT(nfs_setattr_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_setattr_exit); DEFINE_NFS_INODE_EVENT(nfs_writeback_inode_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_inode_exit); DEFINE_NFS_INODE_EVENT(nfs_fsync_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit); DEFINE_NFS_INODE_EVENT(nfs_access_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_set_cache_invalid); DEFINE_NFS_INODE_EVENT(nfs_readdir_force_readdirplus); DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_cache_fill_done); DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_uncached_done); TRACE_EVENT(nfs_access_exit, TP_PROTO( const struct inode *inode, unsigned int mask, unsigned int permitted, int error ), TP_ARGS(inode, mask, permitted, error), TP_STRUCT__entry( __field(unsigned long, error) __field(dev_t, dev) __field(u32, fhandle) __field(unsigned char, type) __field(u64, fileid) __field(u64, version) __field(loff_t, size) __field(unsigned long, nfsi_flags) __field(unsigned long, cache_validity) __field(unsigned int, mask) __field(unsigned int, permitted) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->error = error < 0 ? -error : 0; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->type = nfs_umode_to_dtype(inode->i_mode); __entry->version = inode_peek_iversion_raw(inode); __entry->size = i_size_read(inode); __entry->nfsi_flags = nfsi->flags; __entry->cache_validity = nfsi->cache_validity; __entry->mask = mask; __entry->permitted = permitted; ), TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "type=%u (%s) version=%llu size=%lld " "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s) " "mask=0x%x permitted=0x%x", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->type, show_fs_dirent_type(__entry->type), (unsigned long long)__entry->version, (long long)__entry->size, __entry->cache_validity, nfs_show_cache_validity(__entry->cache_validity), __entry->nfsi_flags, nfs_show_nfsi_flags(__entry->nfsi_flags), __entry->mask, __entry->permitted ) ); DECLARE_EVENT_CLASS(nfs_update_size_class, TP_PROTO( const struct inode *inode, loff_t new_size ), TP_ARGS(inode, new_size), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) __field(loff_t, cur_size) __field(loff_t, new_size) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->fileid = nfsi->fileid; __entry->version = inode_peek_iversion_raw(inode); __entry->cur_size = i_size_read(inode); __entry->new_size = new_size; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu cursize=%lld newsize=%lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->cur_size, __entry->new_size ) ); #define DEFINE_NFS_UPDATE_SIZE_EVENT(name) \ DEFINE_EVENT(nfs_update_size_class, nfs_size_##name, \ TP_PROTO( \ const struct inode *inode, \ loff_t new_size \ ), \ TP_ARGS(inode, new_size)) DEFINE_NFS_UPDATE_SIZE_EVENT(truncate); DEFINE_NFS_UPDATE_SIZE_EVENT(wcc); DEFINE_NFS_UPDATE_SIZE_EVENT(update); DEFINE_NFS_UPDATE_SIZE_EVENT(grow); DECLARE_EVENT_CLASS(nfs_inode_range_event, TP_PROTO( const struct inode *inode, loff_t range_start, loff_t range_end ), TP_ARGS(inode, range_start, range_end), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) __field(loff_t, range_start) __field(loff_t, range_end) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->fileid = nfsi->fileid; __entry->version = inode_peek_iversion_raw(inode); __entry->range_start = range_start; __entry->range_end = range_end; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " "range=[%lld, %lld]", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->range_start, __entry->range_end ) ); #define DEFINE_NFS_INODE_RANGE_EVENT(name) \ DEFINE_EVENT(nfs_inode_range_event, name, \ TP_PROTO( \ const struct inode *inode, \ loff_t range_start, \ loff_t range_end \ ), \ TP_ARGS(inode, range_start, range_end)) DEFINE_NFS_INODE_RANGE_EVENT(nfs_readdir_invalidate_cache_range); DECLARE_EVENT_CLASS(nfs_readdir_event, TP_PROTO( const struct file *file, const __be32 *verifier, u64 cookie, pgoff_t page_index, unsigned int dtsize ), TP_ARGS(file, verifier, cookie, page_index, dtsize), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) __array(char, verifier, NFS4_VERIFIER_SIZE) __field(u64, cookie) __field(pgoff_t, index) __field(unsigned int, dtsize) ), TP_fast_assign( const struct inode *dir = file_inode(file); const struct nfs_inode *nfsi = NFS_I(dir); __entry->dev = dir->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(dir); if (cookie != 0) memcpy(__entry->verifier, verifier, NFS4_VERIFIER_SIZE); else memset(__entry->verifier, 0, NFS4_VERIFIER_SIZE); __entry->cookie = cookie; __entry->index = page_index; __entry->dtsize = dtsize; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " "cookie=%s:0x%llx cache_index=%lu dtsize=%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, show_nfs4_verifier(__entry->verifier), (unsigned long long)__entry->cookie, __entry->index, __entry->dtsize ) ); #define DEFINE_NFS_READDIR_EVENT(name) \ DEFINE_EVENT(nfs_readdir_event, name, \ TP_PROTO( \ const struct file *file, \ const __be32 *verifier, \ u64 cookie, \ pgoff_t page_index, \ unsigned int dtsize \ ), \ TP_ARGS(file, verifier, cookie, page_index, dtsize)) DEFINE_NFS_READDIR_EVENT(nfs_readdir_cache_fill); DEFINE_NFS_READDIR_EVENT(nfs_readdir_uncached); DECLARE_EVENT_CLASS(nfs_lookup_event, TP_PROTO( const struct inode *dir, const struct dentry *dentry, unsigned int flags ), TP_ARGS(dir, dentry, flags), TP_STRUCT__entry( __field(unsigned long, flags) __field(dev_t, dev) __field(u64, dir) __field(u64, fileid) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; __entry->fileid = d_is_negative(dentry) ? 0 : NFS_FILEID(d_inode(dentry)); __assign_str(name); ), TP_printk( "flags=0x%lx (%s) name=%02x:%02x:%llu/%s fileid=%llu", __entry->flags, show_fs_lookup_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name), __entry->fileid ) ); #define DEFINE_NFS_LOOKUP_EVENT(name) \ DEFINE_EVENT(nfs_lookup_event, name, \ TP_PROTO( \ const struct inode *dir, \ const struct dentry *dentry, \ unsigned int flags \ ), \ TP_ARGS(dir, dentry, flags)) DECLARE_EVENT_CLASS(nfs_lookup_event_done, TP_PROTO( const struct inode *dir, const struct dentry *dentry, unsigned int flags, int error ), TP_ARGS(dir, dentry, flags, error), TP_STRUCT__entry( __field(unsigned long, error) __field(unsigned long, flags) __field(dev_t, dev) __field(u64, dir) __field(u64, fileid) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->error = error < 0 ? -error : 0; __entry->flags = flags; __entry->fileid = d_is_negative(dentry) ? 0 : NFS_FILEID(d_inode(dentry)); __assign_str(name); ), TP_printk( "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s fileid=%llu", -__entry->error, show_nfs_status(__entry->error), __entry->flags, show_fs_lookup_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name), __entry->fileid ) ); #define DEFINE_NFS_LOOKUP_EVENT_DONE(name) \ DEFINE_EVENT(nfs_lookup_event_done, name, \ TP_PROTO( \ const struct inode *dir, \ const struct dentry *dentry, \ unsigned int flags, \ int error \ ), \ TP_ARGS(dir, dentry, flags, error)) DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_enter); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_exit); DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit); DEFINE_NFS_LOOKUP_EVENT(nfs_readdir_lookup); DEFINE_NFS_LOOKUP_EVENT(nfs_readdir_lookup_revalidate_failed); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_readdir_lookup_revalidate); TRACE_EVENT(nfs_atomic_open_enter, TP_PROTO( const struct inode *dir, const struct nfs_open_context *ctx, unsigned int flags ), TP_ARGS(dir, ctx, flags), TP_STRUCT__entry( __field(unsigned long, flags) __field(unsigned long, fmode) __field(dev_t, dev) __field(u64, dir) __string(name, ctx->dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; __entry->fmode = (__force unsigned long)ctx->mode; __assign_str(name); ), TP_printk( "flags=0x%lx (%s) fmode=%s name=%02x:%02x:%llu/%s", __entry->flags, show_fs_fcntl_open_flags(__entry->flags), show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); TRACE_EVENT(nfs_atomic_open_exit, TP_PROTO( const struct inode *dir, const struct nfs_open_context *ctx, unsigned int flags, int error ), TP_ARGS(dir, ctx, flags, error), TP_STRUCT__entry( __field(unsigned long, error) __field(unsigned long, flags) __field(unsigned long, fmode) __field(dev_t, dev) __field(u64, dir) __string(name, ctx->dentry->d_name.name) ), TP_fast_assign( __entry->error = -error; __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; __entry->fmode = (__force unsigned long)ctx->mode; __assign_str(name); ), TP_printk( "error=%ld (%s) flags=0x%lx (%s) fmode=%s " "name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), __entry->flags, show_fs_fcntl_open_flags(__entry->flags), show_fs_fmode_flags(__entry->fmode), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); TRACE_EVENT(nfs_create_enter, TP_PROTO( const struct inode *dir, const struct dentry *dentry, unsigned int flags ), TP_ARGS(dir, dentry, flags), TP_STRUCT__entry( __field(unsigned long, flags) __field(dev_t, dev) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; __assign_str(name); ), TP_printk( "flags=0x%lx (%s) name=%02x:%02x:%llu/%s", __entry->flags, show_fs_fcntl_open_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); TRACE_EVENT(nfs_create_exit, TP_PROTO( const struct inode *dir, const struct dentry *dentry, unsigned int flags, int error ), TP_ARGS(dir, dentry, flags, error), TP_STRUCT__entry( __field(unsigned long, error) __field(unsigned long, flags) __field(dev_t, dev) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->error = -error; __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->flags = flags; __assign_str(name); ), TP_printk( "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), __entry->flags, show_fs_fcntl_open_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); DECLARE_EVENT_CLASS(nfs_directory_event, TP_PROTO( const struct inode *dir, const struct dentry *dentry ), TP_ARGS(dir, dentry), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __assign_str(name); ), TP_printk( "name=%02x:%02x:%llu/%s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); #define DEFINE_NFS_DIRECTORY_EVENT(name) \ DEFINE_EVENT(nfs_directory_event, name, \ TP_PROTO( \ const struct inode *dir, \ const struct dentry *dentry \ ), \ TP_ARGS(dir, dentry)) DECLARE_EVENT_CLASS(nfs_directory_event_done, TP_PROTO( const struct inode *dir, const struct dentry *dentry, int error ), TP_ARGS(dir, dentry, error), TP_STRUCT__entry( __field(unsigned long, error) __field(dev_t, dev) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->error = error < 0 ? -error : 0; __assign_str(name); ), TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); #define DEFINE_NFS_DIRECTORY_EVENT_DONE(name) \ DEFINE_EVENT(nfs_directory_event_done, name, \ TP_PROTO( \ const struct inode *dir, \ const struct dentry *dentry, \ int error \ ), \ TP_ARGS(dir, dentry, error)) DEFINE_NFS_DIRECTORY_EVENT(nfs_mknod_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_mknod_exit); DEFINE_NFS_DIRECTORY_EVENT(nfs_mkdir_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_mkdir_exit); DEFINE_NFS_DIRECTORY_EVENT(nfs_rmdir_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_rmdir_exit); DEFINE_NFS_DIRECTORY_EVENT(nfs_remove_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_remove_exit); DEFINE_NFS_DIRECTORY_EVENT(nfs_unlink_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_unlink_exit); DEFINE_NFS_DIRECTORY_EVENT(nfs_symlink_enter); DEFINE_NFS_DIRECTORY_EVENT_DONE(nfs_symlink_exit); TRACE_EVENT(nfs_link_enter, TP_PROTO( const struct inode *inode, const struct inode *dir, const struct dentry *dentry ), TP_ARGS(inode, dir, dentry), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, fileid) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->dir = NFS_FILEID(dir); __assign_str(name); ), TP_printk( "fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fileid, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); TRACE_EVENT(nfs_link_exit, TP_PROTO( const struct inode *inode, const struct inode *dir, const struct dentry *dentry, int error ), TP_ARGS(inode, dir, dentry, error), TP_STRUCT__entry( __field(unsigned long, error) __field(dev_t, dev) __field(u64, fileid) __field(u64, dir) __string(name, dentry->d_name.name) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->fileid = NFS_FILEID(inode); __entry->dir = NFS_FILEID(dir); __entry->error = error < 0 ? -error : 0; __assign_str(name); ), TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fileid, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); DECLARE_EVENT_CLASS(nfs_rename_event, TP_PROTO( const struct inode *old_dir, const struct dentry *old_dentry, const struct inode *new_dir, const struct dentry *new_dentry ), TP_ARGS(old_dir, old_dentry, new_dir, new_dentry), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, old_dir) __field(u64, new_dir) __string(old_name, old_dentry->d_name.name) __string(new_name, new_dentry->d_name.name) ), TP_fast_assign( __entry->dev = old_dir->i_sb->s_dev; __entry->old_dir = NFS_FILEID(old_dir); __entry->new_dir = NFS_FILEID(new_dir); __assign_str(old_name); __assign_str(new_name); ), TP_printk( "old_name=%02x:%02x:%llu/%s new_name=%02x:%02x:%llu/%s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->old_dir, __get_str(old_name), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->new_dir, __get_str(new_name) ) ); #define DEFINE_NFS_RENAME_EVENT(name) \ DEFINE_EVENT(nfs_rename_event, name, \ TP_PROTO( \ const struct inode *old_dir, \ const struct dentry *old_dentry, \ const struct inode *new_dir, \ const struct dentry *new_dentry \ ), \ TP_ARGS(old_dir, old_dentry, new_dir, new_dentry)) DECLARE_EVENT_CLASS(nfs_rename_event_done, TP_PROTO( const struct inode *old_dir, const struct dentry *old_dentry, const struct inode *new_dir, const struct dentry *new_dentry, int error ), TP_ARGS(old_dir, old_dentry, new_dir, new_dentry, error), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, error) __field(u64, old_dir) __string(old_name, old_dentry->d_name.name) __field(u64, new_dir) __string(new_name, new_dentry->d_name.name) ), TP_fast_assign( __entry->dev = old_dir->i_sb->s_dev; __entry->error = -error; __entry->old_dir = NFS_FILEID(old_dir); __entry->new_dir = NFS_FILEID(new_dir); __assign_str(old_name); __assign_str(new_name); ), TP_printk( "error=%ld (%s) old_name=%02x:%02x:%llu/%s " "new_name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->old_dir, __get_str(old_name), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->new_dir, __get_str(new_name) ) ); #define DEFINE_NFS_RENAME_EVENT_DONE(name) \ DEFINE_EVENT(nfs_rename_event_done, name, \ TP_PROTO( \ const struct inode *old_dir, \ const struct dentry *old_dentry, \ const struct inode *new_dir, \ const struct dentry *new_dentry, \ int error \ ), \ TP_ARGS(old_dir, old_dentry, new_dir, \ new_dentry, error)) DEFINE_NFS_RENAME_EVENT(nfs_rename_enter); DEFINE_NFS_RENAME_EVENT_DONE(nfs_rename_exit); DEFINE_NFS_RENAME_EVENT_DONE(nfs_async_rename_done); TRACE_EVENT(nfs_sillyrename_unlink, TP_PROTO( const struct nfs_unlinkdata *data, int error ), TP_ARGS(data, error), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, error) __field(u64, dir) __dynamic_array(char, name, data->args.name.len + 1) ), TP_fast_assign( struct inode *dir = d_inode(data->dentry->d_parent); size_t len = data->args.name.len; __entry->dev = dir->i_sb->s_dev; __entry->dir = NFS_FILEID(dir); __entry->error = -error; memcpy(__get_str(name), data->args.name.name, len); __get_str(name)[len] = 0; ), TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) ) ); DECLARE_EVENT_CLASS(nfs_folio_event, TP_PROTO( const struct inode *inode, loff_t offset, size_t count ), TP_ARGS(inode, offset, count), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) __field(loff_t, offset) __field(size_t, count) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); __entry->offset = offset, __entry->count = count; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " "offset=%lld count=%zu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->offset, __entry->count ) ); #define DEFINE_NFS_FOLIO_EVENT(name) \ DEFINE_EVENT(nfs_folio_event, name, \ TP_PROTO( \ const struct inode *inode, \ loff_t offset, \ size_t count \ ), \ TP_ARGS(inode, offset, count)) DECLARE_EVENT_CLASS(nfs_folio_event_done, TP_PROTO( const struct inode *inode, loff_t offset, size_t count, int ret ), TP_ARGS(inode, offset, count, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(int, ret) __field(u64, fileid) __field(u64, version) __field(loff_t, offset) __field(size_t, count) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); __entry->offset = offset, __entry->count = count, __entry->ret = ret; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " "offset=%lld count=%zu ret=%d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->offset, __entry->count, __entry->ret ) ); #define DEFINE_NFS_FOLIO_EVENT_DONE(name) \ DEFINE_EVENT(nfs_folio_event_done, name, \ TP_PROTO( \ const struct inode *inode, \ loff_t offset, \ size_t count, \ int ret \ ), \ TP_ARGS(inode, offset, count, ret)) DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done); DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_done); DEFINE_NFS_FOLIO_EVENT(nfs_invalidate_folio); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_launder_folio_done); TRACE_EVENT(nfs_aop_readahead, TP_PROTO( const struct inode *inode, loff_t pos, unsigned int nr_pages ), TP_ARGS(inode, pos, nr_pages), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(u64, version) __field(loff_t, offset) __field(unsigned int, nr_pages) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); __entry->offset = pos; __entry->nr_pages = nr_pages; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu offset=%lld nr_pages=%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->offset, __entry->nr_pages ) ); TRACE_EVENT(nfs_aop_readahead_done, TP_PROTO( const struct inode *inode, unsigned int nr_pages, int ret ), TP_ARGS(inode, nr_pages, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(int, ret) __field(u64, fileid) __field(u64, version) __field(loff_t, offset) __field(unsigned int, nr_pages) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); __entry->nr_pages = nr_pages; __entry->ret = ret; ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu nr_pages=%u ret=%d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->version, __entry->nr_pages, __entry->ret ) ); TRACE_EVENT(nfs_initiate_read, TP_PROTO( const struct nfs_pgio_header *hdr ), TP_ARGS(hdr), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, count) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; __entry->offset = hdr->args.offset; __entry->count = hdr->args.count; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->count ) ); TRACE_EVENT(nfs_readpage_done, TP_PROTO( const struct rpc_task *task, const struct nfs_pgio_header *hdr ), TP_ARGS(task, hdr), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, arg_count) __field(u32, res_count) __field(bool, eof) __field(int, error) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; __entry->eof = hdr->res.eof; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u res=%u%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, __entry->eof ? " eof" : "" ) ); TRACE_EVENT(nfs_readpage_short, TP_PROTO( const struct rpc_task *task, const struct nfs_pgio_header *hdr ), TP_ARGS(task, hdr), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, arg_count) __field(u32, res_count) __field(bool, eof) __field(int, error) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; __entry->eof = hdr->res.eof; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u res=%u%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, __entry->eof ? " eof" : "" ) ); TRACE_EVENT(nfs_pgio_error, TP_PROTO( const struct nfs_pgio_header *hdr, int error, loff_t pos ), TP_ARGS(hdr, error, pos), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, arg_count) __field(u32, res_count) __field(loff_t, pos) __field(int, error) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; __entry->error = error; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk("error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u res=%u pos=%llu", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, __entry->pos ) ); TRACE_EVENT(nfs_initiate_write, TP_PROTO( const struct nfs_pgio_header *hdr ), TP_ARGS(hdr), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, count) __field(unsigned long, stable) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; __entry->offset = hdr->args.offset; __entry->count = hdr->args.count; __entry->stable = hdr->args.stable; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u stable=%s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->count, show_nfs_stable_how(__entry->stable) ) ); TRACE_EVENT(nfs_writeback_done, TP_PROTO( const struct rpc_task *task, const struct nfs_pgio_header *hdr ), TP_ARGS(task, hdr), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, arg_count) __field(u32, res_count) __field(int, error) __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), TP_fast_assign( const struct inode *inode = hdr->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = hdr->args.fh ? hdr->args.fh : &nfsi->fh; const struct nfs_writeverf *verf = hdr->res.verf; __entry->error = task->tk_status; __entry->offset = hdr->args.offset; __entry->arg_count = hdr->args.count; __entry->res_count = hdr->res.count; __entry->stable = verf->committed; memcpy(__entry->verifier, &verf->verifier, NFS4_VERIFIER_SIZE); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u res=%u stable=%s " "verifier=%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, show_nfs_stable_how(__entry->stable), show_nfs4_verifier(__entry->verifier) ) ); DECLARE_EVENT_CLASS(nfs_page_error_class, TP_PROTO( const struct inode *inode, const struct nfs_page *req, int error ), TP_ARGS(inode, req, error), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(unsigned int, count) __field(int, error) ), TP_fast_assign( const struct nfs_inode *nfsi = NFS_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->offset = req_offset(req); __entry->count = req->wb_bytes; __entry->error = error; ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->offset, __entry->count ) ); #define DEFINE_NFS_PAGEERR_EVENT(name) \ DEFINE_EVENT(nfs_page_error_class, name, \ TP_PROTO( \ const struct inode *inode, \ const struct nfs_page *req, \ int error \ ), \ TP_ARGS(inode, req, error)) DEFINE_NFS_PAGEERR_EVENT(nfs_write_error); DEFINE_NFS_PAGEERR_EVENT(nfs_comp_error); DEFINE_NFS_PAGEERR_EVENT(nfs_commit_error); TRACE_EVENT(nfs_initiate_commit, TP_PROTO( const struct nfs_commit_data *data ), TP_ARGS(data), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(u32, count) ), TP_fast_assign( const struct inode *inode = data->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = data->args.fh ? data->args.fh : &nfsi->fh; __entry->offset = data->args.offset; __entry->count = data->args.count; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->count ) ); TRACE_EVENT(nfs_commit_done, TP_PROTO( const struct rpc_task *task, const struct nfs_commit_data *data ), TP_ARGS(task, data), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) __field(loff_t, offset) __field(int, error) __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), TP_fast_assign( const struct inode *inode = data->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = data->args.fh ? data->args.fh : &nfsi->fh; const struct nfs_writeverf *verf = data->res.verf; __entry->error = task->tk_status; __entry->offset = data->args.offset; __entry->stable = verf->committed; memcpy(__entry->verifier, &verf->verifier, NFS4_VERIFIER_SIZE); __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld stable=%s verifier=%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, show_nfs_stable_how(__entry->stable), show_nfs4_verifier(__entry->verifier) ) ); #define nfs_show_direct_req_flags(v) \ __print_flags(v, "|", \ { NFS_ODIRECT_DO_COMMIT, "DO_COMMIT" }, \ { NFS_ODIRECT_RESCHED_WRITES, "RESCHED_WRITES" }, \ { NFS_ODIRECT_SHOULD_DIRTY, "SHOULD DIRTY" }, \ { NFS_ODIRECT_DONE, "DONE" } ) DECLARE_EVENT_CLASS(nfs_direct_req_class, TP_PROTO( const struct nfs_direct_req *dreq ), TP_ARGS(dreq), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, fileid) __field(u32, fhandle) __field(loff_t, offset) __field(ssize_t, count) __field(ssize_t, error) __field(int, flags) ), TP_fast_assign( const struct inode *inode = dreq->inode; const struct nfs_inode *nfsi = NFS_I(inode); const struct nfs_fh *fh = &nfsi->fh; __entry->dev = inode->i_sb->s_dev; __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(fh); __entry->offset = dreq->io_start; __entry->count = dreq->count; __entry->error = dreq->error; __entry->flags = dreq->flags; ), TP_printk( "error=%zd fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%zd flags=%s", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->offset, __entry->count, nfs_show_direct_req_flags(__entry->flags) ) ); #define DEFINE_NFS_DIRECT_REQ_EVENT(name) \ DEFINE_EVENT(nfs_direct_req_class, name, \ TP_PROTO( \ const struct nfs_direct_req *dreq \ ), \ TP_ARGS(dreq)) DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_commit_complete); DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_resched_write); DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_complete); DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_completion); DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_schedule_iovec); DEFINE_NFS_DIRECT_REQ_EVENT(nfs_direct_write_reschedule_io); TRACE_EVENT(nfs_fh_to_dentry, TP_PROTO( const struct super_block *sb, const struct nfs_fh *fh, u64 fileid, int error ), TP_ARGS(sb, fh, fileid, error), TP_STRUCT__entry( __field(int, error) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) ), TP_fast_assign( __entry->error = error; __entry->dev = sb->s_dev; __entry->fileid = fileid; __entry->fhandle = nfs_fhandle_hash(fh); ), TP_printk( "error=%d fileid=%02x:%02x:%llu fhandle=0x%08x ", __entry->error, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle ) ); TRACE_EVENT(nfs_mount_assign, TP_PROTO( const char *option, const char *value ), TP_ARGS(option, value), TP_STRUCT__entry( __string(option, option) __string(value, value) ), TP_fast_assign( __assign_str(option); __assign_str(value); ), TP_printk("option %s=%s", __get_str(option), __get_str(value) ) ); TRACE_EVENT(nfs_mount_option, TP_PROTO( const struct fs_parameter *param ), TP_ARGS(param), TP_STRUCT__entry( __string(option, param->key) ), TP_fast_assign( __assign_str(option); ), TP_printk("option %s", __get_str(option)) ); TRACE_EVENT(nfs_mount_path, TP_PROTO( const char *path ), TP_ARGS(path), TP_STRUCT__entry( __string(path, path) ), TP_fast_assign( __assign_str(path); ), TP_printk("path='%s'", __get_str(path)) ); DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, int error ), TP_ARGS(xdr, error), TP_STRUCT__entry( __field(unsigned int, task_id) __field(unsigned int, client_id) __field(u32, xid) __field(int, version) __field(unsigned long, error) __string(program, xdr->rqst->rq_task->tk_client->cl_program->name) __string(procedure, xdr->rqst->rq_task->tk_msg.rpc_proc->p_name) ), TP_fast_assign( const struct rpc_rqst *rqstp = xdr->rqst; const struct rpc_task *task = rqstp->rq_task; __entry->task_id = task->tk_pid; __entry->client_id = task->tk_client->cl_clid; __entry->xid = be32_to_cpu(rqstp->rq_xid); __entry->version = task->tk_client->cl_vers; __entry->error = error; __assign_str(program); __assign_str(procedure); ), TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x %sv%d %s error=%ld (%s)", __entry->task_id, __entry->client_id, __entry->xid, __get_str(program), __entry->version, __get_str(procedure), -__entry->error, show_nfs_status(__entry->error) ) ); #define DEFINE_NFS_XDR_EVENT(name) \ DEFINE_EVENT(nfs_xdr_event, name, \ TP_PROTO( \ const struct xdr_stream *xdr, \ int error \ ), \ TP_ARGS(xdr, error)) DEFINE_NFS_XDR_EVENT(nfs_xdr_status); DEFINE_NFS_XDR_EVENT(nfs_xdr_bad_filehandle); #endif /* _TRACE_NFS_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE nfstrace /* This part must be outside protection */ #include <trace/define_trace.h> |
| 4 1 3 5 4 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 2000-2001 Svenning Soerensen <svenning@post5.tele.dk> * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> */ #include <linux/ip.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/ipv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_nat.h> static unsigned int netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct nf_nat_range2 *range = par->targinfo; struct nf_nat_range2 newrange; struct nf_conn *ct; enum ip_conntrack_info ctinfo; union nf_inet_addr new_addr, netmask; unsigned int i; ct = nf_ct_get(skb, &ctinfo); for (i = 0; i < ARRAY_SIZE(range->min_addr.ip6); i++) netmask.ip6[i] = ~(range->min_addr.ip6[i] ^ range->max_addr.ip6[i]); if (xt_hooknum(par) == NF_INET_PRE_ROUTING || xt_hooknum(par) == NF_INET_LOCAL_OUT) new_addr.in6 = ipv6_hdr(skb)->daddr; else new_addr.in6 = ipv6_hdr(skb)->saddr; for (i = 0; i < ARRAY_SIZE(new_addr.ip6); i++) { new_addr.ip6[i] &= ~netmask.ip6[i]; new_addr.ip6[i] |= range->min_addr.ip6[i] & netmask.ip6[i]; } newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; newrange.min_addr = new_addr; newrange.max_addr = new_addr; newrange.min_proto = range->min_proto; newrange.max_proto = range->max_proto; return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(xt_hooknum(par))); } static int netmap_tg6_checkentry(const struct xt_tgchk_param *par) { const struct nf_nat_range2 *range = par->targinfo; if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) return -EINVAL; return nf_ct_netns_get(par->net, par->family); } static void netmap_tg_destroy(const struct xt_tgdtor_param *par) { nf_ct_netns_put(par->net, par->family); } static unsigned int netmap_tg4(struct sk_buff *skb, const struct xt_action_param *par) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; __be32 new_ip, netmask; const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; struct nf_nat_range2 newrange; WARN_ON(xt_hooknum(par) != NF_INET_PRE_ROUTING && xt_hooknum(par) != NF_INET_POST_ROUTING && xt_hooknum(par) != NF_INET_LOCAL_OUT && xt_hooknum(par) != NF_INET_LOCAL_IN); ct = nf_ct_get(skb, &ctinfo); netmask = ~(mr->range[0].min_ip ^ mr->range[0].max_ip); if (xt_hooknum(par) == NF_INET_PRE_ROUTING || xt_hooknum(par) == NF_INET_LOCAL_OUT) new_ip = ip_hdr(skb)->daddr & ~netmask; else new_ip = ip_hdr(skb)->saddr & ~netmask; new_ip |= mr->range[0].min_ip & netmask; memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); newrange.flags = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS; newrange.min_addr.ip = new_ip; newrange.max_addr.ip = new_ip; newrange.min_proto = mr->range[0].min; newrange.max_proto = mr->range[0].max; /* Hand modified range to generic setup. */ return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(xt_hooknum(par))); } static int netmap_tg4_check(const struct xt_tgchk_param *par) { const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; if (!(mr->range[0].flags & NF_NAT_RANGE_MAP_IPS)) { pr_debug("bad MAP_IPS.\n"); return -EINVAL; } if (mr->rangesize != 1) { pr_debug("bad rangesize %u.\n", mr->rangesize); return -EINVAL; } return nf_ct_netns_get(par->net, par->family); } static struct xt_target netmap_tg_reg[] __read_mostly = { { .name = "NETMAP", .family = NFPROTO_IPV6, .revision = 0, .target = netmap_tg6, .targetsize = sizeof(struct nf_nat_range), .table = "nat", .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .checkentry = netmap_tg6_checkentry, .destroy = netmap_tg_destroy, .me = THIS_MODULE, }, { .name = "NETMAP", .family = NFPROTO_IPV4, .revision = 0, .target = netmap_tg4, .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), .table = "nat", .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .checkentry = netmap_tg4_check, .destroy = netmap_tg_destroy, .me = THIS_MODULE, }, }; static int __init netmap_tg_init(void) { return xt_register_targets(netmap_tg_reg, ARRAY_SIZE(netmap_tg_reg)); } static void netmap_tg_exit(void) { xt_unregister_targets(netmap_tg_reg, ARRAY_SIZE(netmap_tg_reg)); } module_init(netmap_tg_init); module_exit(netmap_tg_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Xtables: 1:1 NAT mapping of subnets"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS("ip6t_NETMAP"); MODULE_ALIAS("ipt_NETMAP"); |
| 123 1 11 67 41 3 43 3 41 44 1648 1604 45 6 632 631 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/gen_estimator.c Simple rate estimator. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Eric Dumazet <edumazet@google.com> * * Changes: * Jamal Hadi Salim - moved it to net/core and reshulfed * names to make it usable in general net subsystem. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/seqlock.h> #include <net/sock.h> #include <net/gen_stats.h> /* This code is NOT intended to be used for statistics collection, * its purpose is to provide a base for statistical multiplexing * for controlled load service. * If you need only statistics, run a user level daemon which * periodically reads byte counters. */ struct net_rate_estimator { struct gnet_stats_basic_sync *bstats; spinlock_t *stats_lock; bool running; struct gnet_stats_basic_sync __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ seqcount_t seq; u64 last_packets; u64 last_bytes; u64 avpps; u64 avbps; unsigned long next_jiffies; struct timer_list timer; struct rcu_head rcu; }; static void est_fetch_counters(struct net_rate_estimator *e, struct gnet_stats_basic_sync *b) { gnet_stats_basic_sync_init(b); if (e->stats_lock) spin_lock(e->stats_lock); gnet_stats_add_basic(b, e->cpu_bstats, e->bstats, e->running); if (e->stats_lock) spin_unlock(e->stats_lock); } static void est_timer(struct timer_list *t) { struct net_rate_estimator *est = from_timer(est, t, timer); struct gnet_stats_basic_sync b; u64 b_bytes, b_packets; u64 rate, brate; est_fetch_counters(est, &b); b_bytes = u64_stats_read(&b.bytes); b_packets = u64_stats_read(&b.packets); brate = (b_bytes - est->last_bytes) << (10 - est->intvl_log); brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log); rate = (b_packets - est->last_packets) << (10 - est->intvl_log); rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); write_seqcount_begin(&est->seq); est->avbps += brate; est->avpps += rate; write_seqcount_end(&est->seq); est->last_bytes = b_bytes; est->last_packets = b_packets; est->next_jiffies += ((HZ/4) << est->intvl_log); if (unlikely(time_after_eq(jiffies, est->next_jiffies))) { /* Ouch... timer was delayed. */ est->next_jiffies = jiffies + 1; } mod_timer(&est->timer, est->next_jiffies); } /** * gen_new_estimator - create a new rate estimator * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path * @running: true if @bstats represents a running qdisc, thus @bstats' * internal values might change during basic reads. Only used * if @bstats_cpu is NULL * @opt: rate estimator configuration TLV * * Creates a new rate estimator with &bstats as source and &rate_est * as destination. A new timer with the interval specified in the * configuration TLV is created. Upon each interval, the latest statistics * will be read from &bstats and the estimated rate will be stored in * &rate_est with the statistics lock grabbed during this period. * * Returns 0 on success or a negative error code. * */ int gen_new_estimator(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, bool running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); struct net_rate_estimator *old, *est; struct gnet_stats_basic_sync b; int intvl_log; if (nla_len(opt) < sizeof(*parm)) return -EINVAL; /* allowed timer periods are : * -2 : 250ms, -1 : 500ms, 0 : 1 sec * 1 : 2 sec, 2 : 4 sec, 3 : 8 sec */ if (parm->interval < -2 || parm->interval > 3) return -EINVAL; if (parm->ewma_log == 0 || parm->ewma_log >= 31) return -EINVAL; est = kzalloc(sizeof(*est), GFP_KERNEL); if (!est) return -ENOBUFS; seqcount_init(&est->seq); intvl_log = parm->interval + 2; est->bstats = bstats; est->stats_lock = lock; est->running = running; est->ewma_log = parm->ewma_log; est->intvl_log = intvl_log; est->cpu_bstats = cpu_bstats; if (lock) local_bh_disable(); est_fetch_counters(est, &b); if (lock) local_bh_enable(); est->last_bytes = u64_stats_read(&b.bytes); est->last_packets = u64_stats_read(&b.packets); if (lock) spin_lock_bh(lock); old = rcu_dereference_protected(*rate_est, 1); if (old) { del_timer_sync(&old->timer); est->avbps = old->avbps; est->avpps = old->avpps; } est->next_jiffies = jiffies + ((HZ/4) << intvl_log); timer_setup(&est->timer, est_timer, 0); mod_timer(&est->timer, est->next_jiffies); rcu_assign_pointer(*rate_est, est); if (lock) spin_unlock_bh(lock); if (old) kfree_rcu(old, rcu); return 0; } EXPORT_SYMBOL(gen_new_estimator); /** * gen_kill_estimator - remove a rate estimator * @rate_est: rate estimator * * Removes the rate estimator. * */ void gen_kill_estimator(struct net_rate_estimator __rcu **rate_est) { struct net_rate_estimator *est; est = unrcu_pointer(xchg(rate_est, NULL)); if (est) { timer_shutdown_sync(&est->timer); kfree_rcu(est, rcu); } } EXPORT_SYMBOL(gen_kill_estimator); /** * gen_replace_estimator - replace rate estimator configuration * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path * @running: true if @bstats represents a running qdisc, thus @bstats' * internal values might change during basic reads. Only used * if @cpu_bstats is NULL * @opt: rate estimator configuration TLV * * Replaces the configuration of a rate estimator by calling * gen_kill_estimator() and gen_new_estimator(). * * Returns 0 on success or a negative error code. */ int gen_replace_estimator(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, bool running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, lock, running, opt); } EXPORT_SYMBOL(gen_replace_estimator); /** * gen_estimator_active - test if estimator is currently in use * @rate_est: rate estimator * * Returns true if estimator is active, and false if not. */ bool gen_estimator_active(struct net_rate_estimator __rcu **rate_est) { return !!rcu_access_pointer(*rate_est); } EXPORT_SYMBOL(gen_estimator_active); bool gen_estimator_read(struct net_rate_estimator __rcu **rate_est, struct gnet_stats_rate_est64 *sample) { struct net_rate_estimator *est; unsigned seq; rcu_read_lock(); est = rcu_dereference(*rate_est); if (!est) { rcu_read_unlock(); return false; } do { seq = read_seqcount_begin(&est->seq); sample->bps = est->avbps >> 8; sample->pps = est->avpps >> 8; } while (read_seqcount_retry(&est->seq, seq)); rcu_read_unlock(); return true; } EXPORT_SYMBOL(gen_estimator_read); |
| 3 89 162 29 133 190 5 183 3 3 3 154 149 52 97 1 7 4 4 27 27 1516 1494 23 294 290 3 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 | // SPDX-License-Identifier: GPL-2.0-or-later /* * lwtunnel Infrastructure for light weight tunnels like mpls * * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com> */ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/lwtunnel.h> #include <linux/in.h> #include <linux/init.h> #include <linux/err.h> #include <net/lwtunnel.h> #include <net/rtnetlink.h> #include <net/ip6_fib.h> #include <net/rtnh.h> DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled); EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled); #ifdef CONFIG_MODULES static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) { /* Only lwt encaps implemented without using an interface for * the encap need to return a string here. */ switch (encap_type) { case LWTUNNEL_ENCAP_MPLS: return "MPLS"; case LWTUNNEL_ENCAP_ILA: return "ILA"; case LWTUNNEL_ENCAP_SEG6: return "SEG6"; case LWTUNNEL_ENCAP_BPF: return "BPF"; case LWTUNNEL_ENCAP_SEG6_LOCAL: return "SEG6LOCAL"; case LWTUNNEL_ENCAP_RPL: return "RPL"; case LWTUNNEL_ENCAP_IOAM6: return "IOAM6"; case LWTUNNEL_ENCAP_XFRM: /* module autoload not supported for encap type */ return NULL; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: case LWTUNNEL_ENCAP_NONE: case __LWTUNNEL_ENCAP_MAX: /* should not have got here */ WARN_ON(1); break; } return NULL; } #endif /* CONFIG_MODULES */ struct lwtunnel_state *lwtunnel_state_alloc(int encap_len) { struct lwtunnel_state *lws; lws = kzalloc(sizeof(*lws) + encap_len, GFP_ATOMIC); return lws; } EXPORT_SYMBOL_GPL(lwtunnel_state_alloc); static const struct lwtunnel_encap_ops __rcu * lwtun_encaps[LWTUNNEL_ENCAP_MAX + 1] __read_mostly; int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *ops, unsigned int num) { if (num > LWTUNNEL_ENCAP_MAX) return -ERANGE; return !cmpxchg((const struct lwtunnel_encap_ops **) &lwtun_encaps[num], NULL, ops) ? 0 : -1; } EXPORT_SYMBOL_GPL(lwtunnel_encap_add_ops); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops, unsigned int encap_type) { int ret; if (encap_type == LWTUNNEL_ENCAP_NONE || encap_type > LWTUNNEL_ENCAP_MAX) return -ERANGE; ret = (cmpxchg((const struct lwtunnel_encap_ops **) &lwtun_encaps[encap_type], ops, NULL) == ops) ? 0 : -1; synchronize_net(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_encap_del_ops); int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; bool found = false; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || encap_type > LWTUNNEL_ENCAP_MAX) { NL_SET_ERR_MSG_ATTR(extack, encap, "Unknown LWT encapsulation type"); return ret; } ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); if (likely(ops && ops->build_state && try_module_get(ops->owner))) found = true; rcu_read_unlock(); if (found) { ret = ops->build_state(net, encap, family, cfg, lws, extack); if (ret) module_put(ops->owner); } else { /* don't rely on -EOPNOTSUPP to detect match as build_state * handlers could return it */ NL_SET_ERR_MSG_ATTR(extack, encap, "LWT encapsulation type not supported"); } return ret; } EXPORT_SYMBOL_GPL(lwtunnel_build_state); int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || encap_type > LWTUNNEL_ENCAP_MAX) { NL_SET_ERR_MSG(extack, "Unknown lwt encapsulation type"); return ret; } rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); rcu_read_unlock(); #ifdef CONFIG_MODULES if (!ops) { const char *encap_type_str = lwtunnel_encap_str(encap_type); if (encap_type_str) { __rtnl_unlock(); request_module("rtnl-lwt-%s", encap_type_str); rtnl_lock(); rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); rcu_read_unlock(); } } #endif ret = ops ? 0 : -EOPNOTSUPP; if (ret < 0) NL_SET_ERR_MSG(extack, "lwt encapsulation type not supported"); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, struct netlink_ext_ack *extack) { struct rtnexthop *rtnh = (struct rtnexthop *)attr; struct nlattr *nla_entype; struct nlattr *attrs; u16 encap_type; int attrlen; while (rtnh_ok(rtnh, remaining)) { attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { attrs = rtnh_attrs(rtnh); nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla_entype) { if (nla_len(nla_entype) < sizeof(u16)) { NL_SET_ERR_MSG(extack, "Invalid RTA_ENCAP_TYPE"); return -EINVAL; } encap_type = nla_get_u16(nla_entype); if (lwtunnel_valid_encap_type(encap_type, extack) != 0) return -EOPNOTSUPP; } } rtnh = rtnh_next(rtnh, &remaining); } return 0; } EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type_attr); void lwtstate_free(struct lwtunnel_state *lws) { const struct lwtunnel_encap_ops *ops = lwtun_encaps[lws->type]; if (ops->destroy_state) { ops->destroy_state(lws); kfree_rcu(lws, rcu); } else { kfree(lws); } module_put(ops->owner); } EXPORT_SYMBOL_GPL(lwtstate_free); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr) { const struct lwtunnel_encap_ops *ops; struct nlattr *nest; int ret; if (!lwtstate) return 0; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; nest = nla_nest_start_noflag(skb, encap_attr); if (!nest) return -EMSGSIZE; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->fill_encap)) ret = ops->fill_encap(skb, lwtstate); rcu_read_unlock(); if (ret) goto nla_put_failure; nla_nest_end(skb, nest); ret = nla_put_u16(skb, encap_type_attr, lwtstate->type); if (ret) goto nla_put_failure; return 0; nla_put_failure: nla_nest_cancel(skb, nest); return (ret == -EOPNOTSUPP ? 0 : ret); } EXPORT_SYMBOL_GPL(lwtunnel_fill_encap); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) { const struct lwtunnel_encap_ops *ops; int ret = 0; if (!lwtstate) return 0; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->get_encap_size)) ret = nla_total_size(ops->get_encap_size(lwtstate)); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_get_encap_size); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) { const struct lwtunnel_encap_ops *ops; int ret = 0; if (!a && !b) return 0; if (!a || !b) return 1; if (a->type != b->type) return 1; if (a->type == LWTUNNEL_ENCAP_NONE || a->type > LWTUNNEL_ENCAP_MAX) return 0; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[a->type]); if (likely(ops && ops->cmp_encap)) ret = ops->cmp_encap(a, b); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_cmp_encap); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; int ret = -EINVAL; if (!dst) goto drop; lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->output)) ret = ops->output(net, sk, skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; return ret; drop: kfree_skb(skb); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_output); int lwtunnel_xmit(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; int ret = -EINVAL; if (!dst) goto drop; lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->xmit)) ret = ops->xmit(skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; return ret; drop: kfree_skb(skb); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_xmit); int lwtunnel_input(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; int ret = -EINVAL; if (!dst) goto drop; lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || lwtstate->type > LWTUNNEL_ENCAP_MAX) return 0; ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->input)) ret = ops->input(skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; return ret; drop: kfree_skb(skb); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_input); |
| 6 2 1 3 16 5 3 1 4 1 2 2 2 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | // SPDX-License-Identifier: GPL-2.0-only /* * * Generic part shared by ipv4 and ipv6 backends. */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_fib.h> #define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \ NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF | \ NFTA_FIB_F_PRESENT) const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = { [NFTA_FIB_DREG] = { .type = NLA_U32 }, [NFTA_FIB_RESULT] = { .type = NLA_U32 }, [NFTA_FIB_FLAGS] = NLA_POLICY_MASK(NLA_BE32, NFTA_FIB_F_ALL), }; EXPORT_SYMBOL(nft_fib_policy); int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_fib *priv = nft_expr_priv(expr); unsigned int hooks; switch (priv->result) { case NFT_FIB_RESULT_OIF: case NFT_FIB_RESULT_OIFNAME: hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD); break; case NFT_FIB_RESULT_ADDRTYPE: if (priv->flags & NFTA_FIB_F_IIF) hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD); else if (priv->flags & NFTA_FIB_F_OIF) hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_FORWARD); else hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING); break; default: return -EINVAL; } return nft_chain_validate_hooks(ctx->chain, hooks); } EXPORT_SYMBOL_GPL(nft_fib_validate); int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_fib *priv = nft_expr_priv(expr); unsigned int len; int err; if (!tb[NFTA_FIB_DREG] || !tb[NFTA_FIB_RESULT] || !tb[NFTA_FIB_FLAGS]) return -EINVAL; priv->flags = ntohl(nla_get_be32(tb[NFTA_FIB_FLAGS])); if (priv->flags == 0) return -EINVAL; if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) == (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) return -EINVAL; if ((priv->flags & (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) == (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) return -EINVAL; if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) == 0) return -EINVAL; priv->result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT])); switch (priv->result) { case NFT_FIB_RESULT_OIF: if (priv->flags & NFTA_FIB_F_OIF) return -EINVAL; len = sizeof(int); break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_OIF) return -EINVAL; len = IFNAMSIZ; break; case NFT_FIB_RESULT_ADDRTYPE: len = sizeof(u32); break; default: return -EINVAL; } err = nft_parse_register_store(ctx, tb[NFTA_FIB_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, len); if (err < 0) return err; return 0; } EXPORT_SYMBOL_GPL(nft_fib_init); int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_fib *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_FIB_DREG, priv->dreg)) return -1; if (nla_put_be32(skb, NFTA_FIB_RESULT, htonl(priv->result))) return -1; if (nla_put_be32(skb, NFTA_FIB_FLAGS, htonl(priv->flags))) return -1; return 0; } EXPORT_SYMBOL_GPL(nft_fib_dump); void nft_fib_store_result(void *reg, const struct nft_fib *priv, const struct net_device *dev) { u32 *dreg = reg; int index; switch (priv->result) { case NFT_FIB_RESULT_OIF: index = dev ? dev->ifindex : 0; if (priv->flags & NFTA_FIB_F_PRESENT) nft_reg_store8(dreg, !!index); else *dreg = index; break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_PRESENT) nft_reg_store8(dreg, !!dev); else strscpy_pad(reg, dev ? dev->name : "", IFNAMSIZ); break; default: WARN_ON_ONCE(1); *dreg = 0; break; } } EXPORT_SYMBOL_GPL(nft_fib_store_result); bool nft_fib_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { const struct nft_fib *priv = nft_expr_priv(expr); unsigned int len = NFT_REG32_SIZE; const struct nft_fib *fib; switch (priv->result) { case NFT_FIB_RESULT_OIF: break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_PRESENT) len = NFT_REG32_SIZE; else len = IFNAMSIZ; break; case NFT_FIB_RESULT_ADDRTYPE: break; default: WARN_ON_ONCE(1); break; } if (!nft_reg_track_cmp(track, expr, priv->dreg)) { nft_reg_track_update(track, expr, priv->dreg, len); return false; } fib = nft_expr_priv(track->regs[priv->dreg].selector); if (priv->result != fib->result || priv->flags != fib->flags) { nft_reg_track_update(track, expr, priv->dreg, len); return false; } if (!track->regs[priv->dreg].bitwise) return true; return false; } EXPORT_SYMBOL_GPL(nft_fib_reduce); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Query routing table from nftables"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); |
| 12 2 11 8 8 3 6 6 6 1 6 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 | // SPDX-License-Identifier: GPL-2.0-only /* * Stream Parser * * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> */ #include <linux/bpf.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/file.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/init.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/uaccess.h> #include <linux/workqueue.h> #include <net/strparser.h> #include <net/netns/generic.h> #include <net/sock.h> static struct workqueue_struct *strp_wq; static inline struct _strp_msg *_strp_msg(struct sk_buff *skb) { return (struct _strp_msg *)((void *)skb->cb + offsetof(struct sk_skb_cb, strp)); } /* Lower lock held */ static void strp_abort_strp(struct strparser *strp, int err) { /* Unrecoverable error in receive */ cancel_delayed_work(&strp->msg_timer_work); if (strp->stopped) return; strp->stopped = 1; if (strp->sk) { struct sock *sk = strp->sk; /* Report an error on the lower socket */ sk->sk_err = -err; sk_error_report(sk); } } static void strp_start_timer(struct strparser *strp, long timeo) { if (timeo && timeo != LONG_MAX) mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo); } /* Lower lock held */ static void strp_parser_err(struct strparser *strp, int err, read_descriptor_t *desc) { desc->error = err; kfree_skb(strp->skb_head); strp->skb_head = NULL; strp->cb.abort_parser(strp, err); } static inline int strp_peek_len(struct strparser *strp) { if (strp->sk) { struct socket *sock = strp->sk->sk_socket; return sock->ops->peek_len(sock); } /* If we don't have an associated socket there's nothing to peek. * Return int max to avoid stopping the strparser. */ return INT_MAX; } /* Lower socket lock held */ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, unsigned int orig_offset, size_t orig_len, size_t max_msg_size, long timeo) { struct strparser *strp = (struct strparser *)desc->arg.data; struct _strp_msg *stm; struct sk_buff *head, *skb; size_t eaten = 0, cand_len; ssize_t extra; int err; bool cloned_orig = false; if (strp->paused) return 0; head = strp->skb_head; if (head) { /* Message already in progress */ if (unlikely(orig_offset)) { /* Getting data with a non-zero offset when a message is * in progress is not expected. If it does happen, we * need to clone and pull since we can't deal with * offsets in the skbs for a message expect in the head. */ orig_skb = skb_clone(orig_skb, GFP_ATOMIC); if (!orig_skb) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = -ENOMEM; return 0; } if (!pskb_pull(orig_skb, orig_offset)) { STRP_STATS_INCR(strp->stats.mem_fail); kfree_skb(orig_skb); desc->error = -ENOMEM; return 0; } cloned_orig = true; orig_offset = 0; } if (!strp->skb_nextp) { /* We are going to append to the frags_list of head. * Need to unshare the frag_list. */ err = skb_unclone(head, GFP_ATOMIC); if (err) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = err; return 0; } if (unlikely(skb_shinfo(head)->frag_list)) { /* We can't append to an sk_buff that already * has a frag_list. We create a new head, point * the frag_list of that to the old head, and * then are able to use the old head->next for * appending to the message. */ if (WARN_ON(head->next)) { desc->error = -EINVAL; return 0; } skb = alloc_skb_for_msg(head); if (!skb) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = -ENOMEM; return 0; } strp->skb_nextp = &head->next; strp->skb_head = skb; head = skb; } else { strp->skb_nextp = &skb_shinfo(head)->frag_list; } } } while (eaten < orig_len) { /* Always clone since we will consume something */ skb = skb_clone(orig_skb, GFP_ATOMIC); if (!skb) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = -ENOMEM; break; } cand_len = orig_len - eaten; head = strp->skb_head; if (!head) { head = skb; strp->skb_head = head; /* Will set skb_nextp on next packet if needed */ strp->skb_nextp = NULL; stm = _strp_msg(head); memset(stm, 0, sizeof(*stm)); stm->strp.offset = orig_offset + eaten; } else { /* Unclone if we are appending to an skb that we * already share a frag_list with. */ if (skb_has_frag_list(skb)) { err = skb_unclone(skb, GFP_ATOMIC); if (err) { STRP_STATS_INCR(strp->stats.mem_fail); desc->error = err; break; } } stm = _strp_msg(head); *strp->skb_nextp = skb; strp->skb_nextp = &skb->next; head->data_len += skb->len; head->len += skb->len; head->truesize += skb->truesize; } if (!stm->strp.full_len) { ssize_t len; len = (*strp->cb.parse_msg)(strp, head); if (!len) { /* Need more header to determine length */ if (!stm->accum_len) { /* Start RX timer for new message */ strp_start_timer(strp, timeo); } stm->accum_len += cand_len; eaten += cand_len; STRP_STATS_INCR(strp->stats.need_more_hdr); WARN_ON(eaten != orig_len); break; } else if (len < 0) { if (len == -ESTRPIPE && stm->accum_len) { len = -ENODATA; strp->unrecov_intr = 1; } else { strp->interrupted = 1; } strp_parser_err(strp, len, desc); break; } else if (len > max_msg_size) { /* Message length exceeds maximum allowed */ STRP_STATS_INCR(strp->stats.msg_too_big); strp_parser_err(strp, -EMSGSIZE, desc); break; } else if (len <= (ssize_t)head->len - skb->len - stm->strp.offset) { /* Length must be into new skb (and also * greater than zero) */ STRP_STATS_INCR(strp->stats.bad_hdr_len); strp_parser_err(strp, -EPROTO, desc); break; } stm->strp.full_len = len; } extra = (ssize_t)(stm->accum_len + cand_len) - stm->strp.full_len; if (extra < 0) { /* Message not complete yet. */ if (stm->strp.full_len - stm->accum_len > strp_peek_len(strp)) { /* Don't have the whole message in the socket * buffer. Set strp->need_bytes to wait for * the rest of the message. Also, set "early * eaten" since we've already buffered the skb * but don't consume yet per strp_read_sock. */ if (!stm->accum_len) { /* Start RX timer for new message */ strp_start_timer(strp, timeo); } stm->accum_len += cand_len; eaten += cand_len; strp->need_bytes = stm->strp.full_len - stm->accum_len; STRP_STATS_ADD(strp->stats.bytes, cand_len); desc->count = 0; /* Stop reading socket */ break; } stm->accum_len += cand_len; eaten += cand_len; WARN_ON(eaten != orig_len); break; } /* Positive extra indicates more bytes than needed for the * message */ WARN_ON(extra > cand_len); eaten += (cand_len - extra); /* Hurray, we have a new message! */ cancel_delayed_work(&strp->msg_timer_work); strp->skb_head = NULL; strp->need_bytes = 0; STRP_STATS_INCR(strp->stats.msgs); /* Give skb to upper layer */ strp->cb.rcv_msg(strp, head); if (unlikely(strp->paused)) { /* Upper layer paused strp */ break; } } if (cloned_orig) kfree_skb(orig_skb); STRP_STATS_ADD(strp->stats.bytes, eaten); return eaten; } int strp_process(struct strparser *strp, struct sk_buff *orig_skb, unsigned int orig_offset, size_t orig_len, size_t max_msg_size, long timeo) { read_descriptor_t desc; /* Dummy arg to strp_recv */ desc.arg.data = strp; return __strp_recv(&desc, orig_skb, orig_offset, orig_len, max_msg_size, timeo); } EXPORT_SYMBOL_GPL(strp_process); static int strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, unsigned int orig_offset, size_t orig_len) { struct strparser *strp = (struct strparser *)desc->arg.data; return __strp_recv(desc, orig_skb, orig_offset, orig_len, strp->sk->sk_rcvbuf, strp->sk->sk_rcvtimeo); } static int default_read_sock_done(struct strparser *strp, int err) { return err; } /* Called with lock held on lower socket */ static int strp_read_sock(struct strparser *strp) { struct socket *sock = strp->sk->sk_socket; read_descriptor_t desc; if (unlikely(!sock || !sock->ops || !sock->ops->read_sock)) return -EBUSY; desc.arg.data = strp; desc.error = 0; desc.count = 1; /* give more than one skb per call */ /* sk should be locked here, so okay to do read_sock */ sock->ops->read_sock(strp->sk, &desc, strp_recv); desc.error = strp->cb.read_sock_done(strp, desc.error); return desc.error; } /* Lower sock lock held */ void strp_data_ready(struct strparser *strp) { if (unlikely(strp->stopped) || strp->paused) return; /* This check is needed to synchronize with do_strp_work. * do_strp_work acquires a process lock (lock_sock) whereas * the lock held here is bh_lock_sock. The two locks can be * held by different threads at the same time, but bh_lock_sock * allows a thread in BH context to safely check if the process * lock is held. In this case, if the lock is held, queue work. */ if (sock_owned_by_user_nocheck(strp->sk)) { queue_work(strp_wq, &strp->work); return; } if (strp->need_bytes) { if (strp_peek_len(strp) < strp->need_bytes) return; } if (strp_read_sock(strp) == -ENOMEM) queue_work(strp_wq, &strp->work); } EXPORT_SYMBOL_GPL(strp_data_ready); static void do_strp_work(struct strparser *strp) { /* We need the read lock to synchronize with strp_data_ready. We * need the socket lock for calling strp_read_sock. */ strp->cb.lock(strp); if (unlikely(strp->stopped)) goto out; if (strp->paused) goto out; if (strp_read_sock(strp) == -ENOMEM) queue_work(strp_wq, &strp->work); out: strp->cb.unlock(strp); } static void strp_work(struct work_struct *w) { do_strp_work(container_of(w, struct strparser, work)); } static void strp_msg_timeout(struct work_struct *w) { struct strparser *strp = container_of(w, struct strparser, msg_timer_work.work); /* Message assembly timed out */ STRP_STATS_INCR(strp->stats.msg_timeouts); strp->cb.lock(strp); strp->cb.abort_parser(strp, -ETIMEDOUT); strp->cb.unlock(strp); } static void strp_sock_lock(struct strparser *strp) { lock_sock(strp->sk); } static void strp_sock_unlock(struct strparser *strp) { release_sock(strp->sk); } int strp_init(struct strparser *strp, struct sock *sk, const struct strp_callbacks *cb) { if (!cb || !cb->rcv_msg || !cb->parse_msg) return -EINVAL; /* The sk (sock) arg determines the mode of the stream parser. * * If the sock is set then the strparser is in receive callback mode. * The upper layer calls strp_data_ready to kick receive processing * and strparser calls the read_sock function on the socket to * get packets. * * If the sock is not set then the strparser is in general mode. * The upper layer calls strp_process for each skb to be parsed. */ if (!sk) { if (!cb->lock || !cb->unlock) return -EINVAL; } memset(strp, 0, sizeof(*strp)); strp->sk = sk; strp->cb.lock = cb->lock ? : strp_sock_lock; strp->cb.unlock = cb->unlock ? : strp_sock_unlock; strp->cb.rcv_msg = cb->rcv_msg; strp->cb.parse_msg = cb->parse_msg; strp->cb.read_sock_done = cb->read_sock_done ? : default_read_sock_done; strp->cb.abort_parser = cb->abort_parser ? : strp_abort_strp; INIT_DELAYED_WORK(&strp->msg_timer_work, strp_msg_timeout); INIT_WORK(&strp->work, strp_work); return 0; } EXPORT_SYMBOL_GPL(strp_init); /* Sock process lock held (lock_sock) */ void __strp_unpause(struct strparser *strp) { strp->paused = 0; if (strp->need_bytes) { if (strp_peek_len(strp) < strp->need_bytes) return; } strp_read_sock(strp); } EXPORT_SYMBOL_GPL(__strp_unpause); void strp_unpause(struct strparser *strp) { strp->paused = 0; /* Sync setting paused with RX work */ smp_mb(); queue_work(strp_wq, &strp->work); } EXPORT_SYMBOL_GPL(strp_unpause); /* strp must already be stopped so that strp_recv will no longer be called. * Note that strp_done is not called with the lower socket held. */ void strp_done(struct strparser *strp) { WARN_ON(!strp->stopped); cancel_delayed_work_sync(&strp->msg_timer_work); cancel_work_sync(&strp->work); if (strp->skb_head) { kfree_skb(strp->skb_head); strp->skb_head = NULL; } } EXPORT_SYMBOL_GPL(strp_done); void strp_stop(struct strparser *strp) { strp->stopped = 1; } EXPORT_SYMBOL_GPL(strp_stop); void strp_check_rcv(struct strparser *strp) { queue_work(strp_wq, &strp->work); } EXPORT_SYMBOL_GPL(strp_check_rcv); static int __init strp_dev_init(void) { BUILD_BUG_ON(sizeof(struct sk_skb_cb) > sizeof_field(struct sk_buff, cb)); strp_wq = create_singlethread_workqueue("kstrp"); if (unlikely(!strp_wq)) return -ENOMEM; return 0; } device_initcall(strp_dev_init); |
| 1 80 24 82 186 82 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Cryptographic scatter and gather helpers. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2002 Adam J. Richter <adam@yggdrasil.com> * Copyright (c) 2004 Jean-Luc Cooke <jlcooke@certainkey.com> * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_SCATTERWALK_H #define _CRYPTO_SCATTERWALK_H #include <crypto/algapi.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/scatterlist.h> static inline void scatterwalk_crypto_chain(struct scatterlist *head, struct scatterlist *sg, int num) { if (sg) sg_chain(head, num, sg); else sg_mark_end(head); } static inline unsigned int scatterwalk_pagelen(struct scatter_walk *walk) { unsigned int len = walk->sg->offset + walk->sg->length - walk->offset; unsigned int len_this_page = offset_in_page(~walk->offset) + 1; return len_this_page > len ? len : len_this_page; } static inline unsigned int scatterwalk_clamp(struct scatter_walk *walk, unsigned int nbytes) { unsigned int len_this_page = scatterwalk_pagelen(walk); return nbytes > len_this_page ? len_this_page : nbytes; } static inline void scatterwalk_advance(struct scatter_walk *walk, unsigned int nbytes) { walk->offset += nbytes; } static inline struct page *scatterwalk_page(struct scatter_walk *walk) { return sg_page(walk->sg) + (walk->offset >> PAGE_SHIFT); } static inline void scatterwalk_unmap(void *vaddr) { kunmap_local(vaddr); } static inline void scatterwalk_start(struct scatter_walk *walk, struct scatterlist *sg) { walk->sg = sg; walk->offset = sg->offset; } static inline void *scatterwalk_map(struct scatter_walk *walk) { return kmap_local_page(scatterwalk_page(walk)) + offset_in_page(walk->offset); } static inline void scatterwalk_pagedone(struct scatter_walk *walk, int out, unsigned int more) { if (out) { struct page *page; page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT); flush_dcache_page(page); } if (more && walk->offset >= walk->sg->offset + walk->sg->length) scatterwalk_start(walk, sg_next(walk->sg)); } static inline void scatterwalk_done(struct scatter_walk *walk, int out, int more) { if (!more || walk->offset >= walk->sg->offset + walk->sg->length || !(walk->offset & (PAGE_SIZE - 1))) scatterwalk_pagedone(walk, out, more); } void scatterwalk_copychunks(void *buf, struct scatter_walk *walk, size_t nbytes, int out); void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg, unsigned int start, unsigned int nbytes, int out); struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2], struct scatterlist *src, unsigned int len); #endif /* _CRYPTO_SCATTERWALK_H */ |
| 62 40 5 12 57 5185 5187 5189 5186 5187 5179 5185 5190 222 3137 7 222 3142 3142 3135 7 618 1114 617 2 18 18 4145 4149 4149 2893 1415 2 1 4150 84 34 84 94 12 442 436 80 436 12 442 633 633 300 633 264 94 448 499 641 243 498 498 498 499 192 192 2307 24 2310 2307 2308 2550 2546 3 229 2521 2612 2610 2607 2612 26 573 574 575 1809 2624 89 2550 2551 1736 575 11544 25 25 25 11521 11539 78 78 3206 3205 3142 69 3144 3145 3142 3143 3144 3142 3140 3144 15 4078 24 156 1 139 2 19 3179 1065 140 2991 3179 201 2991 2931 2930 2931 75 3183 75 3181 9 16 13 21 14 9 5 6 3 3 2 3 1 2 2 23 14 9 8 4 6 16 14 3 2 3 2 13 3 1 1 2 3285 3283 285 19 289 15 4298 4293 2208 2202 5 76 76 3071 3071 9 618 2579 1970 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <uapi/linux/btf.h> #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/random.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/objtool.h> #include <linux/overflow.h> #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/perf_event.h> #include <linux/extable.h> #include <linux/log2.h> #include <linux/bpf_verifier.h> #include <linux/nodemask.h> #include <linux/nospec.h> #include <linux/bpf_mem_alloc.h> #include <linux/memcontrol.h> #include <linux/execmem.h> #include <asm/barrier.h> #include <asm/unaligned.h> /* Registers */ #define BPF_R0 regs[BPF_REG_0] #define BPF_R1 regs[BPF_REG_1] #define BPF_R2 regs[BPF_REG_2] #define BPF_R3 regs[BPF_REG_3] #define BPF_R4 regs[BPF_REG_4] #define BPF_R5 regs[BPF_REG_5] #define BPF_R6 regs[BPF_REG_6] #define BPF_R7 regs[BPF_REG_7] #define BPF_R8 regs[BPF_REG_8] #define BPF_R9 regs[BPF_REG_9] #define BPF_R10 regs[BPF_REG_10] /* Named registers */ #define DST regs[insn->dst_reg] #define SRC regs[insn->src_reg] #define FP regs[BPF_REG_FP] #define AX regs[BPF_REG_AX] #define ARG1 regs[BPF_REG_ARG1] #define CTX regs[BPF_REG_CTX] #define OFF insn->off #define IMM insn->imm struct bpf_mem_alloc bpf_global_ma; bool bpf_global_ma_set; /* No hurry in this branch * * Exported for the bpf jit load helper. */ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; if (k >= SKF_NET_OFF) { ptr = skb_network_header(skb) + k - SKF_NET_OFF; } else if (k >= SKF_LL_OFF) { if (unlikely(!skb_mac_header_was_set(skb))) return NULL; ptr = skb_mac_header(skb) + k - SKF_LL_OFF; } if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; return NULL; } /* tell bpf programs that include vmlinux.h kernel's PAGE_SIZE */ enum page_size_enum { __PAGE_SIZE = PAGE_SIZE }; struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog_aux *aux; struct bpf_prog *fp; size = round_up(size, __PAGE_SIZE); fp = __vmalloc(size, gfp_flags); if (fp == NULL) return NULL; aux = kzalloc(sizeof(*aux), bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags)); if (aux == NULL) { vfree(fp); return NULL; } fp->active = alloc_percpu_gfp(int, bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags)); if (!fp->active) { vfree(fp); kfree(aux); return NULL; } fp->pages = size / PAGE_SIZE; fp->aux = aux; fp->aux->prog = fp; fp->jit_requested = ebpf_jit_enabled(); fp->blinding_requested = bpf_jit_blinding_enabled(fp); #ifdef CONFIG_CGROUP_BPF aux->cgroup_atype = CGROUP_BPF_ATTACH_TYPE_INVALID; #endif INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode); #ifdef CONFIG_FINEIBT INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode); #endif mutex_init(&fp->aux->used_maps_mutex); mutex_init(&fp->aux->dst_mutex); return fp; } struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog *prog; int cpu; prog = bpf_prog_alloc_no_stats(size, gfp_extra_flags); if (!prog) return NULL; prog->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags); if (!prog->stats) { free_percpu(prog->active); kfree(prog->aux); vfree(prog); return NULL; } for_each_possible_cpu(cpu) { struct bpf_prog_stats *pstats; pstats = per_cpu_ptr(prog->stats, cpu); u64_stats_init(&pstats->syncp); } return prog; } EXPORT_SYMBOL_GPL(bpf_prog_alloc); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) { if (!prog->aux->nr_linfo || !prog->jit_requested) return 0; prog->aux->jited_linfo = kvcalloc(prog->aux->nr_linfo, sizeof(*prog->aux->jited_linfo), bpf_memcg_flags(GFP_KERNEL | __GFP_NOWARN)); if (!prog->aux->jited_linfo) return -ENOMEM; return 0; } void bpf_prog_jit_attempt_done(struct bpf_prog *prog) { if (prog->aux->jited_linfo && (!prog->jited || !prog->aux->jited_linfo[0])) { kvfree(prog->aux->jited_linfo); prog->aux->jited_linfo = NULL; } kfree(prog->aux->kfunc_tab); prog->aux->kfunc_tab = NULL; } /* The jit engine is responsible to provide an array * for insn_off to the jited_off mapping (insn_to_jit_off). * * The idx to this array is the insn_off. Hence, the insn_off * here is relative to the prog itself instead of the main prog. * This array has one entry for each xlated bpf insn. * * jited_off is the byte off to the end of the jited insn. * * Hence, with * insn_start: * The first bpf insn off of the prog. The insn off * here is relative to the main prog. * e.g. if prog is a subprog, insn_start > 0 * linfo_idx: * The prog's idx to prog->aux->linfo and jited_linfo * * jited_linfo[linfo_idx] = prog->bpf_func * * For i > linfo_idx, * * jited_linfo[i] = prog->bpf_func + * insn_to_jit_off[linfo[i].insn_off - insn_start - 1] */ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off) { u32 linfo_idx, insn_start, insn_end, nr_linfo, i; const struct bpf_line_info *linfo; void **jited_linfo; if (!prog->aux->jited_linfo || prog->aux->func_idx > prog->aux->func_cnt) /* Userspace did not provide linfo */ return; linfo_idx = prog->aux->linfo_idx; linfo = &prog->aux->linfo[linfo_idx]; insn_start = linfo[0].insn_off; insn_end = insn_start + prog->len; jited_linfo = &prog->aux->jited_linfo[linfo_idx]; jited_linfo[0] = prog->bpf_func; nr_linfo = prog->aux->nr_linfo - linfo_idx; for (i = 1; i < nr_linfo && linfo[i].insn_off < insn_end; i++) /* The verifier ensures that linfo[i].insn_off is * strictly increasing */ jited_linfo[i] = prog->bpf_func + insn_to_jit_off[linfo[i].insn_off - insn_start - 1]; } struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog *fp; u32 pages; size = round_up(size, PAGE_SIZE); pages = size / PAGE_SIZE; if (pages <= fp_old->pages) return fp_old; fp = __vmalloc(size, gfp_flags); if (fp) { memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); fp->pages = pages; fp->aux->prog = fp; /* We keep fp->aux from fp_old around in the new * reallocated structure. */ fp_old->aux = NULL; fp_old->stats = NULL; fp_old->active = NULL; __bpf_prog_free(fp_old); } return fp; } void __bpf_prog_free(struct bpf_prog *fp) { if (fp->aux) { mutex_destroy(&fp->aux->used_maps_mutex); mutex_destroy(&fp->aux->dst_mutex); kfree(fp->aux->poke_tab); kfree(fp->aux); } free_percpu(fp->stats); free_percpu(fp->active); vfree(fp); } int bpf_prog_calc_tag(struct bpf_prog *fp) { const u32 bits_offset = SHA1_BLOCK_SIZE - sizeof(__be64); u32 raw_size = bpf_prog_tag_scratch_size(fp); u32 digest[SHA1_DIGEST_WORDS]; u32 ws[SHA1_WORKSPACE_WORDS]; u32 i, bsize, psize, blocks; struct bpf_insn *dst; bool was_ld_map; u8 *raw, *todo; __be32 *result; __be64 *bits; raw = vmalloc(raw_size); if (!raw) return -ENOMEM; sha1_init(digest); memset(ws, 0, sizeof(ws)); /* We need to take out the map fd for the digest calculation * since they are unstable from user space side. */ dst = (void *)raw; for (i = 0, was_ld_map = false; i < fp->len; i++) { dst[i] = fp->insnsi[i]; if (!was_ld_map && dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) && (dst[i].src_reg == BPF_PSEUDO_MAP_FD || dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) { was_ld_map = true; dst[i].imm = 0; } else if (was_ld_map && dst[i].code == 0 && dst[i].dst_reg == 0 && dst[i].src_reg == 0 && dst[i].off == 0) { was_ld_map = false; dst[i].imm = 0; } else { was_ld_map = false; } } psize = bpf_prog_insn_size(fp); memset(&raw[psize], 0, raw_size - psize); raw[psize++] = 0x80; bsize = round_up(psize, SHA1_BLOCK_SIZE); blocks = bsize / SHA1_BLOCK_SIZE; todo = raw; if (bsize - psize >= sizeof(__be64)) { bits = (__be64 *)(todo + bsize - sizeof(__be64)); } else { bits = (__be64 *)(todo + bsize + bits_offset); blocks++; } *bits = cpu_to_be64((psize - 1) << 3); while (blocks--) { sha1_transform(digest, todo, ws); todo += SHA1_BLOCK_SIZE; } result = (__force __be32 *)digest; for (i = 0; i < SHA1_DIGEST_WORDS; i++) result[i] = cpu_to_be32(digest[i]); memcpy(fp->tag, result, sizeof(fp->tag)); vfree(raw); return 0; } static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { const s64 imm_min = S32_MIN, imm_max = S32_MAX; s32 delta = end_new - end_old; s64 imm = insn->imm; if (curr < pos && curr + imm + 1 >= end_old) imm += delta; else if (curr >= end_new && curr + imm + 1 < end_new) imm -= delta; if (imm < imm_min || imm > imm_max) return -ERANGE; if (!probe_pass) insn->imm = imm; return 0; } static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { s64 off_min, off_max, off; s32 delta = end_new - end_old; if (insn->code == (BPF_JMP32 | BPF_JA)) { off = insn->imm; off_min = S32_MIN; off_max = S32_MAX; } else { off = insn->off; off_min = S16_MIN; off_max = S16_MAX; } if (curr < pos && curr + off + 1 >= end_old) off += delta; else if (curr >= end_new && curr + off + 1 < end_new) off -= delta; if (off < off_min || off > off_max) return -ERANGE; if (!probe_pass) { if (insn->code == (BPF_JMP32 | BPF_JA)) insn->imm = off; else insn->off = off; } return 0; } static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old, s32 end_new, const bool probe_pass) { u32 i, insn_cnt = prog->len + (probe_pass ? end_new - end_old : 0); struct bpf_insn *insn = prog->insnsi; int ret = 0; for (i = 0; i < insn_cnt; i++, insn++) { u8 code; /* In the probing pass we still operate on the original, * unpatched image in order to check overflows before we * do any other adjustments. Therefore skip the patchlet. */ if (probe_pass && i == pos) { i = end_new; insn = prog->insnsi + end_old; } if (bpf_pseudo_func(insn)) { ret = bpf_adj_delta_to_imm(insn, pos, end_old, end_new, i, probe_pass); if (ret) return ret; continue; } code = insn->code; if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || BPF_OP(code) == BPF_EXIT) continue; /* Adjust offset of jmps if we cross patch boundaries. */ if (BPF_OP(code) == BPF_CALL) { if (insn->src_reg != BPF_PSEUDO_CALL) continue; ret = bpf_adj_delta_to_imm(insn, pos, end_old, end_new, i, probe_pass); } else { ret = bpf_adj_delta_to_off(insn, pos, end_old, end_new, i, probe_pass); } if (ret) break; } return ret; } static void bpf_adj_linfo(struct bpf_prog *prog, u32 off, u32 delta) { struct bpf_line_info *linfo; u32 i, nr_linfo; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo || !delta) return; linfo = prog->aux->linfo; for (i = 0; i < nr_linfo; i++) if (off < linfo[i].insn_off) break; /* Push all off < linfo[i].insn_off by delta */ for (; i < nr_linfo; i++) linfo[i].insn_off += delta; } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len) { u32 insn_adj_cnt, insn_rest, insn_delta = len - 1; const u32 cnt_max = S16_MAX; struct bpf_prog *prog_adj; int err; /* Since our patchlet doesn't expand the image, we're done. */ if (insn_delta == 0) { memcpy(prog->insnsi + off, patch, sizeof(*patch)); return prog; } insn_adj_cnt = prog->len + insn_delta; /* Reject anything that would potentially let the insn->off * target overflow when we have excessive program expansions. * We need to probe here before we do any reallocation where * we afterwards may not fail anymore. */ if (insn_adj_cnt > cnt_max && (err = bpf_adj_branches(prog, off, off + 1, off + len, true))) return ERR_PTR(err); /* Several new instructions need to be inserted. Make room * for them. Likely, there's no need for a new allocation as * last page could have large enough tailroom. */ prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt), GFP_USER); if (!prog_adj) return ERR_PTR(-ENOMEM); prog_adj->len = insn_adj_cnt; /* Patching happens in 3 steps: * * 1) Move over tail of insnsi from next instruction onwards, * so we can patch the single target insn with one or more * new ones (patching is always from 1 to n insns, n > 0). * 2) Inject new instructions at the target location. * 3) Adjust branch offsets if necessary. */ insn_rest = insn_adj_cnt - off - len; memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1, sizeof(*patch) * insn_rest); memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len); /* We are guaranteed to not fail at this point, otherwise * the ship has sailed to reverse to the original state. An * overflow cannot happen at this point. */ BUG_ON(bpf_adj_branches(prog_adj, off, off + 1, off + len, false)); bpf_adj_linfo(prog_adj, off, insn_delta); return prog_adj; } int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) { /* Branch offsets can't overflow when program is shrinking, no need * to call bpf_adj_branches(..., true) here */ memmove(prog->insnsi + off, prog->insnsi + off + cnt, sizeof(struct bpf_insn) * (prog->len - off - cnt)); prog->len -= cnt; return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false)); } static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) { int i; for (i = 0; i < fp->aux->real_func_cnt; i++) bpf_prog_kallsyms_del(fp->aux->func[i]); } void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) { bpf_prog_kallsyms_del_subprogs(fp); bpf_prog_kallsyms_del(fp); } #ifdef CONFIG_BPF_JIT /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; long bpf_jit_limit __read_mostly; long bpf_jit_limit_max __read_mostly; static void bpf_prog_ksym_set_addr(struct bpf_prog *prog) { WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog)); prog->aux->ksym.start = (unsigned long) prog->bpf_func; prog->aux->ksym.end = prog->aux->ksym.start + prog->jited_len; } static void bpf_prog_ksym_set_name(struct bpf_prog *prog) { char *sym = prog->aux->ksym.name; const char *end = sym + KSYM_NAME_LEN; const struct btf_type *type; const char *func_name; BUILD_BUG_ON(sizeof("bpf_prog_") + sizeof(prog->tag) * 2 + /* name has been null terminated. * We should need +1 for the '_' preceding * the name. However, the null character * is double counted between the name and the * sizeof("bpf_prog_") above, so we omit * the +1 here. */ sizeof(prog->aux->name) > KSYM_NAME_LEN); sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_"); sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); /* prog->aux->name will be ignored if full btf name is available */ if (prog->aux->func_info_cnt && prog->aux->func_idx < prog->aux->func_info_cnt) { type = btf_type_by_id(prog->aux->btf, prog->aux->func_info[prog->aux->func_idx].type_id); func_name = btf_name_by_offset(prog->aux->btf, type->name_off); snprintf(sym, (size_t)(end - sym), "_%s", func_name); return; } if (prog->aux->name[0]) snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name); else *sym = 0; } static unsigned long bpf_get_ksym_start(struct latch_tree_node *n) { return container_of(n, struct bpf_ksym, tnode)->start; } static __always_inline bool bpf_tree_less(struct latch_tree_node *a, struct latch_tree_node *b) { return bpf_get_ksym_start(a) < bpf_get_ksym_start(b); } static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n) { unsigned long val = (unsigned long)key; const struct bpf_ksym *ksym; ksym = container_of(n, struct bpf_ksym, tnode); if (val < ksym->start) return -1; /* Ensure that we detect return addresses as part of the program, when * the final instruction is a call for a program part of the stack * trace. Therefore, do val > ksym->end instead of val >= ksym->end. */ if (val > ksym->end) return 1; return 0; } static const struct latch_tree_ops bpf_tree_ops = { .less = bpf_tree_less, .comp = bpf_tree_comp, }; static DEFINE_SPINLOCK(bpf_lock); static LIST_HEAD(bpf_kallsyms); static struct latch_tree_root bpf_tree __cacheline_aligned; void bpf_ksym_add(struct bpf_ksym *ksym) { spin_lock_bh(&bpf_lock); WARN_ON_ONCE(!list_empty(&ksym->lnode)); list_add_tail_rcu(&ksym->lnode, &bpf_kallsyms); latch_tree_insert(&ksym->tnode, &bpf_tree, &bpf_tree_ops); spin_unlock_bh(&bpf_lock); } static void __bpf_ksym_del(struct bpf_ksym *ksym) { if (list_empty(&ksym->lnode)) return; latch_tree_erase(&ksym->tnode, &bpf_tree, &bpf_tree_ops); list_del_rcu(&ksym->lnode); } void bpf_ksym_del(struct bpf_ksym *ksym) { spin_lock_bh(&bpf_lock); __bpf_ksym_del(ksym); spin_unlock_bh(&bpf_lock); } static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) { return fp->jited && !bpf_prog_was_classic(fp); } void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || !bpf_token_capable(fp->aux->token, CAP_BPF)) return; bpf_prog_ksym_set_addr(fp); bpf_prog_ksym_set_name(fp); fp->aux->ksym.prog = true; bpf_ksym_add(&fp->aux->ksym); #ifdef CONFIG_FINEIBT /* * When FineIBT, code in the __cfi_foo() symbols can get executed * and hence unwinder needs help. */ if (cfi_mode != CFI_FINEIBT) return; snprintf(fp->aux->ksym_prefix.name, KSYM_NAME_LEN, "__cfi_%s", fp->aux->ksym.name); fp->aux->ksym_prefix.start = (unsigned long) fp->bpf_func - 16; fp->aux->ksym_prefix.end = (unsigned long) fp->bpf_func; bpf_ksym_add(&fp->aux->ksym_prefix); #endif } void bpf_prog_kallsyms_del(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp)) return; bpf_ksym_del(&fp->aux->ksym); #ifdef CONFIG_FINEIBT if (cfi_mode != CFI_FINEIBT) return; bpf_ksym_del(&fp->aux->ksym_prefix); #endif } static struct bpf_ksym *bpf_ksym_find(unsigned long addr) { struct latch_tree_node *n; n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops); return n ? container_of(n, struct bpf_ksym, tnode) : NULL; } int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { struct bpf_ksym *ksym; int ret = 0; rcu_read_lock(); ksym = bpf_ksym_find(addr); if (ksym) { unsigned long symbol_start = ksym->start; unsigned long symbol_end = ksym->end; ret = strscpy(sym, ksym->name, KSYM_NAME_LEN); if (size) *size = symbol_end - symbol_start; if (off) *off = addr - symbol_start; } rcu_read_unlock(); return ret; } bool is_bpf_text_address(unsigned long addr) { bool ret; rcu_read_lock(); ret = bpf_ksym_find(addr) != NULL; rcu_read_unlock(); return ret; } struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { struct bpf_ksym *ksym = bpf_ksym_find(addr); return ksym && ksym->prog ? container_of(ksym, struct bpf_prog_aux, ksym)->prog : NULL; } const struct exception_table_entry *search_bpf_extables(unsigned long addr) { const struct exception_table_entry *e = NULL; struct bpf_prog *prog; rcu_read_lock(); prog = bpf_prog_ksym_find(addr); if (!prog) goto out; if (!prog->aux->num_exentries) goto out; e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr); out: rcu_read_unlock(); return e; } int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { struct bpf_ksym *ksym; unsigned int it = 0; int ret = -ERANGE; if (!bpf_jit_kallsyms_enabled()) return ret; rcu_read_lock(); list_for_each_entry_rcu(ksym, &bpf_kallsyms, lnode) { if (it++ != symnum) continue; strscpy(sym, ksym->name, KSYM_NAME_LEN); *value = ksym->start; *type = BPF_SYM_ELF_TYPE; ret = 0; break; } rcu_read_unlock(); return ret; } int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; static const u32 poke_tab_max = 1024; u32 slot = prog->aux->size_poke_tab; u32 size = slot + 1; if (size > poke_tab_max) return -ENOSPC; if (poke->tailcall_target || poke->tailcall_target_stable || poke->tailcall_bypass || poke->adj_off || poke->bypass_addr) return -EINVAL; switch (poke->reason) { case BPF_POKE_REASON_TAIL_CALL: if (!poke->tail_call.map) return -EINVAL; break; default: return -EINVAL; } tab = krealloc_array(tab, size, sizeof(*poke), GFP_KERNEL); if (!tab) return -ENOMEM; memcpy(&tab[slot], poke, sizeof(*poke)); prog->aux->size_poke_tab = size; prog->aux->poke_tab = tab; return slot; } /* * BPF program pack allocator. * * Most BPF programs are pretty small. Allocating a hole page for each * program is sometime a waste. Many small bpf program also adds pressure * to instruction TLB. To solve this issue, we introduce a BPF program pack * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86) * to host BPF programs. */ #define BPF_PROG_CHUNK_SHIFT 6 #define BPF_PROG_CHUNK_SIZE (1 << BPF_PROG_CHUNK_SHIFT) #define BPF_PROG_CHUNK_MASK (~(BPF_PROG_CHUNK_SIZE - 1)) struct bpf_prog_pack { struct list_head list; void *ptr; unsigned long bitmap[]; }; void bpf_jit_fill_hole_with_zero(void *area, unsigned int size) { memset(area, 0, size); } #define BPF_PROG_SIZE_TO_NBITS(size) (round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE) static DEFINE_MUTEX(pack_mutex); static LIST_HEAD(pack_list); /* PMD_SIZE is not available in some special config, e.g. ARCH=arm with * CONFIG_MMU=n. Use PAGE_SIZE in these cases. */ #ifdef PMD_SIZE /* PMD_SIZE is really big for some archs. It doesn't make sense to * reserve too much memory in one allocation. Hardcode BPF_PROG_PACK_SIZE to * 2MiB * num_possible_nodes(). On most architectures PMD_SIZE will be * greater than or equal to 2MB. */ #define BPF_PROG_PACK_SIZE (SZ_2M * num_possible_nodes()) #else #define BPF_PROG_PACK_SIZE PAGE_SIZE #endif #define BPF_PROG_CHUNK_COUNT (BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE) static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_prog_pack *pack; int err; pack = kzalloc(struct_size(pack, bitmap, BITS_TO_LONGS(BPF_PROG_CHUNK_COUNT)), GFP_KERNEL); if (!pack) return NULL; pack->ptr = bpf_jit_alloc_exec(BPF_PROG_PACK_SIZE); if (!pack->ptr) goto out; bpf_fill_ill_insns(pack->ptr, BPF_PROG_PACK_SIZE); bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE); set_vm_flush_reset_perms(pack->ptr); err = set_memory_rox((unsigned long)pack->ptr, BPF_PROG_PACK_SIZE / PAGE_SIZE); if (err) goto out; list_add_tail(&pack->list, &pack_list); return pack; out: bpf_jit_free_exec(pack->ptr); kfree(pack); return NULL; } void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) { unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size); struct bpf_prog_pack *pack; unsigned long pos; void *ptr = NULL; mutex_lock(&pack_mutex); if (size > BPF_PROG_PACK_SIZE) { size = round_up(size, PAGE_SIZE); ptr = bpf_jit_alloc_exec(size); if (ptr) { int err; bpf_fill_ill_insns(ptr, size); set_vm_flush_reset_perms(ptr); err = set_memory_rox((unsigned long)ptr, size / PAGE_SIZE); if (err) { bpf_jit_free_exec(ptr); ptr = NULL; } } goto out; } list_for_each_entry(pack, &pack_list, list) { pos = bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0, nbits, 0); if (pos < BPF_PROG_CHUNK_COUNT) goto found_free_area; } pack = alloc_new_pack(bpf_fill_ill_insns); if (!pack) goto out; pos = 0; found_free_area: bitmap_set(pack->bitmap, pos, nbits); ptr = (void *)(pack->ptr) + (pos << BPF_PROG_CHUNK_SHIFT); out: mutex_unlock(&pack_mutex); return ptr; } void bpf_prog_pack_free(void *ptr, u32 size) { struct bpf_prog_pack *pack = NULL, *tmp; unsigned int nbits; unsigned long pos; mutex_lock(&pack_mutex); if (size > BPF_PROG_PACK_SIZE) { bpf_jit_free_exec(ptr); goto out; } list_for_each_entry(tmp, &pack_list, list) { if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) { pack = tmp; break; } } if (WARN_ONCE(!pack, "bpf_prog_pack bug\n")) goto out; nbits = BPF_PROG_SIZE_TO_NBITS(size); pos = ((unsigned long)ptr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT; WARN_ONCE(bpf_arch_text_invalidate(ptr, size), "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n"); bitmap_clear(pack->bitmap, pos, nbits); if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0, BPF_PROG_CHUNK_COUNT, 0) == 0) { list_del(&pack->list); bpf_jit_free_exec(pack->ptr); kfree(pack); } out: mutex_unlock(&pack_mutex); } static atomic_long_t bpf_jit_current; /* Can be overridden by an arch's JIT compiler if it has a custom, * dedicated BPF backend memory area, or if neither of the two * below apply. */ u64 __weak bpf_jit_alloc_exec_limit(void) { #if defined(MODULES_VADDR) return MODULES_END - MODULES_VADDR; #else return VMALLOC_END - VMALLOC_START; #endif } static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ bpf_jit_limit_max = bpf_jit_alloc_exec_limit(); bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 1, PAGE_SIZE), LONG_MAX); return 0; } pure_initcall(bpf_jit_charge_init); int bpf_jit_charge_modmem(u32 size) { if (atomic_long_add_return(size, &bpf_jit_current) > READ_ONCE(bpf_jit_limit)) { if (!bpf_capable()) { atomic_long_sub(size, &bpf_jit_current); return -EPERM; } } return 0; } void bpf_jit_uncharge_modmem(u32 size) { atomic_long_sub(size, &bpf_jit_current); } void *__weak bpf_jit_alloc_exec(unsigned long size) { return execmem_alloc(EXECMEM_BPF, size); } void __weak bpf_jit_free_exec(void *addr) { execmem_free(addr); } struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *hdr; u32 size, hole, start; WARN_ON_ONCE(!is_power_of_2(alignment) || alignment > BPF_IMAGE_ALIGNMENT); /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); if (bpf_jit_charge_modmem(size)) return NULL; hdr = bpf_jit_alloc_exec(size); if (!hdr) { bpf_jit_uncharge_modmem(size); return NULL; } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); hdr->size = size; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = get_random_u32_below(hole) & ~(alignment - 1); /* Leave a random number of instructions before BPF code. */ *image_ptr = &hdr->image[start]; return hdr; } void bpf_jit_binary_free(struct bpf_binary_header *hdr) { u32 size = hdr->size; bpf_jit_free_exec(hdr); bpf_jit_uncharge_modmem(size); } /* Allocate jit binary from bpf_prog_pack allocator. * Since the allocated memory is RO+X, the JIT engine cannot write directly * to the memory. To solve this problem, a RW buffer is also allocated at * as the same time. The JIT engine should calculate offsets based on the * RO memory address, but write JITed program to the RW buffer. Once the * JIT engine finishes, it calls bpf_jit_binary_pack_finalize, which copies * the JITed program to the RO memory. */ struct bpf_binary_header * bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, struct bpf_binary_header **rw_header, u8 **rw_image, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *ro_header; u32 size, hole, start; WARN_ON_ONCE(!is_power_of_2(alignment) || alignment > BPF_IMAGE_ALIGNMENT); /* add 16 bytes for a random section of illegal instructions */ size = round_up(proglen + sizeof(*ro_header) + 16, BPF_PROG_CHUNK_SIZE); if (bpf_jit_charge_modmem(size)) return NULL; ro_header = bpf_prog_pack_alloc(size, bpf_fill_ill_insns); if (!ro_header) { bpf_jit_uncharge_modmem(size); return NULL; } *rw_header = kvmalloc(size, GFP_KERNEL); if (!*rw_header) { bpf_prog_pack_free(ro_header, size); bpf_jit_uncharge_modmem(size); return NULL; } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(*rw_header, size); (*rw_header)->size = size; hole = min_t(unsigned int, size - (proglen + sizeof(*ro_header)), BPF_PROG_CHUNK_SIZE - sizeof(*ro_header)); start = get_random_u32_below(hole) & ~(alignment - 1); *image_ptr = &ro_header->image[start]; *rw_image = &(*rw_header)->image[start]; return ro_header; } /* Copy JITed text from rw_header to its final location, the ro_header. */ int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header) { void *ptr; ptr = bpf_arch_text_copy(ro_header, rw_header, rw_header->size); kvfree(rw_header); if (IS_ERR(ptr)) { bpf_prog_pack_free(ro_header, ro_header->size); return PTR_ERR(ptr); } return 0; } /* bpf_jit_binary_pack_free is called in two different scenarios: * 1) when the program is freed after; * 2) when the JIT engine fails (before bpf_jit_binary_pack_finalize). * For case 2), we need to free both the RO memory and the RW buffer. * * bpf_jit_binary_pack_free requires proper ro_header->size. However, * bpf_jit_binary_pack_alloc does not set it. Therefore, ro_header->size * must be set with either bpf_jit_binary_pack_finalize (normal path) or * bpf_arch_text_copy (when jit fails). */ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header) { u32 size = ro_header->size; bpf_prog_pack_free(ro_header, size); kvfree(rw_header); bpf_jit_uncharge_modmem(size); } struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp) { unsigned long real_start = (unsigned long)fp->bpf_func; unsigned long addr; addr = real_start & BPF_PROG_CHUNK_MASK; return (void *)addr; } static inline struct bpf_binary_header * bpf_jit_binary_hdr(const struct bpf_prog *fp) { unsigned long real_start = (unsigned long)fp->bpf_func; unsigned long addr; addr = real_start & PAGE_MASK; return (void *)addr; } /* This symbol is only overridden by archs that have different * requirements than the usual eBPF JITs, f.e. when they only * implement cBPF JIT, do not set images read-only, etc. */ void __weak bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) { struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); bpf_jit_binary_free(hdr); WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp)); } bpf_prog_unlock_free(fp); } int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed) { s16 off = insn->off; s32 imm = insn->imm; u8 *addr; int err; *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; if (!*func_addr_fixed) { /* Place-holder address till the last pass has collected * all addresses for JITed subprograms in which case we * can pick them up from prog->aux. */ if (!extra_pass) addr = NULL; else if (prog->aux->func && off >= 0 && off < prog->aux->real_func_cnt) addr = (u8 *)prog->aux->func[off]->bpf_func; else return -EINVAL; } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && bpf_jit_supports_far_kfunc_call()) { err = bpf_get_kfunc_addr(prog, insn->imm, insn->off, &addr); if (err) return err; } else { /* Address of a BPF helper call. Since part of the core * kernel, it's always at a fixed location. __bpf_call_base * and the helper with imm relative to it are both in core * kernel. */ addr = (u8 *)__bpf_call_base + imm; } *func_addr = (unsigned long)addr; return 0; } static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff, bool emit_zext) { struct bpf_insn *to = to_buff; u32 imm_rnd = get_random_u32(); s16 off; BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG); /* Constraints on AX register: * * AX register is inaccessible from user space. It is mapped in * all JITs, and used here for constant blinding rewrites. It is * typically "stateless" meaning its contents are only valid within * the executed instruction, but not across several instructions. * There are a few exceptions however which are further detailed * below. * * Constant blinding is only used by JITs, not in the interpreter. * The interpreter uses AX in some occasions as a local temporary * register e.g. in DIV or MOD instructions. * * In restricted circumstances, the verifier can also use the AX * register for rewrites as long as they do not interfere with * the above cases! */ if (from->dst_reg == BPF_REG_AX || from->src_reg == BPF_REG_AX) goto out; if (from->imm == 0 && (from->code == (BPF_ALU | BPF_MOV | BPF_K) || from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) { *to++ = BPF_ALU64_REG(BPF_XOR, from->dst_reg, from->dst_reg); goto out; } switch (from->code) { case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MOV | BPF_K: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU32_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_ALU64 | BPF_ADD | BPF_K: case BPF_ALU64 | BPF_SUB | BPF_K: case BPF_ALU64 | BPF_AND | BPF_K: case BPF_ALU64 | BPF_OR | BPF_K: case BPF_ALU64 | BPF_XOR | BPF_K: case BPF_ALU64 | BPF_MUL | BPF_K: case BPF_ALU64 | BPF_MOV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_MOD | BPF_K: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_REG_OFF(from->code, from->dst_reg, BPF_REG_AX, from->off); break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSLE | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; if (off < 0) off -= 2; *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; case BPF_JMP32 | BPF_JEQ | BPF_K: case BPF_JMP32 | BPF_JNE | BPF_K: case BPF_JMP32 | BPF_JGT | BPF_K: case BPF_JMP32 | BPF_JLT | BPF_K: case BPF_JMP32 | BPF_JGE | BPF_K: case BPF_JMP32 | BPF_JLE | BPF_K: case BPF_JMP32 | BPF_JSGT | BPF_K: case BPF_JMP32 | BPF_JSLT | BPF_K: case BPF_JMP32 | BPF_JSGE | BPF_K: case BPF_JMP32 | BPF_JSLE | BPF_K: case BPF_JMP32 | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; if (off < 0) off -= 2; *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_JMP32_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; case BPF_LD | BPF_IMM | BPF_DW: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); *to++ = BPF_ALU64_REG(BPF_MOV, aux[0].dst_reg, BPF_REG_AX); break; case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */ *to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm); *to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); if (emit_zext) *to++ = BPF_ZEXT_REG(BPF_REG_AX); *to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX); break; case BPF_ST | BPF_MEM | BPF_DW: case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off); break; } out: return to - to_buff; } static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other, gfp_t gfp_extra_flags) { gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; fp = __vmalloc(fp_other->pages * PAGE_SIZE, gfp_flags); if (fp != NULL) { /* aux->prog still points to the fp_other one, so * when promoting the clone to the real program, * this still needs to be adapted. */ memcpy(fp, fp_other, fp_other->pages * PAGE_SIZE); } return fp; } static void bpf_prog_clone_free(struct bpf_prog *fp) { /* aux was stolen by the other clone, so we cannot free * it from this path! It will be freed eventually by the * other program on release. * * At this point, we don't need a deferred release since * clone is guaranteed to not be locked. */ fp->aux = NULL; fp->stats = NULL; fp->active = NULL; __bpf_prog_free(fp); } void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other) { /* We have to repoint aux->prog to self, as we don't * know whether fp here is the clone or the original. */ fp->aux->prog = fp; bpf_prog_clone_free(fp_other); } struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) { struct bpf_insn insn_buff[16], aux[2]; struct bpf_prog *clone, *tmp; int insn_delta, insn_cnt; struct bpf_insn *insn; int i, rewritten; if (!prog->blinding_requested || prog->blinded) return prog; clone = bpf_prog_clone_create(prog, GFP_USER); if (!clone) return ERR_PTR(-ENOMEM); insn_cnt = clone->len; insn = clone->insnsi; for (i = 0; i < insn_cnt; i++, insn++) { if (bpf_pseudo_func(insn)) { /* ld_imm64 with an address of bpf subprog is not * a user controlled constant. Don't randomize it, * since it will conflict with jit_subprogs() logic. */ insn++; i++; continue; } /* We temporarily need to hold the original ld64 insn * so that we can still access the first part in the * second blinding run. */ if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW) && insn[1].code == 0) memcpy(aux, insn, sizeof(aux)); rewritten = bpf_jit_blind_insn(insn, aux, insn_buff, clone->aux->verifier_zext); if (!rewritten) continue; tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten); if (IS_ERR(tmp)) { /* Patching may have repointed aux->prog during * realloc from the original one, so we need to * fix it up here on error. */ bpf_jit_prog_release_other(prog, clone); return tmp; } clone = tmp; insn_delta = rewritten - 1; /* Walk new program and skip insns we just inserted. */ insn = clone->insnsi + i + insn_delta; insn_cnt += insn_delta; i += insn_delta; } clone->blinded = 1; return clone; } #endif /* CONFIG_BPF_JIT */ /* Base function for offset calculation. Needs to go into .text section, * therefore keeping it non-static as well; will also be used by JITs * anyway later on, so do not let the compiler omit it. This also needs * to go into kallsyms for correlation from e.g. bpftool, so naming * must not change. */ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return 0; } EXPORT_SYMBOL_GPL(__bpf_call_base); /* All UAPI available opcodes. */ #define BPF_INSN_MAP(INSN_2, INSN_3) \ /* 32 bit ALU operations. */ \ /* Register based. */ \ INSN_3(ALU, ADD, X), \ INSN_3(ALU, SUB, X), \ INSN_3(ALU, AND, X), \ INSN_3(ALU, OR, X), \ INSN_3(ALU, LSH, X), \ INSN_3(ALU, RSH, X), \ INSN_3(ALU, XOR, X), \ INSN_3(ALU, MUL, X), \ INSN_3(ALU, MOV, X), \ INSN_3(ALU, ARSH, X), \ INSN_3(ALU, DIV, X), \ INSN_3(ALU, MOD, X), \ INSN_2(ALU, NEG), \ INSN_3(ALU, END, TO_BE), \ INSN_3(ALU, END, TO_LE), \ /* Immediate based. */ \ INSN_3(ALU, ADD, K), \ INSN_3(ALU, SUB, K), \ INSN_3(ALU, AND, K), \ INSN_3(ALU, OR, K), \ INSN_3(ALU, LSH, K), \ INSN_3(ALU, RSH, K), \ INSN_3(ALU, XOR, K), \ INSN_3(ALU, MUL, K), \ INSN_3(ALU, MOV, K), \ INSN_3(ALU, ARSH, K), \ INSN_3(ALU, DIV, K), \ INSN_3(ALU, MOD, K), \ /* 64 bit ALU operations. */ \ /* Register based. */ \ INSN_3(ALU64, ADD, X), \ INSN_3(ALU64, SUB, X), \ INSN_3(ALU64, AND, X), \ INSN_3(ALU64, OR, X), \ INSN_3(ALU64, LSH, X), \ INSN_3(ALU64, RSH, X), \ INSN_3(ALU64, XOR, X), \ INSN_3(ALU64, MUL, X), \ INSN_3(ALU64, MOV, X), \ INSN_3(ALU64, ARSH, X), \ INSN_3(ALU64, DIV, X), \ INSN_3(ALU64, MOD, X), \ INSN_2(ALU64, NEG), \ INSN_3(ALU64, END, TO_LE), \ /* Immediate based. */ \ INSN_3(ALU64, ADD, K), \ INSN_3(ALU64, SUB, K), \ INSN_3(ALU64, AND, K), \ INSN_3(ALU64, OR, K), \ INSN_3(ALU64, LSH, K), \ INSN_3(ALU64, RSH, K), \ INSN_3(ALU64, XOR, K), \ INSN_3(ALU64, MUL, K), \ INSN_3(ALU64, MOV, K), \ INSN_3(ALU64, ARSH, K), \ INSN_3(ALU64, DIV, K), \ INSN_3(ALU64, MOD, K), \ /* Call instruction. */ \ INSN_2(JMP, CALL), \ /* Exit instruction. */ \ INSN_2(JMP, EXIT), \ /* 32-bit Jump instructions. */ \ /* Register based. */ \ INSN_3(JMP32, JEQ, X), \ INSN_3(JMP32, JNE, X), \ INSN_3(JMP32, JGT, X), \ INSN_3(JMP32, JLT, X), \ INSN_3(JMP32, JGE, X), \ INSN_3(JMP32, JLE, X), \ INSN_3(JMP32, JSGT, X), \ INSN_3(JMP32, JSLT, X), \ INSN_3(JMP32, JSGE, X), \ INSN_3(JMP32, JSLE, X), \ INSN_3(JMP32, JSET, X), \ /* Immediate based. */ \ INSN_3(JMP32, JEQ, K), \ INSN_3(JMP32, JNE, K), \ INSN_3(JMP32, JGT, K), \ INSN_3(JMP32, JLT, K), \ INSN_3(JMP32, JGE, K), \ INSN_3(JMP32, JLE, K), \ INSN_3(JMP32, JSGT, K), \ INSN_3(JMP32, JSLT, K), \ INSN_3(JMP32, JSGE, K), \ INSN_3(JMP32, JSLE, K), \ INSN_3(JMP32, JSET, K), \ /* Jump instructions. */ \ /* Register based. */ \ INSN_3(JMP, JEQ, X), \ INSN_3(JMP, JNE, X), \ INSN_3(JMP, JGT, X), \ INSN_3(JMP, JLT, X), \ INSN_3(JMP, JGE, X), \ INSN_3(JMP, JLE, X), \ INSN_3(JMP, JSGT, X), \ INSN_3(JMP, JSLT, X), \ INSN_3(JMP, JSGE, X), \ INSN_3(JMP, JSLE, X), \ INSN_3(JMP, JSET, X), \ /* Immediate based. */ \ INSN_3(JMP, JEQ, K), \ INSN_3(JMP, JNE, K), \ INSN_3(JMP, JGT, K), \ INSN_3(JMP, JLT, K), \ INSN_3(JMP, JGE, K), \ INSN_3(JMP, JLE, K), \ INSN_3(JMP, JSGT, K), \ INSN_3(JMP, JSLT, K), \ INSN_3(JMP, JSGE, K), \ INSN_3(JMP, JSLE, K), \ INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ INSN_2(JMP32, JA), \ /* Store instructions. */ \ /* Register based. */ \ INSN_3(STX, MEM, B), \ INSN_3(STX, MEM, H), \ INSN_3(STX, MEM, W), \ INSN_3(STX, MEM, DW), \ INSN_3(STX, ATOMIC, W), \ INSN_3(STX, ATOMIC, DW), \ /* Immediate based. */ \ INSN_3(ST, MEM, B), \ INSN_3(ST, MEM, H), \ INSN_3(ST, MEM, W), \ INSN_3(ST, MEM, DW), \ /* Load instructions. */ \ /* Register based. */ \ INSN_3(LDX, MEM, B), \ INSN_3(LDX, MEM, H), \ INSN_3(LDX, MEM, W), \ INSN_3(LDX, MEM, DW), \ INSN_3(LDX, MEMSX, B), \ INSN_3(LDX, MEMSX, H), \ INSN_3(LDX, MEMSX, W), \ /* Immediate based. */ \ INSN_3(LD, IMM, DW) bool bpf_opcode_in_insntable(u8 code) { #define BPF_INSN_2_TBL(x, y) [BPF_##x | BPF_##y] = true #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true static const bool public_insntable[256] = { [0 ... 255] = false, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL), /* UAPI exposed, but rewritten opcodes. cBPF carry-over. */ [BPF_LD | BPF_ABS | BPF_B] = true, [BPF_LD | BPF_ABS | BPF_H] = true, [BPF_LD | BPF_ABS | BPF_W] = true, [BPF_LD | BPF_IND | BPF_B] = true, [BPF_LD | BPF_IND | BPF_H] = true, [BPF_LD | BPF_IND | BPF_W] = true, [BPF_JMP | BPF_JCOND] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL return public_insntable[code]; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON /** * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers * @insn: is the array of eBPF instructions * * Decode and execute eBPF instructions. * * Return: whatever value is in %BPF_R0 at program exit */ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) { #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z static const void * const jumptable[256] __annotate_jump_table = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_LBL, BPF_INSN_3_LBL), /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC, [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW, [BPF_LDX | BPF_PROBE_MEMSX | BPF_B] = &&LDX_PROBE_MEMSX_B, [BPF_LDX | BPF_PROBE_MEMSX | BPF_H] = &&LDX_PROBE_MEMSX_H, [BPF_LDX | BPF_PROBE_MEMSX | BPF_W] = &&LDX_PROBE_MEMSX_W, }; #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL u32 tail_call_cnt = 0; #define CONT ({ insn++; goto select_insn; }) #define CONT_JMP ({ insn++; goto select_insn; }) select_insn: goto *jumptable[insn->code]; /* Explicitly mask the register-based shift amounts with 63 or 31 * to avoid undefined behavior. Normally this won't affect the * generated code, for example, in case of native 64 bit archs such * as x86-64 or arm64, the compiler is optimizing the AND away for * the interpreter. In case of JITs, each of the JIT backends compiles * the BPF shift operations to machine instructions which produce * implementation-defined results in such a case; the resulting * contents of the register may be arbitrary, but program behaviour * as a whole remains defined. In other words, in case of JIT backends, * the AND must /not/ be added to the emitted LSH/RSH/ARSH translation. */ /* ALU (shifts) */ #define SHT(OPCODE, OP) \ ALU64_##OPCODE##_X: \ DST = DST OP (SRC & 63); \ CONT; \ ALU_##OPCODE##_X: \ DST = (u32) DST OP ((u32) SRC & 31); \ CONT; \ ALU64_##OPCODE##_K: \ DST = DST OP IMM; \ CONT; \ ALU_##OPCODE##_K: \ DST = (u32) DST OP (u32) IMM; \ CONT; /* ALU (rest) */ #define ALU(OPCODE, OP) \ ALU64_##OPCODE##_X: \ DST = DST OP SRC; \ CONT; \ ALU_##OPCODE##_X: \ DST = (u32) DST OP (u32) SRC; \ CONT; \ ALU64_##OPCODE##_K: \ DST = DST OP IMM; \ CONT; \ ALU_##OPCODE##_K: \ DST = (u32) DST OP (u32) IMM; \ CONT; ALU(ADD, +) ALU(SUB, -) ALU(AND, &) ALU(OR, |) ALU(XOR, ^) ALU(MUL, *) SHT(LSH, <<) SHT(RSH, >>) #undef SHT #undef ALU ALU_NEG: DST = (u32) -DST; CONT; ALU64_NEG: DST = -DST; CONT; ALU_MOV_X: switch (OFF) { case 0: DST = (u32) SRC; break; case 8: DST = (u32)(s8) SRC; break; case 16: DST = (u32)(s16) SRC; break; } CONT; ALU_MOV_K: DST = (u32) IMM; CONT; ALU64_MOV_X: switch (OFF) { case 0: DST = SRC; break; case 8: DST = (s8) SRC; break; case 16: DST = (s16) SRC; break; case 32: DST = (s32) SRC; break; } CONT; ALU64_MOV_K: DST = IMM; CONT; LD_IMM_DW: DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32; insn++; CONT; ALU_ARSH_X: DST = (u64) (u32) (((s32) DST) >> (SRC & 31)); CONT; ALU_ARSH_K: DST = (u64) (u32) (((s32) DST) >> IMM); CONT; ALU64_ARSH_X: (*(s64 *) &DST) >>= (SRC & 63); CONT; ALU64_ARSH_K: (*(s64 *) &DST) >>= IMM; CONT; ALU64_MOD_X: switch (OFF) { case 0: div64_u64_rem(DST, SRC, &AX); DST = AX; break; case 1: AX = div64_s64(DST, SRC); DST = DST - AX * SRC; break; } CONT; ALU_MOD_X: switch (OFF) { case 0: AX = (u32) DST; DST = do_div(AX, (u32) SRC); break; case 1: AX = abs((s32)DST); AX = do_div(AX, abs((s32)SRC)); if ((s32)DST < 0) DST = (u32)-AX; else DST = (u32)AX; break; } CONT; ALU64_MOD_K: switch (OFF) { case 0: div64_u64_rem(DST, IMM, &AX); DST = AX; break; case 1: AX = div64_s64(DST, IMM); DST = DST - AX * IMM; break; } CONT; ALU_MOD_K: switch (OFF) { case 0: AX = (u32) DST; DST = do_div(AX, (u32) IMM); break; case 1: AX = abs((s32)DST); AX = do_div(AX, abs((s32)IMM)); if ((s32)DST < 0) DST = (u32)-AX; else DST = (u32)AX; break; } CONT; ALU64_DIV_X: switch (OFF) { case 0: DST = div64_u64(DST, SRC); break; case 1: DST = div64_s64(DST, SRC); break; } CONT; ALU_DIV_X: switch (OFF) { case 0: AX = (u32) DST; do_div(AX, (u32) SRC); DST = (u32) AX; break; case 1: AX = abs((s32)DST); do_div(AX, abs((s32)SRC)); if (((s32)DST < 0) == ((s32)SRC < 0)) DST = (u32)AX; else DST = (u32)-AX; break; } CONT; ALU64_DIV_K: switch (OFF) { case 0: DST = div64_u64(DST, IMM); break; case 1: DST = div64_s64(DST, IMM); break; } CONT; ALU_DIV_K: switch (OFF) { case 0: AX = (u32) DST; do_div(AX, (u32) IMM); DST = (u32) AX; break; case 1: AX = abs((s32)DST); do_div(AX, abs((s32)IMM)); if (((s32)DST < 0) == ((s32)IMM < 0)) DST = (u32)AX; else DST = (u32)-AX; break; } CONT; ALU_END_TO_BE: switch (IMM) { case 16: DST = (__force u16) cpu_to_be16(DST); break; case 32: DST = (__force u32) cpu_to_be32(DST); break; case 64: DST = (__force u64) cpu_to_be64(DST); break; } CONT; ALU_END_TO_LE: switch (IMM) { case 16: DST = (__force u16) cpu_to_le16(DST); break; case 32: DST = (__force u32) cpu_to_le32(DST); break; case 64: DST = (__force u64) cpu_to_le64(DST); break; } CONT; ALU64_END_TO_LE: switch (IMM) { case 16: DST = (__force u16) __swab16(DST); break; case 32: DST = (__force u32) __swab32(DST); break; case 64: DST = (__force u64) __swab64(DST); break; } CONT; /* CALL */ JMP_CALL: /* Function call scratches BPF_R1-BPF_R5 registers, * preserves BPF_R6-BPF_R9, and stores return value * into BPF_R0. */ BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, BPF_R4, BPF_R5); CONT; JMP_CALL_ARGS: BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2, BPF_R3, BPF_R4, BPF_R5, insn + insn->off + 1); CONT; JMP_TAIL_CALL: { struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; prog = READ_ONCE(array->ptrs[index]); if (!prog) goto out; /* ARG1 at this point is guaranteed to point to CTX from * the verifier side due to the fact that the tail call is * handled like a helper, that is, bpf_tail_call_proto, * where arg1_type is ARG_PTR_TO_CTX. */ insn = prog->insnsi; goto select_insn; out: CONT; } JMP_JA: insn += insn->off; CONT; JMP32_JA: insn += insn->imm; CONT; JMP_EXIT: return BPF_R0; /* JMP */ #define COND_JMP(SIGN, OPCODE, CMP_OP) \ JMP_##OPCODE##_X: \ if ((SIGN##64) DST CMP_OP (SIGN##64) SRC) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP32_##OPCODE##_X: \ if ((SIGN##32) DST CMP_OP (SIGN##32) SRC) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP_##OPCODE##_K: \ if ((SIGN##64) DST CMP_OP (SIGN##64) IMM) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; \ JMP32_##OPCODE##_K: \ if ((SIGN##32) DST CMP_OP (SIGN##32) IMM) { \ insn += insn->off; \ CONT_JMP; \ } \ CONT; COND_JMP(u, JEQ, ==) COND_JMP(u, JNE, !=) COND_JMP(u, JGT, >) COND_JMP(u, JLT, <) COND_JMP(u, JGE, >=) COND_JMP(u, JLE, <=) COND_JMP(u, JSET, &) COND_JMP(s, JSGT, >) COND_JMP(s, JSLT, <) COND_JMP(s, JSGE, >=) COND_JMP(s, JSLE, <=) #undef COND_JMP /* ST, STX and LDX*/ ST_NOSPEC: /* Speculation barrier for mitigating Speculative Store Bypass. * In case of arm64, we rely on the firmware mitigation as * controlled via the ssbd kernel parameter. Whenever the * mitigation is enabled, it works for all of the kernel code * with no need to provide any additional instructions here. * In case of x86, we use 'lfence' insn for mitigation. We * reuse preexisting logic from Spectre v1 mitigation that * happens to produce the required code on x86 for v4 as well. */ barrier_nospec(); CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ CONT; \ ST_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \ CONT; \ LDX_MEM_##SIZEOP: \ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ CONT; \ LDX_PROBE_MEM_##SIZEOP: \ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ (const void *)(long) (SRC + insn->off)); \ DST = *((SIZE *)&DST); \ CONT; LDST(B, u8) LDST(H, u16) LDST(W, u32) LDST(DW, u64) #undef LDST #define LDSX(SIZEOP, SIZE) \ LDX_MEMSX_##SIZEOP: \ DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ CONT; \ LDX_PROBE_MEMSX_##SIZEOP: \ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \ (const void *)(long) (SRC + insn->off)); \ DST = *((SIZE *)&DST); \ CONT; LDSX(B, s8) LDSX(H, s16) LDSX(W, s32) #undef LDSX #define ATOMIC_ALU_OP(BOP, KOP) \ case BOP: \ if (BPF_SIZE(insn->code) == BPF_W) \ atomic_##KOP((u32) SRC, (atomic_t *)(unsigned long) \ (DST + insn->off)); \ else \ atomic64_##KOP((u64) SRC, (atomic64_t *)(unsigned long) \ (DST + insn->off)); \ break; \ case BOP | BPF_FETCH: \ if (BPF_SIZE(insn->code) == BPF_W) \ SRC = (u32) atomic_fetch_##KOP( \ (u32) SRC, \ (atomic_t *)(unsigned long) (DST + insn->off)); \ else \ SRC = (u64) atomic64_fetch_##KOP( \ (u64) SRC, \ (atomic64_t *)(unsigned long) (DST + insn->off)); \ break; STX_ATOMIC_DW: STX_ATOMIC_W: switch (IMM) { ATOMIC_ALU_OP(BPF_ADD, add) ATOMIC_ALU_OP(BPF_AND, and) ATOMIC_ALU_OP(BPF_OR, or) ATOMIC_ALU_OP(BPF_XOR, xor) #undef ATOMIC_ALU_OP case BPF_XCHG: if (BPF_SIZE(insn->code) == BPF_W) SRC = (u32) atomic_xchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) SRC); else SRC = (u64) atomic64_xchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) SRC); break; case BPF_CMPXCHG: if (BPF_SIZE(insn->code) == BPF_W) BPF_R0 = (u32) atomic_cmpxchg( (atomic_t *)(unsigned long) (DST + insn->off), (u32) BPF_R0, (u32) SRC); else BPF_R0 = (u64) atomic64_cmpxchg( (atomic64_t *)(unsigned long) (DST + insn->off), (u64) BPF_R0, (u64) SRC); break; default: goto default_label; } CONT; default_label: /* If we ever reach this, we have a bug somewhere. Die hard here * instead of just returning 0; we could be somewhere in a subprog, * so execution could continue otherwise which we do /not/ want. * * Note, verifier whitelists all opcodes in bpf_opcode_in_insntable(). */ pr_warn("BPF interpreter: unknown opcode %02x (imm: 0x%x)\n", insn->code, insn->imm); BUG_ON(1); return 0; } #define PROG_NAME(stack_size) __bpf_prog_run##stack_size #define DEFINE_BPF_PROG_RUN(stack_size) \ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ u64 regs[MAX_BPF_EXT_REG] = {}; \ \ kmsan_unpoison_memory(stack, sizeof(stack)); \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ ARG1 = (u64) (unsigned long) ctx; \ return ___bpf_prog_run(regs, insn); \ } #define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size #define DEFINE_BPF_PROG_RUN_ARGS(stack_size) \ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \ const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ u64 regs[MAX_BPF_EXT_REG]; \ \ kmsan_unpoison_memory(stack, sizeof(stack)); \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ BPF_R1 = r1; \ BPF_R2 = r2; \ BPF_R3 = r3; \ BPF_R4 = r4; \ BPF_R5 = r5; \ return ___bpf_prog_run(regs, insn); \ } #define EVAL1(FN, X) FN(X) #define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y) #define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y) #define EVAL4(FN, X, Y...) FN(X) EVAL3(FN, Y) #define EVAL5(FN, X, Y...) FN(X) EVAL4(FN, Y) #define EVAL6(FN, X, Y...) FN(X) EVAL5(FN, Y) EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512); EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192); EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384); EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512); #define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size), static unsigned int (*interpreters[])(const void *ctx, const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST #define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size), static __maybe_unused u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, const struct bpf_insn *insn) = { EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192) EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384) EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) }; #undef PROG_NAME_LIST #ifdef CONFIG_BPF_SYSCALL void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) { stack_depth = max_t(u32, stack_depth, 1); insn->off = (s16) insn->imm; insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] - __bpf_call_base_args; insn->code = BPF_JMP | BPF_CALL_ARGS; } #endif #else static unsigned int __bpf_prog_ret0_warn(const void *ctx, const struct bpf_insn *insn) { /* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON * is not working properly, so warn about it! */ WARN_ON_ONCE(1); return 0; } #endif bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp) { enum bpf_prog_type prog_type = resolve_prog_type(fp); bool ret; if (fp->kprobe_override) return false; /* XDP programs inserted into maps are not guaranteed to run on * a particular netdev (and can run outside driver context entirely * in the case of devmap and cpumap). Until device checks * are implemented, prohibit adding dev-bound programs to program maps. */ if (bpf_prog_is_dev_bound(fp->aux)) return false; spin_lock(&map->owner.lock); if (!map->owner.type) { /* There's no owner yet where we could check for * compatibility. */ map->owner.type = prog_type; map->owner.jited = fp->jited; map->owner.xdp_has_frags = fp->aux->xdp_has_frags; ret = true; } else { ret = map->owner.type == prog_type && map->owner.jited == fp->jited && map->owner.xdp_has_frags == fp->aux->xdp_has_frags; } spin_unlock(&map->owner.lock); return ret; } static int bpf_check_tail_call(const struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; int i, ret = 0; mutex_lock(&aux->used_maps_mutex); for (i = 0; i < aux->used_map_cnt; i++) { struct bpf_map *map = aux->used_maps[i]; if (!map_type_contains_progs(map)) continue; if (!bpf_prog_map_compatible(map, fp)) { ret = -EINVAL; goto out; } } out: mutex_unlock(&aux->used_maps_mutex); return ret; } static void bpf_prog_select_func(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; #else fp->bpf_func = __bpf_prog_ret0_warn; #endif } /** * bpf_prog_select_runtime - select exec runtime for BPF program * @fp: bpf_prog populated with BPF program * @err: pointer to error variable * * Try to JIT eBPF program, if JIT is not available, use interpreter. * The BPF program will be executed via bpf_prog_run() function. * * Return: the &fp argument along with &err set to 0 for success or * a negative errno code on failure */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { /* In case of BPF to BPF calls, verifier did all the prep * work with regards to JITing, etc. */ bool jit_needed = false; if (fp->bpf_func) goto finalize; if (IS_ENABLED(CONFIG_BPF_JIT_ALWAYS_ON) || bpf_prog_has_kfunc_call(fp)) jit_needed = true; bpf_prog_select_func(fp); /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during * blinding, bpf_int_jit_compile() must always return a * valid program, which in this case would simply not * be JITed, but falls back to the interpreter. */ if (!bpf_prog_is_offloaded(fp->aux)) { *err = bpf_prog_alloc_jited_linfo(fp); if (*err) return fp; fp = bpf_int_jit_compile(fp); bpf_prog_jit_attempt_done(fp); if (!fp->jited && jit_needed) { *err = -ENOTSUPP; return fp; } } else { *err = bpf_prog_offload_compile(fp); if (*err) return fp; } finalize: *err = bpf_prog_lock_ro(fp); if (*err) return fp; /* The tail call compatibility check can only be done at * this late stage as we need to determine, if we deal * with JITed or non JITed program concatenations and not * all eBPF JITs might immediately support all features. */ *err = bpf_check_tail_call(fp); return fp; } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); static unsigned int __bpf_prog_ret1(const void *ctx, const struct bpf_insn *insn) { return 1; } static struct bpf_prog_dummy { struct bpf_prog prog; } dummy_bpf_prog = { .prog = { .bpf_func = __bpf_prog_ret1, }, }; struct bpf_empty_prog_array bpf_empty_prog_array = { .null_prog = NULL, }; EXPORT_SYMBOL(bpf_empty_prog_array); struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { struct bpf_prog_array *p; if (prog_cnt) p = kzalloc(struct_size(p, items, prog_cnt + 1), flags); else p = &bpf_empty_prog_array.hdr; return p; } void bpf_prog_array_free(struct bpf_prog_array *progs) { if (!progs || progs == &bpf_empty_prog_array.hdr) return; kfree_rcu(progs, rcu); } static void __bpf_prog_array_free_sleepable_cb(struct rcu_head *rcu) { struct bpf_prog_array *progs; /* If RCU Tasks Trace grace period implies RCU grace period, there is * no need to call kfree_rcu(), just call kfree() directly. */ progs = container_of(rcu, struct bpf_prog_array, rcu); if (rcu_trace_implies_rcu_gp()) kfree(progs); else kfree_rcu(progs, rcu); } void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs) { if (!progs || progs == &bpf_empty_prog_array.hdr) return; call_rcu_tasks_trace(&progs->rcu, __bpf_prog_array_free_sleepable_cb); } int bpf_prog_array_length(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; u32 cnt = 0; for (item = array->items; item->prog; item++) if (item->prog != &dummy_bpf_prog.prog) cnt++; return cnt; } bool bpf_prog_array_is_empty(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; for (item = array->items; item->prog; item++) if (item->prog != &dummy_bpf_prog.prog) return false; return true; } static bool bpf_prog_array_copy_core(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt) { struct bpf_prog_array_item *item; int i = 0; for (item = array->items; item->prog; item++) { if (item->prog == &dummy_bpf_prog.prog) continue; prog_ids[i] = item->prog->aux->id; if (++i == request_cnt) { item++; break; } } return !!(item->prog); } int bpf_prog_array_copy_to_user(struct bpf_prog_array *array, __u32 __user *prog_ids, u32 cnt) { unsigned long err = 0; bool nospc; u32 *ids; /* users of this function are doing: * cnt = bpf_prog_array_length(); * if (cnt > 0) * bpf_prog_array_copy_to_user(..., cnt); * so below kcalloc doesn't need extra cnt > 0 check. */ ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN); if (!ids) return -ENOMEM; nospc = bpf_prog_array_copy_core(array, ids, cnt); err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); kfree(ids); if (err) return -EFAULT; if (nospc) return -ENOSPC; return 0; } void bpf_prog_array_delete_safe(struct bpf_prog_array *array, struct bpf_prog *old_prog) { struct bpf_prog_array_item *item; for (item = array->items; item->prog; item++) if (item->prog == old_prog) { WRITE_ONCE(item->prog, &dummy_bpf_prog.prog); break; } } /** * bpf_prog_array_delete_safe_at() - Replaces the program at the given * index into the program array with * a dummy no-op program. * @array: a bpf_prog_array * @index: the index of the program to replace * * Skips over dummy programs, by not counting them, when calculating * the position of the program to replace. * * Return: * * 0 - Success * * -EINVAL - Invalid index value. Must be a non-negative integer. * * -ENOENT - Index out of range */ int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index) { return bpf_prog_array_update_at(array, index, &dummy_bpf_prog.prog); } /** * bpf_prog_array_update_at() - Updates the program at the given index * into the program array. * @array: a bpf_prog_array * @index: the index of the program to update * @prog: the program to insert into the array * * Skips over dummy programs, by not counting them, when calculating * the position of the program to update. * * Return: * * 0 - Success * * -EINVAL - Invalid index value. Must be a non-negative integer. * * -ENOENT - Index out of range */ int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, struct bpf_prog *prog) { struct bpf_prog_array_item *item; if (unlikely(index < 0)) return -EINVAL; for (item = array->items; item->prog; item++) { if (item->prog == &dummy_bpf_prog.prog) continue; if (!index) { WRITE_ONCE(item->prog, prog); return 0; } index--; } return -ENOENT; } int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, u64 bpf_cookie, struct bpf_prog_array **new_array) { int new_prog_cnt, carry_prog_cnt = 0; struct bpf_prog_array_item *existing, *new; struct bpf_prog_array *array; bool found_exclude = false; /* Figure out how many existing progs we need to carry over to * the new array. */ if (old_array) { existing = old_array->items; for (; existing->prog; existing++) { if (existing->prog == exclude_prog) { found_exclude = true; continue; } if (existing->prog != &dummy_bpf_prog.prog) carry_prog_cnt++; if (existing->prog == include_prog) return -EEXIST; } } if (exclude_prog && !found_exclude) return -ENOENT; /* How many progs (not NULL) will be in the new array? */ new_prog_cnt = carry_prog_cnt; if (include_prog) new_prog_cnt += 1; /* Do we have any prog (not NULL) in the new array? */ if (!new_prog_cnt) { *new_array = NULL; return 0; } /* +1 as the end of prog_array is marked with NULL */ array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL); if (!array) return -ENOMEM; new = array->items; /* Fill in the new prog array */ if (carry_prog_cnt) { existing = old_array->items; for (; existing->prog; existing++) { if (existing->prog == exclude_prog || existing->prog == &dummy_bpf_prog.prog) continue; new->prog = existing->prog; new->bpf_cookie = existing->bpf_cookie; new++; } } if (include_prog) { new->prog = include_prog; new->bpf_cookie = bpf_cookie; new++; } new->prog = NULL; *new_array = array; return 0; } int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt) { u32 cnt = 0; if (array) cnt = bpf_prog_array_length(array); *prog_cnt = cnt; /* return early if user requested only program count or nothing to copy */ if (!request_cnt || !cnt) return 0; /* this function is called under trace/bpf_trace.c: bpf_event_mutex */ return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC : 0; } void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len) { struct bpf_map *map; bool sleepable; u32 i; sleepable = aux->prog->sleepable; for (i = 0; i < len; i++) { map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); if (sleepable) atomic64_dec(&map->sleepable_refcnt); bpf_map_put(map); } } static void bpf_free_used_maps(struct bpf_prog_aux *aux) { __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt); kfree(aux->used_maps); } void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len) { #ifdef CONFIG_BPF_SYSCALL struct btf_mod_pair *btf_mod; u32 i; for (i = 0; i < len; i++) { btf_mod = &used_btfs[i]; if (btf_mod->module) module_put(btf_mod->module); btf_put(btf_mod->btf); } #endif } static void bpf_free_used_btfs(struct bpf_prog_aux *aux) { __bpf_free_used_btfs(aux->used_btfs, aux->used_btf_cnt); kfree(aux->used_btfs); } static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; int i; aux = container_of(work, struct bpf_prog_aux, work); #ifdef CONFIG_BPF_SYSCALL bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab); #endif #ifdef CONFIG_CGROUP_BPF if (aux->cgroup_atype != CGROUP_BPF_ATTACH_TYPE_INVALID) bpf_cgroup_atype_put(aux->cgroup_atype); #endif bpf_free_used_maps(aux); bpf_free_used_btfs(aux); if (bpf_prog_is_dev_bound(aux)) bpf_prog_dev_bound_destroy(aux->prog); #ifdef CONFIG_PERF_EVENTS if (aux->prog->has_callchain_buf) put_callchain_buffers(); #endif if (aux->dst_trampoline) bpf_trampoline_put(aux->dst_trampoline); for (i = 0; i < aux->real_func_cnt; i++) { /* We can just unlink the subprog poke descriptor table as * it was originally linked to the main program and is also * released along with it. */ aux->func[i]->aux->poke_tab = NULL; bpf_jit_free(aux->func[i]); } if (aux->real_func_cnt) { kfree(aux->func); bpf_prog_unlock_free(aux->prog); } else { bpf_jit_free(aux->prog); } } void bpf_prog_free(struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; if (aux->dst_prog) bpf_prog_put(aux->dst_prog); bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } EXPORT_SYMBOL_GPL(bpf_prog_free); /* RNG for unprivileged user space with separated state from prandom_u32(). */ static DEFINE_PER_CPU(struct rnd_state, bpf_user_rnd_state); void bpf_user_rnd_init_once(void) { prandom_init_once(&bpf_user_rnd_state); } BPF_CALL_0(bpf_user_rnd_u32) { /* Should someone ever have the rather unwise idea to use some * of the registers passed into this function, then note that * this function is called from native eBPF and classic-to-eBPF * transformations. Register assignments from both sides are * different, f.e. classic always sets fn(ctx, A, X) here. */ struct rnd_state *state; u32 res; state = &get_cpu_var(bpf_user_rnd_state); res = prandom_u32_state(state); put_cpu_var(bpf_user_rnd_state); return res; } BPF_CALL_0(bpf_get_raw_cpu_id) { return raw_smp_processor_id(); } /* Weak definitions of helper functions in case we don't have bpf syscall. */ const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_map_push_elem_proto __weak; const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto __weak; const struct bpf_func_proto bpf_spin_lock_proto __weak; const struct bpf_func_proto bpf_spin_unlock_proto __weak; const struct bpf_func_proto bpf_jiffies64_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_tai_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_snprintf_btf_proto __weak; const struct bpf_func_proto bpf_seq_printf_btf_proto __weak; const struct bpf_func_proto bpf_set_retval_proto __weak; const struct bpf_func_proto bpf_get_retval_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { return NULL; } const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void) { return NULL; } u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { return -ENOTSUPP; } EXPORT_SYMBOL_GPL(bpf_event_output); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = { .func = NULL, .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; /* Stub for JITs that only support cBPF. eBPF programs are interpreted. * It is encouraged to implement bpf_int_jit_compile() instead, so that * eBPF and implicitly also cBPF can get JITed! */ struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog) { return prog; } /* Stub for JITs that support eBPF. All cBPF code gets transformed into * eBPF by the kernel and is later compiled by bpf_int_jit_compile(). */ void __weak bpf_jit_compile(struct bpf_prog *prog) { } bool __weak bpf_helper_changes_pkt_data(void *func) { return false; } /* Return TRUE if the JIT backend wants verifier to enable sub-register usage * analysis code and wants explicit zero extension inserted by verifier. * Otherwise, return FALSE. * * The verifier inserts an explicit zero extension after BPF_CMPXCHGs even if * you don't override this. JITs that don't want these extra insns can detect * them using insn_is_zext. */ bool __weak bpf_jit_needs_zext(void) { return false; } /* Return true if the JIT inlines the call to the helper corresponding to * the imm. * * The verifier will not patch the insn->imm for the call to the helper if * this returns true. */ bool __weak bpf_jit_inlines_helper_call(s32 imm) { return false; } /* Return TRUE if the JIT backend supports mixing bpf2bpf and tailcalls. */ bool __weak bpf_jit_supports_subprog_tailcalls(void) { return false; } bool __weak bpf_jit_supports_percpu_insn(void) { return false; } bool __weak bpf_jit_supports_kfunc_call(void) { return false; } bool __weak bpf_jit_supports_far_kfunc_call(void) { return false; } bool __weak bpf_jit_supports_arena(void) { return false; } bool __weak bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) { return false; } u64 __weak bpf_arch_uaddress_limit(void) { #if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) return TASK_SIZE; #else return 0; #endif } /* Return TRUE if the JIT backend satisfies the following two conditions: * 1) JIT backend supports atomic_xchg() on pointer-sized words. * 2) Under the specific arch, the implementation of xchg() is the same * as atomic_xchg() on pointer-sized words. */ bool __weak bpf_jit_supports_ptr_xchg(void) { return false; } /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { return -EFAULT; } int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2) { return -ENOTSUPP; } void * __weak bpf_arch_text_copy(void *dst, void *src, size_t len) { return ERR_PTR(-ENOTSUPP); } int __weak bpf_arch_text_invalidate(void *dst, size_t len) { return -ENOTSUPP; } bool __weak bpf_jit_supports_exceptions(void) { return false; } void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie) { } /* for configs without MMU or 32-bit */ __weak const struct bpf_map_ops arena_map_ops; __weak u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) { return 0; } __weak u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) { return 0; } #ifdef CONFIG_BPF_SYSCALL static int __init bpf_global_ma_init(void) { int ret; ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false); bpf_global_ma_set = !ret; return ret; } late_initcall(bpf_global_ma_init); #endif DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); /* All definitions of tracepoints related to BPF. */ #define CREATE_TRACE_POINTS #include <linux/bpf_trace.h> EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx); |
| 22 1 2 2 1 1 2 2 51 6 42 1 2 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/oom_kill.c * * Copyright (C) 1998,2000 Rik van Riel * Thanks go out to Claus Fischer for some serious inspiration and * for goading me into coding this file... * Copyright (C) 2010 Google, Inc. * Rewritten by David Rientjes * * The routines in this file are used to kill a process when * we're seriously out of memory. This gets called from __alloc_pages() * in mm/page_alloc.c when we really run out of memory. * * Since we won't call these routines often (on a well-configured * machine) this file will double as a 'coding guide' and a signpost * for newbie kernel hackers. It features several pointers to major * kernel subsystems and hints as to where to find out what things do. */ #include <linux/oom.h> #include <linux/mm.h> #include <linux/err.h> #include <linux/gfp.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/sched/debug.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/timex.h> #include <linux/jiffies.h> #include <linux/cpuset.h> #include <linux/export.h> #include <linux/notifier.h> #include <linux/memcontrol.h> #include <linux/mempolicy.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/freezer.h> #include <linux/ftrace.h> #include <linux/ratelimit.h> #include <linux/kthread.h> #include <linux/init.h> #include <linux/mmu_notifier.h> #include <linux/cred.h> #include <asm/tlb.h> #include "internal.h" #include "slab.h" #define CREATE_TRACE_POINTS #include <trace/events/oom.h> static int sysctl_panic_on_oom; static int sysctl_oom_kill_allocating_task; static int sysctl_oom_dump_tasks = 1; /* * Serializes oom killer invocations (out_of_memory()) from all contexts to * prevent from over eager oom killing (e.g. when the oom killer is invoked * from different domains). * * oom_killer_disable() relies on this lock to stabilize oom_killer_disabled * and mark_oom_victim */ DEFINE_MUTEX(oom_lock); /* Serializes oom_score_adj and oom_score_adj_min updates */ DEFINE_MUTEX(oom_adj_mutex); static inline bool is_memcg_oom(struct oom_control *oc) { return oc->memcg != NULL; } #ifdef CONFIG_NUMA /** * oom_cpuset_eligible() - check task eligibility for kill * @start: task struct of which task to consider * @oc: pointer to struct oom_control * * Task eligibility is determined by whether or not a candidate task, @tsk, * shares the same mempolicy nodes as current if it is bound by such a policy * and whether or not it has the same set of allowed cpuset nodes. * * This function is assuming oom-killer context and 'current' has triggered * the oom-killer. */ static bool oom_cpuset_eligible(struct task_struct *start, struct oom_control *oc) { struct task_struct *tsk; bool ret = false; const nodemask_t *mask = oc->nodemask; rcu_read_lock(); for_each_thread(start, tsk) { if (mask) { /* * If this is a mempolicy constrained oom, tsk's * cpuset is irrelevant. Only return true if its * mempolicy intersects current, otherwise it may be * needlessly killed. */ ret = mempolicy_in_oom_domain(tsk, mask); } else { /* * This is not a mempolicy constrained oom, so only * check the mems of tsk's cpuset. */ ret = cpuset_mems_allowed_intersects(current, tsk); } if (ret) break; } rcu_read_unlock(); return ret; } #else static bool oom_cpuset_eligible(struct task_struct *tsk, struct oom_control *oc) { return true; } #endif /* CONFIG_NUMA */ /* * The process p may have detached its own ->mm while exiting or through * kthread_use_mm(), but one or more of its subthreads may still have a valid * pointer. Return p, or any of its subthreads with a valid ->mm, with * task_lock() held. */ struct task_struct *find_lock_task_mm(struct task_struct *p) { struct task_struct *t; rcu_read_lock(); for_each_thread(p, t) { task_lock(t); if (likely(t->mm)) goto found; task_unlock(t); } t = NULL; found: rcu_read_unlock(); return t; } /* * order == -1 means the oom kill is required by sysrq, otherwise only * for display purposes. */ static inline bool is_sysrq_oom(struct oom_control *oc) { return oc->order == -1; } /* return true if the task is not adequate as candidate victim task. */ static bool oom_unkillable_task(struct task_struct *p) { if (is_global_init(p)) return true; if (p->flags & PF_KTHREAD) return true; return false; } /* * Check whether unreclaimable slab amount is greater than * all user memory(LRU pages). * dump_unreclaimable_slab() could help in the case that * oom due to too much unreclaimable slab used by kernel. */ static bool should_dump_unreclaim_slab(void) { unsigned long nr_lru; nr_lru = global_node_page_state(NR_ACTIVE_ANON) + global_node_page_state(NR_INACTIVE_ANON) + global_node_page_state(NR_ACTIVE_FILE) + global_node_page_state(NR_INACTIVE_FILE) + global_node_page_state(NR_ISOLATED_ANON) + global_node_page_state(NR_ISOLATED_FILE) + global_node_page_state(NR_UNEVICTABLE); return (global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B) > nr_lru); } /** * oom_badness - heuristic function to determine which candidate task to kill * @p: task struct of which task we should calculate * @totalpages: total present RAM allowed for page allocation * * The heuristic for determining which task to kill is made to be as simple and * predictable as possible. The goal is to return the highest value for the * task consuming the most memory to avoid subsequent oom failures. */ long oom_badness(struct task_struct *p, unsigned long totalpages) { long points; long adj; if (oom_unkillable_task(p)) return LONG_MIN; p = find_lock_task_mm(p); if (!p) return LONG_MIN; /* * Do not even consider tasks which are explicitly marked oom * unkillable or have been already oom reaped or the are in * the middle of vfork */ adj = (long)p->signal->oom_score_adj; if (adj == OOM_SCORE_ADJ_MIN || test_bit(MMF_OOM_SKIP, &p->mm->flags) || in_vfork(p)) { task_unlock(p); return LONG_MIN; } /* * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) + mm_pgtables_bytes(p->mm) / PAGE_SIZE; task_unlock(p); /* Normalize to oom_score_adj units */ adj *= totalpages / 1000; points += adj; return points; } static const char * const oom_constraint_text[] = { [CONSTRAINT_NONE] = "CONSTRAINT_NONE", [CONSTRAINT_CPUSET] = "CONSTRAINT_CPUSET", [CONSTRAINT_MEMORY_POLICY] = "CONSTRAINT_MEMORY_POLICY", [CONSTRAINT_MEMCG] = "CONSTRAINT_MEMCG", }; /* * Determine the type of allocation constraint. */ static enum oom_constraint constrained_alloc(struct oom_control *oc) { struct zone *zone; struct zoneref *z; enum zone_type highest_zoneidx = gfp_zone(oc->gfp_mask); bool cpuset_limited = false; int nid; if (is_memcg_oom(oc)) { oc->totalpages = mem_cgroup_get_max(oc->memcg) ?: 1; return CONSTRAINT_MEMCG; } /* Default to all available memory */ oc->totalpages = totalram_pages() + total_swap_pages; if (!IS_ENABLED(CONFIG_NUMA)) return CONSTRAINT_NONE; if (!oc->zonelist) return CONSTRAINT_NONE; /* * Reach here only when __GFP_NOFAIL is used. So, we should avoid * to kill current.We have to random task kill in this case. * Hopefully, CONSTRAINT_THISNODE...but no way to handle it, now. */ if (oc->gfp_mask & __GFP_THISNODE) return CONSTRAINT_NONE; /* * This is not a __GFP_THISNODE allocation, so a truncated nodemask in * the page allocator means a mempolicy is in effect. Cpuset policy * is enforced in get_page_from_freelist(). */ if (oc->nodemask && !nodes_subset(node_states[N_MEMORY], *oc->nodemask)) { oc->totalpages = total_swap_pages; for_each_node_mask(nid, *oc->nodemask) oc->totalpages += node_present_pages(nid); return CONSTRAINT_MEMORY_POLICY; } /* Check this allocation failure is caused by cpuset's wall function */ for_each_zone_zonelist_nodemask(zone, z, oc->zonelist, highest_zoneidx, oc->nodemask) if (!cpuset_zone_allowed(zone, oc->gfp_mask)) cpuset_limited = true; if (cpuset_limited) { oc->totalpages = total_swap_pages; for_each_node_mask(nid, cpuset_current_mems_allowed) oc->totalpages += node_present_pages(nid); return CONSTRAINT_CPUSET; } return CONSTRAINT_NONE; } static int oom_evaluate_task(struct task_struct *task, void *arg) { struct oom_control *oc = arg; long points; if (oom_unkillable_task(task)) goto next; /* p may not have freeable memory in nodemask */ if (!is_memcg_oom(oc) && !oom_cpuset_eligible(task, oc)) goto next; /* * This task already has access to memory reserves and is being killed. * Don't allow any other task to have access to the reserves unless * the task has MMF_OOM_SKIP because chances that it would release * any memory is quite low. */ if (!is_sysrq_oom(oc) && tsk_is_oom_victim(task)) { if (test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags)) goto next; goto abort; } /* * If task is allocating a lot of memory and has been marked to be * killed first if it triggers an oom, then select it. */ if (oom_task_origin(task)) { points = LONG_MAX; goto select; } points = oom_badness(task, oc->totalpages); if (points == LONG_MIN || points < oc->chosen_points) goto next; select: if (oc->chosen) put_task_struct(oc->chosen); get_task_struct(task); oc->chosen = task; oc->chosen_points = points; next: return 0; abort: if (oc->chosen) put_task_struct(oc->chosen); oc->chosen = (void *)-1UL; return 1; } /* * Simple selection loop. We choose the process with the highest number of * 'points'. In case scan was aborted, oc->chosen is set to -1. */ static void select_bad_process(struct oom_control *oc) { oc->chosen_points = LONG_MIN; if (is_memcg_oom(oc)) mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc); else { struct task_struct *p; rcu_read_lock(); for_each_process(p) if (oom_evaluate_task(p, oc)) break; rcu_read_unlock(); } } static int dump_task(struct task_struct *p, void *arg) { struct oom_control *oc = arg; struct task_struct *task; if (oom_unkillable_task(p)) return 0; /* p may not have freeable memory in nodemask */ if (!is_memcg_oom(oc) && !oom_cpuset_eligible(p, oc)) return 0; task = find_lock_task_mm(p); if (!task) { /* * All of p's threads have already detached their mm's. There's * no need to report them; they can't be oom killed anyway. */ return 0; } pr_info("[%7d] %5d %5d %8lu %8lu %8lu %8lu %9lu %8ld %8lu %5hd %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), get_mm_counter(task->mm, MM_ANONPAGES), get_mm_counter(task->mm, MM_FILEPAGES), get_mm_counter(task->mm, MM_SHMEMPAGES), mm_pgtables_bytes(task->mm), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); return 0; } /** * dump_tasks - dump current memory state of all system tasks * @oc: pointer to struct oom_control * * Dumps the current memory state of all eligible tasks. Tasks not in the same * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes * are not shown. * State information includes task's pid, uid, tgid, vm size, rss, * pgtables_bytes, swapents, oom_score_adj value, and name. */ static void dump_tasks(struct oom_control *oc) { pr_info("Tasks state (memory values in pages):\n"); pr_info("[ pid ] uid tgid total_vm rss rss_anon rss_file rss_shmem pgtables_bytes swapents oom_score_adj name\n"); if (is_memcg_oom(oc)) mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); else { struct task_struct *p; rcu_read_lock(); for_each_process(p) dump_task(p, oc); rcu_read_unlock(); } } static void dump_oom_victim(struct oom_control *oc, struct task_struct *victim) { /* one line summary of the oom killer context. */ pr_info("oom-kill:constraint=%s,nodemask=%*pbl", oom_constraint_text[oc->constraint], nodemask_pr_args(oc->nodemask)); cpuset_print_current_mems_allowed(); mem_cgroup_print_oom_context(oc->memcg, victim); pr_cont(",task=%s,pid=%d,uid=%d\n", victim->comm, victim->pid, from_kuid(&init_user_ns, task_uid(victim))); } static void dump_header(struct oom_control *oc) { pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n", current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order, current->signal->oom_score_adj); if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order) pr_warn("COMPACTION is disabled!!!\n"); dump_stack(); if (is_memcg_oom(oc)) mem_cgroup_print_oom_meminfo(oc->memcg); else { __show_mem(SHOW_MEM_FILTER_NODES, oc->nodemask, gfp_zone(oc->gfp_mask)); if (should_dump_unreclaim_slab()) dump_unreclaimable_slab(); } if (sysctl_oom_dump_tasks) dump_tasks(oc); } /* * Number of OOM victims in flight */ static atomic_t oom_victims = ATOMIC_INIT(0); static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait); static bool oom_killer_disabled __read_mostly; /* * task->mm can be NULL if the task is the exited group leader. So to * determine whether the task is using a particular mm, we examine all the * task's threads: if one of those is using this mm then this task was also * using it. */ bool process_shares_mm(struct task_struct *p, struct mm_struct *mm) { struct task_struct *t; for_each_thread(p, t) { struct mm_struct *t_mm = READ_ONCE(t->mm); if (t_mm) return t_mm == mm; } return false; } #ifdef CONFIG_MMU /* * OOM Reaper kernel thread which tries to reap the memory used by the OOM * victim (if that is possible) to help the OOM killer to move on. */ static struct task_struct *oom_reaper_th; static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait); static struct task_struct *oom_reaper_list; static DEFINE_SPINLOCK(oom_reaper_lock); static bool __oom_reap_task_mm(struct mm_struct *mm) { struct vm_area_struct *vma; bool ret = true; VMA_ITERATOR(vmi, mm, 0); /* * Tell all users of get_user/copy_from_user etc... that the content * is no longer stable. No barriers really needed because unmapping * should imply barriers already and the reader would hit a page fault * if it stumbled over a reaped memory. */ set_bit(MMF_UNSTABLE, &mm->flags); for_each_vma(vmi, vma) { if (vma->vm_flags & (VM_HUGETLB|VM_PFNMAP)) continue; /* * Only anonymous pages have a good chance to be dropped * without additional steps which we cannot afford as we * are OOM already. * * We do not even care about fs backed pages because all * which are reclaimable have already been reclaimed and * we do not want to block exit_mmap by keeping mm ref * count elevated without a good reason. */ if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) { struct mmu_notifier_range range; struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, mm, vma->vm_start, vma->vm_end); tlb_gather_mmu(&tlb, mm); if (mmu_notifier_invalidate_range_start_nonblock(&range)) { tlb_finish_mmu(&tlb); ret = false; continue; } unmap_page_range(&tlb, vma, range.start, range.end, NULL); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } } return ret; } /* * Reaps the address space of the give task. * * Returns true on success and false if none or part of the address space * has been reclaimed and the caller should retry later. */ static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) { bool ret = true; if (!mmap_read_trylock(mm)) { trace_skip_task_reaping(tsk->pid); return false; } /* * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't * work on the mm anymore. The check for MMF_OOM_SKIP must run * under mmap_lock for reading because it serializes against the * mmap_write_lock();mmap_write_unlock() cycle in exit_mmap(). */ if (test_bit(MMF_OOM_SKIP, &mm->flags)) { trace_skip_task_reaping(tsk->pid); goto out_unlock; } trace_start_task_reaping(tsk->pid); /* failed to reap part of the address space. Try again later */ ret = __oom_reap_task_mm(mm); if (!ret) goto out_finish; pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", task_pid_nr(tsk), tsk->comm, K(get_mm_counter(mm, MM_ANONPAGES)), K(get_mm_counter(mm, MM_FILEPAGES)), K(get_mm_counter(mm, MM_SHMEMPAGES))); out_finish: trace_finish_task_reaping(tsk->pid); out_unlock: mmap_read_unlock(mm); return ret; } #define MAX_OOM_REAP_RETRIES 10 static void oom_reap_task(struct task_struct *tsk) { int attempts = 0; struct mm_struct *mm = tsk->signal->oom_mm; /* Retry the mmap_read_trylock(mm) a few times */ while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm)) schedule_timeout_idle(HZ/10); if (attempts <= MAX_OOM_REAP_RETRIES || test_bit(MMF_OOM_SKIP, &mm->flags)) goto done; pr_info("oom_reaper: unable to reap pid:%d (%s)\n", task_pid_nr(tsk), tsk->comm); sched_show_task(tsk); debug_show_all_locks(); done: tsk->oom_reaper_list = NULL; /* * Hide this mm from OOM killer because it has been either reaped or * somebody can't call mmap_write_unlock(mm). */ set_bit(MMF_OOM_SKIP, &mm->flags); /* Drop a reference taken by queue_oom_reaper */ put_task_struct(tsk); } static int oom_reaper(void *unused) { set_freezable(); while (true) { struct task_struct *tsk = NULL; wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL); spin_lock_irq(&oom_reaper_lock); if (oom_reaper_list != NULL) { tsk = oom_reaper_list; oom_reaper_list = tsk->oom_reaper_list; } spin_unlock_irq(&oom_reaper_lock); if (tsk) oom_reap_task(tsk); } return 0; } static void wake_oom_reaper(struct timer_list *timer) { struct task_struct *tsk = container_of(timer, struct task_struct, oom_reaper_timer); struct mm_struct *mm = tsk->signal->oom_mm; unsigned long flags; /* The victim managed to terminate on its own - see exit_mmap */ if (test_bit(MMF_OOM_SKIP, &mm->flags)) { put_task_struct(tsk); return; } spin_lock_irqsave(&oom_reaper_lock, flags); tsk->oom_reaper_list = oom_reaper_list; oom_reaper_list = tsk; spin_unlock_irqrestore(&oom_reaper_lock, flags); trace_wake_reaper(tsk->pid); wake_up(&oom_reaper_wait); } /* * Give the OOM victim time to exit naturally before invoking the oom_reaping. * The timers timeout is arbitrary... the longer it is, the longer the worst * case scenario for the OOM can take. If it is too small, the oom_reaper can * get in the way and release resources needed by the process exit path. * e.g. The futex robust list can sit in Anon|Private memory that gets reaped * before the exit path is able to wake the futex waiters. */ #define OOM_REAPER_DELAY (2*HZ) static void queue_oom_reaper(struct task_struct *tsk) { /* mm is already queued? */ if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) return; get_task_struct(tsk); timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0); tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY; add_timer(&tsk->oom_reaper_timer); } #ifdef CONFIG_SYSCTL static struct ctl_table vm_oom_kill_table[] = { { .procname = "panic_on_oom", .data = &sysctl_panic_on_oom, .maxlen = sizeof(sysctl_panic_on_oom), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "oom_kill_allocating_task", .data = &sysctl_oom_kill_allocating_task, .maxlen = sizeof(sysctl_oom_kill_allocating_task), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "oom_dump_tasks", .data = &sysctl_oom_dump_tasks, .maxlen = sizeof(sysctl_oom_dump_tasks), .mode = 0644, .proc_handler = proc_dointvec, }, }; #endif static int __init oom_init(void) { oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper"); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_oom_kill_table); #endif return 0; } subsys_initcall(oom_init) #else static inline void queue_oom_reaper(struct task_struct *tsk) { } #endif /* CONFIG_MMU */ /** * mark_oom_victim - mark the given task as OOM victim * @tsk: task to mark * * Has to be called with oom_lock held and never after * oom has been disabled already. * * tsk->mm has to be non NULL and caller has to guarantee it is stable (either * under task_lock or operate on the current). */ static void mark_oom_victim(struct task_struct *tsk) { const struct cred *cred; struct mm_struct *mm = tsk->mm; WARN_ON(oom_killer_disabled); /* OOM killer might race with memcg OOM */ if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE)) return; /* oom_mm is bound to the signal struct life time. */ if (!cmpxchg(&tsk->signal->oom_mm, NULL, mm)) mmgrab(tsk->signal->oom_mm); /* * Make sure that the task is woken up from uninterruptible sleep * if it is frozen because OOM killer wouldn't be able to free * any memory and livelock. freezing_slow_path will tell the freezer * that TIF_MEMDIE tasks should be ignored. */ __thaw_task(tsk); atomic_inc(&oom_victims); cred = get_task_cred(tsk); trace_mark_victim(tsk, cred->uid.val); put_cred(cred); } /** * exit_oom_victim - note the exit of an OOM victim */ void exit_oom_victim(void) { clear_thread_flag(TIF_MEMDIE); if (!atomic_dec_return(&oom_victims)) wake_up_all(&oom_victims_wait); } /** * oom_killer_enable - enable OOM killer */ void oom_killer_enable(void) { oom_killer_disabled = false; pr_info("OOM killer enabled.\n"); } /** * oom_killer_disable - disable OOM killer * @timeout: maximum timeout to wait for oom victims in jiffies * * Forces all page allocations to fail rather than trigger OOM killer. * Will block and wait until all OOM victims are killed or the given * timeout expires. * * The function cannot be called when there are runnable user tasks because * the userspace would see unexpected allocation failures as a result. Any * new usage of this function should be consulted with MM people. * * Returns true if successful and false if the OOM killer cannot be * disabled. */ bool oom_killer_disable(signed long timeout) { signed long ret; /* * Make sure to not race with an ongoing OOM killer. Check that the * current is not killed (possibly due to sharing the victim's memory). */ if (mutex_lock_killable(&oom_lock)) return false; oom_killer_disabled = true; mutex_unlock(&oom_lock); ret = wait_event_interruptible_timeout(oom_victims_wait, !atomic_read(&oom_victims), timeout); if (ret <= 0) { oom_killer_enable(); return false; } pr_info("OOM killer disabled.\n"); return true; } static inline bool __task_will_free_mem(struct task_struct *task) { struct signal_struct *sig = task->signal; /* * A coredumping process may sleep for an extended period in * coredump_task_exit(), so the oom killer cannot assume that * the process will promptly exit and release memory. */ if (sig->core_state) return false; if (sig->flags & SIGNAL_GROUP_EXIT) return true; if (thread_group_empty(task) && (task->flags & PF_EXITING)) return true; return false; } /* * Checks whether the given task is dying or exiting and likely to * release its address space. This means that all threads and processes * sharing the same mm have to be killed or exiting. * Caller has to make sure that task->mm is stable (hold task_lock or * it operates on the current). */ static bool task_will_free_mem(struct task_struct *task) { struct mm_struct *mm = task->mm; struct task_struct *p; bool ret = true; /* * Skip tasks without mm because it might have passed its exit_mm and * exit_oom_victim. oom_reaper could have rescued that but do not rely * on that for now. We can consider find_lock_task_mm in future. */ if (!mm) return false; if (!__task_will_free_mem(task)) return false; /* * This task has already been drained by the oom reaper so there are * only small chances it will free some more */ if (test_bit(MMF_OOM_SKIP, &mm->flags)) return false; if (atomic_read(&mm->mm_users) <= 1) return true; /* * Make sure that all tasks which share the mm with the given tasks * are dying as well to make sure that a) nobody pins its mm and * b) the task is also reapable by the oom reaper. */ rcu_read_lock(); for_each_process(p) { if (!process_shares_mm(p, mm)) continue; if (same_thread_group(task, p)) continue; ret = __task_will_free_mem(p); if (!ret) break; } rcu_read_unlock(); return ret; } static void __oom_kill_process(struct task_struct *victim, const char *message) { struct task_struct *p; struct mm_struct *mm; bool can_oom_reap = true; p = find_lock_task_mm(victim); if (!p) { pr_info("%s: OOM victim %d (%s) is already exiting. Skip killing the task\n", message, task_pid_nr(victim), victim->comm); put_task_struct(victim); return; } else if (victim != p) { get_task_struct(p); put_task_struct(victim); victim = p; } /* Get a reference to safely compare mm after task_unlock(victim) */ mm = victim->mm; mmgrab(mm); /* Raise event before sending signal: task reaper must see this */ count_vm_event(OOM_KILL); memcg_memory_event_mm(mm, MEMCG_OOM_KILL); /* * We should send SIGKILL before granting access to memory reserves * in order to prevent the OOM victim from depleting the memory * reserves from the user space under its control. */ do_send_sig_info(SIGKILL, SEND_SIG_PRIV, victim, PIDTYPE_TGID); mark_oom_victim(victim); pr_err("%s: Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB, UID:%u pgtables:%lukB oom_score_adj:%hd\n", message, task_pid_nr(victim), victim->comm, K(mm->total_vm), K(get_mm_counter(mm, MM_ANONPAGES)), K(get_mm_counter(mm, MM_FILEPAGES)), K(get_mm_counter(mm, MM_SHMEMPAGES)), from_kuid(&init_user_ns, task_uid(victim)), mm_pgtables_bytes(mm) >> 10, victim->signal->oom_score_adj); task_unlock(victim); /* * Kill all user processes sharing victim->mm in other thread groups, if * any. They don't get access to memory reserves, though, to avoid * depletion of all memory. This prevents mm->mmap_lock livelock when an * oom killed thread cannot exit because it requires the semaphore and * its contended by another thread trying to allocate memory itself. * That thread will now get access to memory reserves since it has a * pending fatal signal. */ rcu_read_lock(); for_each_process(p) { if (!process_shares_mm(p, mm)) continue; if (same_thread_group(p, victim)) continue; if (is_global_init(p)) { can_oom_reap = false; set_bit(MMF_OOM_SKIP, &mm->flags); pr_info("oom killer %d (%s) has mm pinned by %d (%s)\n", task_pid_nr(victim), victim->comm, task_pid_nr(p), p->comm); continue; } /* * No kthread_use_mm() user needs to read from the userspace so * we are ok to reap it. */ if (unlikely(p->flags & PF_KTHREAD)) continue; do_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_TGID); } rcu_read_unlock(); if (can_oom_reap) queue_oom_reaper(victim); mmdrop(mm); put_task_struct(victim); } /* * Kill provided task unless it's secured by setting * oom_score_adj to OOM_SCORE_ADJ_MIN. */ static int oom_kill_memcg_member(struct task_struct *task, void *message) { if (task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN && !is_global_init(task)) { get_task_struct(task); __oom_kill_process(task, message); } return 0; } static void oom_kill_process(struct oom_control *oc, const char *message) { struct task_struct *victim = oc->chosen; struct mem_cgroup *oom_group; static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); /* * If the task is already exiting, don't alarm the sysadmin or kill * its children or threads, just give it access to memory reserves * so it can die quickly */ task_lock(victim); if (task_will_free_mem(victim)) { mark_oom_victim(victim); queue_oom_reaper(victim); task_unlock(victim); put_task_struct(victim); return; } task_unlock(victim); if (__ratelimit(&oom_rs)) { dump_header(oc); dump_oom_victim(oc, victim); } /* * Do we need to kill the entire memory cgroup? * Or even one of the ancestor memory cgroups? * Check this out before killing the victim task. */ oom_group = mem_cgroup_get_oom_group(victim, oc->memcg); __oom_kill_process(victim, message); /* * If necessary, kill all tasks in the selected memory cgroup. */ if (oom_group) { memcg_memory_event(oom_group, MEMCG_OOM_GROUP_KILL); mem_cgroup_print_oom_group(oom_group); mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member, (void *)message); mem_cgroup_put(oom_group); } } /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ static void check_panic_on_oom(struct oom_control *oc) { if (likely(!sysctl_panic_on_oom)) return; if (sysctl_panic_on_oom != 2) { /* * panic_on_oom == 1 only affects CONSTRAINT_NONE, the kernel * does not panic for cpuset, mempolicy, or memcg allocation * failures. */ if (oc->constraint != CONSTRAINT_NONE) return; } /* Do not panic for oom kills triggered by sysrq */ if (is_sysrq_oom(oc)) return; dump_header(oc); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } static BLOCKING_NOTIFIER_HEAD(oom_notify_list); int register_oom_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&oom_notify_list, nb); } EXPORT_SYMBOL_GPL(register_oom_notifier); int unregister_oom_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&oom_notify_list, nb); } EXPORT_SYMBOL_GPL(unregister_oom_notifier); /** * out_of_memory - kill the "best" process when we run out of memory * @oc: pointer to struct oom_control * * If we run out of memory, we have the choice between either * killing a random task (bad), letting the system crash (worse) * OR try to be smart about which process to kill. Note that we * don't have to be perfect here, we just have to be good. */ bool out_of_memory(struct oom_control *oc) { unsigned long freed = 0; if (oom_killer_disabled) return false; if (!is_memcg_oom(oc)) { blocking_notifier_call_chain(&oom_notify_list, 0, &freed); if (freed > 0 && !is_sysrq_oom(oc)) /* Got some memory back in the last second. */ return true; } /* * If current has a pending SIGKILL or is exiting, then automatically * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. */ if (task_will_free_mem(current)) { mark_oom_victim(current); queue_oom_reaper(current); return true; } /* * The OOM killer does not compensate for IO-less reclaim. * But mem_cgroup_oom() has to invoke the OOM killer even * if it is a GFP_NOFS allocation. */ if (!(oc->gfp_mask & __GFP_FS) && !is_memcg_oom(oc)) return true; /* * Check if there were limitations on the allocation (only relevant for * NUMA and memcg) that may require different handling. */ oc->constraint = constrained_alloc(oc); if (oc->constraint != CONSTRAINT_MEMORY_POLICY) oc->nodemask = NULL; check_panic_on_oom(oc); if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task && current->mm && !oom_unkillable_task(current) && oom_cpuset_eligible(current, oc) && current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) { get_task_struct(current); oc->chosen = current; oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)"); return true; } select_bad_process(oc); /* Found nothing?!?! */ if (!oc->chosen) { dump_header(oc); pr_warn("Out of memory and no killable processes...\n"); /* * If we got here due to an actual allocation at the * system level, we cannot survive this and will enter * an endless loop in the allocator. Bail out now. */ if (!is_sysrq_oom(oc) && !is_memcg_oom(oc)) panic("System is deadlocked on memory\n"); } if (oc->chosen && oc->chosen != (void *)-1UL) oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" : "Memory cgroup out of memory"); return !!oc->chosen; } /* * The pagefault handler calls here because some allocation has failed. We have * to take care of the memcg OOM here because this is the only safe context without * any locks held but let the oom killer triggered from the allocation context care * about the global OOM. */ void pagefault_out_of_memory(void) { static DEFINE_RATELIMIT_STATE(pfoom_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); if (mem_cgroup_oom_synchronize(true)) return; if (fatal_signal_pending(current)) return; if (__ratelimit(&pfoom_rs)) pr_warn("Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF\n"); } SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags) { #ifdef CONFIG_MMU struct mm_struct *mm = NULL; struct task_struct *task; struct task_struct *p; unsigned int f_flags; bool reap = false; long ret = 0; if (flags) return -EINVAL; task = pidfd_get_task(pidfd, &f_flags); if (IS_ERR(task)) return PTR_ERR(task); /* * Make sure to choose a thread which still has a reference to mm * during the group exit */ p = find_lock_task_mm(task); if (!p) { ret = -ESRCH; goto put_task; } mm = p->mm; mmgrab(mm); if (task_will_free_mem(p)) reap = true; else { /* Error only if the work has not been done already */ if (!test_bit(MMF_OOM_SKIP, &mm->flags)) ret = -EINVAL; } task_unlock(p); if (!reap) goto drop_mm; if (mmap_read_lock_killable(mm)) { ret = -EINTR; goto drop_mm; } /* * Check MMF_OOM_SKIP again under mmap_read_lock protection to ensure * possible change in exit_mmap is seen */ if (!test_bit(MMF_OOM_SKIP, &mm->flags) && !__oom_reap_task_mm(mm)) ret = -EAGAIN; mmap_read_unlock(mm); drop_mm: mmdrop(mm); put_task: put_task_struct(task); return ret; #else return -ENOSYS; #endif /* CONFIG_MMU */ } |
| 1033 1033 1032 1032 1032 1033 1031 1032 1033 1 552 30 1 549 5 544 521 1 520 1288 1 66 869 811 73 1278 1277 1253 22 795 894 1260 12 4 1262 16 1277 1 1566 6 1543 20 31 45 560 559 542 543 2 543 286 251 534 3 536 535 18 520 111 276 247 535 198 9 189 587 610 1007 103 1 903 24 2 49 46 6 267 851 889 59 321 192 334 792 31 427 278 276 2 591 97 97 97 87 10 97 95 28 82 8 3 1 2 1 2 3359 3360 2939 505 2448 2449 8 1 7 305 49 255 222 109 246 494 1 469 48 101 217 172 87 321 252 1 39 1 15 1 102 2 67 609 607 6 6 1 760 759 1735 1738 157 157 151 6 3 146 6 152 2 14 152 2 11 13 137 68 69 68 135 2 137 3 1 2 84 83 21 7 3 1 49 49 49 3 3 37 18 5 13 414 6 413 1 1 414 414 414 2 414 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * PF_INET protocol family socket handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Changes (see also sock.c) * * piggy, * Karl Knutson : Socket protocol table * A.N.Kuznetsov : Socket death error in accept(). * John Richardson : Fix non blocking error in connect() * so sockets that fail to connect * don't return -EINPROGRESS. * Alan Cox : Asynchronous I/O support * Alan Cox : Keep correct socket pointer on sock * structures * when accept() ed * Alan Cox : Semantics of SO_LINGER aren't state * moved to close when you look carefully. * With this fixed and the accept bug fixed * some RPC stuff seems happier. * Niibe Yutaka : 4.4BSD style write async I/O * Alan Cox, * Tony Gale : Fixed reuse semantics. * Alan Cox : bind() shouldn't abort existing but dead * sockets. Stops FTP netin:.. I hope. * Alan Cox : bind() works correctly for RAW sockets. * Note that FreeBSD at least was broken * in this respect so be careful with * compatibility tests... * Alan Cox : routing cache support * Alan Cox : memzero the socket structure for * compactness. * Matt Day : nonblock connect error handler * Alan Cox : Allow large numbers of pending sockets * (eg for big web sites), but only if * specifically application requested. * Alan Cox : New buffering throughout IP. Used * dumbly. * Alan Cox : New buffering now used smartly. * Alan Cox : BSD rather than common sense * interpretation of listen. * Germano Caronni : Assorted small races. * Alan Cox : sendmsg/recvmsg basic support. * Alan Cox : Only sendmsg/recvmsg now supported. * Alan Cox : Locked down bind (see security list). * Alan Cox : Loosened bind a little. * Mike McLagan : ADD/DEL DLCI Ioctls * Willy Konynenberg : Transparent proxying support. * David S. Miller : New socket lookup architecture. * Some other random speedups. * Cyrus Durgin : Cleaned up file for kmod hacks. * Andi Kleen : Fix inet_stream_connect TCP race. */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/err.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/sched.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/igmp.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <net/checksum.h> #include <net/ip.h> #include <net/protocol.h> #include <net/arp.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/inet_connection_sock.h> #include <net/gro.h> #include <net/gso.h> #include <net/tcp.h> #include <net/udp.h> #include <net/udplite.h> #include <net/ping.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/raw.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/ip_tunnels.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/secure_seq.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #include <net/l3mdev.h> #include <net/compat.h> #include <net/rps.h> #include <trace/events/sock.h> /* The inetsw table contains everything that inet_create needs to * build a new socket. */ static struct list_head inetsw[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw_lock); /* New destruction routine */ void inet_sock_destruct(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_error_queue); sk_mem_reclaim_final(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) { pr_err("Attempt to release TCP socket in state %d %p\n", sk->sk_state, sk); return; } if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive inet socket %p\n", sk); return; } WARN_ON_ONCE(atomic_read(&sk->sk_rmem_alloc)); WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); WARN_ON_ONCE(sk->sk_wmem_queued); WARN_ON_ONCE(sk_forward_alloc_get(sk)); kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1)); } EXPORT_SYMBOL(inet_sock_destruct); /* * The routines beyond this point handle the behaviour of an AF_INET * socket object. Mostly it punts to the subprotocols of IP to do * the work. */ /* * Automatically bind an unbound socket. */ static int inet_autobind(struct sock *sk) { struct inet_sock *inet; /* We may need to bind the socket. */ lock_sock(sk); inet = inet_sk(sk); if (!inet->inet_num) { if (sk->sk_prot->get_port(sk, 0)) { release_sock(sk); return -EAGAIN; } inet->inet_sport = htons(inet->inet_num); } release_sock(sk); return 0; } int __inet_listen_sk(struct sock *sk, int backlog) { unsigned char old_state = sk->sk_state; int err, tcp_fastopen; if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN))) return -EINVAL; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ if (old_state != TCP_LISTEN) { /* Enable TFO w/o requiring TCP_FASTOPEN socket option. * Note that only TCP sockets (SOCK_STREAM) will reach here. * Also fastopen backlog may already been set via the option * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); tcp_fastopen_init_key_once(sock_net(sk)); } err = inet_csk_listen_start(sk); if (err) return err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); } return 0; } /* * Move a socket into listening state. */ int inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int err = -EINVAL; lock_sock(sk); if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto out; err = __inet_listen_sk(sk, backlog); out: release_sock(sk); return err; } EXPORT_SYMBOL(inet_listen); /* * Create an inet socket. */ static int inet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct inet_protosw *answer; struct inet_sock *inet; struct proto *answer_prot; unsigned char answer_flags; int try_loading_module = 0; int err; if (protocol < 0 || protocol >= IPPROTO_MAX) return -EINVAL; sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; rcu_read_lock(); list_for_each_entry_rcu(answer, &inetsw[sock->type], list) { err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) break; } else { /* Check for the two wild cases. */ if (IPPROTO_IP == protocol) { protocol = answer->protocol; break; } if (IPPROTO_IP == answer->protocol) break; } err = -EPROTONOSUPPORT; } if (unlikely(err)) { if (try_loading_module < 2) { rcu_read_unlock(); /* * Be more specific, e.g. net-pf-2-proto-132-type-1 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM) */ if (++try_loading_module == 1) request_module("net-pf-%d-proto-%d-type-%d", PF_INET, protocol, sock->type); /* * Fall back to generic, e.g. net-pf-2-proto-132 * (net-pf-PF_INET-proto-IPPROTO_SCTP) */ else request_module("net-pf-%d-proto-%d", PF_INET, protocol); goto lookup_protocol; } else goto out_rcu_unlock; } err = -EPERM; if (sock->type == SOCK_RAW && !kern && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; answer_prot = answer->prot; answer_flags = answer->flags; rcu_read_unlock(); WARN_ON(!answer_prot->slab); err = -ENOMEM; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; err = 0; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; if (INET_PROTOSW_ICSK & answer_flags) inet_init_csk_locks(sk); inet = inet_sk(sk); inet_assign_bit(IS_ICSK, sk, INET_PROTOSW_ICSK & answer_flags); inet_clear_bit(NODEFRAG, sk); if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet_set_bit(HDRINCL, sk); } if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; atomic_set(&inet->inet_id, 0); sock_init_data(sock, sk); sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; inet_set_bit(MC_LOOP, sk); inet->mc_ttl = 1; inet_set_bit(MC_ALL, sk); inet->mc_index = 0; inet->mc_list = NULL; inet->rcv_tos = 0; if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically * shares. */ inet->inet_sport = htons(inet->inet_num); /* Add to protocol hash chains. */ err = sk->sk_prot->hash(sk); if (err) { sk_common_release(sk); goto out; } } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); if (err) { sk_common_release(sk); goto out; } } if (!kern) { err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); if (err) { sk_common_release(sk); goto out; } } out: return err; out_rcu_unlock: rcu_read_unlock(); goto out; } /* * The peer socket should always be NULL (or else). When we call this * function we are destroying the object and from then on nobody * should refer to it. */ int inet_release(struct socket *sock) { struct sock *sk = sock->sk; if (sk) { long timeout; if (!sk->sk_kern_sock) BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk); /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); /* If linger is set, we don't return until the close * is complete. Otherwise we return immediately. The * actually closing is done the same either way. * * If the close is due to the process exiting, we never * linger.. */ timeout = 0; if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING)) timeout = sk->sk_lingertime; sk->sk_prot->close(sk, timeout); sock->sk = NULL; } return 0; } EXPORT_SYMBOL(inet_release); int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) { u32 flags = BIND_WITH_LOCK; int err; /* If the socket has its own bind function then use it. (RAW) */ if (sk->sk_prot->bind) { return sk->sk_prot->bind(sk, uaddr, addr_len); } if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len, CGROUP_INET4_BIND, &flags); if (err) return err; return __inet_bind(sk, uaddr, addr_len, flags); } int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { return inet_bind_sk(sock->sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_bind); int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; u32 tb_id = RT_TABLE_LOCAL; int err; if (addr->sin_family != AF_INET) { /* Compatibility games : accept AF_UNSPEC (mapped to AF_INET) * only if s_addr is INADDR_ANY. */ err = -EAFNOSUPPORT; if (addr->sin_family != AF_UNSPEC || addr->sin_addr.s_addr != htonl(INADDR_ANY)) goto out; } tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since * allowing applications to make a non-local bind solves * several problems with systems using dynamic addressing. * (ie. your servers still start up even if your ISDN link * is temporarily down) */ err = -EADDRNOTAVAIL; if (!inet_addr_valid_or_nonlocal(net, inet, addr->sin_addr.s_addr, chk_addr_ret)) goto out; snum = ntohs(addr->sin_port); err = -EACCES; if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) && snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) goto out; /* We keep a pair of addresses. rcv_saddr is the one * used by hash lookups, and saddr is used for transmit. * * In the BSD API these are the same except where it * would be illegal to use them (multicast/broadcast) in * which case the sending device address is used. */ if (flags & BIND_WITH_LOCK) lock_sock(sk); /* Check these errors (active socket, double bind). */ err = -EINVAL; if (sk->sk_state != TCP_CLOSE || inet->inet_num) goto out_release_sock; inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ /* Make sure we are allowed to bind here. */ if (snum || !(inet_test_bit(BIND_ADDRESS_NO_PORT, sk) || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { err = sk->sk_prot->get_port(sk, snum); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; goto out_release_sock; } if (!(flags & BIND_FROM_BPF)) { err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; if (sk->sk_prot->put_port) sk->sk_prot->put_port(sk); goto out_release_sock; } } } if (inet->inet_rcv_saddr) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; inet->inet_sport = htons(inet->inet_num); inet->inet_daddr = 0; inet->inet_dport = 0; sk_dst_reset(sk); err = 0; out_release_sock: if (flags & BIND_WITH_LOCK) release_sock(sk); out: return err; } int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; const struct proto *prot; int err; if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); if (uaddr->sa_family == AF_UNSPEC) return prot->disconnect(sk, flags); if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) { err = prot->pre_connect(sk, uaddr, addr_len); if (err) return err; } if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk)) return -EAGAIN; return prot->connect(sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_dgram_connect); static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. * Connect() does not allow to get error notifications * without closing the socket. */ while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); if (signal_pending(current) || !timeo) break; } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; return timeo; } /* * Connect to a remote host. There is regrettably still a little * TCP 'magic' in here. */ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags, int is_sendmsg) { struct sock *sk = sock->sk; int err; long timeo; /* * uaddr can be NULL and addr_len can be 0 if: * sk is a TCP fastopen active socket and * TCP_FASTOPEN_CONNECT sockopt is set and * we already have a valid cookie for this socket. * In this case, user can call write() after connect(). * write() will invoke tcp_sendmsg_fastopen() which calls * __inet_stream_connect(). */ if (uaddr) { if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) { sk->sk_disconnects++; err = sk->sk_prot->disconnect(sk, flags); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; goto out; } } switch (sock->state) { default: err = -EINVAL; goto out; case SS_CONNECTED: err = -EISCONN; goto out; case SS_CONNECTING: if (inet_test_bit(DEFER_CONNECT, sk)) err = is_sendmsg ? -EINPROGRESS : -EISCONN; else err = -EALREADY; /* Fall out of switch with err, set for this state */ break; case SS_UNCONNECTED: err = -EISCONN; if (sk->sk_state != TCP_CLOSE) goto out; if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) { err = sk->sk_prot->pre_connect(sk, uaddr, addr_len); if (err) goto out; } err = sk->sk_prot->connect(sk, uaddr, addr_len); if (err < 0) goto out; sock->state = SS_CONNECTING; if (!err && inet_test_bit(DEFER_CONNECT, sk)) goto out; /* Just entered SS_CONNECTING state; the only * difference is that return value in non-blocking * case is EINPROGRESS, rather than EALREADY. */ err = -EINPROGRESS; break; } timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { int writebias = (sk->sk_protocol == IPPROTO_TCP) && tcp_sk(sk)->fastopen_req && tcp_sk(sk)->fastopen_req->data ? 1 : 0; int dis = sk->sk_disconnects; /* Error code is set above */ if (!timeo || !inet_wait_for_connect(sk, timeo, writebias)) goto out; err = sock_intr_errno(timeo); if (signal_pending(current)) goto out; if (dis != sk->sk_disconnects) { err = -EPIPE; goto out; } } /* Connection was closed by RST, timeout, ICMP error * or another process disconnected us. */ if (sk->sk_state == TCP_CLOSE) goto sock_error; /* sk->sk_err may be not zero now, if RECVERR was ordered by user * and error was received after socket entered established state. * Hence, it is handled normally after connect() return successfully. */ sock->state = SS_CONNECTED; err = 0; out: return err; sock_error: err = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; sk->sk_disconnects++; if (sk->sk_prot->disconnect(sk, flags)) sock->state = SS_DISCONNECTING; goto out; } EXPORT_SYMBOL(__inet_stream_connect); int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { int err; lock_sock(sock->sk); err = __inet_stream_connect(sock, uaddr, addr_len, flags, 0); release_sock(sock->sk); return err; } EXPORT_SYMBOL(inet_stream_connect); void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *newsk) { sock_rps_record_flow(newsk); WARN_ON(!((1 << newsk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_RECV | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_CLOSE))); if (test_bit(SOCK_SUPPORT_ZC, &sock->flags)) set_bit(SOCK_SUPPORT_ZC, &newsock->flags); sock_graft(newsk, newsock); newsock->state = SS_CONNECTED; } /* * Accept a pending connection. The TCP layer now gives BSD semantics. */ int inet_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct sock *sk1 = sock->sk, *sk2; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ arg->err = -EINVAL; sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, arg); if (!sk2) return arg->err; lock_sock(sk2); __inet_accept(sock, newsock, sk2); release_sock(sk2); return 0; } EXPORT_SYMBOL(inet_accept); /* * This does both peername and sockname. */ int inet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr); int sin_addr_len = sizeof(*sin); sin->sin_family = AF_INET; lock_sock(sk); if (peer) { if (!inet->inet_dport || (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1)) { release_sock(sk); return -ENOTCONN; } sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET4_GETPEERNAME); } else { __be32 addr = inet->inet_rcv_saddr; if (!addr) addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET4_GETSOCKNAME); } release_sock(sk); memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return sin_addr_len; } EXPORT_SYMBOL(inet_getname); int inet_send_prepare(struct sock *sk) { sock_rps_record_flow(sk); /* We may need to bind the socket. */ if (data_race(!inet_sk(sk)->inet_num) && !sk->sk_prot->no_autobind && inet_autobind(sk)) return -EAGAIN; return 0; } EXPORT_SYMBOL_GPL(inet_send_prepare); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; if (unlikely(inet_send_prepare(sk))) return -EAGAIN; return INDIRECT_CALL_2(sk->sk_prot->sendmsg, tcp_sendmsg, udp_sendmsg, sk, msg, size); } EXPORT_SYMBOL(inet_sendmsg); void inet_splice_eof(struct socket *sock) { const struct proto *prot; struct sock *sk = sock->sk; if (unlikely(inet_send_prepare(sk))) return; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); if (prot->splice_eof) prot->splice_eof(sock); } EXPORT_SYMBOL_GPL(inet_splice_eof); INDIRECT_CALLABLE_DECLARE(int udp_recvmsg(struct sock *, struct msghdr *, size_t, int, int *)); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int addr_len = 0; int err; if (likely(!(flags & MSG_ERRQUEUE))) sock_rps_record_flow(sk); err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg, sk, msg, size, flags, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; return err; } EXPORT_SYMBOL(inet_recvmsg); int inet_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int err = 0; /* This should really check to make sure * the socket is a TCP socket. (WHY AC...) */ how++; /* maps 0->1 has the advantage of making bit 1 rcvs and 1->2 bit 2 snds. 2->3 */ if ((how & ~SHUTDOWN_MASK) || !how) /* MAXINT->0 */ return -EINVAL; lock_sock(sk); if (sock->state == SS_CONNECTING) { if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE)) sock->state = SS_DISCONNECTING; else sock->state = SS_CONNECTED; } switch (sk->sk_state) { case TCP_CLOSE: err = -ENOTCONN; /* Hack to wake up other listeners, who can poll for EPOLLHUP, even on eg. unconnected UDP sockets -- RR */ fallthrough; default: WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how); if (sk->sk_prot->shutdown) sk->sk_prot->shutdown(sk, how); break; /* Remaining two branches are temporary solution for missing * close() in multithreaded environment. It is _not_ a good idea, * but we have no choice until close() is repaired at VFS level. */ case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; fallthrough; case TCP_SYN_SENT: err = sk->sk_prot->disconnect(sk, O_NONBLOCK); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; break; } /* Wake up anyone sleeping in poll. */ sk->sk_state_change(sk); release_sock(sk); return err; } EXPORT_SYMBOL(inet_shutdown); /* * ioctl() calls you can issue on an INET socket. Most of these are * device configuration and stuff and very rarely used. Some ioctls * pass on to the socket itself. * * NOTE: I like the idea of a module for the config stuff. ie ifconfig * loads the devconfigure module does its configuring and unloads it. * There's a good 20K of config code hanging around the kernel. */ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; int err = 0; struct net *net = sock_net(sk); void __user *p = (void __user *)arg; struct ifreq ifr; struct rtentry rt; switch (cmd) { case SIOCADDRT: case SIOCDELRT: if (copy_from_user(&rt, p, sizeof(struct rtentry))) return -EFAULT; err = ip_rt_ioctl(net, cmd, &rt); break; case SIOCRTMSG: err = -EINVAL; break; case SIOCDARP: case SIOCGARP: case SIOCSARP: err = arp_ioctl(net, cmd, (void __user *)arg); break; case SIOCGIFADDR: case SIOCGIFBRDADDR: case SIOCGIFNETMASK: case SIOCGIFDSTADDR: case SIOCGIFPFLAGS: if (get_user_ifreq(&ifr, NULL, p)) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); if (!err && put_user_ifreq(&ifr, p)) err = -EFAULT; break; case SIOCSIFADDR: case SIOCSIFBRDADDR: case SIOCSIFNETMASK: case SIOCSIFDSTADDR: case SIOCSIFPFLAGS: case SIOCSIFFLAGS: if (get_user_ifreq(&ifr, NULL, p)) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); break; default: if (sk->sk_prot->ioctl) err = sk_ioctl(sk, cmd, (void __user *)arg); else err = -ENOIOCTLCMD; break; } return err; } EXPORT_SYMBOL(inet_ioctl); #ifdef CONFIG_COMPAT static int inet_compat_routing_ioctl(struct sock *sk, unsigned int cmd, struct compat_rtentry __user *ur) { compat_uptr_t rtdev; struct rtentry rt; if (copy_from_user(&rt.rt_dst, &ur->rt_dst, 3 * sizeof(struct sockaddr)) || get_user(rt.rt_flags, &ur->rt_flags) || get_user(rt.rt_metric, &ur->rt_metric) || get_user(rt.rt_mtu, &ur->rt_mtu) || get_user(rt.rt_window, &ur->rt_window) || get_user(rt.rt_irtt, &ur->rt_irtt) || get_user(rtdev, &ur->rt_dev)) return -EFAULT; rt.rt_dev = compat_ptr(rtdev); return ip_rt_ioctl(sock_net(sk), cmd, &rt); } static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; switch (cmd) { case SIOCADDRT: case SIOCDELRT: return inet_compat_routing_ioctl(sk, cmd, argp); default: if (!sk->sk_prot->compat_ioctl) return -ENOIOCTLCMD; return sk->sk_prot->compat_ioctl(sk, cmd, arg); } } #endif /* CONFIG_COMPAT */ const struct proto_ops inet_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = inet_getname, .poll = tcp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = inet_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif .splice_eof = inet_splice_eof, .splice_read = tcp_splice_read, .set_peek_off = sk_set_peek_off, .read_sock = tcp_read_sock, .read_skb = tcp_read_skb, .sendmsg_locked = tcp_sendmsg_locked, .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif .set_rcvlowat = tcp_set_rcvlowat, }; EXPORT_SYMBOL(inet_stream_ops); const struct proto_ops inet_dgram_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = inet_getname, .poll = udp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .read_skb = udp_read_skb, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .splice_eof = inet_splice_eof, .set_peek_off = udp_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif }; EXPORT_SYMBOL(inet_dgram_ops); /* * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without * udp_poll */ static const struct proto_ops inet_sockraw_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = inet_getname, .poll = datagram_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .splice_eof = inet_splice_eof, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif }; static const struct net_proto_family inet_family_ops = { .family = PF_INET, .create = inet_create, .owner = THIS_MODULE, }; /* Upon startup we insert all the elements in inetsw_array[] into * the linked list inetsw. */ static struct inet_protosw inetsw_array[] = { { .type = SOCK_STREAM, .protocol = IPPROTO_TCP, .prot = &tcp_prot, .ops = &inet_stream_ops, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }, { .type = SOCK_DGRAM, .protocol = IPPROTO_UDP, .prot = &udp_prot, .ops = &inet_dgram_ops, .flags = INET_PROTOSW_PERMANENT, }, { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMP, .prot = &ping_prot, .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, }, { .type = SOCK_RAW, .protocol = IPPROTO_IP, /* wild card */ .prot = &raw_prot, .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, } }; #define INETSW_ARRAY_LEN ARRAY_SIZE(inetsw_array) void inet_register_protosw(struct inet_protosw *p) { struct list_head *lh; struct inet_protosw *answer; int protocol = p->protocol; struct list_head *last_perm; spin_lock_bh(&inetsw_lock); if (p->type >= SOCK_MAX) goto out_illegal; /* If we are trying to override a permanent protocol, bail. */ last_perm = &inetsw[p->type]; list_for_each(lh, &inetsw[p->type]) { answer = list_entry(lh, struct inet_protosw, list); /* Check only the non-wild match. */ if ((INET_PROTOSW_PERMANENT & answer->flags) == 0) break; if (protocol == answer->protocol) goto out_permanent; last_perm = lh; } /* Add the new entry after the last permanent entry if any, so that * the new entry does not override a permanent entry when matched with * a wild-card protocol. But it is allowed to override any existing * non-permanent entry. This means that when we remove this entry, the * system automatically returns to the old behavior. */ list_add_rcu(&p->list, last_perm); out: spin_unlock_bh(&inetsw_lock); return; out_permanent: pr_err("Attempt to override permanent protocol %d\n", protocol); goto out; out_illegal: pr_err("Ignoring attempt to register invalid socket type %d\n", p->type); goto out; } EXPORT_SYMBOL(inet_register_protosw); void inet_unregister_protosw(struct inet_protosw *p) { if (INET_PROTOSW_PERMANENT & p->flags) { pr_err("Attempt to unregister permanent protocol %d\n", p->protocol); } else { spin_lock_bh(&inetsw_lock); list_del_rcu(&p->list); spin_unlock_bh(&inetsw_lock); synchronize_net(); } } EXPORT_SYMBOL(inet_unregister_protosw); static int inet_sk_reselect_saddr(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; struct flowi4 *fl4; struct rtable *rt; __be32 new_saddr; struct ip_options_rcu *inet_opt; int err; inet_opt = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* Query new route. */ fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, daddr, 0, sk->sk_bound_dev_if, sk->sk_protocol, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) return PTR_ERR(rt); new_saddr = fl4->saddr; if (new_saddr == old_saddr) { sk_setup_caps(sk, &rt->dst); return 0; } err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET); if (err) { ip_rt_put(rt); return err; } sk_setup_caps(sk, &rt->dst); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) { pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n", __func__, &old_saddr, &new_saddr); } /* * XXX The only one ugly spot where we need to * XXX really change the sockets identity after * XXX it has entered the hashes. -DaveM * * Besides that, it does not check for connection * uniqueness. Wait for troubles. */ return __sk_prot_rehash(sk); } int inet_sk_rebuild_header(struct sock *sk) { struct rtable *rt = dst_rtable(__sk_dst_check(sk, 0)); struct inet_sock *inet = inet_sk(sk); __be32 daddr; struct ip_options_rcu *inet_opt; struct flowi4 *fl4; int err; /* Route is OK, nothing to do. */ if (rt) return 0; /* Reroute. */ rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); daddr = inet->inet_daddr; if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; rcu_read_unlock(); fl4 = &inet->cork.fl.u.ip4; rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (!IS_ERR(rt)) { err = 0; sk_setup_caps(sk, &rt->dst); } else { err = PTR_ERR(rt); /* Routing failed... */ sk->sk_route_caps = 0; /* * Other protocols have to map its equivalent state to TCP_SYN_SENT. * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme */ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) || sk->sk_state != TCP_SYN_SENT || (sk->sk_userlocks & SOCK_BINDADDR_LOCK) || (err = inet_sk_reselect_saddr(sk)) != 0) WRITE_ONCE(sk->sk_err_soft, -err); } return err; } EXPORT_SYMBOL(inet_sk_rebuild_header); void inet_sk_set_state(struct sock *sk, int state) { trace_inet_sock_set_state(sk, sk->sk_state, state); sk->sk_state = state; } EXPORT_SYMBOL(inet_sk_set_state); void inet_sk_state_store(struct sock *sk, int newstate) { trace_inet_sock_set_state(sk, sk->sk_state, newstate); smp_store_release(&sk->sk_state, newstate); } struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { bool udpfrag = false, fixedid = false, gso_partial, encap; struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; unsigned int offset = 0; struct iphdr *iph; int proto, tot_len; int nhoff; int ihl; int id; skb_reset_network_header(skb); nhoff = skb_network_header(skb) - skb_mac_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(*iph)))) goto out; iph = ip_hdr(skb); ihl = iph->ihl * 4; if (ihl < sizeof(*iph)) goto out; id = ntohs(iph->id); proto = iph->protocol; /* Warning: after this point, iph might be no longer valid */ if (unlikely(!pskb_may_pull(skb, ihl))) goto out; __skb_pull(skb, ihl); encap = SKB_GSO_CB(skb)->encap_level > 0; if (encap) features &= skb->dev->hw_enc_features; SKB_GSO_CB(skb)->encap_level += ihl; skb_reset_transport_header(skb); segs = ERR_PTR(-EPROTONOSUPPORT); if (!skb->encapsulation || encap) { udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); /* fixed ID is invalid if DF bit is not set */ if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF))) goto out; } ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { segs = ops->callbacks.gso_segment(skb, features); if (!segs) skb->network_header = skb_mac_header(skb) + nhoff - skb->head; } if (IS_ERR_OR_NULL(segs)) goto out; gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); skb = segs; do { iph = (struct iphdr *)(skb_mac_header(skb) + nhoff); if (udpfrag) { iph->frag_off = htons(offset >> 3); if (skb->next) iph->frag_off |= htons(IP_MF); offset += skb->len - nhoff - ihl; tot_len = skb->len - nhoff; } else if (skb_is_gso(skb)) { if (!fixedid) { iph->id = htons(id); id += skb_shinfo(skb)->gso_segs; } if (gso_partial) tot_len = skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)iph; else tot_len = skb->len - nhoff; } else { if (!fixedid) iph->id = htons(id++); tot_len = skb->len - nhoff; } iph->tot_len = htons(tot_len); ip_send_check(iph); if (encap) skb_reset_inner_headers(skb); skb->network_header = (u8 *)iph - skb->head; skb_reset_mac_len(skb); } while ((skb = skb->next)); out: return segs; } static struct sk_buff *ipip_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP4)) return ERR_PTR(-EINVAL); return inet_gso_segment(skb, features); } struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct net_offload *ops; struct sk_buff *pp = NULL; const struct iphdr *iph; struct sk_buff *p; unsigned int hlen; unsigned int off; int flush = 1; int proto; off = skb_gro_offset(skb); hlen = off + sizeof(*iph); iph = skb_gro_header(skb, hlen, off); if (unlikely(!iph)) goto out; proto = iph->protocol; ops = rcu_dereference(inet_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) goto out; if (*(u8 *)iph != 0x45) goto out; if (ip_is_fragment(iph)) goto out; if (unlikely(ip_fast_csum((u8 *)iph, 5))) goto out; NAPI_GRO_CB(skb)->proto = proto; flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (ntohl(*(__be32 *)&iph->id) & ~IP_DF)); list_for_each_entry(p, head, list) { struct iphdr *iph2; if (!NAPI_GRO_CB(p)->same_flow) continue; iph2 = (struct iphdr *)(p->data + off); /* The above works because, with the exception of the top * (inner most) layer, we only aggregate pkts with the same * hdr length so all the hdrs we'll need to verify will start * at the same offset. */ if ((iph->protocol ^ iph2->protocol) | ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } NAPI_GRO_CB(skb)->flush |= flush; NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 */ skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); pp = indirect_call_gro_receive(tcp4_gro_receive, udp4_gro_receive, ops->callbacks.gro_receive, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } static struct sk_buff *ipip_gro_receive(struct list_head *head, struct sk_buff *skb) { if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } NAPI_GRO_CB(skb)->encap_mark = 1; return inet_gro_receive(head, skb); } #define SECONDS_PER_DAY 86400 /* inet_current_timestamp - Return IP network timestamp * * Return milliseconds since midnight in network byte order. */ __be32 inet_current_timestamp(void) { u32 secs; u32 msecs; struct timespec64 ts; ktime_get_real_ts64(&ts); /* Get secs since midnight. */ (void)div_u64_rem(ts.tv_sec, SECONDS_PER_DAY, &secs); /* Convert to msecs. */ msecs = secs * MSEC_PER_SEC; /* Convert nsec to msec. */ msecs += (u32)ts.tv_nsec / NSEC_PER_MSEC; /* Convert to network byte order. */ return htonl(msecs); } EXPORT_SYMBOL(inet_current_timestamp); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { unsigned int family = READ_ONCE(sk->sk_family); if (family == AF_INET) return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len); #endif return -EINVAL; } EXPORT_SYMBOL(inet_recv_error); int inet_gro_complete(struct sk_buff *skb, int nhoff) { struct iphdr *iph = (struct iphdr *)(skb->data + nhoff); const struct net_offload *ops; __be16 totlen = iph->tot_len; int proto = iph->protocol; int err = -ENOSYS; if (skb->encapsulation) { skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP)); skb_set_inner_network_header(skb, nhoff); } iph_set_totlen(iph, skb->len - nhoff); csum_replace2(&iph->check, totlen, iph->tot_len); ops = rcu_dereference(inet_offloads[proto]); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out; /* Only need to add sizeof(*iph) to get to the next hdr below * because any hdr with option will have been flushed in * inet_gro_receive(). */ err = INDIRECT_CALL_2(ops->callbacks.gro_complete, tcp4_gro_complete, udp4_gro_complete, skb, nhoff + sizeof(*iph)); out: return err; } static int ipip_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; return inet_gro_complete(skb, nhoff); } int inet_ctl_sock_create(struct sock **sk, unsigned short family, unsigned short type, unsigned char protocol, struct net *net) { struct socket *sock; int rc = sock_create_kern(net, family, type, protocol, &sock); if (rc == 0) { *sk = sock->sk; (*sk)->sk_allocation = GFP_ATOMIC; (*sk)->sk_use_task_frag = false; /* * Unhash it so that IP input processing does not even see it, * we do not wish this socket to see incoming packets. */ (*sk)->sk_prot->unhash(*sk); } return rc; } EXPORT_SYMBOL_GPL(inet_ctl_sock_create); unsigned long snmp_fold_field(void __percpu *mib, int offt) { unsigned long res = 0; int i; for_each_possible_cpu(i) res += snmp_get_cpu_field(mib, i, offt); return res; } EXPORT_SYMBOL_GPL(snmp_fold_field); #if BITS_PER_LONG==32 u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offt, size_t syncp_offset) { void *bhptr; struct u64_stats_sync *syncp; u64 v; unsigned int start; bhptr = per_cpu_ptr(mib, cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { start = u64_stats_fetch_begin(syncp); v = *(((u64 *)bhptr) + offt); } while (u64_stats_fetch_retry(syncp, start)); return v; } EXPORT_SYMBOL_GPL(snmp_get_cpu_field64); u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_offset) { u64 res = 0; int cpu; for_each_possible_cpu(cpu) { res += snmp_get_cpu_field64(mib, cpu, offt, syncp_offset); } return res; } EXPORT_SYMBOL_GPL(snmp_fold_field64); #endif #ifdef CONFIG_IP_MULTICAST static const struct net_protocol igmp_protocol = { .handler = igmp_rcv, }; #endif static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, .no_policy = 1, }; static __net_init int ipv4_mib_init_net(struct net *net) { int i; net->mib.tcp_statistics = alloc_percpu(struct tcp_mib); if (!net->mib.tcp_statistics) goto err_tcp_mib; net->mib.ip_statistics = alloc_percpu(struct ipstats_mib); if (!net->mib.ip_statistics) goto err_ip_mib; for_each_possible_cpu(i) { struct ipstats_mib *af_inet_stats; af_inet_stats = per_cpu_ptr(net->mib.ip_statistics, i); u64_stats_init(&af_inet_stats->syncp); } net->mib.net_statistics = alloc_percpu(struct linux_mib); if (!net->mib.net_statistics) goto err_net_mib; net->mib.udp_statistics = alloc_percpu(struct udp_mib); if (!net->mib.udp_statistics) goto err_udp_mib; net->mib.udplite_statistics = alloc_percpu(struct udp_mib); if (!net->mib.udplite_statistics) goto err_udplite_mib; net->mib.icmp_statistics = alloc_percpu(struct icmp_mib); if (!net->mib.icmp_statistics) goto err_icmp_mib; net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib), GFP_KERNEL); if (!net->mib.icmpmsg_statistics) goto err_icmpmsg_mib; tcp_mib_init(net); return 0; err_icmpmsg_mib: free_percpu(net->mib.icmp_statistics); err_icmp_mib: free_percpu(net->mib.udplite_statistics); err_udplite_mib: free_percpu(net->mib.udp_statistics); err_udp_mib: free_percpu(net->mib.net_statistics); err_net_mib: free_percpu(net->mib.ip_statistics); err_ip_mib: free_percpu(net->mib.tcp_statistics); err_tcp_mib: return -ENOMEM; } static __net_exit void ipv4_mib_exit_net(struct net *net) { kfree(net->mib.icmpmsg_statistics); free_percpu(net->mib.icmp_statistics); free_percpu(net->mib.udplite_statistics); free_percpu(net->mib.udp_statistics); free_percpu(net->mib.net_statistics); free_percpu(net->mib.ip_statistics); free_percpu(net->mib.tcp_statistics); #ifdef CONFIG_MPTCP /* allocated on demand, see mptcp_init_sock() */ free_percpu(net->mib.mptcp_statistics); #endif } static __net_initdata struct pernet_operations ipv4_mib_ops = { .init = ipv4_mib_init_net, .exit = ipv4_mib_exit_net, }; static int __init init_ipv4_mibs(void) { return register_pernet_subsys(&ipv4_mib_ops); } static __net_init int inet_init_net(struct net *net) { /* * Set defaults for local port range */ net->ipv4.ip_local_ports.range = 60999u << 16 | 32768u; seqlock_init(&net->ipv4.ping_group_range.lock); /* * Sane defaults - nobody may create ping sockets. * Boot scripts should set this to distro-specific group. */ net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1); net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0); /* Default values for sysctl-controlled parameters. * We set them here, in case sysctl is not compiled. */ net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; net->ipv4.sysctl_ip_fwd_update_priority = 1; net->ipv4.sysctl_ip_dynaddr = 0; net->ipv4.sysctl_ip_early_demux = 1; net->ipv4.sysctl_udp_early_demux = 1; net->ipv4.sysctl_tcp_early_demux = 1; net->ipv4.sysctl_nexthop_compat_mode = 1; #ifdef CONFIG_SYSCTL net->ipv4.sysctl_ip_prot_sock = PROT_SOCK; #endif /* Some igmp sysctl, whose values are always used */ net->ipv4.sysctl_igmp_max_memberships = 20; net->ipv4.sysctl_igmp_max_msf = 10; /* IGMP reports for link-local multicast groups are enabled by default */ net->ipv4.sysctl_igmp_llm_reports = 1; net->ipv4.sysctl_igmp_qrv = 2; net->ipv4.sysctl_fib_notify_on_flag_change = 0; return 0; } static __net_initdata struct pernet_operations af_inet_ops = { .init = inet_init_net, }; static int __init init_inet_pernet_ops(void) { return register_pernet_subsys(&af_inet_ops); } static int ipv4_proc_init(void); /* * IP protocol layer initialiser */ static const struct net_offload ipip_offload = { .callbacks = { .gso_segment = ipip_gso_segment, .gro_receive = ipip_gro_receive, .gro_complete = ipip_gro_complete, }, }; static int __init ipip_offload_init(void) { return inet_add_offload(&ipip_offload, IPPROTO_IPIP); } static int __init ipv4_offload_init(void) { /* * Add offloads */ if (udpv4_offload_init() < 0) pr_crit("%s: Cannot add UDP protocol offload\n", __func__); if (tcpv4_offload_init() < 0) pr_crit("%s: Cannot add TCP protocol offload\n", __func__); if (ipip_offload_init() < 0) pr_crit("%s: Cannot add IPIP protocol offload\n", __func__); net_hotdata.ip_packet_offload = (struct packet_offload) { .type = cpu_to_be16(ETH_P_IP), .callbacks = { .gso_segment = inet_gso_segment, .gro_receive = inet_gro_receive, .gro_complete = inet_gro_complete, }, }; dev_add_offload(&net_hotdata.ip_packet_offload); return 0; } fs_initcall(ipv4_offload_init); static struct packet_type ip_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .func = ip_rcv, .list_func = ip_list_rcv, }; static int __init inet_init(void) { struct inet_protosw *q; struct list_head *r; int rc; sock_skb_cb_check_size(sizeof(struct inet_skb_parm)); raw_hashinfo_init(&raw_v4_hashinfo); rc = proto_register(&tcp_prot, 1); if (rc) goto out; rc = proto_register(&udp_prot, 1); if (rc) goto out_unregister_tcp_proto; rc = proto_register(&raw_prot, 1); if (rc) goto out_unregister_udp_proto; rc = proto_register(&ping_prot, 1); if (rc) goto out_unregister_raw_proto; /* * Tell SOCKET that we are alive... */ (void)sock_register(&inet_family_ops); #ifdef CONFIG_SYSCTL ip_static_sysctl_init(); #endif /* * Add all the base protocols. */ if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0) pr_crit("%s: Cannot add ICMP protocol\n", __func__); net_hotdata.udp_protocol = (struct net_protocol) { .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, }; if (inet_add_protocol(&net_hotdata.udp_protocol, IPPROTO_UDP) < 0) pr_crit("%s: Cannot add UDP protocol\n", __func__); net_hotdata.tcp_protocol = (struct net_protocol) { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, .icmp_strict_tag_validation = 1, }; if (inet_add_protocol(&net_hotdata.tcp_protocol, IPPROTO_TCP) < 0) pr_crit("%s: Cannot add TCP protocol\n", __func__); #ifdef CONFIG_IP_MULTICAST if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0) pr_crit("%s: Cannot add IGMP protocol\n", __func__); #endif /* Register the socket-side information for inet_create. */ for (r = &inetsw[0]; r < &inetsw[SOCK_MAX]; ++r) INIT_LIST_HEAD(r); for (q = inetsw_array; q < &inetsw_array[INETSW_ARRAY_LEN]; ++q) inet_register_protosw(q); /* * Set the ARP module up */ arp_init(); /* * Set the IP module up */ ip_init(); /* Initialise per-cpu ipv4 mibs */ if (init_ipv4_mibs()) panic("%s: Cannot init ipv4 mibs\n", __func__); /* Setup TCP slab cache for open requests. */ tcp_init(); /* Setup UDP memory threshold */ udp_init(); /* Add UDP-Lite (RFC 3828) */ udplite4_register(); raw_init(); ping_init(); /* * Set the ICMP layer up */ if (icmp_init() < 0) panic("Failed to create the ICMP control socket.\n"); /* * Initialise the multicast router */ #if defined(CONFIG_IP_MROUTE) if (ip_mr_init()) pr_crit("%s: Cannot init ipv4 mroute\n", __func__); #endif if (init_inet_pernet_ops()) pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__); ipv4_proc_init(); ipfrag_init(); dev_add_pack(&ip_packet_type); ip_tunnel_core_init(); rc = 0; out: return rc; out_unregister_raw_proto: proto_unregister(&raw_prot); out_unregister_udp_proto: proto_unregister(&udp_prot); out_unregister_tcp_proto: proto_unregister(&tcp_prot); goto out; } fs_initcall(inet_init); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS static int __init ipv4_proc_init(void) { int rc = 0; if (raw_proc_init()) goto out_raw; if (tcp4_proc_init()) goto out_tcp; if (udp4_proc_init()) goto out_udp; if (ping_proc_init()) goto out_ping; if (ip_misc_proc_init()) goto out_misc; out: return rc; out_misc: ping_proc_exit(); out_ping: udp4_proc_exit(); out_udp: tcp4_proc_exit(); out_tcp: raw_proc_exit(); out_raw: rc = -ENOMEM; goto out; } #else /* CONFIG_PROC_FS */ static int __init ipv4_proc_init(void) { return 0; } #endif /* CONFIG_PROC_FS */ |
| 8 8 2 2 1 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/seq_file.h> #include <net/ip.h> #include <net/mptcp.h> #include <net/snmp.h> #include <net/net_namespace.h> #include "mib.h" static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPCapableSYNRX", MPTCP_MIB_MPCAPABLEPASSIVE), SNMP_MIB_ITEM("MPCapableSYNTX", MPTCP_MIB_MPCAPABLEACTIVE), SNMP_MIB_ITEM("MPCapableSYNACKRX", MPTCP_MIB_MPCAPABLEACTIVEACK), SNMP_MIB_ITEM("MPCapableACKRX", MPTCP_MIB_MPCAPABLEPASSIVEACK), SNMP_MIB_ITEM("MPCapableFallbackACK", MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK), SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK), SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP), SNMP_MIB_ITEM("MPCapableSYNTXDisabled", MPTCP_MIB_MPCAPABLEACTIVEDISABLED), SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT), SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX), SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX), SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC), SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX), SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), SNMP_MIB_ITEM("MPJoinSynTx", MPTCP_MIB_JOINSYNTX), SNMP_MIB_ITEM("MPJoinSynTxCreatSkErr", MPTCP_MIB_JOINSYNTXCREATSKERR), SNMP_MIB_ITEM("MPJoinSynTxBindErr", MPTCP_MIB_JOINSYNTXBINDERR), SNMP_MIB_ITEM("MPJoinSynTxConnectErr", MPTCP_MIB_JOINSYNTXCONNECTERR), SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH), SNMP_MIB_ITEM("InfiniteMapTx", MPTCP_MIB_INFINITEMAPTX), SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX), SNMP_MIB_ITEM("DSSNoMatchTCP", MPTCP_MIB_DSSTCPMISMATCH), SNMP_MIB_ITEM("DataCsumErr", MPTCP_MIB_DATACSUMERR), SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL), SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE), SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE), SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW), SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA), SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR), SNMP_MIB_ITEM("AddAddrTx", MPTCP_MIB_ADDADDRTX), SNMP_MIB_ITEM("AddAddrTxDrop", MPTCP_MIB_ADDADDRTXDROP), SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD), SNMP_MIB_ITEM("EchoAddTx", MPTCP_MIB_ECHOADDTX), SNMP_MIB_ITEM("EchoAddTxDrop", MPTCP_MIB_ECHOADDTXDROP), SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD), SNMP_MIB_ITEM("AddAddrDrop", MPTCP_MIB_ADDADDRDROP), SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX), SNMP_MIB_ITEM("MPJoinPortSynAckRx", MPTCP_MIB_JOINPORTSYNACKRX), SNMP_MIB_ITEM("MPJoinPortAckRx", MPTCP_MIB_JOINPORTACKRX), SNMP_MIB_ITEM("MismatchPortSynRx", MPTCP_MIB_MISMATCHPORTSYNRX), SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX), SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR), SNMP_MIB_ITEM("RmAddrDrop", MPTCP_MIB_RMADDRDROP), SNMP_MIB_ITEM("RmAddrTx", MPTCP_MIB_RMADDRTX), SNMP_MIB_ITEM("RmAddrTxDrop", MPTCP_MIB_RMADDRTXDROP), SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), SNMP_MIB_ITEM("MPFailTx", MPTCP_MIB_MPFAILTX), SNMP_MIB_ITEM("MPFailRx", MPTCP_MIB_MPFAILRX), SNMP_MIB_ITEM("MPFastcloseTx", MPTCP_MIB_MPFASTCLOSETX), SNMP_MIB_ITEM("MPFastcloseRx", MPTCP_MIB_MPFASTCLOSERX), SNMP_MIB_ITEM("MPRstTx", MPTCP_MIB_MPRSTTX), SNMP_MIB_ITEM("MPRstRx", MPTCP_MIB_MPRSTRX), SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED), SNMP_MIB_ITEM("SubflowStale", MPTCP_MIB_SUBFLOWSTALE), SNMP_MIB_ITEM("SubflowRecover", MPTCP_MIB_SUBFLOWRECOVER), SNMP_MIB_ITEM("SndWndShared", MPTCP_MIB_SNDWNDSHARED), SNMP_MIB_ITEM("RcvWndShared", MPTCP_MIB_RCVWNDSHARED), SNMP_MIB_ITEM("RcvWndConflictUpdate", MPTCP_MIB_RCVWNDCONFLICTUPDATE), SNMP_MIB_ITEM("RcvWndConflict", MPTCP_MIB_RCVWNDCONFLICT), SNMP_MIB_ITEM("MPCurrEstab", MPTCP_MIB_CURRESTAB), SNMP_MIB_ITEM("Blackhole", MPTCP_MIB_BLACKHOLE), SNMP_MIB_SENTINEL }; /* mptcp_mib_alloc - allocate percpu mib counters * * These are allocated when the first mptcp socket is created so * we do not waste percpu memory if mptcp isn't in use. */ bool mptcp_mib_alloc(struct net *net) { struct mptcp_mib __percpu *mib = alloc_percpu(struct mptcp_mib); if (!mib) return false; if (cmpxchg(&net->mib.mptcp_statistics, NULL, mib)) free_percpu(mib); return true; } void mptcp_seq_show(struct seq_file *seq) { unsigned long sum[ARRAY_SIZE(mptcp_snmp_list) - 1]; struct net *net = seq->private; int i; seq_puts(seq, "MPTcpExt:"); for (i = 0; mptcp_snmp_list[i].name; i++) seq_printf(seq, " %s", mptcp_snmp_list[i].name); seq_puts(seq, "\nMPTcpExt:"); memset(sum, 0, sizeof(sum)); if (net->mib.mptcp_statistics) snmp_get_cpu_field_batch(sum, mptcp_snmp_list, net->mib.mptcp_statistics); for (i = 0; mptcp_snmp_list[i].name; i++) seq_printf(seq, " %lu", sum[i]); seq_putc(seq, '\n'); } |
| 39 23 41 21 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 | /* SPDX-License-Identifier: GPL-2.0-only */ #undef TRACE_SYSTEM #define TRACE_SYSTEM l2tp #if !defined(_TRACE_L2TP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_L2TP_H #include <linux/tracepoint.h> #include <linux/l2tp.h> #include "l2tp_core.h" #define encap_type_name(e) { L2TP_ENCAPTYPE_##e, #e } #define show_encap_type_name(val) \ __print_symbolic(val, \ encap_type_name(UDP), \ encap_type_name(IP)) #define pw_type_name(p) { L2TP_PWTYPE_##p, #p } #define show_pw_type_name(val) \ __print_symbolic(val, \ pw_type_name(ETH_VLAN), \ pw_type_name(ETH), \ pw_type_name(PPP), \ pw_type_name(PPP_AC), \ pw_type_name(IP)) DECLARE_EVENT_CLASS(tunnel_only_evt, TP_PROTO(struct l2tp_tunnel *tunnel), TP_ARGS(tunnel), TP_STRUCT__entry( __array(char, name, L2TP_TUNNEL_NAME_MAX) ), TP_fast_assign( memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX); ), TP_printk("%s", __entry->name) ); DECLARE_EVENT_CLASS(session_only_evt, TP_PROTO(struct l2tp_session *session), TP_ARGS(session), TP_STRUCT__entry( __array(char, name, L2TP_SESSION_NAME_MAX) ), TP_fast_assign( memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); ), TP_printk("%s", __entry->name) ); TRACE_EVENT(register_tunnel, TP_PROTO(struct l2tp_tunnel *tunnel), TP_ARGS(tunnel), TP_STRUCT__entry( __array(char, name, L2TP_TUNNEL_NAME_MAX) __field(int, fd) __field(u32, tid) __field(u32, ptid) __field(int, version) __field(enum l2tp_encap_type, encap) ), TP_fast_assign( memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX); __entry->fd = tunnel->fd; __entry->tid = tunnel->tunnel_id; __entry->ptid = tunnel->peer_tunnel_id; __entry->version = tunnel->version; __entry->encap = tunnel->encap; ), TP_printk("%s: type=%s encap=%s version=L2TPv%d tid=%u ptid=%u fd=%d", __entry->name, __entry->fd > 0 ? "managed" : "unmanaged", show_encap_type_name(__entry->encap), __entry->version, __entry->tid, __entry->ptid, __entry->fd) ); DEFINE_EVENT(tunnel_only_evt, delete_tunnel, TP_PROTO(struct l2tp_tunnel *tunnel), TP_ARGS(tunnel) ); DEFINE_EVENT(tunnel_only_evt, free_tunnel, TP_PROTO(struct l2tp_tunnel *tunnel), TP_ARGS(tunnel) ); TRACE_EVENT(register_session, TP_PROTO(struct l2tp_session *session), TP_ARGS(session), TP_STRUCT__entry( __array(char, name, L2TP_SESSION_NAME_MAX) __field(u32, tid) __field(u32, ptid) __field(u32, sid) __field(u32, psid) __field(enum l2tp_pwtype, pwtype) ), TP_fast_assign( memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); __entry->tid = session->tunnel ? session->tunnel->tunnel_id : 0; __entry->ptid = session->tunnel ? session->tunnel->peer_tunnel_id : 0; __entry->sid = session->session_id; __entry->psid = session->peer_session_id; __entry->pwtype = session->pwtype; ), TP_printk("%s: pseudowire=%s sid=%u psid=%u tid=%u ptid=%u", __entry->name, show_pw_type_name(__entry->pwtype), __entry->sid, __entry->psid, __entry->sid, __entry->psid) ); DEFINE_EVENT(session_only_evt, delete_session, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DEFINE_EVENT(session_only_evt, free_session, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DEFINE_EVENT(session_only_evt, session_seqnum_lns_enable, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DEFINE_EVENT(session_only_evt, session_seqnum_lns_disable, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DECLARE_EVENT_CLASS(session_seqnum_evt, TP_PROTO(struct l2tp_session *session), TP_ARGS(session), TP_STRUCT__entry( __array(char, name, L2TP_SESSION_NAME_MAX) __field(u32, ns) __field(u32, nr) ), TP_fast_assign( memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); __entry->ns = session->ns; __entry->nr = session->nr; ), TP_printk("%s: ns=%u nr=%u", __entry->name, __entry->ns, __entry->nr) ); DEFINE_EVENT(session_seqnum_evt, session_seqnum_update, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DEFINE_EVENT(session_seqnum_evt, session_seqnum_reset, TP_PROTO(struct l2tp_session *session), TP_ARGS(session) ); DECLARE_EVENT_CLASS(session_pkt_discard_evt, TP_PROTO(struct l2tp_session *session, u32 pkt_ns), TP_ARGS(session, pkt_ns), TP_STRUCT__entry( __array(char, name, L2TP_SESSION_NAME_MAX) __field(u32, pkt_ns) __field(u32, my_nr) __field(u32, reorder_q_len) ), TP_fast_assign( memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX); __entry->pkt_ns = pkt_ns, __entry->my_nr = session->nr; __entry->reorder_q_len = skb_queue_len(&session->reorder_q); ), TP_printk("%s: pkt_ns=%u my_nr=%u reorder_q_len=%u", __entry->name, __entry->pkt_ns, __entry->my_nr, __entry->reorder_q_len) ); DEFINE_EVENT(session_pkt_discard_evt, session_pkt_expired, TP_PROTO(struct l2tp_session *session, u32 pkt_ns), TP_ARGS(session, pkt_ns) ); DEFINE_EVENT(session_pkt_discard_evt, session_pkt_outside_rx_window, TP_PROTO(struct l2tp_session *session, u32 pkt_ns), TP_ARGS(session, pkt_ns) ); DEFINE_EVENT(session_pkt_discard_evt, session_pkt_oos, TP_PROTO(struct l2tp_session *session, u32 pkt_ns), TP_ARGS(session, pkt_ns) ); #endif /* _TRACE_L2TP_H */ /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 2 2 3 182 182 183 4 180 7 7 1 6 2 5 7 11 1 5 5 81 10 13 6 3 3 3 3 1 1 1 1 1 6 6 5 1 4 5 5 15 13 2 8 8 10 10 1 1 1 3 1 1 1 1 1 1 5 5 34 5 3 1 1 23 21 21 48 48 28 28 33 1 1 2 34 32 2 34 34 10 26 34 34 1 1 34 33 44 43 34 44 39 39 36 11 7 4 4 3 1 2 1 1 1 2 2 6 2 1 1 1 1 3 1 1 8 1 2 1 1 4 3 2 1 1 17 25 3 3 3 40 25 30 23 10 51 1 5 1 44 5 5 3 18 3 8 1 1 5 11 2 1 1 1 3 1 2 54 15 43 1 3 138 3 298 194 10 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 | // SPDX-License-Identifier: GPL-2.0 /* * Written for linux by Johan Myreen as a translation from * the assembly version by Linus (with diacriticals added) * * Some additional features added by Christoph Niemann (ChN), March 1993 * * Loadable keymaps by Risto Kankkunen, May 1993 * * Diacriticals redone & other small changes, aeb@cwi.nl, June 1993 * Added decr/incr_console, dynamic keymaps, Unicode support, * dynamic function/string keys, led setting, Sept 1994 * `Sticky' modifier keys, 951006. * * 11-11-96: SAK should now work in the raw mode (Martin Mares) * * Modified to provide 'generic' keyboard support by Hamish Macdonald * Merge with the m68k keyboard driver and split-off of the PC low-level * parts by Geert Uytterhoeven, May 1997 * * 27-05-97: Added support for the Magic SysRq Key (Martin Mares) * 30-07-98: Dead keys redone, aeb@cwi.nl. * 21-08-02: Converted to input API, major cleanup. (Vojtech Pavlik) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/consolemap.h> #include <linux/init.h> #include <linux/input.h> #include <linux/jiffies.h> #include <linux/kbd_diacr.h> #include <linux/kbd_kern.h> #include <linux/leds.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/nospec.h> #include <linux/notifier.h> #include <linux/reboot.h> #include <linux/sched/debug.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/tty_flip.h> #include <linux/tty.h> #include <linux/uaccess.h> #include <linux/vt_kern.h> #include <asm/irq_regs.h> /* * Exported functions/variables */ #define KBD_DEFMODE (BIT(VC_REPEAT) | BIT(VC_META)) #if defined(CONFIG_X86) || defined(CONFIG_PARISC) #include <asm/kbdleds.h> #else static inline int kbd_defleds(void) { return 0; } #endif #define KBD_DEFLOCK 0 /* * Handler Tables. */ #define K_HANDLERS\ k_self, k_fn, k_spec, k_pad,\ k_dead, k_cons, k_cur, k_shift,\ k_meta, k_ascii, k_lock, k_lowercase,\ k_slock, k_dead2, k_brl, k_ignore typedef void (k_handler_fn)(struct vc_data *vc, unsigned char value, char up_flag); static k_handler_fn K_HANDLERS; static k_handler_fn *k_handler[16] = { K_HANDLERS }; #define FN_HANDLERS\ fn_null, fn_enter, fn_show_ptregs, fn_show_mem,\ fn_show_state, fn_send_intr, fn_lastcons, fn_caps_toggle,\ fn_num, fn_hold, fn_scroll_forw, fn_scroll_back,\ fn_boot_it, fn_caps_on, fn_compose, fn_SAK,\ fn_dec_console, fn_inc_console, fn_spawn_con, fn_bare_num typedef void (fn_handler_fn)(struct vc_data *vc); static fn_handler_fn FN_HANDLERS; static fn_handler_fn *fn_handler[] = { FN_HANDLERS }; /* * Variables exported for vt_ioctl.c */ struct vt_spawn_console vt_spawn_con = { .lock = __SPIN_LOCK_UNLOCKED(vt_spawn_con.lock), .pid = NULL, .sig = 0, }; /* * Internal Data. */ static struct kbd_struct kbd_table[MAX_NR_CONSOLES]; static struct kbd_struct *kbd = kbd_table; /* maximum values each key_handler can handle */ static const unsigned char max_vals[] = { [ KT_LATIN ] = 255, [ KT_FN ] = ARRAY_SIZE(func_table) - 1, [ KT_SPEC ] = ARRAY_SIZE(fn_handler) - 1, [ KT_PAD ] = NR_PAD - 1, [ KT_DEAD ] = NR_DEAD - 1, [ KT_CONS ] = 255, [ KT_CUR ] = 3, [ KT_SHIFT ] = NR_SHIFT - 1, [ KT_META ] = 255, [ KT_ASCII ] = NR_ASCII - 1, [ KT_LOCK ] = NR_LOCK - 1, [ KT_LETTER ] = 255, [ KT_SLOCK ] = NR_LOCK - 1, [ KT_DEAD2 ] = 255, [ KT_BRL ] = NR_BRL - 1, }; static const int NR_TYPES = ARRAY_SIZE(max_vals); static void kbd_bh(struct tasklet_struct *unused); static DECLARE_TASKLET_DISABLED(keyboard_tasklet, kbd_bh); static struct input_handler kbd_handler; static DEFINE_SPINLOCK(kbd_event_lock); static DEFINE_SPINLOCK(led_lock); static DEFINE_SPINLOCK(func_buf_lock); /* guard 'func_buf' and friends */ static DECLARE_BITMAP(key_down, KEY_CNT); /* keyboard key bitmap */ static unsigned char shift_down[NR_SHIFT]; /* shift state counters.. */ static bool dead_key_next; /* Handles a number being assembled on the number pad */ static bool npadch_active; static unsigned int npadch_value; static unsigned int diacr; static bool rep; /* flag telling character repeat */ static int shift_state = 0; static unsigned int ledstate = -1U; /* undefined */ static unsigned char ledioctl; static bool vt_switch; /* * Notifier list for console keyboard events */ static ATOMIC_NOTIFIER_HEAD(keyboard_notifier_list); int register_keyboard_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&keyboard_notifier_list, nb); } EXPORT_SYMBOL_GPL(register_keyboard_notifier); int unregister_keyboard_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&keyboard_notifier_list, nb); } EXPORT_SYMBOL_GPL(unregister_keyboard_notifier); /* * Translation of scancodes to keycodes. We set them on only the first * keyboard in the list that accepts the scancode and keycode. * Explanation for not choosing the first attached keyboard anymore: * USB keyboards for example have two event devices: one for all "normal" * keys and one for extra function keys (like "volume up", "make coffee", * etc.). So this means that scancodes for the extra function keys won't * be valid for the first event device, but will be for the second. */ struct getset_keycode_data { struct input_keymap_entry ke; int error; }; static int getkeycode_helper(struct input_handle *handle, void *data) { struct getset_keycode_data *d = data; d->error = input_get_keycode(handle->dev, &d->ke); return d->error == 0; /* stop as soon as we successfully get one */ } static int getkeycode(unsigned int scancode) { struct getset_keycode_data d = { .ke = { .flags = 0, .len = sizeof(scancode), .keycode = 0, }, .error = -ENODEV, }; memcpy(d.ke.scancode, &scancode, sizeof(scancode)); input_handler_for_each_handle(&kbd_handler, &d, getkeycode_helper); return d.error ?: d.ke.keycode; } static int setkeycode_helper(struct input_handle *handle, void *data) { struct getset_keycode_data *d = data; d->error = input_set_keycode(handle->dev, &d->ke); return d->error == 0; /* stop as soon as we successfully set one */ } static int setkeycode(unsigned int scancode, unsigned int keycode) { struct getset_keycode_data d = { .ke = { .flags = 0, .len = sizeof(scancode), .keycode = keycode, }, .error = -ENODEV, }; memcpy(d.ke.scancode, &scancode, sizeof(scancode)); input_handler_for_each_handle(&kbd_handler, &d, setkeycode_helper); return d.error; } /* * Making beeps and bells. Note that we prefer beeps to bells, but when * shutting the sound off we do both. */ static int kd_sound_helper(struct input_handle *handle, void *data) { unsigned int *hz = data; struct input_dev *dev = handle->dev; if (test_bit(EV_SND, dev->evbit)) { if (test_bit(SND_TONE, dev->sndbit)) { input_inject_event(handle, EV_SND, SND_TONE, *hz); if (*hz) return 0; } if (test_bit(SND_BELL, dev->sndbit)) input_inject_event(handle, EV_SND, SND_BELL, *hz ? 1 : 0); } return 0; } static void kd_nosound(struct timer_list *unused) { static unsigned int zero; input_handler_for_each_handle(&kbd_handler, &zero, kd_sound_helper); } static DEFINE_TIMER(kd_mksound_timer, kd_nosound); void kd_mksound(unsigned int hz, unsigned int ticks) { del_timer_sync(&kd_mksound_timer); input_handler_for_each_handle(&kbd_handler, &hz, kd_sound_helper); if (hz && ticks) mod_timer(&kd_mksound_timer, jiffies + ticks); } EXPORT_SYMBOL(kd_mksound); /* * Setting the keyboard rate. */ static int kbd_rate_helper(struct input_handle *handle, void *data) { struct input_dev *dev = handle->dev; struct kbd_repeat *rpt = data; if (test_bit(EV_REP, dev->evbit)) { if (rpt[0].delay > 0) input_inject_event(handle, EV_REP, REP_DELAY, rpt[0].delay); if (rpt[0].period > 0) input_inject_event(handle, EV_REP, REP_PERIOD, rpt[0].period); rpt[1].delay = dev->rep[REP_DELAY]; rpt[1].period = dev->rep[REP_PERIOD]; } return 0; } int kbd_rate(struct kbd_repeat *rpt) { struct kbd_repeat data[2] = { *rpt }; input_handler_for_each_handle(&kbd_handler, data, kbd_rate_helper); *rpt = data[1]; /* Copy currently used settings */ return 0; } /* * Helper Functions. */ static void put_queue(struct vc_data *vc, int ch) { tty_insert_flip_char(&vc->port, ch, 0); tty_flip_buffer_push(&vc->port); } static void puts_queue(struct vc_data *vc, const char *cp) { tty_insert_flip_string(&vc->port, cp, strlen(cp)); tty_flip_buffer_push(&vc->port); } static void applkey(struct vc_data *vc, int key, char mode) { static char buf[] = { 0x1b, 'O', 0x00, 0x00 }; buf[1] = (mode ? 'O' : '['); buf[2] = key; puts_queue(vc, buf); } /* * Many other routines do put_queue, but I think either * they produce ASCII, or they produce some user-assigned * string, and in both cases we might assume that it is * in utf-8 already. */ static void to_utf8(struct vc_data *vc, uint c) { if (c < 0x80) /* 0******* */ put_queue(vc, c); else if (c < 0x800) { /* 110***** 10****** */ put_queue(vc, 0xc0 | (c >> 6)); put_queue(vc, 0x80 | (c & 0x3f)); } else if (c < 0x10000) { if (c >= 0xD800 && c < 0xE000) return; if (c == 0xFFFF) return; /* 1110**** 10****** 10****** */ put_queue(vc, 0xe0 | (c >> 12)); put_queue(vc, 0x80 | ((c >> 6) & 0x3f)); put_queue(vc, 0x80 | (c & 0x3f)); } else if (c < 0x110000) { /* 11110*** 10****** 10****** 10****** */ put_queue(vc, 0xf0 | (c >> 18)); put_queue(vc, 0x80 | ((c >> 12) & 0x3f)); put_queue(vc, 0x80 | ((c >> 6) & 0x3f)); put_queue(vc, 0x80 | (c & 0x3f)); } } /* FIXME: review locking for vt.c callers */ static void set_leds(void) { tasklet_schedule(&keyboard_tasklet); } /* * Called after returning from RAW mode or when changing consoles - recompute * shift_down[] and shift_state from key_down[] maybe called when keymap is * undefined, so that shiftkey release is seen. The caller must hold the * kbd_event_lock. */ static void do_compute_shiftstate(void) { unsigned int k, sym, val; shift_state = 0; memset(shift_down, 0, sizeof(shift_down)); for_each_set_bit(k, key_down, min(NR_KEYS, KEY_CNT)) { sym = U(key_maps[0][k]); if (KTYP(sym) != KT_SHIFT && KTYP(sym) != KT_SLOCK) continue; val = KVAL(sym); if (val == KVAL(K_CAPSSHIFT)) val = KVAL(K_SHIFT); shift_down[val]++; shift_state |= BIT(val); } } /* We still have to export this method to vt.c */ void vt_set_leds_compute_shiftstate(void) { unsigned long flags; /* * When VT is switched, the keyboard led needs to be set once. * Ensure that after the switch is completed, the state of the * keyboard LED is consistent with the state of the keyboard lock. */ vt_switch = true; set_leds(); spin_lock_irqsave(&kbd_event_lock, flags); do_compute_shiftstate(); spin_unlock_irqrestore(&kbd_event_lock, flags); } /* * We have a combining character DIACR here, followed by the character CH. * If the combination occurs in the table, return the corresponding value. * Otherwise, if CH is a space or equals DIACR, return DIACR. * Otherwise, conclude that DIACR was not combining after all, * queue it and return CH. */ static unsigned int handle_diacr(struct vc_data *vc, unsigned int ch) { unsigned int d = diacr; unsigned int i; diacr = 0; if ((d & ~0xff) == BRL_UC_ROW) { if ((ch & ~0xff) == BRL_UC_ROW) return d | ch; } else { for (i = 0; i < accent_table_size; i++) if (accent_table[i].diacr == d && accent_table[i].base == ch) return accent_table[i].result; } if (ch == ' ' || ch == (BRL_UC_ROW|0) || ch == d) return d; if (kbd->kbdmode == VC_UNICODE) to_utf8(vc, d); else { int c = conv_uni_to_8bit(d); if (c != -1) put_queue(vc, c); } return ch; } /* * Special function handlers */ static void fn_enter(struct vc_data *vc) { if (diacr) { if (kbd->kbdmode == VC_UNICODE) to_utf8(vc, diacr); else { int c = conv_uni_to_8bit(diacr); if (c != -1) put_queue(vc, c); } diacr = 0; } put_queue(vc, '\r'); if (vc_kbd_mode(kbd, VC_CRLF)) put_queue(vc, '\n'); } static void fn_caps_toggle(struct vc_data *vc) { if (rep) return; chg_vc_kbd_led(kbd, VC_CAPSLOCK); } static void fn_caps_on(struct vc_data *vc) { if (rep) return; set_vc_kbd_led(kbd, VC_CAPSLOCK); } static void fn_show_ptregs(struct vc_data *vc) { struct pt_regs *regs = get_irq_regs(); if (regs) show_regs(regs); } static void fn_hold(struct vc_data *vc) { struct tty_struct *tty = vc->port.tty; if (rep || !tty) return; /* * Note: SCROLLOCK will be set (cleared) by stop_tty (start_tty); * these routines are also activated by ^S/^Q. * (And SCROLLOCK can also be set by the ioctl KDSKBLED.) */ if (tty->flow.stopped) start_tty(tty); else stop_tty(tty); } static void fn_num(struct vc_data *vc) { if (vc_kbd_mode(kbd, VC_APPLIC)) applkey(vc, 'P', 1); else fn_bare_num(vc); } /* * Bind this to Shift-NumLock if you work in application keypad mode * but want to be able to change the NumLock flag. * Bind this to NumLock if you prefer that the NumLock key always * changes the NumLock flag. */ static void fn_bare_num(struct vc_data *vc) { if (!rep) chg_vc_kbd_led(kbd, VC_NUMLOCK); } static void fn_lastcons(struct vc_data *vc) { /* switch to the last used console, ChN */ set_console(last_console); } static void fn_dec_console(struct vc_data *vc) { int i, cur = fg_console; /* Currently switching? Queue this next switch relative to that. */ if (want_console != -1) cur = want_console; for (i = cur - 1; i != cur; i--) { if (i == -1) i = MAX_NR_CONSOLES - 1; if (vc_cons_allocated(i)) break; } set_console(i); } static void fn_inc_console(struct vc_data *vc) { int i, cur = fg_console; /* Currently switching? Queue this next switch relative to that. */ if (want_console != -1) cur = want_console; for (i = cur+1; i != cur; i++) { if (i == MAX_NR_CONSOLES) i = 0; if (vc_cons_allocated(i)) break; } set_console(i); } static void fn_send_intr(struct vc_data *vc) { tty_insert_flip_char(&vc->port, 0, TTY_BREAK); tty_flip_buffer_push(&vc->port); } static void fn_scroll_forw(struct vc_data *vc) { scrollfront(vc, 0); } static void fn_scroll_back(struct vc_data *vc) { scrollback(vc); } static void fn_show_mem(struct vc_data *vc) { show_mem(); } static void fn_show_state(struct vc_data *vc) { show_state(); } static void fn_boot_it(struct vc_data *vc) { ctrl_alt_del(); } static void fn_compose(struct vc_data *vc) { dead_key_next = true; } static void fn_spawn_con(struct vc_data *vc) { spin_lock(&vt_spawn_con.lock); if (vt_spawn_con.pid) if (kill_pid(vt_spawn_con.pid, vt_spawn_con.sig, 1)) { put_pid(vt_spawn_con.pid); vt_spawn_con.pid = NULL; } spin_unlock(&vt_spawn_con.lock); } static void fn_SAK(struct vc_data *vc) { struct work_struct *SAK_work = &vc_cons[fg_console].SAK_work; schedule_work(SAK_work); } static void fn_null(struct vc_data *vc) { do_compute_shiftstate(); } /* * Special key handlers */ static void k_ignore(struct vc_data *vc, unsigned char value, char up_flag) { } static void k_spec(struct vc_data *vc, unsigned char value, char up_flag) { if (up_flag) return; if (value >= ARRAY_SIZE(fn_handler)) return; if ((kbd->kbdmode == VC_RAW || kbd->kbdmode == VC_MEDIUMRAW || kbd->kbdmode == VC_OFF) && value != KVAL(K_SAK)) return; /* SAK is allowed even in raw mode */ fn_handler[value](vc); } static void k_lowercase(struct vc_data *vc, unsigned char value, char up_flag) { pr_err("k_lowercase was called - impossible\n"); } static void k_unicode(struct vc_data *vc, unsigned int value, char up_flag) { if (up_flag) return; /* no action, if this is a key release */ if (diacr) value = handle_diacr(vc, value); if (dead_key_next) { dead_key_next = false; diacr = value; return; } if (kbd->kbdmode == VC_UNICODE) to_utf8(vc, value); else { int c = conv_uni_to_8bit(value); if (c != -1) put_queue(vc, c); } } /* * Handle dead key. Note that we now may have several * dead keys modifying the same character. Very useful * for Vietnamese. */ static void k_deadunicode(struct vc_data *vc, unsigned int value, char up_flag) { if (up_flag) return; diacr = (diacr ? handle_diacr(vc, value) : value); } static void k_self(struct vc_data *vc, unsigned char value, char up_flag) { k_unicode(vc, conv_8bit_to_uni(value), up_flag); } static void k_dead2(struct vc_data *vc, unsigned char value, char up_flag) { k_deadunicode(vc, value, up_flag); } /* * Obsolete - for backwards compatibility only */ static void k_dead(struct vc_data *vc, unsigned char value, char up_flag) { static const unsigned char ret_diacr[NR_DEAD] = { '`', /* dead_grave */ '\'', /* dead_acute */ '^', /* dead_circumflex */ '~', /* dead_tilda */ '"', /* dead_diaeresis */ ',', /* dead_cedilla */ '_', /* dead_macron */ 'U', /* dead_breve */ '.', /* dead_abovedot */ '*', /* dead_abovering */ '=', /* dead_doubleacute */ 'c', /* dead_caron */ 'k', /* dead_ogonek */ 'i', /* dead_iota */ '#', /* dead_voiced_sound */ 'o', /* dead_semivoiced_sound */ '!', /* dead_belowdot */ '?', /* dead_hook */ '+', /* dead_horn */ '-', /* dead_stroke */ ')', /* dead_abovecomma */ '(', /* dead_abovereversedcomma */ ':', /* dead_doublegrave */ 'n', /* dead_invertedbreve */ ';', /* dead_belowcomma */ '$', /* dead_currency */ '@', /* dead_greek */ }; k_deadunicode(vc, ret_diacr[value], up_flag); } static void k_cons(struct vc_data *vc, unsigned char value, char up_flag) { if (up_flag) return; set_console(value); } static void k_fn(struct vc_data *vc, unsigned char value, char up_flag) { if (up_flag) return; if ((unsigned)value < ARRAY_SIZE(func_table)) { unsigned long flags; spin_lock_irqsave(&func_buf_lock, flags); if (func_table[value]) puts_queue(vc, func_table[value]); spin_unlock_irqrestore(&func_buf_lock, flags); } else pr_err("k_fn called with value=%d\n", value); } static void k_cur(struct vc_data *vc, unsigned char value, char up_flag) { static const char cur_chars[] = "BDCA"; if (up_flag) return; applkey(vc, cur_chars[value], vc_kbd_mode(kbd, VC_CKMODE)); } static void k_pad(struct vc_data *vc, unsigned char value, char up_flag) { static const char pad_chars[] = "0123456789+-*/\015,.?()#"; static const char app_map[] = "pqrstuvwxylSRQMnnmPQS"; if (up_flag) return; /* no action, if this is a key release */ /* kludge... shift forces cursor/number keys */ if (vc_kbd_mode(kbd, VC_APPLIC) && !shift_down[KG_SHIFT]) { applkey(vc, app_map[value], 1); return; } if (!vc_kbd_led(kbd, VC_NUMLOCK)) { switch (value) { case KVAL(K_PCOMMA): case KVAL(K_PDOT): k_fn(vc, KVAL(K_REMOVE), 0); return; case KVAL(K_P0): k_fn(vc, KVAL(K_INSERT), 0); return; case KVAL(K_P1): k_fn(vc, KVAL(K_SELECT), 0); return; case KVAL(K_P2): k_cur(vc, KVAL(K_DOWN), 0); return; case KVAL(K_P3): k_fn(vc, KVAL(K_PGDN), 0); return; case KVAL(K_P4): k_cur(vc, KVAL(K_LEFT), 0); return; case KVAL(K_P6): k_cur(vc, KVAL(K_RIGHT), 0); return; case KVAL(K_P7): k_fn(vc, KVAL(K_FIND), 0); return; case KVAL(K_P8): k_cur(vc, KVAL(K_UP), 0); return; case KVAL(K_P9): k_fn(vc, KVAL(K_PGUP), 0); return; case KVAL(K_P5): applkey(vc, 'G', vc_kbd_mode(kbd, VC_APPLIC)); return; } } put_queue(vc, pad_chars[value]); if (value == KVAL(K_PENTER) && vc_kbd_mode(kbd, VC_CRLF)) put_queue(vc, '\n'); } static void k_shift(struct vc_data *vc, unsigned char value, char up_flag) { int old_state = shift_state; if (rep) return; /* * Mimic typewriter: * a CapsShift key acts like Shift but undoes CapsLock */ if (value == KVAL(K_CAPSSHIFT)) { value = KVAL(K_SHIFT); if (!up_flag) clr_vc_kbd_led(kbd, VC_CAPSLOCK); } if (up_flag) { /* * handle the case that two shift or control * keys are depressed simultaneously */ if (shift_down[value]) shift_down[value]--; } else shift_down[value]++; if (shift_down[value]) shift_state |= BIT(value); else shift_state &= ~BIT(value); /* kludge */ if (up_flag && shift_state != old_state && npadch_active) { if (kbd->kbdmode == VC_UNICODE) to_utf8(vc, npadch_value); else put_queue(vc, npadch_value & 0xff); npadch_active = false; } } static void k_meta(struct vc_data *vc, unsigned char value, char up_flag) { if (up_flag) return; if (vc_kbd_mode(kbd, VC_META)) { put_queue(vc, '\033'); put_queue(vc, value); } else put_queue(vc, value | BIT(7)); } static void k_ascii(struct vc_data *vc, unsigned char value, char up_flag) { unsigned int base; if (up_flag) return; if (value < 10) { /* decimal input of code, while Alt depressed */ base = 10; } else { /* hexadecimal input of code, while AltGr depressed */ value -= 10; base = 16; } if (!npadch_active) { npadch_value = 0; npadch_active = true; } npadch_value = npadch_value * base + value; } static void k_lock(struct vc_data *vc, unsigned char value, char up_flag) { if (up_flag || rep) return; chg_vc_kbd_lock(kbd, value); } static void k_slock(struct vc_data *vc, unsigned char value, char up_flag) { k_shift(vc, value, up_flag); if (up_flag || rep) return; chg_vc_kbd_slock(kbd, value); /* try to make Alt, oops, AltGr and such work */ if (!key_maps[kbd->lockstate ^ kbd->slockstate]) { kbd->slockstate = 0; chg_vc_kbd_slock(kbd, value); } } /* by default, 300ms interval for combination release */ static unsigned brl_timeout = 300; MODULE_PARM_DESC(brl_timeout, "Braille keys release delay in ms (0 for commit on first key release)"); module_param(brl_timeout, uint, 0644); static unsigned brl_nbchords = 1; MODULE_PARM_DESC(brl_nbchords, "Number of chords that produce a braille pattern (0 for dead chords)"); module_param(brl_nbchords, uint, 0644); static void k_brlcommit(struct vc_data *vc, unsigned int pattern, char up_flag) { static unsigned long chords; static unsigned committed; if (!brl_nbchords) k_deadunicode(vc, BRL_UC_ROW | pattern, up_flag); else { committed |= pattern; chords++; if (chords == brl_nbchords) { k_unicode(vc, BRL_UC_ROW | committed, up_flag); chords = 0; committed = 0; } } } static void k_brl(struct vc_data *vc, unsigned char value, char up_flag) { static unsigned pressed, committing; static unsigned long releasestart; if (kbd->kbdmode != VC_UNICODE) { if (!up_flag) pr_warn("keyboard mode must be unicode for braille patterns\n"); return; } if (!value) { k_unicode(vc, BRL_UC_ROW, up_flag); return; } if (value > 8) return; if (!up_flag) { pressed |= BIT(value - 1); if (!brl_timeout) committing = pressed; } else if (brl_timeout) { if (!committing || time_after(jiffies, releasestart + msecs_to_jiffies(brl_timeout))) { committing = pressed; releasestart = jiffies; } pressed &= ~BIT(value - 1); if (!pressed && committing) { k_brlcommit(vc, committing, 0); committing = 0; } } else { if (committing) { k_brlcommit(vc, committing, 0); committing = 0; } pressed &= ~BIT(value - 1); } } #if IS_ENABLED(CONFIG_INPUT_LEDS) && IS_ENABLED(CONFIG_LEDS_TRIGGERS) struct kbd_led_trigger { struct led_trigger trigger; unsigned int mask; }; static int kbd_led_trigger_activate(struct led_classdev *cdev) { struct kbd_led_trigger *trigger = container_of(cdev->trigger, struct kbd_led_trigger, trigger); tasklet_disable(&keyboard_tasklet); if (ledstate != -1U) led_set_brightness(cdev, ledstate & trigger->mask ? LED_FULL : LED_OFF); tasklet_enable(&keyboard_tasklet); return 0; } #define KBD_LED_TRIGGER(_led_bit, _name) { \ .trigger = { \ .name = _name, \ .activate = kbd_led_trigger_activate, \ }, \ .mask = BIT(_led_bit), \ } #define KBD_LOCKSTATE_TRIGGER(_led_bit, _name) \ KBD_LED_TRIGGER((_led_bit) + 8, _name) static struct kbd_led_trigger kbd_led_triggers[] = { KBD_LED_TRIGGER(VC_SCROLLOCK, "kbd-scrolllock"), KBD_LED_TRIGGER(VC_NUMLOCK, "kbd-numlock"), KBD_LED_TRIGGER(VC_CAPSLOCK, "kbd-capslock"), KBD_LED_TRIGGER(VC_KANALOCK, "kbd-kanalock"), KBD_LOCKSTATE_TRIGGER(VC_SHIFTLOCK, "kbd-shiftlock"), KBD_LOCKSTATE_TRIGGER(VC_ALTGRLOCK, "kbd-altgrlock"), KBD_LOCKSTATE_TRIGGER(VC_CTRLLOCK, "kbd-ctrllock"), KBD_LOCKSTATE_TRIGGER(VC_ALTLOCK, "kbd-altlock"), KBD_LOCKSTATE_TRIGGER(VC_SHIFTLLOCK, "kbd-shiftllock"), KBD_LOCKSTATE_TRIGGER(VC_SHIFTRLOCK, "kbd-shiftrlock"), KBD_LOCKSTATE_TRIGGER(VC_CTRLLLOCK, "kbd-ctrlllock"), KBD_LOCKSTATE_TRIGGER(VC_CTRLRLOCK, "kbd-ctrlrlock"), }; static void kbd_propagate_led_state(unsigned int old_state, unsigned int new_state) { struct kbd_led_trigger *trigger; unsigned int changed = old_state ^ new_state; int i; for (i = 0; i < ARRAY_SIZE(kbd_led_triggers); i++) { trigger = &kbd_led_triggers[i]; if (changed & trigger->mask) led_trigger_event(&trigger->trigger, new_state & trigger->mask ? LED_FULL : LED_OFF); } } static int kbd_update_leds_helper(struct input_handle *handle, void *data) { unsigned int led_state = *(unsigned int *)data; if (test_bit(EV_LED, handle->dev->evbit)) kbd_propagate_led_state(~led_state, led_state); return 0; } static void kbd_init_leds(void) { int error; int i; for (i = 0; i < ARRAY_SIZE(kbd_led_triggers); i++) { error = led_trigger_register(&kbd_led_triggers[i].trigger); if (error) pr_err("error %d while registering trigger %s\n", error, kbd_led_triggers[i].trigger.name); } } #else static int kbd_update_leds_helper(struct input_handle *handle, void *data) { unsigned int leds = *(unsigned int *)data; if (test_bit(EV_LED, handle->dev->evbit)) { input_inject_event(handle, EV_LED, LED_SCROLLL, !!(leds & BIT(0))); input_inject_event(handle, EV_LED, LED_NUML, !!(leds & BIT(1))); input_inject_event(handle, EV_LED, LED_CAPSL, !!(leds & BIT(2))); input_inject_event(handle, EV_SYN, SYN_REPORT, 0); } return 0; } static void kbd_propagate_led_state(unsigned int old_state, unsigned int new_state) { input_handler_for_each_handle(&kbd_handler, &new_state, kbd_update_leds_helper); } static void kbd_init_leds(void) { } #endif /* * The leds display either (i) the status of NumLock, CapsLock, ScrollLock, * or (ii) whatever pattern of lights people want to show using KDSETLED, * or (iii) specified bits of specified words in kernel memory. */ static unsigned char getledstate(void) { return ledstate & 0xff; } void setledstate(struct kbd_struct *kb, unsigned int led) { unsigned long flags; spin_lock_irqsave(&led_lock, flags); if (!(led & ~7)) { ledioctl = led; kb->ledmode = LED_SHOW_IOCTL; } else kb->ledmode = LED_SHOW_FLAGS; set_leds(); spin_unlock_irqrestore(&led_lock, flags); } static inline unsigned char getleds(void) { struct kbd_struct *kb = kbd_table + fg_console; if (kb->ledmode == LED_SHOW_IOCTL) return ledioctl; return kb->ledflagstate; } /** * vt_get_leds - helper for braille console * @console: console to read * @flag: flag we want to check * * Check the status of a keyboard led flag and report it back */ int vt_get_leds(unsigned int console, int flag) { struct kbd_struct *kb = &kbd_table[console]; int ret; unsigned long flags; spin_lock_irqsave(&led_lock, flags); ret = vc_kbd_led(kb, flag); spin_unlock_irqrestore(&led_lock, flags); return ret; } EXPORT_SYMBOL_GPL(vt_get_leds); /** * vt_set_led_state - set LED state of a console * @console: console to set * @leds: LED bits * * Set the LEDs on a console. This is a wrapper for the VT layer * so that we can keep kbd knowledge internal */ void vt_set_led_state(unsigned int console, int leds) { struct kbd_struct *kb = &kbd_table[console]; setledstate(kb, leds); } /** * vt_kbd_con_start - Keyboard side of console start * @console: console * * Handle console start. This is a wrapper for the VT layer * so that we can keep kbd knowledge internal * * FIXME: We eventually need to hold the kbd lock here to protect * the LED updating. We can't do it yet because fn_hold calls stop_tty * and start_tty under the kbd_event_lock, while normal tty paths * don't hold the lock. We probably need to split out an LED lock * but not during an -rc release! */ void vt_kbd_con_start(unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; spin_lock_irqsave(&led_lock, flags); clr_vc_kbd_led(kb, VC_SCROLLOCK); set_leds(); spin_unlock_irqrestore(&led_lock, flags); } /** * vt_kbd_con_stop - Keyboard side of console stop * @console: console * * Handle console stop. This is a wrapper for the VT layer * so that we can keep kbd knowledge internal */ void vt_kbd_con_stop(unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; spin_lock_irqsave(&led_lock, flags); set_vc_kbd_led(kb, VC_SCROLLOCK); set_leds(); spin_unlock_irqrestore(&led_lock, flags); } /* * This is the tasklet that updates LED state of LEDs using standard * keyboard triggers. The reason we use tasklet is that we need to * handle the scenario when keyboard handler is not registered yet * but we already getting updates from the VT to update led state. */ static void kbd_bh(struct tasklet_struct *unused) { unsigned int leds; unsigned long flags; spin_lock_irqsave(&led_lock, flags); leds = getleds(); leds |= (unsigned int)kbd->lockstate << 8; spin_unlock_irqrestore(&led_lock, flags); if (vt_switch) { ledstate = ~leds; vt_switch = false; } if (leds != ledstate) { kbd_propagate_led_state(ledstate, leds); ledstate = leds; } } #if defined(CONFIG_X86) || defined(CONFIG_ALPHA) ||\ defined(CONFIG_MIPS) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) ||\ defined(CONFIG_PARISC) || defined(CONFIG_SUPERH) ||\ (defined(CONFIG_ARM) && defined(CONFIG_KEYBOARD_ATKBD) && !defined(CONFIG_ARCH_RPC)) static inline bool kbd_is_hw_raw(const struct input_dev *dev) { if (!test_bit(EV_MSC, dev->evbit) || !test_bit(MSC_RAW, dev->mscbit)) return false; return dev->id.bustype == BUS_I8042 && dev->id.vendor == 0x0001 && dev->id.product == 0x0001; } static const unsigned short x86_keycodes[256] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84,118, 86, 87, 88,115,120,119,121,112,123, 92, 284,285,309, 0,312, 91,327,328,329,331,333,335,336,337,338,339, 367,288,302,304,350, 89,334,326,267,126,268,269,125,347,348,349, 360,261,262,263,268,376,100,101,321,316,373,286,289,102,351,355, 103,104,105,275,287,279,258,106,274,107,294,364,358,363,362,361, 291,108,381,281,290,272,292,305,280, 99,112,257,306,359,113,114, 264,117,271,374,379,265,266, 93, 94, 95, 85,259,375,260, 90,116, 377,109,111,277,278,282,283,295,296,297,299,300,301,293,303,307, 308,310,313,314,315,317,318,319,320,357,322,323,324,325,276,330, 332,340,365,342,343,344,345,346,356,270,341,368,369,370,371,372 }; #ifdef CONFIG_SPARC static int sparc_l1_a_state; extern void sun_do_break(void); #endif static int emulate_raw(struct vc_data *vc, unsigned int keycode, unsigned char up_flag) { int code; switch (keycode) { case KEY_PAUSE: put_queue(vc, 0xe1); put_queue(vc, 0x1d | up_flag); put_queue(vc, 0x45 | up_flag); break; case KEY_HANGEUL: if (!up_flag) put_queue(vc, 0xf2); break; case KEY_HANJA: if (!up_flag) put_queue(vc, 0xf1); break; case KEY_SYSRQ: /* * Real AT keyboards (that's what we're trying * to emulate here) emit 0xe0 0x2a 0xe0 0x37 when * pressing PrtSc/SysRq alone, but simply 0x54 * when pressing Alt+PrtSc/SysRq. */ if (test_bit(KEY_LEFTALT, key_down) || test_bit(KEY_RIGHTALT, key_down)) { put_queue(vc, 0x54 | up_flag); } else { put_queue(vc, 0xe0); put_queue(vc, 0x2a | up_flag); put_queue(vc, 0xe0); put_queue(vc, 0x37 | up_flag); } break; default: if (keycode > 255) return -1; code = x86_keycodes[keycode]; if (!code) return -1; if (code & 0x100) put_queue(vc, 0xe0); put_queue(vc, (code & 0x7f) | up_flag); break; } return 0; } #else static inline bool kbd_is_hw_raw(const struct input_dev *dev) { return false; } static int emulate_raw(struct vc_data *vc, unsigned int keycode, unsigned char up_flag) { if (keycode > 127) return -1; put_queue(vc, keycode | up_flag); return 0; } #endif static void kbd_rawcode(unsigned char data) { struct vc_data *vc = vc_cons[fg_console].d; kbd = &kbd_table[vc->vc_num]; if (kbd->kbdmode == VC_RAW) put_queue(vc, data); } static void kbd_keycode(unsigned int keycode, int down, bool hw_raw) { struct vc_data *vc = vc_cons[fg_console].d; unsigned short keysym, *key_map; unsigned char type; bool raw_mode; struct tty_struct *tty; int shift_final; struct keyboard_notifier_param param = { .vc = vc, .value = keycode, .down = down }; int rc; tty = vc->port.tty; if (tty && (!tty->driver_data)) { /* No driver data? Strange. Okay we fix it then. */ tty->driver_data = vc; } kbd = &kbd_table[vc->vc_num]; #ifdef CONFIG_SPARC if (keycode == KEY_STOP) sparc_l1_a_state = down; #endif rep = (down == 2); raw_mode = (kbd->kbdmode == VC_RAW); if (raw_mode && !hw_raw) if (emulate_raw(vc, keycode, !down << 7)) if (keycode < BTN_MISC && printk_ratelimit()) pr_warn("can't emulate rawmode for keycode %d\n", keycode); #ifdef CONFIG_SPARC if (keycode == KEY_A && sparc_l1_a_state) { sparc_l1_a_state = false; sun_do_break(); } #endif if (kbd->kbdmode == VC_MEDIUMRAW) { /* * This is extended medium raw mode, with keys above 127 * encoded as 0, high 7 bits, low 7 bits, with the 0 bearing * the 'up' flag if needed. 0 is reserved, so this shouldn't * interfere with anything else. The two bytes after 0 will * always have the up flag set not to interfere with older * applications. This allows for 16384 different keycodes, * which should be enough. */ if (keycode < 128) { put_queue(vc, keycode | (!down << 7)); } else { put_queue(vc, !down << 7); put_queue(vc, (keycode >> 7) | BIT(7)); put_queue(vc, keycode | BIT(7)); } raw_mode = true; } assign_bit(keycode, key_down, down); if (rep && (!vc_kbd_mode(kbd, VC_REPEAT) || (tty && !L_ECHO(tty) && tty_chars_in_buffer(tty)))) { /* * Don't repeat a key if the input buffers are not empty and the * characters get aren't echoed locally. This makes key repeat * usable with slow applications and under heavy loads. */ return; } param.shift = shift_final = (shift_state | kbd->slockstate) ^ kbd->lockstate; param.ledstate = kbd->ledflagstate; key_map = key_maps[shift_final]; rc = atomic_notifier_call_chain(&keyboard_notifier_list, KBD_KEYCODE, ¶m); if (rc == NOTIFY_STOP || !key_map) { atomic_notifier_call_chain(&keyboard_notifier_list, KBD_UNBOUND_KEYCODE, ¶m); do_compute_shiftstate(); kbd->slockstate = 0; return; } if (keycode < NR_KEYS) keysym = key_map[keycode]; else if (keycode >= KEY_BRL_DOT1 && keycode <= KEY_BRL_DOT8) keysym = U(K(KT_BRL, keycode - KEY_BRL_DOT1 + 1)); else return; type = KTYP(keysym); if (type < 0xf0) { param.value = keysym; rc = atomic_notifier_call_chain(&keyboard_notifier_list, KBD_UNICODE, ¶m); if (rc != NOTIFY_STOP) if (down && !raw_mode) k_unicode(vc, keysym, !down); return; } type -= 0xf0; if (type == KT_LETTER) { type = KT_LATIN; if (vc_kbd_led(kbd, VC_CAPSLOCK)) { key_map = key_maps[shift_final ^ BIT(KG_SHIFT)]; if (key_map) keysym = key_map[keycode]; } } param.value = keysym; rc = atomic_notifier_call_chain(&keyboard_notifier_list, KBD_KEYSYM, ¶m); if (rc == NOTIFY_STOP) return; if ((raw_mode || kbd->kbdmode == VC_OFF) && type != KT_SPEC && type != KT_SHIFT) return; (*k_handler[type])(vc, keysym & 0xff, !down); param.ledstate = kbd->ledflagstate; atomic_notifier_call_chain(&keyboard_notifier_list, KBD_POST_KEYSYM, ¶m); if (type != KT_SLOCK) kbd->slockstate = 0; } static void kbd_event(struct input_handle *handle, unsigned int event_type, unsigned int event_code, int value) { /* We are called with interrupts disabled, just take the lock */ spin_lock(&kbd_event_lock); if (event_type == EV_MSC && event_code == MSC_RAW && kbd_is_hw_raw(handle->dev)) kbd_rawcode(value); if (event_type == EV_KEY && event_code <= KEY_MAX) kbd_keycode(event_code, value, kbd_is_hw_raw(handle->dev)); spin_unlock(&kbd_event_lock); tasklet_schedule(&keyboard_tasklet); do_poke_blanked_console = 1; schedule_console_callback(); } static bool kbd_match(struct input_handler *handler, struct input_dev *dev) { if (test_bit(EV_SND, dev->evbit)) return true; if (test_bit(EV_KEY, dev->evbit)) { if (find_next_bit(dev->keybit, BTN_MISC, KEY_RESERVED) < BTN_MISC) return true; if (find_next_bit(dev->keybit, KEY_BRL_DOT10 + 1, KEY_BRL_DOT1) <= KEY_BRL_DOT10) return true; } return false; } /* * When a keyboard (or other input device) is found, the kbd_connect * function is called. The function then looks at the device, and if it * likes it, it can open it and get events from it. In this (kbd_connect) * function, we should decide which VT to bind that keyboard to initially. */ static int kbd_connect(struct input_handler *handler, struct input_dev *dev, const struct input_device_id *id) { struct input_handle *handle; int error; handle = kzalloc(sizeof(struct input_handle), GFP_KERNEL); if (!handle) return -ENOMEM; handle->dev = dev; handle->handler = handler; handle->name = "kbd"; error = input_register_handle(handle); if (error) goto err_free_handle; error = input_open_device(handle); if (error) goto err_unregister_handle; return 0; err_unregister_handle: input_unregister_handle(handle); err_free_handle: kfree(handle); return error; } static void kbd_disconnect(struct input_handle *handle) { input_close_device(handle); input_unregister_handle(handle); kfree(handle); } /* * Start keyboard handler on the new keyboard by refreshing LED state to * match the rest of the system. */ static void kbd_start(struct input_handle *handle) { tasklet_disable(&keyboard_tasklet); if (ledstate != -1U) kbd_update_leds_helper(handle, &ledstate); tasklet_enable(&keyboard_tasklet); } static const struct input_device_id kbd_ids[] = { { .flags = INPUT_DEVICE_ID_MATCH_EVBIT, .evbit = { BIT_MASK(EV_KEY) }, }, { .flags = INPUT_DEVICE_ID_MATCH_EVBIT, .evbit = { BIT_MASK(EV_SND) }, }, { }, /* Terminating entry */ }; MODULE_DEVICE_TABLE(input, kbd_ids); static struct input_handler kbd_handler = { .event = kbd_event, .match = kbd_match, .connect = kbd_connect, .disconnect = kbd_disconnect, .start = kbd_start, .name = "kbd", .id_table = kbd_ids, }; int __init kbd_init(void) { int i; int error; for (i = 0; i < MAX_NR_CONSOLES; i++) { kbd_table[i].ledflagstate = kbd_defleds(); kbd_table[i].default_ledflagstate = kbd_defleds(); kbd_table[i].ledmode = LED_SHOW_FLAGS; kbd_table[i].lockstate = KBD_DEFLOCK; kbd_table[i].slockstate = 0; kbd_table[i].modeflags = KBD_DEFMODE; kbd_table[i].kbdmode = default_utf8 ? VC_UNICODE : VC_XLATE; } kbd_init_leds(); error = input_register_handler(&kbd_handler); if (error) return error; tasklet_enable(&keyboard_tasklet); tasklet_schedule(&keyboard_tasklet); return 0; } /* Ioctl support code */ /** * vt_do_diacrit - diacritical table updates * @cmd: ioctl request * @udp: pointer to user data for ioctl * @perm: permissions check computed by caller * * Update the diacritical tables atomically and safely. Lock them * against simultaneous keypresses */ int vt_do_diacrit(unsigned int cmd, void __user *udp, int perm) { unsigned long flags; int asize; int ret = 0; switch (cmd) { case KDGKBDIACR: { struct kbdiacrs __user *a = udp; struct kbdiacr *dia; int i; dia = kmalloc_array(MAX_DIACR, sizeof(struct kbdiacr), GFP_KERNEL); if (!dia) return -ENOMEM; /* Lock the diacriticals table, make a copy and then copy it after we unlock */ spin_lock_irqsave(&kbd_event_lock, flags); asize = accent_table_size; for (i = 0; i < asize; i++) { dia[i].diacr = conv_uni_to_8bit( accent_table[i].diacr); dia[i].base = conv_uni_to_8bit( accent_table[i].base); dia[i].result = conv_uni_to_8bit( accent_table[i].result); } spin_unlock_irqrestore(&kbd_event_lock, flags); if (put_user(asize, &a->kb_cnt)) ret = -EFAULT; else if (copy_to_user(a->kbdiacr, dia, asize * sizeof(struct kbdiacr))) ret = -EFAULT; kfree(dia); return ret; } case KDGKBDIACRUC: { struct kbdiacrsuc __user *a = udp; void *buf; buf = kmalloc_array(MAX_DIACR, sizeof(struct kbdiacruc), GFP_KERNEL); if (buf == NULL) return -ENOMEM; /* Lock the diacriticals table, make a copy and then copy it after we unlock */ spin_lock_irqsave(&kbd_event_lock, flags); asize = accent_table_size; memcpy(buf, accent_table, asize * sizeof(struct kbdiacruc)); spin_unlock_irqrestore(&kbd_event_lock, flags); if (put_user(asize, &a->kb_cnt)) ret = -EFAULT; else if (copy_to_user(a->kbdiacruc, buf, asize*sizeof(struct kbdiacruc))) ret = -EFAULT; kfree(buf); return ret; } case KDSKBDIACR: { struct kbdiacrs __user *a = udp; struct kbdiacr *dia = NULL; unsigned int ct; int i; if (!perm) return -EPERM; if (get_user(ct, &a->kb_cnt)) return -EFAULT; if (ct >= MAX_DIACR) return -EINVAL; if (ct) { dia = memdup_array_user(a->kbdiacr, ct, sizeof(struct kbdiacr)); if (IS_ERR(dia)) return PTR_ERR(dia); } spin_lock_irqsave(&kbd_event_lock, flags); accent_table_size = ct; for (i = 0; i < ct; i++) { accent_table[i].diacr = conv_8bit_to_uni(dia[i].diacr); accent_table[i].base = conv_8bit_to_uni(dia[i].base); accent_table[i].result = conv_8bit_to_uni(dia[i].result); } spin_unlock_irqrestore(&kbd_event_lock, flags); kfree(dia); return 0; } case KDSKBDIACRUC: { struct kbdiacrsuc __user *a = udp; unsigned int ct; void *buf = NULL; if (!perm) return -EPERM; if (get_user(ct, &a->kb_cnt)) return -EFAULT; if (ct >= MAX_DIACR) return -EINVAL; if (ct) { buf = memdup_array_user(a->kbdiacruc, ct, sizeof(struct kbdiacruc)); if (IS_ERR(buf)) return PTR_ERR(buf); } spin_lock_irqsave(&kbd_event_lock, flags); if (ct) memcpy(accent_table, buf, ct * sizeof(struct kbdiacruc)); accent_table_size = ct; spin_unlock_irqrestore(&kbd_event_lock, flags); kfree(buf); return 0; } } return ret; } /** * vt_do_kdskbmode - set keyboard mode ioctl * @console: the console to use * @arg: the requested mode * * Update the keyboard mode bits while holding the correct locks. * Return 0 for success or an error code. */ int vt_do_kdskbmode(unsigned int console, unsigned int arg) { struct kbd_struct *kb = &kbd_table[console]; int ret = 0; unsigned long flags; spin_lock_irqsave(&kbd_event_lock, flags); switch(arg) { case K_RAW: kb->kbdmode = VC_RAW; break; case K_MEDIUMRAW: kb->kbdmode = VC_MEDIUMRAW; break; case K_XLATE: kb->kbdmode = VC_XLATE; do_compute_shiftstate(); break; case K_UNICODE: kb->kbdmode = VC_UNICODE; do_compute_shiftstate(); break; case K_OFF: kb->kbdmode = VC_OFF; break; default: ret = -EINVAL; } spin_unlock_irqrestore(&kbd_event_lock, flags); return ret; } /** * vt_do_kdskbmeta - set keyboard meta state * @console: the console to use * @arg: the requested meta state * * Update the keyboard meta bits while holding the correct locks. * Return 0 for success or an error code. */ int vt_do_kdskbmeta(unsigned int console, unsigned int arg) { struct kbd_struct *kb = &kbd_table[console]; int ret = 0; unsigned long flags; spin_lock_irqsave(&kbd_event_lock, flags); switch(arg) { case K_METABIT: clr_vc_kbd_mode(kb, VC_META); break; case K_ESCPREFIX: set_vc_kbd_mode(kb, VC_META); break; default: ret = -EINVAL; } spin_unlock_irqrestore(&kbd_event_lock, flags); return ret; } int vt_do_kbkeycode_ioctl(int cmd, struct kbkeycode __user *user_kbkc, int perm) { struct kbkeycode tmp; int kc = 0; if (copy_from_user(&tmp, user_kbkc, sizeof(struct kbkeycode))) return -EFAULT; switch (cmd) { case KDGETKEYCODE: kc = getkeycode(tmp.scancode); if (kc >= 0) kc = put_user(kc, &user_kbkc->keycode); break; case KDSETKEYCODE: if (!perm) return -EPERM; kc = setkeycode(tmp.scancode, tmp.keycode); break; } return kc; } static unsigned short vt_kdgkbent(unsigned char kbdmode, unsigned char idx, unsigned char map) { unsigned short *key_map, val; unsigned long flags; /* Ensure another thread doesn't free it under us */ spin_lock_irqsave(&kbd_event_lock, flags); key_map = key_maps[map]; if (key_map) { val = U(key_map[idx]); if (kbdmode != VC_UNICODE && KTYP(val) >= NR_TYPES) val = K_HOLE; } else val = idx ? K_HOLE : K_NOSUCHMAP; spin_unlock_irqrestore(&kbd_event_lock, flags); return val; } static int vt_kdskbent(unsigned char kbdmode, unsigned char idx, unsigned char map, unsigned short val) { unsigned long flags; unsigned short *key_map, *new_map, oldval; if (!idx && val == K_NOSUCHMAP) { spin_lock_irqsave(&kbd_event_lock, flags); /* deallocate map */ key_map = key_maps[map]; if (map && key_map) { key_maps[map] = NULL; if (key_map[0] == U(K_ALLOCATED)) { kfree(key_map); keymap_count--; } } spin_unlock_irqrestore(&kbd_event_lock, flags); return 0; } if (KTYP(val) < NR_TYPES) { if (KVAL(val) > max_vals[KTYP(val)]) return -EINVAL; } else if (kbdmode != VC_UNICODE) return -EINVAL; /* ++Geert: non-PC keyboards may generate keycode zero */ #if !defined(__mc68000__) && !defined(__powerpc__) /* assignment to entry 0 only tests validity of args */ if (!idx) return 0; #endif new_map = kmalloc(sizeof(plain_map), GFP_KERNEL); if (!new_map) return -ENOMEM; spin_lock_irqsave(&kbd_event_lock, flags); key_map = key_maps[map]; if (key_map == NULL) { int j; if (keymap_count >= MAX_NR_OF_USER_KEYMAPS && !capable(CAP_SYS_RESOURCE)) { spin_unlock_irqrestore(&kbd_event_lock, flags); kfree(new_map); return -EPERM; } key_maps[map] = new_map; key_map = new_map; key_map[0] = U(K_ALLOCATED); for (j = 1; j < NR_KEYS; j++) key_map[j] = U(K_HOLE); keymap_count++; } else kfree(new_map); oldval = U(key_map[idx]); if (val == oldval) goto out; /* Attention Key */ if ((oldval == K_SAK || val == K_SAK) && !capable(CAP_SYS_ADMIN)) { spin_unlock_irqrestore(&kbd_event_lock, flags); return -EPERM; } key_map[idx] = U(val); if (!map && (KTYP(oldval) == KT_SHIFT || KTYP(val) == KT_SHIFT)) do_compute_shiftstate(); out: spin_unlock_irqrestore(&kbd_event_lock, flags); return 0; } int vt_do_kdsk_ioctl(int cmd, struct kbentry __user *user_kbe, int perm, unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; struct kbentry kbe; if (copy_from_user(&kbe, user_kbe, sizeof(struct kbentry))) return -EFAULT; switch (cmd) { case KDGKBENT: return put_user(vt_kdgkbent(kb->kbdmode, kbe.kb_index, kbe.kb_table), &user_kbe->kb_value); case KDSKBENT: if (!perm || !capable(CAP_SYS_TTY_CONFIG)) return -EPERM; return vt_kdskbent(kb->kbdmode, kbe.kb_index, kbe.kb_table, kbe.kb_value); } return 0; } static char *vt_kdskbsent(char *kbs, unsigned char cur) { static DECLARE_BITMAP(is_kmalloc, MAX_NR_FUNC); char *cur_f = func_table[cur]; if (cur_f && strlen(cur_f) >= strlen(kbs)) { strcpy(cur_f, kbs); return kbs; } func_table[cur] = kbs; return __test_and_set_bit(cur, is_kmalloc) ? cur_f : NULL; } int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm) { unsigned char kb_func; unsigned long flags; char *kbs; int ret; if (get_user(kb_func, &user_kdgkb->kb_func)) return -EFAULT; kb_func = array_index_nospec(kb_func, MAX_NR_FUNC); switch (cmd) { case KDGKBSENT: { /* size should have been a struct member */ ssize_t len = sizeof(user_kdgkb->kb_string); kbs = kmalloc(len, GFP_KERNEL); if (!kbs) return -ENOMEM; spin_lock_irqsave(&func_buf_lock, flags); len = strscpy(kbs, func_table[kb_func] ? : "", len); spin_unlock_irqrestore(&func_buf_lock, flags); if (len < 0) { ret = -ENOSPC; break; } ret = copy_to_user(user_kdgkb->kb_string, kbs, len + 1) ? -EFAULT : 0; break; } case KDSKBSENT: if (!perm || !capable(CAP_SYS_TTY_CONFIG)) return -EPERM; kbs = strndup_user(user_kdgkb->kb_string, sizeof(user_kdgkb->kb_string)); if (IS_ERR(kbs)) return PTR_ERR(kbs); spin_lock_irqsave(&func_buf_lock, flags); kbs = vt_kdskbsent(kbs, kb_func); spin_unlock_irqrestore(&func_buf_lock, flags); ret = 0; break; } kfree(kbs); return ret; } int vt_do_kdskled(unsigned int console, int cmd, unsigned long arg, int perm) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; unsigned char ucval; switch(cmd) { /* the ioctls below read/set the flags usually shown in the leds */ /* don't use them - they will go away without warning */ case KDGKBLED: spin_lock_irqsave(&kbd_event_lock, flags); ucval = kb->ledflagstate | (kb->default_ledflagstate << 4); spin_unlock_irqrestore(&kbd_event_lock, flags); return put_user(ucval, (char __user *)arg); case KDSKBLED: if (!perm) return -EPERM; if (arg & ~0x77) return -EINVAL; spin_lock_irqsave(&led_lock, flags); kb->ledflagstate = (arg & 7); kb->default_ledflagstate = ((arg >> 4) & 7); set_leds(); spin_unlock_irqrestore(&led_lock, flags); return 0; /* the ioctls below only set the lights, not the functions */ /* for those, see KDGKBLED and KDSKBLED above */ case KDGETLED: ucval = getledstate(); return put_user(ucval, (char __user *)arg); case KDSETLED: if (!perm) return -EPERM; setledstate(kb, arg); return 0; } return -ENOIOCTLCMD; } int vt_do_kdgkbmode(unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; /* This is a spot read so needs no locking */ switch (kb->kbdmode) { case VC_RAW: return K_RAW; case VC_MEDIUMRAW: return K_MEDIUMRAW; case VC_UNICODE: return K_UNICODE; case VC_OFF: return K_OFF; default: return K_XLATE; } } /** * vt_do_kdgkbmeta - report meta status * @console: console to report * * Report the meta flag status of this console */ int vt_do_kdgkbmeta(unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; /* Again a spot read so no locking */ return vc_kbd_mode(kb, VC_META) ? K_ESCPREFIX : K_METABIT; } /** * vt_reset_unicode - reset the unicode status * @console: console being reset * * Restore the unicode console state to its default */ void vt_reset_unicode(unsigned int console) { unsigned long flags; spin_lock_irqsave(&kbd_event_lock, flags); kbd_table[console].kbdmode = default_utf8 ? VC_UNICODE : VC_XLATE; spin_unlock_irqrestore(&kbd_event_lock, flags); } /** * vt_get_shift_state - shift bit state * * Report the shift bits from the keyboard state. We have to export * this to support some oddities in the vt layer. */ int vt_get_shift_state(void) { /* Don't lock as this is a transient report */ return shift_state; } /** * vt_reset_keyboard - reset keyboard state * @console: console to reset * * Reset the keyboard bits for a console as part of a general console * reset event */ void vt_reset_keyboard(unsigned int console) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; spin_lock_irqsave(&kbd_event_lock, flags); set_vc_kbd_mode(kb, VC_REPEAT); clr_vc_kbd_mode(kb, VC_CKMODE); clr_vc_kbd_mode(kb, VC_APPLIC); clr_vc_kbd_mode(kb, VC_CRLF); kb->lockstate = 0; kb->slockstate = 0; spin_lock(&led_lock); kb->ledmode = LED_SHOW_FLAGS; kb->ledflagstate = kb->default_ledflagstate; spin_unlock(&led_lock); /* do not do set_leds here because this causes an endless tasklet loop when the keyboard hasn't been initialized yet */ spin_unlock_irqrestore(&kbd_event_lock, flags); } /** * vt_get_kbd_mode_bit - read keyboard status bits * @console: console to read from * @bit: mode bit to read * * Report back a vt mode bit. We do this without locking so the * caller must be sure that there are no synchronization needs */ int vt_get_kbd_mode_bit(unsigned int console, int bit) { struct kbd_struct *kb = &kbd_table[console]; return vc_kbd_mode(kb, bit); } /** * vt_set_kbd_mode_bit - read keyboard status bits * @console: console to read from * @bit: mode bit to read * * Set a vt mode bit. We do this without locking so the * caller must be sure that there are no synchronization needs */ void vt_set_kbd_mode_bit(unsigned int console, int bit) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; spin_lock_irqsave(&kbd_event_lock, flags); set_vc_kbd_mode(kb, bit); spin_unlock_irqrestore(&kbd_event_lock, flags); } /** * vt_clr_kbd_mode_bit - read keyboard status bits * @console: console to read from * @bit: mode bit to read * * Report back a vt mode bit. We do this without locking so the * caller must be sure that there are no synchronization needs */ void vt_clr_kbd_mode_bit(unsigned int console, int bit) { struct kbd_struct *kb = &kbd_table[console]; unsigned long flags; spin_lock_irqsave(&kbd_event_lock, flags); clr_vc_kbd_mode(kb, bit); spin_unlock_irqrestore(&kbd_event_lock, flags); } |
| 2 3 3 3 3 3 4 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 | // SPDX-License-Identifier: GPL-2.0+ /* * inode.c -- user mode filesystem api for usb gadget controllers * * Copyright (C) 2003-2004 David Brownell * Copyright (C) 2003 Agilent Technologies */ /* #define VERBOSE_DEBUG */ #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/pagemap.h> #include <linux/uts.h> #include <linux/wait.h> #include <linux/compiler.h> #include <linux/uaccess.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/kthread.h> #include <linux/aio.h> #include <linux/uio.h> #include <linux/refcount.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/moduleparam.h> #include <linux/usb/gadgetfs.h> #include <linux/usb/gadget.h> #include <linux/usb/composite.h> /* for USB_GADGET_DELAYED_STATUS */ /* Undef helpers from linux/usb/composite.h as gadgetfs redefines them */ #undef DBG #undef ERROR #undef INFO /* * The gadgetfs API maps each endpoint to a file descriptor so that you * can use standard synchronous read/write calls for I/O. There's some * O_NONBLOCK and O_ASYNC/FASYNC style i/o support. Example usermode * drivers show how this works in practice. You can also use AIO to * eliminate I/O gaps between requests, to help when streaming data. * * Key parts that must be USB-specific are protocols defining how the * read/write operations relate to the hardware state machines. There * are two types of files. One type is for the device, implementing ep0. * The other type is for each IN or OUT endpoint. In both cases, the * user mode driver must configure the hardware before using it. * * - First, dev_config() is called when /dev/gadget/$CHIP is configured * (by writing configuration and device descriptors). Afterwards it * may serve as a source of device events, used to handle all control * requests other than basic enumeration. * * - Then, after a SET_CONFIGURATION control request, ep_config() is * called when each /dev/gadget/ep* file is configured (by writing * endpoint descriptors). Afterwards these files are used to write() * IN data or to read() OUT data. To halt the endpoint, a "wrong * direction" request is issued (like reading an IN endpoint). * * Unlike "usbfs" the only ioctl()s are for things that are rare, and maybe * not possible on all hardware. For example, precise fault handling with * respect to data left in endpoint fifos after aborted operations; or * selective clearing of endpoint halts, to implement SET_INTERFACE. */ #define DRIVER_DESC "USB Gadget filesystem" #define DRIVER_VERSION "24 Aug 2004" static const char driver_desc [] = DRIVER_DESC; static const char shortname [] = "gadgetfs"; MODULE_DESCRIPTION (DRIVER_DESC); MODULE_AUTHOR ("David Brownell"); MODULE_LICENSE ("GPL"); static int ep_open(struct inode *, struct file *); /*----------------------------------------------------------------------*/ #define GADGETFS_MAGIC 0xaee71ee7 /* /dev/gadget/$CHIP represents ep0 and the whole device */ enum ep0_state { /* DISABLED is the initial state. */ STATE_DEV_DISABLED = 0, /* Only one open() of /dev/gadget/$CHIP; only one file tracks * ep0/device i/o modes and binding to the controller. Driver * must always write descriptors to initialize the device, then * the device becomes UNCONNECTED until enumeration. */ STATE_DEV_OPENED, /* From then on, ep0 fd is in either of two basic modes: * - (UN)CONNECTED: read usb_gadgetfs_event(s) from it * - SETUP: read/write will transfer control data and succeed; * or if "wrong direction", performs protocol stall */ STATE_DEV_UNCONNECTED, STATE_DEV_CONNECTED, STATE_DEV_SETUP, /* UNBOUND means the driver closed ep0, so the device won't be * accessible again (DEV_DISABLED) until all fds are closed. */ STATE_DEV_UNBOUND, }; /* enough for the whole queue: most events invalidate others */ #define N_EVENT 5 #define RBUF_SIZE 256 struct dev_data { spinlock_t lock; refcount_t count; int udc_usage; enum ep0_state state; /* P: lock */ struct usb_gadgetfs_event event [N_EVENT]; unsigned ev_next; struct fasync_struct *fasync; u8 current_config; /* drivers reading ep0 MUST handle control requests (SETUP) * reported that way; else the host will time out. */ unsigned usermode_setup : 1, setup_in : 1, setup_can_stall : 1, setup_out_ready : 1, setup_out_error : 1, setup_abort : 1, gadget_registered : 1; unsigned setup_wLength; /* the rest is basically write-once */ struct usb_config_descriptor *config, *hs_config; struct usb_device_descriptor *dev; struct usb_request *req; struct usb_gadget *gadget; struct list_head epfiles; void *buf; wait_queue_head_t wait; struct super_block *sb; struct dentry *dentry; /* except this scratch i/o buffer for ep0 */ u8 rbuf[RBUF_SIZE]; }; static inline void get_dev (struct dev_data *data) { refcount_inc (&data->count); } static void put_dev (struct dev_data *data) { if (likely (!refcount_dec_and_test (&data->count))) return; /* needs no more cleanup */ BUG_ON (waitqueue_active (&data->wait)); kfree (data); } static struct dev_data *dev_new (void) { struct dev_data *dev; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return NULL; dev->state = STATE_DEV_DISABLED; refcount_set (&dev->count, 1); spin_lock_init (&dev->lock); INIT_LIST_HEAD (&dev->epfiles); init_waitqueue_head (&dev->wait); return dev; } /*----------------------------------------------------------------------*/ /* other /dev/gadget/$ENDPOINT files represent endpoints */ enum ep_state { STATE_EP_DISABLED = 0, STATE_EP_READY, STATE_EP_ENABLED, STATE_EP_UNBOUND, }; struct ep_data { struct mutex lock; enum ep_state state; refcount_t count; struct dev_data *dev; /* must hold dev->lock before accessing ep or req */ struct usb_ep *ep; struct usb_request *req; ssize_t status; char name [16]; struct usb_endpoint_descriptor desc, hs_desc; struct list_head epfiles; wait_queue_head_t wait; struct dentry *dentry; }; static inline void get_ep (struct ep_data *data) { refcount_inc (&data->count); } static void put_ep (struct ep_data *data) { if (likely (!refcount_dec_and_test (&data->count))) return; put_dev (data->dev); /* needs no more cleanup */ BUG_ON (!list_empty (&data->epfiles)); BUG_ON (waitqueue_active (&data->wait)); kfree (data); } /*----------------------------------------------------------------------*/ /* most "how to use the hardware" policy choices are in userspace: * mapping endpoint roles (which the driver needs) to the capabilities * which the usb controller has. most of those capabilities are exposed * implicitly, starting with the driver name and then endpoint names. */ static const char *CHIP; static DEFINE_MUTEX(sb_mutex); /* Serialize superblock operations */ /*----------------------------------------------------------------------*/ /* NOTE: don't use dev_printk calls before binding to the gadget * at the end of ep0 configuration, or after unbind. */ /* too wordy: dev_printk(level , &(d)->gadget->dev , fmt , ## args) */ #define xprintk(d,level,fmt,args...) \ printk(level "%s: " fmt , shortname , ## args) #ifdef DEBUG #define DBG(dev,fmt,args...) \ xprintk(dev , KERN_DEBUG , fmt , ## args) #else #define DBG(dev,fmt,args...) \ do { } while (0) #endif /* DEBUG */ #ifdef VERBOSE_DEBUG #define VDEBUG DBG #else #define VDEBUG(dev,fmt,args...) \ do { } while (0) #endif /* DEBUG */ #define ERROR(dev,fmt,args...) \ xprintk(dev , KERN_ERR , fmt , ## args) #define INFO(dev,fmt,args...) \ xprintk(dev , KERN_INFO , fmt , ## args) /*----------------------------------------------------------------------*/ /* SYNCHRONOUS ENDPOINT OPERATIONS (bulk/intr/iso) * * After opening, configure non-control endpoints. Then use normal * stream read() and write() requests; and maybe ioctl() to get more * precise FIFO status when recovering from cancellation. */ static void epio_complete (struct usb_ep *ep, struct usb_request *req) { struct ep_data *epdata = ep->driver_data; if (!req->context) return; if (req->status) epdata->status = req->status; else epdata->status = req->actual; complete ((struct completion *)req->context); } /* tasklock endpoint, returning when it's connected. * still need dev->lock to use epdata->ep. */ static int get_ready_ep (unsigned f_flags, struct ep_data *epdata, bool is_write) { int val; if (f_flags & O_NONBLOCK) { if (!mutex_trylock(&epdata->lock)) goto nonblock; if (epdata->state != STATE_EP_ENABLED && (!is_write || epdata->state != STATE_EP_READY)) { mutex_unlock(&epdata->lock); nonblock: val = -EAGAIN; } else val = 0; return val; } val = mutex_lock_interruptible(&epdata->lock); if (val < 0) return val; switch (epdata->state) { case STATE_EP_ENABLED: return 0; case STATE_EP_READY: /* not configured yet */ if (is_write) return 0; fallthrough; case STATE_EP_UNBOUND: /* clean disconnect */ break; // case STATE_EP_DISABLED: /* "can't happen" */ default: /* error! */ pr_debug ("%s: ep %p not available, state %d\n", shortname, epdata, epdata->state); } mutex_unlock(&epdata->lock); return -ENODEV; } static ssize_t ep_io (struct ep_data *epdata, void *buf, unsigned len) { DECLARE_COMPLETION_ONSTACK (done); int value; spin_lock_irq (&epdata->dev->lock); if (likely (epdata->ep != NULL)) { struct usb_request *req = epdata->req; req->context = &done; req->complete = epio_complete; req->buf = buf; req->length = len; value = usb_ep_queue (epdata->ep, req, GFP_ATOMIC); } else value = -ENODEV; spin_unlock_irq (&epdata->dev->lock); if (likely (value == 0)) { value = wait_for_completion_interruptible(&done); if (value != 0) { spin_lock_irq (&epdata->dev->lock); if (likely (epdata->ep != NULL)) { DBG (epdata->dev, "%s i/o interrupted\n", epdata->name); usb_ep_dequeue (epdata->ep, epdata->req); spin_unlock_irq (&epdata->dev->lock); wait_for_completion(&done); if (epdata->status == -ECONNRESET) epdata->status = -EINTR; } else { spin_unlock_irq (&epdata->dev->lock); DBG (epdata->dev, "endpoint gone\n"); wait_for_completion(&done); epdata->status = -ENODEV; } } return epdata->status; } return value; } static int ep_release (struct inode *inode, struct file *fd) { struct ep_data *data = fd->private_data; int value; value = mutex_lock_interruptible(&data->lock); if (value < 0) return value; /* clean up if this can be reopened */ if (data->state != STATE_EP_UNBOUND) { data->state = STATE_EP_DISABLED; data->desc.bDescriptorType = 0; data->hs_desc.bDescriptorType = 0; usb_ep_disable(data->ep); } mutex_unlock(&data->lock); put_ep (data); return 0; } static long ep_ioctl(struct file *fd, unsigned code, unsigned long value) { struct ep_data *data = fd->private_data; int status; if ((status = get_ready_ep (fd->f_flags, data, false)) < 0) return status; spin_lock_irq (&data->dev->lock); if (likely (data->ep != NULL)) { switch (code) { case GADGETFS_FIFO_STATUS: status = usb_ep_fifo_status (data->ep); break; case GADGETFS_FIFO_FLUSH: usb_ep_fifo_flush (data->ep); break; case GADGETFS_CLEAR_HALT: status = usb_ep_clear_halt (data->ep); break; default: status = -ENOTTY; } } else status = -ENODEV; spin_unlock_irq (&data->dev->lock); mutex_unlock(&data->lock); return status; } /*----------------------------------------------------------------------*/ /* ASYNCHRONOUS ENDPOINT I/O OPERATIONS (bulk/intr/iso) */ struct kiocb_priv { struct usb_request *req; struct ep_data *epdata; struct kiocb *iocb; struct mm_struct *mm; struct work_struct work; void *buf; struct iov_iter to; const void *to_free; unsigned actual; }; static int ep_aio_cancel(struct kiocb *iocb) { struct kiocb_priv *priv = iocb->private; struct ep_data *epdata; int value; local_irq_disable(); epdata = priv->epdata; // spin_lock(&epdata->dev->lock); if (likely(epdata && epdata->ep && priv->req)) value = usb_ep_dequeue (epdata->ep, priv->req); else value = -EINVAL; // spin_unlock(&epdata->dev->lock); local_irq_enable(); return value; } static void ep_user_copy_worker(struct work_struct *work) { struct kiocb_priv *priv = container_of(work, struct kiocb_priv, work); struct mm_struct *mm = priv->mm; struct kiocb *iocb = priv->iocb; size_t ret; kthread_use_mm(mm); ret = copy_to_iter(priv->buf, priv->actual, &priv->to); kthread_unuse_mm(mm); if (!ret) ret = -EFAULT; /* completing the iocb can drop the ctx and mm, don't touch mm after */ iocb->ki_complete(iocb, ret); kfree(priv->buf); kfree(priv->to_free); kfree(priv); } static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) { struct kiocb *iocb = req->context; struct kiocb_priv *priv = iocb->private; struct ep_data *epdata = priv->epdata; /* lock against disconnect (and ideally, cancel) */ spin_lock(&epdata->dev->lock); priv->req = NULL; priv->epdata = NULL; /* if this was a write or a read returning no data then we * don't need to copy anything to userspace, so we can * complete the aio request immediately. */ if (priv->to_free == NULL || unlikely(req->actual == 0)) { kfree(req->buf); kfree(priv->to_free); kfree(priv); iocb->private = NULL; iocb->ki_complete(iocb, req->actual ? req->actual : (long)req->status); } else { /* ep_copy_to_user() won't report both; we hide some faults */ if (unlikely(0 != req->status)) DBG(epdata->dev, "%s fault %d len %d\n", ep->name, req->status, req->actual); priv->buf = req->buf; priv->actual = req->actual; INIT_WORK(&priv->work, ep_user_copy_worker); schedule_work(&priv->work); } usb_ep_free_request(ep, req); spin_unlock(&epdata->dev->lock); put_ep(epdata); } static ssize_t ep_aio(struct kiocb *iocb, struct kiocb_priv *priv, struct ep_data *epdata, char *buf, size_t len) { struct usb_request *req; ssize_t value; iocb->private = priv; priv->iocb = iocb; kiocb_set_cancel_fn(iocb, ep_aio_cancel); get_ep(epdata); priv->epdata = epdata; priv->actual = 0; priv->mm = current->mm; /* mm teardown waits for iocbs in exit_aio() */ /* each kiocb is coupled to one usb_request, but we can't * allocate or submit those if the host disconnected. */ spin_lock_irq(&epdata->dev->lock); value = -ENODEV; if (unlikely(epdata->ep == NULL)) goto fail; req = usb_ep_alloc_request(epdata->ep, GFP_ATOMIC); value = -ENOMEM; if (unlikely(!req)) goto fail; priv->req = req; req->buf = buf; req->length = len; req->complete = ep_aio_complete; req->context = iocb; value = usb_ep_queue(epdata->ep, req, GFP_ATOMIC); if (unlikely(0 != value)) { usb_ep_free_request(epdata->ep, req); goto fail; } spin_unlock_irq(&epdata->dev->lock); return -EIOCBQUEUED; fail: spin_unlock_irq(&epdata->dev->lock); kfree(priv->to_free); kfree(priv); put_ep(epdata); return value; } static ssize_t ep_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct ep_data *epdata = file->private_data; size_t len = iov_iter_count(to); ssize_t value; char *buf; if ((value = get_ready_ep(file->f_flags, epdata, false)) < 0) return value; /* halt any endpoint by doing a "wrong direction" i/o call */ if (usb_endpoint_dir_in(&epdata->desc)) { if (usb_endpoint_xfer_isoc(&epdata->desc) || !is_sync_kiocb(iocb)) { mutex_unlock(&epdata->lock); return -EINVAL; } DBG (epdata->dev, "%s halt\n", epdata->name); spin_lock_irq(&epdata->dev->lock); if (likely(epdata->ep != NULL)) usb_ep_set_halt(epdata->ep); spin_unlock_irq(&epdata->dev->lock); mutex_unlock(&epdata->lock); return -EBADMSG; } buf = kmalloc(len, GFP_KERNEL); if (unlikely(!buf)) { mutex_unlock(&epdata->lock); return -ENOMEM; } if (is_sync_kiocb(iocb)) { value = ep_io(epdata, buf, len); if (value >= 0 && (copy_to_iter(buf, value, to) != value)) value = -EFAULT; } else { struct kiocb_priv *priv = kzalloc(sizeof *priv, GFP_KERNEL); value = -ENOMEM; if (!priv) goto fail; priv->to_free = dup_iter(&priv->to, to, GFP_KERNEL); if (!iter_is_ubuf(&priv->to) && !priv->to_free) { kfree(priv); goto fail; } value = ep_aio(iocb, priv, epdata, buf, len); if (value == -EIOCBQUEUED) buf = NULL; } fail: kfree(buf); mutex_unlock(&epdata->lock); return value; } static ssize_t ep_config(struct ep_data *, const char *, size_t); static ssize_t ep_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct ep_data *epdata = file->private_data; size_t len = iov_iter_count(from); bool configured; ssize_t value; char *buf; if ((value = get_ready_ep(file->f_flags, epdata, true)) < 0) return value; configured = epdata->state == STATE_EP_ENABLED; /* halt any endpoint by doing a "wrong direction" i/o call */ if (configured && !usb_endpoint_dir_in(&epdata->desc)) { if (usb_endpoint_xfer_isoc(&epdata->desc) || !is_sync_kiocb(iocb)) { mutex_unlock(&epdata->lock); return -EINVAL; } DBG (epdata->dev, "%s halt\n", epdata->name); spin_lock_irq(&epdata->dev->lock); if (likely(epdata->ep != NULL)) usb_ep_set_halt(epdata->ep); spin_unlock_irq(&epdata->dev->lock); mutex_unlock(&epdata->lock); return -EBADMSG; } buf = kmalloc(len, GFP_KERNEL); if (unlikely(!buf)) { mutex_unlock(&epdata->lock); return -ENOMEM; } if (unlikely(!copy_from_iter_full(buf, len, from))) { value = -EFAULT; goto out; } if (unlikely(!configured)) { value = ep_config(epdata, buf, len); } else if (is_sync_kiocb(iocb)) { value = ep_io(epdata, buf, len); } else { struct kiocb_priv *priv = kzalloc(sizeof *priv, GFP_KERNEL); value = -ENOMEM; if (priv) { value = ep_aio(iocb, priv, epdata, buf, len); if (value == -EIOCBQUEUED) buf = NULL; } } out: kfree(buf); mutex_unlock(&epdata->lock); return value; } /*----------------------------------------------------------------------*/ /* used after endpoint configuration */ static const struct file_operations ep_io_operations = { .owner = THIS_MODULE, .open = ep_open, .release = ep_release, .llseek = no_llseek, .unlocked_ioctl = ep_ioctl, .read_iter = ep_read_iter, .write_iter = ep_write_iter, }; /* ENDPOINT INITIALIZATION * * fd = open ("/dev/gadget/$ENDPOINT", O_RDWR) * status = write (fd, descriptors, sizeof descriptors) * * That write establishes the endpoint configuration, configuring * the controller to process bulk, interrupt, or isochronous transfers * at the right maxpacket size, and so on. * * The descriptors are message type 1, identified by a host order u32 * at the beginning of what's written. Descriptor order is: full/low * speed descriptor, then optional high speed descriptor. */ static ssize_t ep_config (struct ep_data *data, const char *buf, size_t len) { struct usb_ep *ep; u32 tag; int value, length = len; if (data->state != STATE_EP_READY) { value = -EL2HLT; goto fail; } value = len; if (len < USB_DT_ENDPOINT_SIZE + 4) goto fail0; /* we might need to change message format someday */ memcpy(&tag, buf, 4); if (tag != 1) { DBG(data->dev, "config %s, bad tag %d\n", data->name, tag); goto fail0; } buf += 4; len -= 4; /* NOTE: audio endpoint extensions not accepted here; * just don't include the extra bytes. */ /* full/low speed descriptor, then high speed */ memcpy(&data->desc, buf, USB_DT_ENDPOINT_SIZE); if (data->desc.bLength != USB_DT_ENDPOINT_SIZE || data->desc.bDescriptorType != USB_DT_ENDPOINT) goto fail0; if (len != USB_DT_ENDPOINT_SIZE) { if (len != 2 * USB_DT_ENDPOINT_SIZE) goto fail0; memcpy(&data->hs_desc, buf + USB_DT_ENDPOINT_SIZE, USB_DT_ENDPOINT_SIZE); if (data->hs_desc.bLength != USB_DT_ENDPOINT_SIZE || data->hs_desc.bDescriptorType != USB_DT_ENDPOINT) { DBG(data->dev, "config %s, bad hs length or type\n", data->name); goto fail0; } } spin_lock_irq (&data->dev->lock); if (data->dev->state == STATE_DEV_UNBOUND) { value = -ENOENT; goto gone; } else { ep = data->ep; if (ep == NULL) { value = -ENODEV; goto gone; } } switch (data->dev->gadget->speed) { case USB_SPEED_LOW: case USB_SPEED_FULL: ep->desc = &data->desc; break; case USB_SPEED_HIGH: /* fails if caller didn't provide that descriptor... */ ep->desc = &data->hs_desc; break; default: DBG(data->dev, "unconnected, %s init abandoned\n", data->name); value = -EINVAL; goto gone; } value = usb_ep_enable(ep); if (value == 0) { data->state = STATE_EP_ENABLED; value = length; } gone: spin_unlock_irq (&data->dev->lock); if (value < 0) { fail: data->desc.bDescriptorType = 0; data->hs_desc.bDescriptorType = 0; } return value; fail0: value = -EINVAL; goto fail; } static int ep_open (struct inode *inode, struct file *fd) { struct ep_data *data = inode->i_private; int value = -EBUSY; if (mutex_lock_interruptible(&data->lock) != 0) return -EINTR; spin_lock_irq (&data->dev->lock); if (data->dev->state == STATE_DEV_UNBOUND) value = -ENOENT; else if (data->state == STATE_EP_DISABLED) { value = 0; data->state = STATE_EP_READY; get_ep (data); fd->private_data = data; VDEBUG (data->dev, "%s ready\n", data->name); } else DBG (data->dev, "%s state %d\n", data->name, data->state); spin_unlock_irq (&data->dev->lock); mutex_unlock(&data->lock); return value; } /*----------------------------------------------------------------------*/ /* EP0 IMPLEMENTATION can be partly in userspace. * * Drivers that use this facility receive various events, including * control requests the kernel doesn't handle. Drivers that don't * use this facility may be too simple-minded for real applications. */ static inline void ep0_readable (struct dev_data *dev) { wake_up (&dev->wait); kill_fasync (&dev->fasync, SIGIO, POLL_IN); } static void clean_req (struct usb_ep *ep, struct usb_request *req) { struct dev_data *dev = ep->driver_data; if (req->buf != dev->rbuf) { kfree(req->buf); req->buf = dev->rbuf; } req->complete = epio_complete; dev->setup_out_ready = 0; } static void ep0_complete (struct usb_ep *ep, struct usb_request *req) { struct dev_data *dev = ep->driver_data; unsigned long flags; int free = 1; /* for control OUT, data must still get to userspace */ spin_lock_irqsave(&dev->lock, flags); if (!dev->setup_in) { dev->setup_out_error = (req->status != 0); if (!dev->setup_out_error) free = 0; dev->setup_out_ready = 1; ep0_readable (dev); } /* clean up as appropriate */ if (free && req->buf != &dev->rbuf) clean_req (ep, req); req->complete = epio_complete; spin_unlock_irqrestore(&dev->lock, flags); } static int setup_req (struct usb_ep *ep, struct usb_request *req, u16 len) { struct dev_data *dev = ep->driver_data; if (dev->setup_out_ready) { DBG (dev, "ep0 request busy!\n"); return -EBUSY; } if (len > sizeof (dev->rbuf)) req->buf = kmalloc(len, GFP_ATOMIC); if (req->buf == NULL) { req->buf = dev->rbuf; return -ENOMEM; } req->complete = ep0_complete; req->length = len; req->zero = 0; return 0; } static ssize_t ep0_read (struct file *fd, char __user *buf, size_t len, loff_t *ptr) { struct dev_data *dev = fd->private_data; ssize_t retval; enum ep0_state state; spin_lock_irq (&dev->lock); if (dev->state <= STATE_DEV_OPENED) { retval = -EINVAL; goto done; } /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; retval = -EIDRM; goto done; } /* control DATA stage */ if ((state = dev->state) == STATE_DEV_SETUP) { if (dev->setup_in) { /* stall IN */ VDEBUG(dev, "ep0in stall\n"); (void) usb_ep_set_halt (dev->gadget->ep0); retval = -EL2HLT; dev->state = STATE_DEV_CONNECTED; } else if (len == 0) { /* ack SET_CONFIGURATION etc */ struct usb_ep *ep = dev->gadget->ep0; struct usb_request *req = dev->req; if ((retval = setup_req (ep, req, 0)) == 0) { ++dev->udc_usage; spin_unlock_irq (&dev->lock); retval = usb_ep_queue (ep, req, GFP_KERNEL); spin_lock_irq (&dev->lock); --dev->udc_usage; } dev->state = STATE_DEV_CONNECTED; /* assume that was SET_CONFIGURATION */ if (dev->current_config) { unsigned power; if (gadget_is_dualspeed(dev->gadget) && (dev->gadget->speed == USB_SPEED_HIGH)) power = dev->hs_config->bMaxPower; else power = dev->config->bMaxPower; usb_gadget_vbus_draw(dev->gadget, 2 * power); } } else { /* collect OUT data */ if ((fd->f_flags & O_NONBLOCK) != 0 && !dev->setup_out_ready) { retval = -EAGAIN; goto done; } spin_unlock_irq (&dev->lock); retval = wait_event_interruptible (dev->wait, dev->setup_out_ready != 0); /* FIXME state could change from under us */ spin_lock_irq (&dev->lock); if (retval) goto done; if (dev->state != STATE_DEV_SETUP) { retval = -ECANCELED; goto done; } dev->state = STATE_DEV_CONNECTED; if (dev->setup_out_error) retval = -EIO; else { len = min (len, (size_t)dev->req->actual); ++dev->udc_usage; spin_unlock_irq(&dev->lock); if (copy_to_user (buf, dev->req->buf, len)) retval = -EFAULT; else retval = len; spin_lock_irq(&dev->lock); --dev->udc_usage; clean_req (dev->gadget->ep0, dev->req); /* NOTE userspace can't yet choose to stall */ } } goto done; } /* else normal: return event data */ if (len < sizeof dev->event [0]) { retval = -EINVAL; goto done; } len -= len % sizeof (struct usb_gadgetfs_event); dev->usermode_setup = 1; scan: /* return queued events right away */ if (dev->ev_next != 0) { unsigned i, n; n = len / sizeof (struct usb_gadgetfs_event); if (dev->ev_next < n) n = dev->ev_next; /* ep0 i/o has special semantics during STATE_DEV_SETUP */ for (i = 0; i < n; i++) { if (dev->event [i].type == GADGETFS_SETUP) { dev->state = STATE_DEV_SETUP; n = i + 1; break; } } spin_unlock_irq (&dev->lock); len = n * sizeof (struct usb_gadgetfs_event); if (copy_to_user (buf, &dev->event, len)) retval = -EFAULT; else retval = len; if (len > 0) { /* NOTE this doesn't guard against broken drivers; * concurrent ep0 readers may lose events. */ spin_lock_irq (&dev->lock); if (dev->ev_next > n) { memmove(&dev->event[0], &dev->event[n], sizeof (struct usb_gadgetfs_event) * (dev->ev_next - n)); } dev->ev_next -= n; spin_unlock_irq (&dev->lock); } return retval; } if (fd->f_flags & O_NONBLOCK) { retval = -EAGAIN; goto done; } switch (state) { default: DBG (dev, "fail %s, state %d\n", __func__, state); retval = -ESRCH; break; case STATE_DEV_UNCONNECTED: case STATE_DEV_CONNECTED: spin_unlock_irq (&dev->lock); DBG (dev, "%s wait\n", __func__); /* wait for events */ retval = wait_event_interruptible (dev->wait, dev->ev_next != 0); if (retval < 0) return retval; spin_lock_irq (&dev->lock); goto scan; } done: spin_unlock_irq (&dev->lock); return retval; } static struct usb_gadgetfs_event * next_event (struct dev_data *dev, enum usb_gadgetfs_event_type type) { struct usb_gadgetfs_event *event; unsigned i; switch (type) { /* these events purge the queue */ case GADGETFS_DISCONNECT: if (dev->state == STATE_DEV_SETUP) dev->setup_abort = 1; fallthrough; case GADGETFS_CONNECT: dev->ev_next = 0; break; case GADGETFS_SETUP: /* previous request timed out */ case GADGETFS_SUSPEND: /* same effect */ /* these events can't be repeated */ for (i = 0; i != dev->ev_next; i++) { if (dev->event [i].type != type) continue; DBG(dev, "discard old event[%d] %d\n", i, type); dev->ev_next--; if (i == dev->ev_next) break; /* indices start at zero, for simplicity */ memmove (&dev->event [i], &dev->event [i + 1], sizeof (struct usb_gadgetfs_event) * (dev->ev_next - i)); } break; default: BUG (); } VDEBUG(dev, "event[%d] = %d\n", dev->ev_next, type); event = &dev->event [dev->ev_next++]; BUG_ON (dev->ev_next > N_EVENT); memset (event, 0, sizeof *event); event->type = type; return event; } static ssize_t ep0_write (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) { struct dev_data *dev = fd->private_data; ssize_t retval = -ESRCH; /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; retval = -EIDRM; /* data and/or status stage for control request */ } else if (dev->state == STATE_DEV_SETUP) { len = min_t(size_t, len, dev->setup_wLength); if (dev->setup_in) { retval = setup_req (dev->gadget->ep0, dev->req, len); if (retval == 0) { dev->state = STATE_DEV_CONNECTED; ++dev->udc_usage; spin_unlock_irq (&dev->lock); if (copy_from_user (dev->req->buf, buf, len)) retval = -EFAULT; else { if (len < dev->setup_wLength) dev->req->zero = 1; retval = usb_ep_queue ( dev->gadget->ep0, dev->req, GFP_KERNEL); } spin_lock_irq(&dev->lock); --dev->udc_usage; if (retval < 0) { clean_req (dev->gadget->ep0, dev->req); } else retval = len; return retval; } /* can stall some OUT transfers */ } else if (dev->setup_can_stall) { VDEBUG(dev, "ep0out stall\n"); (void) usb_ep_set_halt (dev->gadget->ep0); retval = -EL2HLT; dev->state = STATE_DEV_CONNECTED; } else { DBG(dev, "bogus ep0out stall!\n"); } } else DBG (dev, "fail %s, state %d\n", __func__, dev->state); return retval; } static int ep0_fasync (int f, struct file *fd, int on) { struct dev_data *dev = fd->private_data; // caller must F_SETOWN before signal delivery happens VDEBUG (dev, "%s %s\n", __func__, on ? "on" : "off"); return fasync_helper (f, fd, on, &dev->fasync); } static struct usb_gadget_driver gadgetfs_driver; static int dev_release (struct inode *inode, struct file *fd) { struct dev_data *dev = fd->private_data; /* closing ep0 === shutdown all */ if (dev->gadget_registered) { usb_gadget_unregister_driver (&gadgetfs_driver); dev->gadget_registered = false; } /* at this point "good" hardware has disconnected the * device from USB; the host won't see it any more. * alternatively, all host requests will time out. */ kfree (dev->buf); dev->buf = NULL; /* other endpoints were all decoupled from this device */ spin_lock_irq(&dev->lock); dev->state = STATE_DEV_DISABLED; spin_unlock_irq(&dev->lock); put_dev (dev); return 0; } static __poll_t ep0_poll (struct file *fd, poll_table *wait) { struct dev_data *dev = fd->private_data; __poll_t mask = 0; if (dev->state <= STATE_DEV_OPENED) return DEFAULT_POLLMASK; poll_wait(fd, &dev->wait, wait); spin_lock_irq(&dev->lock); /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; mask = EPOLLHUP; goto out; } if (dev->state == STATE_DEV_SETUP) { if (dev->setup_in || dev->setup_can_stall) mask = EPOLLOUT; } else { if (dev->ev_next != 0) mask = EPOLLIN; } out: spin_unlock_irq(&dev->lock); return mask; } static long gadget_dev_ioctl (struct file *fd, unsigned code, unsigned long value) { struct dev_data *dev = fd->private_data; struct usb_gadget *gadget = dev->gadget; long ret = -ENOTTY; spin_lock_irq(&dev->lock); if (dev->state == STATE_DEV_OPENED || dev->state == STATE_DEV_UNBOUND) { /* Not bound to a UDC */ } else if (gadget->ops->ioctl) { ++dev->udc_usage; spin_unlock_irq(&dev->lock); ret = gadget->ops->ioctl (gadget, code, value); spin_lock_irq(&dev->lock); --dev->udc_usage; } spin_unlock_irq(&dev->lock); return ret; } /*----------------------------------------------------------------------*/ /* The in-kernel gadget driver handles most ep0 issues, in particular * enumerating the single configuration (as provided from user space). * * Unrecognized ep0 requests may be handled in user space. */ static void make_qualifier (struct dev_data *dev) { struct usb_qualifier_descriptor qual; struct usb_device_descriptor *desc; qual.bLength = sizeof qual; qual.bDescriptorType = USB_DT_DEVICE_QUALIFIER; qual.bcdUSB = cpu_to_le16 (0x0200); desc = dev->dev; qual.bDeviceClass = desc->bDeviceClass; qual.bDeviceSubClass = desc->bDeviceSubClass; qual.bDeviceProtocol = desc->bDeviceProtocol; /* assumes ep0 uses the same value for both speeds ... */ qual.bMaxPacketSize0 = dev->gadget->ep0->maxpacket; qual.bNumConfigurations = 1; qual.bRESERVED = 0; memcpy (dev->rbuf, &qual, sizeof qual); } static int config_buf (struct dev_data *dev, u8 type, unsigned index) { int len; int hs = 0; /* only one configuration */ if (index > 0) return -EINVAL; if (gadget_is_dualspeed(dev->gadget)) { hs = (dev->gadget->speed == USB_SPEED_HIGH); if (type == USB_DT_OTHER_SPEED_CONFIG) hs = !hs; } if (hs) { dev->req->buf = dev->hs_config; len = le16_to_cpu(dev->hs_config->wTotalLength); } else { dev->req->buf = dev->config; len = le16_to_cpu(dev->config->wTotalLength); } ((u8 *)dev->req->buf) [1] = type; return len; } static int gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) { struct dev_data *dev = get_gadget_data (gadget); struct usb_request *req = dev->req; int value = -EOPNOTSUPP; struct usb_gadgetfs_event *event; u16 w_value = le16_to_cpu(ctrl->wValue); u16 w_length = le16_to_cpu(ctrl->wLength); if (w_length > RBUF_SIZE) { if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp = cpu_to_le16(RBUF_SIZE); w_length = RBUF_SIZE; } else { return value; } } spin_lock (&dev->lock); dev->setup_abort = 0; if (dev->state == STATE_DEV_UNCONNECTED) { if (gadget_is_dualspeed(gadget) && gadget->speed == USB_SPEED_HIGH && dev->hs_config == NULL) { spin_unlock(&dev->lock); ERROR (dev, "no high speed config??\n"); return -EINVAL; } dev->state = STATE_DEV_CONNECTED; INFO (dev, "connected\n"); event = next_event (dev, GADGETFS_CONNECT); event->u.speed = gadget->speed; ep0_readable (dev); /* host may have given up waiting for response. we can miss control * requests handled lower down (device/endpoint status and features); * then ep0_{read,write} will report the wrong status. controller * driver will have aborted pending i/o. */ } else if (dev->state == STATE_DEV_SETUP) dev->setup_abort = 1; req->buf = dev->rbuf; req->context = NULL; switch (ctrl->bRequest) { case USB_REQ_GET_DESCRIPTOR: if (ctrl->bRequestType != USB_DIR_IN) goto unrecognized; switch (w_value >> 8) { case USB_DT_DEVICE: value = min (w_length, (u16) sizeof *dev->dev); dev->dev->bMaxPacketSize0 = dev->gadget->ep0->maxpacket; req->buf = dev->dev; break; case USB_DT_DEVICE_QUALIFIER: if (!dev->hs_config) break; value = min (w_length, (u16) sizeof (struct usb_qualifier_descriptor)); make_qualifier (dev); break; case USB_DT_OTHER_SPEED_CONFIG: case USB_DT_CONFIG: value = config_buf (dev, w_value >> 8, w_value & 0xff); if (value >= 0) value = min (w_length, (u16) value); break; case USB_DT_STRING: goto unrecognized; default: // all others are errors break; } break; /* currently one config, two speeds */ case USB_REQ_SET_CONFIGURATION: if (ctrl->bRequestType != 0) goto unrecognized; if (0 == (u8) w_value) { value = 0; dev->current_config = 0; usb_gadget_vbus_draw(gadget, 8 /* mA */ ); // user mode expected to disable endpoints } else { u8 config, power; if (gadget_is_dualspeed(gadget) && gadget->speed == USB_SPEED_HIGH) { config = dev->hs_config->bConfigurationValue; power = dev->hs_config->bMaxPower; } else { config = dev->config->bConfigurationValue; power = dev->config->bMaxPower; } if (config == (u8) w_value) { value = 0; dev->current_config = config; usb_gadget_vbus_draw(gadget, 2 * power); } } /* report SET_CONFIGURATION like any other control request, * except that usermode may not stall this. the next * request mustn't be allowed start until this finishes: * endpoints and threads set up, etc. * * NOTE: older PXA hardware (before PXA 255: without UDCCFR) * has bad/racey automagic that prevents synchronizing here. * even kernel mode drivers often miss them. */ if (value == 0) { INFO (dev, "configuration #%d\n", dev->current_config); usb_gadget_set_state(gadget, USB_STATE_CONFIGURED); if (dev->usermode_setup) { dev->setup_can_stall = 0; goto delegate; } } break; #ifndef CONFIG_USB_PXA25X /* PXA automagically handles this request too */ case USB_REQ_GET_CONFIGURATION: if (ctrl->bRequestType != 0x80) goto unrecognized; *(u8 *)req->buf = dev->current_config; value = min (w_length, (u16) 1); break; #endif default: unrecognized: VDEBUG (dev, "%s req%02x.%02x v%04x i%04x l%d\n", dev->usermode_setup ? "delegate" : "fail", ctrl->bRequestType, ctrl->bRequest, w_value, le16_to_cpu(ctrl->wIndex), w_length); /* if there's an ep0 reader, don't stall */ if (dev->usermode_setup) { dev->setup_can_stall = 1; delegate: dev->setup_in = (ctrl->bRequestType & USB_DIR_IN) ? 1 : 0; dev->setup_wLength = w_length; dev->setup_out_ready = 0; dev->setup_out_error = 0; /* read DATA stage for OUT right away */ if (unlikely (!dev->setup_in && w_length)) { value = setup_req (gadget->ep0, dev->req, w_length); if (value < 0) break; ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, dev->req, GFP_KERNEL); spin_lock (&dev->lock); --dev->udc_usage; if (value < 0) { clean_req (gadget->ep0, dev->req); break; } /* we can't currently stall these */ dev->setup_can_stall = 0; } /* state changes when reader collects event */ event = next_event (dev, GADGETFS_SETUP); event->u.setup = *ctrl; ep0_readable (dev); spin_unlock (&dev->lock); /* * Return USB_GADGET_DELAYED_STATUS as a workaround to * stop some UDC drivers (e.g. dwc3) from automatically * proceeding with the status stage for 0-length * transfers. * Should be removed once all UDC drivers are fixed to * always delay the status stage until a response is * queued to EP0. */ return w_length == 0 ? USB_GADGET_DELAYED_STATUS : 0; } } /* proceed with data transfer and status phases? */ if (value >= 0 && dev->state != STATE_DEV_SETUP) { req->length = value; req->zero = value < w_length; ++dev->udc_usage; spin_unlock (&dev->lock); value = usb_ep_queue (gadget->ep0, req, GFP_KERNEL); spin_lock(&dev->lock); --dev->udc_usage; spin_unlock(&dev->lock); if (value < 0) { DBG (dev, "ep_queue --> %d\n", value); req->status = 0; } return value; } /* device stalls when value < 0 */ spin_unlock (&dev->lock); return value; } static void destroy_ep_files (struct dev_data *dev) { DBG (dev, "%s %d\n", __func__, dev->state); /* dev->state must prevent interference */ spin_lock_irq (&dev->lock); while (!list_empty(&dev->epfiles)) { struct ep_data *ep; struct inode *parent; struct dentry *dentry; /* break link to FS */ ep = list_first_entry (&dev->epfiles, struct ep_data, epfiles); list_del_init (&ep->epfiles); spin_unlock_irq (&dev->lock); dentry = ep->dentry; ep->dentry = NULL; parent = d_inode(dentry->d_parent); /* break link to controller */ mutex_lock(&ep->lock); if (ep->state == STATE_EP_ENABLED) (void) usb_ep_disable (ep->ep); ep->state = STATE_EP_UNBOUND; usb_ep_free_request (ep->ep, ep->req); ep->ep = NULL; mutex_unlock(&ep->lock); wake_up (&ep->wait); put_ep (ep); /* break link to dcache */ inode_lock(parent); d_delete (dentry); dput (dentry); inode_unlock(parent); spin_lock_irq (&dev->lock); } spin_unlock_irq (&dev->lock); } static struct dentry * gadgetfs_create_file (struct super_block *sb, char const *name, void *data, const struct file_operations *fops); static int activate_ep_files (struct dev_data *dev) { struct usb_ep *ep; struct ep_data *data; gadget_for_each_ep (ep, dev->gadget) { data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) goto enomem0; data->state = STATE_EP_DISABLED; mutex_init(&data->lock); init_waitqueue_head (&data->wait); strncpy (data->name, ep->name, sizeof (data->name) - 1); refcount_set (&data->count, 1); data->dev = dev; get_dev (dev); data->ep = ep; ep->driver_data = data; data->req = usb_ep_alloc_request (ep, GFP_KERNEL); if (!data->req) goto enomem1; data->dentry = gadgetfs_create_file (dev->sb, data->name, data, &ep_io_operations); if (!data->dentry) goto enomem2; list_add_tail (&data->epfiles, &dev->epfiles); } return 0; enomem2: usb_ep_free_request (ep, data->req); enomem1: put_dev (dev); kfree (data); enomem0: DBG (dev, "%s enomem\n", __func__); destroy_ep_files (dev); return -ENOMEM; } static void gadgetfs_unbind (struct usb_gadget *gadget) { struct dev_data *dev = get_gadget_data (gadget); DBG (dev, "%s\n", __func__); spin_lock_irq (&dev->lock); dev->state = STATE_DEV_UNBOUND; while (dev->udc_usage > 0) { spin_unlock_irq(&dev->lock); usleep_range(1000, 2000); spin_lock_irq(&dev->lock); } spin_unlock_irq (&dev->lock); destroy_ep_files (dev); gadget->ep0->driver_data = NULL; set_gadget_data (gadget, NULL); /* we've already been disconnected ... no i/o is active */ if (dev->req) usb_ep_free_request (gadget->ep0, dev->req); DBG (dev, "%s done\n", __func__); put_dev (dev); } static struct dev_data *the_device; static int gadgetfs_bind(struct usb_gadget *gadget, struct usb_gadget_driver *driver) { struct dev_data *dev = the_device; if (!dev) return -ESRCH; if (0 != strcmp (CHIP, gadget->name)) { pr_err("%s expected %s controller not %s\n", shortname, CHIP, gadget->name); return -ENODEV; } set_gadget_data (gadget, dev); dev->gadget = gadget; gadget->ep0->driver_data = dev; /* preallocate control response and buffer */ dev->req = usb_ep_alloc_request (gadget->ep0, GFP_KERNEL); if (!dev->req) goto enomem; dev->req->context = NULL; dev->req->complete = epio_complete; if (activate_ep_files (dev) < 0) goto enomem; INFO (dev, "bound to %s driver\n", gadget->name); spin_lock_irq(&dev->lock); dev->state = STATE_DEV_UNCONNECTED; spin_unlock_irq(&dev->lock); get_dev (dev); return 0; enomem: gadgetfs_unbind (gadget); return -ENOMEM; } static void gadgetfs_disconnect (struct usb_gadget *gadget) { struct dev_data *dev = get_gadget_data (gadget); unsigned long flags; spin_lock_irqsave (&dev->lock, flags); if (dev->state == STATE_DEV_UNCONNECTED) goto exit; dev->state = STATE_DEV_UNCONNECTED; INFO (dev, "disconnected\n"); next_event (dev, GADGETFS_DISCONNECT); ep0_readable (dev); exit: spin_unlock_irqrestore (&dev->lock, flags); } static void gadgetfs_suspend (struct usb_gadget *gadget) { struct dev_data *dev = get_gadget_data (gadget); unsigned long flags; INFO (dev, "suspended from state %d\n", dev->state); spin_lock_irqsave(&dev->lock, flags); switch (dev->state) { case STATE_DEV_SETUP: // VERY odd... host died?? case STATE_DEV_CONNECTED: case STATE_DEV_UNCONNECTED: next_event (dev, GADGETFS_SUSPEND); ep0_readable (dev); fallthrough; default: break; } spin_unlock_irqrestore(&dev->lock, flags); } static struct usb_gadget_driver gadgetfs_driver = { .function = (char *) driver_desc, .bind = gadgetfs_bind, .unbind = gadgetfs_unbind, .setup = gadgetfs_setup, .reset = gadgetfs_disconnect, .disconnect = gadgetfs_disconnect, .suspend = gadgetfs_suspend, .driver = { .name = shortname, }, }; /*----------------------------------------------------------------------*/ /* DEVICE INITIALIZATION * * fd = open ("/dev/gadget/$CHIP", O_RDWR) * status = write (fd, descriptors, sizeof descriptors) * * That write establishes the device configuration, so the kernel can * bind to the controller ... guaranteeing it can handle enumeration * at all necessary speeds. Descriptor order is: * * . message tag (u32, host order) ... for now, must be zero; it * would change to support features like multi-config devices * . full/low speed config ... all wTotalLength bytes (with interface, * class, altsetting, endpoint, and other descriptors) * . high speed config ... all descriptors, for high speed operation; * this one's optional except for high-speed hardware * . device descriptor * * Endpoints are not yet enabled. Drivers must wait until device * configuration and interface altsetting changes create * the need to configure (or unconfigure) them. * * After initialization, the device stays active for as long as that * $CHIP file is open. Events must then be read from that descriptor, * such as configuration notifications. */ static int is_valid_config(struct usb_config_descriptor *config, unsigned int total) { return config->bDescriptorType == USB_DT_CONFIG && config->bLength == USB_DT_CONFIG_SIZE && total >= USB_DT_CONFIG_SIZE && config->bConfigurationValue != 0 && (config->bmAttributes & USB_CONFIG_ATT_ONE) != 0 && (config->bmAttributes & USB_CONFIG_ATT_WAKEUP) == 0; /* FIXME if gadget->is_otg, _must_ include an otg descriptor */ /* FIXME check lengths: walk to end */ } static ssize_t dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) { struct dev_data *dev = fd->private_data; ssize_t value, length = len; unsigned total; u32 tag; char *kbuf; spin_lock_irq(&dev->lock); if (dev->state > STATE_DEV_OPENED) { value = ep0_write(fd, buf, len, ptr); spin_unlock_irq(&dev->lock); return value; } spin_unlock_irq(&dev->lock); if ((len < (USB_DT_CONFIG_SIZE + USB_DT_DEVICE_SIZE + 4)) || (len > PAGE_SIZE * 4)) return -EINVAL; /* we might need to change message format someday */ if (copy_from_user (&tag, buf, 4)) return -EFAULT; if (tag != 0) return -EINVAL; buf += 4; length -= 4; kbuf = memdup_user(buf, length); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); spin_lock_irq (&dev->lock); value = -EINVAL; if (dev->buf) { spin_unlock_irq(&dev->lock); kfree(kbuf); return value; } dev->buf = kbuf; /* full or low speed config */ dev->config = (void *) kbuf; total = le16_to_cpu(dev->config->wTotalLength); if (!is_valid_config(dev->config, total) || total > length - USB_DT_DEVICE_SIZE) goto fail; kbuf += total; length -= total; /* optional high speed config */ if (kbuf [1] == USB_DT_CONFIG) { dev->hs_config = (void *) kbuf; total = le16_to_cpu(dev->hs_config->wTotalLength); if (!is_valid_config(dev->hs_config, total) || total > length - USB_DT_DEVICE_SIZE) goto fail; kbuf += total; length -= total; } else { dev->hs_config = NULL; } /* could support multiple configs, using another encoding! */ /* device descriptor (tweaked for paranoia) */ if (length != USB_DT_DEVICE_SIZE) goto fail; dev->dev = (void *)kbuf; if (dev->dev->bLength != USB_DT_DEVICE_SIZE || dev->dev->bDescriptorType != USB_DT_DEVICE || dev->dev->bNumConfigurations != 1) goto fail; dev->dev->bcdUSB = cpu_to_le16 (0x0200); /* triggers gadgetfs_bind(); then we can enumerate. */ spin_unlock_irq (&dev->lock); if (dev->hs_config) gadgetfs_driver.max_speed = USB_SPEED_HIGH; else gadgetfs_driver.max_speed = USB_SPEED_FULL; value = usb_gadget_register_driver(&gadgetfs_driver); if (value != 0) { spin_lock_irq(&dev->lock); goto fail; } else { /* at this point "good" hardware has for the first time * let the USB the host see us. alternatively, if users * unplug/replug that will clear all the error state. * * note: everything running before here was guaranteed * to choke driver model style diagnostics. from here * on, they can work ... except in cleanup paths that * kick in after the ep0 descriptor is closed. */ value = len; dev->gadget_registered = true; } return value; fail: dev->config = NULL; dev->hs_config = NULL; dev->dev = NULL; spin_unlock_irq (&dev->lock); pr_debug ("%s: %s fail %zd, %p\n", shortname, __func__, value, dev); kfree (dev->buf); dev->buf = NULL; return value; } static int gadget_dev_open (struct inode *inode, struct file *fd) { struct dev_data *dev = inode->i_private; int value = -EBUSY; spin_lock_irq(&dev->lock); if (dev->state == STATE_DEV_DISABLED) { dev->ev_next = 0; dev->state = STATE_DEV_OPENED; fd->private_data = dev; get_dev (dev); value = 0; } spin_unlock_irq(&dev->lock); return value; } static const struct file_operations ep0_operations = { .llseek = no_llseek, .open = gadget_dev_open, .read = ep0_read, .write = dev_config, .fasync = ep0_fasync, .poll = ep0_poll, .unlocked_ioctl = gadget_dev_ioctl, .release = dev_release, }; /*----------------------------------------------------------------------*/ /* FILESYSTEM AND SUPERBLOCK OPERATIONS * * Mounting the filesystem creates a controller file, used first for * device configuration then later for event monitoring. */ /* FIXME PAM etc could set this security policy without mount options * if epfiles inherited ownership and permissons from ep0 ... */ static unsigned default_uid; static unsigned default_gid; static unsigned default_perm = S_IRUSR | S_IWUSR; module_param (default_uid, uint, 0644); module_param (default_gid, uint, 0644); module_param (default_perm, uint, 0644); static struct inode * gadgetfs_make_inode (struct super_block *sb, void *data, const struct file_operations *fops, int mode) { struct inode *inode = new_inode (sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = make_kuid(&init_user_ns, default_uid); inode->i_gid = make_kgid(&init_user_ns, default_gid); simple_inode_init_ts(inode); inode->i_private = data; inode->i_fop = fops; } return inode; } /* creates in fs root directory, so non-renamable and non-linkable. * so inode and dentry are paired, until device reconfig. */ static struct dentry * gadgetfs_create_file (struct super_block *sb, char const *name, void *data, const struct file_operations *fops) { struct dentry *dentry; struct inode *inode; dentry = d_alloc_name(sb->s_root, name); if (!dentry) return NULL; inode = gadgetfs_make_inode (sb, data, fops, S_IFREG | (default_perm & S_IRWXUGO)); if (!inode) { dput(dentry); return NULL; } d_add (dentry, inode); return dentry; } static const struct super_operations gadget_fs_operations = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, }; static int gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct dev_data *dev; int rc; mutex_lock(&sb_mutex); if (the_device) { rc = -ESRCH; goto Done; } CHIP = usb_get_gadget_udc_name(); if (!CHIP) { rc = -ENODEV; goto Done; } /* superblock */ sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = GADGETFS_MAGIC; sb->s_op = &gadget_fs_operations; sb->s_time_gran = 1; /* root inode */ inode = gadgetfs_make_inode (sb, NULL, &simple_dir_operations, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) goto Enomem; inode->i_op = &simple_dir_inode_operations; if (!(sb->s_root = d_make_root (inode))) goto Enomem; /* the ep0 file is named after the controller we expect; * user mode code can use it for sanity checks, like we do. */ dev = dev_new (); if (!dev) goto Enomem; dev->sb = sb; dev->dentry = gadgetfs_create_file(sb, CHIP, dev, &ep0_operations); if (!dev->dentry) { put_dev(dev); goto Enomem; } /* other endpoint files are available after hardware setup, * from binding to a controller. */ the_device = dev; rc = 0; goto Done; Enomem: kfree(CHIP); CHIP = NULL; rc = -ENOMEM; Done: mutex_unlock(&sb_mutex); return rc; } /* "mount -t gadgetfs path /dev/gadget" ends up here */ static int gadgetfs_get_tree(struct fs_context *fc) { return get_tree_single(fc, gadgetfs_fill_super); } static const struct fs_context_operations gadgetfs_context_ops = { .get_tree = gadgetfs_get_tree, }; static int gadgetfs_init_fs_context(struct fs_context *fc) { fc->ops = &gadgetfs_context_ops; return 0; } static void gadgetfs_kill_sb (struct super_block *sb) { mutex_lock(&sb_mutex); kill_litter_super (sb); if (the_device) { put_dev (the_device); the_device = NULL; } kfree(CHIP); CHIP = NULL; mutex_unlock(&sb_mutex); } /*----------------------------------------------------------------------*/ static struct file_system_type gadgetfs_type = { .owner = THIS_MODULE, .name = shortname, .init_fs_context = gadgetfs_init_fs_context, .kill_sb = gadgetfs_kill_sb, }; MODULE_ALIAS_FS("gadgetfs"); /*----------------------------------------------------------------------*/ static int __init gadgetfs_init (void) { int status; status = register_filesystem (&gadgetfs_type); if (status == 0) pr_info ("%s: %s, version " DRIVER_VERSION "\n", shortname, driver_desc); return status; } module_init (gadgetfs_init); static void __exit gadgetfs_cleanup (void) { pr_debug ("unregister %s\n", shortname); unregister_filesystem (&gadgetfs_type); } module_exit (gadgetfs_cleanup); |
| 1 4 4 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2011 Patrick McHardy <kaber@trash.net> * * Based on Rusty Russell's IPv4 NAT code. Development of IPv6 NAT * funded by Astaro. */ #include <linux/module.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include <net/netfilter/nf_nat.h> struct ip6table_nat_pernet { struct nf_hook_ops *nf_nat_ops; }; static unsigned int ip6table_nat_net_id __read_mostly; static const struct xt_table nf_nat_ipv6_table = { .name = "nat", .valid_hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, .af = NFPROTO_IPV6, }; static const struct nf_hook_ops nf_nat_ipv6_ops[] = { { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, { .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, }, }; static int ip6t_nat_register_lookups(struct net *net) { struct ip6table_nat_pernet *xt_nat_net; struct nf_hook_ops *ops; struct xt_table *table; int i, ret; table = xt_find_table(net, NFPROTO_IPV6, "nat"); if (WARN_ON_ONCE(!table)) return -ENOENT; xt_nat_net = net_generic(net, ip6table_nat_net_id); ops = kmemdup(nf_nat_ipv6_ops, sizeof(nf_nat_ipv6_ops), GFP_KERNEL); if (!ops) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) { ops[i].priv = table; ret = nf_nat_ipv6_register_fn(net, &ops[i]); if (ret) { while (i) nf_nat_ipv6_unregister_fn(net, &ops[--i]); kfree(ops); return ret; } } xt_nat_net->nf_nat_ops = ops; return 0; } static void ip6t_nat_unregister_lookups(struct net *net) { struct ip6table_nat_pernet *xt_nat_net = net_generic(net, ip6table_nat_net_id); struct nf_hook_ops *ops = xt_nat_net->nf_nat_ops; int i; if (!ops) return; for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) nf_nat_ipv6_unregister_fn(net, &ops[i]); kfree(ops); } static int ip6table_nat_table_init(struct net *net) { struct ip6t_replace *repl; int ret; repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table); if (repl == NULL) return -ENOMEM; ret = ip6t_register_table(net, &nf_nat_ipv6_table, repl, NULL); if (ret < 0) { kfree(repl); return ret; } ret = ip6t_nat_register_lookups(net); if (ret < 0) ip6t_unregister_table_exit(net, "nat"); kfree(repl); return ret; } static void __net_exit ip6table_nat_net_pre_exit(struct net *net) { ip6t_nat_unregister_lookups(net); } static void __net_exit ip6table_nat_net_exit(struct net *net) { ip6t_unregister_table_exit(net, "nat"); } static struct pernet_operations ip6table_nat_net_ops = { .pre_exit = ip6table_nat_net_pre_exit, .exit = ip6table_nat_net_exit, .id = &ip6table_nat_net_id, .size = sizeof(struct ip6table_nat_pernet), }; static int __init ip6table_nat_init(void) { int ret; /* net->gen->ptr[ip6table_nat_net_id] must be allocated * before calling ip6t_nat_register_lookups(). */ ret = register_pernet_subsys(&ip6table_nat_net_ops); if (ret < 0) return ret; ret = xt_register_template(&nf_nat_ipv6_table, ip6table_nat_table_init); if (ret) unregister_pernet_subsys(&ip6table_nat_net_ops); return ret; } static void __exit ip6table_nat_exit(void) { xt_unregister_template(&nf_nat_ipv6_table); unregister_pernet_subsys(&ip6table_nat_net_ops); } module_init(ip6table_nat_init); module_exit(ip6table_nat_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Ip6tables legacy nat table"); |
| 414 414 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * proc.c - procfs support for Protocol family CAN core module * * Copyright (c) 2002-2007 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/if_arp.h> #include <linux/can/can-ml.h> #include <linux/can/core.h> #include "af_can.h" /* * proc filenames for the PF_CAN core */ #define CAN_PROC_STATS "stats" #define CAN_PROC_RESET_STATS "reset_stats" #define CAN_PROC_RCVLIST_ALL "rcvlist_all" #define CAN_PROC_RCVLIST_FIL "rcvlist_fil" #define CAN_PROC_RCVLIST_INV "rcvlist_inv" #define CAN_PROC_RCVLIST_SFF "rcvlist_sff" #define CAN_PROC_RCVLIST_EFF "rcvlist_eff" #define CAN_PROC_RCVLIST_ERR "rcvlist_err" static int user_reset; static const char rx_list_name[][8] = { [RX_ERR] = "rx_err", [RX_ALL] = "rx_all", [RX_FIL] = "rx_fil", [RX_INV] = "rx_inv", }; /* * af_can statistics stuff */ static void can_init_stats(struct net *net) { struct can_pkg_stats *pkg_stats = net->can.pkg_stats; struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats; /* * This memset function is called from a timer context (when * can_stattimer is active which is the default) OR in a process * context (reading the proc_fs when can_stattimer is disabled). */ memset(pkg_stats, 0, sizeof(struct can_pkg_stats)); pkg_stats->jiffies_init = jiffies; rcv_lists_stats->stats_reset++; if (user_reset) { user_reset = 0; rcv_lists_stats->user_reset++; } } static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif, unsigned long count) { if (oldjif == newjif) return 0; /* see can_stat_update() - this should NEVER happen! */ if (count > (ULONG_MAX / HZ)) { printk(KERN_ERR "can: calc_rate: count exceeded! %ld\n", count); return 99999999; } return (count * HZ) / (newjif - oldjif); } void can_stat_update(struct timer_list *t) { struct net *net = from_timer(net, t, can.stattimer); struct can_pkg_stats *pkg_stats = net->can.pkg_stats; unsigned long j = jiffies; /* snapshot */ /* restart counting in timer context on user request */ if (user_reset) can_init_stats(net); /* restart counting on jiffies overflow */ if (j < pkg_stats->jiffies_init) can_init_stats(net); /* prevent overflow in calc_rate() */ if (pkg_stats->rx_frames > (ULONG_MAX / HZ)) can_init_stats(net); /* prevent overflow in calc_rate() */ if (pkg_stats->tx_frames > (ULONG_MAX / HZ)) can_init_stats(net); /* matches overflow - very improbable */ if (pkg_stats->matches > (ULONG_MAX / 100)) can_init_stats(net); /* calc total values */ if (pkg_stats->rx_frames) pkg_stats->total_rx_match_ratio = (pkg_stats->matches * 100) / pkg_stats->rx_frames; pkg_stats->total_tx_rate = calc_rate(pkg_stats->jiffies_init, j, pkg_stats->tx_frames); pkg_stats->total_rx_rate = calc_rate(pkg_stats->jiffies_init, j, pkg_stats->rx_frames); /* calc current values */ if (pkg_stats->rx_frames_delta) pkg_stats->current_rx_match_ratio = (pkg_stats->matches_delta * 100) / pkg_stats->rx_frames_delta; pkg_stats->current_tx_rate = calc_rate(0, HZ, pkg_stats->tx_frames_delta); pkg_stats->current_rx_rate = calc_rate(0, HZ, pkg_stats->rx_frames_delta); /* check / update maximum values */ if (pkg_stats->max_tx_rate < pkg_stats->current_tx_rate) pkg_stats->max_tx_rate = pkg_stats->current_tx_rate; if (pkg_stats->max_rx_rate < pkg_stats->current_rx_rate) pkg_stats->max_rx_rate = pkg_stats->current_rx_rate; if (pkg_stats->max_rx_match_ratio < pkg_stats->current_rx_match_ratio) pkg_stats->max_rx_match_ratio = pkg_stats->current_rx_match_ratio; /* clear values for 'current rate' calculation */ pkg_stats->tx_frames_delta = 0; pkg_stats->rx_frames_delta = 0; pkg_stats->matches_delta = 0; /* restart timer (one second) */ mod_timer(&net->can.stattimer, round_jiffies(jiffies + HZ)); } /* * proc read functions */ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, struct net_device *dev) { struct receiver *r; hlist_for_each_entry_rcu(r, rx_list, list) { char *fmt = (r->can_id & CAN_EFF_FLAG)? " %-5s %08x %08x %pK %pK %8ld %s\n" : " %-5s %03x %08x %pK %pK %8ld %s\n"; seq_printf(m, fmt, DNAME(dev), r->can_id, r->mask, r->func, r->data, r->matches, r->ident); } } static void can_print_recv_banner(struct seq_file *m) { /* * can1. 00000000 00000000 00000000 * ....... 0 tp20 */ if (IS_ENABLED(CONFIG_64BIT)) seq_puts(m, " device can_id can_mask function userdata matches ident\n"); else seq_puts(m, " device can_id can_mask function userdata matches ident\n"); } static int can_stats_proc_show(struct seq_file *m, void *v) { struct net *net = m->private; struct can_pkg_stats *pkg_stats = net->can.pkg_stats; struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats; seq_putc(m, '\n'); seq_printf(m, " %8ld transmitted frames (TXF)\n", pkg_stats->tx_frames); seq_printf(m, " %8ld received frames (RXF)\n", pkg_stats->rx_frames); seq_printf(m, " %8ld matched frames (RXMF)\n", pkg_stats->matches); seq_putc(m, '\n'); if (net->can.stattimer.function == can_stat_update) { seq_printf(m, " %8ld %% total match ratio (RXMR)\n", pkg_stats->total_rx_match_ratio); seq_printf(m, " %8ld frames/s total tx rate (TXR)\n", pkg_stats->total_tx_rate); seq_printf(m, " %8ld frames/s total rx rate (RXR)\n", pkg_stats->total_rx_rate); seq_putc(m, '\n'); seq_printf(m, " %8ld %% current match ratio (CRXMR)\n", pkg_stats->current_rx_match_ratio); seq_printf(m, " %8ld frames/s current tx rate (CTXR)\n", pkg_stats->current_tx_rate); seq_printf(m, " %8ld frames/s current rx rate (CRXR)\n", pkg_stats->current_rx_rate); seq_putc(m, '\n'); seq_printf(m, " %8ld %% max match ratio (MRXMR)\n", pkg_stats->max_rx_match_ratio); seq_printf(m, " %8ld frames/s max tx rate (MTXR)\n", pkg_stats->max_tx_rate); seq_printf(m, " %8ld frames/s max rx rate (MRXR)\n", pkg_stats->max_rx_rate); seq_putc(m, '\n'); } seq_printf(m, " %8ld current receive list entries (CRCV)\n", rcv_lists_stats->rcv_entries); seq_printf(m, " %8ld maximum receive list entries (MRCV)\n", rcv_lists_stats->rcv_entries_max); if (rcv_lists_stats->stats_reset) seq_printf(m, "\n %8ld statistic resets (STR)\n", rcv_lists_stats->stats_reset); if (rcv_lists_stats->user_reset) seq_printf(m, " %8ld user statistic resets (USTR)\n", rcv_lists_stats->user_reset); seq_putc(m, '\n'); return 0; } static int can_reset_stats_proc_show(struct seq_file *m, void *v) { struct net *net = m->private; struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats; struct can_pkg_stats *pkg_stats = net->can.pkg_stats; user_reset = 1; if (net->can.stattimer.function == can_stat_update) { seq_printf(m, "Scheduled statistic reset #%ld.\n", rcv_lists_stats->stats_reset + 1); } else { if (pkg_stats->jiffies_init != jiffies) can_init_stats(net); seq_printf(m, "Performed statistic reset #%ld.\n", rcv_lists_stats->stats_reset); } return 0; } static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx, struct net_device *dev, struct can_dev_rcv_lists *dev_rcv_lists) { if (!hlist_empty(&dev_rcv_lists->rx[idx])) { can_print_recv_banner(m); can_print_rcvlist(m, &dev_rcv_lists->rx[idx], dev); } else seq_printf(m, " (%s: no entry)\n", DNAME(dev)); } static int can_rcvlist_proc_show(struct seq_file *m, void *v) { /* double cast to prevent GCC warning */ int idx = (int)(long)pde_data(m->file->f_inode); struct net_device *dev; struct can_dev_rcv_lists *dev_rcv_lists; struct net *net = m->private; seq_printf(m, "\nreceive list '%s':\n", rx_list_name[idx]); rcu_read_lock(); /* receive list for 'all' CAN devices (dev == NULL) */ dev_rcv_lists = net->can.rx_alldev_list; can_rcvlist_proc_show_one(m, idx, NULL, dev_rcv_lists); /* receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { struct can_ml_priv *can_ml = can_get_ml_priv(dev); if (can_ml) can_rcvlist_proc_show_one(m, idx, dev, &can_ml->dev_rcv_lists); } rcu_read_unlock(); seq_putc(m, '\n'); return 0; } static inline void can_rcvlist_proc_show_array(struct seq_file *m, struct net_device *dev, struct hlist_head *rcv_array, unsigned int rcv_array_sz) { unsigned int i; int all_empty = 1; /* check whether at least one list is non-empty */ for (i = 0; i < rcv_array_sz; i++) if (!hlist_empty(&rcv_array[i])) { all_empty = 0; break; } if (!all_empty) { can_print_recv_banner(m); for (i = 0; i < rcv_array_sz; i++) { if (!hlist_empty(&rcv_array[i])) can_print_rcvlist(m, &rcv_array[i], dev); } } else seq_printf(m, " (%s: no entry)\n", DNAME(dev)); } static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) { struct net_device *dev; struct can_dev_rcv_lists *dev_rcv_lists; struct net *net = m->private; /* RX_SFF */ seq_puts(m, "\nreceive list 'rx_sff':\n"); rcu_read_lock(); /* sff receive list for 'all' CAN devices (dev == NULL) */ dev_rcv_lists = net->can.rx_alldev_list; can_rcvlist_proc_show_array(m, NULL, dev_rcv_lists->rx_sff, ARRAY_SIZE(dev_rcv_lists->rx_sff)); /* sff receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { struct can_ml_priv *can_ml = can_get_ml_priv(dev); if (can_ml) { dev_rcv_lists = &can_ml->dev_rcv_lists; can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_sff, ARRAY_SIZE(dev_rcv_lists->rx_sff)); } } rcu_read_unlock(); seq_putc(m, '\n'); return 0; } static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v) { struct net_device *dev; struct can_dev_rcv_lists *dev_rcv_lists; struct net *net = m->private; /* RX_EFF */ seq_puts(m, "\nreceive list 'rx_eff':\n"); rcu_read_lock(); /* eff receive list for 'all' CAN devices (dev == NULL) */ dev_rcv_lists = net->can.rx_alldev_list; can_rcvlist_proc_show_array(m, NULL, dev_rcv_lists->rx_eff, ARRAY_SIZE(dev_rcv_lists->rx_eff)); /* eff receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { struct can_ml_priv *can_ml = can_get_ml_priv(dev); if (can_ml) { dev_rcv_lists = &can_ml->dev_rcv_lists; can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_eff, ARRAY_SIZE(dev_rcv_lists->rx_eff)); } } rcu_read_unlock(); seq_putc(m, '\n'); return 0; } /* * can_init_proc - create main CAN proc directory and procfs entries */ void can_init_proc(struct net *net) { /* create /proc/net/can directory */ net->can.proc_dir = proc_net_mkdir(net, "can", net->proc_net); if (!net->can.proc_dir) { printk(KERN_INFO "can: failed to create /proc/net/can . " "CONFIG_PROC_FS missing?\n"); return; } /* own procfs entries from the AF_CAN core */ net->can.pde_stats = proc_create_net_single(CAN_PROC_STATS, 0644, net->can.proc_dir, can_stats_proc_show, NULL); net->can.pde_reset_stats = proc_create_net_single(CAN_PROC_RESET_STATS, 0644, net->can.proc_dir, can_reset_stats_proc_show, NULL); net->can.pde_rcvlist_err = proc_create_net_single(CAN_PROC_RCVLIST_ERR, 0644, net->can.proc_dir, can_rcvlist_proc_show, (void *)RX_ERR); net->can.pde_rcvlist_all = proc_create_net_single(CAN_PROC_RCVLIST_ALL, 0644, net->can.proc_dir, can_rcvlist_proc_show, (void *)RX_ALL); net->can.pde_rcvlist_fil = proc_create_net_single(CAN_PROC_RCVLIST_FIL, 0644, net->can.proc_dir, can_rcvlist_proc_show, (void *)RX_FIL); net->can.pde_rcvlist_inv = proc_create_net_single(CAN_PROC_RCVLIST_INV, 0644, net->can.proc_dir, can_rcvlist_proc_show, (void *)RX_INV); net->can.pde_rcvlist_eff = proc_create_net_single(CAN_PROC_RCVLIST_EFF, 0644, net->can.proc_dir, can_rcvlist_eff_proc_show, NULL); net->can.pde_rcvlist_sff = proc_create_net_single(CAN_PROC_RCVLIST_SFF, 0644, net->can.proc_dir, can_rcvlist_sff_proc_show, NULL); } /* * can_remove_proc - remove procfs entries and main CAN proc directory */ void can_remove_proc(struct net *net) { if (!net->can.proc_dir) return; if (net->can.pde_stats) remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir); if (net->can.pde_reset_stats) remove_proc_entry(CAN_PROC_RESET_STATS, net->can.proc_dir); if (net->can.pde_rcvlist_err) remove_proc_entry(CAN_PROC_RCVLIST_ERR, net->can.proc_dir); if (net->can.pde_rcvlist_all) remove_proc_entry(CAN_PROC_RCVLIST_ALL, net->can.proc_dir); if (net->can.pde_rcvlist_fil) remove_proc_entry(CAN_PROC_RCVLIST_FIL, net->can.proc_dir); if (net->can.pde_rcvlist_inv) remove_proc_entry(CAN_PROC_RCVLIST_INV, net->can.proc_dir); if (net->can.pde_rcvlist_eff) remove_proc_entry(CAN_PROC_RCVLIST_EFF, net->can.proc_dir); if (net->can.pde_rcvlist_sff) remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir); remove_proc_entry("can", net->proc_net); } |
| 93 27 18 237 80 304 305 45 15 415 73 73 141 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the UDP module. * * Version: @(#)udp.h 1.0.2 05/07/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Fixes: * Alan Cox : Turned on udp checksums. I don't want to * chase 'memory corruption' bugs that aren't! */ #ifndef _UDP_H #define _UDP_H #include <linux/list.h> #include <linux/bug.h> #include <net/inet_sock.h> #include <net/gso.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> #include <linux/ipv6.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/indirect_call_wrapper.h> /** * struct udp_skb_cb - UDP(-Lite) private variables * * @header: private variables used by IPv4/IPv6 * @cscov: checksum coverage length (UDP-Lite only) * @partial_cov: if set indicates partial csum coverage */ struct udp_skb_cb { union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; __u16 cscov; __u8 partial_cov; }; #define UDP_SKB_CB(__skb) ((struct udp_skb_cb *)((__skb)->cb)) /** * struct udp_hslot - UDP hash slot * * @head: head of list of sockets * @count: number of sockets in 'head' list * @lock: spinlock protecting changes to head/count */ struct udp_hslot { struct hlist_head head; int count; spinlock_t lock; } __attribute__((aligned(2 * sizeof(long)))); /** * struct udp_table - UDP table * * @hash: hash table, sockets are hashed on (local port) * @hash2: hash table, sockets are hashed on (local port, local address) * @mask: number of slots in hash tables, minus 1 * @log: log2(number of slots in hash table) */ struct udp_table { struct udp_hslot *hash; struct udp_hslot *hash2; unsigned int mask; unsigned int log; }; extern struct udp_table udp_table; void udp_table_init(struct udp_table *, const char *); static inline struct udp_hslot *udp_hashslot(struct udp_table *table, const struct net *net, unsigned int num) { return &table->hash[udp_hashfn(net, num, table->mask)]; } /* * For secondary hash, net_hash_mix() is performed before calling * udp_hashslot2(), this explains difference with udp_hashslot() */ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, unsigned int hash) { return &table->hash2[hash & table->mask]; } extern struct proto udp_prot; extern atomic_long_t udp_memory_allocated; DECLARE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); /* sysctl variables for udp */ extern long sysctl_udp_mem[3]; extern int sysctl_udp_rmem_min; extern int sysctl_udp_wmem_min; struct sk_buff; /* * Generic checksumming routines for UDP(-Lite) v4 and v6 */ static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb) { return (UDP_SKB_CB(skb)->cscov == skb->len ? __skb_checksum_complete(skb) : __skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov)); } static inline int udp_lib_checksum_complete(struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && __udp_lib_checksum_complete(skb); } /** * udp_csum_outgoing - compute UDPv4/v6 checksum over fragments * @sk: socket we are writing to * @skb: sk_buff containing the filled-in UDP header * (checksum field must be zeroed out) */ static inline __wsum udp_csum_outgoing(struct sock *sk, struct sk_buff *skb) { __wsum csum = csum_partial(skb_transport_header(skb), sizeof(struct udphdr), 0); skb_queue_walk(&sk->sk_write_queue, skb) { csum = csum_add(csum, skb->csum); } return csum; } static inline __wsum udp_csum(struct sk_buff *skb) { __wsum csum = csum_partial(skb_transport_header(skb), sizeof(struct udphdr), skb->csum); for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next) { csum = csum_add(csum, skb->csum); } return csum; } static inline __sum16 udp_v4_check(int len, __be32 saddr, __be32 daddr, __wsum base) { return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_UDP, base); } void udp_set_csum(bool nocheck, struct sk_buff *skb, __be32 saddr, __be32 daddr, int len); static inline void udp_csum_pull_header(struct sk_buff *skb) { if (!skb->csum_valid && skb->ip_summed == CHECKSUM_NONE) skb->csum = csum_partial(skb->data, sizeof(struct udphdr), skb->csum); skb_pull_rcsum(skb, sizeof(struct udphdr)); UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr); } typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport, __be16 dport); void udp_v6_early_demux(struct sk_buff *skb); INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6); static inline void udp_lib_init_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); skb_queue_head_init(&up->reader_queue); up->forward_threshold = sk->sk_rcvbuf >> 2; set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); } /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ static inline int udp_lib_hash(struct sock *sk) { BUG(); return 0; } void udp_lib_unhash(struct sock *sk); void udp_lib_rehash(struct sock *sk, u16 new_hash); static inline void udp_lib_close(struct sock *sk, long timeout) { sk_common_release(sk); } int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned int hash2_nulladdr); u32 udp_flow_hashrnd(void); static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, int min, int max, bool use_eth) { u32 hash; if (min >= max) { /* Use default range */ inet_get_local_port_range(net, &min, &max); } hash = skb_get_hash(skb); if (unlikely(!hash)) { if (use_eth) { /* Can't find a normal hash, caller has indicated an * Ethernet packet so use that to compute a hash. */ hash = jhash(skb->data, 2 * ETH_ALEN, (__force u32) skb->protocol); } else { /* Can't derive any sort of hash for the packet, set * to some consistent random value. */ hash = udp_flow_hashrnd(); } } /* Since this is being sent on the wire obfuscate hash a bit * to minimize possibility that any useful information to an * attacker is leaked. Only upper 16 bits are relevant in the * computation for 16 bit port value. */ hash ^= hash << 16; return htons((((u64) hash * (max - min)) >> 32) + min); } static inline int udp_rqueue_get(struct sock *sk) { return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } static inline bool udp_sk_bound_dev_eq(const struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_udp_l3mdev_accept), bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); #endif } /* net/ipv4/udp.c */ void udp_destruct_common(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off, int *err); static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, int *err) { int off = 0; return __skb_recv_udp(sk, flags, &off, err); } int udp_v4_early_demux(struct sk_buff *skb); bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); int udp_err(struct sk_buff *, u32); int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); void udp_splice_eof(struct socket *sock); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size); void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); int udp_rcv(struct sk_buff *skb); int udp_ioctl(struct sock *sk, int cmd, int *karg); int udp_init_sock(struct sock *sk); int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int __udp_disconnect(struct sock *sk, int flags); int udp_disconnect(struct sock *sk, int flags); __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait); struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6); int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif); struct sock *__udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); /* UDP uses skb->dev_scratch to cache as much information as possible and avoid * possibly multiple cache miss on dequeue() */ struct udp_dev_scratch { /* skb->truesize and the stateless bit are embedded in a single field; * do not use a bitfield since the compiler emits better/smaller code * this way */ u32 _tsize_state; #if BITS_PER_LONG == 64 /* len and the bit needed to compute skb_csum_unnecessary * will be on cold cache lines at recvmsg time. * skb->len can be stored on 16 bits since the udp header has been * already validated and pulled. */ u16 len; bool is_linear; bool csum_unnecessary; #endif }; static inline struct udp_dev_scratch *udp_skb_scratch(struct sk_buff *skb) { return (struct udp_dev_scratch *)&skb->dev_scratch; } #if BITS_PER_LONG == 64 static inline unsigned int udp_skb_len(struct sk_buff *skb) { return udp_skb_scratch(skb)->len; } static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) { return udp_skb_scratch(skb)->csum_unnecessary; } static inline bool udp_skb_is_linear(struct sk_buff *skb) { return udp_skb_scratch(skb)->is_linear; } #else static inline unsigned int udp_skb_len(struct sk_buff *skb) { return skb->len; } static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) { return skb_csum_unnecessary(skb); } static inline bool udp_skb_is_linear(struct sk_buff *skb) { return !skb_is_nonlinear(skb); } #endif static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, struct iov_iter *to) { return copy_to_iter_full(skb->data + off, len, to) ? 0 : -EFAULT; } /* * SNMP statistics for UDP and UDP-Lite */ #define UDP_INC_STATS(net, field, is_udplite) do { \ if (is_udplite) SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ else SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) #define __UDP_INC_STATS(net, field, is_udplite) do { \ if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ else __SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) #define __UDP6_INC_STATS(net, field, is_udplite) do { \ if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_stats_in6, field);\ else __SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) #define UDP6_INC_STATS(net, field, __lite) do { \ if (__lite) SNMP_INC_STATS((net)->mib.udplite_stats_in6, field); \ else SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) #if IS_ENABLED(CONFIG_IPV6) #define __UDPX_MIB(sk, ipv4) \ ({ \ ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ sock_net(sk)->mib.udp_statistics) : \ (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 : \ sock_net(sk)->mib.udp_stats_in6); \ }) #else #define __UDPX_MIB(sk, ipv4) \ ({ \ IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ sock_net(sk)->mib.udp_statistics; \ }) #endif #define __UDPX_INC_STATS(sk, field) \ __SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field) #ifdef CONFIG_PROC_FS struct udp_seq_afinfo { sa_family_t family; struct udp_table *udp_table; }; struct udp_iter_state { struct seq_net_private p; int bucket; }; void *udp_seq_start(struct seq_file *seq, loff_t *pos); void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos); void udp_seq_stop(struct seq_file *seq, void *v); extern const struct seq_operations udp_seq_ops; extern const struct seq_operations udp6_seq_ops; int udp4_proc_init(void); void udp4_proc_exit(void); #endif /* CONFIG_PROC_FS */ int udpv4_offload_init(void); void udp_init(void); DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); void udp_encap_enable(void); void udp_encap_disable(void); #if IS_ENABLED(CONFIG_IPV6) DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void); #endif static inline struct sk_buff *udp_rcv_segment(struct sock *sk, struct sk_buff *skb, bool ipv4) { netdev_features_t features = NETIF_F_SG; struct sk_buff *segs; /* Avoid csum recalculation by skb_segment unless userspace explicitly * asks for the final checksum values */ if (!inet_get_convert_csum(sk)) features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; /* UDP segmentation expects packets of type CHECKSUM_PARTIAL or * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial * packets in udp_gro_complete_segment. As does UDP GSO, verified by * udp_send_skb. But when those packets are looped in dev_loopback_xmit * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY. * Reset in this specific case, where PARTIAL is both correct and * required. */ if (skb->pkt_type == PACKET_LOOPBACK) skb->ip_summed = CHECKSUM_PARTIAL; /* the GSO CB lays after the UDP one, no need to save and restore any * CB fragment */ segs = __skb_gso_segment(skb, features, false); if (IS_ERR_OR_NULL(segs)) { int segs_nr = skb_shinfo(skb)->gso_segs; atomic_add(segs_nr, &sk->sk_drops); SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr); kfree_skb(skb); return NULL; } consume_skb(skb); return segs; } static inline void udp_post_segment_fix_csum(struct sk_buff *skb) { /* UDP-lite can't land here - no GRO */ WARN_ON_ONCE(UDP_SKB_CB(skb)->partial_cov); /* UDP packets generated with UDP_SEGMENT and traversing: * * UDP tunnel(xmit) -> veth (segmentation) -> veth (gro) -> UDP tunnel (rx) * * can reach an UDP socket with CHECKSUM_NONE, because * __iptunnel_pull_header() converts CHECKSUM_PARTIAL into NONE. * SKB_GSO_UDP_L4 or SKB_GSO_FRAGLIST packets with no UDP tunnel will * have a valid checksum, as the GRO engine validates the UDP csum * before the aggregation and nobody strips such info in between. * Instead of adding another check in the tunnel fastpath, we can force * a valid csum after the segmentation. * Additionally fixup the UDP CB. */ UDP_SKB_CB(skb)->cscov = skb->len; if (skb->ip_summed == CHECKSUM_NONE && !skb->csum_valid) skb->csum_valid = 1; } #ifdef CONFIG_BPF_SYSCALL struct sk_psock; int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); #endif #endif /* _UDP_H */ |
| 188 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H #include <linux/mm.h> #include <linux/percpu_counter.h> #include <linux/atomic.h> #include <uapi/linux/mman.h> /* * Arrange for legacy / undefined architecture specific flags to be * ignored by mmap handling code. */ #ifndef MAP_32BIT #define MAP_32BIT 0 #endif #ifndef MAP_ABOVE4G #define MAP_ABOVE4G 0 #endif #ifndef MAP_HUGE_2MB #define MAP_HUGE_2MB 0 #endif #ifndef MAP_HUGE_1GB #define MAP_HUGE_1GB 0 #endif #ifndef MAP_UNINITIALIZED #define MAP_UNINITIALIZED 0 #endif #ifndef MAP_SYNC #define MAP_SYNC 0 #endif /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. * * MAP_EXECUTABLE and MAP_DENYWRITE are completely ignored throughout the * kernel. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ | MAP_FIXED \ | MAP_ANONYMOUS \ | MAP_DENYWRITE \ | MAP_EXECUTABLE \ | MAP_UNINITIALIZED \ | MAP_GROWSDOWN \ | MAP_LOCKED \ | MAP_NORESERVE \ | MAP_POPULATE \ | MAP_NONBLOCK \ | MAP_STACK \ | MAP_HUGETLB \ | MAP_32BIT \ | MAP_ABOVE4G \ | MAP_HUGE_2MB \ | MAP_HUGE_1GB) extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP extern s32 vm_committed_as_batch; extern void mm_compute_batch(int overcommit_policy); #else #define vm_committed_as_batch 0 static inline void mm_compute_batch(int overcommit_policy) { } #endif unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) { vm_acct_memory(-pages); } /* * Allow architectures to handle additional protection and flag bits. The * overriding macros must be defined in the arch-specific asm/mman.h file. */ #ifndef arch_calc_vm_prot_bits #define arch_calc_vm_prot_bits(prot, pkey) 0 #endif #ifndef arch_calc_vm_flag_bits #define arch_calc_vm_flag_bits(flags) 0 #endif #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have * already been masked out. * * Returns true if the prot flags are valid */ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0; } #define arch_validate_prot arch_validate_prot #endif #ifndef arch_validate_flags /* * This is called from mmap() and mprotect() with the updated vma->vm_flags. * * Returns true if the VM_* flags are valid. */ static inline bool arch_validate_flags(unsigned long flags) { return true; } #define arch_validate_flags arch_validate_flags #endif /* * Optimisation macro. It is equivalent to: * (x & bit1) ? bit2 : 0 * but this version is faster. * ("bit1" and "bit2" must be single bits) */ #define _calc_vm_trans(x, bit1, bit2) \ ((!(bit1) || !(bit2)) ? 0 : \ ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \ : ((x) & (bit1)) / ((bit1) / (bit2)))) /* * Combine the mmap "prot" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { return _calc_vm_trans(prot, PROT_READ, VM_READ ) | _calc_vm_trans(prot, PROT_WRITE, VM_WRITE) | _calc_vm_trans(prot, PROT_EXEC, VM_EXEC) | arch_calc_vm_prot_bits(prot, pkey); } /* * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_flag_bits(unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | arch_calc_vm_flag_bits(flags); } unsigned long vm_commit_limit(void); #ifndef arch_memory_deny_write_exec_supported static inline bool arch_memory_deny_write_exec_supported(void) { return true; } #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported #endif /* * Denies creating a writable executable mapping or gaining executable permissions. * * This denies the following: * * a) mmap(PROT_WRITE | PROT_EXEC) * * b) mmap(PROT_WRITE) * mprotect(PROT_EXEC) * * c) mmap(PROT_WRITE) * mprotect(PROT_READ) * mprotect(PROT_EXEC) * * But allows the following: * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) */ static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) return true; if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) return true; return false; } #endif /* _LINUX_MMAN_H */ |
| 1 1 8 2 2 2 2 2 2 7 2 1 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 | // SPDX-License-Identifier: GPL-2.0-only /* * Vxlan vni filter for collect metadata mode * * Authors: Roopa Prabhu <roopa@nvidia.com> * */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/etherdevice.h> #include <linux/rhashtable.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/vxlan.h> #include "vxlan_private.h" static inline int vxlan_vni_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct vxlan_vni_node *vnode = ptr; __be32 vni = *(__be32 *)arg->key; return vnode->vni != vni; } const struct rhashtable_params vxlan_vni_rht_params = { .head_offset = offsetof(struct vxlan_vni_node, vnode), .key_offset = offsetof(struct vxlan_vni_node, vni), .key_len = sizeof(__be32), .nelem_hint = 3, .max_size = VXLAN_N_VID, .obj_cmpfn = vxlan_vni_cmp, .automatic_shrinking = true, }; static void vxlan_vs_add_del_vninode(struct vxlan_dev *vxlan, struct vxlan_vni_node *v, bool del) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_dev_node *node; struct vxlan_sock *vs; spin_lock(&vn->sock_lock); if (del) { if (!hlist_unhashed(&v->hlist4.hlist)) hlist_del_init_rcu(&v->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) if (!hlist_unhashed(&v->hlist6.hlist)) hlist_del_init_rcu(&v->hlist6.hlist); #endif goto out; } #if IS_ENABLED(CONFIG_IPV6) vs = rtnl_dereference(vxlan->vn6_sock); if (vs && v) { node = &v->hlist6; hlist_add_head_rcu(&node->hlist, vni_head(vs, v->vni)); } #endif vs = rtnl_dereference(vxlan->vn4_sock); if (vs && v) { node = &v->hlist4; hlist_add_head_rcu(&node->hlist, vni_head(vs, v->vni)); } out: spin_unlock(&vn->sock_lock); } void vxlan_vs_add_vnigrp(struct vxlan_dev *vxlan, struct vxlan_sock *vs, bool ipv6) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_vni_group *vg = rtnl_dereference(vxlan->vnigrp); struct vxlan_vni_node *v, *tmp; struct vxlan_dev_node *node; if (!vg) return; spin_lock(&vn->sock_lock); list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { #if IS_ENABLED(CONFIG_IPV6) if (ipv6) node = &v->hlist6; else #endif node = &v->hlist4; node->vxlan = vxlan; hlist_add_head_rcu(&node->hlist, vni_head(vs, v->vni)); } spin_unlock(&vn->sock_lock); } void vxlan_vs_del_vnigrp(struct vxlan_dev *vxlan) { struct vxlan_vni_group *vg = rtnl_dereference(vxlan->vnigrp); struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_vni_node *v, *tmp; if (!vg) return; spin_lock(&vn->sock_lock); list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { hlist_del_init_rcu(&v->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&v->hlist6.hlist); #endif } spin_unlock(&vn->sock_lock); } static void vxlan_vnifilter_stats_get(const struct vxlan_vni_node *vninode, struct vxlan_vni_stats *dest) { int i; memset(dest, 0, sizeof(*dest)); for_each_possible_cpu(i) { struct vxlan_vni_stats_pcpu *pstats; struct vxlan_vni_stats temp; unsigned int start; pstats = per_cpu_ptr(vninode->stats, i); do { start = u64_stats_fetch_begin(&pstats->syncp); memcpy(&temp, &pstats->stats, sizeof(temp)); } while (u64_stats_fetch_retry(&pstats->syncp, start)); dest->rx_packets += temp.rx_packets; dest->rx_bytes += temp.rx_bytes; dest->rx_drops += temp.rx_drops; dest->rx_errors += temp.rx_errors; dest->tx_packets += temp.tx_packets; dest->tx_bytes += temp.tx_bytes; dest->tx_drops += temp.tx_drops; dest->tx_errors += temp.tx_errors; } } static void vxlan_vnifilter_stats_add(struct vxlan_vni_node *vninode, int type, unsigned int len) { struct vxlan_vni_stats_pcpu *pstats = this_cpu_ptr(vninode->stats); u64_stats_update_begin(&pstats->syncp); switch (type) { case VXLAN_VNI_STATS_RX: pstats->stats.rx_bytes += len; pstats->stats.rx_packets++; break; case VXLAN_VNI_STATS_RX_DROPS: pstats->stats.rx_drops++; break; case VXLAN_VNI_STATS_RX_ERRORS: pstats->stats.rx_errors++; break; case VXLAN_VNI_STATS_TX: pstats->stats.tx_bytes += len; pstats->stats.tx_packets++; break; case VXLAN_VNI_STATS_TX_DROPS: pstats->stats.tx_drops++; break; case VXLAN_VNI_STATS_TX_ERRORS: pstats->stats.tx_errors++; break; } u64_stats_update_end(&pstats->syncp); } void vxlan_vnifilter_count(struct vxlan_dev *vxlan, __be32 vni, struct vxlan_vni_node *vninode, int type, unsigned int len) { struct vxlan_vni_node *vnode; if (!(vxlan->cfg.flags & VXLAN_F_VNIFILTER)) return; if (vninode) { vnode = vninode; } else { vnode = vxlan_vnifilter_lookup(vxlan, vni); if (!vnode) return; } vxlan_vnifilter_stats_add(vnode, type, len); } static u32 vnirange(struct vxlan_vni_node *vbegin, struct vxlan_vni_node *vend) { return (be32_to_cpu(vend->vni) - be32_to_cpu(vbegin->vni)); } static size_t vxlan_vnifilter_entry_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct tunnel_msg)) + nla_total_size(0) /* VXLAN_VNIFILTER_ENTRY */ + nla_total_size(sizeof(u32)) /* VXLAN_VNIFILTER_ENTRY_START */ + nla_total_size(sizeof(u32)) /* VXLAN_VNIFILTER_ENTRY_END */ + nla_total_size(sizeof(struct in6_addr));/* VXLAN_VNIFILTER_ENTRY_GROUP{6} */ } static int __vnifilter_entry_fill_stats(struct sk_buff *skb, const struct vxlan_vni_node *vbegin) { struct vxlan_vni_stats vstats; struct nlattr *vstats_attr; vstats_attr = nla_nest_start(skb, VXLAN_VNIFILTER_ENTRY_STATS); if (!vstats_attr) goto out_stats_err; vxlan_vnifilter_stats_get(vbegin, &vstats); if (nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_BYTES, vstats.rx_bytes, VNIFILTER_ENTRY_STATS_PAD) || nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_PKTS, vstats.rx_packets, VNIFILTER_ENTRY_STATS_PAD) || nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_DROPS, vstats.rx_drops, VNIFILTER_ENTRY_STATS_PAD) || nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_RX_ERRORS, vstats.rx_errors, VNIFILTER_ENTRY_STATS_PAD) || nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_BYTES, vstats.tx_bytes, VNIFILTER_ENTRY_STATS_PAD) || nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_PKTS, vstats.tx_packets, VNIFILTER_ENTRY_STATS_PAD) || nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_DROPS, vstats.tx_drops, VNIFILTER_ENTRY_STATS_PAD) || nla_put_u64_64bit(skb, VNIFILTER_ENTRY_STATS_TX_ERRORS, vstats.tx_errors, VNIFILTER_ENTRY_STATS_PAD)) goto out_stats_err; nla_nest_end(skb, vstats_attr); return 0; out_stats_err: nla_nest_cancel(skb, vstats_attr); return -EMSGSIZE; } static bool vxlan_fill_vni_filter_entry(struct sk_buff *skb, struct vxlan_vni_node *vbegin, struct vxlan_vni_node *vend, bool fill_stats) { struct nlattr *ventry; u32 vs = be32_to_cpu(vbegin->vni); u32 ve = 0; if (vbegin != vend) ve = be32_to_cpu(vend->vni); ventry = nla_nest_start(skb, VXLAN_VNIFILTER_ENTRY); if (!ventry) return false; if (nla_put_u32(skb, VXLAN_VNIFILTER_ENTRY_START, vs)) goto out_err; if (ve && nla_put_u32(skb, VXLAN_VNIFILTER_ENTRY_END, ve)) goto out_err; if (!vxlan_addr_any(&vbegin->remote_ip)) { if (vbegin->remote_ip.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, VXLAN_VNIFILTER_ENTRY_GROUP, vbegin->remote_ip.sin.sin_addr.s_addr)) goto out_err; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, VXLAN_VNIFILTER_ENTRY_GROUP6, &vbegin->remote_ip.sin6.sin6_addr)) goto out_err; #endif } } if (fill_stats && __vnifilter_entry_fill_stats(skb, vbegin)) goto out_err; nla_nest_end(skb, ventry); return true; out_err: nla_nest_cancel(skb, ventry); return false; } static void vxlan_vnifilter_notify(const struct vxlan_dev *vxlan, struct vxlan_vni_node *vninode, int cmd) { struct tunnel_msg *tmsg; struct sk_buff *skb; struct nlmsghdr *nlh; struct net *net = dev_net(vxlan->dev); int err = -ENOBUFS; skb = nlmsg_new(vxlan_vnifilter_entry_nlmsg_size(), GFP_KERNEL); if (!skb) goto out_err; err = -EMSGSIZE; nlh = nlmsg_put(skb, 0, 0, cmd, sizeof(*tmsg), 0); if (!nlh) goto out_err; tmsg = nlmsg_data(nlh); memset(tmsg, 0, sizeof(*tmsg)); tmsg->family = AF_BRIDGE; tmsg->ifindex = vxlan->dev->ifindex; if (!vxlan_fill_vni_filter_entry(skb, vninode, vninode, false)) goto out_err; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_TUNNEL, NULL, GFP_KERNEL); return; out_err: rtnl_set_sk_err(net, RTNLGRP_TUNNEL, err); kfree_skb(skb); } static int vxlan_vnifilter_dump_dev(const struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct vxlan_vni_node *tmp, *v, *vbegin = NULL, *vend = NULL; struct vxlan_dev *vxlan = netdev_priv(dev); struct tunnel_msg *new_tmsg, *tmsg; int idx = 0, s_idx = cb->args[1]; struct vxlan_vni_group *vg; struct nlmsghdr *nlh; bool dump_stats; int err = 0; if (!(vxlan->cfg.flags & VXLAN_F_VNIFILTER)) return -EINVAL; /* RCU needed because of the vni locking rules (rcu || rtnl) */ vg = rcu_dereference(vxlan->vnigrp); if (!vg || !vg->num_vnis) return 0; tmsg = nlmsg_data(cb->nlh); dump_stats = !!(tmsg->flags & TUNNEL_MSG_FLAG_STATS); nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWTUNNEL, sizeof(*new_tmsg), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; new_tmsg = nlmsg_data(nlh); memset(new_tmsg, 0, sizeof(*new_tmsg)); new_tmsg->family = PF_BRIDGE; new_tmsg->ifindex = dev->ifindex; list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { if (idx < s_idx) { idx++; continue; } if (!vbegin) { vbegin = v; vend = v; continue; } if (!dump_stats && vnirange(vend, v) == 1 && vxlan_addr_equal(&v->remote_ip, &vend->remote_ip)) { goto update_end; } else { if (!vxlan_fill_vni_filter_entry(skb, vbegin, vend, dump_stats)) { err = -EMSGSIZE; break; } idx += vnirange(vbegin, vend) + 1; vbegin = v; } update_end: vend = v; } if (!err && vbegin) { if (!vxlan_fill_vni_filter_entry(skb, vbegin, vend, dump_stats)) err = -EMSGSIZE; } cb->args[1] = err ? idx : 0; nlmsg_end(skb, nlh); return err; } static int vxlan_vnifilter_dump(struct sk_buff *skb, struct netlink_callback *cb) { int idx = 0, err = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); struct tunnel_msg *tmsg; struct net_device *dev; tmsg = nlmsg_data(cb->nlh); if (tmsg->flags & ~TUNNEL_MSG_VALID_USER_FLAGS) { NL_SET_ERR_MSG(cb->extack, "Invalid tunnelmsg flags in ancillary header"); return -EINVAL; } rcu_read_lock(); if (tmsg->ifindex) { dev = dev_get_by_index_rcu(net, tmsg->ifindex); if (!dev) { err = -ENODEV; goto out_err; } if (!netif_is_vxlan(dev)) { NL_SET_ERR_MSG(cb->extack, "The device is not a vxlan device"); err = -EINVAL; goto out_err; } err = vxlan_vnifilter_dump_dev(dev, skb, cb); /* if the dump completed without an error we return 0 here */ if (err != -EMSGSIZE) goto out_err; } else { for_each_netdev_rcu(net, dev) { if (!netif_is_vxlan(dev)) continue; if (idx < s_idx) goto skip; err = vxlan_vnifilter_dump_dev(dev, skb, cb); if (err == -EMSGSIZE) break; skip: idx++; } } cb->args[0] = idx; rcu_read_unlock(); return skb->len; out_err: rcu_read_unlock(); return err; } static const struct nla_policy vni_filter_entry_policy[VXLAN_VNIFILTER_ENTRY_MAX + 1] = { [VXLAN_VNIFILTER_ENTRY_START] = { .type = NLA_U32 }, [VXLAN_VNIFILTER_ENTRY_END] = { .type = NLA_U32 }, [VXLAN_VNIFILTER_ENTRY_GROUP] = { .type = NLA_BINARY, .len = sizeof_field(struct iphdr, daddr) }, [VXLAN_VNIFILTER_ENTRY_GROUP6] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr) }, }; static const struct nla_policy vni_filter_policy[VXLAN_VNIFILTER_MAX + 1] = { [VXLAN_VNIFILTER_ENTRY] = { .type = NLA_NESTED }, }; static int vxlan_update_default_fdb_entry(struct vxlan_dev *vxlan, __be32 vni, union vxlan_addr *old_remote_ip, union vxlan_addr *remote_ip, struct netlink_ext_ack *extack) { struct vxlan_rdst *dst = &vxlan->default_dst; u32 hash_index; int err = 0; hash_index = fdb_head_index(vxlan, all_zeros_mac, vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); if (remote_ip && !vxlan_addr_any(remote_ip)) { err = vxlan_fdb_update(vxlan, all_zeros_mac, remote_ip, NUD_REACHABLE | NUD_PERMANENT, NLM_F_APPEND | NLM_F_CREATE, vxlan->cfg.dst_port, vni, vni, dst->remote_ifindex, NTF_SELF, 0, true, extack); if (err) { spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } } if (old_remote_ip && !vxlan_addr_any(old_remote_ip)) { __vxlan_fdb_delete(vxlan, all_zeros_mac, *old_remote_ip, vxlan->cfg.dst_port, vni, vni, dst->remote_ifindex, true); } spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } static int vxlan_vni_update_group(struct vxlan_dev *vxlan, struct vxlan_vni_node *vninode, union vxlan_addr *group, bool create, bool *changed, struct netlink_ext_ack *extack) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_rdst *dst = &vxlan->default_dst; union vxlan_addr *newrip = NULL, *oldrip = NULL; union vxlan_addr old_remote_ip; int ret = 0; memcpy(&old_remote_ip, &vninode->remote_ip, sizeof(old_remote_ip)); /* if per vni remote ip is not present use vxlan dev * default dst remote ip for fdb entry */ if (group && !vxlan_addr_any(group)) { newrip = group; } else { if (!vxlan_addr_any(&dst->remote_ip)) newrip = &dst->remote_ip; } /* if old rip exists, and no newrip, * explicitly delete old rip */ if (!newrip && !vxlan_addr_any(&old_remote_ip)) oldrip = &old_remote_ip; if (!newrip && !oldrip) return 0; if (!create && oldrip && newrip && vxlan_addr_equal(oldrip, newrip)) return 0; ret = vxlan_update_default_fdb_entry(vxlan, vninode->vni, oldrip, newrip, extack); if (ret) goto out; if (group) memcpy(&vninode->remote_ip, group, sizeof(vninode->remote_ip)); if (vxlan->dev->flags & IFF_UP) { if (vxlan_addr_multicast(&old_remote_ip) && !vxlan_group_used(vn, vxlan, vninode->vni, &old_remote_ip, vxlan->default_dst.remote_ifindex)) { ret = vxlan_igmp_leave(vxlan, &old_remote_ip, 0); if (ret) goto out; } if (vxlan_addr_multicast(&vninode->remote_ip)) { ret = vxlan_igmp_join(vxlan, &vninode->remote_ip, 0); if (ret == -EADDRINUSE) ret = 0; if (ret) goto out; } } *changed = true; return 0; out: return ret; } int vxlan_vnilist_update_group(struct vxlan_dev *vxlan, union vxlan_addr *old_remote_ip, union vxlan_addr *new_remote_ip, struct netlink_ext_ack *extack) { struct list_head *headp, *hpos; struct vxlan_vni_group *vg; struct vxlan_vni_node *vent; int ret; vg = rtnl_dereference(vxlan->vnigrp); headp = &vg->vni_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct vxlan_vni_node, vlist); if (vxlan_addr_any(&vent->remote_ip)) { ret = vxlan_update_default_fdb_entry(vxlan, vent->vni, old_remote_ip, new_remote_ip, extack); if (ret) return ret; } } return 0; } static void vxlan_vni_delete_group(struct vxlan_dev *vxlan, struct vxlan_vni_node *vninode) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_rdst *dst = &vxlan->default_dst; /* if per vni remote_ip not present, delete the * default dst remote_ip previously added for this vni */ if (!vxlan_addr_any(&vninode->remote_ip) || !vxlan_addr_any(&dst->remote_ip)) __vxlan_fdb_delete(vxlan, all_zeros_mac, (vxlan_addr_any(&vninode->remote_ip) ? dst->remote_ip : vninode->remote_ip), vxlan->cfg.dst_port, vninode->vni, vninode->vni, dst->remote_ifindex, true); if (vxlan->dev->flags & IFF_UP) { if (vxlan_addr_multicast(&vninode->remote_ip) && !vxlan_group_used(vn, vxlan, vninode->vni, &vninode->remote_ip, dst->remote_ifindex)) { vxlan_igmp_leave(vxlan, &vninode->remote_ip, 0); } } } static int vxlan_vni_update(struct vxlan_dev *vxlan, struct vxlan_vni_group *vg, __be32 vni, union vxlan_addr *group, bool *changed, struct netlink_ext_ack *extack) { struct vxlan_vni_node *vninode; int ret; vninode = rhashtable_lookup_fast(&vg->vni_hash, &vni, vxlan_vni_rht_params); if (!vninode) return 0; ret = vxlan_vni_update_group(vxlan, vninode, group, false, changed, extack); if (ret) return ret; if (changed) vxlan_vnifilter_notify(vxlan, vninode, RTM_NEWTUNNEL); return 0; } static void __vxlan_vni_add_list(struct vxlan_vni_group *vg, struct vxlan_vni_node *v) { struct list_head *headp, *hpos; struct vxlan_vni_node *vent; headp = &vg->vni_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct vxlan_vni_node, vlist); if (be32_to_cpu(v->vni) < be32_to_cpu(vent->vni)) continue; else break; } list_add_rcu(&v->vlist, hpos); vg->num_vnis++; } static void __vxlan_vni_del_list(struct vxlan_vni_group *vg, struct vxlan_vni_node *v) { list_del_rcu(&v->vlist); vg->num_vnis--; } static struct vxlan_vni_node *vxlan_vni_alloc(struct vxlan_dev *vxlan, __be32 vni) { struct vxlan_vni_node *vninode; vninode = kzalloc(sizeof(*vninode), GFP_KERNEL); if (!vninode) return NULL; vninode->stats = netdev_alloc_pcpu_stats(struct vxlan_vni_stats_pcpu); if (!vninode->stats) { kfree(vninode); return NULL; } vninode->vni = vni; vninode->hlist4.vxlan = vxlan; #if IS_ENABLED(CONFIG_IPV6) vninode->hlist6.vxlan = vxlan; #endif return vninode; } static void vxlan_vni_free(struct vxlan_vni_node *vninode) { free_percpu(vninode->stats); kfree(vninode); } static int vxlan_vni_add(struct vxlan_dev *vxlan, struct vxlan_vni_group *vg, u32 vni, union vxlan_addr *group, struct netlink_ext_ack *extack) { struct vxlan_vni_node *vninode; __be32 v = cpu_to_be32(vni); bool changed = false; int err = 0; if (vxlan_vnifilter_lookup(vxlan, v)) return vxlan_vni_update(vxlan, vg, v, group, &changed, extack); err = vxlan_vni_in_use(vxlan->net, vxlan, &vxlan->cfg, v); if (err) { NL_SET_ERR_MSG(extack, "VNI in use"); return err; } vninode = vxlan_vni_alloc(vxlan, v); if (!vninode) return -ENOMEM; err = rhashtable_lookup_insert_fast(&vg->vni_hash, &vninode->vnode, vxlan_vni_rht_params); if (err) { vxlan_vni_free(vninode); return err; } __vxlan_vni_add_list(vg, vninode); if (vxlan->dev->flags & IFF_UP) vxlan_vs_add_del_vninode(vxlan, vninode, false); err = vxlan_vni_update_group(vxlan, vninode, group, true, &changed, extack); if (changed) vxlan_vnifilter_notify(vxlan, vninode, RTM_NEWTUNNEL); return err; } static void vxlan_vni_node_rcu_free(struct rcu_head *rcu) { struct vxlan_vni_node *v; v = container_of(rcu, struct vxlan_vni_node, rcu); vxlan_vni_free(v); } static int vxlan_vni_del(struct vxlan_dev *vxlan, struct vxlan_vni_group *vg, u32 vni, struct netlink_ext_ack *extack) { struct vxlan_vni_node *vninode; __be32 v = cpu_to_be32(vni); int err = 0; vg = rtnl_dereference(vxlan->vnigrp); vninode = rhashtable_lookup_fast(&vg->vni_hash, &v, vxlan_vni_rht_params); if (!vninode) { err = -ENOENT; goto out; } vxlan_vni_delete_group(vxlan, vninode); err = rhashtable_remove_fast(&vg->vni_hash, &vninode->vnode, vxlan_vni_rht_params); if (err) goto out; __vxlan_vni_del_list(vg, vninode); vxlan_vnifilter_notify(vxlan, vninode, RTM_DELTUNNEL); if (vxlan->dev->flags & IFF_UP) vxlan_vs_add_del_vninode(vxlan, vninode, true); call_rcu(&vninode->rcu, vxlan_vni_node_rcu_free); return 0; out: return err; } static int vxlan_vni_add_del(struct vxlan_dev *vxlan, __u32 start_vni, __u32 end_vni, union vxlan_addr *group, int cmd, struct netlink_ext_ack *extack) { struct vxlan_vni_group *vg; int v, err = 0; vg = rtnl_dereference(vxlan->vnigrp); for (v = start_vni; v <= end_vni; v++) { switch (cmd) { case RTM_NEWTUNNEL: err = vxlan_vni_add(vxlan, vg, v, group, extack); break; case RTM_DELTUNNEL: err = vxlan_vni_del(vxlan, vg, v, extack); break; default: err = -EOPNOTSUPP; break; } if (err) goto out; } return 0; out: return err; } static int vxlan_process_vni_filter(struct vxlan_dev *vxlan, struct nlattr *nlvnifilter, int cmd, struct netlink_ext_ack *extack) { struct nlattr *vattrs[VXLAN_VNIFILTER_ENTRY_MAX + 1]; u32 vni_start = 0, vni_end = 0; union vxlan_addr group; int err; err = nla_parse_nested(vattrs, VXLAN_VNIFILTER_ENTRY_MAX, nlvnifilter, vni_filter_entry_policy, extack); if (err) return err; if (vattrs[VXLAN_VNIFILTER_ENTRY_START]) { vni_start = nla_get_u32(vattrs[VXLAN_VNIFILTER_ENTRY_START]); vni_end = vni_start; } if (vattrs[VXLAN_VNIFILTER_ENTRY_END]) vni_end = nla_get_u32(vattrs[VXLAN_VNIFILTER_ENTRY_END]); if (!vni_start && !vni_end) { NL_SET_ERR_MSG_ATTR(extack, nlvnifilter, "vni start nor end found in vni entry"); return -EINVAL; } if (vattrs[VXLAN_VNIFILTER_ENTRY_GROUP]) { group.sin.sin_addr.s_addr = nla_get_in_addr(vattrs[VXLAN_VNIFILTER_ENTRY_GROUP]); group.sa.sa_family = AF_INET; } else if (vattrs[VXLAN_VNIFILTER_ENTRY_GROUP6]) { group.sin6.sin6_addr = nla_get_in6_addr(vattrs[VXLAN_VNIFILTER_ENTRY_GROUP6]); group.sa.sa_family = AF_INET6; } else { memset(&group, 0, sizeof(group)); } if (vxlan_addr_multicast(&group) && !vxlan->default_dst.remote_ifindex) { NL_SET_ERR_MSG(extack, "Local interface required for multicast remote group"); return -EINVAL; } err = vxlan_vni_add_del(vxlan, vni_start, vni_end, &group, cmd, extack); if (err) return err; return 0; } void vxlan_vnigroup_uninit(struct vxlan_dev *vxlan) { struct vxlan_vni_node *v, *tmp; struct vxlan_vni_group *vg; vg = rtnl_dereference(vxlan->vnigrp); list_for_each_entry_safe(v, tmp, &vg->vni_list, vlist) { rhashtable_remove_fast(&vg->vni_hash, &v->vnode, vxlan_vni_rht_params); hlist_del_init_rcu(&v->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&v->hlist6.hlist); #endif __vxlan_vni_del_list(vg, v); vxlan_vnifilter_notify(vxlan, v, RTM_DELTUNNEL); call_rcu(&v->rcu, vxlan_vni_node_rcu_free); } rhashtable_destroy(&vg->vni_hash); kfree(vg); } int vxlan_vnigroup_init(struct vxlan_dev *vxlan) { struct vxlan_vni_group *vg; int ret; vg = kzalloc(sizeof(*vg), GFP_KERNEL); if (!vg) return -ENOMEM; ret = rhashtable_init(&vg->vni_hash, &vxlan_vni_rht_params); if (ret) { kfree(vg); return ret; } INIT_LIST_HEAD(&vg->vni_list); rcu_assign_pointer(vxlan->vnigrp, vg); return 0; } static int vxlan_vnifilter_process(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct tunnel_msg *tmsg; struct vxlan_dev *vxlan; struct net_device *dev; struct nlattr *attr; int err, vnis = 0; int rem; /* this should validate the header and check for remaining bytes */ err = nlmsg_parse(nlh, sizeof(*tmsg), NULL, VXLAN_VNIFILTER_MAX, vni_filter_policy, extack); if (err < 0) return err; tmsg = nlmsg_data(nlh); dev = __dev_get_by_index(net, tmsg->ifindex); if (!dev) return -ENODEV; if (!netif_is_vxlan(dev)) { NL_SET_ERR_MSG_MOD(extack, "The device is not a vxlan device"); return -EINVAL; } vxlan = netdev_priv(dev); if (!(vxlan->cfg.flags & VXLAN_F_VNIFILTER)) return -EOPNOTSUPP; nlmsg_for_each_attr(attr, nlh, sizeof(*tmsg), rem) { switch (nla_type(attr)) { case VXLAN_VNIFILTER_ENTRY: err = vxlan_process_vni_filter(vxlan, attr, nlh->nlmsg_type, extack); break; default: continue; } vnis++; if (err) break; } if (!vnis) { NL_SET_ERR_MSG_MOD(extack, "No vnis found to process"); err = -EINVAL; } return err; } void vxlan_vnifilter_init(void) { rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_GETTUNNEL, NULL, vxlan_vnifilter_dump, 0); rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_NEWTUNNEL, vxlan_vnifilter_process, NULL, 0); rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_DELTUNNEL, vxlan_vnifilter_process, NULL, 0); } void vxlan_vnifilter_uninit(void) { rtnl_unregister(PF_BRIDGE, RTM_GETTUNNEL); rtnl_unregister(PF_BRIDGE, RTM_NEWTUNNEL); rtnl_unregister(PF_BRIDGE, RTM_DELTUNNEL); } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 | // SPDX-License-Identifier: GPL-2.0-only /* * 802_3 * * Author: * Chris Vitale csv@bluetail.com * * May 2003 * */ #include <linux/module.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_bridge/ebtables.h> #include <linux/skbuff.h> #include <uapi/linux/netfilter_bridge/ebt_802_3.h> static struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb) { return (struct ebt_802_3_hdr *)skb_mac_header(skb); } static bool ebt_802_3_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_802_3_info *info = par->matchinfo; const struct ebt_802_3_hdr *hdr = ebt_802_3_hdr(skb); __be16 type = hdr->llc.ui.ctrl & IS_UI ? hdr->llc.ui.type : hdr->llc.ni.type; if (info->bitmask & EBT_802_3_SAP) { if (NF_INVF(info, EBT_802_3_SAP, info->sap != hdr->llc.ui.ssap)) return false; if (NF_INVF(info, EBT_802_3_SAP, info->sap != hdr->llc.ui.dsap)) return false; } if (info->bitmask & EBT_802_3_TYPE) { if (!(hdr->llc.ui.dsap == CHECK_TYPE && hdr->llc.ui.ssap == CHECK_TYPE)) return false; if (NF_INVF(info, EBT_802_3_TYPE, info->type != type)) return false; } return true; } static int ebt_802_3_mt_check(const struct xt_mtchk_param *par) { const struct ebt_802_3_info *info = par->matchinfo; if (info->bitmask & ~EBT_802_3_MASK || info->invflags & ~EBT_802_3_MASK) return -EINVAL; return 0; } static struct xt_match ebt_802_3_mt_reg __read_mostly = { .name = "802_3", .revision = 0, .family = NFPROTO_BRIDGE, .match = ebt_802_3_mt, .checkentry = ebt_802_3_mt_check, .matchsize = sizeof(struct ebt_802_3_info), .me = THIS_MODULE, }; static int __init ebt_802_3_init(void) { return xt_register_match(&ebt_802_3_mt_reg); } static void __exit ebt_802_3_fini(void) { xt_unregister_match(&ebt_802_3_mt_reg); } module_init(ebt_802_3_init); module_exit(ebt_802_3_fini); MODULE_DESCRIPTION("Ebtables: DSAP/SSAP field and SNAP type matching"); MODULE_LICENSE("GPL"); |
| 13 72 7 7 59 59 6 1 46 7 5 2 4 1 7 7 5 12 8 4 51 52 8 8 44 44 48 2 44 2 1 94 94 94 94 94 9 23 23 94 23 23 94 69 41 58 35 35 23 23 23 1 1 1 35 16 148 149 140 1 16 113 1 113 36 36 12 31 31 61 12 48 41 41 7 7 7 7 7 9 9 9 2 2 160 64 2 2 2 2 1 2 2 2 2 160 73 77 160 65 159 160 160 160 2 2 160 62 61 159 156 74 72 160 162 162 160 136 1 137 66 66 66 66 41 27 40 40 40 11 11 11 8 7 1 2 2 2 2 1 2 2 2 2 2 2 2 2 1 245 2 246 1 247 245 246 246 135 3 35 139 138 139 113 36 36 29 98 58 139 138 35 46 44 1 7 7 8 247 247 247 246 53 53 53 352 351 353 15 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2017 - 2019, Intel Corporation. */ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> #include <crypto/sha2.h> #include <crypto/utils.h> #include <net/sock.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/protocol.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/ip6_route.h> #include <net/transp_v6.h> #endif #include <net/mptcp.h> #include "protocol.h" #include "mib.h" #include <trace/events/mptcp.h> #include <trace/events/sock.h> static void mptcp_subflow_ops_undo_override(struct sock *ssk); static void SUBFLOW_REQ_INC_STATS(struct request_sock *req, enum linux_mptcp_mib_field field) { MPTCP_INC_STATS(sock_net(req_to_sk(req)), field); } static void subflow_req_destructor(struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); pr_debug("subflow_req=%p\n", subflow_req); if (subflow_req->msk) sock_put((struct sock *)subflow_req->msk); mptcp_token_destroy_request(req); } static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2, void *hmac) { u8 msg[8]; put_unaligned_be32(nonce1, &msg[0]); put_unaligned_be32(nonce2, &msg[4]); mptcp_crypto_hmac_sha(key1, key2, msg, 8, hmac); } static bool mptcp_can_accept_new_subflow(const struct mptcp_sock *msk) { return mptcp_is_fully_established((void *)msk) && ((mptcp_pm_is_userspace(msk) && mptcp_userspace_pm_active(msk)) || READ_ONCE(msk->pm.accept_subflow)); } /* validate received token and create truncated hmac and nonce for SYN-ACK */ static void subflow_req_create_thmac(struct mptcp_subflow_request_sock *subflow_req) { struct mptcp_sock *msk = subflow_req->msk; u8 hmac[SHA256_DIGEST_SIZE]; get_random_bytes(&subflow_req->local_nonce, sizeof(u32)); subflow_generate_hmac(READ_ONCE(msk->local_key), READ_ONCE(msk->remote_key), subflow_req->local_nonce, subflow_req->remote_nonce, hmac); subflow_req->thmac = get_unaligned_be64(hmac); } static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct mptcp_sock *msk; int local_id; msk = mptcp_token_get_sock(sock_net(req_to_sk(req)), subflow_req->token); if (!msk) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN); return NULL; } local_id = mptcp_pm_get_local_id(msk, (struct sock_common *)req); if (local_id < 0) { sock_put((struct sock *)msk); return NULL; } subflow_req->local_id = local_id; subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req); return msk; } static void subflow_init_req(struct request_sock *req, const struct sock *sk_listener) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); subflow_req->mp_capable = 0; subflow_req->mp_join = 0; subflow_req->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk_listener)); subflow_req->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk_listener)); subflow_req->msk = NULL; mptcp_token_init_request(req); } static bool subflow_use_different_sport(struct mptcp_sock *msk, const struct sock *sk) { return inet_sk(sk)->inet_sport != inet_sk((struct sock *)msk)->inet_sport; } static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason) { struct mptcp_ext *mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (mpext) { memset(mpext, 0, sizeof(*mpext)); mpext->reset_reason = reason; } } /* Init mptcp request socket. * * Returns an error code if a JOIN has failed and a TCP reset * should be sent. */ static int subflow_check_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb) { struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct mptcp_options_received mp_opt; bool opt_mp_capable, opt_mp_join; pr_debug("subflow_req=%p, listener=%p\n", subflow_req, listener); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of * TCP option space. */ if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info)) { subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP); return -EINVAL; } #endif mptcp_get_options(skb, &mp_opt); opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYN); opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYN); if (opt_mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); if (opt_mp_join) return 0; } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); if (mp_opt.backup) SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); } if (opt_mp_capable && listener->request_mptcp) { int err, retries = MPTCP_TOKEN_MAX_RETRIES; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; again: do { get_random_bytes(&subflow_req->local_key, sizeof(subflow_req->local_key)); } while (subflow_req->local_key == 0); if (unlikely(req->syncookie)) { mptcp_crypto_key_sha(subflow_req->local_key, &subflow_req->token, &subflow_req->idsn); if (mptcp_token_exists(subflow_req->token)) { if (retries-- > 0) goto again; SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT); } else { subflow_req->mp_capable = 1; } return 0; } err = mptcp_token_new_request(req); if (err == 0) subflow_req->mp_capable = 1; else if (retries-- > 0) goto again; else SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT); } else if (opt_mp_join && listener->request_mptcp) { subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; subflow_req->mp_join = 1; subflow_req->backup = mp_opt.backup; subflow_req->remote_id = mp_opt.join_id; subflow_req->token = mp_opt.token; subflow_req->remote_nonce = mp_opt.nonce; subflow_req->msk = subflow_token_join_request(req); /* Can't fall back to TCP in this case. */ if (!subflow_req->msk) { subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP); return -EPERM; } if (subflow_use_different_sport(subflow_req->msk, sk_listener)) { pr_debug("syn inet_sport=%d %d\n", ntohs(inet_sk(sk_listener)->inet_sport), ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); return -EPERM; } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX); } subflow_req_create_thmac(subflow_req); if (unlikely(req->syncookie)) { if (!mptcp_can_accept_new_subflow(subflow_req->msk)) { subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); return -EPERM; } subflow_init_req_cookie_join_save(subflow_req, skb); } pr_debug("token=%u, remote_nonce=%u msk=%p\n", subflow_req->token, subflow_req->remote_nonce, subflow_req->msk); } return 0; } int mptcp_subflow_init_cookie_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb) { struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct mptcp_options_received mp_opt; bool opt_mp_capable, opt_mp_join; int err; subflow_init_req(req, sk_listener); mptcp_get_options(skb, &mp_opt); opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK); opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK); if (opt_mp_capable && opt_mp_join) return -EINVAL; if (opt_mp_capable && listener->request_mptcp) { if (mp_opt.sndr_key == 0) return -EINVAL; subflow_req->local_key = mp_opt.rcvr_key; err = mptcp_token_new_request(req); if (err) return err; subflow_req->mp_capable = 1; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1; } else if (opt_mp_join && listener->request_mptcp) { if (!mptcp_token_join_cookie_init_state(subflow_req, skb)) return -EINVAL; subflow_req->mp_join = 1; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1; } return 0; } EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req); static enum sk_rst_reason mptcp_get_rst_reason(const struct sk_buff *skb) { const struct mptcp_ext *mpext = mptcp_get_ext(skb); if (!mpext) return SK_RST_REASON_NOT_SPECIFIED; return sk_rst_convert_mptcp_reason(mpext->reset_reason); } static struct dst_entry *subflow_v4_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req, u32 tw_isn) { struct dst_entry *dst; int err; tcp_rsk(req)->is_mptcp = 1; subflow_init_req(req, sk); dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req, tw_isn); if (!dst) return NULL; err = subflow_check_req(req, sk, skb); if (err == 0) return dst; dst_release(dst); if (!req->syncookie) tcp_request_sock_ops.send_reset(sk, skb, mptcp_get_rst_reason(skb)); return NULL; } static void subflow_prep_synack(const struct sock *sk, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct inet_request_sock *ireq = inet_rsk(req); /* clear tstamp_ok, as needed depending on cookie */ if (foc && foc->len > -1) ireq->tstamp_ok = 0; if (synack_type == TCP_SYNACK_FASTOPEN) mptcp_fastopen_subflow_synack_set_params(subflow, req); } static int subflow_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { subflow_prep_synack(sk, req, foc, synack_type); return tcp_request_sock_ipv4_ops.send_synack(sk, dst, fl, req, foc, synack_type, syn_skb); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) static int subflow_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { subflow_prep_synack(sk, req, foc, synack_type); return tcp_request_sock_ipv6_ops.send_synack(sk, dst, fl, req, foc, synack_type, syn_skb); } static struct dst_entry *subflow_v6_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req, u32 tw_isn) { struct dst_entry *dst; int err; tcp_rsk(req)->is_mptcp = 1; subflow_init_req(req, sk); dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req, tw_isn); if (!dst) return NULL; err = subflow_check_req(req, sk, skb); if (err == 0) return dst; dst_release(dst); if (!req->syncookie) tcp6_request_sock_ops.send_reset(sk, skb, mptcp_get_rst_reason(skb)); return NULL; } #endif /* validate received truncated hmac and create hmac for third ACK */ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow) { u8 hmac[SHA256_DIGEST_SIZE]; u64 thmac; subflow_generate_hmac(subflow->remote_key, subflow->local_key, subflow->remote_nonce, subflow->local_nonce, hmac); thmac = get_unaligned_be64(hmac); pr_debug("subflow=%p, token=%u, thmac=%llu, subflow->thmac=%llu\n", subflow, subflow->token, thmac, subflow->thmac); return thmac == subflow->thmac; } void mptcp_subflow_reset(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; /* mptcp_mp_fail_no_response() can reach here on an already closed * socket */ if (ssk->sk_state == TCP_CLOSE) return; /* must hold: tcp_done() could drop last reference on parent */ sock_hold(sk); mptcp_send_active_reset_reason(ssk); tcp_done(ssk); if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags)) mptcp_schedule_work(sk); sock_put(sk); } static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct sock *sk) { return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport; } void __mptcp_sync_state(struct sock *sk, int state) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk = msk->first; subflow = mptcp_subflow_ctx(ssk); __mptcp_propagate_sndbuf(sk, ssk); if (!msk->rcvspace_init) mptcp_rcv_space_init(msk, ssk); if (sk->sk_state == TCP_SYN_SENT) { /* subflow->idsn is always available is TCP_SYN_SENT state, * even for the FASTOPEN scenarios */ WRITE_ONCE(msk->write_seq, subflow->idsn + 1); WRITE_ONCE(msk->snd_nxt, msk->write_seq); mptcp_set_state(sk, state); sk->sk_state_change(sk); } } static void subflow_set_remote_key(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt) { /* active MPC subflow will reach here multiple times: * at subflow_finish_connect() time and at 4th ack time */ if (subflow->remote_key_valid) return; subflow->remote_key_valid = 1; subflow->remote_key = mp_opt->sndr_key; mptcp_crypto_key_sha(subflow->remote_key, NULL, &subflow->iasn); subflow->iasn++; WRITE_ONCE(msk->remote_key, subflow->remote_key); WRITE_ONCE(msk->ack_seq, subflow->iasn); WRITE_ONCE(msk->can_ack, true); atomic64_set(&msk->rcv_wnd_sent, subflow->iasn); } static void mptcp_propagate_state(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt) { struct mptcp_sock *msk = mptcp_sk(sk); mptcp_data_lock(sk); if (mp_opt) { /* Options are available only in the non fallback cases * avoid updating rx path fields otherwise */ WRITE_ONCE(msk->snd_una, subflow->idsn + 1); WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); subflow_set_remote_key(msk, subflow, mp_opt); } if (!sock_owned_by_user(sk)) { __mptcp_sync_state(sk, ssk->sk_state); } else { msk->pending_state = ssk->sk_state; __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); } mptcp_data_unlock(sk); } static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_options_received mp_opt; struct sock *parent = subflow->conn; struct mptcp_sock *msk; subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); /* be sure no special action on any packet other than syn-ack */ if (subflow->conn_finished) return; msk = mptcp_sk(parent); subflow->rel_write_seq = 1; subflow->conn_finished = 1; subflow->ssn_offset = TCP_SKB_CB(skb)->seq; pr_debug("subflow=%p synack seq=%x\n", subflow, subflow->ssn_offset); mptcp_get_options(skb, &mp_opt); if (subflow->request_mptcp) { if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYNACK)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEFALLBACK); mptcp_do_fallback(sk); pr_fallback(msk); goto fallback; } if (mp_opt.suboptions & OPTION_MPTCP_CSUMREQD) WRITE_ONCE(msk->csum_enabled, true); if (mp_opt.deny_join_id0) WRITE_ONCE(msk->pm.remote_deny_join_id0, true); subflow->mp_capable = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); mptcp_active_enable(parent); mptcp_propagate_state(parent, sk, subflow, &mp_opt); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYNACK)) { subflow->reset_reason = MPTCP_RST_EMPTCP; goto do_reset; } subflow->backup = mp_opt.backup; subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; WRITE_ONCE(subflow->remote_id, mp_opt.join_id); pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d\n", subflow, subflow->thmac, subflow->remote_nonce, subflow->backup); if (!subflow_thmac_valid(subflow)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC); subflow->reset_reason = MPTCP_RST_EMPTCP; goto do_reset; } if (!mptcp_finish_join(sk)) goto do_reset; subflow_generate_hmac(subflow->local_key, subflow->remote_key, subflow->local_nonce, subflow->remote_nonce, hmac); memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN); subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); if (subflow->backup) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX); if (subflow_use_different_dport(msk, sk)) { pr_debug("synack inet_dport=%d %d\n", ntohs(inet_sk(sk)->inet_dport), ntohs(inet_sk(parent)->inet_dport)); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX); } } else if (mptcp_check_fallback(sk)) { /* It looks like MPTCP is blocked, while TCP is not */ if (subflow->mpc_drop) mptcp_active_disable(parent); fallback: mptcp_propagate_state(parent, sk, subflow, NULL); } return; do_reset: subflow->reset_transient = 0; mptcp_subflow_reset(sk); } static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id) { WARN_ON_ONCE(local_id < 0 || local_id > 255); WRITE_ONCE(subflow->local_id, local_id); } static int subflow_chk_local_id(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); int err; if (likely(subflow->local_id >= 0)) return 0; err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk); if (err < 0) return err; subflow_set_local_id(subflow, err); subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk); return 0; } static int subflow_rebuild_header(struct sock *sk) { int err = subflow_chk_local_id(sk); if (unlikely(err < 0)) return err; return inet_sk_rebuild_header(sk); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) static int subflow_v6_rebuild_header(struct sock *sk) { int err = subflow_chk_local_id(sk); if (unlikely(err < 0)) return err; return inet6_sk_rebuild_header(sk); } #endif static struct request_sock_ops mptcp_subflow_v4_request_sock_ops __ro_after_init; static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init; static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); pr_debug("subflow=%p\n", subflow); /* Never answer to SYNs sent to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; return tcp_conn_request(&mptcp_subflow_v4_request_sock_ops, &subflow_request_sock_ipv4_ops, sk, skb); drop: tcp_listendrop(sk); return 0; } static void subflow_v4_req_destructor(struct request_sock *req) { subflow_req_destructor(req); tcp_request_sock_ops.destructor(req); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) static struct request_sock_ops mptcp_subflow_v6_request_sock_ops __ro_after_init; static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init; static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init; static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init; static struct proto tcpv6_prot_override __ro_after_init; static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); pr_debug("subflow=%p\n", subflow); if (skb->protocol == htons(ETH_P_IP)) return subflow_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) goto drop; if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); return 0; } return tcp_conn_request(&mptcp_subflow_v6_request_sock_ops, &subflow_request_sock_ipv6_ops, sk, skb); drop: tcp_listendrop(sk); return 0; /* don't send reset */ } static void subflow_v6_req_destructor(struct request_sock *req) { subflow_req_destructor(req); tcp6_request_sock_ops.destructor(req); } #endif struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener) { if (ops->family == AF_INET) ops = &mptcp_subflow_v4_request_sock_ops; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (ops->family == AF_INET6) ops = &mptcp_subflow_v6_request_sock_ops; #endif return inet_reqsk_alloc(ops, sk_listener, attach_listener); } EXPORT_SYMBOL(mptcp_subflow_reqsk_alloc); /* validate hmac received in third ACK */ static bool subflow_hmac_valid(const struct request_sock *req, const struct mptcp_options_received *mp_opt) { const struct mptcp_subflow_request_sock *subflow_req; u8 hmac[SHA256_DIGEST_SIZE]; struct mptcp_sock *msk; subflow_req = mptcp_subflow_rsk(req); msk = subflow_req->msk; if (!msk) return false; subflow_generate_hmac(READ_ONCE(msk->remote_key), READ_ONCE(msk->local_key), subflow_req->remote_nonce, subflow_req->local_nonce, hmac); return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN); } static void subflow_ulp_fallback(struct sock *sk, struct mptcp_subflow_context *old_ctx) { struct inet_connection_sock *icsk = inet_csk(sk); mptcp_subflow_tcp_fallback(sk, old_ctx); icsk->icsk_ulp_ops = NULL; rcu_assign_pointer(icsk->icsk_ulp_data, NULL); tcp_sk(sk)->is_mptcp = 0; mptcp_subflow_ops_undo_override(sk); } void mptcp_subflow_drop_ctx(struct sock *ssk) { struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk); if (!ctx) return; list_del(&mptcp_subflow_ctx(ssk)->node); if (inet_csk(ssk)->icsk_ulp_ops) { subflow_ulp_fallback(ssk, ctx); if (ctx->conn) sock_put(ctx->conn); } kfree_rcu(ctx, rcu); } void __mptcp_subflow_fully_established(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt) { subflow_set_remote_key(msk, subflow, mp_opt); subflow->fully_established = 1; WRITE_ONCE(msk->fully_established, true); if (subflow->is_mptfo) __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); } static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req) { struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk); struct mptcp_subflow_request_sock *subflow_req; struct mptcp_options_received mp_opt; bool fallback, fallback_is_fatal; enum sk_rst_reason reason; struct mptcp_sock *owner; struct sock *child; pr_debug("listener=%p, req=%p, conn=%p\n", listener, req, listener->conn); /* After child creation we must look for MPC even when options * are not parsed */ mp_opt.suboptions = 0; /* hopefully temporary handling for MP_JOIN+syncookie */ subflow_req = mptcp_subflow_rsk(req); fallback_is_fatal = tcp_rsk(req)->is_mptcp && subflow_req->mp_join; fallback = !tcp_rsk(req)->is_mptcp; if (fallback) goto create_child; /* if the sk is MP_CAPABLE, we try to fetch the client key */ if (subflow_req->mp_capable) { /* we can receive and accept an in-window, out-of-order pkt, * which may not carry the MP_CAPABLE opt even on mptcp enabled * paths: always try to extract the peer key, and fallback * for packets missing it. * Even OoO DSS packets coming legitly after dropped or * reordered MPC will cause fallback, but we don't have other * options. */ mptcp_get_options(skb, &mp_opt); if (!(mp_opt.suboptions & (OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_ACK))) fallback = true; } else if (subflow_req->mp_join) { mptcp_get_options(skb, &mp_opt); if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK) || !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); fallback = true; } } create_child: child = listener->icsk_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash, own_req); if (child && *own_req) { struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child); tcp_rsk(req)->drop_req = false; /* we need to fallback on ctx allocation failure and on pre-reqs * checking above. In the latter scenario we additionally need * to reset the context to non MPTCP status. */ if (!ctx || fallback) { if (fallback_is_fatal) { subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP); goto dispose_child; } goto fallback; } /* ssk inherits options of listener sk */ ctx->setsockopt_seq = listener->setsockopt_seq; if (ctx->mp_capable) { ctx->conn = mptcp_sk_clone_init(listener->conn, &mp_opt, child, req); if (!ctx->conn) goto fallback; ctx->subflow_id = 1; owner = mptcp_sk(ctx->conn); mptcp_pm_new_connection(owner, child, 1); /* with OoO packets we can reach here without ingress * mpc option */ if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) { mptcp_pm_fully_established(owner, child); ctx->pm_notified = 1; } } else if (ctx->mp_join) { owner = subflow_req->msk; if (!owner) { subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); goto dispose_child; } /* move the msk reference ownership to the subflow */ subflow_req->msk = NULL; ctx->conn = (struct sock *)owner; if (subflow_use_different_sport(owner, sk)) { pr_debug("ack inet_sport=%d %d\n", ntohs(inet_sk(sk)->inet_sport), ntohs(inet_sk((struct sock *)owner)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(owner, sk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX); subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); goto dispose_child; } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX); } if (!mptcp_finish_join(child)) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(child); subflow_add_reset_reason(skb, subflow->reset_reason); goto dispose_child; } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX); tcp_rsk(req)->drop_req = true; } } /* check for expected invariant - should never trigger, just help * catching earlier subtle bugs */ WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp && (!mptcp_subflow_ctx(child) || !mptcp_subflow_ctx(child)->conn)); return child; dispose_child: mptcp_subflow_drop_ctx(child); tcp_rsk(req)->drop_req = true; inet_csk_prepare_for_destroy_sock(child); tcp_done(child); reason = mptcp_get_rst_reason(skb); req->rsk_ops->send_reset(sk, skb, reason); /* The last child reference will be released by the caller */ return child; fallback: if (fallback) SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); mptcp_subflow_drop_ctx(child); return child; } static struct inet_connection_sock_af_ops subflow_specific __ro_after_init; static struct proto tcp_prot_override __ro_after_init; enum mapping_status { MAPPING_OK, MAPPING_INVALID, MAPPING_EMPTY, MAPPING_DATA_FIN, MAPPING_DUMMY, MAPPING_BAD_CSUM }; static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d\n", ssn, subflow->map_subflow_seq, subflow->map_data_len); } static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); unsigned int skb_consumed; skb_consumed = tcp_sk(ssk)->copied_seq - TCP_SKB_CB(skb)->seq; if (WARN_ON_ONCE(skb_consumed >= skb->len)) return true; return skb->len - skb_consumed <= subflow->map_data_len - mptcp_subflow_get_map_offset(subflow); } static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); u32 ssn = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; if (unlikely(before(ssn, subflow->map_subflow_seq))) { /* Mapping covers data later in the subflow stream, * currently unsupported. */ dbg_bad_map(subflow, ssn); return false; } if (unlikely(!before(ssn, subflow->map_subflow_seq + subflow->map_data_len))) { /* Mapping does covers past subflow data, invalid */ dbg_bad_map(subflow, ssn); return false; } return true; } static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *skb, bool csum_reqd) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); u32 offset, seq, delta; __sum16 csum; int len; if (!csum_reqd) return MAPPING_OK; /* mapping already validated on previous traversal */ if (subflow->map_csum_len == subflow->map_data_len) return MAPPING_OK; /* traverse the receive queue, ensuring it contains a full * DSS mapping and accumulating the related csum. * Preserve the accoumlate csum across multiple calls, to compute * the csum only once */ delta = subflow->map_data_len - subflow->map_csum_len; for (;;) { seq = tcp_sk(ssk)->copied_seq + subflow->map_csum_len; offset = seq - TCP_SKB_CB(skb)->seq; /* if the current skb has not been accounted yet, csum its contents * up to the amount covered by the current DSS */ if (offset < skb->len) { __wsum csum; len = min(skb->len - offset, delta); csum = skb_checksum(skb, offset, len, 0); subflow->map_data_csum = csum_block_add(subflow->map_data_csum, csum, subflow->map_csum_len); delta -= len; subflow->map_csum_len += len; } if (delta == 0) break; if (skb_queue_is_last(&ssk->sk_receive_queue, skb)) { /* if this subflow is closed, the partial mapping * will be never completed; flush the pending skbs, so * that subflow_sched_work_if_closed() can kick in */ if (unlikely(ssk->sk_state == TCP_CLOSE)) while ((skb = skb_peek(&ssk->sk_receive_queue))) sk_eat_skb(ssk, skb); /* not enough data to validate the csum */ return MAPPING_EMPTY; } /* the DSS mapping for next skbs will be validated later, * when a get_mapping_status call will process such skb */ skb = skb->next; } /* note that 'map_data_len' accounts only for the carried data, does * not include the eventual seq increment due to the data fin, * while the pseudo header requires the original DSS data len, * including that */ csum = __mptcp_make_csum(subflow->map_seq, subflow->map_subflow_seq, subflow->map_data_len + subflow->map_data_fin, subflow->map_data_csum); if (unlikely(csum)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); return MAPPING_BAD_CSUM; } subflow->valid_csum_seen = 1; return MAPPING_OK; } static enum mapping_status get_mapping_status(struct sock *ssk, struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool csum_reqd = READ_ONCE(msk->csum_enabled); struct mptcp_ext *mpext; struct sk_buff *skb; u16 data_len; u64 map_seq; skb = skb_peek(&ssk->sk_receive_queue); if (!skb) return MAPPING_EMPTY; if (mptcp_check_fallback(ssk)) return MAPPING_DUMMY; mpext = mptcp_get_ext(skb); if (!mpext || !mpext->use_map) { if (!subflow->map_valid && !skb->len) { /* the TCP stack deliver 0 len FIN pkt to the receive * queue, that is the only 0len pkts ever expected here, * and we can admit no mapping only for 0 len pkts */ if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) WARN_ONCE(1, "0len seq %d:%d flags %x", TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, TCP_SKB_CB(skb)->tcp_flags); sk_eat_skb(ssk, skb); return MAPPING_EMPTY; } if (!subflow->map_valid) return MAPPING_INVALID; goto validate_seq; } trace_get_mapping_status(mpext); data_len = mpext->data_len; if (data_len == 0) { pr_debug("infinite mapping received\n"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); subflow->map_data_len = 0; return MAPPING_INVALID; } if (mpext->data_fin == 1) { u64 data_fin_seq; if (data_len == 1) { bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq, mpext->dsn64); pr_debug("DATA_FIN with no payload seq=%llu\n", mpext->data_seq); if (subflow->map_valid) { /* A DATA_FIN might arrive in a DSS * option before the previous mapping * has been fully consumed. Continue * handling the existing mapping. */ skb_ext_del(skb, SKB_EXT_MPTCP); return MAPPING_OK; } if (updated) mptcp_schedule_work((struct sock *)msk); return MAPPING_DATA_FIN; } data_fin_seq = mpext->data_seq + data_len - 1; /* If mpext->data_seq is a 32-bit value, data_fin_seq must also * be limited to 32 bits. */ if (!mpext->dsn64) data_fin_seq &= GENMASK_ULL(31, 0); mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64); pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d\n", data_fin_seq, mpext->dsn64); /* Adjust for DATA_FIN using 1 byte of sequence space */ data_len--; } map_seq = mptcp_expand_seq(READ_ONCE(msk->ack_seq), mpext->data_seq, mpext->dsn64); WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64); if (subflow->map_valid) { /* Allow replacing only with an identical map */ if (subflow->map_seq == map_seq && subflow->map_subflow_seq == mpext->subflow_seq && subflow->map_data_len == data_len && subflow->map_csum_reqd == mpext->csum_reqd) { skb_ext_del(skb, SKB_EXT_MPTCP); goto validate_csum; } /* If this skb data are fully covered by the current mapping, * the new map would need caching, which is not supported */ if (skb_is_fully_mapped(ssk, skb)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSNOMATCH); return MAPPING_INVALID; } /* will validate the next map after consuming the current one */ goto validate_csum; } subflow->map_seq = map_seq; subflow->map_subflow_seq = mpext->subflow_seq; subflow->map_data_len = data_len; subflow->map_valid = 1; subflow->map_data_fin = mpext->data_fin; subflow->mpc_map = mpext->mpc_map; subflow->map_csum_reqd = mpext->csum_reqd; subflow->map_csum_len = 0; subflow->map_data_csum = csum_unfold(mpext->csum); /* Cfr RFC 8684 Section 3.3.0 */ if (unlikely(subflow->map_csum_reqd != csum_reqd)) return MAPPING_INVALID; pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n", subflow->map_seq, subflow->map_subflow_seq, subflow->map_data_len, subflow->map_csum_reqd, subflow->map_data_csum); validate_seq: /* we revalidate valid mapping on new skb, because we must ensure * the current skb is completely covered by the available mapping */ if (!validate_mapping(ssk, skb)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSTCPMISMATCH); return MAPPING_INVALID; } skb_ext_del(skb, SKB_EXT_MPTCP); validate_csum: return validate_data_csum(ssk, skb, csum_reqd); } static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, u64 limit) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; struct tcp_sock *tp = tcp_sk(ssk); u32 offset, incr, avail_len; offset = tp->copied_seq - TCP_SKB_CB(skb)->seq; if (WARN_ON_ONCE(offset > skb->len)) goto out; avail_len = skb->len - offset; incr = limit >= avail_len ? avail_len + fin : limit; pr_debug("discarding=%d len=%d offset=%d seq=%d\n", incr, skb->len, offset, subflow->map_subflow_seq); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA); tcp_sk(ssk)->copied_seq += incr; out: if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq)) sk_eat_skb(ssk, skb); if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) subflow->map_valid = 0; } /* sched mptcp worker to remove the subflow if no more data is pending */ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; if (likely(ssk->sk_state != TCP_CLOSE && (ssk->sk_state != TCP_CLOSE_WAIT || inet_sk_state_load(sk) != TCP_ESTABLISHED))) return; if (skb_queue_empty(&ssk->sk_receive_queue) && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) mptcp_schedule_work(sk); } static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) { struct mptcp_sock *msk = mptcp_sk(subflow->conn); if (subflow->mp_join) return false; else if (READ_ONCE(msk->csum_enabled)) return !subflow->valid_csum_seen; else return !subflow->fully_established; } static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); unsigned long fail_tout; /* graceful failure can happen only on the MPC subflow */ if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first))) return; /* since the close timeout take precedence on the fail one, * no need to start the latter when the first is already set */ if (sock_flag((struct sock *)msk, SOCK_DEAD)) return; /* we don't need extreme accuracy here, use a zero fail_tout as special * value meaning no fail timeout at all; */ fail_tout = jiffies + TCP_RTO_MAX; if (!fail_tout) fail_tout = 1; WRITE_ONCE(subflow->fail_tout, fail_tout); tcp_send_ack(ssk); mptcp_reset_tout_timer(msk, subflow->fail_tout); } static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); enum mapping_status status; struct mptcp_sock *msk; struct sk_buff *skb; if (!skb_peek(&ssk->sk_receive_queue)) WRITE_ONCE(subflow->data_avail, false); if (subflow->data_avail) return true; msk = mptcp_sk(subflow->conn); for (;;) { u64 ack_seq; u64 old_ack; status = get_mapping_status(ssk, msk); trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue)); if (unlikely(status == MAPPING_INVALID || status == MAPPING_DUMMY || status == MAPPING_BAD_CSUM)) goto fallback; if (status != MAPPING_OK) goto no_data; skb = skb_peek(&ssk->sk_receive_queue); if (WARN_ON_ONCE(!skb)) goto no_data; if (unlikely(!READ_ONCE(msk->can_ack))) goto fallback; old_ack = READ_ONCE(msk->ack_seq); ack_seq = mptcp_subflow_get_mapped_dsn(subflow); pr_debug("msk ack_seq=%llx subflow ack_seq=%llx\n", old_ack, ack_seq); if (unlikely(before64(ack_seq, old_ack))) { mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); continue; } WRITE_ONCE(subflow->data_avail, true); break; } return true; no_data: subflow_sched_work_if_closed(msk, ssk); return false; fallback: if (!__mptcp_check_fallback(msk)) { /* RFC 8684 section 3.7. */ if (status == MAPPING_BAD_CSUM && (subflow->mp_join || subflow->valid_csum_seen)) { subflow->send_mp_fail = 1; if (!READ_ONCE(msk->allow_infinite_fallback)) { subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; goto reset; } mptcp_subflow_fail(msk, ssk); WRITE_ONCE(subflow->data_avail, true); return true; } if (!subflow_can_fallback(subflow) && subflow->map_data_len) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMPTCP; reset: WRITE_ONCE(ssk->sk_err, EBADMSG); tcp_set_state(ssk, TCP_CLOSE); while ((skb = skb_peek(&ssk->sk_receive_queue))) sk_eat_skb(ssk, skb); mptcp_send_active_reset_reason(ssk); WRITE_ONCE(subflow->data_avail, false); return false; } mptcp_do_fallback(ssk); } skb = skb_peek(&ssk->sk_receive_queue); subflow->map_valid = 1; subflow->map_seq = READ_ONCE(msk->ack_seq); subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; WRITE_ONCE(subflow->data_avail, true); return true; } bool mptcp_subflow_data_available(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); /* check if current mapping is still valid */ if (subflow->map_valid && mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { subflow->map_valid = 0; WRITE_ONCE(subflow->data_avail, false); pr_debug("Done with mapping: seq=%u data_len=%u\n", subflow->map_subflow_seq, subflow->map_data_len); } return subflow_check_data_avail(sk); } /* If ssk has an mptcp parent socket, use the mptcp rcvbuf occupancy, * not the ssk one. * * In mptcp, rwin is about the mptcp-level connection data. * * Data that is still on the ssk rx queue can thus be ignored, * as far as mptcp peer is concerned that data is still inflight. * DSS ACK is updated when skb is moved to the mptcp rx queue. */ void mptcp_space(const struct sock *ssk, int *space, int *full_space) { const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); const struct sock *sk = subflow->conn; *space = __mptcp_space(sk); *full_space = mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } static void subflow_error_report(struct sock *ssk) { struct sock *sk = mptcp_subflow_ctx(ssk)->conn; /* bail early if this is a no-op, so that we avoid introducing a * problematic lockdep dependency between TCP accept queue lock * and msk socket spinlock */ if (!sk->sk_socket) return; mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_error_report(sk); else __set_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } static void subflow_data_ready(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); u16 state = 1 << inet_sk_state_load(sk); struct sock *parent = subflow->conn; struct mptcp_sock *msk; trace_sk_data_ready(sk); msk = mptcp_sk(parent); if (state & TCPF_LISTEN) { /* MPJ subflow are removed from accept queue before reaching here, * avoid stray wakeups */ if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) return; parent->sk_data_ready(parent); return; } WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && !subflow->mp_join && !(state & TCPF_CLOSE)); if (mptcp_subflow_data_available(sk)) { mptcp_data_ready(parent, sk); /* subflow-level lowat test are not relevant. * respect the msk-level threshold eventually mandating an immediate ack */ if (mptcp_data_avail(msk) < parent->sk_rcvlowat && (tcp_sk(sk)->rcv_nxt - tcp_sk(sk)->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss) inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } else if (unlikely(sk->sk_err)) { subflow_error_report(sk); } } static void subflow_write_space(struct sock *ssk) { struct sock *sk = mptcp_subflow_ctx(ssk)->conn; mptcp_propagate_sndbuf(sk, ssk); mptcp_write_space(sk); } static const struct inet_connection_sock_af_ops * subflow_default_af_ops(struct sock *sk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (sk->sk_family == AF_INET6) return &subflow_v6_specific; #endif return &subflow_specific; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct inet_connection_sock *icsk = inet_csk(sk); const struct inet_connection_sock_af_ops *target; target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk); pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d\n", subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped); if (likely(icsk->icsk_af_ops == target)) return; subflow->icsk_af_ops = icsk->icsk_af_ops; icsk->icsk_af_ops = target; } #endif void mptcp_info2sockaddr(const struct mptcp_addr_info *info, struct sockaddr_storage *addr, unsigned short family) { memset(addr, 0, sizeof(*addr)); addr->ss_family = family; if (addr->ss_family == AF_INET) { struct sockaddr_in *in_addr = (struct sockaddr_in *)addr; if (info->family == AF_INET) in_addr->sin_addr = info->addr; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (ipv6_addr_v4mapped(&info->addr6)) in_addr->sin_addr.s_addr = info->addr6.s6_addr32[3]; #endif in_addr->sin_port = info->port; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (addr->ss_family == AF_INET6) { struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)addr; if (info->family == AF_INET) ipv6_addr_set_v4mapped(info->addr.s_addr, &in6_addr->sin6_addr); else in6_addr->sin6_addr = info->addr6; in6_addr->sin6_port = info->port; } #endif } int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local, const struct mptcp_addr_info *remote) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_subflow_context *subflow; int local_id = local->addr.id; struct sockaddr_storage addr; int remote_id = remote->id; int err = -ENOTCONN; struct socket *sf; struct sock *ssk; u32 remote_token; int addrlen; /* The userspace PM sent the request too early? */ if (!mptcp_is_fully_established(sk)) goto err_out; err = mptcp_subflow_create_socket(sk, local->addr.family, &sf); if (err) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXCREATSKERR); pr_debug("msk=%p local=%d remote=%d create sock error: %d\n", msk, local_id, remote_id, err); goto err_out; } ssk = sf->sk; subflow = mptcp_subflow_ctx(ssk); do { get_random_bytes(&subflow->local_nonce, sizeof(u32)); } while (!subflow->local_nonce); /* if 'IPADDRANY', the ID will be set later, after the routing */ if (local->addr.family == AF_INET) { if (!local->addr.addr.s_addr) local_id = -1; #if IS_ENABLED(CONFIG_MPTCP_IPV6) } else if (sk->sk_family == AF_INET6) { if (ipv6_addr_any(&local->addr.addr6)) local_id = -1; #endif } if (local_id >= 0) subflow_set_local_id(subflow, local_id); subflow->remote_key_valid = 1; subflow->remote_key = READ_ONCE(msk->remote_key); subflow->local_key = READ_ONCE(msk->local_key); subflow->token = msk->token; mptcp_info2sockaddr(&local->addr, &addr, ssk->sk_family); addrlen = sizeof(struct sockaddr_in); #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (addr.ss_family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif ssk->sk_bound_dev_if = local->ifindex; err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen); if (err) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXBINDERR); pr_debug("msk=%p local=%d remote=%d bind error: %d\n", msk, local_id, remote_id, err); goto failed; } mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL); pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d\n", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; WRITE_ONCE(subflow->remote_id, remote_id); subflow->request_join = 1; subflow->request_bkup = !!(local->flags & MPTCP_PM_ADDR_FLAG_BACKUP); subflow->subflow_id = msk->subflow_id++; mptcp_info2sockaddr(remote, &addr, ssk->sk_family); sock_hold(ssk); list_add_tail(&subflow->node, &msk->conn_list); err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK); if (err && err != -EINPROGRESS) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXCONNECTERR); pr_debug("msk=%p local=%d remote=%d connect error: %d\n", msk, local_id, remote_id, err); goto failed_unlink; } MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTX); /* discard the subflow socket */ mptcp_sock_graft(ssk, sk->sk_socket); iput(SOCK_INODE(sf)); WRITE_ONCE(msk->allow_infinite_fallback, false); mptcp_stop_tout_timer(sk); return 0; failed_unlink: list_del(&subflow->node); sock_put(mptcp_subflow_tcp_sock(subflow)); failed: subflow->disposable = 1; sock_release(sf); err_out: /* we account subflows before the creation, and this failures will not * be caught by sk_state_change() */ mptcp_pm_close_subflow(msk); return err; } static void mptcp_attach_cgroup(struct sock *parent, struct sock *child) { #ifdef CONFIG_SOCK_CGROUP_DATA struct sock_cgroup_data *parent_skcd = &parent->sk_cgrp_data, *child_skcd = &child->sk_cgrp_data; /* only the additional subflows created by kworkers have to be modified */ if (cgroup_id(sock_cgroup_ptr(parent_skcd)) != cgroup_id(sock_cgroup_ptr(child_skcd))) { #ifdef CONFIG_MEMCG struct mem_cgroup *memcg = parent->sk_memcg; mem_cgroup_sk_free(child); if (memcg && css_tryget(&memcg->css)) child->sk_memcg = memcg; #endif /* CONFIG_MEMCG */ cgroup_sk_free(child_skcd); *child_skcd = *parent_skcd; cgroup_sk_clone(child_skcd); } #endif /* CONFIG_SOCK_CGROUP_DATA */ } static void mptcp_subflow_ops_override(struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (ssk->sk_prot == &tcpv6_prot) ssk->sk_prot = &tcpv6_prot_override; else #endif ssk->sk_prot = &tcp_prot_override; } static void mptcp_subflow_ops_undo_override(struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (ssk->sk_prot == &tcpv6_prot_override) ssk->sk_prot = &tcpv6_prot; else #endif ssk->sk_prot = &tcp_prot; } int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, struct socket **new_sock) { struct mptcp_subflow_context *subflow; struct net *net = sock_net(sk); struct socket *sf; int err; /* un-accepted server sockets can reach here - on bad configuration * bail early to avoid greater trouble later */ if (unlikely(!sk->sk_socket)) return -EINVAL; err = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &sf); if (err) return err; lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING); err = security_mptcp_add_subflow(sk, sf->sk); if (err) goto err_free; /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); /* kernel sockets do not by default acquire net ref, but TCP timer * needs it. * Update ns_tracker to current stack trace and refcounted tracker. */ __netns_tracker_free(net, &sf->sk->ns_tracker, false); sf->sk->sk_net_refcnt = 1; get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); err = tcp_set_ulp(sf->sk, "mptcp"); if (err) goto err_free; mptcp_sockopt_sync_locked(mptcp_sk(sk), sf->sk); release_sock(sf->sk); /* the newly created socket really belongs to the owning MPTCP * socket, even if for additional subflows the allocation is performed * by a kernel workqueue. Adjust inode references, so that the * procfs/diag interfaces really show this one belonging to the correct * user. */ SOCK_INODE(sf)->i_ino = SOCK_INODE(sk->sk_socket)->i_ino; SOCK_INODE(sf)->i_uid = SOCK_INODE(sk->sk_socket)->i_uid; SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid; subflow = mptcp_subflow_ctx(sf->sk); pr_debug("subflow=%p\n", subflow); *new_sock = sf; sock_hold(sk); subflow->conn = sk; mptcp_subflow_ops_override(sf->sk); return 0; err_free: release_sock(sf->sk); sock_release(sf); return err; } static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, gfp_t priority) { struct inet_connection_sock *icsk = inet_csk(sk); struct mptcp_subflow_context *ctx; ctx = kzalloc(sizeof(*ctx), priority); if (!ctx) return NULL; rcu_assign_pointer(icsk->icsk_ulp_data, ctx); INIT_LIST_HEAD(&ctx->node); INIT_LIST_HEAD(&ctx->delegated_node); pr_debug("subflow=%p\n", ctx); ctx->tcp_sock = sk; WRITE_ONCE(ctx->local_id, -1); return ctx; } static void __subflow_state_change(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_all(&wq->wait); rcu_read_unlock(); } static bool subflow_is_done(const struct sock *sk) { return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE; } static void subflow_state_change(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct sock *parent = subflow->conn; struct mptcp_sock *msk; __subflow_state_change(sk); msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { mptcp_do_fallback(sk); pr_fallback(msk); subflow->conn_finished = 1; mptcp_propagate_state(parent, sk, subflow, NULL); } /* as recvmsg() does not acquire the subflow socket for ssk selection * a fin packet carrying a DSS can be unnoticed if we don't trigger * the data available machinery here. */ if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); else if (unlikely(sk->sk_err)) subflow_error_report(sk); subflow_sched_work_if_closed(mptcp_sk(parent), sk); /* when the fallback subflow closes the rx side, trigger a 'dummy' * ingress data fin, so that the msk state will follow along */ if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk && mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true)) mptcp_schedule_work(parent); } void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) { struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; struct request_sock *req, *head, *tail; struct mptcp_subflow_context *subflow; struct sock *sk, *ssk; /* Due to lock dependencies no relevant lock can be acquired under rskq_lock. * Splice the req list, so that accept() can not reach the pending ssk after * the listener socket is released below. */ spin_lock_bh(&queue->rskq_lock); head = queue->rskq_accept_head; tail = queue->rskq_accept_tail; queue->rskq_accept_head = NULL; queue->rskq_accept_tail = NULL; spin_unlock_bh(&queue->rskq_lock); if (!head) return; /* can't acquire the msk socket lock under the subflow one, * or will cause ABBA deadlock */ release_sock(listener_ssk); for (req = head; req; req = req->dl_next) { ssk = req->sk; if (!sk_is_mptcp(ssk)) continue; subflow = mptcp_subflow_ctx(ssk); if (!subflow || !subflow->conn) continue; sk = subflow->conn; sock_hold(sk); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); __mptcp_unaccepted_force_close(sk); release_sock(sk); /* lockdep will report a false positive ABBA deadlock * between cancel_work_sync and the listener socket. * The involved locks belong to different sockets WRT * the existing AB chain. * Using a per socket key is problematic as key * deregistration requires process context and must be * performed at socket disposal time, in atomic * context. * Just tell lockdep to consider the listener socket * released here. */ mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_); mptcp_cancel_work(sk); mutex_acquire(&listener_sk->sk_lock.dep_map, 0, 0, _RET_IP_); sock_put(sk); } /* we are still under the listener msk socket lock */ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); /* restore the listener queue, to let the TCP code clean it up */ spin_lock_bh(&queue->rskq_lock); WARN_ON_ONCE(queue->rskq_accept_head); queue->rskq_accept_head = head; queue->rskq_accept_tail = tail; spin_unlock_bh(&queue->rskq_lock); } static int subflow_ulp_init(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct mptcp_subflow_context *ctx; struct tcp_sock *tp = tcp_sk(sk); int err = 0; /* disallow attaching ULP to a socket unless it has been * created with sock_create_kern() */ if (!sk->sk_kern_sock) { err = -EOPNOTSUPP; goto out; } ctx = subflow_create_ctx(sk, GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto out; } pr_debug("subflow=%p, family=%d\n", ctx, sk->sk_family); tp->is_mptcp = 1; ctx->icsk_af_ops = icsk->icsk_af_ops; icsk->icsk_af_ops = subflow_default_af_ops(sk); ctx->tcp_state_change = sk->sk_state_change; ctx->tcp_error_report = sk->sk_error_report; WARN_ON_ONCE(sk->sk_data_ready != sock_def_readable); WARN_ON_ONCE(sk->sk_write_space != sk_stream_write_space); sk->sk_data_ready = subflow_data_ready; sk->sk_write_space = subflow_write_space; sk->sk_state_change = subflow_state_change; sk->sk_error_report = subflow_error_report; out: return err; } static void subflow_ulp_release(struct sock *ssk) { struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk); bool release = true; struct sock *sk; if (!ctx) return; sk = ctx->conn; if (sk) { /* if the msk has been orphaned, keep the ctx * alive, will be freed by __mptcp_close_ssk(), * when the subflow is still unaccepted */ release = ctx->disposable || list_empty(&ctx->node); /* inet_child_forget() does not call sk_state_change(), * explicitly trigger the socket close machinery */ if (!release && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags)) mptcp_schedule_work(sk); sock_put(sk); } mptcp_subflow_ops_undo_override(ssk); if (release) kfree_rcu(ctx, rcu); } static void subflow_ulp_clone(const struct request_sock *req, struct sock *newsk, const gfp_t priority) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct mptcp_subflow_context *old_ctx = mptcp_subflow_ctx(newsk); struct mptcp_subflow_context *new_ctx; if (!tcp_rsk(req)->is_mptcp || (!subflow_req->mp_capable && !subflow_req->mp_join)) { subflow_ulp_fallback(newsk, old_ctx); return; } new_ctx = subflow_create_ctx(newsk, priority); if (!new_ctx) { subflow_ulp_fallback(newsk, old_ctx); return; } new_ctx->conn_finished = 1; new_ctx->icsk_af_ops = old_ctx->icsk_af_ops; new_ctx->tcp_state_change = old_ctx->tcp_state_change; new_ctx->tcp_error_report = old_ctx->tcp_error_report; new_ctx->rel_write_seq = 1; new_ctx->tcp_sock = newsk; if (subflow_req->mp_capable) { /* see comments in subflow_syn_recv_sock(), MPTCP connection * is fully established only after we receive the remote key */ new_ctx->mp_capable = 1; new_ctx->local_key = subflow_req->local_key; new_ctx->token = subflow_req->token; new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->idsn = subflow_req->idsn; /* this is the first subflow, id is always 0 */ subflow_set_local_id(new_ctx, 0); } else if (subflow_req->mp_join) { new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->mp_join = 1; new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; new_ctx->request_bkup = subflow_req->request_bkup; WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; /* the subflow req id is valid, fetched via subflow_check_req() * and subflow_token_join_request() */ subflow_set_local_id(new_ctx, subflow_req->local_id); } } static void tcp_release_cb_override(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); long status; /* process and clear all the pending actions, but leave the subflow into * the napi queue. To respect locking, only the same CPU that originated * the action can touch the list. mptcp_napi_poll will take care of it. */ status = set_mask_bits(&subflow->delegated_status, MPTCP_DELEGATE_ACTIONS_MASK, 0); if (status) mptcp_subflow_process_delegated(ssk, status); tcp_release_cb(ssk); } static int tcp_abort_override(struct sock *ssk, int err) { /* closing a listener subflow requires a great deal of care. * keep it simple and just prevent such operation */ if (inet_sk_state_load(ssk) == TCP_LISTEN) return -EINVAL; return tcp_abort(ssk, err); } static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = { .name = "mptcp", .owner = THIS_MODULE, .init = subflow_ulp_init, .release = subflow_ulp_release, .clone = subflow_ulp_clone, }; static int subflow_ops_init(struct request_sock_ops *subflow_ops) { subflow_ops->obj_size = sizeof(struct mptcp_subflow_request_sock); subflow_ops->slab = kmem_cache_create(subflow_ops->slab_name, subflow_ops->obj_size, 0, SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU, NULL); if (!subflow_ops->slab) return -ENOMEM; return 0; } void __init mptcp_subflow_init(void) { mptcp_subflow_v4_request_sock_ops = tcp_request_sock_ops; mptcp_subflow_v4_request_sock_ops.slab_name = "request_sock_subflow_v4"; mptcp_subflow_v4_request_sock_ops.destructor = subflow_v4_req_destructor; if (subflow_ops_init(&mptcp_subflow_v4_request_sock_ops) != 0) panic("MPTCP: failed to init subflow v4 request sock ops\n"); subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops; subflow_request_sock_ipv4_ops.route_req = subflow_v4_route_req; subflow_request_sock_ipv4_ops.send_synack = subflow_v4_send_synack; subflow_specific = ipv4_specific; subflow_specific.conn_request = subflow_v4_conn_request; subflow_specific.syn_recv_sock = subflow_syn_recv_sock; subflow_specific.sk_rx_dst_set = subflow_finish_connect; subflow_specific.rebuild_header = subflow_rebuild_header; tcp_prot_override = tcp_prot; tcp_prot_override.release_cb = tcp_release_cb_override; tcp_prot_override.diag_destroy = tcp_abort_override; #if IS_ENABLED(CONFIG_MPTCP_IPV6) /* In struct mptcp_subflow_request_sock, we assume the TCP request sock * structures for v4 and v6 have the same size. It should not changed in * the future but better to make sure to be warned if it is no longer * the case. */ BUILD_BUG_ON(sizeof(struct tcp_request_sock) != sizeof(struct tcp6_request_sock)); mptcp_subflow_v6_request_sock_ops = tcp6_request_sock_ops; mptcp_subflow_v6_request_sock_ops.slab_name = "request_sock_subflow_v6"; mptcp_subflow_v6_request_sock_ops.destructor = subflow_v6_req_destructor; if (subflow_ops_init(&mptcp_subflow_v6_request_sock_ops) != 0) panic("MPTCP: failed to init subflow v6 request sock ops\n"); subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops; subflow_request_sock_ipv6_ops.route_req = subflow_v6_route_req; subflow_request_sock_ipv6_ops.send_synack = subflow_v6_send_synack; subflow_v6_specific = ipv6_specific; subflow_v6_specific.conn_request = subflow_v6_conn_request; subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock; subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect; subflow_v6_specific.rebuild_header = subflow_v6_rebuild_header; subflow_v6m_specific = subflow_v6_specific; subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit; subflow_v6m_specific.send_check = ipv4_specific.send_check; subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len; subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced; subflow_v6m_specific.rebuild_header = subflow_rebuild_header; tcpv6_prot_override = tcpv6_prot; tcpv6_prot_override.release_cb = tcp_release_cb_override; tcpv6_prot_override.diag_destroy = tcp_abort_override; #endif mptcp_diag_subflow_init(&subflow_ulp_ops); if (tcp_register_ulp(&subflow_ulp_ops) != 0) panic("MPTCP: failed to register subflows to ULP\n"); } |
| 554 457 84 378 29 488 2 9 1 1 2 21 556 527 488 555 1 555 555 556 29 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 | // SPDX-License-Identifier: GPL-2.0 /* * XFRM compat layer * Author: Dmitry Safonov <dima@arista.com> * Based on code and translator idea by: Florian Westphal <fw@strlen.de> */ #include <linux/compat.h> #include <linux/nospec.h> #include <linux/xfrm.h> #include <net/xfrm.h> struct compat_xfrm_lifetime_cfg { compat_u64 soft_byte_limit, hard_byte_limit; compat_u64 soft_packet_limit, hard_packet_limit; compat_u64 soft_add_expires_seconds, hard_add_expires_seconds; compat_u64 soft_use_expires_seconds, hard_use_expires_seconds; }; /* same size on 32bit, but only 4 byte alignment required */ struct compat_xfrm_lifetime_cur { compat_u64 bytes, packets, add_time, use_time; }; /* same size on 32bit, but only 4 byte alignment required */ struct compat_xfrm_userpolicy_info { struct xfrm_selector sel; struct compat_xfrm_lifetime_cfg lft; struct compat_xfrm_lifetime_cur curlft; __u32 priority, index; u8 dir, action, flags, share; /* 4 bytes additional padding on 64bit */ }; struct compat_xfrm_usersa_info { struct xfrm_selector sel; struct xfrm_id id; xfrm_address_t saddr; struct compat_xfrm_lifetime_cfg lft; struct compat_xfrm_lifetime_cur curlft; struct xfrm_stats stats; __u32 seq, reqid; u16 family; u8 mode, replay_window, flags; /* 4 bytes additional padding on 64bit */ }; struct compat_xfrm_user_acquire { struct xfrm_id id; xfrm_address_t saddr; struct xfrm_selector sel; struct compat_xfrm_userpolicy_info policy; /* 4 bytes additional padding on 64bit */ __u32 aalgos, ealgos, calgos, seq; }; struct compat_xfrm_userspi_info { struct compat_xfrm_usersa_info info; /* 4 bytes additional padding on 64bit */ __u32 min, max; }; struct compat_xfrm_user_expire { struct compat_xfrm_usersa_info state; /* 8 bytes additional padding on 64bit */ u8 hard; }; struct compat_xfrm_user_polexpire { struct compat_xfrm_userpolicy_info pol; /* 8 bytes additional padding on 64bit */ u8 hard; }; #define XMSGSIZE(type) sizeof(struct type) static const int compat_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info), [XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info), [XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userspi_info), [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_acquire), [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_expire), [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info), [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info), [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_polexpire), [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush), [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0, [XFRM_MSG_NEWAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), [XFRM_MSG_GETAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), [XFRM_MSG_REPORT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report), [XFRM_MSG_MIGRATE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_NEWSADINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_MAPPING - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping) }; static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_UNSPEC] = { .strict_start_type = XFRMA_SA_DIR }, [XFRMA_SA] = { .len = XMSGSIZE(compat_xfrm_usersa_info)}, [XFRMA_POLICY] = { .len = XMSGSIZE(compat_xfrm_userpolicy_info)}, [XFRMA_LASTUSED] = { .type = NLA_U64}, [XFRMA_ALG_AUTH_TRUNC] = { .len = sizeof(struct xfrm_algo_auth)}, [XFRMA_ALG_AEAD] = { .len = sizeof(struct xfrm_algo_aead) }, [XFRMA_ALG_AUTH] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ALG_CRYPT] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, [XFRMA_ETIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SRCADDR] = { .len = sizeof(xfrm_address_t) }, [XFRMA_COADDR] = { .len = sizeof(xfrm_address_t) }, [XFRMA_POLICY_TYPE] = { .len = sizeof(struct xfrm_userpolicy_type)}, [XFRMA_MIGRATE] = { .len = sizeof(struct xfrm_user_migrate) }, [XFRMA_KMADDRESS] = { .len = sizeof(struct xfrm_user_kmaddress) }, [XFRMA_MARK] = { .len = sizeof(struct xfrm_mark) }, [XFRMA_TFCPAD] = { .type = NLA_U32 }, [XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) }, [XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 }, [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, [XFRMA_SET_MARK] = { .type = NLA_U32 }, [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, }; static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src, u16 type) { int payload = compat_msg_min[type]; int src_len = xfrm_msg_min[type]; struct nlmsghdr *nlh_dst; /* Compat messages are shorter or equal to native (+padding) */ if (WARN_ON_ONCE(src_len < payload)) return ERR_PTR(-EMSGSIZE); nlh_dst = nlmsg_put(skb, nlh_src->nlmsg_pid, nlh_src->nlmsg_seq, nlh_src->nlmsg_type, payload, nlh_src->nlmsg_flags); if (!nlh_dst) return ERR_PTR(-EMSGSIZE); memset(nlmsg_data(nlh_dst), 0, payload); switch (nlh_src->nlmsg_type) { /* Compat message has the same layout as native */ case XFRM_MSG_DELSA: case XFRM_MSG_DELPOLICY: case XFRM_MSG_FLUSHSA: case XFRM_MSG_FLUSHPOLICY: case XFRM_MSG_NEWAE: case XFRM_MSG_REPORT: case XFRM_MSG_MIGRATE: case XFRM_MSG_NEWSADINFO: case XFRM_MSG_NEWSPDINFO: case XFRM_MSG_MAPPING: WARN_ON_ONCE(src_len != payload); memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), src_len); break; /* 4 byte alignment for trailing u64 on native, but not on compat */ case XFRM_MSG_NEWSA: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_UPDSA: case XFRM_MSG_UPDPOLICY: WARN_ON_ONCE(src_len != payload + 4); memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), payload); break; case XFRM_MSG_EXPIRE: { const struct xfrm_user_expire *src_ue = nlmsg_data(nlh_src); struct compat_xfrm_user_expire *dst_ue = nlmsg_data(nlh_dst); /* compat_xfrm_user_expire has 4-byte smaller state */ memcpy(dst_ue, src_ue, sizeof(dst_ue->state)); dst_ue->hard = src_ue->hard; break; } case XFRM_MSG_ACQUIRE: { const struct xfrm_user_acquire *src_ua = nlmsg_data(nlh_src); struct compat_xfrm_user_acquire *dst_ua = nlmsg_data(nlh_dst); memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos)); dst_ua->aalgos = src_ua->aalgos; dst_ua->ealgos = src_ua->ealgos; dst_ua->calgos = src_ua->calgos; dst_ua->seq = src_ua->seq; break; } case XFRM_MSG_POLEXPIRE: { const struct xfrm_user_polexpire *src_upe = nlmsg_data(nlh_src); struct compat_xfrm_user_polexpire *dst_upe = nlmsg_data(nlh_dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_upe, src_upe, sizeof(dst_upe->pol)); dst_upe->hard = src_upe->hard; break; } case XFRM_MSG_ALLOCSPI: { const struct xfrm_userspi_info *src_usi = nlmsg_data(nlh_src); struct compat_xfrm_userspi_info *dst_usi = nlmsg_data(nlh_dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_usi, src_usi, sizeof(src_usi->info)); dst_usi->min = src_usi->min; dst_usi->max = src_usi->max; break; } /* Not being sent by kernel */ case XFRM_MSG_GETSA: case XFRM_MSG_GETPOLICY: case XFRM_MSG_GETAE: case XFRM_MSG_GETSADINFO: case XFRM_MSG_GETSPDINFO: default: pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type); return ERR_PTR(-EOPNOTSUPP); } return nlh_dst; } static int xfrm_nla_cpy(struct sk_buff *dst, const struct nlattr *src, int len) { return nla_put(dst, src->nla_type, len, nla_data(src)); } static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) { switch (src->nla_type) { case XFRMA_PAD: /* Ignore */ return 0; case XFRMA_UNSPEC: case XFRMA_ALG_AUTH: case XFRMA_ALG_CRYPT: case XFRMA_ALG_COMP: case XFRMA_ENCAP: case XFRMA_TMPL: return xfrm_nla_cpy(dst, src, nla_len(src)); case XFRMA_SA: return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_usersa_info)); case XFRMA_POLICY: return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_userpolicy_info)); case XFRMA_SEC_CTX: return xfrm_nla_cpy(dst, src, nla_len(src)); case XFRMA_LTIME_VAL: return nla_put_64bit(dst, src->nla_type, nla_len(src), nla_data(src), XFRMA_PAD); case XFRMA_REPLAY_VAL: case XFRMA_REPLAY_THRESH: case XFRMA_ETIMER_THRESH: case XFRMA_SRCADDR: case XFRMA_COADDR: return xfrm_nla_cpy(dst, src, nla_len(src)); case XFRMA_LASTUSED: return nla_put_64bit(dst, src->nla_type, nla_len(src), nla_data(src), XFRMA_PAD); case XFRMA_POLICY_TYPE: case XFRMA_MIGRATE: case XFRMA_ALG_AEAD: case XFRMA_KMADDRESS: case XFRMA_ALG_AUTH_TRUNC: case XFRMA_MARK: case XFRMA_TFCPAD: case XFRMA_REPLAY_ESN_VAL: case XFRMA_SA_EXTRA_FLAGS: case XFRMA_PROTO: case XFRMA_ADDRESS_FILTER: case XFRMA_OFFLOAD_DEV: case XFRMA_SET_MARK: case XFRMA_SET_MARK_MASK: case XFRMA_IF_ID: case XFRMA_MTIMER_THRESH: case XFRMA_SA_DIR: case XFRMA_NAT_KEEPALIVE_INTERVAL: return xfrm_nla_cpy(dst, src, nla_len(src)); default: BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } } /* Take kernel-built (64bit layout) and create 32bit layout for userspace */ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) { u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE; const struct nlattr *nla, *attrs; struct nlmsghdr *nlh_dst; int len, remaining; nlh_dst = xfrm_nlmsg_put_compat(dst, nlh_src, type); if (IS_ERR(nlh_dst)) return PTR_ERR(nlh_dst); attrs = nlmsg_attrdata(nlh_src, xfrm_msg_min[type]); len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]); nla_for_each_attr(nla, attrs, len, remaining) { int err; switch (nlh_src->nlmsg_type) { case XFRM_MSG_NEWSPDINFO: err = xfrm_nla_cpy(dst, nla, nla_len(nla)); break; default: err = xfrm_xlate64_attr(dst, nla); break; } if (err) return err; } nlmsg_end(dst, nlh_dst); return 0; } static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src) { u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE; struct sk_buff *new = NULL; int err; if (type >= ARRAY_SIZE(xfrm_msg_min)) { pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type); return -EOPNOTSUPP; } if (skb_shinfo(skb)->frag_list == NULL) { new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC); if (!new) return -ENOMEM; skb_shinfo(skb)->frag_list = new; } err = xfrm_xlate64(skb_shinfo(skb)->frag_list, nlh_src); if (err) { if (new) { kfree_skb(new); skb_shinfo(skb)->frag_list = NULL; } return err; } return 0; } /* Calculates len of translated 64-bit message. */ static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src, struct nlattr *attrs[XFRMA_MAX + 1], int maxtype) { size_t len = nlmsg_len(src); switch (src->nlmsg_type) { case XFRM_MSG_NEWSA: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_ALLOCSPI: case XFRM_MSG_ACQUIRE: case XFRM_MSG_UPDPOLICY: case XFRM_MSG_UPDSA: len += 4; break; case XFRM_MSG_EXPIRE: case XFRM_MSG_POLEXPIRE: len += 8; break; case XFRM_MSG_NEWSPDINFO: /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ return len; default: break; } /* Unexpected for anything, but XFRM_MSG_NEWSPDINFO, please * correct both 64=>32-bit and 32=>64-bit translators to copy * new attributes. */ if (WARN_ON_ONCE(maxtype)) return len; if (attrs[XFRMA_SA]) len += 4; if (attrs[XFRMA_POLICY]) len += 4; /* XXX: some attrs may need to be realigned * if !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */ return len; } static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src, size_t size, int copy_len, int payload) { struct nlmsghdr *nlmsg = dst; struct nlattr *nla; /* xfrm_user_rcv_msg_compat() relies on fact that 32-bit messages * have the same len or shorted than 64-bit ones. * 32-bit translation that is bigger than 64-bit original is unexpected. */ if (WARN_ON_ONCE(copy_len > payload)) copy_len = payload; if (size - *pos < nla_attr_size(payload)) return -ENOBUFS; nla = dst + *pos; memcpy(nla, src, nla_attr_size(copy_len)); nla->nla_len = nla_attr_size(payload); *pos += nla_attr_size(copy_len); nlmsg->nlmsg_len += nla->nla_len; memset(dst + *pos, 0, payload - copy_len); *pos += payload - copy_len; return 0; } static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, size_t *pos, size_t size, struct netlink_ext_ack *extack) { int type = nla_type(nla); u16 pol_len32, pol_len64; int err; if (type > XFRMA_MAX) { BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } type = array_index_nospec(type, XFRMA_MAX + 1); if (nla_len(nla) < compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; } pol_len32 = compat_policy[type].len; pol_len64 = xfrma_policy[type].len; /* XFRMA_SA and XFRMA_POLICY - need to know how-to translate */ if (pol_len32 != pol_len64) { if (nla_len(nla) != compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; } err = xfrm_attr_cpy32(dst, pos, nla, size, pol_len32, pol_len64); if (err) return err; } return xfrm_attr_cpy32(dst, pos, nla, size, nla_len(nla), nla_len(nla)); } static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src, struct nlattr *attrs[XFRMA_MAX+1], size_t size, u8 type, int maxtype, struct netlink_ext_ack *extack) { size_t pos; int i; memcpy(dst, src, NLMSG_HDRLEN); dst->nlmsg_len = NLMSG_HDRLEN + xfrm_msg_min[type]; memset(nlmsg_data(dst), 0, xfrm_msg_min[type]); switch (src->nlmsg_type) { /* Compat message has the same layout as native */ case XFRM_MSG_DELSA: case XFRM_MSG_GETSA: case XFRM_MSG_DELPOLICY: case XFRM_MSG_GETPOLICY: case XFRM_MSG_FLUSHSA: case XFRM_MSG_FLUSHPOLICY: case XFRM_MSG_NEWAE: case XFRM_MSG_GETAE: case XFRM_MSG_REPORT: case XFRM_MSG_MIGRATE: case XFRM_MSG_NEWSADINFO: case XFRM_MSG_GETSADINFO: case XFRM_MSG_NEWSPDINFO: case XFRM_MSG_GETSPDINFO: case XFRM_MSG_MAPPING: memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]); break; /* 4 byte alignment for trailing u64 on native, but not on compat */ case XFRM_MSG_NEWSA: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_UPDSA: case XFRM_MSG_UPDPOLICY: memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]); break; case XFRM_MSG_EXPIRE: { const struct compat_xfrm_user_expire *src_ue = nlmsg_data(src); struct xfrm_user_expire *dst_ue = nlmsg_data(dst); /* compat_xfrm_user_expire has 4-byte smaller state */ memcpy(dst_ue, src_ue, sizeof(src_ue->state)); dst_ue->hard = src_ue->hard; break; } case XFRM_MSG_ACQUIRE: { const struct compat_xfrm_user_acquire *src_ua = nlmsg_data(src); struct xfrm_user_acquire *dst_ua = nlmsg_data(dst); memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos)); dst_ua->aalgos = src_ua->aalgos; dst_ua->ealgos = src_ua->ealgos; dst_ua->calgos = src_ua->calgos; dst_ua->seq = src_ua->seq; break; } case XFRM_MSG_POLEXPIRE: { const struct compat_xfrm_user_polexpire *src_upe = nlmsg_data(src); struct xfrm_user_polexpire *dst_upe = nlmsg_data(dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_upe, src_upe, sizeof(src_upe->pol)); dst_upe->hard = src_upe->hard; break; } case XFRM_MSG_ALLOCSPI: { const struct compat_xfrm_userspi_info *src_usi = nlmsg_data(src); struct xfrm_userspi_info *dst_usi = nlmsg_data(dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_usi, src_usi, sizeof(src_usi->info)); dst_usi->min = src_usi->min; dst_usi->max = src_usi->max; break; } default: NL_SET_ERR_MSG(extack, "Unsupported message type"); return -EOPNOTSUPP; } pos = dst->nlmsg_len; if (maxtype) { /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ WARN_ON_ONCE(src->nlmsg_type != XFRM_MSG_NEWSPDINFO); for (i = 1; i <= maxtype; i++) { int err; if (!attrs[i]) continue; /* just copy - no need for translation */ err = xfrm_attr_cpy32(dst, &pos, attrs[i], size, nla_len(attrs[i]), nla_len(attrs[i])); if (err) return err; } return 0; } for (i = 1; i < XFRMA_MAX + 1; i++) { int err; if (i == XFRMA_PAD) continue; if (!attrs[i]) continue; err = xfrm_xlate32_attr(dst, attrs[i], &pos, size, extack); if (err) return err; } return 0; } static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { /* netlink_rcv_skb() checks if a message has full (struct nlmsghdr) */ u16 type = h32->nlmsg_type - XFRM_MSG_BASE; struct nlattr *attrs[XFRMA_MAX+1]; struct nlmsghdr *h64; size_t len; int err; BUILD_BUG_ON(ARRAY_SIZE(xfrm_msg_min) != ARRAY_SIZE(compat_msg_min)); if (type >= ARRAY_SIZE(xfrm_msg_min)) return ERR_PTR(-EINVAL); /* Don't call parse: the message might have only nlmsg header */ if ((h32->nlmsg_type == XFRM_MSG_GETSA || h32->nlmsg_type == XFRM_MSG_GETPOLICY) && (h32->nlmsg_flags & NLM_F_DUMP)) return NULL; err = nlmsg_parse_deprecated(h32, compat_msg_min[type], attrs, maxtype ? : XFRMA_MAX, policy ? : compat_policy, extack); if (err < 0) return ERR_PTR(err); len = xfrm_user_rcv_calculate_len64(h32, attrs, maxtype); /* The message doesn't need translation */ if (len == nlmsg_len(h32)) return NULL; len += NLMSG_HDRLEN; h64 = kvmalloc(len, GFP_KERNEL); if (!h64) return ERR_PTR(-ENOMEM); err = xfrm_xlate32(h64, h32, attrs, len, type, maxtype, extack); if (err < 0) { kvfree(h64); return ERR_PTR(err); } return h64; } static int xfrm_user_policy_compat(u8 **pdata32, int optlen) { struct compat_xfrm_userpolicy_info *p = (void *)*pdata32; u8 *src_templates, *dst_templates; u8 *data64; if (optlen < sizeof(*p)) return -EINVAL; data64 = kmalloc_track_caller(optlen + 4, GFP_USER | __GFP_NOWARN); if (!data64) return -ENOMEM; memcpy(data64, *pdata32, sizeof(*p)); memset(data64 + sizeof(*p), 0, 4); src_templates = *pdata32 + sizeof(*p); dst_templates = data64 + sizeof(*p) + 4; memcpy(dst_templates, src_templates, optlen - sizeof(*p)); kfree(*pdata32); *pdata32 = data64; return 0; } static struct xfrm_translator xfrm_translator = { .owner = THIS_MODULE, .alloc_compat = xfrm_alloc_compat, .rcv_msg_compat = xfrm_user_rcv_msg_compat, .xlate_user_policy_sockptr = xfrm_user_policy_compat, }; static int __init xfrm_compat_init(void) { return xfrm_register_translator(&xfrm_translator); } static void __exit xfrm_compat_exit(void) { xfrm_unregister_translator(&xfrm_translator); } module_init(xfrm_compat_init); module_exit(xfrm_compat_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Dmitry Safonov"); MODULE_DESCRIPTION("XFRM 32-bit compatibility layer"); |
| 28 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM vsyscall #if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define __VSYSCALL_TRACE_H #include <linux/tracepoint.h> TRACE_EVENT(emulate_vsyscall, TP_PROTO(int nr), TP_ARGS(nr), TP_STRUCT__entry(__field(int, nr)), TP_fast_assign( __entry->nr = nr; ), TP_printk("nr = %d", __entry->nr) ); #endif #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/ #define TRACE_INCLUDE_FILE vsyscall_trace #include <trace/define_trace.h> |
| 41 41 11 41 41 41 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2021 NXP */ #include "netlink.h" #include "common.h" struct phc_vclocks_req_info { struct ethnl_req_info base; }; struct phc_vclocks_reply_data { struct ethnl_reply_data base; int num; int *index; }; #define PHC_VCLOCKS_REPDATA(__reply_base) \ container_of(__reply_base, struct phc_vclocks_reply_data, base) const struct nla_policy ethnl_phc_vclocks_get_policy[] = { [ETHTOOL_A_PHC_VCLOCKS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; data->num = ethtool_get_phc_vclocks(dev, &data->index); ethnl_ops_complete(dev); return ret; } static int phc_vclocks_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); int len = 0; if (data->num > 0) { len += nla_total_size(sizeof(u32)); len += nla_total_size(sizeof(s32) * data->num); } return len; } static int phc_vclocks_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); if (data->num <= 0) return 0; if (nla_put_u32(skb, ETHTOOL_A_PHC_VCLOCKS_NUM, data->num) || nla_put(skb, ETHTOOL_A_PHC_VCLOCKS_INDEX, sizeof(s32) * data->num, data->index)) return -EMSGSIZE; return 0; } static void phc_vclocks_cleanup_data(struct ethnl_reply_data *reply_base) { const struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base); kfree(data->index); } const struct ethnl_request_ops ethnl_phc_vclocks_request_ops = { .request_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, .reply_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, .hdr_attr = ETHTOOL_A_PHC_VCLOCKS_HEADER, .req_info_size = sizeof(struct phc_vclocks_req_info), .reply_data_size = sizeof(struct phc_vclocks_reply_data), .prepare_data = phc_vclocks_prepare_data, .reply_size = phc_vclocks_reply_size, .fill_reply = phc_vclocks_fill_reply, .cleanup_data = phc_vclocks_cleanup_data, }; |
| 3292 3664 341 434 790 1591 1599 34 1643 1142 316 965 10 3 1281 2740 2743 2741 1541 648 2746 7 22 3 1 26 1221 41 14 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_NEIGHBOUR_H #define _NET_NEIGHBOUR_H #include <linux/neighbour.h> /* * Generic neighbour manipulation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * * Changes: * * Harald Welte: <laforge@gnumonks.org> * - Add neighbour cache statistics like rtstat */ #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> #include <linux/bitmap.h> #include <linux/err.h> #include <linux/sysctl.h> #include <linux/workqueue.h> #include <net/rtnetlink.h> /* * NUD stands for "neighbor unreachability detection" */ #define NUD_IN_TIMER (NUD_INCOMPLETE|NUD_REACHABLE|NUD_DELAY|NUD_PROBE) #define NUD_VALID (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE|NUD_PROBE|NUD_STALE|NUD_DELAY) #define NUD_CONNECTED (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE) struct neighbour; enum { NEIGH_VAR_MCAST_PROBES, NEIGH_VAR_UCAST_PROBES, NEIGH_VAR_APP_PROBES, NEIGH_VAR_MCAST_REPROBES, NEIGH_VAR_RETRANS_TIME, NEIGH_VAR_BASE_REACHABLE_TIME, NEIGH_VAR_DELAY_PROBE_TIME, NEIGH_VAR_INTERVAL_PROBE_TIME_MS, NEIGH_VAR_GC_STALETIME, NEIGH_VAR_QUEUE_LEN_BYTES, NEIGH_VAR_PROXY_QLEN, NEIGH_VAR_ANYCAST_DELAY, NEIGH_VAR_PROXY_DELAY, NEIGH_VAR_LOCKTIME, #define NEIGH_VAR_DATA_MAX (NEIGH_VAR_LOCKTIME + 1) /* Following are used as a second way to access one of the above */ NEIGH_VAR_QUEUE_LEN, /* same data as NEIGH_VAR_QUEUE_LEN_BYTES */ NEIGH_VAR_RETRANS_TIME_MS, /* same data as NEIGH_VAR_RETRANS_TIME */ NEIGH_VAR_BASE_REACHABLE_TIME_MS, /* same data as NEIGH_VAR_BASE_REACHABLE_TIME */ /* Following are used by "default" only */ NEIGH_VAR_GC_INTERVAL, NEIGH_VAR_GC_THRESH1, NEIGH_VAR_GC_THRESH2, NEIGH_VAR_GC_THRESH3, NEIGH_VAR_MAX }; struct neigh_parms { possible_net_t net; struct net_device *dev; netdevice_tracker dev_tracker; struct list_head list; int (*neigh_setup)(struct neighbour *); struct neigh_table *tbl; void *sysctl_table; int dead; refcount_t refcnt; struct rcu_head rcu_head; int reachable_time; u32 qlen; int data[NEIGH_VAR_DATA_MAX]; DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX); }; static inline void neigh_var_set(struct neigh_parms *p, int index, int val) { set_bit(index, p->data_state); p->data[index] = val; } #define NEIGH_VAR(p, attr) ((p)->data[NEIGH_VAR_ ## attr]) /* In ndo_neigh_setup, NEIGH_VAR_INIT should be used. * In other cases, NEIGH_VAR_SET should be used. */ #define NEIGH_VAR_INIT(p, attr, val) (NEIGH_VAR(p, attr) = val) #define NEIGH_VAR_SET(p, attr, val) neigh_var_set(p, NEIGH_VAR_ ## attr, val) static inline void neigh_parms_data_state_setall(struct neigh_parms *p) { bitmap_fill(p->data_state, NEIGH_VAR_DATA_MAX); } static inline void neigh_parms_data_state_cleanall(struct neigh_parms *p) { bitmap_zero(p->data_state, NEIGH_VAR_DATA_MAX); } struct neigh_statistics { unsigned long allocs; /* number of allocated neighs */ unsigned long destroys; /* number of destroyed neighs */ unsigned long hash_grows; /* number of hash resizes */ unsigned long res_failed; /* number of failed resolutions */ unsigned long lookups; /* number of lookups */ unsigned long hits; /* number of hits (among lookups) */ unsigned long rcv_probes_mcast; /* number of received mcast ipv6 */ unsigned long rcv_probes_ucast; /* number of received ucast ipv6 */ unsigned long periodic_gc_runs; /* number of periodic GC runs */ unsigned long forced_gc_runs; /* number of forced GC runs */ unsigned long unres_discards; /* number of unresolved drops */ unsigned long table_fulls; /* times even gc couldn't help */ }; #define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field) struct neighbour { struct neighbour __rcu *next; struct neigh_table *tbl; struct neigh_parms *parms; unsigned long confirmed; unsigned long updated; rwlock_t lock; refcount_t refcnt; unsigned int arp_queue_len_bytes; struct sk_buff_head arp_queue; struct timer_list timer; unsigned long used; atomic_t probes; u8 nud_state; u8 type; u8 dead; u8 protocol; u32 flags; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8); struct hh_cache hh; int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; struct list_head gc_list; struct list_head managed_list; struct rcu_head rcu; struct net_device *dev; netdevice_tracker dev_tracker; u8 primary_key[]; } __randomize_layout; struct neigh_ops { int family; void (*solicit)(struct neighbour *, struct sk_buff *); void (*error_report)(struct neighbour *, struct sk_buff *); int (*output)(struct neighbour *, struct sk_buff *); int (*connected_output)(struct neighbour *, struct sk_buff *); }; struct pneigh_entry { struct pneigh_entry *next; possible_net_t net; struct net_device *dev; netdevice_tracker dev_tracker; u32 flags; u8 protocol; u32 key[]; }; /* * neighbour table manipulation */ #define NEIGH_NUM_HASH_RND 4 struct neigh_hash_table { struct neighbour __rcu **hash_buckets; unsigned int hash_shift; __u32 hash_rnd[NEIGH_NUM_HASH_RND]; struct rcu_head rcu; }; struct neigh_table { int family; unsigned int entry_size; unsigned int key_len; __be16 protocol; __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); bool (*key_eq)(const struct neighbour *, const void *pkey); int (*constructor)(struct neighbour *); int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); void (*proxy_redo)(struct sk_buff *skb); int (*is_multicast)(const void *pkey); bool (*allow_add)(const struct net_device *dev, struct netlink_ext_ack *extack); char *id; struct neigh_parms parms; struct list_head parms_list; int gc_interval; int gc_thresh1; int gc_thresh2; int gc_thresh3; unsigned long last_flush; struct delayed_work gc_work; struct delayed_work managed_work; struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; atomic_t gc_entries; struct list_head gc_list; struct list_head managed_list; rwlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; struct neigh_hash_table __rcu *nht; struct pneigh_entry **phash_buckets; }; enum { NEIGH_ARP_TABLE = 0, NEIGH_ND_TABLE = 1, NEIGH_DN_TABLE = 2, NEIGH_NR_TABLES, NEIGH_LINK_TABLE = NEIGH_NR_TABLES /* Pseudo table for neigh_xmit */ }; static inline int neigh_parms_family(struct neigh_parms *p) { return p->tbl->family; } #define NEIGH_PRIV_ALIGN sizeof(long long) #define NEIGH_ENTRY_SIZE(size) ALIGN((size), NEIGH_PRIV_ALIGN) static inline void *neighbour_priv(const struct neighbour *n) { return (char *)n + n->tbl->entry_size; } /* flags for neigh_update() */ #define NEIGH_UPDATE_F_OVERRIDE BIT(0) #define NEIGH_UPDATE_F_WEAK_OVERRIDE BIT(1) #define NEIGH_UPDATE_F_OVERRIDE_ISROUTER BIT(2) #define NEIGH_UPDATE_F_USE BIT(3) #define NEIGH_UPDATE_F_MANAGED BIT(4) #define NEIGH_UPDATE_F_EXT_LEARNED BIT(5) #define NEIGH_UPDATE_F_ISROUTER BIT(6) #define NEIGH_UPDATE_F_ADMIN BIT(7) /* In-kernel representation for NDA_FLAGS_EXT flags: */ #define NTF_OLD_MASK 0xff #define NTF_EXT_SHIFT 8 #define NTF_EXT_MASK (NTF_EXT_MANAGED) #define NTF_MANAGED (NTF_EXT_MANAGED << NTF_EXT_SHIFT) extern const struct nla_policy nda_policy[]; static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) { return *(const u32 *)n->primary_key == *(const u32 *)pkey; } static inline bool neigh_key_eq128(const struct neighbour *n, const void *pkey) { const u32 *n32 = (const u32 *)n->primary_key; const u32 *p32 = pkey; return ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) | (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0; } static inline struct neighbour *___neigh_lookup_noref( struct neigh_table *tbl, bool (*key_eq)(const struct neighbour *n, const void *pkey), __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd), const void *pkey, struct net_device *dev) { struct neigh_hash_table *nht = rcu_dereference(tbl->nht); struct neighbour *n; u32 hash_val; hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); for (n = rcu_dereference(nht->hash_buckets[hash_val]); n != NULL; n = rcu_dereference(n->next)) { if (n->dev == dev && key_eq(n, pkey)) return n; } return NULL; } static inline struct neighbour *__neigh_lookup_noref(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { return ___neigh_lookup_noref(tbl, tbl->key_eq, tbl->hash, pkey, dev); } static inline void neigh_confirm(struct neighbour *n) { if (n) { unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); } } void neigh_table_init(int index, struct neigh_table *tbl); int neigh_table_clear(int index, struct neigh_table *tbl); struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev); struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref); static inline struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { return __neigh_create(tbl, pkey, dev, true); } void neigh_destroy(struct neighbour *neigh); int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, const bool immediate_ok); int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev); int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb); struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev); struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl); void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms); static inline struct net *neigh_parms_net(const struct neigh_parms *parms) { return read_pnet(&parms->net); } unsigned long neigh_rand_reach_time(unsigned long base); void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb); struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev, int creat); struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); static inline struct net *pneigh_net(const struct pneigh_entry *pneigh) { return read_pnet(&pneigh->net); } void neigh_app_ns(struct neighbour *n); void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie); void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)); int neigh_xmit(int fam, struct net_device *, const void *, struct sk_buff *); struct neigh_seq_state { struct seq_net_private p; struct neigh_table *tbl; struct neigh_hash_table *nht; void *(*neigh_sub_iter)(struct neigh_seq_state *state, struct neighbour *n, loff_t *pos); unsigned int bucket; unsigned int flags; #define NEIGH_SEQ_NEIGH_ONLY 0x00000001 #define NEIGH_SEQ_IS_PNEIGH 0x00000002 #define NEIGH_SEQ_SKIP_NOARP 0x00000004 }; void *neigh_seq_start(struct seq_file *, loff_t *, struct neigh_table *, unsigned int); void *neigh_seq_next(struct seq_file *, void *, loff_t *); void neigh_seq_stop(struct seq_file *, void *); int neigh_proc_dointvec(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_proc_dointvec_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_proc_dointvec_ms_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, proc_handler *proc_handler); void neigh_sysctl_unregister(struct neigh_parms *p); static inline void __neigh_parms_put(struct neigh_parms *parms) { refcount_dec(&parms->refcnt); } static inline struct neigh_parms *neigh_parms_clone(struct neigh_parms *parms) { refcount_inc(&parms->refcnt); return parms; } /* * Neighbour references */ static inline void neigh_release(struct neighbour *neigh) { if (refcount_dec_and_test(&neigh->refcnt)) neigh_destroy(neigh); } static inline struct neighbour * neigh_clone(struct neighbour *neigh) { if (neigh) refcount_inc(&neigh->refcnt); return neigh; } #define neigh_hold(n) refcount_inc(&(n)->refcnt) static __always_inline int neigh_event_send_probe(struct neighbour *neigh, struct sk_buff *skb, const bool immediate_ok) { unsigned long now = jiffies; if (READ_ONCE(neigh->used) != now) WRITE_ONCE(neigh->used, now); if (!(READ_ONCE(neigh->nud_state) & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))) return __neigh_event_send(neigh, skb, immediate_ok); return 0; } static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { return neigh_event_send_probe(neigh, skb, true); } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) { unsigned int seq, hh_alen; do { seq = read_seqbegin(&hh->hh_lock); hh_alen = HH_DATA_ALIGN(ETH_HLEN); memcpy(skb->data - hh_alen, hh->hh_data, ETH_ALEN + hh_alen - ETH_HLEN); } while (read_seqretry(&hh->hh_lock, seq)); return 0; } #endif static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) { unsigned int hh_alen = 0; unsigned int seq; unsigned int hh_len; do { seq = read_seqbegin(&hh->hh_lock); hh_len = READ_ONCE(hh->hh_len); if (likely(hh_len <= HH_DATA_MOD)) { hh_alen = HH_DATA_MOD; /* skb_push() would proceed silently if we have room for * the unaligned size but not for the aligned size: * check headroom explicitly. */ if (likely(skb_headroom(skb) >= HH_DATA_MOD)) { /* this is inlined by gcc */ memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD); } } else { hh_alen = HH_DATA_ALIGN(hh_len); if (likely(skb_headroom(skb) >= hh_alen)) { memcpy(skb->data - hh_alen, hh->hh_data, hh_alen); } } } while (read_seqretry(&hh->hh_lock, seq)); if (WARN_ON_ONCE(skb_headroom(skb) < hh_alen)) { kfree_skb(skb); return NET_XMIT_DROP; } __skb_push(skb, hh_len); return dev_queue_xmit(skb); } static inline int neigh_output(struct neighbour *n, struct sk_buff *skb, bool skip_cache) { const struct hh_cache *hh = &n->hh; /* n->nud_state and hh->hh_len could be changed under us. * neigh_hh_output() is taking care of the race later. */ if (!skip_cache && (READ_ONCE(n->nud_state) & NUD_CONNECTED) && READ_ONCE(hh->hh_len)) return neigh_hh_output(hh, skb); return READ_ONCE(n->output)(n, skb); } static inline struct neighbour * __neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev, int creat) { struct neighbour *n = neigh_lookup(tbl, pkey, dev); if (n || !creat) return n; n = neigh_create(tbl, pkey, dev); return IS_ERR(n) ? NULL : n; } static inline struct neighbour * __neigh_lookup_errno(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { struct neighbour *n = neigh_lookup(tbl, pkey, dev); if (n) return n; return neigh_create(tbl, pkey, dev); } struct neighbour_cb { unsigned long sched_next; unsigned int flags; }; #define LOCALLY_ENQUEUED 0x1 #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, const struct net_device *dev) { unsigned int seq; do { seq = read_seqbegin(&n->ha_lock); memcpy(dst, n->ha, dev->addr_len); } while (read_seqretry(&n->ha_lock, seq)); } static inline void neigh_update_is_router(struct neighbour *neigh, u32 flags, int *notify) { u8 ndm_flags = 0; ndm_flags |= (flags & NEIGH_UPDATE_F_ISROUTER) ? NTF_ROUTER : 0; if ((neigh->flags ^ ndm_flags) & NTF_ROUTER) { if (ndm_flags & NTF_ROUTER) neigh->flags |= NTF_ROUTER; else neigh->flags &= ~NTF_ROUTER; *notify = 1; } } #endif |
| 5585 986 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2012 Novell Inc. * Copyright (c) 2012-2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org> * Copyright (c) 2012-2019 Linux Foundation * * Core driver model functions and structures that should not be * shared outside of the drivers/base/ directory. * */ #include <linux/notifier.h> /** * struct subsys_private - structure to hold the private to the driver core portions of the bus_type/class structure. * * @subsys - the struct kset that defines this subsystem * @devices_kset - the subsystem's 'devices' directory * @interfaces - list of subsystem interfaces associated * @mutex - protect the devices, and interfaces lists. * * @drivers_kset - the list of drivers associated * @klist_devices - the klist to iterate over the @devices_kset * @klist_drivers - the klist to iterate over the @drivers_kset * @bus_notifier - the bus notifier list for anything that cares about things * on this bus. * @bus - pointer back to the struct bus_type that this structure is associated * with. * @dev_root: Default device to use as the parent. * * @glue_dirs - "glue" directory to put in-between the parent device to * avoid namespace conflicts * @class - pointer back to the struct class that this structure is associated * with. * @lock_key: Lock class key for use by the lock validator * * This structure is the one that is the actual kobject allowing struct * bus_type/class to be statically allocated safely. Nothing outside of the * driver core should ever touch these fields. */ struct subsys_private { struct kset subsys; struct kset *devices_kset; struct list_head interfaces; struct mutex mutex; struct kset *drivers_kset; struct klist klist_devices; struct klist klist_drivers; struct blocking_notifier_head bus_notifier; unsigned int drivers_autoprobe:1; const struct bus_type *bus; struct device *dev_root; struct kset glue_dirs; const struct class *class; struct lock_class_key lock_key; }; #define to_subsys_private(obj) container_of_const(obj, struct subsys_private, subsys.kobj) static inline struct subsys_private *subsys_get(struct subsys_private *sp) { if (sp) kset_get(&sp->subsys); return sp; } static inline void subsys_put(struct subsys_private *sp) { if (sp) kset_put(&sp->subsys); } struct subsys_private *class_to_subsys(const struct class *class); struct driver_private { struct kobject kobj; struct klist klist_devices; struct klist_node knode_bus; struct module_kobject *mkobj; struct device_driver *driver; }; #define to_driver(obj) container_of(obj, struct driver_private, kobj) /** * struct device_private - structure to hold the private to the driver core portions of the device structure. * * @klist_children - klist containing all children of this device * @knode_parent - node in sibling list * @knode_driver - node in driver list * @knode_bus - node in bus list * @knode_class - node in class list * @deferred_probe - entry in deferred_probe_list which is used to retry the * binding of drivers which were unable to get all the resources needed by * the device; typically because it depends on another driver getting * probed first. * @async_driver - pointer to device driver awaiting probe via async_probe * @device - pointer back to the struct device that this structure is * associated with. * @dead - This device is currently either in the process of or has been * removed from the system. Any asynchronous events scheduled for this * device should exit without taking any action. * * Nothing outside of the driver core should ever touch these fields. */ struct device_private { struct klist klist_children; struct klist_node knode_parent; struct klist_node knode_driver; struct klist_node knode_bus; struct klist_node knode_class; struct list_head deferred_probe; const struct device_driver *async_driver; char *deferred_probe_reason; struct device *device; u8 dead:1; }; #define to_device_private_parent(obj) \ container_of(obj, struct device_private, knode_parent) #define to_device_private_driver(obj) \ container_of(obj, struct device_private, knode_driver) #define to_device_private_bus(obj) \ container_of(obj, struct device_private, knode_bus) #define to_device_private_class(obj) \ container_of(obj, struct device_private, knode_class) /* initialisation functions */ int devices_init(void); int buses_init(void); int classes_init(void); int firmware_init(void); #ifdef CONFIG_SYS_HYPERVISOR int hypervisor_init(void); #else static inline int hypervisor_init(void) { return 0; } #endif int platform_bus_init(void); void cpu_dev_init(void); void container_dev_init(void); #ifdef CONFIG_AUXILIARY_BUS void auxiliary_bus_init(void); #else static inline void auxiliary_bus_init(void) { } #endif struct kobject *virtual_device_parent(struct device *dev); int bus_add_device(struct device *dev); void bus_probe_device(struct device *dev); void bus_remove_device(struct device *dev); void bus_notify(struct device *dev, enum bus_notifier_event value); bool bus_is_registered(const struct bus_type *bus); int bus_add_driver(struct device_driver *drv); void bus_remove_driver(struct device_driver *drv); void device_release_driver_internal(struct device *dev, const struct device_driver *drv, struct device *parent); void driver_detach(const struct device_driver *drv); void driver_deferred_probe_del(struct device *dev); void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf); static inline int driver_match_device(const struct device_driver *drv, struct device *dev) { return drv->bus->match ? drv->bus->match(dev, drv) : 1; } static inline void dev_sync_state(struct device *dev) { if (dev->bus->sync_state) dev->bus->sync_state(dev); else if (dev->driver && dev->driver->sync_state) dev->driver->sync_state(dev); } int driver_add_groups(const struct device_driver *drv, const struct attribute_group **groups); void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups); void device_driver_detach(struct device *dev); int devres_release_all(struct device *dev); void device_block_probing(void); void device_unblock_probing(void); void deferred_probe_extend_timeout(void); void driver_deferred_probe_trigger(void); const char *device_get_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); /* /sys/devices directory */ extern struct kset *devices_kset; void devices_kset_move_last(struct device *dev); #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS) int module_add_driver(struct module *mod, const struct device_driver *drv); void module_remove_driver(const struct device_driver *drv); #else static inline int module_add_driver(struct module *mod, struct device_driver *drv) { return 0; } static inline void module_remove_driver(struct device_driver *drv) { } #endif #ifdef CONFIG_DEVTMPFS int devtmpfs_init(void); #else static inline int devtmpfs_init(void) { return 0; } #endif #ifdef CONFIG_BLOCK extern const struct class block_class; static inline bool is_blockdev(struct device *dev) { return dev->class == &block_class; } #else static inline bool is_blockdev(struct device *dev) { return false; } #endif /* Device links support */ int device_links_read_lock(void); void device_links_read_unlock(int idx); int device_links_read_lock_held(void); int device_links_check_suppliers(struct device *dev); void device_links_force_bind(struct device *dev); void device_links_driver_bound(struct device *dev); void device_links_driver_cleanup(struct device *dev); void device_links_no_driver(struct device *dev); bool device_links_busy(struct device *dev); void device_links_unbind_consumers(struct device *dev); void fw_devlink_drivers_done(void); void fw_devlink_probing_done(void); /* device pm support */ void device_pm_move_to_tail(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_create_node(struct device *dev); int devtmpfs_delete_node(struct device *dev); #else static inline int devtmpfs_create_node(struct device *dev) { return 0; } static inline int devtmpfs_delete_node(struct device *dev) { return 0; } #endif void software_node_notify(struct device *dev); void software_node_notify_remove(struct device *dev); |
| 1 1 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 | // SPDX-License-Identifier: GPL-2.0-only /* * NFC Digital Protocol stack * Copyright (c) 2013, Intel Corporation. */ #define pr_fmt(fmt) "digital: %s: " fmt, __func__ #include <linux/module.h> #include "digital.h" #define DIGITAL_PROTO_NFCA_RF_TECH \ (NFC_PROTO_JEWEL_MASK | NFC_PROTO_MIFARE_MASK | \ NFC_PROTO_NFC_DEP_MASK | NFC_PROTO_ISO14443_MASK) #define DIGITAL_PROTO_NFCB_RF_TECH NFC_PROTO_ISO14443_B_MASK #define DIGITAL_PROTO_NFCF_RF_TECH \ (NFC_PROTO_FELICA_MASK | NFC_PROTO_NFC_DEP_MASK) #define DIGITAL_PROTO_ISO15693_RF_TECH NFC_PROTO_ISO15693_MASK /* Delay between each poll frame (ms) */ #define DIGITAL_POLL_INTERVAL 10 struct digital_cmd { struct list_head queue; u8 type; u8 pending; u16 timeout; struct sk_buff *req; struct sk_buff *resp; struct digital_tg_mdaa_params *mdaa_params; nfc_digital_cmd_complete_t cmd_cb; void *cb_context; }; struct sk_buff *digital_skb_alloc(struct nfc_digital_dev *ddev, unsigned int len) { struct sk_buff *skb; skb = alloc_skb(len + ddev->tx_headroom + ddev->tx_tailroom, GFP_KERNEL); if (skb) skb_reserve(skb, ddev->tx_headroom); return skb; } void digital_skb_add_crc(struct sk_buff *skb, crc_func_t crc_func, u16 init, u8 bitwise_inv, u8 msb_first) { u16 crc; crc = crc_func(init, skb->data, skb->len); if (bitwise_inv) crc = ~crc; if (msb_first) crc = __fswab16(crc); skb_put_u8(skb, crc & 0xFF); skb_put_u8(skb, (crc >> 8) & 0xFF); } int digital_skb_check_crc(struct sk_buff *skb, crc_func_t crc_func, u16 crc_init, u8 bitwise_inv, u8 msb_first) { int rc; u16 crc; if (skb->len <= 2) return -EIO; crc = crc_func(crc_init, skb->data, skb->len - 2); if (bitwise_inv) crc = ~crc; if (msb_first) crc = __swab16(crc); rc = (skb->data[skb->len - 2] - (crc & 0xFF)) + (skb->data[skb->len - 1] - ((crc >> 8) & 0xFF)); if (rc) return -EIO; skb_trim(skb, skb->len - 2); return 0; } static inline void digital_switch_rf(struct nfc_digital_dev *ddev, bool on) { ddev->ops->switch_rf(ddev, on); } static inline void digital_abort_cmd(struct nfc_digital_dev *ddev) { ddev->ops->abort_cmd(ddev); } static void digital_wq_cmd_complete(struct work_struct *work) { struct digital_cmd *cmd; struct nfc_digital_dev *ddev = container_of(work, struct nfc_digital_dev, cmd_complete_work); mutex_lock(&ddev->cmd_lock); cmd = list_first_entry_or_null(&ddev->cmd_queue, struct digital_cmd, queue); if (!cmd) { mutex_unlock(&ddev->cmd_lock); return; } list_del(&cmd->queue); mutex_unlock(&ddev->cmd_lock); if (!IS_ERR(cmd->resp)) print_hex_dump_debug("DIGITAL RX: ", DUMP_PREFIX_NONE, 16, 1, cmd->resp->data, cmd->resp->len, false); cmd->cmd_cb(ddev, cmd->cb_context, cmd->resp); kfree(cmd->mdaa_params); kfree(cmd); schedule_work(&ddev->cmd_work); } static void digital_send_cmd_complete(struct nfc_digital_dev *ddev, void *arg, struct sk_buff *resp) { struct digital_cmd *cmd = arg; cmd->resp = resp; schedule_work(&ddev->cmd_complete_work); } static void digital_wq_cmd(struct work_struct *work) { int rc; struct digital_cmd *cmd; struct digital_tg_mdaa_params *params; struct nfc_digital_dev *ddev = container_of(work, struct nfc_digital_dev, cmd_work); mutex_lock(&ddev->cmd_lock); cmd = list_first_entry_or_null(&ddev->cmd_queue, struct digital_cmd, queue); if (!cmd || cmd->pending) { mutex_unlock(&ddev->cmd_lock); return; } cmd->pending = 1; mutex_unlock(&ddev->cmd_lock); if (cmd->req) print_hex_dump_debug("DIGITAL TX: ", DUMP_PREFIX_NONE, 16, 1, cmd->req->data, cmd->req->len, false); switch (cmd->type) { case DIGITAL_CMD_IN_SEND: rc = ddev->ops->in_send_cmd(ddev, cmd->req, cmd->timeout, digital_send_cmd_complete, cmd); break; case DIGITAL_CMD_TG_SEND: rc = ddev->ops->tg_send_cmd(ddev, cmd->req, cmd->timeout, digital_send_cmd_complete, cmd); break; case DIGITAL_CMD_TG_LISTEN: rc = ddev->ops->tg_listen(ddev, cmd->timeout, digital_send_cmd_complete, cmd); break; case DIGITAL_CMD_TG_LISTEN_MDAA: params = cmd->mdaa_params; rc = ddev->ops->tg_listen_mdaa(ddev, params, cmd->timeout, digital_send_cmd_complete, cmd); break; case DIGITAL_CMD_TG_LISTEN_MD: rc = ddev->ops->tg_listen_md(ddev, cmd->timeout, digital_send_cmd_complete, cmd); break; default: pr_err("Unknown cmd type %d\n", cmd->type); return; } if (!rc) return; pr_err("in_send_command returned err %d\n", rc); mutex_lock(&ddev->cmd_lock); list_del(&cmd->queue); mutex_unlock(&ddev->cmd_lock); kfree_skb(cmd->req); kfree(cmd->mdaa_params); kfree(cmd); schedule_work(&ddev->cmd_work); } int digital_send_cmd(struct nfc_digital_dev *ddev, u8 cmd_type, struct sk_buff *skb, struct digital_tg_mdaa_params *params, u16 timeout, nfc_digital_cmd_complete_t cmd_cb, void *cb_context) { struct digital_cmd *cmd; cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); if (!cmd) return -ENOMEM; cmd->type = cmd_type; cmd->timeout = timeout; cmd->req = skb; cmd->mdaa_params = params; cmd->cmd_cb = cmd_cb; cmd->cb_context = cb_context; INIT_LIST_HEAD(&cmd->queue); mutex_lock(&ddev->cmd_lock); list_add_tail(&cmd->queue, &ddev->cmd_queue); mutex_unlock(&ddev->cmd_lock); schedule_work(&ddev->cmd_work); return 0; } int digital_in_configure_hw(struct nfc_digital_dev *ddev, int type, int param) { int rc; rc = ddev->ops->in_configure_hw(ddev, type, param); if (rc) pr_err("in_configure_hw failed: %d\n", rc); return rc; } int digital_tg_configure_hw(struct nfc_digital_dev *ddev, int type, int param) { int rc; rc = ddev->ops->tg_configure_hw(ddev, type, param); if (rc) pr_err("tg_configure_hw failed: %d\n", rc); return rc; } static int digital_tg_listen_mdaa(struct nfc_digital_dev *ddev, u8 rf_tech) { struct digital_tg_mdaa_params *params; int rc; params = kzalloc(sizeof(*params), GFP_KERNEL); if (!params) return -ENOMEM; params->sens_res = DIGITAL_SENS_RES_NFC_DEP; get_random_bytes(params->nfcid1, sizeof(params->nfcid1)); params->sel_res = DIGITAL_SEL_RES_NFC_DEP; params->nfcid2[0] = DIGITAL_SENSF_NFCID2_NFC_DEP_B1; params->nfcid2[1] = DIGITAL_SENSF_NFCID2_NFC_DEP_B2; get_random_bytes(params->nfcid2 + 2, NFC_NFCID2_MAXSIZE - 2); params->sc = DIGITAL_SENSF_FELICA_SC; rc = digital_send_cmd(ddev, DIGITAL_CMD_TG_LISTEN_MDAA, NULL, params, 500, digital_tg_recv_atr_req, NULL); if (rc) kfree(params); return rc; } static int digital_tg_listen_md(struct nfc_digital_dev *ddev, u8 rf_tech) { return digital_send_cmd(ddev, DIGITAL_CMD_TG_LISTEN_MD, NULL, NULL, 500, digital_tg_recv_md_req, NULL); } int digital_target_found(struct nfc_digital_dev *ddev, struct nfc_target *target, u8 protocol) { int rc; u8 framing; u8 rf_tech; u8 poll_tech_count; int (*check_crc)(struct sk_buff *skb); void (*add_crc)(struct sk_buff *skb); rf_tech = ddev->poll_techs[ddev->poll_tech_index].rf_tech; switch (protocol) { case NFC_PROTO_JEWEL: framing = NFC_DIGITAL_FRAMING_NFCA_T1T; check_crc = digital_skb_check_crc_b; add_crc = digital_skb_add_crc_b; break; case NFC_PROTO_MIFARE: framing = NFC_DIGITAL_FRAMING_NFCA_T2T; check_crc = digital_skb_check_crc_a; add_crc = digital_skb_add_crc_a; break; case NFC_PROTO_FELICA: framing = NFC_DIGITAL_FRAMING_NFCF_T3T; check_crc = digital_skb_check_crc_f; add_crc = digital_skb_add_crc_f; break; case NFC_PROTO_NFC_DEP: if (rf_tech == NFC_DIGITAL_RF_TECH_106A) { framing = NFC_DIGITAL_FRAMING_NFCA_NFC_DEP; check_crc = digital_skb_check_crc_a; add_crc = digital_skb_add_crc_a; } else { framing = NFC_DIGITAL_FRAMING_NFCF_NFC_DEP; check_crc = digital_skb_check_crc_f; add_crc = digital_skb_add_crc_f; } break; case NFC_PROTO_ISO15693: framing = NFC_DIGITAL_FRAMING_ISO15693_T5T; check_crc = digital_skb_check_crc_b; add_crc = digital_skb_add_crc_b; break; case NFC_PROTO_ISO14443: framing = NFC_DIGITAL_FRAMING_NFCA_T4T; check_crc = digital_skb_check_crc_a; add_crc = digital_skb_add_crc_a; break; case NFC_PROTO_ISO14443_B: framing = NFC_DIGITAL_FRAMING_NFCB_T4T; check_crc = digital_skb_check_crc_b; add_crc = digital_skb_add_crc_b; break; default: pr_err("Invalid protocol %d\n", protocol); return -EINVAL; } pr_debug("rf_tech=%d, protocol=%d\n", rf_tech, protocol); ddev->curr_rf_tech = rf_tech; if (DIGITAL_DRV_CAPS_IN_CRC(ddev)) { ddev->skb_add_crc = digital_skb_add_crc_none; ddev->skb_check_crc = digital_skb_check_crc_none; } else { ddev->skb_add_crc = add_crc; ddev->skb_check_crc = check_crc; } rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, framing); if (rc) return rc; target->supported_protocols = (1 << protocol); poll_tech_count = ddev->poll_tech_count; ddev->poll_tech_count = 0; rc = nfc_targets_found(ddev->nfc_dev, target, 1); if (rc) { ddev->poll_tech_count = poll_tech_count; return rc; } return 0; } void digital_poll_next_tech(struct nfc_digital_dev *ddev) { u8 rand_mod; digital_switch_rf(ddev, 0); mutex_lock(&ddev->poll_lock); if (!ddev->poll_tech_count) { mutex_unlock(&ddev->poll_lock); return; } get_random_bytes(&rand_mod, sizeof(rand_mod)); ddev->poll_tech_index = rand_mod % ddev->poll_tech_count; mutex_unlock(&ddev->poll_lock); schedule_delayed_work(&ddev->poll_work, msecs_to_jiffies(DIGITAL_POLL_INTERVAL)); } static void digital_wq_poll(struct work_struct *work) { int rc; struct digital_poll_tech *poll_tech; struct nfc_digital_dev *ddev = container_of(work, struct nfc_digital_dev, poll_work.work); mutex_lock(&ddev->poll_lock); if (!ddev->poll_tech_count) { mutex_unlock(&ddev->poll_lock); return; } poll_tech = &ddev->poll_techs[ddev->poll_tech_index]; mutex_unlock(&ddev->poll_lock); rc = poll_tech->poll_func(ddev, poll_tech->rf_tech); if (rc) digital_poll_next_tech(ddev); } static void digital_add_poll_tech(struct nfc_digital_dev *ddev, u8 rf_tech, digital_poll_t poll_func) { struct digital_poll_tech *poll_tech; if (ddev->poll_tech_count >= NFC_DIGITAL_POLL_MODE_COUNT_MAX) return; poll_tech = &ddev->poll_techs[ddev->poll_tech_count++]; poll_tech->rf_tech = rf_tech; poll_tech->poll_func = poll_func; } /** * digital_start_poll - start_poll operation * @nfc_dev: device to be polled * @im_protocols: bitset of nfc initiator protocols to be used for polling * @tm_protocols: bitset of nfc transport protocols to be used for polling * * For every supported protocol, the corresponding polling function is added * to the table of polling technologies (ddev->poll_techs[]) using * digital_add_poll_tech(). * When a polling function fails (by timeout or protocol error) the next one is * schedule by digital_poll_next_tech() on the poll workqueue (ddev->poll_work). */ static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols, __u32 tm_protocols) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); u32 matching_im_protocols, matching_tm_protocols; pr_debug("protocols: im 0x%x, tm 0x%x, supported 0x%x\n", im_protocols, tm_protocols, ddev->protocols); matching_im_protocols = ddev->protocols & im_protocols; matching_tm_protocols = ddev->protocols & tm_protocols; if (!matching_im_protocols && !matching_tm_protocols) { pr_err("Unknown protocol\n"); return -EINVAL; } if (ddev->poll_tech_count) { pr_err("Already polling\n"); return -EBUSY; } if (ddev->curr_protocol) { pr_err("A target is already active\n"); return -EBUSY; } ddev->poll_tech_count = 0; ddev->poll_tech_index = 0; if (matching_im_protocols & DIGITAL_PROTO_NFCA_RF_TECH) digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106A, digital_in_send_sens_req); if (matching_im_protocols & DIGITAL_PROTO_NFCB_RF_TECH) digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106B, digital_in_send_sensb_req); if (matching_im_protocols & DIGITAL_PROTO_NFCF_RF_TECH) { digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_212F, digital_in_send_sensf_req); digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_424F, digital_in_send_sensf_req); } if (matching_im_protocols & DIGITAL_PROTO_ISO15693_RF_TECH) digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_ISO15693, digital_in_send_iso15693_inv_req); if (matching_tm_protocols & NFC_PROTO_NFC_DEP_MASK) { if (ddev->ops->tg_listen_mdaa) { digital_add_poll_tech(ddev, 0, digital_tg_listen_mdaa); } else if (ddev->ops->tg_listen_md) { digital_add_poll_tech(ddev, 0, digital_tg_listen_md); } else { digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106A, digital_tg_listen_nfca); digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_212F, digital_tg_listen_nfcf); digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_424F, digital_tg_listen_nfcf); } } if (!ddev->poll_tech_count) { pr_err("Unsupported protocols: im=0x%x, tm=0x%x\n", matching_im_protocols, matching_tm_protocols); return -EINVAL; } schedule_delayed_work(&ddev->poll_work, 0); return 0; } static void digital_stop_poll(struct nfc_dev *nfc_dev) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); mutex_lock(&ddev->poll_lock); if (!ddev->poll_tech_count) { pr_err("Polling operation was not running\n"); mutex_unlock(&ddev->poll_lock); return; } ddev->poll_tech_count = 0; mutex_unlock(&ddev->poll_lock); cancel_delayed_work_sync(&ddev->poll_work); digital_abort_cmd(ddev); } static int digital_dev_up(struct nfc_dev *nfc_dev) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); digital_switch_rf(ddev, 1); return 0; } static int digital_dev_down(struct nfc_dev *nfc_dev) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); digital_switch_rf(ddev, 0); return 0; } static int digital_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target, __u8 comm_mode, __u8 *gb, size_t gb_len) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); int rc; rc = digital_in_send_atr_req(ddev, target, comm_mode, gb, gb_len); if (!rc) ddev->curr_protocol = NFC_PROTO_NFC_DEP; return rc; } static int digital_dep_link_down(struct nfc_dev *nfc_dev) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); digital_abort_cmd(ddev); ddev->curr_protocol = 0; return 0; } static int digital_activate_target(struct nfc_dev *nfc_dev, struct nfc_target *target, __u32 protocol) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); if (ddev->poll_tech_count) { pr_err("Can't activate a target while polling\n"); return -EBUSY; } if (ddev->curr_protocol) { pr_err("A target is already active\n"); return -EBUSY; } ddev->curr_protocol = protocol; return 0; } static void digital_deactivate_target(struct nfc_dev *nfc_dev, struct nfc_target *target, u8 mode) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); if (!ddev->curr_protocol) { pr_err("No active target\n"); return; } digital_abort_cmd(ddev); ddev->curr_protocol = 0; } static int digital_tg_send(struct nfc_dev *dev, struct sk_buff *skb) { struct nfc_digital_dev *ddev = nfc_get_drvdata(dev); return digital_tg_send_dep_res(ddev, skb); } static void digital_in_send_complete(struct nfc_digital_dev *ddev, void *arg, struct sk_buff *resp) { struct digital_data_exch *data_exch = arg; int rc; if (IS_ERR(resp)) { rc = PTR_ERR(resp); resp = NULL; goto done; } if (ddev->curr_protocol == NFC_PROTO_MIFARE) { rc = digital_in_recv_mifare_res(resp); /* crc check is done in digital_in_recv_mifare_res() */ goto done; } if ((ddev->curr_protocol == NFC_PROTO_ISO14443) || (ddev->curr_protocol == NFC_PROTO_ISO14443_B)) { rc = digital_in_iso_dep_pull_sod(ddev, resp); if (rc) goto done; } rc = ddev->skb_check_crc(resp); done: if (rc) { kfree_skb(resp); resp = NULL; } data_exch->cb(data_exch->cb_context, resp, rc); kfree(data_exch); } static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, struct sk_buff *skb, data_exchange_cb_t cb, void *cb_context) { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); struct digital_data_exch *data_exch; int rc; data_exch = kzalloc(sizeof(*data_exch), GFP_KERNEL); if (!data_exch) return -ENOMEM; data_exch->cb = cb; data_exch->cb_context = cb_context; if (ddev->curr_protocol == NFC_PROTO_NFC_DEP) { rc = digital_in_send_dep_req(ddev, target, skb, data_exch); goto exit; } if ((ddev->curr_protocol == NFC_PROTO_ISO14443) || (ddev->curr_protocol == NFC_PROTO_ISO14443_B)) { rc = digital_in_iso_dep_push_sod(ddev, skb); if (rc) goto exit; } ddev->skb_add_crc(skb); rc = digital_in_send_cmd(ddev, skb, 500, digital_in_send_complete, data_exch); exit: if (rc) kfree(data_exch); return rc; } static const struct nfc_ops digital_nfc_ops = { .dev_up = digital_dev_up, .dev_down = digital_dev_down, .start_poll = digital_start_poll, .stop_poll = digital_stop_poll, .dep_link_up = digital_dep_link_up, .dep_link_down = digital_dep_link_down, .activate_target = digital_activate_target, .deactivate_target = digital_deactivate_target, .tm_send = digital_tg_send, .im_transceive = digital_in_send, }; struct nfc_digital_dev *nfc_digital_allocate_device(const struct nfc_digital_ops *ops, __u32 supported_protocols, __u32 driver_capabilities, int tx_headroom, int tx_tailroom) { struct nfc_digital_dev *ddev; if (!ops->in_configure_hw || !ops->in_send_cmd || !ops->tg_listen || !ops->tg_configure_hw || !ops->tg_send_cmd || !ops->abort_cmd || !ops->switch_rf || (ops->tg_listen_md && !ops->tg_get_rf_tech)) return NULL; ddev = kzalloc(sizeof(*ddev), GFP_KERNEL); if (!ddev) return NULL; ddev->driver_capabilities = driver_capabilities; ddev->ops = ops; mutex_init(&ddev->cmd_lock); INIT_LIST_HEAD(&ddev->cmd_queue); INIT_WORK(&ddev->cmd_work, digital_wq_cmd); INIT_WORK(&ddev->cmd_complete_work, digital_wq_cmd_complete); mutex_init(&ddev->poll_lock); INIT_DELAYED_WORK(&ddev->poll_work, digital_wq_poll); if (supported_protocols & NFC_PROTO_JEWEL_MASK) ddev->protocols |= NFC_PROTO_JEWEL_MASK; if (supported_protocols & NFC_PROTO_MIFARE_MASK) ddev->protocols |= NFC_PROTO_MIFARE_MASK; if (supported_protocols & NFC_PROTO_FELICA_MASK) ddev->protocols |= NFC_PROTO_FELICA_MASK; if (supported_protocols & NFC_PROTO_NFC_DEP_MASK) ddev->protocols |= NFC_PROTO_NFC_DEP_MASK; if (supported_protocols & NFC_PROTO_ISO15693_MASK) ddev->protocols |= NFC_PROTO_ISO15693_MASK; if (supported_protocols & NFC_PROTO_ISO14443_MASK) ddev->protocols |= NFC_PROTO_ISO14443_MASK; if (supported_protocols & NFC_PROTO_ISO14443_B_MASK) ddev->protocols |= NFC_PROTO_ISO14443_B_MASK; ddev->tx_headroom = tx_headroom + DIGITAL_MAX_HEADER_LEN; ddev->tx_tailroom = tx_tailroom + DIGITAL_CRC_LEN; ddev->nfc_dev = nfc_allocate_device(&digital_nfc_ops, ddev->protocols, ddev->tx_headroom, ddev->tx_tailroom); if (!ddev->nfc_dev) { pr_err("nfc_allocate_device failed\n"); goto free_dev; } nfc_set_drvdata(ddev->nfc_dev, ddev); return ddev; free_dev: kfree(ddev); return NULL; } EXPORT_SYMBOL(nfc_digital_allocate_device); void nfc_digital_free_device(struct nfc_digital_dev *ddev) { nfc_free_device(ddev->nfc_dev); kfree(ddev); } EXPORT_SYMBOL(nfc_digital_free_device); int nfc_digital_register_device(struct nfc_digital_dev *ddev) { return nfc_register_device(ddev->nfc_dev); } EXPORT_SYMBOL(nfc_digital_register_device); void nfc_digital_unregister_device(struct nfc_digital_dev *ddev) { struct digital_cmd *cmd, *n; nfc_unregister_device(ddev->nfc_dev); mutex_lock(&ddev->poll_lock); ddev->poll_tech_count = 0; mutex_unlock(&ddev->poll_lock); cancel_delayed_work_sync(&ddev->poll_work); cancel_work_sync(&ddev->cmd_work); cancel_work_sync(&ddev->cmd_complete_work); list_for_each_entry_safe(cmd, n, &ddev->cmd_queue, queue) { list_del(&cmd->queue); /* Call the command callback if any and pass it a ENODEV error. * This gives a chance to the command issuer to free any * allocated buffer. */ if (cmd->cmd_cb) cmd->cmd_cb(ddev, cmd->cb_context, ERR_PTR(-ENODEV)); kfree(cmd->mdaa_params); kfree(cmd); } } EXPORT_SYMBOL(nfc_digital_unregister_device); MODULE_DESCRIPTION("NFC Digital protocol stack"); MODULE_LICENSE("GPL"); |
| 876 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ICMPV6_H #define _LINUX_ICMPV6_H #include <linux/skbuff.h> #include <linux/ipv6.h> #include <uapi/linux/icmpv6.h> static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) { return (struct icmp6hdr *)skb_transport_header(skb); } #include <linux/netdevice.h> #if IS_ENABLED(CONFIG_IPV6) typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr, const struct inet6_skb_parm *parm); void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr, const struct inet6_skb_parm *parm); #if IS_BUILTIN(CONFIG_IPV6) static inline void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct inet6_skb_parm *parm) { icmp6_send(skb, type, code, info, NULL, parm); } static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn) { BUILD_BUG_ON(fn != icmp6_send); return 0; } static inline int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) { BUILD_BUG_ON(fn != icmp6_send); return 0; } #else extern void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct inet6_skb_parm *parm); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); #endif static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { __icmpv6_send(skb, type, code, info, IP6CB(skb)); } int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); #if IS_ENABLED(CONFIG_NF_NAT) void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); #else static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) { struct inet6_skb_parm parm = { 0 }; __icmpv6_send(skb_in, type, code, info, &parm); } #endif #else static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { } static inline void icmpv6_ndo_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { } #endif extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, int *err); extern void icmpv6_cleanup(void); extern void icmpv6_param_prob_reason(struct sk_buff *skb, u8 code, int pos, enum skb_drop_reason reason); struct flowi6; struct in6_addr; void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif); static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { icmpv6_param_prob_reason(skb, code, pos, SKB_DROP_REASON_NOT_SPECIFIED); } static inline bool icmpv6_is_err(int type) { switch (type) { case ICMPV6_DEST_UNREACH: case ICMPV6_PKT_TOOBIG: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: return true; } return false; } #endif |
| 1977 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UNWIND_H #define _ASM_X86_UNWIND_H #include <linux/sched.h> #include <linux/ftrace.h> #include <linux/rethook.h> #include <asm/ptrace.h> #include <asm/stacktrace.h> #define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip)) #define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET) struct unwind_state { struct stack_info stack_info; unsigned long stack_mask; struct task_struct *task; int graph_idx; #if defined(CONFIG_RETHOOK) struct llist_node *kr_cur; #endif bool error; #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; /* * If non-NULL: The current frame is incomplete and doesn't contain a * valid BP. When looking for the next frame, use this instead of the * non-existent saved BP. */ unsigned long *next_bp; struct pt_regs *regs; #else unsigned long *sp; #endif }; void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame); bool unwind_next_frame(struct unwind_state *state); unsigned long unwind_get_return_address(struct unwind_state *state); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state); static inline bool unwind_done(struct unwind_state *state) { return state->stack_info.type == STACK_TYPE_UNKNOWN; } static inline bool unwind_error(struct unwind_state *state) { return state->error; } static inline void unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame) { first_frame = first_frame ? : get_stack_pointer(task, regs); __unwind_start(state, task, regs, first_frame); } #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) /* * If 'partial' returns true, only the iret frame registers are valid. */ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, bool *partial) { if (unwind_done(state)) return NULL; if (partial) { #ifdef CONFIG_UNWINDER_ORC *partial = !state->full_regs; #else *partial = false; #endif } return state->regs; } #else static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, bool *partial) { return NULL; } #endif #ifdef CONFIG_UNWINDER_ORC void unwind_init(void); void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size); #else static inline void unwind_init(void) {} static inline void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size) {} #endif static inline unsigned long unwind_recover_rethook(struct unwind_state *state, unsigned long addr, unsigned long *addr_p) { #ifdef CONFIG_RETHOOK if (is_rethook_trampoline(addr)) return rethook_find_ret_addr(state->task, (unsigned long)addr_p, &state->kr_cur); #endif return addr; } /* Recover the return address modified by rethook and ftrace_graph. */ static inline unsigned long unwind_recover_ret_addr(struct unwind_state *state, unsigned long addr, unsigned long *addr_p) { unsigned long ret; ret = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr, addr_p); return unwind_recover_rethook(state, ret, addr_p); } /* * This disables KASAN checking when reading a value from another task's stack, * since the other task could be running on another CPU and could have poisoned * the stack in the meantime. */ #define READ_ONCE_TASK_STACK(task, x) \ ({ \ unsigned long val; \ if (task == current) \ val = READ_ONCE(x); \ else \ val = READ_ONCE_NOCHECK(x); \ val; \ }) static inline bool task_on_another_cpu(struct task_struct *task) { #ifdef CONFIG_SMP return task != current && task->on_cpu; #else return false; #endif } #endif /* _ASM_X86_UNWIND_H */ |
| 502 124 71 59 25 25 491 196 175 24 423 449 449 449 464 4 445 62 21 113 337 113 447 450 443 11 449 449 450 427 31 404 96 445 2 405 219 445 445 1 445 410 409 8 409 113 113 113 113 113 113 113 2257 1486 915 5 4 547 547 544 540 547 338 3 660 4 4 3 1 335 37 1 35 1 456 381 230 254 452 1 142 245 96 235 13 123 98 218 4 2 212 452 37 2 35 457 3 1 2 1 2 6 1 5 6 1 114 100 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 | // SPDX-License-Identifier: GPL-2.0-or-later /* Basic authentication token and access key management * * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/init.h> #include <linux/poison.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/workqueue.h> #include <linux/random.h> #include <linux/err.h> #include "internal.h" struct kmem_cache *key_jar; struct rb_root key_serial_tree; /* tree of keys indexed by serial */ DEFINE_SPINLOCK(key_serial_lock); struct rb_root key_user_tree; /* tree of quota records indexed by UID */ DEFINE_SPINLOCK(key_user_lock); unsigned int key_quota_root_maxkeys = 1000000; /* root's key count quota */ unsigned int key_quota_root_maxbytes = 25000000; /* root's key space quota */ unsigned int key_quota_maxkeys = 200; /* general key count quota */ unsigned int key_quota_maxbytes = 20000; /* general key space quota */ static LIST_HEAD(key_types_list); static DECLARE_RWSEM(key_types_sem); /* We serialise key instantiation and link */ DEFINE_MUTEX(key_construction_mutex); #ifdef KEY_DEBUGGING void __key_check(const struct key *key) { printk("__key_check: key %p {%08x} should be {%08x}\n", key, key->magic, KEY_DEBUG_MAGIC); BUG(); } #endif /* * Get the key quota record for a user, allocating a new record if one doesn't * already exist. */ struct key_user *key_user_lookup(kuid_t uid) { struct key_user *candidate = NULL, *user; struct rb_node *parent, **p; try_again: parent = NULL; p = &key_user_tree.rb_node; spin_lock(&key_user_lock); /* search the tree for a user record with a matching UID */ while (*p) { parent = *p; user = rb_entry(parent, struct key_user, node); if (uid_lt(uid, user->uid)) p = &(*p)->rb_left; else if (uid_gt(uid, user->uid)) p = &(*p)->rb_right; else goto found; } /* if we get here, we failed to find a match in the tree */ if (!candidate) { /* allocate a candidate user record if we don't already have * one */ spin_unlock(&key_user_lock); user = NULL; candidate = kmalloc(sizeof(struct key_user), GFP_KERNEL); if (unlikely(!candidate)) goto out; /* the allocation may have scheduled, so we need to repeat the * search lest someone else added the record whilst we were * asleep */ goto try_again; } /* if we get here, then the user record still hadn't appeared on the * second pass - so we use the candidate record */ refcount_set(&candidate->usage, 1); atomic_set(&candidate->nkeys, 0); atomic_set(&candidate->nikeys, 0); candidate->uid = uid; candidate->qnkeys = 0; candidate->qnbytes = 0; spin_lock_init(&candidate->lock); mutex_init(&candidate->cons_lock); rb_link_node(&candidate->node, parent, p); rb_insert_color(&candidate->node, &key_user_tree); spin_unlock(&key_user_lock); user = candidate; goto out; /* okay - we found a user record for this UID */ found: refcount_inc(&user->usage); spin_unlock(&key_user_lock); kfree(candidate); out: return user; } /* * Dispose of a user structure */ void key_user_put(struct key_user *user) { if (refcount_dec_and_lock(&user->usage, &key_user_lock)) { rb_erase(&user->node, &key_user_tree); spin_unlock(&key_user_lock); kfree(user); } } /* * Allocate a serial number for a key. These are assigned randomly to avoid * security issues through covert channel problems. */ static inline void key_alloc_serial(struct key *key) { struct rb_node *parent, **p; struct key *xkey; /* propose a random serial number and look for a hole for it in the * serial number tree */ do { get_random_bytes(&key->serial, sizeof(key->serial)); key->serial >>= 1; /* negative numbers are not permitted */ } while (key->serial < 3); spin_lock(&key_serial_lock); attempt_insertion: parent = NULL; p = &key_serial_tree.rb_node; while (*p) { parent = *p; xkey = rb_entry(parent, struct key, serial_node); if (key->serial < xkey->serial) p = &(*p)->rb_left; else if (key->serial > xkey->serial) p = &(*p)->rb_right; else goto serial_exists; } /* we've found a suitable hole - arrange for this key to occupy it */ rb_link_node(&key->serial_node, parent, p); rb_insert_color(&key->serial_node, &key_serial_tree); spin_unlock(&key_serial_lock); return; /* we found a key with the proposed serial number - walk the tree from * that point looking for the next unused serial number */ serial_exists: for (;;) { key->serial++; if (key->serial < 3) { key->serial = 3; goto attempt_insertion; } parent = rb_next(parent); if (!parent) goto attempt_insertion; xkey = rb_entry(parent, struct key, serial_node); if (key->serial < xkey->serial) goto attempt_insertion; } } /** * key_alloc - Allocate a key of the specified type. * @type: The type of key to allocate. * @desc: The key description to allow the key to be searched out. * @uid: The owner of the new key. * @gid: The group ID for the new key's group permissions. * @cred: The credentials specifying UID namespace. * @perm: The permissions mask of the new key. * @flags: Flags specifying quota properties. * @restrict_link: Optional link restriction for new keyrings. * * Allocate a key of the specified type with the attributes given. The key is * returned in an uninstantiated state and the caller needs to instantiate the * key before returning. * * The restrict_link structure (if not NULL) will be freed when the * keyring is destroyed, so it must be dynamically allocated. * * The user's key count quota is updated to reflect the creation of the key and * the user's key data quota has the default for the key type reserved. The * instantiation function should amend this as necessary. If insufficient * quota is available, -EDQUOT will be returned. * * The LSM security modules can prevent a key being created, in which case * -EACCES will be returned. * * Returns a pointer to the new key if successful and an error code otherwise. * * Note that the caller needs to ensure the key type isn't uninstantiated. * Internally this can be done by locking key_types_sem. Externally, this can * be done by either never unregistering the key type, or making sure * key_alloc() calls don't race with module unloading. */ struct key *key_alloc(struct key_type *type, const char *desc, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link) { struct key_user *user = NULL; struct key *key; size_t desclen, quotalen; int ret; unsigned long irqflags; key = ERR_PTR(-EINVAL); if (!desc || !*desc) goto error; if (type->vet_description) { ret = type->vet_description(desc); if (ret < 0) { key = ERR_PTR(ret); goto error; } } desclen = strlen(desc); quotalen = desclen + 1 + type->def_datalen; /* get hold of the key tracking for this user */ user = key_user_lookup(uid); if (!user) goto no_memory_1; /* check that the user's quota permits allocation of another key and * its description */ if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) { unsigned maxkeys = uid_eq(uid, GLOBAL_ROOT_UID) ? key_quota_root_maxkeys : key_quota_maxkeys; unsigned maxbytes = uid_eq(uid, GLOBAL_ROOT_UID) ? key_quota_root_maxbytes : key_quota_maxbytes; spin_lock_irqsave(&user->lock, irqflags); if (!(flags & KEY_ALLOC_QUOTA_OVERRUN)) { if (user->qnkeys + 1 > maxkeys || user->qnbytes + quotalen > maxbytes || user->qnbytes + quotalen < user->qnbytes) goto no_quota; } user->qnkeys++; user->qnbytes += quotalen; spin_unlock_irqrestore(&user->lock, irqflags); } /* allocate and initialise the key and its description */ key = kmem_cache_zalloc(key_jar, GFP_KERNEL); if (!key) goto no_memory_2; key->index_key.desc_len = desclen; key->index_key.description = kmemdup(desc, desclen + 1, GFP_KERNEL); if (!key->index_key.description) goto no_memory_3; key->index_key.type = type; key_set_index_key(&key->index_key); refcount_set(&key->usage, 1); init_rwsem(&key->sem); lockdep_set_class(&key->sem, &type->lock_class); key->user = user; key->quotalen = quotalen; key->datalen = type->def_datalen; key->uid = uid; key->gid = gid; key->perm = perm; key->expiry = TIME64_MAX; key->restrict_link = restrict_link; key->last_used_at = ktime_get_real_seconds(); if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) key->flags |= 1 << KEY_FLAG_IN_QUOTA; if (flags & KEY_ALLOC_BUILT_IN) key->flags |= 1 << KEY_FLAG_BUILTIN; if (flags & KEY_ALLOC_UID_KEYRING) key->flags |= 1 << KEY_FLAG_UID_KEYRING; if (flags & KEY_ALLOC_SET_KEEP) key->flags |= 1 << KEY_FLAG_KEEP; #ifdef KEY_DEBUGGING key->magic = KEY_DEBUG_MAGIC; #endif /* let the security module know about the key */ ret = security_key_alloc(key, cred, flags); if (ret < 0) goto security_error; /* publish the key by giving it a serial number */ refcount_inc(&key->domain_tag->usage); atomic_inc(&user->nkeys); key_alloc_serial(key); error: return key; security_error: kfree(key->description); kmem_cache_free(key_jar, key); if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) { spin_lock_irqsave(&user->lock, irqflags); user->qnkeys--; user->qnbytes -= quotalen; spin_unlock_irqrestore(&user->lock, irqflags); } key_user_put(user); key = ERR_PTR(ret); goto error; no_memory_3: kmem_cache_free(key_jar, key); no_memory_2: if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) { spin_lock_irqsave(&user->lock, irqflags); user->qnkeys--; user->qnbytes -= quotalen; spin_unlock_irqrestore(&user->lock, irqflags); } key_user_put(user); no_memory_1: key = ERR_PTR(-ENOMEM); goto error; no_quota: spin_unlock_irqrestore(&user->lock, irqflags); key_user_put(user); key = ERR_PTR(-EDQUOT); goto error; } EXPORT_SYMBOL(key_alloc); /** * key_payload_reserve - Adjust data quota reservation for the key's payload * @key: The key to make the reservation for. * @datalen: The amount of data payload the caller now wants. * * Adjust the amount of the owning user's key data quota that a key reserves. * If the amount is increased, then -EDQUOT may be returned if there isn't * enough free quota available. * * If successful, 0 is returned. */ int key_payload_reserve(struct key *key, size_t datalen) { int delta = (int)datalen - key->datalen; int ret = 0; key_check(key); /* contemplate the quota adjustment */ if (delta != 0 && test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) { unsigned maxbytes = uid_eq(key->user->uid, GLOBAL_ROOT_UID) ? key_quota_root_maxbytes : key_quota_maxbytes; unsigned long flags; spin_lock_irqsave(&key->user->lock, flags); if (delta > 0 && (key->user->qnbytes + delta > maxbytes || key->user->qnbytes + delta < key->user->qnbytes)) { ret = -EDQUOT; } else { key->user->qnbytes += delta; key->quotalen += delta; } spin_unlock_irqrestore(&key->user->lock, flags); } /* change the recorded data length if that didn't generate an error */ if (ret == 0) key->datalen = datalen; return ret; } EXPORT_SYMBOL(key_payload_reserve); /* * Change the key state to being instantiated. */ static void mark_key_instantiated(struct key *key, int reject_error) { /* Commit the payload before setting the state; barrier versus * key_read_state(). */ smp_store_release(&key->state, (reject_error < 0) ? reject_error : KEY_IS_POSITIVE); } /* * Instantiate a key and link it into the target keyring atomically. Must be * called with the target keyring's semaphore writelocked. The target key's * semaphore need not be locked as instantiation is serialised by * key_construction_mutex. */ static int __key_instantiate_and_link(struct key *key, struct key_preparsed_payload *prep, struct key *keyring, struct key *authkey, struct assoc_array_edit **_edit) { int ret, awaken; key_check(key); key_check(keyring); awaken = 0; ret = -EBUSY; mutex_lock(&key_construction_mutex); /* can't instantiate twice */ if (key->state == KEY_IS_UNINSTANTIATED) { /* instantiate the key */ ret = key->type->instantiate(key, prep); if (ret == 0) { /* mark the key as being instantiated */ atomic_inc(&key->user->nikeys); mark_key_instantiated(key, 0); notify_key(key, NOTIFY_KEY_INSTANTIATED, 0); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; /* and link it into the destination keyring */ if (keyring) { if (test_bit(KEY_FLAG_KEEP, &keyring->flags)) set_bit(KEY_FLAG_KEEP, &key->flags); __key_link(keyring, key, _edit); } /* disable the authorisation key */ if (authkey) key_invalidate(authkey); if (prep->expiry != TIME64_MAX) key_set_expiry(key, prep->expiry); } } mutex_unlock(&key_construction_mutex); /* wake up anyone waiting for a key to be constructed */ if (awaken) wake_up_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT); return ret; } /** * key_instantiate_and_link - Instantiate a key and link it into the keyring. * @key: The key to instantiate. * @data: The data to use to instantiate the keyring. * @datalen: The length of @data. * @keyring: Keyring to create a link in on success (or NULL). * @authkey: The authorisation token permitting instantiation. * * Instantiate a key that's in the uninstantiated state using the provided data * and, if successful, link it in to the destination keyring if one is * supplied. * * If successful, 0 is returned, the authorisation token is revoked and anyone * waiting for the key is woken up. If the key was already instantiated, * -EBUSY will be returned. */ int key_instantiate_and_link(struct key *key, const void *data, size_t datalen, struct key *keyring, struct key *authkey) { struct key_preparsed_payload prep; struct assoc_array_edit *edit = NULL; int ret; memset(&prep, 0, sizeof(prep)); prep.orig_description = key->description; prep.data = data; prep.datalen = datalen; prep.quotalen = key->type->def_datalen; prep.expiry = TIME64_MAX; if (key->type->preparse) { ret = key->type->preparse(&prep); if (ret < 0) goto error; } if (keyring) { ret = __key_link_lock(keyring, &key->index_key); if (ret < 0) goto error; ret = __key_link_begin(keyring, &key->index_key, &edit); if (ret < 0) goto error_link_end; if (keyring->restrict_link && keyring->restrict_link->check) { struct key_restriction *keyres = keyring->restrict_link; ret = keyres->check(keyring, key->type, &prep.payload, keyres->key); if (ret < 0) goto error_link_end; } } ret = __key_instantiate_and_link(key, &prep, keyring, authkey, &edit); error_link_end: if (keyring) __key_link_end(keyring, &key->index_key, edit); error: if (key->type->preparse) key->type->free_preparse(&prep); return ret; } EXPORT_SYMBOL(key_instantiate_and_link); /** * key_reject_and_link - Negatively instantiate a key and link it into the keyring. * @key: The key to instantiate. * @timeout: The timeout on the negative key. * @error: The error to return when the key is hit. * @keyring: Keyring to create a link in on success (or NULL). * @authkey: The authorisation token permitting instantiation. * * Negatively instantiate a key that's in the uninstantiated state and, if * successful, set its timeout and stored error and link it in to the * destination keyring if one is supplied. The key and any links to the key * will be automatically garbage collected after the timeout expires. * * Negative keys are used to rate limit repeated request_key() calls by causing * them to return the stored error code (typically ENOKEY) until the negative * key expires. * * If successful, 0 is returned, the authorisation token is revoked and anyone * waiting for the key is woken up. If the key was already instantiated, * -EBUSY will be returned. */ int key_reject_and_link(struct key *key, unsigned timeout, unsigned error, struct key *keyring, struct key *authkey) { struct assoc_array_edit *edit = NULL; int ret, awaken, link_ret = 0; key_check(key); key_check(keyring); awaken = 0; ret = -EBUSY; if (keyring) { if (keyring->restrict_link) return -EPERM; link_ret = __key_link_lock(keyring, &key->index_key); if (link_ret == 0) { link_ret = __key_link_begin(keyring, &key->index_key, &edit); if (link_ret < 0) __key_link_end(keyring, &key->index_key, edit); } } mutex_lock(&key_construction_mutex); /* can't instantiate twice */ if (key->state == KEY_IS_UNINSTANTIATED) { /* mark the key as being negatively instantiated */ atomic_inc(&key->user->nikeys); mark_key_instantiated(key, -error); notify_key(key, NOTIFY_KEY_INSTANTIATED, -error); key_set_expiry(key, ktime_get_real_seconds() + timeout); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; ret = 0; /* and link it into the destination keyring */ if (keyring && link_ret == 0) __key_link(keyring, key, &edit); /* disable the authorisation key */ if (authkey) key_invalidate(authkey); } mutex_unlock(&key_construction_mutex); if (keyring && link_ret == 0) __key_link_end(keyring, &key->index_key, edit); /* wake up anyone waiting for a key to be constructed */ if (awaken) wake_up_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT); return ret == 0 ? link_ret : ret; } EXPORT_SYMBOL(key_reject_and_link); /** * key_put - Discard a reference to a key. * @key: The key to discard a reference from. * * Discard a reference to a key, and when all the references are gone, we * schedule the cleanup task to come and pull it out of the tree in process * context at some later time. */ void key_put(struct key *key) { if (key) { key_check(key); if (refcount_dec_and_test(&key->usage)) { unsigned long flags; /* deal with the user's key tracking and quota */ if (test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) { spin_lock_irqsave(&key->user->lock, flags); key->user->qnkeys--; key->user->qnbytes -= key->quotalen; spin_unlock_irqrestore(&key->user->lock, flags); } schedule_work(&key_gc_work); } } } EXPORT_SYMBOL(key_put); /* * Find a key by its serial number. */ struct key *key_lookup(key_serial_t id) { struct rb_node *n; struct key *key; spin_lock(&key_serial_lock); /* search the tree for the specified key */ n = key_serial_tree.rb_node; while (n) { key = rb_entry(n, struct key, serial_node); if (id < key->serial) n = n->rb_left; else if (id > key->serial) n = n->rb_right; else goto found; } not_found: key = ERR_PTR(-ENOKEY); goto error; found: /* A key is allowed to be looked up only if someone still owns a * reference to it - otherwise it's awaiting the gc. */ if (!refcount_inc_not_zero(&key->usage)) goto not_found; error: spin_unlock(&key_serial_lock); return key; } EXPORT_SYMBOL(key_lookup); /* * Find and lock the specified key type against removal. * * We return with the sem read-locked if successful. If the type wasn't * available -ENOKEY is returned instead. */ struct key_type *key_type_lookup(const char *type) { struct key_type *ktype; down_read(&key_types_sem); /* look up the key type to see if it's one of the registered kernel * types */ list_for_each_entry(ktype, &key_types_list, link) { if (strcmp(ktype->name, type) == 0) goto found_kernel_type; } up_read(&key_types_sem); ktype = ERR_PTR(-ENOKEY); found_kernel_type: return ktype; } void key_set_timeout(struct key *key, unsigned timeout) { time64_t expiry = TIME64_MAX; /* make the changes with the locks held to prevent races */ down_write(&key->sem); if (timeout > 0) expiry = ktime_get_real_seconds() + timeout; key_set_expiry(key, expiry); up_write(&key->sem); } EXPORT_SYMBOL_GPL(key_set_timeout); /* * Unlock a key type locked by key_type_lookup(). */ void key_type_put(struct key_type *ktype) { up_read(&key_types_sem); } /* * Attempt to update an existing key. * * The key is given to us with an incremented refcount that we need to discard * if we get an error. */ static inline key_ref_t __key_update(key_ref_t key_ref, struct key_preparsed_payload *prep) { struct key *key = key_ref_to_ptr(key_ref); int ret; /* need write permission on the key to update it */ ret = key_permission(key_ref, KEY_NEED_WRITE); if (ret < 0) goto error; ret = -EEXIST; if (!key->type->update) goto error; down_write(&key->sem); ret = key->type->update(key, prep); if (ret == 0) { /* Updating a negative key positively instantiates it */ mark_key_instantiated(key, 0); notify_key(key, NOTIFY_KEY_UPDATED, 0); } up_write(&key->sem); if (ret < 0) goto error; out: return key_ref; error: key_put(key); key_ref = ERR_PTR(ret); goto out; } /* * Create or potentially update a key. The combined logic behind * key_create_or_update() and key_create() */ static key_ref_t __key_create_or_update(key_ref_t keyring_ref, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags, bool allow_update) { struct keyring_index_key index_key = { .description = description, }; struct key_preparsed_payload prep; struct assoc_array_edit *edit = NULL; const struct cred *cred = current_cred(); struct key *keyring, *key = NULL; key_ref_t key_ref; int ret; struct key_restriction *restrict_link = NULL; /* look up the key type to see if it's one of the registered kernel * types */ index_key.type = key_type_lookup(type); if (IS_ERR(index_key.type)) { key_ref = ERR_PTR(-ENODEV); goto error; } key_ref = ERR_PTR(-EINVAL); if (!index_key.type->instantiate || (!index_key.description && !index_key.type->preparse)) goto error_put_type; keyring = key_ref_to_ptr(keyring_ref); key_check(keyring); if (!(flags & KEY_ALLOC_BYPASS_RESTRICTION)) restrict_link = keyring->restrict_link; key_ref = ERR_PTR(-ENOTDIR); if (keyring->type != &key_type_keyring) goto error_put_type; memset(&prep, 0, sizeof(prep)); prep.orig_description = description; prep.data = payload; prep.datalen = plen; prep.quotalen = index_key.type->def_datalen; prep.expiry = TIME64_MAX; if (index_key.type->preparse) { ret = index_key.type->preparse(&prep); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_free_prep; } if (!index_key.description) index_key.description = prep.description; key_ref = ERR_PTR(-EINVAL); if (!index_key.description) goto error_free_prep; } index_key.desc_len = strlen(index_key.description); key_set_index_key(&index_key); ret = __key_link_lock(keyring, &index_key); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_free_prep; } ret = __key_link_begin(keyring, &index_key, &edit); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_link_end; } if (restrict_link && restrict_link->check) { ret = restrict_link->check(keyring, index_key.type, &prep.payload, restrict_link->key); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_link_end; } } /* if we're going to allocate a new key, we're going to have * to modify the keyring */ ret = key_permission(keyring_ref, KEY_NEED_WRITE); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_link_end; } /* if it's requested and possible to update this type of key, search * for an existing key of the same type and description in the * destination keyring and update that instead if possible */ if (allow_update) { if (index_key.type->update) { key_ref = find_key_to_update(keyring_ref, &index_key); if (key_ref) goto found_matching_key; } } else { key_ref = find_key_to_update(keyring_ref, &index_key); if (key_ref) { key_ref_put(key_ref); key_ref = ERR_PTR(-EEXIST); goto error_link_end; } } /* if the client doesn't provide, decide on the permissions we want */ if (perm == KEY_PERM_UNDEF) { perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR; perm |= KEY_USR_VIEW; if (index_key.type->read) perm |= KEY_POS_READ; if (index_key.type == &key_type_keyring || index_key.type->update) perm |= KEY_POS_WRITE; } /* allocate a new key */ key = key_alloc(index_key.type, index_key.description, cred->fsuid, cred->fsgid, cred, perm, flags, NULL); if (IS_ERR(key)) { key_ref = ERR_CAST(key); goto error_link_end; } /* instantiate it and link it into the target keyring */ ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &edit); if (ret < 0) { key_put(key); key_ref = ERR_PTR(ret); goto error_link_end; } security_key_post_create_or_update(keyring, key, payload, plen, flags, true); key_ref = make_key_ref(key, is_key_possessed(keyring_ref)); error_link_end: __key_link_end(keyring, &index_key, edit); error_free_prep: if (index_key.type->preparse) index_key.type->free_preparse(&prep); error_put_type: key_type_put(index_key.type); error: return key_ref; found_matching_key: /* we found a matching key, so we're going to try to update it * - we can drop the locks first as we have the key pinned */ __key_link_end(keyring, &index_key, edit); key = key_ref_to_ptr(key_ref); if (test_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) { ret = wait_for_key_construction(key, true); if (ret < 0) { key_ref_put(key_ref); key_ref = ERR_PTR(ret); goto error_free_prep; } } key_ref = __key_update(key_ref, &prep); if (!IS_ERR(key_ref)) security_key_post_create_or_update(keyring, key, payload, plen, flags, false); goto error_free_prep; } /** * key_create_or_update - Update or create and instantiate a key. * @keyring_ref: A pointer to the destination keyring with possession flag. * @type: The type of key. * @description: The searchable description for the key. * @payload: The data to use to instantiate or update the key. * @plen: The length of @payload. * @perm: The permissions mask for a new key. * @flags: The quota flags for a new key. * * Search the destination keyring for a key of the same description and if one * is found, update it, otherwise create and instantiate a new one and create a * link to it from that keyring. * * If perm is KEY_PERM_UNDEF then an appropriate key permissions mask will be * concocted. * * Returns a pointer to the new key if successful, -ENODEV if the key type * wasn't available, -ENOTDIR if the keyring wasn't a keyring, -EACCES if the * caller isn't permitted to modify the keyring or the LSM did not permit * creation of the key. * * On success, the possession flag from the keyring ref will be tacked on to * the key ref before it is returned. */ key_ref_t key_create_or_update(key_ref_t keyring_ref, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags) { return __key_create_or_update(keyring_ref, type, description, payload, plen, perm, flags, true); } EXPORT_SYMBOL(key_create_or_update); /** * key_create - Create and instantiate a key. * @keyring_ref: A pointer to the destination keyring with possession flag. * @type: The type of key. * @description: The searchable description for the key. * @payload: The data to use to instantiate or update the key. * @plen: The length of @payload. * @perm: The permissions mask for a new key. * @flags: The quota flags for a new key. * * Create and instantiate a new key and link to it from the destination keyring. * * If perm is KEY_PERM_UNDEF then an appropriate key permissions mask will be * concocted. * * Returns a pointer to the new key if successful, -EEXIST if a key with the * same description already exists, -ENODEV if the key type wasn't available, * -ENOTDIR if the keyring wasn't a keyring, -EACCES if the caller isn't * permitted to modify the keyring or the LSM did not permit creation of the * key. * * On success, the possession flag from the keyring ref will be tacked on to * the key ref before it is returned. */ key_ref_t key_create(key_ref_t keyring_ref, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags) { return __key_create_or_update(keyring_ref, type, description, payload, plen, perm, flags, false); } EXPORT_SYMBOL(key_create); /** * key_update - Update a key's contents. * @key_ref: The pointer (plus possession flag) to the key. * @payload: The data to be used to update the key. * @plen: The length of @payload. * * Attempt to update the contents of a key with the given payload data. The * caller must be granted Write permission on the key. Negative keys can be * instantiated by this method. * * Returns 0 on success, -EACCES if not permitted and -EOPNOTSUPP if the key * type does not support updating. The key type may return other errors. */ int key_update(key_ref_t key_ref, const void *payload, size_t plen) { struct key_preparsed_payload prep; struct key *key = key_ref_to_ptr(key_ref); int ret; key_check(key); /* the key must be writable */ ret = key_permission(key_ref, KEY_NEED_WRITE); if (ret < 0) return ret; /* attempt to update it if supported */ if (!key->type->update) return -EOPNOTSUPP; memset(&prep, 0, sizeof(prep)); prep.data = payload; prep.datalen = plen; prep.quotalen = key->type->def_datalen; prep.expiry = TIME64_MAX; if (key->type->preparse) { ret = key->type->preparse(&prep); if (ret < 0) goto error; } down_write(&key->sem); ret = key->type->update(key, &prep); if (ret == 0) { /* Updating a negative key positively instantiates it */ mark_key_instantiated(key, 0); notify_key(key, NOTIFY_KEY_UPDATED, 0); } up_write(&key->sem); error: if (key->type->preparse) key->type->free_preparse(&prep); return ret; } EXPORT_SYMBOL(key_update); /** * key_revoke - Revoke a key. * @key: The key to be revoked. * * Mark a key as being revoked and ask the type to free up its resources. The * revocation timeout is set and the key and all its links will be * automatically garbage collected after key_gc_delay amount of time if they * are not manually dealt with first. */ void key_revoke(struct key *key) { time64_t time; key_check(key); /* make sure no one's trying to change or use the key when we mark it * - we tell lockdep that we might nest because we might be revoking an * authorisation key whilst holding the sem on a key we've just * instantiated */ down_write_nested(&key->sem, 1); if (!test_and_set_bit(KEY_FLAG_REVOKED, &key->flags)) { notify_key(key, NOTIFY_KEY_REVOKED, 0); if (key->type->revoke) key->type->revoke(key); /* set the death time to no more than the expiry time */ time = ktime_get_real_seconds(); if (key->revoked_at == 0 || key->revoked_at > time) { key->revoked_at = time; key_schedule_gc(key->revoked_at + key_gc_delay); } } up_write(&key->sem); } EXPORT_SYMBOL(key_revoke); /** * key_invalidate - Invalidate a key. * @key: The key to be invalidated. * * Mark a key as being invalidated and have it cleaned up immediately. The key * is ignored by all searches and other operations from this point. */ void key_invalidate(struct key *key) { kenter("%d", key_serial(key)); key_check(key); if (!test_bit(KEY_FLAG_INVALIDATED, &key->flags)) { down_write_nested(&key->sem, 1); if (!test_and_set_bit(KEY_FLAG_INVALIDATED, &key->flags)) { notify_key(key, NOTIFY_KEY_INVALIDATED, 0); key_schedule_gc_links(); } up_write(&key->sem); } } EXPORT_SYMBOL(key_invalidate); /** * generic_key_instantiate - Simple instantiation of a key from preparsed data * @key: The key to be instantiated * @prep: The preparsed data to load. * * Instantiate a key from preparsed data. We assume we can just copy the data * in directly and clear the old pointers. * * This can be pointed to directly by the key type instantiate op pointer. */ int generic_key_instantiate(struct key *key, struct key_preparsed_payload *prep) { int ret; pr_devel("==>%s()\n", __func__); ret = key_payload_reserve(key, prep->quotalen); if (ret == 0) { rcu_assign_keypointer(key, prep->payload.data[0]); key->payload.data[1] = prep->payload.data[1]; key->payload.data[2] = prep->payload.data[2]; key->payload.data[3] = prep->payload.data[3]; prep->payload.data[0] = NULL; prep->payload.data[1] = NULL; prep->payload.data[2] = NULL; prep->payload.data[3] = NULL; } pr_devel("<==%s() = %d\n", __func__, ret); return ret; } EXPORT_SYMBOL(generic_key_instantiate); /** * register_key_type - Register a type of key. * @ktype: The new key type. * * Register a new key type. * * Returns 0 on success or -EEXIST if a type of this name already exists. */ int register_key_type(struct key_type *ktype) { struct key_type *p; int ret; memset(&ktype->lock_class, 0, sizeof(ktype->lock_class)); ret = -EEXIST; down_write(&key_types_sem); /* disallow key types with the same name */ list_for_each_entry(p, &key_types_list, link) { if (strcmp(p->name, ktype->name) == 0) goto out; } /* store the type */ list_add(&ktype->link, &key_types_list); pr_notice("Key type %s registered\n", ktype->name); ret = 0; out: up_write(&key_types_sem); return ret; } EXPORT_SYMBOL(register_key_type); /** * unregister_key_type - Unregister a type of key. * @ktype: The key type. * * Unregister a key type and mark all the extant keys of this type as dead. * Those keys of this type are then destroyed to get rid of their payloads and * they and their links will be garbage collected as soon as possible. */ void unregister_key_type(struct key_type *ktype) { down_write(&key_types_sem); list_del_init(&ktype->link); downgrade_write(&key_types_sem); key_gc_keytype(ktype); pr_notice("Key type %s unregistered\n", ktype->name); up_read(&key_types_sem); } EXPORT_SYMBOL(unregister_key_type); /* * Initialise the key management state. */ void __init key_init(void) { /* allocate a slab in which we can store keys */ key_jar = kmem_cache_create("key_jar", sizeof(struct key), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); /* add the special key types */ list_add_tail(&key_type_keyring.link, &key_types_list); list_add_tail(&key_type_dead.link, &key_types_list); list_add_tail(&key_type_user.link, &key_types_list); list_add_tail(&key_type_logon.link, &key_types_list); /* record the root user tracking */ rb_link_node(&root_key_user.node, NULL, &key_user_tree.rb_node); rb_insert_color(&root_key_user.node, &key_user_tree); } |
| 9 3 9 2 4 1 2 4 4 19 19 2 4 4 9 9 4 12 10 1 60 2 39 18 56 55 4 58 2 75 33 42 3 12 12 60 93 319 4 2 2 6 193 194 1 189 189 182 3 184 93 93 6 93 83 11 93 73 73 1 72 71 8 3 5 30 30 22 1 13 9 5 12 12 112 111 2 111 1 62 62 13 12 1 17 16 1 427 4 433 418 418 5 9 2 402 398 29 1 80 10 78 12 3 60 28 30 63 1 5 1 54 10 62 40 1 39 35 25 2 24 2 3 24 24 79 2 72 6 71 6 68 9 69 8 75 2 73 4 61 16 75 2 74 3 77 73 42 33 2 68 7 2 66 6 4 16 5 10 4 2 5 2 4 1 65 69 18 416 417 410 421 81 3 40 40 1 39 17 17 18 11 11 1 5 3 14 14 13 1 8 543 676 3 1 1 2 2 1 2 2 2 1 1 1 1 1 2 657 43 572 36 561 1 2 567 1 9 416 398 398 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: GRE over IP protocol decoder. * * Authors: Alexey Kuznetsov (kuznet@ms2.inr.ac.ru) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/gre.h> #include <net/dst_metadata.h> #include <net/erspan.h> #include <net/inet_dscp.h> /* Problems & solutions -------------------- 1. The most important issue is detecting local dead loops. They would cause complete host lockup in transmit, which would be "resolved" by stack overflow or, if queueing is enabled, with infinite looping in net_bh. We cannot track such dead loops during route installation, it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu counter, since when we enter the first ndo_xmit(), cpu migration is forbidden. We force an exit if this counter reaches RECURSION_LIMIT 2. Networking dead loops would not kill routers, but would really kill network. IP hop limit plays role of "t->recursion" in this case, if we copy it from packet being encapsulated to upper header. It is very good solution, but it introduces two problems: - Routing protocols, using packets with ttl=1 (OSPF, RIP2), do not work over tunnels. - traceroute does not work. I planned to relay ICMP from tunnel, so that this problem would be solved and traceroute output would even more informative. This idea appeared to be wrong: only Linux complies to rfc1812 now (yes, guys, Linux is the only true router now :-)), all routers (at least, in neighbourhood of mine) return only 8 bytes of payload. It is the end. Hence, if we want that OSPF worked or traceroute said something reasonable, we should search for another solution. One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made all that we could make. Even if it is your gated who injected fatal route to network, even if it were you who configured fatal static route: you are innocent. :-) Alexey Kuznetsov. */ static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static struct rtnl_link_ops ipgre_link_ops __read_mostly; static const struct header_ops ipgre_header_ops; static int ipgre_tunnel_init(struct net_device *dev); static void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, bool truncate, bool is_ipv4); static unsigned int ipgre_net_id __read_mostly; static unsigned int gre_tap_net_id __read_mostly; static unsigned int erspan_net_id __read_mostly; static int ipgre_err(struct sk_buff *skb, u32 info, const struct tnl_ptk_info *tpi) { /* All the routers (except for Linux) return only 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. Moreover, Cisco "wise men" put GRE key to the third word in GRE header. It makes impossible maintaining even soft state for keyed GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, what the hell these idiots break standards established by themselves??? */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; const struct iphdr *iph; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else if (tpi->proto == htons(ETH_P_ERSPAN) || tpi->proto == htons(ETH_P_ERSPAN2)) itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); iph = (const struct iphdr *)(icmp_hdr(skb) + 1); t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); if (!t) return -ENOENT; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: break; } #if IS_ENABLED(CONFIG_IPV6) if (tpi->proto == htons(ETH_P_IPV6) && !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, type, data_len)) return 0; #endif if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) return 0; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) return 0; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; return 0; } static void gre_err(struct sk_buff *skb, u32 info) { /* All the routers (except for Linux) return only * 8 bytes of packet payload. It means, that precise relaying of * ICMP in the real Internet is absolutely infeasible. * * Moreover, Cisco "wise men" put GRE key to the third word * in GRE header. It makes impossible maintaining even soft * state for keyed * GRE tunnels with enabled checksum. Tell them "thank you". * * Well, I wonder, rfc1812 was written by Cisco employee, * what the hell these idiots break standards established * by themselves??? */ const struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), iph->ihl * 4) < 0) return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, skb->dev->ifindex, IPPROTO_GRE); return; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, IPPROTO_GRE); return; } ipgre_err(skb, info, &tpi); } static bool is_erspan_type1(int gre_hdr_len) { /* Both ERSPAN type I (version 0) and type II (version 1) use * protocol 0x88BE, but the type I has only 4-byte GRE header, * while type II has 8-byte. */ return gre_hdr_len == 4; } static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int gre_hdr_len) { struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; IP_TUNNEL_DECLARE_FLAGS(flags); struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; struct erspan_md2 *md2; int ver; int len; ip_tunnel_flags_copy(flags, tpi->flags); itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); } else { if (unlikely(!pskb_may_pull(skb, gre_hdr_len + sizeof(*ershdr)))) return PACKET_REJECT; ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; iph = ip_hdr(skb); __set_bit(IP_TUNNEL_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, tpi->key); } if (tunnel) { if (is_erspan_type1(gre_hdr_len)) len = gre_hdr_len; else len = gre_hdr_len + erspan_hdr_len(ver); if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), false, false) < 0) goto drop; if (tunnel->collect_md) { struct erspan_metadata *pkt_md, *md; struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, sizeof(*md)); if (!tun_dst) return PACKET_REJECT; /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it */ gh = skb_network_header(skb) + skb_network_header_len(skb); pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + sizeof(*ershdr)); md = ip_tunnel_info_opts(&tun_dst->u.tun_info); md->version = ver; md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); info->options_len = sizeof(*md); } skb_reset_mac_header(skb); ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_REJECT; drop: kfree_skb(skb); return PACKET_RCVD; } static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn, int hdr_len, bool raw_proto) { struct metadata_dst *tun_dst = NULL; const struct iphdr *iph; struct ip_tunnel *tunnel; iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->saddr, iph->daddr, tpi->key); if (tunnel) { const struct iphdr *tnl_params; if (__iptunnel_pull_header(skb, hdr_len, tpi->proto, raw_proto, false) < 0) goto drop; /* Special case for ipgre_header_parse(), which expects the * mac_header to point to the outer IP header. */ if (tunnel->dev->header_ops == &ipgre_header_ops) skb_pop_mac_header(skb); else skb_reset_mac_header(skb); tnl_params = &tunnel->parms.iph; if (tunnel->collect_md || tnl_params->daddr == 0) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __be64 tun_id; __set_bit(IP_TUNNEL_CSUM_BIT, flags); __set_bit(IP_TUNNEL_KEY_BIT, flags); ip_tunnel_flags_and(flags, tpi->flags, flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) return PACKET_REJECT; } ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_NEXT; drop: kfree_skb(skb); return PACKET_RCVD; } static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, int hdr_len) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; int res; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, false); if (res == PACKET_NEXT && tpi->proto == htons(ETH_P_TEB)) { /* ipgre tunnels in collect metadata mode should receive * also ETH_P_TEB traffic. */ itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, true); } return res; } static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; int hdr_len; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { /* Looped back packet, drop it! */ if (rt_is_output_route(skb_rtable(skb))) goto drop; } #endif hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0); if (hdr_len < 0) goto drop; if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; } if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags); ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, test_bit(IP_TUNNEL_SEQ_BIT, flags) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } static int gre_handle_offloads(struct sk_buff *skb, bool csum) { return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; tunnel_hlen = gre_calc_hlen(key->tun_flags); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; /* Push Tunnel header. */ if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto err_free_skb; __set_bit(IP_TUNNEL_CSUM_BIT, flags); __set_bit(IP_TUNNEL_KEY_BIT, flags); __set_bit(IP_TUNNEL_SEQ_BIT, flags); ip_tunnel_flags_and(flags, tun_info->key.tun_flags, flags); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), test_bit(IP_TUNNEL_SEQ_BIT, flags) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); } static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; bool truncate = false; __be16 proto; int tunnel_hlen; int version; int nhoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; tunnel_hlen = 8 + erspan_hdr_len(version); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; if (gre_handle_offloads(skb, false)) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto err_free_skb; truncate = true; } nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; if (skb->protocol == htons(ETH_P_IPV6)) { int thoff; if (skb_transport_header_was_set(skb)) thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) truncate = true; } if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); proto = htons(ETH_P_ERSPAN); } else if (version == 2) { erspan_build_header_v2(skb, ntohl(tunnel_id_to_key32(key->tun_id)), md->u.md2.dir, get_hwid(&md->u.md2), truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto err_free_skb; } __set_bit(IP_TUNNEL_SEQ_BIT, flags); gre_build_header(skb, 8, flags, proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); } static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct ip_tunnel_key *key; struct rtable *rt; struct flowi4 fl4; if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), key->tos & ~INET_ECN_MASK, dev_net(dev), 0, skb->mark, skb_get_hash(skb), key->flow_flags); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = fl4.saddr; return 0; } static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; } if (dev->header_ops) { int pull_len = tunnel->hlen + sizeof(struct iphdr); if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; if (!pskb_network_may_pull(skb, pull_len)) goto free_skb; /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start(skb) < skb->data) goto free_skb; } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; tnl_params = &tunnel->parms.iph; } if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static netdev_tx_t erspan_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); bool truncate = false; __be16 proto; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { erspan_fb_xmit(skb, dev); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, false)) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto free_skb; truncate = true; } /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); __clear_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags); } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); proto = htons(ETH_P_ERSPAN); } else if (tunnel->erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto free_skb; } __clear_bit(IP_TUNNEL_KEY_BIT, tunnel->parms.o_flags); __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB)); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); int len; len = tunnel->tun_hlen; tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; if (dev->header_ops) dev->hard_header_len += len; else dev->needed_headroom += len; if (set_mtu) WRITE_ONCE(dev->mtu, max_t(int, dev->mtu - len, 68)); if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags) || (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && tunnel->encap.type != TUNNEL_ENCAP_NONE)) { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } else { dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; } } static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { __be16 i_flags, o_flags; int err; if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || !ip_tunnel_flags_is_be16_compat(p->o_flags)) return -EOVERFLOW; i_flags = ip_tunnel_flags_to_be16(p->i_flags); o_flags = ip_tunnel_flags_to_be16(p->o_flags); if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || ((i_flags | o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } gre_flags_to_tnl_flags(p->i_flags, i_flags); gre_flags_to_tnl_flags(p->o_flags, o_flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); ip_tunnel_flags_from_be16(p->i_flags, i_flags); o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); ip_tunnel_flags_from_be16(p->o_flags, o_flags); return 0; } /* Nice toy. Unfortunately, useless in real life :-) It allows to construct virtual multiprotocol broadcast "LAN" over the Internet, provided multicast routing is tuned. I have no idea was this bicycle invented before me, so that I had to set ARPHRD_IPGRE to a random value. I have an impression, that Cisco could make something similar, but this feature is apparently missing in IOS<=11.2(8). I set up 10.66.66/24 and fec0:6666:6666::0/96 as virtual networks with broadcast 224.66.66.66. If you have access to mbone, play with me :-) ping -t 255 224.66.66.66 If nobody answers, mbone does not work. ip tunnel add Universe mode gre remote 224.66.66.66 local <Your_real_addr> ttl 255 ip addr add 10.66.66.<somewhat>/24 dev Universe ifconfig Universe up ifconfig Universe add fe80::<Your_real_addr>/10 ifconfig Universe add fec0:6666:6666::<Your_real_addr>/96 ftp 10.66.66.66 ... ftp fec0:6666:6666::193.233.7.65 ... */ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph; struct gre_base_hdr *greh; iph = skb_push(skb, t->hlen + sizeof(*iph)); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); memcpy(iph, &t->parms.iph, sizeof(struct iphdr)); /* Set the source hardware address. */ if (saddr) memcpy(&iph->saddr, saddr, 4); if (daddr) memcpy(&iph->daddr, daddr, 4); if (iph->daddr) return t->hlen + sizeof(*iph); return -(t->hlen + sizeof(*iph)); } static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr) { const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb); memcpy(haddr, &iph->saddr, 4); return 4; } static const struct header_ops ipgre_header_ops = { .create = ipgre_header, .parse = ipgre_header_parse, }; #ifdef CONFIG_NET_IPGRE_BROADCAST static int ipgre_open(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { struct flowi4 fl4; struct rtable *rt; rt = ip_route_output_gre(t->net, &fl4, t->parms.iph.daddr, t->parms.iph.saddr, t->parms.o_key, t->parms.iph.tos & INET_DSCP_MASK, t->parms.link); if (IS_ERR(rt)) return -EADDRNOTAVAIL; dev = rt->dst.dev; ip_rt_put(rt); if (!__in_dev_get_rtnl(dev)) return -EADDRNOTAVAIL; t->mlink = dev->ifindex; ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr); } return 0; } static int ipgre_close(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev; in_dev = inetdev_by_index(t->net, t->mlink); if (in_dev) ip_mc_dec_group(in_dev, t->parms.iph.daddr); } return 0; } #endif static const struct net_device_ops ipgre_netdev_ops = { .ndo_init = ipgre_tunnel_init, .ndo_uninit = ip_tunnel_uninit, #ifdef CONFIG_NET_IPGRE_BROADCAST .ndo_open = ipgre_open, .ndo_stop = ipgre_close, #endif .ndo_start_xmit = ipgre_xmit, .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipgre_tunnel_ctl, }; #define GRE_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_HW_CSUM) static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; dev->type = ARPHRD_IPGRE; ip_tunnel_setup(dev, ipgre_net_id); } static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags)) return; if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && tunnel->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->lltx = true; } static int ipgre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; __gre_tunnel_init(dev); __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; if (iph->daddr && !tunnel->collect_md) { #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { if (!iph->saddr) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } #endif } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } return ip_tunnel_init(dev); } static const struct gre_protocol ipgre_protocol = { .handler = gre_rcv, .err_handler = gre_err, }; static int __net_init ipgre_init_net(struct net *net) { return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } static void __net_exit ipgre_exit_batch_rtnl(struct list_head *list_net, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops, dev_to_kill); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, .exit_batch_rtnl = ipgre_exit_batch_rtnl, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags; if (!data) return 0; flags = 0; if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (flags & (GRE_VERSION|GRE_ROUTING)) return -EINVAL; if (data[IFLA_GRE_COLLECT_METADATA] && data[IFLA_GRE_ENCAP_TYPE] && nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE) return -EINVAL; return 0; } static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be32 daddr; if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) goto out; if (data[IFLA_GRE_REMOTE]) { memcpy(&daddr, nla_data(data[IFLA_GRE_REMOTE]), 4); if (!daddr) return -EINVAL; } out: return ipgre_tunnel_validate(tb, data, extack); } static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags = 0; int ret; if (!data) return 0; ret = ipgre_tap_validate(tb, data, extack); if (ret) return ret; if (data[IFLA_GRE_ERSPAN_VER] && nla_get_u8(data[IFLA_GRE_ERSPAN_VER]) == 0) return 0; /* ERSPAN type II/III should only have GRE sequence and key flag */ if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (!data[IFLA_GRE_COLLECT_METADATA] && flags != (GRE_SEQ | GRE_KEY)) return -EINVAL; /* ERSPAN Session ID only has 10-bit. Since we reuse * 32-bit key field as ID, check it's range. */ if (data[IFLA_GRE_IKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_IKEY])) & ~ID_MASK)) return -EINVAL; if (data[IFLA_GRE_OKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_OKEY])) & ~ID_MASK)) return -EINVAL; return 0; } static int ipgre_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); memset(parms, 0, sizeof(*parms)); parms->iph.protocol = IPPROTO_GRE; if (!data) return 0; if (data[IFLA_GRE_LINK]) parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) gre_flags_to_tnl_flags(parms->i_flags, nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) gre_flags_to_tnl_flags(parms->o_flags, nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); if (data[IFLA_GRE_OKEY]) parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]); if (data[IFLA_GRE_LOCAL]) parms->iph.saddr = nla_get_in_addr(data[IFLA_GRE_LOCAL]); if (data[IFLA_GRE_REMOTE]) parms->iph.daddr = nla_get_in_addr(data[IFLA_GRE_REMOTE]); if (data[IFLA_GRE_TTL]) parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]); if (data[IFLA_GRE_TOS]) parms->iph.tos = nla_get_u8(data[IFLA_GRE_TOS]); if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) { if (t->ignore_df) return -EINVAL; parms->iph.frag_off = htons(IP_DF); } if (data[IFLA_GRE_COLLECT_METADATA]) { t->collect_md = true; if (dev->type == ARPHRD_IPGRE) dev->type = ARPHRD_NONE; } if (data[IFLA_GRE_IGNORE_DF]) { if (nla_get_u8(data[IFLA_GRE_IGNORE_DF]) && (parms->iph.frag_off & htons(IP_DF))) return -EINVAL; t->ignore_df = !!nla_get_u8(data[IFLA_GRE_IGNORE_DF]); } if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); return 0; } static int erspan_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); int err; err = ipgre_netlink_parms(dev, data, tb, parms, fwmark); if (err) return err; if (!data) return 0; if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); if (t->erspan_ver > 2) return -EINVAL; } if (t->erspan_ver == 1) { if (data[IFLA_GRE_ERSPAN_INDEX]) { t->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); if (t->index & ~INDEX_MASK) return -EINVAL; } } else if (t->erspan_ver == 2) { if (data[IFLA_GRE_ERSPAN_DIR]) { t->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); if (t->dir & ~(DIR_MASK >> DIR_OFFSET)) return -EINVAL; } if (data[IFLA_GRE_ERSPAN_HWID]) { t->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); if (t->hwid & ~(HWID_MASK >> HWID_OFFSET)) return -EINVAL; } } return 0; } /* This function returns true when ENCAP attributes are present in the nl msg */ static bool ipgre_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { bool ret = false; memset(ipencap, 0, sizeof(*ipencap)); if (!data) return ret; if (data[IFLA_GRE_ENCAP_TYPE]) { ret = true; ipencap->type = nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]); } if (data[IFLA_GRE_ENCAP_FLAGS]) { ret = true; ipencap->flags = nla_get_u16(data[IFLA_GRE_ENCAP_FLAGS]); } if (data[IFLA_GRE_ENCAP_SPORT]) { ret = true; ipencap->sport = nla_get_be16(data[IFLA_GRE_ENCAP_SPORT]); } if (data[IFLA_GRE_ENCAP_DPORT]) { ret = true; ipencap->dport = nla_get_be16(data[IFLA_GRE_ENCAP_DPORT]); } return ret; } static int gre_tap_init(struct net_device *dev) { __gre_tunnel_init(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops gre_tap_netdev_ops = { .ndo_init = gre_tap_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = gre_tap_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static int erspan_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (tunnel->erspan_ver == 0) tunnel->tun_hlen = 4; /* 4-byte GRE hdr. */ else tunnel->tun_hlen = 8; /* 8-byte GRE hdr. */ tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + erspan_hdr_len(tunnel->erspan_ver); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops erspan_netdev_ops = { .ndo_init = erspan_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = erspan_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &gre_tap_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } static int ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) { struct ip_tunnel_encap ipencap; if (ipgre_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } return 0; } static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int erspan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); ipgre_link_update(dev, !tb[IFLA_MTU]); return 0; } static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); return 0; } static size_t ipgre_get_size(const struct net_device *dev) { return /* IFLA_GRE_LINK */ nla_total_size(4) + /* IFLA_GRE_IFLAGS */ nla_total_size(2) + /* IFLA_GRE_OFLAGS */ nla_total_size(2) + /* IFLA_GRE_IKEY */ nla_total_size(4) + /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ nla_total_size(4) + /* IFLA_GRE_REMOTE */ nla_total_size(4) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ nla_total_size(1) + /* IFLA_GRE_PMTUDISC */ nla_total_size(1) + /* IFLA_GRE_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_GRE_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_GRE_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_GRE_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_GRE_COLLECT_METADATA */ nla_total_size(0) + /* IFLA_GRE_IGNORE_DF */ nla_total_size(1) + /* IFLA_GRE_FWMARK */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_INDEX */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_VER */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_DIR */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_HWID */ nla_total_size(2) + 0; } static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern *p = &t->parms; IP_TUNNEL_DECLARE_FLAGS(o_flags); ip_tunnel_flags_copy(o_flags, p->o_flags); if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || nla_put_in_addr(skb, IFLA_GRE_REMOTE, p->iph.daddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) || nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) || nla_put_u8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF))) || nla_put_u32(skb, IFLA_GRE_FWMARK, t->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE, t->encap.type) || nla_put_be16(skb, IFLA_GRE_ENCAP_SPORT, t->encap.sport) || nla_put_be16(skb, IFLA_GRE_ENCAP_DPORT, t->encap.dport) || nla_put_u16(skb, IFLA_GRE_ENCAP_FLAGS, t->encap.flags)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GRE_IGNORE_DF, t->ignore_df)) goto nla_put_failure; if (t->collect_md) { if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (t->erspan_ver <= 2) { if (t->erspan_ver != 0 && !t->collect_md) __set_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) goto nla_put_failure; if (t->erspan_ver == 1) { if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) goto nla_put_failure; } else if (t->erspan_ver == 2) { if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) goto nla_put_failure; } } return ipgre_fill_info(skb, dev); nla_put_failure: return -EMSGSIZE; } static void erspan_setup(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, erspan_net_id); t->erspan_ver = 1; } static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_LINK] = { .type = NLA_U32 }, [IFLA_GRE_IFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GRE_IGNORE_DF] = { .type = NLA_U8 }, [IFLA_GRE_FWMARK] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_INDEX] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_VER] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_DIR] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_HWID] = { .type = NLA_U16 }, }; static struct rtnl_link_ops ipgre_link_ops __read_mostly = { .kind = "gre", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tunnel_setup, .validate = ipgre_tunnel_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops ipgre_tap_ops __read_mostly = { .kind = "gretap", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tap_setup, .validate = ipgre_tap_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops erspan_link_ops __read_mostly = { .kind = "erspan", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = erspan_setup, .validate = erspan_validate, .newlink = erspan_newlink, .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = erspan_fill_info, .get_link_net = ip_tunnel_get_link_net, }; struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); struct ip_tunnel *t; int err; memset(&tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &ipgre_tap_ops, tb, NULL); if (IS_ERR(dev)) return dev; /* Configure flow based GRE device. */ t = netdev_priv(dev); t->collect_md = true; err = ipgre_newlink(net, dev, tb, NULL, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); if (err) goto out; err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto out; return dev; out: ip_tunnel_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(gretap_fb_dev_create); static int __net_init ipgre_tap_init_net(struct net *net) { return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } static void __net_exit ipgre_tap_exit_batch_rtnl(struct list_head *list_net, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops, dev_to_kill); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, .exit_batch_rtnl = ipgre_tap_exit_batch_rtnl, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __net_init erspan_init_net(struct net *net) { return ip_tunnel_init_net(net, erspan_net_id, &erspan_link_ops, "erspan0"); } static void __net_exit erspan_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops, dev_to_kill); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, .exit_batch_rtnl = erspan_exit_batch_rtnl, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __init ipgre_init(void) { int err; pr_info("GRE over IPv4 tunneling driver\n"); err = register_pernet_device(&ipgre_net_ops); if (err < 0) return err; err = register_pernet_device(&ipgre_tap_net_ops); if (err < 0) goto pnet_tap_failed; err = register_pernet_device(&erspan_net_ops); if (err < 0) goto pnet_erspan_failed; err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; } err = rtnl_link_register(&ipgre_link_ops); if (err < 0) goto rtnl_link_failed; err = rtnl_link_register(&ipgre_tap_ops); if (err < 0) goto tap_ops_failed; err = rtnl_link_register(&erspan_link_ops); if (err < 0) goto erspan_link_failed; return 0; erspan_link_failed: rtnl_link_unregister(&ipgre_tap_ops); tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: unregister_pernet_device(&erspan_net_ops); pnet_erspan_failed: unregister_pernet_device(&ipgre_tap_net_ops); pnet_tap_failed: unregister_pernet_device(&ipgre_net_ops); return err; } static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); rtnl_link_unregister(&erspan_link_ops); gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); unregister_pernet_device(&ipgre_tap_net_ops); unregister_pernet_device(&ipgre_net_ops); unregister_pernet_device(&erspan_net_ops); } module_init(ipgre_init); module_exit(ipgre_fini); MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); MODULE_ALIAS_RTNL_LINK("erspan"); MODULE_ALIAS_NETDEV("gre0"); MODULE_ALIAS_NETDEV("gretap0"); MODULE_ALIAS_NETDEV("erspan0"); |
| 7 7 527 477 182 317 310 7 308 11 646 768 671 527 646 673 667 14 674 664 14 14 644 8 39 470 1 666 258 646 1 647 646 647 54 24 330 4 46 326 32 3 13 52 2 241 332 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2003, 2004 * * This file is part of the SCTP kernel implementation * * This file contains the code relating the chunk abstraction. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * Jon Grimm <jgrimm@us.ibm.com> * Sridhar Samudrala <sri@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/kernel.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/sock.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> /* This file is mostly in anticipation of future work, but initially * populate with fragment tracking for an outbound message. */ /* Initialize datamsg from memory. */ static void sctp_datamsg_init(struct sctp_datamsg *msg) { refcount_set(&msg->refcnt, 1); msg->send_failed = 0; msg->send_error = 0; msg->can_delay = 1; msg->abandoned = 0; msg->expires_at = 0; INIT_LIST_HEAD(&msg->chunks); } /* Allocate and initialize datamsg. */ static struct sctp_datamsg *sctp_datamsg_new(gfp_t gfp) { struct sctp_datamsg *msg; msg = kmalloc(sizeof(struct sctp_datamsg), gfp); if (msg) { sctp_datamsg_init(msg); SCTP_DBG_OBJCNT_INC(datamsg); } return msg; } void sctp_datamsg_free(struct sctp_datamsg *msg) { struct sctp_chunk *chunk; /* This doesn't have to be a _safe vairant because * sctp_chunk_free() only drops the refs. */ list_for_each_entry(chunk, &msg->chunks, frag_list) sctp_chunk_free(chunk); sctp_datamsg_put(msg); } /* Final destructruction of datamsg memory. */ static void sctp_datamsg_destroy(struct sctp_datamsg *msg) { struct sctp_association *asoc = NULL; struct list_head *pos, *temp; struct sctp_chunk *chunk; struct sctp_ulpevent *ev; int error, sent; /* Release all references. */ list_for_each_safe(pos, temp, &msg->chunks) { list_del_init(pos); chunk = list_entry(pos, struct sctp_chunk, frag_list); if (!msg->send_failed) { sctp_chunk_put(chunk); continue; } asoc = chunk->asoc; error = msg->send_error ?: asoc->outqueue.error; sent = chunk->has_tsn ? SCTP_DATA_SENT : SCTP_DATA_UNSENT; if (sctp_ulpevent_type_enabled(asoc->subscribe, SCTP_SEND_FAILED)) { ev = sctp_ulpevent_make_send_failed(asoc, chunk, sent, error, GFP_ATOMIC); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } if (sctp_ulpevent_type_enabled(asoc->subscribe, SCTP_SEND_FAILED_EVENT)) { ev = sctp_ulpevent_make_send_failed_event(asoc, chunk, sent, error, GFP_ATOMIC); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } sctp_chunk_put(chunk); } SCTP_DBG_OBJCNT_DEC(datamsg); kfree(msg); } /* Hold a reference. */ static void sctp_datamsg_hold(struct sctp_datamsg *msg) { refcount_inc(&msg->refcnt); } /* Release a reference. */ void sctp_datamsg_put(struct sctp_datamsg *msg) { if (refcount_dec_and_test(&msg->refcnt)) sctp_datamsg_destroy(msg); } /* Assign a chunk to this datamsg. */ static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chunk) { sctp_datamsg_hold(msg); chunk->msg = msg; } /* A data chunk can have a maximum payload of (2^16 - 20). Break * down any such message into smaller chunks. Opportunistically, fragment * the chunks down to the current MTU constraints. We may get refragmented * later if the PMTU changes, but it is _much better_ to fragment immediately * with a reasonable guess than always doing our fragmentation on the * soft-interrupt. */ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, struct iov_iter *from) { size_t len, first_len, max_data, remaining; size_t msg_len = iov_iter_count(from); struct sctp_shared_key *shkey = NULL; struct list_head *pos, *temp; struct sctp_chunk *chunk; struct sctp_datamsg *msg; int err; msg = sctp_datamsg_new(GFP_KERNEL); if (!msg) return ERR_PTR(-ENOMEM); /* Note: Calculate this outside of the loop, so that all fragments * have the same expiration. */ if (asoc->peer.prsctp_capable && sinfo->sinfo_timetolive && (SCTP_PR_TTL_ENABLED(sinfo->sinfo_flags) || !SCTP_PR_POLICY(sinfo->sinfo_flags))) msg->expires_at = jiffies + msecs_to_jiffies(sinfo->sinfo_timetolive); /* This is the biggest possible DATA chunk that can fit into * the packet */ max_data = asoc->frag_point; if (unlikely(!max_data)) { max_data = sctp_min_frag_point(sctp_sk(asoc->base.sk), sctp_datachk_len(&asoc->stream)); pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%zu)", __func__, asoc, max_data); } /* If the peer requested that we authenticate DATA chunks * we need to account for bundling of the AUTH chunks along with * DATA. */ if (sctp_auth_send_cid(SCTP_CID_DATA, asoc)) { struct sctp_hmac *hmac_desc = sctp_auth_asoc_get_hmac(asoc); if (hmac_desc) max_data -= SCTP_PAD4(sizeof(struct sctp_auth_chunk) + hmac_desc->hmac_len); if (sinfo->sinfo_tsn && sinfo->sinfo_ssn != asoc->active_key_id) { shkey = sctp_auth_get_shkey(asoc, sinfo->sinfo_ssn); if (!shkey) { err = -EINVAL; goto errout; } } else { shkey = asoc->shkey; } } /* Set first_len and then account for possible bundles on first frag */ first_len = max_data; /* Check to see if we have a pending SACK and try to let it be bundled * with this message. Do this if we don't have any data queued already. * To check that, look at out_qlen and retransmit list. * NOTE: we will not reduce to account for SACK, if the message would * not have been fragmented. */ if (timer_pending(&asoc->timers[SCTP_EVENT_TIMEOUT_SACK]) && asoc->outqueue.out_qlen == 0 && list_empty(&asoc->outqueue.retransmit) && msg_len > max_data) first_len -= SCTP_PAD4(sizeof(struct sctp_sack_chunk)); /* Encourage Cookie-ECHO bundling. */ if (asoc->state < SCTP_STATE_COOKIE_ECHOED) first_len -= SCTP_ARBITRARY_COOKIE_ECHO_LEN; /* Account for a different sized first fragment */ if (msg_len >= first_len) { msg->can_delay = 0; if (msg_len > first_len) SCTP_INC_STATS(asoc->base.net, SCTP_MIB_FRAGUSRMSGS); } else { /* Which may be the only one... */ first_len = msg_len; } /* Create chunks for all DATA chunks. */ for (remaining = msg_len; remaining; remaining -= len) { u8 frag = SCTP_DATA_MIDDLE_FRAG; if (remaining == msg_len) { /* First frag, which may also be the last */ frag |= SCTP_DATA_FIRST_FRAG; len = first_len; } else { /* Middle frags */ len = max_data; } if (len >= remaining) { /* Last frag, which may also be the first */ len = remaining; frag |= SCTP_DATA_LAST_FRAG; /* The application requests to set the I-bit of the * last DATA chunk of a user message when providing * the user message to the SCTP implementation. */ if ((sinfo->sinfo_flags & SCTP_EOF) || (sinfo->sinfo_flags & SCTP_SACK_IMMEDIATELY)) frag |= SCTP_DATA_SACK_IMM; } chunk = asoc->stream.si->make_datafrag(asoc, sinfo, len, frag, GFP_KERNEL); if (!chunk) { err = -ENOMEM; goto errout; } err = sctp_user_addto_chunk(chunk, len, from); if (err < 0) goto errout_chunk_free; chunk->shkey = shkey; /* Put the chunk->skb back into the form expected by send. */ __skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr - chunk->skb->data); sctp_datamsg_assign(msg, chunk); list_add_tail(&chunk->frag_list, &msg->chunks); } return msg; errout_chunk_free: sctp_chunk_free(chunk); errout: list_for_each_safe(pos, temp, &msg->chunks) { list_del_init(pos); chunk = list_entry(pos, struct sctp_chunk, frag_list); sctp_chunk_free(chunk); } sctp_datamsg_put(msg); return ERR_PTR(err); } /* Check whether this message has expired. */ int sctp_chunk_abandoned(struct sctp_chunk *chunk) { if (!chunk->asoc->peer.prsctp_capable) return 0; if (chunk->msg->abandoned) return 1; if (!chunk->has_tsn && !(chunk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG)) return 0; if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = SCTP_SO(&chunk->asoc->stream, chunk->sinfo.sinfo_stream); if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(TTL)]++; } else { chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; } chunk->msg->abandoned = 1; return 1; } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { struct sctp_stream_out *streamout = SCTP_SO(&chunk->asoc->stream, chunk->sinfo.sinfo_stream); chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++; chunk->msg->abandoned = 1; return 1; } else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) && chunk->msg->expires_at && time_after(jiffies, chunk->msg->expires_at)) { chunk->msg->abandoned = 1; return 1; } /* PRIO policy is processed by sendmsg, not here */ return 0; } /* This chunk (and consequently entire message) has failed in its sending. */ void sctp_chunk_fail(struct sctp_chunk *chunk, int error) { chunk->msg->send_failed = 1; chunk->msg->send_error = error; } |
| 24 48 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 | // SPDX-License-Identifier: GPL-2.0 /* File: fs/ext4/acl.h (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #include <linux/posix_acl_xattr.h> #define EXT4_ACL_VERSION 0x0001 typedef struct { __le16 e_tag; __le16 e_perm; __le32 e_id; } ext4_acl_entry; typedef struct { __le16 e_tag; __le16 e_perm; } ext4_acl_entry_short; typedef struct { __le32 a_version; } ext4_acl_header; static inline size_t ext4_acl_size(int count) { if (count <= 4) { return sizeof(ext4_acl_header) + count * sizeof(ext4_acl_entry_short); } else { return sizeof(ext4_acl_header) + 4 * sizeof(ext4_acl_entry_short) + (count - 4) * sizeof(ext4_acl_entry); } } static inline int ext4_acl_count(size_t size) { ssize_t s; size -= sizeof(ext4_acl_header); s = size - 4 * sizeof(ext4_acl_entry_short); if (s < 0) { if (size % sizeof(ext4_acl_entry_short)) return -1; return size / sizeof(ext4_acl_entry_short); } else { if (s % sizeof(ext4_acl_entry)) return -1; return s / sizeof(ext4_acl_entry) + 4; } } #ifdef CONFIG_EXT4_FS_POSIX_ACL /* acl.c */ struct posix_acl *ext4_get_acl(struct inode *inode, int type, bool rcu); int ext4_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); #else /* CONFIG_EXT4_FS_POSIX_ACL */ #include <linux/sched.h> #define ext4_get_acl NULL #define ext4_set_acl NULL static inline int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { return 0; } #endif /* CONFIG_EXT4_FS_POSIX_ACL */ |
| 85 85 85 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 | /* * Copyright (c) 2014 Intel Corporation. All rights reserved. * Copyright (c) 2014 Chelsio, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include "iwpm_util.h" static const char iwpm_ulib_name[IWPM_ULIBNAME_SIZE] = "iWarpPortMapperUser"; u16 iwpm_ulib_version = IWPM_UABI_VERSION_MIN; static int iwpm_user_pid = IWPM_PID_UNDEFINED; static atomic_t echo_nlmsg_seq; /** * iwpm_valid_pid - Check if the userspace iwarp port mapper pid is valid * * Returns true if the pid is greater than zero, otherwise returns false */ int iwpm_valid_pid(void) { return iwpm_user_pid > 0; } /** * iwpm_register_pid - Send a netlink query to userspace * to get the iwarp port mapper pid * @pm_msg: Contains driver info to send to the userspace port mapper * @nl_client: The index of the netlink client * * nlmsg attributes: * [IWPM_NLA_REG_PID_SEQ] * [IWPM_NLA_REG_IF_NAME] * [IWPM_NLA_REG_IBDEV_NAME] * [IWPM_NLA_REG_ULIB_NAME] */ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client) { struct sk_buff *skb = NULL; struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlmsghdr *nlh; u32 msg_seq; const char *err_str = ""; int ret = -EINVAL; if (iwpm_check_registration(nl_client, IWPM_REG_VALID) || iwpm_user_pid == IWPM_PID_UNAVAILABLE) return 0; skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REG_PID, &nlh, nl_client); if (!skb) { err_str = "Unable to create a nlmsg"; goto pid_query_error; } nlh->nlmsg_seq = iwpm_get_nlmsg_seq(); nlmsg_request = iwpm_get_nlmsg_request(nlh->nlmsg_seq, nl_client, GFP_KERNEL); if (!nlmsg_request) { err_str = "Unable to allocate netlink request"; goto pid_query_error; } msg_seq = atomic_read(&echo_nlmsg_seq); /* fill in the pid request message */ err_str = "Unable to put attribute of the nlmsg"; ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq, IWPM_NLA_REG_PID_SEQ); if (ret) goto pid_query_error; ret = ibnl_put_attr(skb, nlh, IFNAMSIZ, pm_msg->if_name, IWPM_NLA_REG_IF_NAME); if (ret) goto pid_query_error; ret = ibnl_put_attr(skb, nlh, IWPM_DEVNAME_SIZE, pm_msg->dev_name, IWPM_NLA_REG_IBDEV_NAME); if (ret) goto pid_query_error; ret = ibnl_put_attr(skb, nlh, IWPM_ULIBNAME_SIZE, (char *)iwpm_ulib_name, IWPM_NLA_REG_ULIB_NAME); if (ret) goto pid_query_error; nlmsg_end(skb, nlh); pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n", __func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name); ret = rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_IWPM, GFP_KERNEL); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ iwpm_user_pid = IWPM_PID_UNAVAILABLE; err_str = "Unable to send a nlmsg"; goto pid_query_error; } nlmsg_request->req_buffer = pm_msg; ret = iwpm_wait_complete_req(nlmsg_request); return ret; pid_query_error: pr_info("%s: %s (client = %u)\n", __func__, err_str, nl_client); dev_kfree_skb(skb); if (nlmsg_request) iwpm_free_nlmsg_request(&nlmsg_request->kref); return ret; } /** * iwpm_add_mapping - Send a netlink add mapping request to * the userspace port mapper * @pm_msg: Contains the local ip/tcp address info to send * @nl_client: The index of the netlink client * * nlmsg attributes: * [IWPM_NLA_MANAGE_MAPPING_SEQ] * [IWPM_NLA_MANAGE_ADDR] * [IWPM_NLA_MANAGE_FLAGS] * * If the request is successful, the pm_msg stores * the port mapper response (mapped address info) */ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) { struct sk_buff *skb = NULL; struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlmsghdr *nlh; u32 msg_seq; const char *err_str = ""; int ret = -EINVAL; if (!iwpm_valid_pid()) return 0; if (!iwpm_check_registration(nl_client, IWPM_REG_VALID)) { err_str = "Unregistered port mapper client"; goto add_mapping_error; } skb = iwpm_create_nlmsg(RDMA_NL_IWPM_ADD_MAPPING, &nlh, nl_client); if (!skb) { err_str = "Unable to create a nlmsg"; goto add_mapping_error; } nlh->nlmsg_seq = iwpm_get_nlmsg_seq(); nlmsg_request = iwpm_get_nlmsg_request(nlh->nlmsg_seq, nl_client, GFP_KERNEL); if (!nlmsg_request) { err_str = "Unable to allocate netlink request"; goto add_mapping_error; } msg_seq = atomic_read(&echo_nlmsg_seq); /* fill in the add mapping message */ err_str = "Unable to put attribute of the nlmsg"; ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq, IWPM_NLA_MANAGE_MAPPING_SEQ); if (ret) goto add_mapping_error; ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage), &pm_msg->loc_addr, IWPM_NLA_MANAGE_ADDR); if (ret) goto add_mapping_error; /* If flags are required and we're not V4, then return a quiet error */ if (pm_msg->flags && iwpm_ulib_version == IWPM_UABI_VERSION_MIN) { ret = -EINVAL; goto add_mapping_error_nowarn; } if (iwpm_ulib_version > IWPM_UABI_VERSION_MIN) { ret = ibnl_put_attr(skb, nlh, sizeof(u32), &pm_msg->flags, IWPM_NLA_MANAGE_FLAGS); if (ret) goto add_mapping_error; } nlmsg_end(skb, nlh); nlmsg_request->req_buffer = pm_msg; ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ iwpm_user_pid = IWPM_PID_UNDEFINED; err_str = "Unable to send a nlmsg"; goto add_mapping_error; } ret = iwpm_wait_complete_req(nlmsg_request); return ret; add_mapping_error: pr_info("%s: %s (client = %u)\n", __func__, err_str, nl_client); add_mapping_error_nowarn: dev_kfree_skb(skb); if (nlmsg_request) iwpm_free_nlmsg_request(&nlmsg_request->kref); return ret; } /** * iwpm_add_and_query_mapping - Process the port mapper response to * iwpm_add_and_query_mapping request * @pm_msg: Contains the local ip/tcp address info to send * @nl_client: The index of the netlink client * * nlmsg attributes: * [IWPM_NLA_QUERY_MAPPING_SEQ] * [IWPM_NLA_QUERY_LOCAL_ADDR] * [IWPM_NLA_QUERY_REMOTE_ADDR] * [IWPM_NLA_QUERY_FLAGS] */ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client) { struct sk_buff *skb = NULL; struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlmsghdr *nlh; u32 msg_seq; const char *err_str = ""; int ret = -EINVAL; if (!iwpm_valid_pid()) return 0; if (!iwpm_check_registration(nl_client, IWPM_REG_VALID)) { err_str = "Unregistered port mapper client"; goto query_mapping_error; } ret = -ENOMEM; skb = iwpm_create_nlmsg(RDMA_NL_IWPM_QUERY_MAPPING, &nlh, nl_client); if (!skb) { err_str = "Unable to create a nlmsg"; goto query_mapping_error; } nlh->nlmsg_seq = iwpm_get_nlmsg_seq(); nlmsg_request = iwpm_get_nlmsg_request(nlh->nlmsg_seq, nl_client, GFP_KERNEL); if (!nlmsg_request) { err_str = "Unable to allocate netlink request"; goto query_mapping_error; } msg_seq = atomic_read(&echo_nlmsg_seq); /* fill in the query message */ err_str = "Unable to put attribute of the nlmsg"; ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq, IWPM_NLA_QUERY_MAPPING_SEQ); if (ret) goto query_mapping_error; ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage), &pm_msg->loc_addr, IWPM_NLA_QUERY_LOCAL_ADDR); if (ret) goto query_mapping_error; ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage), &pm_msg->rem_addr, IWPM_NLA_QUERY_REMOTE_ADDR); if (ret) goto query_mapping_error; /* If flags are required and we're not V4, then return a quite error */ if (pm_msg->flags && iwpm_ulib_version == IWPM_UABI_VERSION_MIN) { ret = -EINVAL; goto query_mapping_error_nowarn; } if (iwpm_ulib_version > IWPM_UABI_VERSION_MIN) { ret = ibnl_put_attr(skb, nlh, sizeof(u32), &pm_msg->flags, IWPM_NLA_QUERY_FLAGS); if (ret) goto query_mapping_error; } nlmsg_end(skb, nlh); nlmsg_request->req_buffer = pm_msg; ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ err_str = "Unable to send a nlmsg"; goto query_mapping_error; } ret = iwpm_wait_complete_req(nlmsg_request); return ret; query_mapping_error: pr_info("%s: %s (client = %u)\n", __func__, err_str, nl_client); query_mapping_error_nowarn: dev_kfree_skb(skb); if (nlmsg_request) iwpm_free_nlmsg_request(&nlmsg_request->kref); return ret; } /** * iwpm_remove_mapping - Send a netlink remove mapping request * to the userspace port mapper * * @local_addr: Local ip/tcp address to remove * @nl_client: The index of the netlink client * * nlmsg attributes: * [IWPM_NLA_MANAGE_MAPPING_SEQ] * [IWPM_NLA_MANAGE_ADDR] */ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client) { struct sk_buff *skb = NULL; struct nlmsghdr *nlh; u32 msg_seq; const char *err_str = ""; int ret = -EINVAL; if (!iwpm_valid_pid()) return 0; if (iwpm_check_registration(nl_client, IWPM_REG_UNDEF)) { err_str = "Unregistered port mapper client"; goto remove_mapping_error; } skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REMOVE_MAPPING, &nlh, nl_client); if (!skb) { ret = -ENOMEM; err_str = "Unable to create a nlmsg"; goto remove_mapping_error; } msg_seq = atomic_read(&echo_nlmsg_seq); nlh->nlmsg_seq = iwpm_get_nlmsg_seq(); err_str = "Unable to put attribute of the nlmsg"; ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq, IWPM_NLA_MANAGE_MAPPING_SEQ); if (ret) goto remove_mapping_error; ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage), local_addr, IWPM_NLA_MANAGE_ADDR); if (ret) goto remove_mapping_error; nlmsg_end(skb, nlh); ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid); if (ret) { skb = NULL; /* skb is freed in the netlink send-op handling */ iwpm_user_pid = IWPM_PID_UNDEFINED; err_str = "Unable to send a nlmsg"; goto remove_mapping_error; } iwpm_print_sockaddr(local_addr, "remove_mapping: Local sockaddr:"); return 0; remove_mapping_error: pr_info("%s: %s (client = %u)\n", __func__, err_str, nl_client); if (skb) dev_kfree_skb_any(skb); return ret; } /* netlink attribute policy for the received response to register pid request */ static const struct nla_policy resp_reg_policy[IWPM_NLA_RREG_PID_MAX] = { [IWPM_NLA_RREG_PID_SEQ] = { .type = NLA_U32 }, [IWPM_NLA_RREG_IBDEV_NAME] = { .type = NLA_STRING, .len = IWPM_DEVNAME_SIZE - 1 }, [IWPM_NLA_RREG_ULIB_NAME] = { .type = NLA_STRING, .len = IWPM_ULIBNAME_SIZE - 1 }, [IWPM_NLA_RREG_ULIB_VER] = { .type = NLA_U16 }, [IWPM_NLA_RREG_PID_ERR] = { .type = NLA_U16 } }; /** * iwpm_register_pid_cb - Process the port mapper response to * iwpm_register_pid query * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) * * If successful, the function receives the userspace port mapper pid * which is used in future communication with the port mapper */ int iwpm_register_pid_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlattr *nltb[IWPM_NLA_RREG_PID_MAX]; struct iwpm_dev_data *pm_msg; char *dev_name, *iwpm_name; u32 msg_seq; u8 nl_client; u16 iwpm_version; const char *msg_type = "Register Pid response"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_RREG_PID_MAX, resp_reg_policy, nltb, msg_type)) return -EINVAL; msg_seq = nla_get_u32(nltb[IWPM_NLA_RREG_PID_SEQ]); nlmsg_request = iwpm_find_nlmsg_request(msg_seq); if (!nlmsg_request) { pr_info("%s: Could not find a matching request (seq = %u)\n", __func__, msg_seq); return -EINVAL; } pm_msg = nlmsg_request->req_buffer; nl_client = nlmsg_request->nl_client; dev_name = (char *)nla_data(nltb[IWPM_NLA_RREG_IBDEV_NAME]); iwpm_name = (char *)nla_data(nltb[IWPM_NLA_RREG_ULIB_NAME]); iwpm_version = nla_get_u16(nltb[IWPM_NLA_RREG_ULIB_VER]); /* check device name, ulib name and version */ if (strcmp(pm_msg->dev_name, dev_name) || strcmp(iwpm_ulib_name, iwpm_name) || iwpm_version < IWPM_UABI_VERSION_MIN) { pr_info("%s: Incorrect info (dev = %s name = %s version = %u)\n", __func__, dev_name, iwpm_name, iwpm_version); nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; goto register_pid_response_exit; } iwpm_user_pid = cb->nlh->nlmsg_pid; iwpm_ulib_version = iwpm_version; if (iwpm_ulib_version < IWPM_UABI_VERSION) pr_warn_once("%s: Down level iwpmd/pid %d. Continuing...", __func__, iwpm_user_pid); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n", __func__, iwpm_user_pid); iwpm_set_registration(nl_client, IWPM_REG_VALID); register_pid_response_exit: nlmsg_request->request_done = 1; /* always for found nlmsg_request */ kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request); barrier(); up(&nlmsg_request->sem); return 0; } /* netlink attribute policy for the received response to add mapping request */ static const struct nla_policy resp_add_policy[IWPM_NLA_RMANAGE_MAPPING_MAX] = { [IWPM_NLA_RMANAGE_MAPPING_SEQ] = { .type = NLA_U32 }, [IWPM_NLA_RMANAGE_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RMANAGE_MAPPED_LOC_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RMANAGE_MAPPING_ERR] = { .type = NLA_U16 } }; /** * iwpm_add_mapping_cb - Process the port mapper response to * iwpm_add_mapping request * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) */ int iwpm_add_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct iwpm_sa_data *pm_msg; struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlattr *nltb[IWPM_NLA_RMANAGE_MAPPING_MAX]; struct sockaddr_storage *local_sockaddr; struct sockaddr_storage *mapped_sockaddr; const char *msg_type; u32 msg_seq; msg_type = "Add Mapping response"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_RMANAGE_MAPPING_MAX, resp_add_policy, nltb, msg_type)) return -EINVAL; atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); msg_seq = nla_get_u32(nltb[IWPM_NLA_RMANAGE_MAPPING_SEQ]); nlmsg_request = iwpm_find_nlmsg_request(msg_seq); if (!nlmsg_request) { pr_info("%s: Could not find a matching request (seq = %u)\n", __func__, msg_seq); return -EINVAL; } pm_msg = nlmsg_request->req_buffer; local_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RMANAGE_ADDR]); mapped_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RMANAGE_MAPPED_LOC_ADDR]); if (iwpm_compare_sockaddr(local_sockaddr, &pm_msg->loc_addr)) { nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; goto add_mapping_response_exit; } if (mapped_sockaddr->ss_family != local_sockaddr->ss_family) { pr_info("%s: Sockaddr family doesn't match the requested one\n", __func__); nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; goto add_mapping_response_exit; } memcpy(&pm_msg->mapped_loc_addr, mapped_sockaddr, sizeof(*mapped_sockaddr)); iwpm_print_sockaddr(&pm_msg->loc_addr, "add_mapping: Local sockaddr:"); iwpm_print_sockaddr(&pm_msg->mapped_loc_addr, "add_mapping: Mapped local sockaddr:"); add_mapping_response_exit: nlmsg_request->request_done = 1; /* always for found request */ kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request); barrier(); up(&nlmsg_request->sem); return 0; } /* netlink attribute policy for the response to add and query mapping request * and response with remote address info */ static const struct nla_policy resp_query_policy[IWPM_NLA_RQUERY_MAPPING_MAX] = { [IWPM_NLA_RQUERY_MAPPING_SEQ] = { .type = NLA_U32 }, [IWPM_NLA_RQUERY_LOCAL_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RQUERY_REMOTE_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RQUERY_MAPPED_LOC_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RQUERY_MAPPED_REM_ADDR] = { .len = sizeof(struct sockaddr_storage) }, [IWPM_NLA_RQUERY_MAPPING_ERR] = { .type = NLA_U16 } }; /** * iwpm_add_and_query_mapping_cb - Process the port mapper response to * iwpm_add_and_query_mapping request * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) */ int iwpm_add_and_query_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct iwpm_sa_data *pm_msg; struct iwpm_nlmsg_request *nlmsg_request = NULL; struct nlattr *nltb[IWPM_NLA_RQUERY_MAPPING_MAX]; struct sockaddr_storage *local_sockaddr, *remote_sockaddr; struct sockaddr_storage *mapped_loc_sockaddr, *mapped_rem_sockaddr; const char *msg_type; u32 msg_seq; u16 err_code; msg_type = "Query Mapping response"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_RQUERY_MAPPING_MAX, resp_query_policy, nltb, msg_type)) return -EINVAL; atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); msg_seq = nla_get_u32(nltb[IWPM_NLA_RQUERY_MAPPING_SEQ]); nlmsg_request = iwpm_find_nlmsg_request(msg_seq); if (!nlmsg_request) { pr_info("%s: Could not find a matching request (seq = %u)\n", __func__, msg_seq); return -EINVAL; } pm_msg = nlmsg_request->req_buffer; local_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_LOCAL_ADDR]); remote_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_REMOTE_ADDR]); mapped_loc_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_LOC_ADDR]); mapped_rem_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_REM_ADDR]); err_code = nla_get_u16(nltb[IWPM_NLA_RQUERY_MAPPING_ERR]); if (err_code == IWPM_REMOTE_QUERY_REJECT) { pr_info("%s: Received a Reject (pid = %u, echo seq = %u)\n", __func__, cb->nlh->nlmsg_pid, msg_seq); nlmsg_request->err_code = IWPM_REMOTE_QUERY_REJECT; } if (iwpm_compare_sockaddr(local_sockaddr, &pm_msg->loc_addr) || iwpm_compare_sockaddr(remote_sockaddr, &pm_msg->rem_addr)) { pr_info("%s: Incorrect local sockaddr\n", __func__); nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; goto query_mapping_response_exit; } if (mapped_loc_sockaddr->ss_family != local_sockaddr->ss_family || mapped_rem_sockaddr->ss_family != remote_sockaddr->ss_family) { pr_info("%s: Sockaddr family doesn't match the requested one\n", __func__); nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR; goto query_mapping_response_exit; } memcpy(&pm_msg->mapped_loc_addr, mapped_loc_sockaddr, sizeof(*mapped_loc_sockaddr)); memcpy(&pm_msg->mapped_rem_addr, mapped_rem_sockaddr, sizeof(*mapped_rem_sockaddr)); iwpm_print_sockaddr(&pm_msg->loc_addr, "query_mapping: Local sockaddr:"); iwpm_print_sockaddr(&pm_msg->mapped_loc_addr, "query_mapping: Mapped local sockaddr:"); iwpm_print_sockaddr(&pm_msg->rem_addr, "query_mapping: Remote sockaddr:"); iwpm_print_sockaddr(&pm_msg->mapped_rem_addr, "query_mapping: Mapped remote sockaddr:"); query_mapping_response_exit: nlmsg_request->request_done = 1; /* always for found request */ kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request); barrier(); up(&nlmsg_request->sem); return 0; } /** * iwpm_remote_info_cb - Process remote connecting peer address info, which * the port mapper has received from the connecting peer * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) * * Stores the IPv4/IPv6 address info in a hash table */ int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *nltb[IWPM_NLA_RQUERY_MAPPING_MAX]; struct sockaddr_storage *local_sockaddr, *remote_sockaddr; struct sockaddr_storage *mapped_loc_sockaddr, *mapped_rem_sockaddr; struct iwpm_remote_info *rem_info; const char *msg_type; u8 nl_client; int ret = -EINVAL; msg_type = "Remote Mapping info"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_RQUERY_MAPPING_MAX, resp_query_policy, nltb, msg_type)) return ret; nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); local_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_LOCAL_ADDR]); remote_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_REMOTE_ADDR]); mapped_loc_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_LOC_ADDR]); mapped_rem_sockaddr = (struct sockaddr_storage *) nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_REM_ADDR]); if (mapped_loc_sockaddr->ss_family != local_sockaddr->ss_family || mapped_rem_sockaddr->ss_family != remote_sockaddr->ss_family) { pr_info("%s: Sockaddr family doesn't match the requested one\n", __func__); return ret; } rem_info = kzalloc(sizeof(struct iwpm_remote_info), GFP_ATOMIC); if (!rem_info) { ret = -ENOMEM; return ret; } memcpy(&rem_info->mapped_loc_sockaddr, mapped_loc_sockaddr, sizeof(struct sockaddr_storage)); memcpy(&rem_info->remote_sockaddr, remote_sockaddr, sizeof(struct sockaddr_storage)); memcpy(&rem_info->mapped_rem_sockaddr, mapped_rem_sockaddr, sizeof(struct sockaddr_storage)); rem_info->nl_client = nl_client; iwpm_add_remote_info(rem_info); iwpm_print_sockaddr(local_sockaddr, "remote_info: Local sockaddr:"); iwpm_print_sockaddr(mapped_loc_sockaddr, "remote_info: Mapped local sockaddr:"); iwpm_print_sockaddr(remote_sockaddr, "remote_info: Remote sockaddr:"); iwpm_print_sockaddr(mapped_rem_sockaddr, "remote_info: Mapped remote sockaddr:"); return ret; } /* netlink attribute policy for the received request for mapping info */ static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = { [IWPM_NLA_MAPINFO_ULIB_NAME] = { .type = NLA_STRING, .len = IWPM_ULIBNAME_SIZE - 1 }, [IWPM_NLA_MAPINFO_ULIB_VER] = { .type = NLA_U16 } }; /** * iwpm_mapping_info_cb - Process a notification that the userspace * port mapper daemon is started * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) * * Using the received port mapper pid, send all the local mapping * info records to the userspace port mapper */ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *nltb[IWPM_NLA_MAPINFO_REQ_MAX]; const char *msg_type = "Mapping Info response"; u8 nl_client; char *iwpm_name; u16 iwpm_version; int ret = -EINVAL; if (iwpm_parse_nlmsg(cb, IWPM_NLA_MAPINFO_REQ_MAX, resp_mapinfo_policy, nltb, msg_type)) { pr_info("%s: Unable to parse nlmsg\n", __func__); return ret; } iwpm_name = (char *)nla_data(nltb[IWPM_NLA_MAPINFO_ULIB_NAME]); iwpm_version = nla_get_u16(nltb[IWPM_NLA_MAPINFO_ULIB_VER]); if (strcmp(iwpm_ulib_name, iwpm_name) || iwpm_version < IWPM_UABI_VERSION_MIN) { pr_info("%s: Invalid port mapper name = %s version = %u\n", __func__, iwpm_name, iwpm_version); return ret; } nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type); iwpm_set_registration(nl_client, IWPM_REG_INCOMPL); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); iwpm_user_pid = cb->nlh->nlmsg_pid; if (iwpm_ulib_version < IWPM_UABI_VERSION) pr_warn_once("%s: Down level iwpmd/pid %d. Continuing...", __func__, iwpm_user_pid); if (!iwpm_mapinfo_available()) return 0; pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n", __func__, iwpm_user_pid); ret = iwpm_send_mapinfo(nl_client, iwpm_user_pid); return ret; } /* netlink attribute policy for the received mapping info ack */ static const struct nla_policy ack_mapinfo_policy[IWPM_NLA_MAPINFO_NUM_MAX] = { [IWPM_NLA_MAPINFO_SEQ] = { .type = NLA_U32 }, [IWPM_NLA_MAPINFO_SEND_NUM] = { .type = NLA_U32 }, [IWPM_NLA_MAPINFO_ACK_NUM] = { .type = NLA_U32 } }; /** * iwpm_ack_mapping_info_cb - Process the port mapper ack for * the provided local mapping info records * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) */ int iwpm_ack_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *nltb[IWPM_NLA_MAPINFO_NUM_MAX]; u32 mapinfo_send, mapinfo_ack; const char *msg_type = "Mapping Info Ack"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_MAPINFO_NUM_MAX, ack_mapinfo_policy, nltb, msg_type)) return -EINVAL; mapinfo_send = nla_get_u32(nltb[IWPM_NLA_MAPINFO_SEND_NUM]); mapinfo_ack = nla_get_u32(nltb[IWPM_NLA_MAPINFO_ACK_NUM]); if (mapinfo_ack != mapinfo_send) pr_info("%s: Invalid mapinfo number (sent = %u ack-ed = %u)\n", __func__, mapinfo_send, mapinfo_ack); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); return 0; } /* netlink attribute policy for the received port mapper error message */ static const struct nla_policy map_error_policy[IWPM_NLA_ERR_MAX] = { [IWPM_NLA_ERR_SEQ] = { .type = NLA_U32 }, [IWPM_NLA_ERR_CODE] = { .type = NLA_U16 }, }; /** * iwpm_mapping_error_cb - Process port mapper notification for error * * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) */ int iwpm_mapping_error_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct iwpm_nlmsg_request *nlmsg_request = NULL; int nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type); struct nlattr *nltb[IWPM_NLA_ERR_MAX]; u32 msg_seq; u16 err_code; const char *msg_type = "Mapping Error Msg"; if (iwpm_parse_nlmsg(cb, IWPM_NLA_ERR_MAX, map_error_policy, nltb, msg_type)) return -EINVAL; msg_seq = nla_get_u32(nltb[IWPM_NLA_ERR_SEQ]); err_code = nla_get_u16(nltb[IWPM_NLA_ERR_CODE]); pr_info("%s: Received msg seq = %u err code = %u client = %d\n", __func__, msg_seq, err_code, nl_client); /* look for nlmsg_request */ nlmsg_request = iwpm_find_nlmsg_request(msg_seq); if (!nlmsg_request) { /* not all errors have associated requests */ pr_debug("Could not find matching req (seq = %u)\n", msg_seq); return 0; } atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); nlmsg_request->err_code = err_code; nlmsg_request->request_done = 1; /* always for found request */ kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request); barrier(); up(&nlmsg_request->sem); return 0; } /* netlink attribute policy for the received hello request */ static const struct nla_policy hello_policy[IWPM_NLA_HELLO_MAX] = { [IWPM_NLA_HELLO_ABI_VERSION] = { .type = NLA_U16 } }; /** * iwpm_hello_cb - Process a hello message from iwpmd * * @skb: The socket buffer * @cb: Contains the received message (payload and netlink header) * * Using the received port mapper pid, send the kernel's abi_version * after adjusting it to support the iwpmd version. */ int iwpm_hello_cb(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *nltb[IWPM_NLA_HELLO_MAX]; const char *msg_type = "Hello request"; u8 nl_client; u16 abi_version; int ret = -EINVAL; if (iwpm_parse_nlmsg(cb, IWPM_NLA_HELLO_MAX, hello_policy, nltb, msg_type)) { pr_info("%s: Unable to parse nlmsg\n", __func__); return ret; } abi_version = nla_get_u16(nltb[IWPM_NLA_HELLO_ABI_VERSION]); nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type); iwpm_set_registration(nl_client, IWPM_REG_INCOMPL); atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq); iwpm_ulib_version = min_t(u16, IWPM_UABI_VERSION, abi_version); pr_debug("Using ABI version %u\n", iwpm_ulib_version); iwpm_user_pid = cb->nlh->nlmsg_pid; ret = iwpm_send_hello(nl_client, iwpm_user_pid, iwpm_ulib_version); return ret; } |
| 2 32 62 4 60 57 34 2 32 20 54 54 51 17 17 9 9 8 8 3 1 1 1 3330 1192 15 7 2 9 5 7 7 7 7 7 7 7 1535 7 3 5 7 7 3 3 23 2 1 5 6 8 2 5 17 12 5 6 6 1 2 11 10 9 1 5 15 7 24 2 23 40 40 33 33 22 7 7 2 19 24 3032 3032 4316 4314 3 1 1 1 5 3 3 64 39 6 2 8 1 1 2 3 14 2 3 20 20 1 44 2 33 3 16 18 16 3 51 51 58 58 38 38 1 305 305 121 4 4181 4179 2052 311 1354 305 242 242 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io */ /* Devmaps primary use is as a backend map for XDP BPF helper call * bpf_redirect_map(). Because XDP is mostly concerned with performance we * spent some effort to ensure the datapath with redirect maps does not use * any locking. This is a quick note on the details. * * We have three possible paths to get into the devmap control plane bpf * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall * will invoke an update, delete, or lookup operation. To ensure updates and * deletes appear atomic from the datapath side xchg() is used to modify the * netdev_map array. Then because the datapath does a lookup into the netdev_map * array (read-only) from an RCU critical section we use call_rcu() to wait for * an rcu grace period before free'ing the old data structures. This ensures the * datapath always has a valid copy. However, the datapath does a "flush" * operation that pushes any pending packets in the driver outside the RCU * critical section. Each bpf_dtab_netdev tracks these pending operations using * a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until * this list is empty, indicating outstanding flush operations have completed. * * BPF syscalls may race with BPF program calls on any of the update, delete * or lookup operations. As noted above the xchg() operation also keep the * netdev_map consistent in this case. From the devmap side BPF programs * calling into these operations are the same as multiple user space threads * making system calls. * * Finally, any of the above may race with a netdev_unregister notifier. The * unregister notifier must search for net devices in the map structure that * contain a reference to the net device and remove them. This is a two step * process (a) dereference the bpf_dtab_netdev object in netdev_map and (b) * check to see if the ifindex is the same as the net_device being removed. * When removing the dev a cmpxchg() is used to ensure the correct dev is * removed, in the case of a concurrent update or delete operation it is * possible that the initially referenced dev is no longer in the map. As the * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. * * The devmap_hash type is a map type which interprets keys as ifindexes and * indexes these using a hashmap. This allows maps that use ifindex as key to be * densely packed instead of having holes in the lookup array for unused * ifindexes. The setup and packet enqueue/send code is shared between the two * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> #include <linux/btf_ids.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; struct net_device *dev; struct net_device *dev_rx; struct bpf_prog *xdp_prog; unsigned int count; }; struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; struct bpf_prog *xdp_prog; struct rcu_head rcu; unsigned int idx; struct bpf_devmap_val val; }; struct bpf_dtab { struct bpf_map map; struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; /* these are only used for DEVMAP_HASH type maps */ struct hlist_head *dev_index_head; spinlock_t index_lock; unsigned int items; u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); static struct hlist_head *dev_map_create_hash(unsigned int entries, int numa_node) { int i; struct hlist_head *hash; hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, int idx) { return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; } static int dev_map_alloc_check(union bpf_attr *attr) { u32 valsize = attr->value_size; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex * 8 bytes: ifindex + prog fd */ if (attr->max_entries == 0 || attr->key_size != 4 || (valsize != offsetofend(struct bpf_devmap_val, ifindex) && valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return -EINVAL; if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Hash table size must be power of 2; roundup_pow_of_two() * can overflow into UB on 32-bit arches */ if (attr->max_entries > 1UL << 31) return -EINVAL; } return 0; } static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* Hash table size must be power of 2 */ dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) return -ENOMEM; } return 0; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; int err; dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE); if (!dtab) return ERR_PTR(-ENOMEM); err = dev_map_init_map(dtab, attr); if (err) { bpf_map_area_free(dtab); return ERR_PTR(err); } spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; } static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); int i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were * disconnected from events. The following synchronize_rcu() guarantees * both rcu read critical sections complete and waits for * preempt-disable regions (NAPI being the relevant context here) so we * are certain there will be no further reads against the netdev_map and * all flush operations are complete. Flush operations can only be done * from NAPI context for this reason. */ spin_lock(&dev_map_lock); list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); /* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map() * during NAPI callback and cleared after the XDP redirect. There is no * explicit RCU read section which protects bpf_redirect_info->map but * local_bh_disable() also marks the beginning an RCU section. This * makes the complete softirq callback RCU protected. Thus after * following synchronize_rcu() there no bpf_redirect_info->map == map * assignment. */ synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ rcu_barrier(); if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { hlist_del_rcu(&dev->index_hlist); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } } bpf_map_area_free(dtab->dev_index_head); } else { for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; dev = rcu_dereference_raw(dtab->netdev_map[i]); if (!dev) continue; if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } bpf_map_area_free(dtab->netdev_map); } bpf_map_area_free(dtab); } static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = next_key; if (index >= dtab->map.max_entries) { *next = 0; return 0; } if (index == dtab->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0; } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct hlist_head *head = dev_map_index_hash(dtab, key); struct bpf_dtab_netdev *dev; hlist_for_each_entry_rcu(dev, head, index_hlist, lockdep_is_held(&dtab->index_lock)) if (dev->idx == key) return dev; return NULL; } static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 idx, *next = next_key; struct bpf_dtab_netdev *dev, *next_dev; struct hlist_head *head; int i = 0; if (!key) goto find_first; idx = *(u32 *)key; dev = __dev_map_hash_lookup_elem(map, idx); if (!dev) goto find_first; next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } i = idx & (dtab->n_buckets - 1); i++; find_first: for (; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } } return -ENOENT; } static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, struct net_device *dev) { struct xdp_txq_info txq = { .dev = dev }; struct xdp_buff xdp; int i, nframes = 0; for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; u32 act; int err; xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { case XDP_PASS: err = xdp_update_frame_from_buff(&xdp, xdpf); if (unlikely(err < 0)) xdp_return_frame_rx_napi(xdpf); else frames[nframes++] = xdpf; break; default: bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); break; } } return nframes; /* sent frames count */ } static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; unsigned int cnt = bq->count; int sent = 0, err = 0; int to_send = cnt; int i; if (unlikely(!cnt)) return; for (i = 0; i < cnt; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } if (bq->xdp_prog) { to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev); if (!to_send) goto out; } sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags); if (sent < 0) { /* If ndo_xdp_xmit fails with an errno, no frames have * been xmit'ed. */ err = sent; sent = 0; } /* If not all frames have been transmitted, it is our * responsibility to free them */ for (i = sent; unlikely(i < to_send); i++) xdp_return_frame_rx_napi(bq->q[i]); out: bq->count = 0; trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); } /* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the * driver before returning from its napi->poll() routine. See the comment above * xdp_do_flush() in filter.c. */ void __dev_flush(struct list_head *flush_list) { struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { bq_xmit_all(bq, XDP_XMIT_FLUSH); bq->dev_rx = NULL; bq->xdp_prog = NULL; __list_del_clearprev(&bq->flush_node); } } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *obj; if (key >= map->max_entries) return NULL; obj = rcu_dereference_check(dtab->netdev_map[key], rcu_read_lock_bh_held()); return obj; } /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu * variable access, and map elements stick around. See comment above * xdp_do_flush() in filter.c. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) bq_xmit_all(bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed * from net_device drivers NAPI func end. * * Do the same with xdp_prog and flush_list since these fields * are only ever modified together. */ if (!bq->dev_rx) { struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list(); bq->dev_rx = dev_rx; bq->xdp_prog = xdp_prog; list_add(&bq->flush_node, flush_list); } bq->q[bq->count++] = xdpf; } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { int err; if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return -EOPNOTSUPP; if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && xdp_frame_has_frags(xdpf))) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf)); if (unlikely(err)) return err; bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst) { struct xdp_txq_info txq = { .dev = dst->dev }; struct xdp_buff xdp; u32 act; if (!dst->xdp_prog) return XDP_PASS; __skb_pull(skb, skb->mac_len); xdp.txq = &txq; act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog); switch (act) { case XDP_PASS: __skb_push(skb, skb->mac_len); break; default: bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dst->dev, dst->xdp_prog, act); fallthrough; case XDP_DROP: kfree_skb(skb); break; } return act; } int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); } static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { if (!obj) return false; if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return false; if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && xdp_frame_has_frags(xdpf))) return false; if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf))) return false; return true; } static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, struct net_device *dev_rx, struct xdp_frame *xdpf) { struct xdp_frame *nxdpf; nxdpf = xdpf_clone(xdpf); if (!nxdpf) return -ENOMEM; bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); return 0; } static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex) { while (num_excluded--) { if (ifindex == excluded[num_excluded]) return true; } return false; } /* Get ifindex of each upper device. 'indexes' must be able to hold at * least MAX_NEST_DEV elements. * Returns the number of ifindexes added. */ static int get_upper_ifindexes(struct net_device *dev, int *indexes) { struct net_device *upper; struct list_head *iter; int n = 0; netdev_for_each_upper_dev_rcu(dev, upper, iter) { indexes[n++] = upper->ifindex; } return n; } int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); excluded_devices[num_excluded++] = dev_rx->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, lockdep_is_held(&dtab->index_lock)) { if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } } /* consume the last copy of the frame */ if (last_dst) bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); else xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ return 0; } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { int err; err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; /* Redirect has already succeeded semantically at this point, so we just * return 0 even if packet is dropped. Helper below takes care of * freeing skb. */ if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS) return 0; skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); return 0; } static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct sk_buff *nskb; int err; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; err = dev_map_generic_redirect(dst, nskb, xdp_prog); if (unlikely(err)) { consume_skb(nskb); return err; } return 0; } int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; struct hlist_node *next; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev, excluded_devices); excluded_devices[num_excluded++] = dev->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!dst) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dst, next, head, index_hlist) { if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } } /* consume the first skb and return */ if (last_dst) return dev_map_generic_redirect(last_dst, skb, xdp_prog); /* dtab is empty */ consume_skb(skb); return 0; } static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void __dev_map_entry_free(struct rcu_head *rcu) { struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } static long dev_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; int k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); if (old_dev) { call_rcu(&old_dev->rcu, __dev_map_entry_free); atomic_dec((atomic_t *)&dtab->items); } return 0; } static long dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; int k = *(u32 *)key; unsigned long flags; int ret = -ENOENT; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, k); if (old_dev) { dtab->items--; hlist_del_init_rcu(&old_dev->index_hlist); call_rcu(&old_dev->rcu, __dev_map_entry_free); ret = 0; } spin_unlock_irqrestore(&dtab->index_lock, flags); return ret; } static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_dtab *dtab, struct bpf_devmap_val *val, unsigned int idx) { struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), GFP_NOWAIT | __GFP_NOWARN, dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); dev->dev = dev_get_by_index(net, val->ifindex); if (!dev->dev) goto err_out; if (val->bpf_prog.fd > 0) { prog = bpf_prog_get_type_dev(val->bpf_prog.fd, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) goto err_put_dev; if (prog->expected_attach_type != BPF_XDP_DEVMAP || !bpf_prog_map_compatible(&dtab->map, prog)) goto err_put_prog; } dev->idx = idx; if (prog) { dev->xdp_prog = prog; dev->val.bpf_prog.id = prog->aux->id; } else { dev->xdp_prog = NULL; dev->val.bpf_prog.id = 0; } dev->val.ifindex = val->ifindex; return dev; err_put_prog: bpf_prog_put(prog); err_put_dev: dev_put(dev->dev); err_out: kfree(dev); return ERR_PTR(-EINVAL); } static long __dev_map_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 i = *(u32 *)key; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; if (unlikely(i >= dtab->map.max_entries)) return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) return -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (!val.ifindex) { dev = NULL; /* can not specify fd if ifindex is 0 */ if (val.bpf_prog.fd > 0) return -EINVAL; } else { dev = __dev_map_alloc_node(net, dtab, &val, i); if (IS_ERR(dev)) return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed * Remembering the driver side flush operation will happen before the * net device is removed. */ old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); else atomic_inc((atomic_t *)&dtab->items); return 0; } static long dev_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static long __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 idx = *(u32 *)key; unsigned long flags; int err = -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (unlikely(map_flags > BPF_EXIST || !val.ifindex)) return -EINVAL; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, idx); if (old_dev && (map_flags & BPF_NOEXIST)) goto out_err; dev = __dev_map_alloc_node(net, dtab, &val, idx); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out_err; } if (old_dev) { hlist_del_rcu(&old_dev->index_hlist); } else { if (dtab->items >= dtab->map.max_entries) { spin_unlock_irqrestore(&dtab->index_lock, flags); call_rcu(&dev->rcu, __dev_map_entry_free); return -E2BIG; } dtab->items++; } hlist_add_head_rcu(&dev->index_hlist, dev_map_index_hash(dtab, idx)); spin_unlock_irqrestore(&dtab->index_lock, flags); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; out_err: spin_unlock_irqrestore(&dtab->index_lock, flags); return err; } static long dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_hash_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static long dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } static long dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_hash_lookup_elem); } static u64 dev_map_mem_usage(const struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u64 usage = sizeof(struct bpf_dtab); if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) usage += (u64)dtab->n_buckets * sizeof(struct hlist_head); else usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *); usage += atomic_read((atomic_t *)&dtab->items) * (u64)sizeof(struct bpf_dtab_netdev); return usage; } BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab) const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_get_next_key, .map_lookup_elem = dev_map_lookup_elem, .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_map_redirect, }; const struct bpf_map_ops dev_map_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_hash_get_next_key, .map_lookup_elem = dev_map_hash_lookup_elem, .map_update_elem = dev_map_hash_update_elem, .map_delete_elem = dev_map_hash_delete_elem, .map_check_btf = map_check_no_btf, .map_mem_usage = dev_map_mem_usage, .map_btf_id = &dev_map_btf_ids[0], .map_redirect = dev_hash_map_redirect, }; static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, struct net_device *netdev) { unsigned long flags; u32 i; spin_lock_irqsave(&dtab->index_lock, flags); for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { if (netdev != dev->dev) continue; dtab->items--; hlist_del_rcu(&dev->index_hlist); call_rcu(&dev->rcu, __dev_map_entry_free); } } spin_unlock_irqrestore(&dtab->index_lock, flags); } static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct bpf_dtab *dtab; int i, cpu; switch (event) { case NETDEV_REGISTER: if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) break; /* will be freed in free_netdev() */ netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue); if (!netdev->xdp_bulkq) return NOTIFY_BAD; for_each_possible_cpu(cpu) per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete * operation does not free a netdev_map entry while we * are comparing it against the netdev being unregistered. */ rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) { if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dev_map_hash_remove_netdev(dtab, netdev); continue; } for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); if (dev == odev) { call_rcu(&dev->rcu, __dev_map_entry_free); atomic_dec((atomic_t *)&dtab->items); } } } rcu_read_unlock(); break; default: break; } return NOTIFY_OK; } static struct notifier_block dev_map_notifier = { .notifier_call = dev_map_notification, }; static int __init dev_map_init(void) { /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); return 0; } subsys_initcall(dev_map_init); |
| 58 58 6 6 6 6 6 6 1 1 48 1 47 48 4 28 1 1 2 35 3 1 2 2 1 28 6 14 1 5 8 1 1 1 1 4 1 1 1 1 9 1 1 1 2 2 2 1 6 1 1 2 2 2 1 1 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 | // SPDX-License-Identifier: GPL-2.0-only /* * File: pep.c * * Phonet pipe protocol end point socket * * Copyright (C) 2008 Nokia Corporation. * * Author: Rémi Denis-Courmont */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/socket.h> #include <net/sock.h> #include <net/tcp_states.h> #include <asm/ioctls.h> #include <linux/phonet.h> #include <linux/module.h> #include <net/phonet/phonet.h> #include <net/phonet/pep.h> #include <net/phonet/gprs.h> /* sk_state values: * TCP_CLOSE sock not in use yet * TCP_CLOSE_WAIT disconnected pipe * TCP_LISTEN listening pipe endpoint * TCP_SYN_RECV connected pipe in disabled state * TCP_ESTABLISHED connected pipe in enabled state * * pep_sock locking: * - sk_state, hlist: sock lock needed * - listener: read only * - pipe_handle: read only */ #define CREDITS_MAX 10 #define CREDITS_THR 7 #define pep_sb_size(s) (((s) + 5) & ~3) /* 2-bytes head, 32-bits aligned */ /* Get the next TLV sub-block. */ static unsigned char *pep_get_sb(struct sk_buff *skb, u8 *ptype, u8 *plen, void *buf) { void *data = NULL; struct { u8 sb_type; u8 sb_len; } *ph, h; int buflen = *plen; ph = skb_header_pointer(skb, 0, 2, &h); if (ph == NULL || ph->sb_len < 2 || !pskb_may_pull(skb, ph->sb_len)) return NULL; ph->sb_len -= 2; *ptype = ph->sb_type; *plen = ph->sb_len; if (buflen > ph->sb_len) buflen = ph->sb_len; data = skb_header_pointer(skb, 2, buflen, buf); __skb_pull(skb, 2 + ph->sb_len); return data; } static struct sk_buff *pep_alloc_skb(struct sock *sk, const void *payload, int len, gfp_t priority) { struct sk_buff *skb = alloc_skb(MAX_PNPIPE_HEADER + len, priority); if (!skb) return NULL; skb_set_owner_w(skb, sk); skb_reserve(skb, MAX_PNPIPE_HEADER); __skb_put(skb, len); skb_copy_to_linear_data(skb, payload, len); __skb_push(skb, sizeof(struct pnpipehdr)); skb_reset_transport_header(skb); return skb; } static int pep_reply(struct sock *sk, struct sk_buff *oskb, u8 code, const void *data, int len, gfp_t priority) { const struct pnpipehdr *oph = pnp_hdr(oskb); struct pnpipehdr *ph; struct sk_buff *skb; struct sockaddr_pn peer; skb = pep_alloc_skb(sk, data, len, priority); if (!skb) return -ENOMEM; ph = pnp_hdr(skb); ph->utid = oph->utid; ph->message_id = oph->message_id + 1; /* REQ -> RESP */ ph->pipe_handle = oph->pipe_handle; ph->error_code = code; pn_skb_get_src_sockaddr(oskb, &peer); return pn_skb_send(sk, skb, &peer); } static int pep_indicate(struct sock *sk, u8 id, u8 code, const void *data, int len, gfp_t priority) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *ph; struct sk_buff *skb; skb = pep_alloc_skb(sk, data, len, priority); if (!skb) return -ENOMEM; ph = pnp_hdr(skb); ph->utid = 0; ph->message_id = id; ph->pipe_handle = pn->pipe_handle; ph->error_code = code; return pn_skb_send(sk, skb, NULL); } #define PAD 0x00 static int pipe_handler_request(struct sock *sk, u8 id, u8 code, const void *data, int len) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *ph; struct sk_buff *skb; skb = pep_alloc_skb(sk, data, len, GFP_KERNEL); if (!skb) return -ENOMEM; ph = pnp_hdr(skb); ph->utid = id; /* whatever */ ph->message_id = id; ph->pipe_handle = pn->pipe_handle; ph->error_code = code; return pn_skb_send(sk, skb, NULL); } static int pipe_handler_send_created_ind(struct sock *sk) { struct pep_sock *pn = pep_sk(sk); u8 data[4] = { PN_PIPE_SB_NEGOTIATED_FC, pep_sb_size(2), pn->tx_fc, pn->rx_fc, }; return pep_indicate(sk, PNS_PIPE_CREATED_IND, 1 /* sub-blocks */, data, 4, GFP_ATOMIC); } static int pep_accept_conn(struct sock *sk, struct sk_buff *skb) { static const u8 data[20] = { PAD, PAD, PAD, 2 /* sub-blocks */, PN_PIPE_SB_REQUIRED_FC_TX, pep_sb_size(5), 3, PAD, PN_MULTI_CREDIT_FLOW_CONTROL, PN_ONE_CREDIT_FLOW_CONTROL, PN_LEGACY_FLOW_CONTROL, PAD, PN_PIPE_SB_PREFERRED_FC_RX, pep_sb_size(5), 3, PAD, PN_MULTI_CREDIT_FLOW_CONTROL, PN_ONE_CREDIT_FLOW_CONTROL, PN_LEGACY_FLOW_CONTROL, PAD, }; might_sleep(); return pep_reply(sk, skb, PN_PIPE_NO_ERROR, data, sizeof(data), GFP_KERNEL); } static int pep_reject_conn(struct sock *sk, struct sk_buff *skb, u8 code, gfp_t priority) { static const u8 data[4] = { PAD, PAD, PAD, 0 /* sub-blocks */ }; WARN_ON(code == PN_PIPE_NO_ERROR); return pep_reply(sk, skb, code, data, sizeof(data), priority); } /* Control requests are not sent by the pipe service and have a specific * message format. */ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, gfp_t priority) { const struct pnpipehdr *oph = pnp_hdr(oskb); struct sk_buff *skb; struct pnpipehdr *ph; struct sockaddr_pn dst; u8 data[4] = { oph->pep_type, /* PEP type */ code, /* error code, at an unusual offset */ PAD, PAD, }; skb = pep_alloc_skb(sk, data, 4, priority); if (!skb) return -ENOMEM; ph = pnp_hdr(skb); ph->utid = oph->utid; ph->message_id = PNS_PEP_CTRL_RESP; ph->pipe_handle = oph->pipe_handle; ph->data0 = oph->data[0]; /* CTRL id */ pn_skb_get_src_sockaddr(oskb, &dst); return pn_skb_send(sk, skb, &dst); } static int pipe_snd_status(struct sock *sk, u8 type, u8 status, gfp_t priority) { u8 data[4] = { type, PAD, PAD, status }; return pep_indicate(sk, PNS_PEP_STATUS_IND, PN_PEP_TYPE_COMMON, data, 4, priority); } /* Send our RX flow control information to the sender. * Socket must be locked. */ static void pipe_grant_credits(struct sock *sk, gfp_t priority) { struct pep_sock *pn = pep_sk(sk); BUG_ON(sk->sk_state != TCP_ESTABLISHED); switch (pn->rx_fc) { case PN_LEGACY_FLOW_CONTROL: /* TODO */ break; case PN_ONE_CREDIT_FLOW_CONTROL: if (pipe_snd_status(sk, PN_PEP_IND_FLOW_CONTROL, PEP_IND_READY, priority) == 0) pn->rx_credits = 1; break; case PN_MULTI_CREDIT_FLOW_CONTROL: if ((pn->rx_credits + CREDITS_THR) > CREDITS_MAX) break; if (pipe_snd_status(sk, PN_PEP_IND_ID_MCFC_GRANT_CREDITS, CREDITS_MAX - pn->rx_credits, priority) == 0) pn->rx_credits = CREDITS_MAX; break; } } static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *hdr; int wake = 0; if (!pskb_may_pull(skb, sizeof(*hdr) + 4)) return -EINVAL; hdr = pnp_hdr(skb); if (hdr->pep_type != PN_PEP_TYPE_COMMON) { net_dbg_ratelimited("Phonet unknown PEP type: %u\n", (unsigned int)hdr->pep_type); return -EOPNOTSUPP; } switch (hdr->data[0]) { case PN_PEP_IND_FLOW_CONTROL: switch (pn->tx_fc) { case PN_LEGACY_FLOW_CONTROL: switch (hdr->data[3]) { case PEP_IND_BUSY: atomic_set(&pn->tx_credits, 0); break; case PEP_IND_READY: atomic_set(&pn->tx_credits, wake = 1); break; } break; case PN_ONE_CREDIT_FLOW_CONTROL: if (hdr->data[3] == PEP_IND_READY) atomic_set(&pn->tx_credits, wake = 1); break; } break; case PN_PEP_IND_ID_MCFC_GRANT_CREDITS: if (pn->tx_fc != PN_MULTI_CREDIT_FLOW_CONTROL) break; atomic_add(wake = hdr->data[3], &pn->tx_credits); break; default: net_dbg_ratelimited("Phonet unknown PEP indication: %u\n", (unsigned int)hdr->data[0]); return -EOPNOTSUPP; } if (wake) sk->sk_write_space(sk); return 0; } static int pipe_rcv_created(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *hdr = pnp_hdr(skb); u8 n_sb = hdr->data0; pn->rx_fc = pn->tx_fc = PN_LEGACY_FLOW_CONTROL; __skb_pull(skb, sizeof(*hdr)); while (n_sb > 0) { u8 type, buf[2], len = sizeof(buf); u8 *data = pep_get_sb(skb, &type, &len, buf); if (data == NULL) return -EINVAL; switch (type) { case PN_PIPE_SB_NEGOTIATED_FC: if (len < 2 || (data[0] | data[1]) > 3) break; pn->tx_fc = data[0] & 3; pn->rx_fc = data[1] & 3; break; } n_sb--; } return 0; } /* Queue an skb to a connected sock. * Socket lock must be held. */ static int pipe_do_rcv(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *hdr = pnp_hdr(skb); struct sk_buff_head *queue; int err = 0; BUG_ON(sk->sk_state == TCP_CLOSE_WAIT); switch (hdr->message_id) { case PNS_PEP_CONNECT_REQ: pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE, GFP_ATOMIC); break; case PNS_PEP_DISCONNECT_REQ: pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC); sk->sk_state = TCP_CLOSE_WAIT; if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); break; case PNS_PEP_ENABLE_REQ: /* Wait for PNS_PIPE_(ENABLED|REDIRECTED)_IND */ pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC); break; case PNS_PEP_RESET_REQ: switch (hdr->state_after_reset) { case PN_PIPE_DISABLE: pn->init_enable = 0; break; case PN_PIPE_ENABLE: pn->init_enable = 1; break; default: /* not allowed to send an error here!? */ err = -EINVAL; goto out; } fallthrough; case PNS_PEP_DISABLE_REQ: atomic_set(&pn->tx_credits, 0); pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC); break; case PNS_PEP_CTRL_REQ: if (skb_queue_len(&pn->ctrlreq_queue) >= PNPIPE_CTRLREQ_MAX) { atomic_inc(&sk->sk_drops); break; } __skb_pull(skb, 4); queue = &pn->ctrlreq_queue; goto queue; case PNS_PIPE_ALIGNED_DATA: __skb_pull(skb, 1); fallthrough; case PNS_PIPE_DATA: __skb_pull(skb, 3); /* Pipe data header */ if (!pn_flow_safe(pn->rx_fc)) { err = sock_queue_rcv_skb(sk, skb); if (!err) return NET_RX_SUCCESS; err = -ENOBUFS; break; } if (pn->rx_credits == 0) { atomic_inc(&sk->sk_drops); err = -ENOBUFS; break; } pn->rx_credits--; queue = &sk->sk_receive_queue; goto queue; case PNS_PEP_STATUS_IND: pipe_rcv_status(sk, skb); break; case PNS_PIPE_REDIRECTED_IND: err = pipe_rcv_created(sk, skb); break; case PNS_PIPE_CREATED_IND: err = pipe_rcv_created(sk, skb); if (err) break; fallthrough; case PNS_PIPE_RESET_IND: if (!pn->init_enable) break; fallthrough; case PNS_PIPE_ENABLED_IND: if (!pn_flow_safe(pn->tx_fc)) { atomic_set(&pn->tx_credits, 1); sk->sk_write_space(sk); } if (sk->sk_state == TCP_ESTABLISHED) break; /* Nothing to do */ sk->sk_state = TCP_ESTABLISHED; pipe_grant_credits(sk, GFP_ATOMIC); break; case PNS_PIPE_DISABLED_IND: sk->sk_state = TCP_SYN_RECV; pn->rx_credits = 0; break; default: net_dbg_ratelimited("Phonet unknown PEP message: %u\n", hdr->message_id); err = -EINVAL; } out: kfree_skb(skb); return (err == -ENOBUFS) ? NET_RX_DROP : NET_RX_SUCCESS; queue: skb->dev = NULL; skb_set_owner_r(skb, sk); skb_queue_tail(queue, skb); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return NET_RX_SUCCESS; } /* Destroy connected sock. */ static void pipe_destruct(struct sock *sk) { struct pep_sock *pn = pep_sk(sk); skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&pn->ctrlreq_queue); } static u8 pipe_negotiate_fc(const u8 *fcs, unsigned int n) { unsigned int i; u8 final_fc = PN_NO_FLOW_CONTROL; for (i = 0; i < n; i++) { u8 fc = fcs[i]; if (fc > final_fc && fc < PN_MAX_FLOW_CONTROL) final_fc = fc; } return final_fc; } static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *hdr; u8 n_sb; if (!pskb_pull(skb, sizeof(*hdr) + 4)) return -EINVAL; hdr = pnp_hdr(skb); if (hdr->error_code != PN_PIPE_NO_ERROR) return -ECONNREFUSED; /* Parse sub-blocks */ n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[6], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); if (data == NULL) return -EINVAL; switch (type) { case PN_PIPE_SB_REQUIRED_FC_TX: if (len < 2 || len < data[0]) break; pn->tx_fc = pipe_negotiate_fc(data + 2, len - 2); break; case PN_PIPE_SB_PREFERRED_FC_RX: if (len < 2 || len < data[0]) break; pn->rx_fc = pipe_negotiate_fc(data + 2, len - 2); break; } n_sb--; } return pipe_handler_send_created_ind(sk); } static int pep_enableresp_rcv(struct sock *sk, struct sk_buff *skb) { struct pnpipehdr *hdr = pnp_hdr(skb); if (hdr->error_code != PN_PIPE_NO_ERROR) return -ECONNREFUSED; return pep_indicate(sk, PNS_PIPE_ENABLED_IND, 0 /* sub-blocks */, NULL, 0, GFP_ATOMIC); } static void pipe_start_flow_control(struct sock *sk) { struct pep_sock *pn = pep_sk(sk); if (!pn_flow_safe(pn->tx_fc)) { atomic_set(&pn->tx_credits, 1); sk->sk_write_space(sk); } pipe_grant_credits(sk, GFP_ATOMIC); } /* Queue an skb to an actively connected sock. * Socket lock must be held. */ static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *hdr = pnp_hdr(skb); int err = NET_RX_SUCCESS; switch (hdr->message_id) { case PNS_PIPE_ALIGNED_DATA: __skb_pull(skb, 1); fallthrough; case PNS_PIPE_DATA: __skb_pull(skb, 3); /* Pipe data header */ if (!pn_flow_safe(pn->rx_fc)) { err = sock_queue_rcv_skb(sk, skb); if (!err) return NET_RX_SUCCESS; err = NET_RX_DROP; break; } if (pn->rx_credits == 0) { atomic_inc(&sk->sk_drops); err = NET_RX_DROP; break; } pn->rx_credits--; skb->dev = NULL; skb_set_owner_r(skb, sk); skb_queue_tail(&sk->sk_receive_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return NET_RX_SUCCESS; case PNS_PEP_CONNECT_RESP: if (sk->sk_state != TCP_SYN_SENT) break; if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); if (pep_connresp_rcv(sk, skb)) { sk->sk_state = TCP_CLOSE_WAIT; break; } if (pn->init_enable == PN_PIPE_DISABLE) sk->sk_state = TCP_SYN_RECV; else { sk->sk_state = TCP_ESTABLISHED; pipe_start_flow_control(sk); } break; case PNS_PEP_ENABLE_RESP: if (sk->sk_state != TCP_SYN_SENT) break; if (pep_enableresp_rcv(sk, skb)) { sk->sk_state = TCP_CLOSE_WAIT; break; } sk->sk_state = TCP_ESTABLISHED; pipe_start_flow_control(sk); break; case PNS_PEP_DISCONNECT_RESP: /* sock should already be dead, nothing to do */ break; case PNS_PEP_STATUS_IND: pipe_rcv_status(sk, skb); break; } kfree_skb(skb); return err; } /* Listening sock must be locked */ static struct sock *pep_find_pipe(const struct hlist_head *hlist, const struct sockaddr_pn *dst, u8 pipe_handle) { struct sock *sknode; u16 dobj = pn_sockaddr_get_object(dst); sk_for_each(sknode, hlist) { struct pep_sock *pnnode = pep_sk(sknode); /* Ports match, but addresses might not: */ if (pnnode->pn_sk.sobject != dobj) continue; if (pnnode->pipe_handle != pipe_handle) continue; if (sknode->sk_state == TCP_CLOSE_WAIT) continue; sock_hold(sknode); return sknode; } return NULL; } /* * Deliver an skb to a listening sock. * Socket lock must be held. * We then queue the skb to the right connected sock (if any). */ static int pep_do_rcv(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct sock *sknode; struct pnpipehdr *hdr; struct sockaddr_pn dst; u8 pipe_handle; if (!pskb_may_pull(skb, sizeof(*hdr))) goto drop; hdr = pnp_hdr(skb); pipe_handle = hdr->pipe_handle; if (pipe_handle == PN_PIPE_INVALID_HANDLE) goto drop; pn_skb_get_dst_sockaddr(skb, &dst); /* Look for an existing pipe handle */ sknode = pep_find_pipe(&pn->hlist, &dst, pipe_handle); if (sknode) return sk_receive_skb(sknode, skb, 1); switch (hdr->message_id) { case PNS_PEP_CONNECT_REQ: if (sk->sk_state != TCP_LISTEN || sk_acceptq_is_full(sk)) { pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE, GFP_ATOMIC); break; } skb_queue_head(&sk->sk_receive_queue, skb); sk_acceptq_added(sk); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return NET_RX_SUCCESS; case PNS_PEP_DISCONNECT_REQ: pep_reply(sk, skb, PN_PIPE_NO_ERROR, NULL, 0, GFP_ATOMIC); break; case PNS_PEP_CTRL_REQ: pep_ctrlreq_error(sk, skb, PN_PIPE_INVALID_HANDLE, GFP_ATOMIC); break; case PNS_PEP_RESET_REQ: case PNS_PEP_ENABLE_REQ: case PNS_PEP_DISABLE_REQ: /* invalid handle is not even allowed here! */ break; default: if ((1 << sk->sk_state) & ~(TCPF_CLOSE|TCPF_LISTEN|TCPF_CLOSE_WAIT)) /* actively connected socket */ return pipe_handler_do_rcv(sk, skb); } drop: kfree_skb(skb); return NET_RX_SUCCESS; } static int pipe_do_remove(struct sock *sk) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *ph; struct sk_buff *skb; skb = pep_alloc_skb(sk, NULL, 0, GFP_KERNEL); if (!skb) return -ENOMEM; ph = pnp_hdr(skb); ph->utid = 0; ph->message_id = PNS_PIPE_REMOVE_REQ; ph->pipe_handle = pn->pipe_handle; ph->data0 = PAD; return pn_skb_send(sk, skb, NULL); } /* associated socket ceases to exist */ static void pep_sock_close(struct sock *sk, long timeout) { struct pep_sock *pn = pep_sk(sk); int ifindex = 0; sock_hold(sk); /* keep a reference after sk_common_release() */ sk_common_release(sk); lock_sock(sk); if ((1 << sk->sk_state) & (TCPF_SYN_RECV|TCPF_ESTABLISHED)) { if (sk->sk_backlog_rcv == pipe_do_rcv) /* Forcefully remove dangling Phonet pipe */ pipe_do_remove(sk); else pipe_handler_request(sk, PNS_PEP_DISCONNECT_REQ, PAD, NULL, 0); } sk->sk_state = TCP_CLOSE; ifindex = pn->ifindex; pn->ifindex = 0; release_sock(sk); if (ifindex) gprs_detach(sk); sock_put(sk); } static struct sock *pep_sock_accept(struct sock *sk, struct proto_accept_arg *arg) { struct pep_sock *pn = pep_sk(sk), *newpn; struct sock *newsk = NULL; struct sk_buff *skb; struct pnpipehdr *hdr; struct sockaddr_pn dst, src; int err; u16 peer_type; u8 pipe_handle, enabled, n_sb; u8 aligned = 0; skb = skb_recv_datagram(sk, (arg->flags & O_NONBLOCK) ? MSG_DONTWAIT : 0, &arg->err); if (!skb) return NULL; lock_sock(sk); if (sk->sk_state != TCP_LISTEN) { err = -EINVAL; goto drop; } sk_acceptq_removed(sk); err = -EPROTO; if (!pskb_may_pull(skb, sizeof(*hdr) + 4)) goto drop; hdr = pnp_hdr(skb); pipe_handle = hdr->pipe_handle; switch (hdr->state_after_connect) { case PN_PIPE_DISABLE: enabled = 0; break; case PN_PIPE_ENABLE: enabled = 1; break; default: pep_reject_conn(sk, skb, PN_PIPE_ERR_INVALID_PARAM, GFP_KERNEL); goto drop; } peer_type = hdr->other_pep_type << 8; /* Parse sub-blocks (options) */ n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[1], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); if (data == NULL) goto drop; switch (type) { case PN_PIPE_SB_CONNECT_REQ_PEP_SUB_TYPE: if (len < 1) goto drop; peer_type = (peer_type & 0xff00) | data[0]; break; case PN_PIPE_SB_ALIGNED_DATA: aligned = data[0] != 0; break; } n_sb--; } /* Check for duplicate pipe handle */ newsk = pep_find_pipe(&pn->hlist, &dst, pipe_handle); if (unlikely(newsk)) { __sock_put(newsk); newsk = NULL; pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE, GFP_KERNEL); goto drop; } /* Create a new to-be-accepted sock */ newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, arg->kern); if (!newsk) { pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL); err = -ENOBUFS; goto drop; } sock_init_data(NULL, newsk); newsk->sk_state = TCP_SYN_RECV; newsk->sk_backlog_rcv = pipe_do_rcv; newsk->sk_protocol = sk->sk_protocol; newsk->sk_destruct = pipe_destruct; newpn = pep_sk(newsk); pn_skb_get_dst_sockaddr(skb, &dst); pn_skb_get_src_sockaddr(skb, &src); newpn->pn_sk.sobject = pn_sockaddr_get_object(&dst); newpn->pn_sk.dobject = pn_sockaddr_get_object(&src); newpn->pn_sk.resource = pn_sockaddr_get_resource(&dst); sock_hold(sk); newpn->listener = sk; skb_queue_head_init(&newpn->ctrlreq_queue); newpn->pipe_handle = pipe_handle; atomic_set(&newpn->tx_credits, 0); newpn->ifindex = 0; newpn->peer_type = peer_type; newpn->rx_credits = 0; newpn->rx_fc = newpn->tx_fc = PN_LEGACY_FLOW_CONTROL; newpn->init_enable = enabled; newpn->aligned = aligned; err = pep_accept_conn(newsk, skb); if (err) { __sock_put(sk); sock_put(newsk); newsk = NULL; goto drop; } sk_add_node(newsk, &pn->hlist); drop: release_sock(sk); kfree_skb(skb); arg->err = err; return newsk; } static int pep_sock_connect(struct sock *sk, struct sockaddr *addr, int len) { struct pep_sock *pn = pep_sk(sk); int err; u8 data[4] = { 0 /* sub-blocks */, PAD, PAD, PAD }; if (pn->pipe_handle == PN_PIPE_INVALID_HANDLE) pn->pipe_handle = 1; /* anything but INVALID_HANDLE */ err = pipe_handler_request(sk, PNS_PEP_CONNECT_REQ, pn->init_enable, data, 4); if (err) { pn->pipe_handle = PN_PIPE_INVALID_HANDLE; return err; } sk->sk_state = TCP_SYN_SENT; return 0; } static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len) { int err; err = pipe_handler_request(sk, PNS_PEP_ENABLE_REQ, PAD, NULL, 0); if (err) return err; sk->sk_state = TCP_SYN_SENT; return 0; } static unsigned int pep_first_packet_length(struct sock *sk) { struct pep_sock *pn = pep_sk(sk); struct sk_buff_head *q; struct sk_buff *skb; unsigned int len = 0; bool found = false; if (sock_flag(sk, SOCK_URGINLINE)) { q = &pn->ctrlreq_queue; spin_lock_bh(&q->lock); skb = skb_peek(q); if (skb) { len = skb->len; found = true; } spin_unlock_bh(&q->lock); } if (likely(!found)) { q = &sk->sk_receive_queue; spin_lock_bh(&q->lock); skb = skb_peek(q); if (skb) len = skb->len; spin_unlock_bh(&q->lock); } return len; } static int pep_ioctl(struct sock *sk, int cmd, int *karg) { struct pep_sock *pn = pep_sk(sk); int ret = -ENOIOCTLCMD; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) { ret = -EINVAL; break; } *karg = pep_first_packet_length(sk); ret = 0; break; case SIOCPNENABLEPIPE: lock_sock(sk); if (sk->sk_state == TCP_SYN_SENT) ret = -EBUSY; else if (sk->sk_state == TCP_ESTABLISHED) ret = -EISCONN; else if (!pn->pn_sk.sobject) ret = -EADDRNOTAVAIL; else ret = pep_sock_enable(sk, NULL, 0); release_sock(sk); break; } return ret; } static int pep_init(struct sock *sk) { struct pep_sock *pn = pep_sk(sk); sk->sk_destruct = pipe_destruct; INIT_HLIST_HEAD(&pn->hlist); pn->listener = NULL; skb_queue_head_init(&pn->ctrlreq_queue); atomic_set(&pn->tx_credits, 0); pn->ifindex = 0; pn->peer_type = 0; pn->pipe_handle = PN_PIPE_INVALID_HANDLE; pn->rx_credits = 0; pn->rx_fc = pn->tx_fc = PN_LEGACY_FLOW_CONTROL; pn->init_enable = 1; pn->aligned = 0; return 0; } static int pep_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct pep_sock *pn = pep_sk(sk); int val = 0, err = 0; if (level != SOL_PNPIPE) return -ENOPROTOOPT; if (optlen >= sizeof(int)) { if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; } lock_sock(sk); switch (optname) { case PNPIPE_ENCAP: if (val && val != PNPIPE_ENCAP_IP) { err = -EINVAL; break; } if (!pn->ifindex == !val) break; /* Nothing to do! */ if (!capable(CAP_NET_ADMIN)) { err = -EPERM; break; } if (val) { release_sock(sk); err = gprs_attach(sk); if (err > 0) { pn->ifindex = err; err = 0; } } else { pn->ifindex = 0; release_sock(sk); gprs_detach(sk); err = 0; } goto out_norel; case PNPIPE_HANDLE: if ((sk->sk_state == TCP_CLOSE) && (val >= 0) && (val < PN_PIPE_INVALID_HANDLE)) pn->pipe_handle = val; else err = -EINVAL; break; case PNPIPE_INITSTATE: pn->init_enable = !!val; break; default: err = -ENOPROTOOPT; } release_sock(sk); out_norel: return err; } static int pep_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct pep_sock *pn = pep_sk(sk); int len, val; if (level != SOL_PNPIPE) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; switch (optname) { case PNPIPE_ENCAP: val = pn->ifindex ? PNPIPE_ENCAP_IP : PNPIPE_ENCAP_NONE; break; case PNPIPE_IFINDEX: val = pn->ifindex; break; case PNPIPE_HANDLE: val = pn->pipe_handle; if (val == PN_PIPE_INVALID_HANDLE) return -EINVAL; break; case PNPIPE_INITSTATE: val = pn->init_enable; break; default: return -ENOPROTOOPT; } len = min_t(unsigned int, sizeof(int), len); if (put_user(len, optlen)) return -EFAULT; if (put_user(val, (int __user *) optval)) return -EFAULT; return 0; } static int pipe_skb_send(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *ph; int err; if (pn_flow_safe(pn->tx_fc) && !atomic_add_unless(&pn->tx_credits, -1, 0)) { kfree_skb(skb); return -ENOBUFS; } skb_push(skb, 3 + pn->aligned); skb_reset_transport_header(skb); ph = pnp_hdr(skb); ph->utid = 0; if (pn->aligned) { ph->message_id = PNS_PIPE_ALIGNED_DATA; ph->data0 = 0; /* padding */ } else ph->message_id = PNS_PIPE_DATA; ph->pipe_handle = pn->pipe_handle; err = pn_skb_send(sk, skb, NULL); if (err && pn_flow_safe(pn->tx_fc)) atomic_inc(&pn->tx_credits); return err; } static int pep_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct pep_sock *pn = pep_sk(sk); struct sk_buff *skb; long timeo; int flags = msg->msg_flags; int err, done; if (len > USHRT_MAX) return -EMSGSIZE; if ((msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL| MSG_CMSG_COMPAT)) || !(msg->msg_flags & MSG_EOR)) return -EOPNOTSUPP; skb = sock_alloc_send_skb(sk, MAX_PNPIPE_HEADER + len, flags & MSG_DONTWAIT, &err); if (!skb) return err; skb_reserve(skb, MAX_PHONET_HEADER + 3 + pn->aligned); err = memcpy_from_msg(skb_put(skb, len), msg, len); if (err < 0) goto outfree; lock_sock(sk); timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); if ((1 << sk->sk_state) & (TCPF_LISTEN|TCPF_CLOSE)) { err = -ENOTCONN; goto out; } if (sk->sk_state != TCP_ESTABLISHED) { /* Wait until the pipe gets to enabled state */ disabled: err = sk_stream_wait_connect(sk, &timeo); if (err) goto out; if (sk->sk_state == TCP_CLOSE_WAIT) { err = -ECONNRESET; goto out; } } BUG_ON(sk->sk_state != TCP_ESTABLISHED); /* Wait until flow control allows TX */ done = atomic_read(&pn->tx_credits); while (!done) { DEFINE_WAIT_FUNC(wait, woken_wake_function); if (!timeo) { err = -EAGAIN; goto out; } if (signal_pending(current)) { err = sock_intr_errno(timeo); goto out; } add_wait_queue(sk_sleep(sk), &wait); done = sk_wait_event(sk, &timeo, atomic_read(&pn->tx_credits), &wait); remove_wait_queue(sk_sleep(sk), &wait); if (sk->sk_state != TCP_ESTABLISHED) goto disabled; } err = pipe_skb_send(sk, skb); if (err >= 0) err = len; /* success! */ skb = NULL; out: release_sock(sk); outfree: kfree_skb(skb); return err; } int pep_writeable(struct sock *sk) { struct pep_sock *pn = pep_sk(sk); return atomic_read(&pn->tx_credits); } int pep_write(struct sock *sk, struct sk_buff *skb) { struct sk_buff *rskb, *fs; int flen = 0; if (pep_sk(sk)->aligned) return pipe_skb_send(sk, skb); rskb = alloc_skb(MAX_PNPIPE_HEADER, GFP_ATOMIC); if (!rskb) { kfree_skb(skb); return -ENOMEM; } skb_shinfo(rskb)->frag_list = skb; rskb->len += skb->len; rskb->data_len += rskb->len; rskb->truesize += rskb->len; /* Avoid nested fragments */ skb_walk_frags(skb, fs) flen += fs->len; skb->next = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); skb->len -= flen; skb->data_len -= flen; skb->truesize -= flen; skb_reserve(rskb, MAX_PHONET_HEADER + 3); return pipe_skb_send(sk, rskb); } struct sk_buff *pep_read(struct sock *sk) { struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue); if (sk->sk_state == TCP_ESTABLISHED) pipe_grant_credits(sk, GFP_ATOMIC); return skb; } static int pep_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct sk_buff *skb; int err; if (flags & ~(MSG_OOB|MSG_PEEK|MSG_TRUNC|MSG_DONTWAIT|MSG_WAITALL| MSG_NOSIGNAL|MSG_CMSG_COMPAT)) return -EOPNOTSUPP; if (unlikely(1 << sk->sk_state & (TCPF_LISTEN | TCPF_CLOSE))) return -ENOTCONN; if ((flags & MSG_OOB) || sock_flag(sk, SOCK_URGINLINE)) { /* Dequeue and acknowledge control request */ struct pep_sock *pn = pep_sk(sk); if (flags & MSG_PEEK) return -EOPNOTSUPP; skb = skb_dequeue(&pn->ctrlreq_queue); if (skb) { pep_ctrlreq_error(sk, skb, PN_PIPE_NO_ERROR, GFP_KERNEL); msg->msg_flags |= MSG_OOB; goto copy; } if (flags & MSG_OOB) return -EINVAL; } skb = skb_recv_datagram(sk, flags, &err); lock_sock(sk); if (skb == NULL) { if (err == -ENOTCONN && sk->sk_state == TCP_CLOSE_WAIT) err = -ECONNRESET; release_sock(sk); return err; } if (sk->sk_state == TCP_ESTABLISHED) pipe_grant_credits(sk, GFP_KERNEL); release_sock(sk); copy: msg->msg_flags |= MSG_EOR; if (skb->len > len) msg->msg_flags |= MSG_TRUNC; else len = skb->len; err = skb_copy_datagram_msg(skb, 0, msg, len); if (!err) err = (flags & MSG_TRUNC) ? skb->len : len; skb_free_datagram(sk, skb); return err; } static void pep_sock_unhash(struct sock *sk) { struct pep_sock *pn = pep_sk(sk); struct sock *skparent = NULL; lock_sock(sk); if (pn->listener != NULL) { skparent = pn->listener; pn->listener = NULL; release_sock(sk); pn = pep_sk(skparent); lock_sock(skparent); sk_del_node_init(sk); sk = skparent; } /* Unhash a listening sock only when it is closed * and all of its active connected pipes are closed. */ if (hlist_empty(&pn->hlist)) pn_sock_unhash(&pn->pn_sk.sk); release_sock(sk); if (skparent) sock_put(skparent); } static struct proto pep_proto = { .close = pep_sock_close, .accept = pep_sock_accept, .connect = pep_sock_connect, .ioctl = pep_ioctl, .init = pep_init, .setsockopt = pep_setsockopt, .getsockopt = pep_getsockopt, .sendmsg = pep_sendmsg, .recvmsg = pep_recvmsg, .backlog_rcv = pep_do_rcv, .hash = pn_sock_hash, .unhash = pep_sock_unhash, .get_port = pn_sock_get_port, .obj_size = sizeof(struct pep_sock), .owner = THIS_MODULE, .name = "PNPIPE", }; static const struct phonet_protocol pep_pn_proto = { .ops = &phonet_stream_ops, .prot = &pep_proto, .sock_type = SOCK_SEQPACKET, }; static int __init pep_register(void) { return phonet_proto_register(PN_PROTO_PIPE, &pep_pn_proto); } static void __exit pep_unregister(void) { phonet_proto_unregister(PN_PROTO_PIPE, &pep_pn_proto); } module_init(pep_register); module_exit(pep_unregister); MODULE_AUTHOR("Remi Denis-Courmont, Nokia"); MODULE_DESCRIPTION("Phonet pipe protocol"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NET_PF_PROTO(PF_PHONET, PN_PROTO_PIPE); |
| 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 | // SPDX-License-Identifier: GPL-2.0-only /* * File: pep-gprs.c * * GPRS over Phonet pipe end point socket * * Copyright (C) 2008 Nokia Corporation. * * Author: Rémi Denis-Courmont */ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_ether.h> #include <linux/if_arp.h> #include <net/sock.h> #include <linux/if_phonet.h> #include <net/tcp_states.h> #include <net/phonet/gprs.h> #include <trace/events/sock.h> #define GPRS_DEFAULT_MTU 1400 struct gprs_dev { struct sock *sk; void (*old_state_change)(struct sock *); void (*old_data_ready)(struct sock *); void (*old_write_space)(struct sock *); struct net_device *dev; }; static __be16 gprs_type_trans(struct sk_buff *skb) { const u8 *pvfc; u8 buf; pvfc = skb_header_pointer(skb, 0, 1, &buf); if (!pvfc) return htons(0); /* Look at IP version field */ switch (*pvfc >> 4) { case 4: return htons(ETH_P_IP); case 6: return htons(ETH_P_IPV6); } return htons(0); } static void gprs_writeable(struct gprs_dev *gp) { struct net_device *dev = gp->dev; if (pep_writeable(gp->sk)) netif_wake_queue(dev); } /* * Socket callbacks */ static void gprs_state_change(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; if (sk->sk_state == TCP_CLOSE_WAIT) { struct net_device *dev = gp->dev; netif_stop_queue(dev); netif_carrier_off(dev); } } static int gprs_recv(struct gprs_dev *gp, struct sk_buff *skb) { struct net_device *dev = gp->dev; int err = 0; __be16 protocol = gprs_type_trans(skb); if (!protocol) { err = -EINVAL; goto drop; } if (skb_headroom(skb) & 3) { struct sk_buff *rskb, *fs; int flen = 0; /* Phonet Pipe data header may be misaligned (3 bytes), * so wrap the IP packet as a single fragment of an head-less * socket buffer. The network stack will pull what it needs, * but at least, the whole IP payload is not memcpy'd. */ rskb = netdev_alloc_skb(dev, 0); if (!rskb) { err = -ENOBUFS; goto drop; } skb_shinfo(rskb)->frag_list = skb; rskb->len += skb->len; rskb->data_len += rskb->len; rskb->truesize += rskb->len; /* Avoid nested fragments */ skb_walk_frags(skb, fs) flen += fs->len; skb->next = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); skb->len -= flen; skb->data_len -= flen; skb->truesize -= flen; skb = rskb; } skb->protocol = protocol; skb_reset_mac_header(skb); skb->dev = dev; if (likely(dev->flags & IFF_UP)) { dev->stats.rx_packets++; dev->stats.rx_bytes += skb->len; netif_rx(skb); skb = NULL; } else err = -ENODEV; drop: if (skb) { dev_kfree_skb(skb); dev->stats.rx_dropped++; } return err; } static void gprs_data_ready(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; struct sk_buff *skb; trace_sk_data_ready(sk); while ((skb = pep_read(sk)) != NULL) { skb_orphan(skb); gprs_recv(gp, skb); } } static void gprs_write_space(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; if (netif_running(gp->dev)) gprs_writeable(gp); } /* * Network device callbacks */ static int gprs_open(struct net_device *dev) { struct gprs_dev *gp = netdev_priv(dev); gprs_writeable(gp); return 0; } static int gprs_close(struct net_device *dev) { netif_stop_queue(dev); return 0; } static netdev_tx_t gprs_xmit(struct sk_buff *skb, struct net_device *dev) { struct gprs_dev *gp = netdev_priv(dev); struct sock *sk = gp->sk; int len, err; switch (skb->protocol) { case htons(ETH_P_IP): case htons(ETH_P_IPV6): break; default: dev_kfree_skb(skb); return NETDEV_TX_OK; } skb_orphan(skb); skb_set_owner_w(skb, sk); len = skb->len; err = pep_write(sk, skb); if (err) { net_dbg_ratelimited("%s: TX error (%d)\n", dev->name, err); dev->stats.tx_aborted_errors++; dev->stats.tx_errors++; } else { dev->stats.tx_packets++; dev->stats.tx_bytes += len; } netif_stop_queue(dev); if (pep_writeable(sk)) netif_wake_queue(dev); return NETDEV_TX_OK; } static const struct net_device_ops gprs_netdev_ops = { .ndo_open = gprs_open, .ndo_stop = gprs_close, .ndo_start_xmit = gprs_xmit, }; static void gprs_setup(struct net_device *dev) { dev->features = NETIF_F_FRAGLIST; dev->type = ARPHRD_PHONET_PIPE; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->mtu = GPRS_DEFAULT_MTU; dev->min_mtu = 576; dev->max_mtu = (PHONET_MAX_MTU - 11); dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 10; dev->netdev_ops = &gprs_netdev_ops; dev->needs_free_netdev = true; } /* * External interface */ /* * Attach a GPRS interface to a datagram socket. * Returns the interface index on success, negative error code on error. */ int gprs_attach(struct sock *sk) { static const char ifname[] = "gprs%d"; struct gprs_dev *gp; struct net_device *dev; int err; if (unlikely(sk->sk_type == SOCK_STREAM)) return -EINVAL; /* need packet boundaries */ /* Create net device */ dev = alloc_netdev(sizeof(*gp), ifname, NET_NAME_UNKNOWN, gprs_setup); if (!dev) return -ENOMEM; gp = netdev_priv(dev); gp->sk = sk; gp->dev = dev; netif_stop_queue(dev); err = register_netdev(dev); if (err) { free_netdev(dev); return err; } lock_sock(sk); if (unlikely(sk->sk_user_data)) { err = -EBUSY; goto out_rel; } if (unlikely((1 << sk->sk_state & (TCPF_CLOSE|TCPF_LISTEN)) || sock_flag(sk, SOCK_DEAD))) { err = -EINVAL; goto out_rel; } sk->sk_user_data = gp; gp->old_state_change = sk->sk_state_change; gp->old_data_ready = sk->sk_data_ready; gp->old_write_space = sk->sk_write_space; sk->sk_state_change = gprs_state_change; sk->sk_data_ready = gprs_data_ready; sk->sk_write_space = gprs_write_space; release_sock(sk); sock_hold(sk); printk(KERN_DEBUG"%s: attached\n", dev->name); return dev->ifindex; out_rel: release_sock(sk); unregister_netdev(dev); return err; } void gprs_detach(struct sock *sk) { struct gprs_dev *gp = sk->sk_user_data; struct net_device *dev = gp->dev; lock_sock(sk); sk->sk_user_data = NULL; sk->sk_state_change = gp->old_state_change; sk->sk_data_ready = gp->old_data_ready; sk->sk_write_space = gp->old_write_space; release_sock(sk); printk(KERN_DEBUG"%s: detached\n", dev->name); unregister_netdev(dev); sock_put(sk); } |
| 31 31 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __MAC802154_DRIVER_OPS #define __MAC802154_DRIVER_OPS #include <linux/types.h> #include <linux/rtnetlink.h> #include <net/mac802154.h> #include "ieee802154_i.h" #include "trace.h" static inline int drv_xmit_async(struct ieee802154_local *local, struct sk_buff *skb) { return local->ops->xmit_async(&local->hw, skb); } static inline int drv_xmit_sync(struct ieee802154_local *local, struct sk_buff *skb) { might_sleep(); return local->ops->xmit_sync(&local->hw, skb); } static inline int drv_set_pan_id(struct ieee802154_local *local, __le16 pan_id) { struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); if (!local->ops->set_hw_addr_filt) { WARN_ON(1); return -EOPNOTSUPP; } filt.pan_id = pan_id; trace_802154_drv_set_pan_id(local, pan_id); ret = local->ops->set_hw_addr_filt(&local->hw, &filt, IEEE802154_AFILT_PANID_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_extended_addr(struct ieee802154_local *local, __le64 extended_addr) { struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); if (!local->ops->set_hw_addr_filt) { WARN_ON(1); return -EOPNOTSUPP; } filt.ieee_addr = extended_addr; trace_802154_drv_set_extended_addr(local, extended_addr); ret = local->ops->set_hw_addr_filt(&local->hw, &filt, IEEE802154_AFILT_IEEEADDR_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_short_addr(struct ieee802154_local *local, __le16 short_addr) { struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); if (!local->ops->set_hw_addr_filt) { WARN_ON(1); return -EOPNOTSUPP; } filt.short_addr = short_addr; trace_802154_drv_set_short_addr(local, short_addr); ret = local->ops->set_hw_addr_filt(&local->hw, &filt, IEEE802154_AFILT_SADDR_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_pan_coord(struct ieee802154_local *local, bool is_coord) { struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); if (!local->ops->set_hw_addr_filt) { WARN_ON(1); return -EOPNOTSUPP; } filt.pan_coord = is_coord; trace_802154_drv_set_pan_coord(local, is_coord); ret = local->ops->set_hw_addr_filt(&local->hw, &filt, IEEE802154_AFILT_PANC_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_promiscuous_mode(struct ieee802154_local *local, bool on) { int ret; might_sleep(); if (!local->ops->set_promiscuous_mode) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_promiscuous_mode(local, on); ret = local->ops->set_promiscuous_mode(&local->hw, on); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_start(struct ieee802154_local *local, enum ieee802154_filtering_level level, const struct ieee802154_hw_addr_filt *addr_filt) { int ret; might_sleep(); /* setup receive mode parameters e.g. address mode */ if (local->hw.flags & IEEE802154_HW_AFILT) { ret = drv_set_pan_id(local, addr_filt->pan_id); if (ret < 0) return ret; ret = drv_set_short_addr(local, addr_filt->short_addr); if (ret < 0) return ret; ret = drv_set_extended_addr(local, addr_filt->ieee_addr); if (ret < 0) return ret; } switch (level) { case IEEE802154_FILTERING_NONE: fallthrough; case IEEE802154_FILTERING_1_FCS: fallthrough; case IEEE802154_FILTERING_2_PROMISCUOUS: /* TODO: Requires a different receive mode setup e.g. * at86rf233 hardware. */ fallthrough; case IEEE802154_FILTERING_3_SCAN: if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { ret = drv_set_promiscuous_mode(local, true); if (ret < 0) return ret; } else { return -EOPNOTSUPP; } /* In practice other filtering levels can be requested, but as * for now most hardware/drivers only support * IEEE802154_FILTERING_NONE, we fallback to this actual * filtering level in hardware and make our own additional * filtering in mac802154 receive path. * * TODO: Move this logic to the device drivers as hardware may * support more higher level filters. Hardware may also require * a different order how register are set, which could currently * be buggy, so all received parameters need to be moved to the * start() callback and let the driver go into the mode before * it will turn on receive handling. */ local->phy->filtering = IEEE802154_FILTERING_NONE; break; case IEEE802154_FILTERING_4_FRAME_FIELDS: /* Do not error out if IEEE802154_HW_PROMISCUOUS because we * expect the hardware to operate at the level * IEEE802154_FILTERING_4_FRAME_FIELDS anyway. */ if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { ret = drv_set_promiscuous_mode(local, false); if (ret < 0) return ret; } local->phy->filtering = IEEE802154_FILTERING_4_FRAME_FIELDS; break; default: WARN_ON(1); return -EINVAL; } trace_802154_drv_start(local); local->started = true; smp_mb(); ret = local->ops->start(&local->hw); trace_802154_drv_return_int(local, ret); return ret; } static inline void drv_stop(struct ieee802154_local *local) { might_sleep(); trace_802154_drv_stop(local); local->ops->stop(&local->hw); trace_802154_drv_return_void(local); /* sync away all work on the tasklet before clearing started */ tasklet_disable(&local->tasklet); tasklet_enable(&local->tasklet); barrier(); local->started = false; } static inline int drv_set_channel(struct ieee802154_local *local, u8 page, u8 channel) { int ret; might_sleep(); trace_802154_drv_set_channel(local, page, channel); ret = local->ops->set_channel(&local->hw, page, channel); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_tx_power(struct ieee802154_local *local, s32 mbm) { int ret; might_sleep(); if (!local->ops->set_txpower) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_tx_power(local, mbm); ret = local->ops->set_txpower(&local->hw, mbm); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_cca_mode(struct ieee802154_local *local, const struct wpan_phy_cca *cca) { int ret; might_sleep(); if (!local->ops->set_cca_mode) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_cca_mode(local, cca); ret = local->ops->set_cca_mode(&local->hw, cca); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_lbt_mode(struct ieee802154_local *local, bool mode) { int ret; might_sleep(); if (!local->ops->set_lbt) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_lbt_mode(local, mode); ret = local->ops->set_lbt(&local->hw, mode); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_cca_ed_level(struct ieee802154_local *local, s32 mbm) { int ret; might_sleep(); if (!local->ops->set_cca_ed_level) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_cca_ed_level(local, mbm); ret = local->ops->set_cca_ed_level(&local->hw, mbm); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_csma_params(struct ieee802154_local *local, u8 min_be, u8 max_be, u8 max_csma_backoffs) { int ret; might_sleep(); if (!local->ops->set_csma_params) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_csma_params(local, min_be, max_be, max_csma_backoffs); ret = local->ops->set_csma_params(&local->hw, min_be, max_be, max_csma_backoffs); trace_802154_drv_return_int(local, ret); return ret; } static inline int drv_set_max_frame_retries(struct ieee802154_local *local, s8 max_frame_retries) { int ret; might_sleep(); if (!local->ops->set_frame_retries) { WARN_ON(1); return -EOPNOTSUPP; } trace_802154_drv_set_max_frame_retries(local, max_frame_retries); ret = local->ops->set_frame_retries(&local->hw, max_frame_retries); trace_802154_drv_return_int(local, ret); return ret; } #endif /* __MAC802154_DRIVER_OPS */ |
| 188 8 188 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TTY_FLIP_H #define _LINUX_TTY_FLIP_H #include <linux/tty_buffer.h> #include <linux/tty_port.h> struct tty_ldisc; int tty_buffer_set_limit(struct tty_port *port, int limit); unsigned int tty_buffer_space_avail(struct tty_port *port); int tty_buffer_request_room(struct tty_port *port, size_t size); size_t __tty_insert_flip_string_flags(struct tty_port *port, const u8 *chars, const u8 *flags, bool mutable_flags, size_t size); size_t tty_prepare_flip_string(struct tty_port *port, u8 **chars, size_t size); void tty_flip_buffer_push(struct tty_port *port); /** * tty_insert_flip_string_fixed_flag - add characters to the tty buffer * @port: tty port * @chars: characters * @flag: flag value for each character * @size: size * * Queue a series of bytes to the tty buffering. All the characters passed are * marked with the supplied flag. * * Returns: the number added. */ static inline size_t tty_insert_flip_string_fixed_flag(struct tty_port *port, const u8 *chars, u8 flag, size_t size) { return __tty_insert_flip_string_flags(port, chars, &flag, false, size); } /** * tty_insert_flip_string_flags - add characters to the tty buffer * @port: tty port * @chars: characters * @flags: flag bytes * @size: size * * Queue a series of bytes to the tty buffering. For each character the flags * array indicates the status of the character. * * Returns: the number added. */ static inline size_t tty_insert_flip_string_flags(struct tty_port *port, const u8 *chars, const u8 *flags, size_t size) { return __tty_insert_flip_string_flags(port, chars, flags, true, size); } /** * tty_insert_flip_char - add one character to the tty buffer * @port: tty port * @ch: character * @flag: flag byte * * Queue a single byte @ch to the tty buffering, with an optional flag. */ static inline size_t tty_insert_flip_char(struct tty_port *port, u8 ch, u8 flag) { struct tty_buffer *tb = port->buf.tail; int change; change = !tb->flags && (flag != TTY_NORMAL); if (!change && tb->used < tb->size) { if (tb->flags) *flag_buf_ptr(tb, tb->used) = flag; *char_buf_ptr(tb, tb->used++) = ch; return 1; } return __tty_insert_flip_string_flags(port, &ch, &flag, false, 1); } static inline size_t tty_insert_flip_string(struct tty_port *port, const u8 *chars, size_t size) { return tty_insert_flip_string_fixed_flag(port, chars, TTY_NORMAL, size); } size_t tty_ldisc_receive_buf(struct tty_ldisc *ld, const u8 *p, const u8 *f, size_t count); void tty_buffer_lock_exclusive(struct tty_port *port); void tty_buffer_unlock_exclusive(struct tty_port *port); #endif /* _LINUX_TTY_FLIP_H */ |
| 21 1 1 18 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | // SPDX-License-Identifier: GPL-2.0-only /* iptables module for the IPv4 and TCP ECN bits, Version 1.5 * * (C) 2002 by Harald Welte <laforge@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <net/ip.h> #include <linux/tcp.h> #include <net/checksum.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ipt_ECN.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: Explicit Congestion Notification (ECN) flag modification"); /* set ECT codepoint from IP header. * return false if there was an error. */ static inline bool set_ect_ip(struct sk_buff *skb, const struct ipt_ECN_info *einfo) { struct iphdr *iph = ip_hdr(skb); if ((iph->tos & IPT_ECN_IP_MASK) != (einfo->ip_ect & IPT_ECN_IP_MASK)) { __u8 oldtos; if (skb_ensure_writable(skb, sizeof(struct iphdr))) return false; iph = ip_hdr(skb); oldtos = iph->tos; iph->tos &= ~IPT_ECN_IP_MASK; iph->tos |= (einfo->ip_ect & IPT_ECN_IP_MASK); csum_replace2(&iph->check, htons(oldtos), htons(iph->tos)); } return true; } /* Return false if there was an error. */ static inline bool set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo) { struct tcphdr _tcph, *tcph; __be16 oldval; /* Not enough header? */ tcph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph); if (!tcph) return false; if ((!(einfo->operation & IPT_ECN_OP_SET_ECE) || tcph->ece == einfo->proto.tcp.ece) && (!(einfo->operation & IPT_ECN_OP_SET_CWR) || tcph->cwr == einfo->proto.tcp.cwr)) return true; if (skb_ensure_writable(skb, ip_hdrlen(skb) + sizeof(*tcph))) return false; tcph = (void *)ip_hdr(skb) + ip_hdrlen(skb); oldval = ((__be16 *)tcph)[6]; if (einfo->operation & IPT_ECN_OP_SET_ECE) tcph->ece = einfo->proto.tcp.ece; if (einfo->operation & IPT_ECN_OP_SET_CWR) tcph->cwr = einfo->proto.tcp.cwr; inet_proto_csum_replace2(&tcph->check, skb, oldval, ((__be16 *)tcph)[6], false); return true; } static unsigned int ecn_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipt_ECN_info *einfo = par->targinfo; if (einfo->operation & IPT_ECN_OP_SET_IP) if (!set_ect_ip(skb, einfo)) return NF_DROP; if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) && ip_hdr(skb)->protocol == IPPROTO_TCP) if (!set_ect_tcp(skb, einfo)) return NF_DROP; return XT_CONTINUE; } static int ecn_tg_check(const struct xt_tgchk_param *par) { const struct ipt_ECN_info *einfo = par->targinfo; const struct ipt_entry *e = par->entryinfo; if (einfo->operation & IPT_ECN_OP_MASK) return -EINVAL; if (einfo->ip_ect & ~IPT_ECN_IP_MASK) return -EINVAL; if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) && (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { pr_info_ratelimited("cannot use operation on non-tcp rule\n"); return -EINVAL; } return 0; } static struct xt_target ecn_tg_reg __read_mostly = { .name = "ECN", .family = NFPROTO_IPV4, .target = ecn_tg, .targetsize = sizeof(struct ipt_ECN_info), .table = "mangle", .checkentry = ecn_tg_check, .me = THIS_MODULE, }; static int __init ecn_tg_init(void) { return xt_register_target(&ecn_tg_reg); } static void __exit ecn_tg_exit(void) { xt_unregister_target(&ecn_tg_reg); } module_init(ecn_tg_init); module_exit(ecn_tg_exit); |
| 69 69 117 167 96 16 94 82 20 13 1 15 7 5 9 5 6 5 1 6 7 2 1 64 6 96 23 7 7 87 72 29 29 68 70 15 59 70 70 70 52 142 3 3 3 147 9 142 146 141 12 146 9 142 142 3 7 139 141 117 147 52 13 2 34 13 36 36 36 30 16 22 2 33 29 29 1 27 2 28 2 2 25 29 3 1 2 2 169 169 169 159 14 6 10 2 10 5 2 3 169 17 11 6 6 6 1 6 13 3 27 16 165 3 4 3 6 3 3 3 3 13 13 6 17 4 4 4 4 4 4 4 3 23 1 21 15 87 9 78 87 76 76 38 4 34 34 2 1 1 9 2 1 1 2 2 2 1 2 9 9 1 17 9 5 5 5 5 9 4 1 1 4 1 4 1 1 1 28 3 3 4 7 20 7 20 1 1 12 12 12 1 1 2 1 19 1 1 16 11 5 10 6 9 7 7 9 9 3 2 1 2 3 1 2 19 2 17 17 1 2 3 11 3 2 5 1 1 6 149 37 14 8 26 5 5 31 14 23 3 3 3 17 7 151 151 15 31 8 18 15 13 4 6 9 11 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Timers abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/delay.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/mutex.h> #include <linux/device.h> #include <linux/module.h> #include <linux/string.h> #include <linux/sched/signal.h> #include <linux/anon_inodes.h> #include <linux/idr.h> #include <sound/core.h> #include <sound/timer.h> #include <sound/control.h> #include <sound/info.h> #include <sound/minors.h> #include <sound/initval.h> #include <linux/kmod.h> /* internal flags */ #define SNDRV_TIMER_IFLG_PAUSED 0x00010000 #define SNDRV_TIMER_IFLG_DEAD 0x00020000 #if IS_ENABLED(CONFIG_SND_HRTIMER) #define DEFAULT_TIMER_LIMIT 4 #else #define DEFAULT_TIMER_LIMIT 1 #endif static int timer_limit = DEFAULT_TIMER_LIMIT; static int timer_tstamp_monotonic = 1; MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, Takashi Iwai <tiwai@suse.de>"); MODULE_DESCRIPTION("ALSA timer interface"); MODULE_LICENSE("GPL"); module_param(timer_limit, int, 0444); MODULE_PARM_DESC(timer_limit, "Maximum global timers in system."); module_param(timer_tstamp_monotonic, int, 0444); MODULE_PARM_DESC(timer_tstamp_monotonic, "Use posix monotonic clock source for timestamps (default)."); MODULE_ALIAS_CHARDEV(CONFIG_SND_MAJOR, SNDRV_MINOR_TIMER); MODULE_ALIAS("devname:snd/timer"); enum timer_tread_format { TREAD_FORMAT_NONE = 0, TREAD_FORMAT_TIME64, TREAD_FORMAT_TIME32, }; struct snd_timer_tread32 { int event; s32 tstamp_sec; s32 tstamp_nsec; unsigned int val; }; struct snd_timer_tread64 { int event; u8 pad1[4]; s64 tstamp_sec; s64 tstamp_nsec; unsigned int val; u8 pad2[4]; }; struct snd_timer_user { struct snd_timer_instance *timeri; int tread; /* enhanced read with timestamps and events */ unsigned long ticks; unsigned long overrun; int qhead; int qtail; int qused; int queue_size; bool disconnected; struct snd_timer_read *queue; struct snd_timer_tread64 *tqueue; spinlock_t qlock; unsigned long last_resolution; unsigned int filter; struct timespec64 tstamp; /* trigger tstamp */ wait_queue_head_t qchange_sleep; struct snd_fasync *fasync; struct mutex ioctl_lock; }; struct snd_timer_status32 { s32 tstamp_sec; /* Timestamp - last update */ s32 tstamp_nsec; unsigned int resolution; /* current period resolution in ns */ unsigned int lost; /* counter of master tick lost */ unsigned int overrun; /* count of read queue overruns */ unsigned int queue; /* used queue size */ unsigned char reserved[64]; /* reserved */ }; #define SNDRV_TIMER_IOCTL_STATUS32 _IOR('T', 0x14, struct snd_timer_status32) struct snd_timer_status64 { s64 tstamp_sec; /* Timestamp - last update */ s64 tstamp_nsec; unsigned int resolution; /* current period resolution in ns */ unsigned int lost; /* counter of master tick lost */ unsigned int overrun; /* count of read queue overruns */ unsigned int queue; /* used queue size */ unsigned char reserved[64]; /* reserved */ }; #ifdef CONFIG_SND_UTIMER #define SNDRV_UTIMERS_MAX_COUNT 128 /* Internal data structure for keeping the state of the userspace-driven timer */ struct snd_utimer { char *name; struct snd_timer *timer; unsigned int id; }; #endif #define SNDRV_TIMER_IOCTL_STATUS64 _IOR('T', 0x14, struct snd_timer_status64) /* list of timers */ static LIST_HEAD(snd_timer_list); /* list of slave instances */ static LIST_HEAD(snd_timer_slave_list); /* lock for slave active lists */ static DEFINE_SPINLOCK(slave_active_lock); #define MAX_SLAVE_INSTANCES 1000 static int num_slaves; static DEFINE_MUTEX(register_mutex); static int snd_timer_free(struct snd_timer *timer); static int snd_timer_dev_free(struct snd_device *device); static int snd_timer_dev_register(struct snd_device *device); static int snd_timer_dev_disconnect(struct snd_device *device); static void snd_timer_reschedule(struct snd_timer * timer, unsigned long ticks_left); /* * create a timer instance with the given owner string. */ struct snd_timer_instance *snd_timer_instance_new(const char *owner) { struct snd_timer_instance *timeri; timeri = kzalloc(sizeof(*timeri), GFP_KERNEL); if (timeri == NULL) return NULL; timeri->owner = kstrdup(owner, GFP_KERNEL); if (! timeri->owner) { kfree(timeri); return NULL; } INIT_LIST_HEAD(&timeri->open_list); INIT_LIST_HEAD(&timeri->active_list); INIT_LIST_HEAD(&timeri->ack_list); INIT_LIST_HEAD(&timeri->slave_list_head); INIT_LIST_HEAD(&timeri->slave_active_head); return timeri; } EXPORT_SYMBOL(snd_timer_instance_new); void snd_timer_instance_free(struct snd_timer_instance *timeri) { if (timeri) { if (timeri->private_free) timeri->private_free(timeri); kfree(timeri->owner); kfree(timeri); } } EXPORT_SYMBOL(snd_timer_instance_free); /* * find a timer instance from the given timer id */ static struct snd_timer *snd_timer_find(struct snd_timer_id *tid) { struct snd_timer *timer; list_for_each_entry(timer, &snd_timer_list, device_list) { if (timer->tmr_class != tid->dev_class) continue; if ((timer->tmr_class == SNDRV_TIMER_CLASS_CARD || timer->tmr_class == SNDRV_TIMER_CLASS_PCM) && (timer->card == NULL || timer->card->number != tid->card)) continue; if (timer->tmr_device != tid->device) continue; if (timer->tmr_subdevice != tid->subdevice) continue; return timer; } return NULL; } #ifdef CONFIG_MODULES static void snd_timer_request(struct snd_timer_id *tid) { switch (tid->dev_class) { case SNDRV_TIMER_CLASS_GLOBAL: if (tid->device < timer_limit) request_module("snd-timer-%i", tid->device); break; case SNDRV_TIMER_CLASS_CARD: case SNDRV_TIMER_CLASS_PCM: if (tid->card < snd_ecards_limit) request_module("snd-card-%i", tid->card); break; default: break; } } #endif /* move the slave if it belongs to the master; return 1 if match */ static int check_matching_master_slave(struct snd_timer_instance *master, struct snd_timer_instance *slave) { if (slave->slave_class != master->slave_class || slave->slave_id != master->slave_id) return 0; if (master->timer->num_instances >= master->timer->max_instances) return -EBUSY; list_move_tail(&slave->open_list, &master->slave_list_head); master->timer->num_instances++; guard(spinlock_irq)(&slave_active_lock); guard(spinlock)(&master->timer->lock); slave->master = master; slave->timer = master->timer; if (slave->flags & SNDRV_TIMER_IFLG_RUNNING) list_add_tail(&slave->active_list, &master->slave_active_head); return 1; } /* * look for a master instance matching with the slave id of the given slave. * when found, relink the open_link of the slave. * * call this with register_mutex down. */ static int snd_timer_check_slave(struct snd_timer_instance *slave) { struct snd_timer *timer; struct snd_timer_instance *master; int err = 0; /* FIXME: it's really dumb to look up all entries.. */ list_for_each_entry(timer, &snd_timer_list, device_list) { list_for_each_entry(master, &timer->open_list_head, open_list) { err = check_matching_master_slave(master, slave); if (err != 0) /* match found or error */ goto out; } } out: return err < 0 ? err : 0; } /* * look for slave instances matching with the slave id of the given master. * when found, relink the open_link of slaves. * * call this with register_mutex down. */ static int snd_timer_check_master(struct snd_timer_instance *master) { struct snd_timer_instance *slave, *tmp; int err = 0; /* check all pending slaves */ list_for_each_entry_safe(slave, tmp, &snd_timer_slave_list, open_list) { err = check_matching_master_slave(master, slave); if (err < 0) break; } return err < 0 ? err : 0; } static void snd_timer_close_locked(struct snd_timer_instance *timeri, struct device **card_devp_to_put); /* * open a timer instance * when opening a master, the slave id must be here given. */ int snd_timer_open(struct snd_timer_instance *timeri, struct snd_timer_id *tid, unsigned int slave_id) { struct snd_timer *timer; struct device *card_dev_to_put = NULL; int err; mutex_lock(®ister_mutex); if (tid->dev_class == SNDRV_TIMER_CLASS_SLAVE) { /* open a slave instance */ if (tid->dev_sclass <= SNDRV_TIMER_SCLASS_NONE || tid->dev_sclass > SNDRV_TIMER_SCLASS_OSS_SEQUENCER) { pr_debug("ALSA: timer: invalid slave class %i\n", tid->dev_sclass); err = -EINVAL; goto unlock; } if (num_slaves >= MAX_SLAVE_INSTANCES) { err = -EBUSY; goto unlock; } timeri->slave_class = tid->dev_sclass; timeri->slave_id = tid->device; timeri->flags |= SNDRV_TIMER_IFLG_SLAVE; list_add_tail(&timeri->open_list, &snd_timer_slave_list); num_slaves++; err = snd_timer_check_slave(timeri); goto list_added; } /* open a master instance */ timer = snd_timer_find(tid); #ifdef CONFIG_MODULES if (!timer) { mutex_unlock(®ister_mutex); snd_timer_request(tid); mutex_lock(®ister_mutex); timer = snd_timer_find(tid); } #endif if (!timer) { err = -ENODEV; goto unlock; } if (!list_empty(&timer->open_list_head)) { struct snd_timer_instance *t = list_entry(timer->open_list_head.next, struct snd_timer_instance, open_list); if (t->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) { err = -EBUSY; goto unlock; } } if (timer->num_instances >= timer->max_instances) { err = -EBUSY; goto unlock; } if (!try_module_get(timer->module)) { err = -EBUSY; goto unlock; } /* take a card refcount for safe disconnection */ if (timer->card) { get_device(&timer->card->card_dev); card_dev_to_put = &timer->card->card_dev; } if (list_empty(&timer->open_list_head) && timer->hw.open) { err = timer->hw.open(timer); if (err) { module_put(timer->module); goto unlock; } } timeri->timer = timer; timeri->slave_class = tid->dev_sclass; timeri->slave_id = slave_id; list_add_tail(&timeri->open_list, &timer->open_list_head); timer->num_instances++; err = snd_timer_check_master(timeri); list_added: if (err < 0) snd_timer_close_locked(timeri, &card_dev_to_put); unlock: mutex_unlock(®ister_mutex); /* put_device() is called after unlock for avoiding deadlock */ if (err < 0 && card_dev_to_put) put_device(card_dev_to_put); return err; } EXPORT_SYMBOL(snd_timer_open); /* remove slave links, called from snd_timer_close_locked() below */ static void remove_slave_links(struct snd_timer_instance *timeri, struct snd_timer *timer) { struct snd_timer_instance *slave, *tmp; guard(spinlock_irq)(&slave_active_lock); guard(spinlock)(&timer->lock); timeri->timer = NULL; list_for_each_entry_safe(slave, tmp, &timeri->slave_list_head, open_list) { list_move_tail(&slave->open_list, &snd_timer_slave_list); timer->num_instances--; slave->master = NULL; slave->timer = NULL; list_del_init(&slave->ack_list); list_del_init(&slave->active_list); } } /* * close a timer instance * call this with register_mutex down. */ static void snd_timer_close_locked(struct snd_timer_instance *timeri, struct device **card_devp_to_put) { struct snd_timer *timer = timeri->timer; if (timer) { guard(spinlock_irq)(&timer->lock); timeri->flags |= SNDRV_TIMER_IFLG_DEAD; } if (!list_empty(&timeri->open_list)) { list_del_init(&timeri->open_list); if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) num_slaves--; } /* force to stop the timer */ snd_timer_stop(timeri); if (timer) { timer->num_instances--; /* wait, until the active callback is finished */ spin_lock_irq(&timer->lock); while (timeri->flags & SNDRV_TIMER_IFLG_CALLBACK) { spin_unlock_irq(&timer->lock); udelay(10); spin_lock_irq(&timer->lock); } spin_unlock_irq(&timer->lock); remove_slave_links(timeri, timer); /* slave doesn't need to release timer resources below */ if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) timer = NULL; } if (timer) { if (list_empty(&timer->open_list_head) && timer->hw.close) timer->hw.close(timer); /* release a card refcount for safe disconnection */ if (timer->card) *card_devp_to_put = &timer->card->card_dev; module_put(timer->module); } } /* * close a timer instance */ void snd_timer_close(struct snd_timer_instance *timeri) { struct device *card_dev_to_put = NULL; if (snd_BUG_ON(!timeri)) return; scoped_guard(mutex, ®ister_mutex) snd_timer_close_locked(timeri, &card_dev_to_put); /* put_device() is called after unlock for avoiding deadlock */ if (card_dev_to_put) put_device(card_dev_to_put); } EXPORT_SYMBOL(snd_timer_close); static unsigned long snd_timer_hw_resolution(struct snd_timer *timer) { if (timer->hw.c_resolution) return timer->hw.c_resolution(timer); else return timer->hw.resolution; } unsigned long snd_timer_resolution(struct snd_timer_instance *timeri) { struct snd_timer * timer; unsigned long ret = 0; if (timeri == NULL) return 0; timer = timeri->timer; if (timer) { guard(spinlock_irqsave)(&timer->lock); ret = snd_timer_hw_resolution(timer); } return ret; } EXPORT_SYMBOL(snd_timer_resolution); static void snd_timer_notify1(struct snd_timer_instance *ti, int event) { struct snd_timer *timer = ti->timer; unsigned long resolution = 0; struct snd_timer_instance *ts; struct timespec64 tstamp; if (timer_tstamp_monotonic) ktime_get_ts64(&tstamp); else ktime_get_real_ts64(&tstamp); if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_START || event > SNDRV_TIMER_EVENT_PAUSE)) return; if (timer && (event == SNDRV_TIMER_EVENT_START || event == SNDRV_TIMER_EVENT_CONTINUE)) resolution = snd_timer_hw_resolution(timer); if (ti->ccallback) ti->ccallback(ti, event, &tstamp, resolution); if (ti->flags & SNDRV_TIMER_IFLG_SLAVE) return; if (timer == NULL) return; if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) return; event += 10; /* convert to SNDRV_TIMER_EVENT_MXXX */ list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) ts->ccallback(ts, event, &tstamp, resolution); } /* start/continue a master timer */ static int snd_timer_start1(struct snd_timer_instance *timeri, bool start, unsigned long ticks) { struct snd_timer *timer; int result; timer = timeri->timer; if (!timer) return -EINVAL; guard(spinlock_irqsave)(&timer->lock); if (timeri->flags & SNDRV_TIMER_IFLG_DEAD) return -EINVAL; if (timer->card && timer->card->shutdown) return -ENODEV; if (timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START)) return -EBUSY; /* check the actual time for the start tick; * bail out as error if it's way too low (< 100us) */ if (start && !(timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) { if ((u64)snd_timer_hw_resolution(timer) * ticks < 100000) return -EINVAL; } if (start) timeri->ticks = timeri->cticks = ticks; else if (!timeri->cticks) timeri->cticks = 1; timeri->pticks = 0; list_move_tail(&timeri->active_list, &timer->active_list_head); if (timer->running) { if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) goto __start_now; timer->flags |= SNDRV_TIMER_FLG_RESCHED; timeri->flags |= SNDRV_TIMER_IFLG_START; result = 1; /* delayed start */ } else { if (start) timer->sticks = ticks; timer->hw.start(timer); __start_now: timer->running++; timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; result = 0; } snd_timer_notify1(timeri, start ? SNDRV_TIMER_EVENT_START : SNDRV_TIMER_EVENT_CONTINUE); return result; } /* start/continue a slave timer */ static int snd_timer_start_slave(struct snd_timer_instance *timeri, bool start) { guard(spinlock_irqsave)(&slave_active_lock); if (timeri->flags & SNDRV_TIMER_IFLG_DEAD) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_RUNNING) return -EBUSY; timeri->flags |= SNDRV_TIMER_IFLG_RUNNING; if (timeri->master && timeri->timer) { guard(spinlock)(&timeri->timer->lock); list_add_tail(&timeri->active_list, &timeri->master->slave_active_head); snd_timer_notify1(timeri, start ? SNDRV_TIMER_EVENT_START : SNDRV_TIMER_EVENT_CONTINUE); } return 1; /* delayed start */ } /* stop/pause a master timer */ static int snd_timer_stop1(struct snd_timer_instance *timeri, bool stop) { struct snd_timer *timer; timer = timeri->timer; if (!timer) return -EINVAL; guard(spinlock_irqsave)(&timer->lock); list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); if (!(timeri->flags & (SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START))) return -EBUSY; if (timer->card && timer->card->shutdown) return 0; if (stop) { timeri->cticks = timeri->ticks; timeri->pticks = 0; } if ((timeri->flags & SNDRV_TIMER_IFLG_RUNNING) && !(--timer->running)) { timer->hw.stop(timer); if (timer->flags & SNDRV_TIMER_FLG_RESCHED) { timer->flags &= ~SNDRV_TIMER_FLG_RESCHED; snd_timer_reschedule(timer, 0); if (timer->flags & SNDRV_TIMER_FLG_CHANGE) { timer->flags &= ~SNDRV_TIMER_FLG_CHANGE; timer->hw.start(timer); } } } timeri->flags &= ~(SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START); if (stop) timeri->flags &= ~SNDRV_TIMER_IFLG_PAUSED; else timeri->flags |= SNDRV_TIMER_IFLG_PAUSED; snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP : SNDRV_TIMER_EVENT_PAUSE); return 0; } /* stop/pause a slave timer */ static int snd_timer_stop_slave(struct snd_timer_instance *timeri, bool stop) { bool running; guard(spinlock_irqsave)(&slave_active_lock); running = timeri->flags & SNDRV_TIMER_IFLG_RUNNING; timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; if (timeri->timer) { guard(spinlock)(&timeri->timer->lock); list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); if (running) snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP : SNDRV_TIMER_EVENT_PAUSE); } return running ? 0 : -EBUSY; } /* * start the timer instance */ int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks) { if (timeri == NULL || ticks < 1) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_start_slave(timeri, true); else return snd_timer_start1(timeri, true, ticks); } EXPORT_SYMBOL(snd_timer_start); /* * stop the timer instance. * * do not call this from the timer callback! */ int snd_timer_stop(struct snd_timer_instance *timeri) { if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_stop_slave(timeri, true); else return snd_timer_stop1(timeri, true); } EXPORT_SYMBOL(snd_timer_stop); /* * start again.. the tick is kept. */ int snd_timer_continue(struct snd_timer_instance *timeri) { /* timer can continue only after pause */ if (!(timeri->flags & SNDRV_TIMER_IFLG_PAUSED)) return -EINVAL; if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_start_slave(timeri, false); else return snd_timer_start1(timeri, false, 0); } EXPORT_SYMBOL(snd_timer_continue); /* * pause.. remember the ticks left */ int snd_timer_pause(struct snd_timer_instance * timeri) { if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE) return snd_timer_stop_slave(timeri, false); else return snd_timer_stop1(timeri, false); } EXPORT_SYMBOL(snd_timer_pause); /* * reschedule the timer * * start pending instances and check the scheduling ticks. * when the scheduling ticks is changed set CHANGE flag to reprogram the timer. */ static void snd_timer_reschedule(struct snd_timer * timer, unsigned long ticks_left) { struct snd_timer_instance *ti; unsigned long ticks = ~0UL; list_for_each_entry(ti, &timer->active_list_head, active_list) { if (ti->flags & SNDRV_TIMER_IFLG_START) { ti->flags &= ~SNDRV_TIMER_IFLG_START; ti->flags |= SNDRV_TIMER_IFLG_RUNNING; timer->running++; } if (ti->flags & SNDRV_TIMER_IFLG_RUNNING) { if (ticks > ti->cticks) ticks = ti->cticks; } } if (ticks == ~0UL) { timer->flags &= ~SNDRV_TIMER_FLG_RESCHED; return; } if (ticks > timer->hw.ticks) ticks = timer->hw.ticks; if (ticks_left != ticks) timer->flags |= SNDRV_TIMER_FLG_CHANGE; timer->sticks = ticks; } /* call callbacks in timer ack list */ static void snd_timer_process_callbacks(struct snd_timer *timer, struct list_head *head) { struct snd_timer_instance *ti; unsigned long resolution, ticks; while (!list_empty(head)) { ti = list_first_entry(head, struct snd_timer_instance, ack_list); /* remove from ack_list and make empty */ list_del_init(&ti->ack_list); if (!(ti->flags & SNDRV_TIMER_IFLG_DEAD)) { ticks = ti->pticks; ti->pticks = 0; resolution = ti->resolution; ti->flags |= SNDRV_TIMER_IFLG_CALLBACK; spin_unlock(&timer->lock); if (ti->callback) ti->callback(ti, resolution, ticks); spin_lock(&timer->lock); ti->flags &= ~SNDRV_TIMER_IFLG_CALLBACK; } } } /* clear pending instances from ack list */ static void snd_timer_clear_callbacks(struct snd_timer *timer, struct list_head *head) { guard(spinlock_irqsave)(&timer->lock); while (!list_empty(head)) list_del_init(head->next); } /* * timer work * */ static void snd_timer_work(struct work_struct *work) { struct snd_timer *timer = container_of(work, struct snd_timer, task_work); if (timer->card && timer->card->shutdown) { snd_timer_clear_callbacks(timer, &timer->sack_list_head); return; } guard(spinlock_irqsave)(&timer->lock); snd_timer_process_callbacks(timer, &timer->sack_list_head); } /* * timer interrupt * * ticks_left is usually equal to timer->sticks. * */ void snd_timer_interrupt(struct snd_timer * timer, unsigned long ticks_left) { struct snd_timer_instance *ti, *ts, *tmp; unsigned long resolution; struct list_head *ack_list_head; if (timer == NULL) return; if (timer->card && timer->card->shutdown) { snd_timer_clear_callbacks(timer, &timer->ack_list_head); return; } guard(spinlock_irqsave)(&timer->lock); /* remember the current resolution */ resolution = snd_timer_hw_resolution(timer); /* loop for all active instances * Here we cannot use list_for_each_entry because the active_list of a * processed instance is relinked to done_list_head before the callback * is called. */ list_for_each_entry_safe(ti, tmp, &timer->active_list_head, active_list) { if (ti->flags & SNDRV_TIMER_IFLG_DEAD) continue; if (!(ti->flags & SNDRV_TIMER_IFLG_RUNNING)) continue; ti->pticks += ticks_left; ti->resolution = resolution; if (ti->cticks < ticks_left) ti->cticks = 0; else ti->cticks -= ticks_left; if (ti->cticks) /* not expired */ continue; if (ti->flags & SNDRV_TIMER_IFLG_AUTO) { ti->cticks = ti->ticks; } else { ti->flags &= ~SNDRV_TIMER_IFLG_RUNNING; --timer->running; list_del_init(&ti->active_list); } if ((timer->hw.flags & SNDRV_TIMER_HW_WORK) || (ti->flags & SNDRV_TIMER_IFLG_FAST)) ack_list_head = &timer->ack_list_head; else ack_list_head = &timer->sack_list_head; if (list_empty(&ti->ack_list)) list_add_tail(&ti->ack_list, ack_list_head); list_for_each_entry(ts, &ti->slave_active_head, active_list) { ts->pticks = ti->pticks; ts->resolution = resolution; if (list_empty(&ts->ack_list)) list_add_tail(&ts->ack_list, ack_list_head); } } if (timer->flags & SNDRV_TIMER_FLG_RESCHED) snd_timer_reschedule(timer, timer->sticks); if (timer->running) { if (timer->hw.flags & SNDRV_TIMER_HW_STOP) { timer->hw.stop(timer); timer->flags |= SNDRV_TIMER_FLG_CHANGE; } if (!(timer->hw.flags & SNDRV_TIMER_HW_AUTO) || (timer->flags & SNDRV_TIMER_FLG_CHANGE)) { /* restart timer */ timer->flags &= ~SNDRV_TIMER_FLG_CHANGE; timer->hw.start(timer); } } else { timer->hw.stop(timer); } /* now process all fast callbacks */ snd_timer_process_callbacks(timer, &timer->ack_list_head); /* do we have any slow callbacks? */ if (!list_empty(&timer->sack_list_head)) queue_work(system_highpri_wq, &timer->task_work); } EXPORT_SYMBOL(snd_timer_interrupt); /* */ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid, struct snd_timer **rtimer) { struct snd_timer *timer; int err; static const struct snd_device_ops ops = { .dev_free = snd_timer_dev_free, .dev_register = snd_timer_dev_register, .dev_disconnect = snd_timer_dev_disconnect, }; if (snd_BUG_ON(!tid)) return -EINVAL; if (tid->dev_class == SNDRV_TIMER_CLASS_CARD || tid->dev_class == SNDRV_TIMER_CLASS_PCM) { if (WARN_ON(!card)) return -EINVAL; } if (rtimer) *rtimer = NULL; timer = kzalloc(sizeof(*timer), GFP_KERNEL); if (!timer) return -ENOMEM; timer->tmr_class = tid->dev_class; timer->card = card; timer->tmr_device = tid->device; timer->tmr_subdevice = tid->subdevice; if (id) strscpy(timer->id, id, sizeof(timer->id)); timer->sticks = 1; INIT_LIST_HEAD(&timer->device_list); INIT_LIST_HEAD(&timer->open_list_head); INIT_LIST_HEAD(&timer->active_list_head); INIT_LIST_HEAD(&timer->ack_list_head); INIT_LIST_HEAD(&timer->sack_list_head); spin_lock_init(&timer->lock); INIT_WORK(&timer->task_work, snd_timer_work); timer->max_instances = 1000; /* default limit per timer */ if (card != NULL) { timer->module = card->module; err = snd_device_new(card, SNDRV_DEV_TIMER, timer, &ops); if (err < 0) { snd_timer_free(timer); return err; } } if (rtimer) *rtimer = timer; return 0; } EXPORT_SYMBOL(snd_timer_new); static int snd_timer_free(struct snd_timer *timer) { if (!timer) return 0; guard(mutex)(®ister_mutex); if (! list_empty(&timer->open_list_head)) { struct list_head *p, *n; struct snd_timer_instance *ti; pr_warn("ALSA: timer %p is busy?\n", timer); list_for_each_safe(p, n, &timer->open_list_head) { list_del_init(p); ti = list_entry(p, struct snd_timer_instance, open_list); ti->timer = NULL; } } list_del(&timer->device_list); if (timer->private_free) timer->private_free(timer); kfree(timer); return 0; } static int snd_timer_dev_free(struct snd_device *device) { struct snd_timer *timer = device->device_data; return snd_timer_free(timer); } static int snd_timer_dev_register(struct snd_device *dev) { struct snd_timer *timer = dev->device_data; struct snd_timer *timer1; if (snd_BUG_ON(!timer || !timer->hw.start || !timer->hw.stop)) return -ENXIO; if (!(timer->hw.flags & SNDRV_TIMER_HW_SLAVE) && !timer->hw.resolution && timer->hw.c_resolution == NULL) return -EINVAL; guard(mutex)(®ister_mutex); list_for_each_entry(timer1, &snd_timer_list, device_list) { if (timer1->tmr_class > timer->tmr_class) break; if (timer1->tmr_class < timer->tmr_class) continue; if (timer1->card && timer->card) { if (timer1->card->number > timer->card->number) break; if (timer1->card->number < timer->card->number) continue; } if (timer1->tmr_device > timer->tmr_device) break; if (timer1->tmr_device < timer->tmr_device) continue; if (timer1->tmr_subdevice > timer->tmr_subdevice) break; if (timer1->tmr_subdevice < timer->tmr_subdevice) continue; /* conflicts.. */ return -EBUSY; } list_add_tail(&timer->device_list, &timer1->device_list); return 0; } static int snd_timer_dev_disconnect(struct snd_device *device) { struct snd_timer *timer = device->device_data; struct snd_timer_instance *ti; guard(mutex)(®ister_mutex); list_del_init(&timer->device_list); /* wake up pending sleepers */ list_for_each_entry(ti, &timer->open_list_head, open_list) { if (ti->disconnect) ti->disconnect(ti); } return 0; } void snd_timer_notify(struct snd_timer *timer, int event, struct timespec64 *tstamp) { unsigned long resolution = 0; struct snd_timer_instance *ti, *ts; if (timer->card && timer->card->shutdown) return; if (! (timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) return; if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_MSTART || event > SNDRV_TIMER_EVENT_MRESUME)) return; guard(spinlock_irqsave)(&timer->lock); if (event == SNDRV_TIMER_EVENT_MSTART || event == SNDRV_TIMER_EVENT_MCONTINUE || event == SNDRV_TIMER_EVENT_MRESUME) resolution = snd_timer_hw_resolution(timer); list_for_each_entry(ti, &timer->active_list_head, active_list) { if (ti->ccallback) ti->ccallback(ti, event, tstamp, resolution); list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) ts->ccallback(ts, event, tstamp, resolution); } } EXPORT_SYMBOL(snd_timer_notify); /* * exported functions for global timers */ int snd_timer_global_new(char *id, int device, struct snd_timer **rtimer) { struct snd_timer_id tid; tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL; tid.dev_sclass = SNDRV_TIMER_SCLASS_NONE; tid.card = -1; tid.device = device; tid.subdevice = 0; return snd_timer_new(NULL, id, &tid, rtimer); } EXPORT_SYMBOL(snd_timer_global_new); int snd_timer_global_free(struct snd_timer *timer) { return snd_timer_free(timer); } EXPORT_SYMBOL(snd_timer_global_free); int snd_timer_global_register(struct snd_timer *timer) { struct snd_device dev; memset(&dev, 0, sizeof(dev)); dev.device_data = timer; return snd_timer_dev_register(&dev); } EXPORT_SYMBOL(snd_timer_global_register); /* * System timer */ struct snd_timer_system_private { struct timer_list tlist; struct snd_timer *snd_timer; unsigned long last_expires; unsigned long last_jiffies; unsigned long correction; }; static void snd_timer_s_function(struct timer_list *t) { struct snd_timer_system_private *priv = from_timer(priv, t, tlist); struct snd_timer *timer = priv->snd_timer; unsigned long jiff = jiffies; if (time_after(jiff, priv->last_expires)) priv->correction += (long)jiff - (long)priv->last_expires; snd_timer_interrupt(timer, (long)jiff - (long)priv->last_jiffies); } static int snd_timer_s_start(struct snd_timer * timer) { struct snd_timer_system_private *priv; unsigned long njiff; priv = (struct snd_timer_system_private *) timer->private_data; njiff = (priv->last_jiffies = jiffies); if (priv->correction > timer->sticks - 1) { priv->correction -= timer->sticks - 1; njiff++; } else { njiff += timer->sticks - priv->correction; priv->correction = 0; } priv->last_expires = njiff; mod_timer(&priv->tlist, njiff); return 0; } static int snd_timer_s_stop(struct snd_timer * timer) { struct snd_timer_system_private *priv; unsigned long jiff; priv = (struct snd_timer_system_private *) timer->private_data; del_timer(&priv->tlist); jiff = jiffies; if (time_before(jiff, priv->last_expires)) timer->sticks = priv->last_expires - jiff; else timer->sticks = 1; priv->correction = 0; return 0; } static int snd_timer_s_close(struct snd_timer *timer) { struct snd_timer_system_private *priv; priv = (struct snd_timer_system_private *)timer->private_data; del_timer_sync(&priv->tlist); return 0; } static const struct snd_timer_hardware snd_timer_system = { .flags = SNDRV_TIMER_HW_FIRST | SNDRV_TIMER_HW_WORK, .resolution = NSEC_PER_SEC / HZ, .ticks = 10000000L, .close = snd_timer_s_close, .start = snd_timer_s_start, .stop = snd_timer_s_stop }; static void snd_timer_free_system(struct snd_timer *timer) { kfree(timer->private_data); } static int snd_timer_register_system(void) { struct snd_timer *timer; struct snd_timer_system_private *priv; int err; err = snd_timer_global_new("system", SNDRV_TIMER_GLOBAL_SYSTEM, &timer); if (err < 0) return err; strcpy(timer->name, "system timer"); timer->hw = snd_timer_system; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) { snd_timer_free(timer); return -ENOMEM; } priv->snd_timer = timer; timer_setup(&priv->tlist, snd_timer_s_function, 0); timer->private_data = priv; timer->private_free = snd_timer_free_system; return snd_timer_global_register(timer); } #ifdef CONFIG_SND_PROC_FS /* * Info interface */ static void snd_timer_proc_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_timer *timer; struct snd_timer_instance *ti; unsigned long resolution; guard(mutex)(®ister_mutex); list_for_each_entry(timer, &snd_timer_list, device_list) { if (timer->card && timer->card->shutdown) continue; switch (timer->tmr_class) { case SNDRV_TIMER_CLASS_GLOBAL: snd_iprintf(buffer, "G%i: ", timer->tmr_device); break; case SNDRV_TIMER_CLASS_CARD: snd_iprintf(buffer, "C%i-%i: ", timer->card->number, timer->tmr_device); break; case SNDRV_TIMER_CLASS_PCM: snd_iprintf(buffer, "P%i-%i-%i: ", timer->card->number, timer->tmr_device, timer->tmr_subdevice); break; default: snd_iprintf(buffer, "?%i-%i-%i-%i: ", timer->tmr_class, timer->card ? timer->card->number : -1, timer->tmr_device, timer->tmr_subdevice); } snd_iprintf(buffer, "%s :", timer->name); scoped_guard(spinlock_irq, &timer->lock) resolution = snd_timer_hw_resolution(timer); if (resolution) snd_iprintf(buffer, " %lu.%03luus (%lu ticks)", resolution / 1000, resolution % 1000, timer->hw.ticks); if (timer->hw.flags & SNDRV_TIMER_HW_SLAVE) snd_iprintf(buffer, " SLAVE"); snd_iprintf(buffer, "\n"); list_for_each_entry(ti, &timer->open_list_head, open_list) snd_iprintf(buffer, " Client %s : %s\n", ti->owner ? ti->owner : "unknown", (ti->flags & (SNDRV_TIMER_IFLG_START | SNDRV_TIMER_IFLG_RUNNING)) ? "running" : "stopped"); } } static struct snd_info_entry *snd_timer_proc_entry; static void __init snd_timer_proc_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "timers", NULL); if (entry != NULL) { entry->c.text.read = snd_timer_proc_read; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); entry = NULL; } } snd_timer_proc_entry = entry; } static void __exit snd_timer_proc_done(void) { snd_info_free_entry(snd_timer_proc_entry); } #else /* !CONFIG_SND_PROC_FS */ #define snd_timer_proc_init() #define snd_timer_proc_done() #endif /* * USER SPACE interface */ static void snd_timer_user_interrupt(struct snd_timer_instance *timeri, unsigned long resolution, unsigned long ticks) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_read *r; int prev; guard(spinlock)(&tu->qlock); if (tu->qused > 0) { prev = tu->qtail == 0 ? tu->queue_size - 1 : tu->qtail - 1; r = &tu->queue[prev]; if (r->resolution == resolution) { r->ticks += ticks; goto __wake; } } if (tu->qused >= tu->queue_size) { tu->overrun++; } else { r = &tu->queue[tu->qtail++]; tu->qtail %= tu->queue_size; r->resolution = resolution; r->ticks = ticks; tu->qused++; } __wake: snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static void snd_timer_user_append_to_tqueue(struct snd_timer_user *tu, struct snd_timer_tread64 *tread) { if (tu->qused >= tu->queue_size) { tu->overrun++; } else { memcpy(&tu->tqueue[tu->qtail++], tread, sizeof(*tread)); tu->qtail %= tu->queue_size; tu->qused++; } } static void snd_timer_user_ccallback(struct snd_timer_instance *timeri, int event, struct timespec64 *tstamp, unsigned long resolution) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_tread64 r1; if (event >= SNDRV_TIMER_EVENT_START && event <= SNDRV_TIMER_EVENT_PAUSE) tu->tstamp = *tstamp; if ((tu->filter & (1 << event)) == 0 || !tu->tread) return; memset(&r1, 0, sizeof(r1)); r1.event = event; r1.tstamp_sec = tstamp->tv_sec; r1.tstamp_nsec = tstamp->tv_nsec; r1.val = resolution; scoped_guard(spinlock_irqsave, &tu->qlock) snd_timer_user_append_to_tqueue(tu, &r1); snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static void snd_timer_user_disconnect(struct snd_timer_instance *timeri) { struct snd_timer_user *tu = timeri->callback_data; tu->disconnected = true; wake_up(&tu->qchange_sleep); } static void snd_timer_user_tinterrupt(struct snd_timer_instance *timeri, unsigned long resolution, unsigned long ticks) { struct snd_timer_user *tu = timeri->callback_data; struct snd_timer_tread64 *r, r1; struct timespec64 tstamp; int prev, append = 0; memset(&r1, 0, sizeof(r1)); memset(&tstamp, 0, sizeof(tstamp)); scoped_guard(spinlock, &tu->qlock) { if ((tu->filter & ((1 << SNDRV_TIMER_EVENT_RESOLUTION) | (1 << SNDRV_TIMER_EVENT_TICK))) == 0) return; if (tu->last_resolution != resolution || ticks > 0) { if (timer_tstamp_monotonic) ktime_get_ts64(&tstamp); else ktime_get_real_ts64(&tstamp); } if ((tu->filter & (1 << SNDRV_TIMER_EVENT_RESOLUTION)) && tu->last_resolution != resolution) { r1.event = SNDRV_TIMER_EVENT_RESOLUTION; r1.tstamp_sec = tstamp.tv_sec; r1.tstamp_nsec = tstamp.tv_nsec; r1.val = resolution; snd_timer_user_append_to_tqueue(tu, &r1); tu->last_resolution = resolution; append++; } if ((tu->filter & (1 << SNDRV_TIMER_EVENT_TICK)) == 0) break; if (ticks == 0) break; if (tu->qused > 0) { prev = tu->qtail == 0 ? tu->queue_size - 1 : tu->qtail - 1; r = &tu->tqueue[prev]; if (r->event == SNDRV_TIMER_EVENT_TICK) { r->tstamp_sec = tstamp.tv_sec; r->tstamp_nsec = tstamp.tv_nsec; r->val += ticks; append++; break; } } r1.event = SNDRV_TIMER_EVENT_TICK; r1.tstamp_sec = tstamp.tv_sec; r1.tstamp_nsec = tstamp.tv_nsec; r1.val = ticks; snd_timer_user_append_to_tqueue(tu, &r1); append++; } if (append == 0) return; snd_kill_fasync(tu->fasync, SIGIO, POLL_IN); wake_up(&tu->qchange_sleep); } static int realloc_user_queue(struct snd_timer_user *tu, int size) { struct snd_timer_read *queue = NULL; struct snd_timer_tread64 *tqueue = NULL; if (tu->tread) { tqueue = kcalloc(size, sizeof(*tqueue), GFP_KERNEL); if (!tqueue) return -ENOMEM; } else { queue = kcalloc(size, sizeof(*queue), GFP_KERNEL); if (!queue) return -ENOMEM; } guard(spinlock_irq)(&tu->qlock); kfree(tu->queue); kfree(tu->tqueue); tu->queue_size = size; tu->queue = queue; tu->tqueue = tqueue; tu->qhead = tu->qtail = tu->qused = 0; return 0; } static int snd_timer_user_open(struct inode *inode, struct file *file) { struct snd_timer_user *tu; int err; err = stream_open(inode, file); if (err < 0) return err; tu = kzalloc(sizeof(*tu), GFP_KERNEL); if (tu == NULL) return -ENOMEM; spin_lock_init(&tu->qlock); init_waitqueue_head(&tu->qchange_sleep); mutex_init(&tu->ioctl_lock); tu->ticks = 1; if (realloc_user_queue(tu, 128) < 0) { kfree(tu); return -ENOMEM; } file->private_data = tu; return 0; } static int snd_timer_user_release(struct inode *inode, struct file *file) { struct snd_timer_user *tu; if (file->private_data) { tu = file->private_data; file->private_data = NULL; scoped_guard(mutex, &tu->ioctl_lock) { if (tu->timeri) { snd_timer_close(tu->timeri); snd_timer_instance_free(tu->timeri); } } snd_fasync_free(tu->fasync); kfree(tu->queue); kfree(tu->tqueue); kfree(tu); } return 0; } static void snd_timer_user_zero_id(struct snd_timer_id *id) { id->dev_class = SNDRV_TIMER_CLASS_NONE; id->dev_sclass = SNDRV_TIMER_SCLASS_NONE; id->card = -1; id->device = -1; id->subdevice = -1; } static void snd_timer_user_copy_id(struct snd_timer_id *id, struct snd_timer *timer) { id->dev_class = timer->tmr_class; id->dev_sclass = SNDRV_TIMER_SCLASS_NONE; id->card = timer->card ? timer->card->number : -1; id->device = timer->tmr_device; id->subdevice = timer->tmr_subdevice; } static int snd_timer_user_next_device(struct snd_timer_id __user *_tid) { struct snd_timer_id id; struct snd_timer *timer; struct list_head *p; if (copy_from_user(&id, _tid, sizeof(id))) return -EFAULT; guard(mutex)(®ister_mutex); if (id.dev_class < 0) { /* first item */ if (list_empty(&snd_timer_list)) snd_timer_user_zero_id(&id); else { timer = list_entry(snd_timer_list.next, struct snd_timer, device_list); snd_timer_user_copy_id(&id, timer); } } else { switch (id.dev_class) { case SNDRV_TIMER_CLASS_GLOBAL: id.device = id.device < 0 ? 0 : id.device + 1; list_for_each(p, &snd_timer_list) { timer = list_entry(p, struct snd_timer, device_list); if (timer->tmr_class > SNDRV_TIMER_CLASS_GLOBAL) { snd_timer_user_copy_id(&id, timer); break; } if (timer->tmr_device >= id.device) { snd_timer_user_copy_id(&id, timer); break; } } if (p == &snd_timer_list) snd_timer_user_zero_id(&id); break; case SNDRV_TIMER_CLASS_CARD: case SNDRV_TIMER_CLASS_PCM: if (id.card < 0) { id.card = 0; } else { if (id.device < 0) { id.device = 0; } else { if (id.subdevice < 0) id.subdevice = 0; else if (id.subdevice < INT_MAX) id.subdevice++; } } list_for_each(p, &snd_timer_list) { timer = list_entry(p, struct snd_timer, device_list); if (timer->tmr_class > id.dev_class) { snd_timer_user_copy_id(&id, timer); break; } if (timer->tmr_class < id.dev_class) continue; if (timer->card->number > id.card) { snd_timer_user_copy_id(&id, timer); break; } if (timer->card->number < id.card) continue; if (timer->tmr_device > id.device) { snd_timer_user_copy_id(&id, timer); break; } if (timer->tmr_device < id.device) continue; if (timer->tmr_subdevice > id.subdevice) { snd_timer_user_copy_id(&id, timer); break; } if (timer->tmr_subdevice < id.subdevice) continue; snd_timer_user_copy_id(&id, timer); break; } if (p == &snd_timer_list) snd_timer_user_zero_id(&id); break; default: snd_timer_user_zero_id(&id); } } if (copy_to_user(_tid, &id, sizeof(*_tid))) return -EFAULT; return 0; } static int snd_timer_user_ginfo(struct file *file, struct snd_timer_ginfo __user *_ginfo) { struct snd_timer_ginfo *ginfo __free(kfree) = NULL; struct snd_timer_id tid; struct snd_timer *t; struct list_head *p; ginfo = memdup_user(_ginfo, sizeof(*ginfo)); if (IS_ERR(ginfo)) return PTR_ERR(ginfo); tid = ginfo->tid; memset(ginfo, 0, sizeof(*ginfo)); ginfo->tid = tid; guard(mutex)(®ister_mutex); t = snd_timer_find(&tid); if (!t) return -ENODEV; ginfo->card = t->card ? t->card->number : -1; if (t->hw.flags & SNDRV_TIMER_HW_SLAVE) ginfo->flags |= SNDRV_TIMER_FLG_SLAVE; strscpy(ginfo->id, t->id, sizeof(ginfo->id)); strscpy(ginfo->name, t->name, sizeof(ginfo->name)); scoped_guard(spinlock_irq, &t->lock) ginfo->resolution = snd_timer_hw_resolution(t); if (t->hw.resolution_min > 0) { ginfo->resolution_min = t->hw.resolution_min; ginfo->resolution_max = t->hw.resolution_max; } list_for_each(p, &t->open_list_head) { ginfo->clients++; } if (copy_to_user(_ginfo, ginfo, sizeof(*ginfo))) return -EFAULT; return 0; } static int timer_set_gparams(struct snd_timer_gparams *gparams) { struct snd_timer *t; guard(mutex)(®ister_mutex); t = snd_timer_find(&gparams->tid); if (!t) return -ENODEV; if (!list_empty(&t->open_list_head)) return -EBUSY; if (!t->hw.set_period) return -ENOSYS; return t->hw.set_period(t, gparams->period_num, gparams->period_den); } static int snd_timer_user_gparams(struct file *file, struct snd_timer_gparams __user *_gparams) { struct snd_timer_gparams gparams; if (copy_from_user(&gparams, _gparams, sizeof(gparams))) return -EFAULT; return timer_set_gparams(&gparams); } static int snd_timer_user_gstatus(struct file *file, struct snd_timer_gstatus __user *_gstatus) { struct snd_timer_gstatus gstatus; struct snd_timer_id tid; struct snd_timer *t; int err = 0; if (copy_from_user(&gstatus, _gstatus, sizeof(gstatus))) return -EFAULT; tid = gstatus.tid; memset(&gstatus, 0, sizeof(gstatus)); gstatus.tid = tid; guard(mutex)(®ister_mutex); t = snd_timer_find(&tid); if (t != NULL) { guard(spinlock_irq)(&t->lock); gstatus.resolution = snd_timer_hw_resolution(t); if (t->hw.precise_resolution) { t->hw.precise_resolution(t, &gstatus.resolution_num, &gstatus.resolution_den); } else { gstatus.resolution_num = gstatus.resolution; gstatus.resolution_den = 1000000000uL; } } else { err = -ENODEV; } if (err >= 0 && copy_to_user(_gstatus, &gstatus, sizeof(gstatus))) err = -EFAULT; return err; } static int snd_timer_user_tselect(struct file *file, struct snd_timer_select __user *_tselect) { struct snd_timer_user *tu; struct snd_timer_select tselect; char str[32]; int err = 0; tu = file->private_data; if (tu->timeri) { snd_timer_close(tu->timeri); snd_timer_instance_free(tu->timeri); tu->timeri = NULL; } if (copy_from_user(&tselect, _tselect, sizeof(tselect))) { err = -EFAULT; goto __err; } sprintf(str, "application %i", current->pid); if (tselect.id.dev_class != SNDRV_TIMER_CLASS_SLAVE) tselect.id.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION; tu->timeri = snd_timer_instance_new(str); if (!tu->timeri) { err = -ENOMEM; goto __err; } tu->timeri->flags |= SNDRV_TIMER_IFLG_FAST; tu->timeri->callback = tu->tread ? snd_timer_user_tinterrupt : snd_timer_user_interrupt; tu->timeri->ccallback = snd_timer_user_ccallback; tu->timeri->callback_data = (void *)tu; tu->timeri->disconnect = snd_timer_user_disconnect; err = snd_timer_open(tu->timeri, &tselect.id, current->pid); if (err < 0) { snd_timer_instance_free(tu->timeri); tu->timeri = NULL; } __err: return err; } static int snd_timer_user_info(struct file *file, struct snd_timer_info __user *_info) { struct snd_timer_user *tu; struct snd_timer_info *info __free(kfree) = NULL; struct snd_timer *t; tu = file->private_data; if (!tu->timeri) return -EBADFD; t = tu->timeri->timer; if (!t) return -EBADFD; info = kzalloc(sizeof(*info), GFP_KERNEL); if (! info) return -ENOMEM; info->card = t->card ? t->card->number : -1; if (t->hw.flags & SNDRV_TIMER_HW_SLAVE) info->flags |= SNDRV_TIMER_FLG_SLAVE; strscpy(info->id, t->id, sizeof(info->id)); strscpy(info->name, t->name, sizeof(info->name)); scoped_guard(spinlock_irq, &t->lock) info->resolution = snd_timer_hw_resolution(t); if (copy_to_user(_info, info, sizeof(*_info))) return -EFAULT; return 0; } static int snd_timer_user_params(struct file *file, struct snd_timer_params __user *_params) { struct snd_timer_user *tu; struct snd_timer_params params; struct snd_timer *t; int err; tu = file->private_data; if (!tu->timeri) return -EBADFD; t = tu->timeri->timer; if (!t) return -EBADFD; if (copy_from_user(¶ms, _params, sizeof(params))) return -EFAULT; if (!(t->hw.flags & SNDRV_TIMER_HW_SLAVE)) { u64 resolution; if (params.ticks < 1) { err = -EINVAL; goto _end; } /* Don't allow resolution less than 1ms */ resolution = snd_timer_resolution(tu->timeri); resolution *= params.ticks; if (resolution < 1000000) { err = -EINVAL; goto _end; } } if (params.queue_size > 0 && (params.queue_size < 32 || params.queue_size > 1024)) { err = -EINVAL; goto _end; } if (params.filter & ~((1<<SNDRV_TIMER_EVENT_RESOLUTION)| (1<<SNDRV_TIMER_EVENT_TICK)| (1<<SNDRV_TIMER_EVENT_START)| (1<<SNDRV_TIMER_EVENT_STOP)| (1<<SNDRV_TIMER_EVENT_CONTINUE)| (1<<SNDRV_TIMER_EVENT_PAUSE)| (1<<SNDRV_TIMER_EVENT_SUSPEND)| (1<<SNDRV_TIMER_EVENT_RESUME)| (1<<SNDRV_TIMER_EVENT_MSTART)| (1<<SNDRV_TIMER_EVENT_MSTOP)| (1<<SNDRV_TIMER_EVENT_MCONTINUE)| (1<<SNDRV_TIMER_EVENT_MPAUSE)| (1<<SNDRV_TIMER_EVENT_MSUSPEND)| (1<<SNDRV_TIMER_EVENT_MRESUME))) { err = -EINVAL; goto _end; } snd_timer_stop(tu->timeri); scoped_guard(spinlock_irq, &t->lock) { tu->timeri->flags &= ~(SNDRV_TIMER_IFLG_AUTO| SNDRV_TIMER_IFLG_EXCLUSIVE| SNDRV_TIMER_IFLG_EARLY_EVENT); if (params.flags & SNDRV_TIMER_PSFLG_AUTO) tu->timeri->flags |= SNDRV_TIMER_IFLG_AUTO; if (params.flags & SNDRV_TIMER_PSFLG_EXCLUSIVE) tu->timeri->flags |= SNDRV_TIMER_IFLG_EXCLUSIVE; if (params.flags & SNDRV_TIMER_PSFLG_EARLY_EVENT) tu->timeri->flags |= SNDRV_TIMER_IFLG_EARLY_EVENT; } if (params.queue_size > 0 && (unsigned int)tu->queue_size != params.queue_size) { err = realloc_user_queue(tu, params.queue_size); if (err < 0) goto _end; } scoped_guard(spinlock_irq, &tu->qlock) { tu->qhead = tu->qtail = tu->qused = 0; if (tu->timeri->flags & SNDRV_TIMER_IFLG_EARLY_EVENT) { if (tu->tread) { struct snd_timer_tread64 tread; memset(&tread, 0, sizeof(tread)); tread.event = SNDRV_TIMER_EVENT_EARLY; tread.tstamp_sec = 0; tread.tstamp_nsec = 0; tread.val = 0; snd_timer_user_append_to_tqueue(tu, &tread); } else { struct snd_timer_read *r = &tu->queue[0]; r->resolution = 0; r->ticks = 0; tu->qused++; tu->qtail++; } } tu->filter = params.filter; tu->ticks = params.ticks; } err = 0; _end: if (copy_to_user(_params, ¶ms, sizeof(params))) return -EFAULT; return err; } static int snd_timer_user_status32(struct file *file, struct snd_timer_status32 __user *_status) { struct snd_timer_user *tu; struct snd_timer_status32 status; tu = file->private_data; if (!tu->timeri) return -EBADFD; memset(&status, 0, sizeof(status)); status.tstamp_sec = tu->tstamp.tv_sec; status.tstamp_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; scoped_guard(spinlock_irq, &tu->qlock) status.queue = tu->qused; if (copy_to_user(_status, &status, sizeof(status))) return -EFAULT; return 0; } static int snd_timer_user_status64(struct file *file, struct snd_timer_status64 __user *_status) { struct snd_timer_user *tu; struct snd_timer_status64 status; tu = file->private_data; if (!tu->timeri) return -EBADFD; memset(&status, 0, sizeof(status)); status.tstamp_sec = tu->tstamp.tv_sec; status.tstamp_nsec = tu->tstamp.tv_nsec; status.resolution = snd_timer_resolution(tu->timeri); status.lost = tu->timeri->lost; status.overrun = tu->overrun; scoped_guard(spinlock_irq, &tu->qlock) status.queue = tu->qused; if (copy_to_user(_status, &status, sizeof(status))) return -EFAULT; return 0; } static int snd_timer_user_start(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; snd_timer_stop(tu->timeri); tu->timeri->lost = 0; tu->last_resolution = 0; err = snd_timer_start(tu->timeri, tu->ticks); if (err < 0) return err; return 0; } static int snd_timer_user_stop(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; err = snd_timer_stop(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_continue(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; /* start timer instead of continue if it's not used before */ if (!(tu->timeri->flags & SNDRV_TIMER_IFLG_PAUSED)) return snd_timer_user_start(file); tu->timeri->lost = 0; err = snd_timer_continue(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_pause(struct file *file) { int err; struct snd_timer_user *tu; tu = file->private_data; if (!tu->timeri) return -EBADFD; err = snd_timer_pause(tu->timeri); if (err < 0) return err; return 0; } static int snd_timer_user_tread(void __user *argp, struct snd_timer_user *tu, unsigned int cmd, bool compat) { int __user *p = argp; int xarg, old_tread; if (tu->timeri) /* too late */ return -EBUSY; if (get_user(xarg, p)) return -EFAULT; old_tread = tu->tread; if (!xarg) tu->tread = TREAD_FORMAT_NONE; else if (cmd == SNDRV_TIMER_IOCTL_TREAD64 || (IS_ENABLED(CONFIG_64BIT) && !compat)) tu->tread = TREAD_FORMAT_TIME64; else tu->tread = TREAD_FORMAT_TIME32; if (tu->tread != old_tread && realloc_user_queue(tu, tu->queue_size) < 0) { tu->tread = old_tread; return -ENOMEM; } return 0; } enum { SNDRV_TIMER_IOCTL_START_OLD = _IO('T', 0x20), SNDRV_TIMER_IOCTL_STOP_OLD = _IO('T', 0x21), SNDRV_TIMER_IOCTL_CONTINUE_OLD = _IO('T', 0x22), SNDRV_TIMER_IOCTL_PAUSE_OLD = _IO('T', 0x23), }; #ifdef CONFIG_SND_UTIMER /* * Since userspace-driven timers are passed to userspace, we need to have an identifier * which will allow us to use them (basically, the subdevice number of udriven timer). */ static DEFINE_IDA(snd_utimer_ids); static void snd_utimer_put_id(struct snd_utimer *utimer) { int timer_id = utimer->id; snd_BUG_ON(timer_id < 0 || timer_id >= SNDRV_UTIMERS_MAX_COUNT); ida_free(&snd_utimer_ids, timer_id); } static int snd_utimer_take_id(void) { return ida_alloc_max(&snd_utimer_ids, SNDRV_UTIMERS_MAX_COUNT - 1, GFP_KERNEL); } static void snd_utimer_free(struct snd_utimer *utimer) { snd_timer_free(utimer->timer); snd_utimer_put_id(utimer); kfree(utimer->name); kfree(utimer); } static int snd_utimer_release(struct inode *inode, struct file *file) { struct snd_utimer *utimer = (struct snd_utimer *)file->private_data; snd_utimer_free(utimer); return 0; } static int snd_utimer_trigger(struct file *file) { struct snd_utimer *utimer = (struct snd_utimer *)file->private_data; snd_timer_interrupt(utimer->timer, utimer->timer->sticks); return 0; } static long snd_utimer_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { switch (ioctl) { case SNDRV_TIMER_IOCTL_TRIGGER: return snd_utimer_trigger(file); } return -ENOTTY; } static const struct file_operations snd_utimer_fops = { .llseek = noop_llseek, .release = snd_utimer_release, .unlocked_ioctl = snd_utimer_ioctl, }; static int snd_utimer_start(struct snd_timer *t) { return 0; } static int snd_utimer_stop(struct snd_timer *t) { return 0; } static int snd_utimer_open(struct snd_timer *t) { return 0; } static int snd_utimer_close(struct snd_timer *t) { return 0; } static const struct snd_timer_hardware timer_hw = { .flags = SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_WORK, .open = snd_utimer_open, .close = snd_utimer_close, .start = snd_utimer_start, .stop = snd_utimer_stop, }; static int snd_utimer_create(struct snd_timer_uinfo *utimer_info, struct snd_utimer **r_utimer) { struct snd_utimer *utimer; struct snd_timer *timer; struct snd_timer_id tid; int utimer_id; int err = 0; if (!utimer_info || utimer_info->resolution == 0) return -EINVAL; utimer = kzalloc(sizeof(*utimer), GFP_KERNEL); if (!utimer) return -ENOMEM; /* We hold the ioctl lock here so we won't get a race condition when allocating id */ utimer_id = snd_utimer_take_id(); if (utimer_id < 0) { err = utimer_id; goto err_take_id; } utimer->name = kasprintf(GFP_KERNEL, "snd-utimer%d", utimer_id); if (!utimer->name) { err = -ENOMEM; goto err_get_name; } utimer->id = utimer_id; tid.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION; tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL; tid.card = -1; tid.device = SNDRV_TIMER_GLOBAL_UDRIVEN; tid.subdevice = utimer_id; err = snd_timer_new(NULL, utimer->name, &tid, &timer); if (err < 0) { pr_err("Can't create userspace-driven timer\n"); goto err_timer_new; } timer->module = THIS_MODULE; timer->hw = timer_hw; timer->hw.resolution = utimer_info->resolution; timer->hw.ticks = 1; timer->max_instances = MAX_SLAVE_INSTANCES; utimer->timer = timer; err = snd_timer_global_register(timer); if (err < 0) { pr_err("Can't register a userspace-driven timer\n"); goto err_timer_reg; } *r_utimer = utimer; return 0; err_timer_reg: snd_timer_free(timer); err_timer_new: kfree(utimer->name); err_get_name: snd_utimer_put_id(utimer); err_take_id: kfree(utimer); return err; } static int snd_utimer_ioctl_create(struct file *file, struct snd_timer_uinfo __user *_utimer_info) { struct snd_utimer *utimer; struct snd_timer_uinfo *utimer_info __free(kfree) = NULL; int err, timer_fd; utimer_info = memdup_user(_utimer_info, sizeof(*utimer_info)); if (IS_ERR(utimer_info)) return PTR_ERR(utimer_info); err = snd_utimer_create(utimer_info, &utimer); if (err < 0) return err; utimer_info->id = utimer->id; timer_fd = anon_inode_getfd(utimer->name, &snd_utimer_fops, utimer, O_RDWR | O_CLOEXEC); if (timer_fd < 0) { snd_utimer_free(utimer); return timer_fd; } utimer_info->fd = timer_fd; err = copy_to_user(_utimer_info, utimer_info, sizeof(*utimer_info)); if (err) { /* * "Leak" the fd, as there is nothing we can do about it. * It might have been closed already since anon_inode_getfd * makes it available for userspace. * * We have to rely on the process exit path to do any * necessary cleanup (e.g. releasing the file). */ return -EFAULT; } return 0; } #else static int snd_utimer_ioctl_create(struct file *file, struct snd_timer_uinfo __user *_utimer_info) { return -ENOTTY; } #endif static long __snd_timer_user_ioctl(struct file *file, unsigned int cmd, unsigned long arg, bool compat) { struct snd_timer_user *tu; void __user *argp = (void __user *)arg; int __user *p = argp; tu = file->private_data; switch (cmd) { case SNDRV_TIMER_IOCTL_PVERSION: return put_user(SNDRV_TIMER_VERSION, p) ? -EFAULT : 0; case SNDRV_TIMER_IOCTL_NEXT_DEVICE: return snd_timer_user_next_device(argp); case SNDRV_TIMER_IOCTL_TREAD_OLD: case SNDRV_TIMER_IOCTL_TREAD64: return snd_timer_user_tread(argp, tu, cmd, compat); case SNDRV_TIMER_IOCTL_GINFO: return snd_timer_user_ginfo(file, argp); case SNDRV_TIMER_IOCTL_GPARAMS: return snd_timer_user_gparams(file, argp); case SNDRV_TIMER_IOCTL_GSTATUS: return snd_timer_user_gstatus(file, argp); case SNDRV_TIMER_IOCTL_SELECT: return snd_timer_user_tselect(file, argp); case SNDRV_TIMER_IOCTL_INFO: return snd_timer_user_info(file, argp); case SNDRV_TIMER_IOCTL_PARAMS: return snd_timer_user_params(file, argp); case SNDRV_TIMER_IOCTL_STATUS32: return snd_timer_user_status32(file, argp); case SNDRV_TIMER_IOCTL_STATUS64: return snd_timer_user_status64(file, argp); case SNDRV_TIMER_IOCTL_START: case SNDRV_TIMER_IOCTL_START_OLD: return snd_timer_user_start(file); case SNDRV_TIMER_IOCTL_STOP: case SNDRV_TIMER_IOCTL_STOP_OLD: return snd_timer_user_stop(file); case SNDRV_TIMER_IOCTL_CONTINUE: case SNDRV_TIMER_IOCTL_CONTINUE_OLD: return snd_timer_user_continue(file); case SNDRV_TIMER_IOCTL_PAUSE: case SNDRV_TIMER_IOCTL_PAUSE_OLD: return snd_timer_user_pause(file); case SNDRV_TIMER_IOCTL_CREATE: return snd_utimer_ioctl_create(file, argp); } return -ENOTTY; } static long snd_timer_user_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct snd_timer_user *tu = file->private_data; guard(mutex)(&tu->ioctl_lock); return __snd_timer_user_ioctl(file, cmd, arg, false); } static int snd_timer_user_fasync(int fd, struct file * file, int on) { struct snd_timer_user *tu; tu = file->private_data; return snd_fasync_helper(fd, file, on, &tu->fasync); } static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, size_t count, loff_t *offset) { struct snd_timer_tread64 *tread; struct snd_timer_tread32 tread32; struct snd_timer_user *tu; long result = 0, unit; int qhead; int err = 0; tu = file->private_data; switch (tu->tread) { case TREAD_FORMAT_TIME64: unit = sizeof(struct snd_timer_tread64); break; case TREAD_FORMAT_TIME32: unit = sizeof(struct snd_timer_tread32); break; case TREAD_FORMAT_NONE: unit = sizeof(struct snd_timer_read); break; default: WARN_ONCE(1, "Corrupt snd_timer_user\n"); return -ENOTSUPP; } mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); while ((long)count - result >= unit) { while (!tu->qused) { wait_queue_entry_t wait; if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { err = -EAGAIN; goto _error; } set_current_state(TASK_INTERRUPTIBLE); init_waitqueue_entry(&wait, current); add_wait_queue(&tu->qchange_sleep, &wait); spin_unlock_irq(&tu->qlock); mutex_unlock(&tu->ioctl_lock); schedule(); mutex_lock(&tu->ioctl_lock); spin_lock_irq(&tu->qlock); remove_wait_queue(&tu->qchange_sleep, &wait); if (tu->disconnected) { err = -ENODEV; goto _error; } if (signal_pending(current)) { err = -ERESTARTSYS; goto _error; } } qhead = tu->qhead++; tu->qhead %= tu->queue_size; tu->qused--; spin_unlock_irq(&tu->qlock); tread = &tu->tqueue[qhead]; switch (tu->tread) { case TREAD_FORMAT_TIME64: if (copy_to_user(buffer, tread, sizeof(struct snd_timer_tread64))) err = -EFAULT; break; case TREAD_FORMAT_TIME32: memset(&tread32, 0, sizeof(tread32)); tread32 = (struct snd_timer_tread32) { .event = tread->event, .tstamp_sec = tread->tstamp_sec, .tstamp_nsec = tread->tstamp_nsec, .val = tread->val, }; if (copy_to_user(buffer, &tread32, sizeof(tread32))) err = -EFAULT; break; case TREAD_FORMAT_NONE: if (copy_to_user(buffer, &tu->queue[qhead], sizeof(struct snd_timer_read))) err = -EFAULT; break; default: err = -ENOTSUPP; break; } spin_lock_irq(&tu->qlock); if (err < 0) goto _error; result += unit; buffer += unit; } _error: spin_unlock_irq(&tu->qlock); mutex_unlock(&tu->ioctl_lock); return result > 0 ? result : err; } static __poll_t snd_timer_user_poll(struct file *file, poll_table * wait) { __poll_t mask; struct snd_timer_user *tu; tu = file->private_data; poll_wait(file, &tu->qchange_sleep, wait); mask = 0; guard(spinlock_irq)(&tu->qlock); if (tu->qused) mask |= EPOLLIN | EPOLLRDNORM; if (tu->disconnected) mask |= EPOLLERR; return mask; } #ifdef CONFIG_COMPAT #include "timer_compat.c" #else #define snd_timer_user_ioctl_compat NULL #endif static const struct file_operations snd_timer_f_ops = { .owner = THIS_MODULE, .read = snd_timer_user_read, .open = snd_timer_user_open, .release = snd_timer_user_release, .llseek = no_llseek, .poll = snd_timer_user_poll, .unlocked_ioctl = snd_timer_user_ioctl, .compat_ioctl = snd_timer_user_ioctl_compat, .fasync = snd_timer_user_fasync, }; /* unregister the system timer */ static void snd_timer_free_all(void) { struct snd_timer *timer, *n; list_for_each_entry_safe(timer, n, &snd_timer_list, device_list) snd_timer_free(timer); } static struct device *timer_dev; /* * ENTRY functions */ static int __init alsa_timer_init(void) { int err; err = snd_device_alloc(&timer_dev, NULL); if (err < 0) return err; dev_set_name(timer_dev, "timer"); #ifdef SNDRV_OSS_INFO_DEV_TIMERS snd_oss_info_register(SNDRV_OSS_INFO_DEV_TIMERS, SNDRV_CARDS - 1, "system timer"); #endif err = snd_timer_register_system(); if (err < 0) { pr_err("ALSA: unable to register system timer (%i)\n", err); goto put_timer; } err = snd_register_device(SNDRV_DEVICE_TYPE_TIMER, NULL, 0, &snd_timer_f_ops, NULL, timer_dev); if (err < 0) { pr_err("ALSA: unable to register timer device (%i)\n", err); snd_timer_free_all(); goto put_timer; } snd_timer_proc_init(); return 0; put_timer: put_device(timer_dev); return err; } static void __exit alsa_timer_exit(void) { snd_unregister_device(timer_dev); snd_timer_free_all(); put_device(timer_dev); snd_timer_proc_done(); #ifdef SNDRV_OSS_INFO_DEV_TIMERS snd_oss_info_unregister(SNDRV_OSS_INFO_DEV_TIMERS, SNDRV_CARDS - 1); #endif } module_init(alsa_timer_init) module_exit(alsa_timer_exit) |
| 487 134 85 85 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Trace point definitions for the RDMA Connect Manager. * * Author: Chuck Lever <chuck.lever@oracle.com> * * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM rdma_cma #if !defined(_TRACE_RDMA_CMA_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RDMA_CMA_H #include <linux/tracepoint.h> #include <trace/misc/rdma.h> DECLARE_EVENT_CLASS(cma_fsm_class, TP_PROTO( const struct rdma_id_private *id_priv ), TP_ARGS(id_priv), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, tos) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->tos = id_priv->tos; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos ) ); #define DEFINE_CMA_FSM_EVENT(name) \ DEFINE_EVENT(cma_fsm_class, cm_##name, \ TP_PROTO( \ const struct rdma_id_private *id_priv \ ), \ TP_ARGS(id_priv)) DEFINE_CMA_FSM_EVENT(send_rtu); DEFINE_CMA_FSM_EVENT(send_rej); DEFINE_CMA_FSM_EVENT(send_mra); DEFINE_CMA_FSM_EVENT(send_sidr_req); DEFINE_CMA_FSM_EVENT(send_sidr_rep); DEFINE_CMA_FSM_EVENT(disconnect); DEFINE_CMA_FSM_EVENT(sent_drep); DEFINE_CMA_FSM_EVENT(sent_dreq); DEFINE_CMA_FSM_EVENT(id_destroy); TRACE_EVENT(cm_id_attach, TP_PROTO( const struct rdma_id_private *id_priv, const struct ib_device *device ), TP_ARGS(id_priv, device), TP_STRUCT__entry( __field(u32, cm_id) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) __string(devname, device->name) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); __assign_str(devname); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc device=%s", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __get_str(devname) ) ); DECLARE_EVENT_CLASS(cma_qp_class, TP_PROTO( const struct rdma_id_private *id_priv ), TP_ARGS(id_priv), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, tos) __field(u32, qp_num) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->tos = id_priv->tos; __entry->qp_num = id_priv->qp_num; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u qp_num=%u", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos, __entry->qp_num ) ); #define DEFINE_CMA_QP_EVENT(name) \ DEFINE_EVENT(cma_qp_class, cm_##name, \ TP_PROTO( \ const struct rdma_id_private *id_priv \ ), \ TP_ARGS(id_priv)) DEFINE_CMA_QP_EVENT(send_req); DEFINE_CMA_QP_EVENT(send_rep); DEFINE_CMA_QP_EVENT(qp_destroy); /* * enum ib_wp_type, from include/rdma/ib_verbs.h */ #define IB_QP_TYPE_LIST \ ib_qp_type(SMI) \ ib_qp_type(GSI) \ ib_qp_type(RC) \ ib_qp_type(UC) \ ib_qp_type(UD) \ ib_qp_type(RAW_IPV6) \ ib_qp_type(RAW_ETHERTYPE) \ ib_qp_type(RAW_PACKET) \ ib_qp_type(XRC_INI) \ ib_qp_type_end(XRC_TGT) #undef ib_qp_type #undef ib_qp_type_end #define ib_qp_type(x) TRACE_DEFINE_ENUM(IB_QPT_##x); #define ib_qp_type_end(x) TRACE_DEFINE_ENUM(IB_QPT_##x); IB_QP_TYPE_LIST #undef ib_qp_type #undef ib_qp_type_end #define ib_qp_type(x) { IB_QPT_##x, #x }, #define ib_qp_type_end(x) { IB_QPT_##x, #x } #define rdma_show_qp_type(x) \ __print_symbolic(x, IB_QP_TYPE_LIST) TRACE_EVENT(cm_qp_create, TP_PROTO( const struct rdma_id_private *id_priv, const struct ib_pd *pd, const struct ib_qp_init_attr *qp_init_attr, int rc ), TP_ARGS(id_priv, pd, qp_init_attr, rc), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, pd_id) __field(u32, tos) __field(u32, qp_num) __field(u32, send_wr) __field(u32, recv_wr) __field(int, rc) __field(unsigned long, qp_type) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->pd_id = pd->res.id; __entry->tos = id_priv->tos; __entry->send_wr = qp_init_attr->cap.max_send_wr; __entry->recv_wr = qp_init_attr->cap.max_recv_wr; __entry->rc = rc; if (!rc) { __entry->qp_num = id_priv->qp_num; __entry->qp_type = id_priv->id.qp_type; } else { __entry->qp_num = 0; __entry->qp_type = 0; } memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u pd.id=%u qp_type=%s" " send_wr=%u recv_wr=%u qp_num=%u rc=%d", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos, __entry->pd_id, rdma_show_qp_type(__entry->qp_type), __entry->send_wr, __entry->recv_wr, __entry->qp_num, __entry->rc ) ); TRACE_EVENT(cm_req_handler, TP_PROTO( const struct rdma_id_private *id_priv, int event ), TP_ARGS(id_priv, event), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, tos) __field(unsigned long, event) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->tos = id_priv->tos; __entry->event = event; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u %s (%lu)", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos, rdma_show_ib_cm_event(__entry->event), __entry->event ) ); TRACE_EVENT(cm_event_handler, TP_PROTO( const struct rdma_id_private *id_priv, const struct rdma_cm_event *event ), TP_ARGS(id_priv, event), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, tos) __field(unsigned long, event) __field(int, status) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->tos = id_priv->tos; __entry->event = event->event; __entry->status = event->status; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u %s (%lu/%d)", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos, rdma_show_cm_event(__entry->event), __entry->event, __entry->status ) ); TRACE_EVENT(cm_event_done, TP_PROTO( const struct rdma_id_private *id_priv, const struct rdma_cm_event *event, int result ), TP_ARGS(id_priv, event, result), TP_STRUCT__entry( __field(u32, cm_id) __field(u32, tos) __field(unsigned long, event) __field(int, result) __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( __entry->cm_id = id_priv->res.id; __entry->tos = id_priv->tos; __entry->event = event->event; __entry->result = result; memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr, sizeof(struct sockaddr_in6)); memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr, sizeof(struct sockaddr_in6)); ), TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u %s consumer returns %d", __entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos, rdma_show_cm_event(__entry->event), __entry->result ) ); DECLARE_EVENT_CLASS(cma_client_class, TP_PROTO( const struct ib_device *device ), TP_ARGS(device), TP_STRUCT__entry( __string(name, device->name) ), TP_fast_assign( __assign_str(name); ), TP_printk("device name=%s", __get_str(name) ) ); #define DEFINE_CMA_CLIENT_EVENT(name) \ DEFINE_EVENT(cma_client_class, cm_##name, \ TP_PROTO( \ const struct ib_device *device \ ), \ TP_ARGS(device)) DEFINE_CMA_CLIENT_EVENT(add_one); DEFINE_CMA_CLIENT_EVENT(remove_one); #endif /* _TRACE_RDMA_CMA_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE cma_trace #include <trace/define_trace.h> |
| 2 3835 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _NET_RPS_H #define _NET_RPS_H #include <linux/types.h> #include <linux/static_key.h> #include <net/sock.h> #include <net/hotdata.h> #ifdef CONFIG_RPS extern struct static_key_false rps_needed; extern struct static_key_false rfs_needed; /* * This structure holds an RPS map which can be of variable length. The * map is an array of CPUs. */ struct rps_map { unsigned int len; struct rcu_head rcu; u16 cpus[]; }; #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) /* * The rps_dev_flow structure contains the mapping of a flow to a CPU, the * tail pointer for that CPU's input queue at the time of last enqueue, and * a hardware filter index. */ struct rps_dev_flow { u16 cpu; u16 filter; unsigned int last_qtail; }; #define RPS_NO_FILTER 0xffff /* * The rps_dev_flow_table structure contains a table of flow mappings. */ struct rps_dev_flow_table { unsigned int mask; struct rcu_head rcu; struct rps_dev_flow flows[]; }; #define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ ((_num) * sizeof(struct rps_dev_flow))) /* * The rps_sock_flow_table contains mappings of flows to the last CPU * on which they were processed by the application (set in recvmsg). * Each entry is a 32bit value. Upper part is the high-order bits * of flow hash, lower part is CPU number. * rps_cpu_mask is used to partition the space, depending on number of * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, * meaning we use 32-6=26 bits for the hash. */ struct rps_sock_flow_table { u32 mask; u32 ents[] ____cacheline_aligned_in_smp; }; #define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) #define RPS_NO_CPU 0xffff static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, u32 hash) { unsigned int index = hash & table->mask; u32 val = hash & ~net_hotdata.rps_cpu_mask; /* We only give a hint, preemption can change CPU under us */ val |= raw_smp_processor_id(); /* The following WRITE_ONCE() is paired with the READ_ONCE() * here, and another one in get_rps_cpu(). */ if (READ_ONCE(table->ents[index]) != val) WRITE_ONCE(table->ents[index], val); } #endif /* CONFIG_RPS */ static inline void sock_rps_record_flow_hash(__u32 hash) { #ifdef CONFIG_RPS struct rps_sock_flow_table *sock_flow_table; if (!hash) return; rcu_read_lock(); sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); if (sock_flow_table) rps_record_sock_flow(sock_flow_table, hash); rcu_read_unlock(); #endif } static inline void sock_rps_record_flow(const struct sock *sk) { #ifdef CONFIG_RPS if (static_branch_unlikely(&rfs_needed)) { /* Reading sk->sk_rxhash might incur an expensive cache line * miss. * * TCP_ESTABLISHED does cover almost all states where RFS * might be useful, and is cheaper [1] than testing : * IPv4: inet_sk(sk)->inet_daddr * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) * OR an additional socket flag * [1] : sk_state and sk_prot are in the same cache line. */ if (sk->sk_state == TCP_ESTABLISHED) { /* This READ_ONCE() is paired with the WRITE_ONCE() * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). */ sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); } } #endif } static inline u32 rps_input_queue_tail_incr(struct softnet_data *sd) { #ifdef CONFIG_RPS return ++sd->input_queue_tail; #else return 0; #endif } static inline void rps_input_queue_tail_save(u32 *dest, u32 tail) { #ifdef CONFIG_RPS WRITE_ONCE(*dest, tail); #endif } static inline void rps_input_queue_head_add(struct softnet_data *sd, int val) { #ifdef CONFIG_RPS WRITE_ONCE(sd->input_queue_head, sd->input_queue_head + val); #endif } static inline void rps_input_queue_head_incr(struct softnet_data *sd) { rps_input_queue_head_add(sd, 1); } #endif /* _NET_RPS_H */ |
| 763 47 4149 4150 2091 70 687 329 329 329 27 1448 15 573 724 920 4 329 414 1270 1793 1790 624 1229 597 18 72 18 663 1793 1793 1177 643 72 702 89 89 1 9 8 48 48 48 48 53 53 53 50 50 50 50 1437 1438 1438 5 1429 12 22 81 81 81 22 113 113 113 105 105 632 624 15 15 15 754 81 21 22 22 5 22 12 22 60 60 60 60 60 23 48 48 60 60 60 60 60 2322 1301 1433 1432 1434 1433 1434 1432 763 762 7 763 140 29 4181 140 4140 4138 2323 2687 626 745 762 763 118 3 303 5 2 3 737 736 2690 2685 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "hard-interface.h" #include "main.h" #include <linux/atomic.h> #include <linux/byteorder/generic.h> #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/errno.h> #include <linux/gfp.h> #include <linux/if.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/kref.h> #include <linux/limits.h> #include <linux/list.h> #include <linux/minmax.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <uapi/linux/batadv_packet.h> #include "bat_v.h" #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" #include "gateway_client.h" #include "log.h" #include "originator.h" #include "send.h" #include "soft-interface.h" #include "translation-table.h" /** * batadv_hardif_release() - release hard interface from lists and queue for * free after rcu grace period * @ref: kref pointer of the hard interface */ void batadv_hardif_release(struct kref *ref) { struct batadv_hard_iface *hard_iface; hard_iface = container_of(ref, struct batadv_hard_iface, refcount); dev_put(hard_iface->net_dev); kfree_rcu(hard_iface, rcu); } /** * batadv_hardif_get_by_netdev() - Get hard interface object of a net_device * @net_dev: net_device to search for * * Return: batadv_hard_iface of net_dev (with increased refcnt), NULL on errors */ struct batadv_hard_iface * batadv_hardif_get_by_netdev(const struct net_device *net_dev) { struct batadv_hard_iface *hard_iface; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->net_dev == net_dev && kref_get_unless_zero(&hard_iface->refcount)) goto out; } hard_iface = NULL; out: rcu_read_unlock(); return hard_iface; } /** * batadv_getlink_net() - return link net namespace (of use fallback) * @netdev: net_device to check * @fallback_net: return in case get_link_net is not available for @netdev * * Return: result of rtnl_link_ops->get_link_net or @fallback_net */ static struct net *batadv_getlink_net(const struct net_device *netdev, struct net *fallback_net) { if (!netdev->rtnl_link_ops) return fallback_net; if (!netdev->rtnl_link_ops->get_link_net) return fallback_net; return netdev->rtnl_link_ops->get_link_net(netdev); } /** * batadv_mutual_parents() - check if two devices are each others parent * @dev1: 1st net dev * @net1: 1st devices netns * @dev2: 2nd net dev * @net2: 2nd devices netns * * veth devices come in pairs and each is the parent of the other! * * Return: true if the devices are each others parent, otherwise false */ static bool batadv_mutual_parents(const struct net_device *dev1, struct net *net1, const struct net_device *dev2, struct net *net2) { int dev1_parent_iflink = dev_get_iflink(dev1); int dev2_parent_iflink = dev_get_iflink(dev2); const struct net *dev1_parent_net; const struct net *dev2_parent_net; dev1_parent_net = batadv_getlink_net(dev1, net1); dev2_parent_net = batadv_getlink_net(dev2, net2); if (!dev1_parent_iflink || !dev2_parent_iflink) return false; return (dev1_parent_iflink == dev2->ifindex) && (dev2_parent_iflink == dev1->ifindex) && net_eq(dev1_parent_net, net2) && net_eq(dev2_parent_net, net1); } /** * batadv_is_on_batman_iface() - check if a device is a batman iface descendant * @net_dev: the device to check * * If the user creates any virtual device on top of a batman-adv interface, it * is important to prevent this new interface from being used to create a new * mesh network (this behaviour would lead to a batman-over-batman * configuration). This function recursively checks all the fathers of the * device passed as argument looking for a batman-adv soft interface. * * Return: true if the device is descendant of a batman-adv mesh interface (or * if it is a batman-adv interface itself), false otherwise */ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) { struct net *net = dev_net(net_dev); struct net_device *parent_dev; struct net *parent_net; int iflink; bool ret; /* check if this is a batman-adv mesh interface */ if (batadv_softif_is_valid(net_dev)) return true; iflink = dev_get_iflink(net_dev); if (iflink == 0) return false; parent_net = batadv_getlink_net(net_dev, net); /* iflink to itself, most likely physical device */ if (net == parent_net && iflink == net_dev->ifindex) return false; /* recurse over the parent device */ parent_dev = __dev_get_by_index((struct net *)parent_net, iflink); if (!parent_dev) { pr_warn("Cannot find parent device. Skipping batadv-on-batadv check for %s\n", net_dev->name); return false; } if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net)) return false; ret = batadv_is_on_batman_iface(parent_dev); return ret; } static bool batadv_is_valid_iface(const struct net_device *net_dev) { if (net_dev->flags & IFF_LOOPBACK) return false; if (net_dev->type != ARPHRD_ETHER) return false; if (net_dev->addr_len != ETH_ALEN) return false; /* no batman over batman */ if (batadv_is_on_batman_iface(net_dev)) return false; return true; } /** * batadv_get_real_netdevice() - check if the given netdev struct is a virtual * interface on top of another 'real' interface * @netdev: the device to check * * Callers must hold the rtnl semaphore. You may want batadv_get_real_netdev() * instead of this. * * Return: the 'real' net device or the original net device and NULL in case * of an error. */ static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) { struct batadv_hard_iface *hard_iface = NULL; struct net_device *real_netdev = NULL; struct net *real_net; struct net *net; int iflink; ASSERT_RTNL(); if (!netdev) return NULL; iflink = dev_get_iflink(netdev); if (iflink == 0) { dev_hold(netdev); return netdev; } hard_iface = batadv_hardif_get_by_netdev(netdev); if (!hard_iface || !hard_iface->soft_iface) goto out; net = dev_net(hard_iface->soft_iface); real_net = batadv_getlink_net(netdev, net); /* iflink to itself, most likely physical device */ if (net == real_net && netdev->ifindex == iflink) { real_netdev = netdev; dev_hold(real_netdev); goto out; } real_netdev = dev_get_by_index(real_net, iflink); out: batadv_hardif_put(hard_iface); return real_netdev; } /** * batadv_get_real_netdev() - check if the given net_device struct is a virtual * interface on top of another 'real' interface * @net_device: the device to check * * Return: the 'real' net device or the original net device and NULL in case * of an error. */ struct net_device *batadv_get_real_netdev(struct net_device *net_device) { struct net_device *real_netdev; rtnl_lock(); real_netdev = batadv_get_real_netdevice(net_device); rtnl_unlock(); return real_netdev; } /** * batadv_is_wext_netdev() - check if the given net_device struct is a * wext wifi interface * @net_device: the device to check * * Return: true if the net device is a wext wireless device, false * otherwise. */ static bool batadv_is_wext_netdev(struct net_device *net_device) { if (!net_device) return false; #ifdef CONFIG_WIRELESS_EXT /* pre-cfg80211 drivers have to implement WEXT, so it is possible to * check for wireless_handlers != NULL */ if (net_device->wireless_handlers) return true; #endif return false; } /** * batadv_is_cfg80211_netdev() - check if the given net_device struct is a * cfg80211 wifi interface * @net_device: the device to check * * Return: true if the net device is a cfg80211 wireless device, false * otherwise. */ static bool batadv_is_cfg80211_netdev(struct net_device *net_device) { if (!net_device) return false; #if IS_ENABLED(CONFIG_CFG80211) /* cfg80211 drivers have to set ieee80211_ptr */ if (net_device->ieee80211_ptr) return true; #endif return false; } /** * batadv_wifi_flags_evaluate() - calculate wifi flags for net_device * @net_device: the device to check * * Return: batadv_hard_iface_wifi_flags flags of the device */ static u32 batadv_wifi_flags_evaluate(struct net_device *net_device) { u32 wifi_flags = 0; struct net_device *real_netdev; if (batadv_is_wext_netdev(net_device)) wifi_flags |= BATADV_HARDIF_WIFI_WEXT_DIRECT; if (batadv_is_cfg80211_netdev(net_device)) wifi_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT; real_netdev = batadv_get_real_netdevice(net_device); if (!real_netdev) return wifi_flags; if (real_netdev == net_device) goto out; if (batadv_is_wext_netdev(real_netdev)) wifi_flags |= BATADV_HARDIF_WIFI_WEXT_INDIRECT; if (batadv_is_cfg80211_netdev(real_netdev)) wifi_flags |= BATADV_HARDIF_WIFI_CFG80211_INDIRECT; out: dev_put(real_netdev); return wifi_flags; } /** * batadv_is_cfg80211_hardif() - check if the given hardif is a cfg80211 wifi * interface * @hard_iface: the device to check * * Return: true if the net device is a cfg80211 wireless device, false * otherwise. */ bool batadv_is_cfg80211_hardif(struct batadv_hard_iface *hard_iface) { u32 allowed_flags = 0; allowed_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT; allowed_flags |= BATADV_HARDIF_WIFI_CFG80211_INDIRECT; return !!(hard_iface->wifi_flags & allowed_flags); } /** * batadv_is_wifi_hardif() - check if the given hardif is a wifi interface * @hard_iface: the device to check * * Return: true if the net device is a 802.11 wireless device, false otherwise. */ bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface) { if (!hard_iface) return false; return hard_iface->wifi_flags != 0; } /** * batadv_hardif_no_broadcast() - check whether (re)broadcast is necessary * @if_outgoing: the outgoing interface checked and considered for (re)broadcast * @orig_addr: the originator of this packet * @orig_neigh: originator address of the forwarder we just got the packet from * (NULL if we originated) * * Checks whether a packet needs to be (re)broadcasted on the given interface. * * Return: * BATADV_HARDIF_BCAST_NORECIPIENT: No neighbor on interface * BATADV_HARDIF_BCAST_DUPFWD: Just one neighbor, but it is the forwarder * BATADV_HARDIF_BCAST_DUPORIG: Just one neighbor, but it is the originator * BATADV_HARDIF_BCAST_OK: Several neighbors, must broadcast */ int batadv_hardif_no_broadcast(struct batadv_hard_iface *if_outgoing, u8 *orig_addr, u8 *orig_neigh) { struct batadv_hardif_neigh_node *hardif_neigh; struct hlist_node *first; int ret = BATADV_HARDIF_BCAST_OK; rcu_read_lock(); /* 0 neighbors -> no (re)broadcast */ first = rcu_dereference(hlist_first_rcu(&if_outgoing->neigh_list)); if (!first) { ret = BATADV_HARDIF_BCAST_NORECIPIENT; goto out; } /* >1 neighbors -> (re)broadcast */ if (rcu_dereference(hlist_next_rcu(first))) goto out; hardif_neigh = hlist_entry(first, struct batadv_hardif_neigh_node, list); /* 1 neighbor, is the originator -> no rebroadcast */ if (orig_addr && batadv_compare_eth(hardif_neigh->orig, orig_addr)) { ret = BATADV_HARDIF_BCAST_DUPORIG; /* 1 neighbor, is the one we received from -> no rebroadcast */ } else if (orig_neigh && batadv_compare_eth(hardif_neigh->orig, orig_neigh)) { ret = BATADV_HARDIF_BCAST_DUPFWD; } out: rcu_read_unlock(); return ret; } static struct batadv_hard_iface * batadv_hardif_get_active(const struct net_device *soft_iface) { struct batadv_hard_iface *hard_iface; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != soft_iface) continue; if (hard_iface->if_status == BATADV_IF_ACTIVE && kref_get_unless_zero(&hard_iface->refcount)) goto out; } hard_iface = NULL; out: rcu_read_unlock(); return hard_iface; } static void batadv_primary_if_update_addr(struct batadv_priv *bat_priv, struct batadv_hard_iface *oldif) { struct batadv_hard_iface *primary_if; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; batadv_dat_init_own_addr(bat_priv, primary_if); batadv_bla_update_orig_address(bat_priv, primary_if, oldif); out: batadv_hardif_put(primary_if); } static void batadv_primary_if_select(struct batadv_priv *bat_priv, struct batadv_hard_iface *new_hard_iface) { struct batadv_hard_iface *curr_hard_iface; ASSERT_RTNL(); if (new_hard_iface) kref_get(&new_hard_iface->refcount); curr_hard_iface = rcu_replace_pointer(bat_priv->primary_if, new_hard_iface, 1); if (!new_hard_iface) goto out; bat_priv->algo_ops->iface.primary_set(new_hard_iface); batadv_primary_if_update_addr(bat_priv, curr_hard_iface); out: batadv_hardif_put(curr_hard_iface); } static bool batadv_hardif_is_iface_up(const struct batadv_hard_iface *hard_iface) { if (hard_iface->net_dev->flags & IFF_UP) return true; return false; } static void batadv_check_known_mac_addr(const struct net_device *net_dev) { const struct batadv_hard_iface *hard_iface; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->if_status != BATADV_IF_ACTIVE && hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) continue; if (hard_iface->net_dev == net_dev) continue; if (!batadv_compare_eth(hard_iface->net_dev->dev_addr, net_dev->dev_addr)) continue; pr_warn("The newly added mac address (%pM) already exists on: %s\n", net_dev->dev_addr, hard_iface->net_dev->name); pr_warn("It is strongly recommended to keep mac addresses unique to avoid problems!\n"); } rcu_read_unlock(); } /** * batadv_hardif_recalc_extra_skbroom() - Recalculate skbuff extra head/tailroom * @soft_iface: netdev struct of the mesh interface */ static void batadv_hardif_recalc_extra_skbroom(struct net_device *soft_iface) { const struct batadv_hard_iface *hard_iface; unsigned short lower_header_len = ETH_HLEN; unsigned short lower_headroom = 0; unsigned short lower_tailroom = 0; unsigned short needed_headroom; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->if_status == BATADV_IF_NOT_IN_USE) continue; if (hard_iface->soft_iface != soft_iface) continue; lower_header_len = max_t(unsigned short, lower_header_len, hard_iface->net_dev->hard_header_len); lower_headroom = max_t(unsigned short, lower_headroom, hard_iface->net_dev->needed_headroom); lower_tailroom = max_t(unsigned short, lower_tailroom, hard_iface->net_dev->needed_tailroom); } rcu_read_unlock(); needed_headroom = lower_headroom + (lower_header_len - ETH_HLEN); needed_headroom += batadv_max_header_len(); /* fragmentation headers don't strip the unicast/... header */ needed_headroom += sizeof(struct batadv_frag_packet); soft_iface->needed_headroom = needed_headroom; soft_iface->needed_tailroom = lower_tailroom; } /** * batadv_hardif_min_mtu() - Calculate maximum MTU for soft interface * @soft_iface: netdev struct of the soft interface * * Return: MTU for the soft-interface (limited by the minimal MTU of all active * slave interfaces) */ int batadv_hardif_min_mtu(struct net_device *soft_iface) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); const struct batadv_hard_iface *hard_iface; int min_mtu = INT_MAX; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->if_status != BATADV_IF_ACTIVE && hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) continue; if (hard_iface->soft_iface != soft_iface) continue; min_mtu = min_t(int, hard_iface->net_dev->mtu, min_mtu); } rcu_read_unlock(); if (atomic_read(&bat_priv->fragmentation) == 0) goto out; /* with fragmentation enabled the maximum size of internally generated * packets such as translation table exchanges or tvlv containers, etc * has to be calculated */ min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE); min_mtu -= sizeof(struct batadv_frag_packet); min_mtu *= BATADV_FRAG_MAX_FRAGMENTS; out: /* report to the other components the maximum amount of bytes that * batman-adv can send over the wire (without considering the payload * overhead). For example, this value is used by TT to compute the * maximum local table size */ atomic_set(&bat_priv->packet_size_max, min_mtu); /* the real soft-interface MTU is computed by removing the payload * overhead from the maximum amount of bytes that was just computed. * * However batman-adv does not support MTUs bigger than ETH_DATA_LEN */ return min_t(int, min_mtu - batadv_max_header_len(), ETH_DATA_LEN); } /** * batadv_update_min_mtu() - Adjusts the MTU if a new interface with a smaller * MTU appeared * @soft_iface: netdev struct of the soft interface */ void batadv_update_min_mtu(struct net_device *soft_iface) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); int limit_mtu; int mtu; mtu = batadv_hardif_min_mtu(soft_iface); if (bat_priv->mtu_set_by_user) limit_mtu = bat_priv->mtu_set_by_user; else limit_mtu = ETH_DATA_LEN; mtu = min(mtu, limit_mtu); dev_set_mtu(soft_iface, mtu); /* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU. */ batadv_tt_local_resize_to_mtu(soft_iface); } static void batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; if (hard_iface->if_status != BATADV_IF_INACTIVE) goto out; bat_priv = netdev_priv(hard_iface->soft_iface); bat_priv->algo_ops->iface.update_mac(hard_iface); hard_iface->if_status = BATADV_IF_TO_BE_ACTIVATED; /* the first active interface becomes our primary interface or * the next active interface after the old primary interface was removed */ primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) batadv_primary_if_select(bat_priv, hard_iface); batadv_info(hard_iface->soft_iface, "Interface activated: %s\n", hard_iface->net_dev->name); batadv_update_min_mtu(hard_iface->soft_iface); if (bat_priv->algo_ops->iface.activate) bat_priv->algo_ops->iface.activate(hard_iface); out: batadv_hardif_put(primary_if); } static void batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface) { if (hard_iface->if_status != BATADV_IF_ACTIVE && hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) return; hard_iface->if_status = BATADV_IF_INACTIVE; batadv_info(hard_iface->soft_iface, "Interface deactivated: %s\n", hard_iface->net_dev->name); batadv_update_min_mtu(hard_iface->soft_iface); } /** * batadv_hardif_enable_interface() - Enslave hard interface to soft interface * @hard_iface: hard interface to add to soft interface * @soft_iface: netdev struct of the mesh interface * * Return: 0 on success or negative error number in case of failure */ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, struct net_device *soft_iface) { struct batadv_priv *bat_priv; __be16 ethertype = htons(ETH_P_BATMAN); int max_header_len = batadv_max_header_len(); unsigned int required_mtu; unsigned int hardif_mtu; int ret; hardif_mtu = READ_ONCE(hard_iface->net_dev->mtu); required_mtu = READ_ONCE(soft_iface->mtu) + max_header_len; if (hardif_mtu < ETH_MIN_MTU + max_header_len) return -EINVAL; if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) goto out; kref_get(&hard_iface->refcount); dev_hold(soft_iface); hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); ret = netdev_master_upper_dev_link(hard_iface->net_dev, soft_iface, NULL, NULL, NULL); if (ret) goto err_dev; ret = bat_priv->algo_ops->iface.enable(hard_iface); if (ret < 0) goto err_upper; hard_iface->if_status = BATADV_IF_INACTIVE; kref_get(&hard_iface->refcount); hard_iface->batman_adv_ptype.type = ethertype; hard_iface->batman_adv_ptype.func = batadv_batman_skb_recv; hard_iface->batman_adv_ptype.dev = hard_iface->net_dev; dev_add_pack(&hard_iface->batman_adv_ptype); batadv_info(hard_iface->soft_iface, "Adding interface: %s\n", hard_iface->net_dev->name); if (atomic_read(&bat_priv->fragmentation) && hardif_mtu < required_mtu) batadv_info(hard_iface->soft_iface, "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. Packets going over this interface will be fragmented on layer2 which could impact the performance. Setting the MTU to %i would solve the problem.\n", hard_iface->net_dev->name, hardif_mtu, required_mtu); if (!atomic_read(&bat_priv->fragmentation) && hardif_mtu < required_mtu) batadv_info(hard_iface->soft_iface, "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. If you experience problems getting traffic through try increasing the MTU to %i.\n", hard_iface->net_dev->name, hardif_mtu, required_mtu); if (batadv_hardif_is_iface_up(hard_iface)) batadv_hardif_activate_interface(hard_iface); else batadv_err(hard_iface->soft_iface, "Not using interface %s (retrying later): interface not active\n", hard_iface->net_dev->name); batadv_hardif_recalc_extra_skbroom(soft_iface); if (bat_priv->algo_ops->iface.enabled) bat_priv->algo_ops->iface.enabled(hard_iface); out: return 0; err_upper: netdev_upper_dev_unlink(hard_iface->net_dev, soft_iface); err_dev: hard_iface->soft_iface = NULL; dev_put(soft_iface); batadv_hardif_put(hard_iface); return ret; } /** * batadv_hardif_cnt() - get number of interfaces enslaved to soft interface * @soft_iface: soft interface to check * * This function is only using RCU for locking - the result can therefore be * off when another function is modifying the list at the same time. The * caller can use the rtnl_lock to make sure that the count is accurate. * * Return: number of connected/enslaved hard interfaces */ static size_t batadv_hardif_cnt(const struct net_device *soft_iface) { struct batadv_hard_iface *hard_iface; size_t count = 0; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != soft_iface) continue; count++; } rcu_read_unlock(); return count; } /** * batadv_hardif_disable_interface() - Remove hard interface from soft interface * @hard_iface: hard interface to be removed */ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hard_iface *primary_if = NULL; batadv_hardif_deactivate_interface(hard_iface); if (hard_iface->if_status != BATADV_IF_INACTIVE) goto out; batadv_info(hard_iface->soft_iface, "Removing interface: %s\n", hard_iface->net_dev->name); dev_remove_pack(&hard_iface->batman_adv_ptype); batadv_hardif_put(hard_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (hard_iface == primary_if) { struct batadv_hard_iface *new_if; new_if = batadv_hardif_get_active(hard_iface->soft_iface); batadv_primary_if_select(bat_priv, new_if); batadv_hardif_put(new_if); } bat_priv->algo_ops->iface.disable(hard_iface); hard_iface->if_status = BATADV_IF_NOT_IN_USE; /* delete all references to this hard_iface */ batadv_purge_orig_ref(bat_priv); batadv_purge_outstanding_packets(bat_priv, hard_iface); dev_put(hard_iface->soft_iface); netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->soft_iface); batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface); /* nobody uses this interface anymore */ if (batadv_hardif_cnt(hard_iface->soft_iface) <= 1) batadv_gw_check_client_stop(bat_priv); hard_iface->soft_iface = NULL; batadv_hardif_put(hard_iface); out: batadv_hardif_put(primary_if); } static struct batadv_hard_iface * batadv_hardif_add_interface(struct net_device *net_dev) { struct batadv_hard_iface *hard_iface; ASSERT_RTNL(); if (!batadv_is_valid_iface(net_dev)) goto out; dev_hold(net_dev); hard_iface = kzalloc(sizeof(*hard_iface), GFP_ATOMIC); if (!hard_iface) goto release_dev; hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; INIT_LIST_HEAD(&hard_iface->list); INIT_HLIST_HEAD(&hard_iface->neigh_list); mutex_init(&hard_iface->bat_iv.ogm_buff_mutex); spin_lock_init(&hard_iface->neigh_list_lock); kref_init(&hard_iface->refcount); hard_iface->num_bcasts = BATADV_NUM_BCASTS_DEFAULT; hard_iface->wifi_flags = batadv_wifi_flags_evaluate(net_dev); if (batadv_is_wifi_hardif(hard_iface)) hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; atomic_set(&hard_iface->hop_penalty, 0); batadv_v_hardif_init(hard_iface); batadv_check_known_mac_addr(hard_iface->net_dev); kref_get(&hard_iface->refcount); list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list); batadv_hardif_generation++; return hard_iface; release_dev: dev_put(net_dev); out: return NULL; } static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface) { ASSERT_RTNL(); /* first deactivate interface */ if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) batadv_hardif_disable_interface(hard_iface); if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) return; hard_iface->if_status = BATADV_IF_TO_BE_REMOVED; batadv_hardif_put(hard_iface); } /** * batadv_hard_if_event_softif() - Handle events for soft interfaces * @event: NETDEV_* event to handle * @net_dev: net_device which generated an event * * Return: NOTIFY_* result */ static int batadv_hard_if_event_softif(unsigned long event, struct net_device *net_dev) { struct batadv_priv *bat_priv; switch (event) { case NETDEV_REGISTER: bat_priv = netdev_priv(net_dev); batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); break; } return NOTIFY_DONE; } static int batadv_hard_if_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *net_dev = netdev_notifier_info_to_dev(ptr); struct batadv_hard_iface *hard_iface; struct batadv_hard_iface *primary_if = NULL; struct batadv_priv *bat_priv; if (batadv_softif_is_valid(net_dev)) return batadv_hard_if_event_softif(event, net_dev); hard_iface = batadv_hardif_get_by_netdev(net_dev); if (!hard_iface && (event == NETDEV_REGISTER || event == NETDEV_POST_TYPE_CHANGE)) hard_iface = batadv_hardif_add_interface(net_dev); if (!hard_iface) goto out; switch (event) { case NETDEV_UP: batadv_hardif_activate_interface(hard_iface); break; case NETDEV_GOING_DOWN: case NETDEV_DOWN: batadv_hardif_deactivate_interface(hard_iface); break; case NETDEV_UNREGISTER: case NETDEV_PRE_TYPE_CHANGE: list_del_rcu(&hard_iface->list); batadv_hardif_generation++; batadv_hardif_remove_interface(hard_iface); break; case NETDEV_CHANGEMTU: if (hard_iface->soft_iface) batadv_update_min_mtu(hard_iface->soft_iface); break; case NETDEV_CHANGEADDR: if (hard_iface->if_status == BATADV_IF_NOT_IN_USE) goto hardif_put; batadv_check_known_mac_addr(hard_iface->net_dev); bat_priv = netdev_priv(hard_iface->soft_iface); bat_priv->algo_ops->iface.update_mac(hard_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto hardif_put; if (hard_iface == primary_if) batadv_primary_if_update_addr(bat_priv, NULL); break; case NETDEV_CHANGEUPPER: hard_iface->wifi_flags = batadv_wifi_flags_evaluate(net_dev); if (batadv_is_wifi_hardif(hard_iface)) hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; break; default: break; } hardif_put: batadv_hardif_put(hard_iface); out: batadv_hardif_put(primary_if); return NOTIFY_DONE; } struct notifier_block batadv_hard_if_notifier = { .notifier_call = batadv_hard_if_event, }; |
| 21 14 2 1 4 346 347 343 5 4 3 1354 252 5 5 4180 4179 1354 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> #include <net/flow_offload.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> #include <net/pkt_cls.h> static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) { struct nft_flow_rule *flow; flow = kzalloc(sizeof(struct nft_flow_rule), GFP_KERNEL); if (!flow) return NULL; flow->rule = flow_rule_alloc(num_actions); if (!flow->rule) { kfree(flow); return NULL; } flow->rule->match.dissector = &flow->match.dissector; flow->rule->match.mask = &flow->match.mask; flow->rule->match.key = &flow->match.key; return flow; } void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, enum flow_dissector_key_id addr_type) { struct nft_flow_match *match = &flow->match; struct nft_flow_key *mask = &match->mask; struct nft_flow_key *key = &match->key; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) return; key->control.addr_type = addr_type; mask->control.addr_type = 0xffff; match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL); match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = offsetof(struct nft_flow_key, control); } struct nft_offload_ethertype { __be16 value; __be16 mask; }; static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow) { struct nft_flow_match *match = &flow->match; struct nft_offload_ethertype ethertype = { .value = match->key.basic.n_proto, .mask = match->mask.basic.n_proto, }; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || match->key.vlan.vlan_tpid == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.cvlan.vlan_tpid; match->mask.basic.n_proto = match->mask.cvlan.vlan_tpid; match->key.cvlan.vlan_tpid = match->key.vlan.vlan_tpid; match->mask.cvlan.vlan_tpid = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN); } else if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) && (match->key.basic.n_proto == htons(ETH_P_8021Q) || match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = offsetof(struct nft_flow_key, vlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN); } } struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { struct nft_offload_ctx *ctx; struct nft_flow_rule *flow; int num_actions = 0, err; struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->offload_action && expr->ops->offload_action(expr)) num_actions++; expr = nft_expr_next(expr); } if (num_actions == 0) return ERR_PTR(-EOPNOTSUPP); flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); expr = nft_expr_first(rule); ctx = kzalloc(sizeof(struct nft_offload_ctx), GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto err_out; } ctx->net = net; ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; while (nft_expr_more(rule, expr)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; } err = expr->ops->offload(ctx, flow, expr); if (err < 0) goto err_out; expr = nft_expr_next(expr); } nft_flow_rule_transfer_vlan(ctx, flow); flow->proto = ctx->dep.l3num; kfree(ctx); return flow; err_out: kfree(ctx); nft_flow_rule_destroy(flow); return ERR_PTR(err); } void nft_flow_rule_destroy(struct nft_flow_rule *flow) { struct flow_action_entry *entry; int i; flow_action_for_each(i, entry, &flow->rule->action) { switch (entry->id) { case FLOW_ACTION_REDIRECT: case FLOW_ACTION_MIRRED: dev_put(entry->dev); break; default: break; } } kfree(flow->rule); kfree(flow); } void nft_offload_set_dependency(struct nft_offload_ctx *ctx, enum nft_offload_dep_type type) { ctx->dep.type = type; } void nft_offload_update_dependency(struct nft_offload_ctx *ctx, const void *data, u32 len) { switch (ctx->dep.type) { case NFT_OFFLOAD_DEP_NETWORK: WARN_ON(len != sizeof(__u16)); memcpy(&ctx->dep.l3num, data, sizeof(__u16)); break; case NFT_OFFLOAD_DEP_TRANSPORT: WARN_ON(len != sizeof(__u8)); memcpy(&ctx->dep.protonum, data, sizeof(__u8)); break; default: break; } ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; } static void nft_flow_offload_common_init(struct flow_cls_common_offload *common, __be16 proto, int priority, struct netlink_ext_ack *extack) { common->protocol = proto; common->prio = priority; common->extack = extack; } static int nft_setup_cb_call(enum tc_setup_type type, void *type_data, struct list_head *cb_list) { struct flow_block_cb *block_cb; int err; list_for_each_entry(block_cb, cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err < 0) return err; } return 0; } static int nft_chain_offload_priority(const struct nft_base_chain *basechain) { if (basechain->ops.priority <= 0 || basechain->ops.priority > USHRT_MAX) return -1; return 0; } bool nft_chain_offload_support(const struct nft_base_chain *basechain) { struct net_device *dev; struct nft_hook *hook; if (nft_chain_offload_priority(basechain) < 0) return false; list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.pf != NFPROTO_NETDEV || hook->ops.hooknum != NF_NETDEV_INGRESS) return false; dev = hook->ops.dev; if (!dev->netdev_ops->ndo_setup_tc && !flow_indr_dev_exists()) return false; } return true; } static void nft_flow_cls_offload_setup(struct flow_cls_offload *cls_flow, const struct nft_base_chain *basechain, const struct nft_rule *rule, const struct nft_flow_rule *flow, struct netlink_ext_ack *extack, enum flow_cls_command command) { __be16 proto = ETH_P_ALL; memset(cls_flow, 0, sizeof(*cls_flow)); if (flow) proto = flow->proto; nft_flow_offload_common_init(&cls_flow->common, proto, basechain->ops.priority, extack); cls_flow->command = command; cls_flow->cookie = (unsigned long) rule; if (flow) cls_flow->rule = flow->rule; } static int nft_flow_offload_cmd(const struct nft_chain *chain, const struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command, struct flow_cls_offload *cls_flow) { struct netlink_ext_ack extack = {}; struct nft_base_chain *basechain; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); nft_flow_cls_offload_setup(cls_flow, basechain, rule, flow, &extack, command); return nft_setup_cb_call(TC_SETUP_CLSFLOWER, cls_flow, &basechain->flow_block.cb_list); } static int nft_flow_offload_rule(const struct nft_chain *chain, struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command) { struct flow_cls_offload cls_flow; return nft_flow_offload_cmd(chain, rule, flow, command, &cls_flow); } int nft_flow_rule_stats(const struct nft_chain *chain, const struct nft_rule *rule) { struct flow_cls_offload cls_flow = {}; struct nft_expr *expr, *next; int err; err = nft_flow_offload_cmd(chain, rule, NULL, FLOW_CLS_STATS, &cls_flow); if (err < 0) return err; nft_rule_for_each_expr(expr, next, rule) { if (expr->ops->offload_stats) expr->ops->offload_stats(expr, &cls_flow.stats); } return 0; } static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { list_splice(&bo->cb_list, &basechain->flow_block.cb_list); return 0; } static int nft_flow_offload_unbind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { struct flow_block_cb *block_cb, *next; struct flow_cls_offload cls_flow; struct netlink_ext_ack extack; struct nft_chain *chain; struct nft_rule *rule; chain = &basechain->chain; list_for_each_entry(rule, &chain->rules, list) { memset(&extack, 0, sizeof(extack)); nft_flow_cls_offload_setup(&cls_flow, basechain, rule, NULL, &extack, FLOW_CLS_DESTROY); nft_setup_cb_call(TC_SETUP_CLSFLOWER, &cls_flow, &bo->cb_list); } list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { list_del(&block_cb->list); flow_block_cb_free(block_cb); } return 0; } static int nft_block_setup(struct nft_base_chain *basechain, struct flow_block_offload *bo, enum flow_block_command cmd) { int err; switch (cmd) { case FLOW_BLOCK_BIND: err = nft_flow_offload_bind(bo, basechain); break; case FLOW_BLOCK_UNBIND: err = nft_flow_offload_unbind(bo, basechain); break; default: WARN_ON_ONCE(1); err = -EOPNOTSUPP; } return err; } static void nft_flow_block_offload_init(struct flow_block_offload *bo, struct net *net, enum flow_block_command cmd, struct nft_base_chain *basechain, struct netlink_ext_ack *extack) { memset(bo, 0, sizeof(*bo)); bo->net = net; bo->block = &basechain->flow_block; bo->command = cmd; bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo->extack = extack; bo->cb_list_head = &basechain->flow_block.cb_list; INIT_LIST_HEAD(&bo->cb_list); } static int nft_block_offload_cmd(struct nft_base_chain *chain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); if (err < 0) return err; return nft_block_setup(chain, &bo, cmd); } static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) { struct nft_base_chain *basechain = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct flow_block_offload bo; nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); mutex_unlock(&nft_net->commit_mutex); } static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, basechain, &extack); err = flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_BLOCK, basechain, &bo, nft_indr_block_cleanup); if (err < 0) return err; if (list_empty(&bo.cb_list)) return -EOPNOTSUPP; return nft_block_setup(basechain, &bo, cmd); } static int nft_chain_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { int err; if (dev->netdev_ops->ndo_setup_tc) err = nft_block_offload_cmd(basechain, dev, cmd); else err = nft_indr_block_offload_cmd(basechain, dev, cmd); return err; } static int nft_flow_block_chain(struct nft_base_chain *basechain, const struct net_device *this_dev, enum flow_block_command cmd) { struct net_device *dev; struct nft_hook *hook; int err, i = 0; list_for_each_entry(hook, &basechain->hook_list, list) { dev = hook->ops.dev; if (this_dev && this_dev != dev) continue; err = nft_chain_offload_cmd(basechain, dev, cmd); if (err < 0 && cmd == FLOW_BLOCK_BIND) { if (!this_dev) goto err_flow_block; return err; } i++; } return 0; err_flow_block: list_for_each_entry(hook, &basechain->hook_list, list) { if (i-- <= 0) break; dev = hook->ops.dev; nft_chain_offload_cmd(basechain, dev, FLOW_BLOCK_UNBIND); } return err; } static int nft_flow_offload_chain(struct nft_chain *chain, u8 *ppolicy, enum flow_block_command cmd) { struct nft_base_chain *basechain; u8 policy; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); policy = ppolicy ? *ppolicy : basechain->policy; /* Only default policy to accept is supported for now. */ if (cmd == FLOW_BLOCK_BIND && policy == NF_DROP) return -EOPNOTSUPP; return nft_flow_block_chain(basechain, NULL, cmd); } static void nft_flow_rule_offload_abort(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); int err = 0; list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_UNBIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_BIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; } if (WARN_ON_ONCE(err)) break; } } int nft_flow_rule_offload_commit(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; int err = 0; u8 policy; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_BIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_UNBIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; if (trans->flags & NLM_F_REPLACE || !(trans->flags & NLM_F_APPEND)) { err = -EOPNOTSUPP; break; } err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; } if (err) { nft_flow_rule_offload_abort(net, trans); break; } } return err; } static struct nft_chain *__nft_offload_get_chain(const struct nftables_pernet *nft_net, struct net_device *dev) { struct nft_base_chain *basechain; struct nft_hook *hook, *found; const struct nft_table *table; struct nft_chain *chain; list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain) || !(chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; found = NULL; basechain = nft_base_chain(chain); list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.dev != dev) continue; found = hook; break; } if (!found) continue; return chain; } } return NULL; } static int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct nft_chain *chain; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); chain = __nft_offload_get_chain(nft_net, dev); if (chain) nft_flow_block_chain(nft_base_chain(chain), dev, FLOW_BLOCK_UNBIND); mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nft_offload_netdev_notifier = { .notifier_call = nft_offload_netdev_event, }; int nft_offload_init(void) { return register_netdevice_notifier(&nft_offload_netdev_notifier); } void nft_offload_exit(void) { unregister_netdevice_notifier(&nft_offload_netdev_notifier); } |
| 56 60 53 53 2 2 4 4 8 5 5 4 4 4 4 4 4 4 4 4 3 2 2 1 2 2 2 2 3 1 3 1 1 4 2 2 2 52 52 51 2 1 5 5 5 5 5 2 1 1 1 3 3 3 3 2 2 2 2 2 1 3 2 1 1 6 2 2 4 4 1 1 2 6 3 3 3 3 3 3 3 2 1 1 1 1 1 2 3 1 4 1 1 1 1 1 7 5 2 5 51 51 51 51 51 51 1 51 51 51 1 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 1 51 51 51 51 51 51 51 51 51 51 51 51 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include <trace/events/devlink.h> #include "devl_internal.h" struct devlink_stats { u64_stats_t rx_bytes; u64_stats_t rx_packets; struct u64_stats_sync syncp; }; /** * struct devlink_trap_policer_item - Packet trap policer attributes. * @policer: Immutable packet trap policer attributes. * @rate: Rate in packets / sec. * @burst: Burst size in packets. * @list: trap_policer_list member. * * Describes packet trap policer attributes. Created by devlink during trap * policer registration. */ struct devlink_trap_policer_item { const struct devlink_trap_policer *policer; u64 rate; u64 burst; struct list_head list; }; /** * struct devlink_trap_group_item - Packet trap group attributes. * @group: Immutable packet trap group attributes. * @policer_item: Associated policer item. Can be NULL. * @list: trap_group_list member. * @stats: Trap group statistics. * * Describes packet trap group attributes. Created by devlink during trap * group registration. */ struct devlink_trap_group_item { const struct devlink_trap_group *group; struct devlink_trap_policer_item *policer_item; struct list_head list; struct devlink_stats __percpu *stats; }; /** * struct devlink_trap_item - Packet trap attributes. * @trap: Immutable packet trap attributes. * @group_item: Associated group item. * @list: trap_list member. * @action: Trap action. * @stats: Trap statistics. * @priv: Driver private information. * * Describes both mutable and immutable packet trap attributes. Created by * devlink during trap registration and used for all trap related operations. */ struct devlink_trap_item { const struct devlink_trap *trap; struct devlink_trap_group_item *group_item; struct list_head list; enum devlink_trap_action action; struct devlink_stats __percpu *stats; void *priv; }; static struct devlink_trap_policer_item * devlink_trap_policer_item_lookup(struct devlink *devlink, u32 id) { struct devlink_trap_policer_item *policer_item; list_for_each_entry(policer_item, &devlink->trap_policer_list, list) { if (policer_item->policer->id == id) return policer_item; } return NULL; } static struct devlink_trap_item * devlink_trap_item_lookup(struct devlink *devlink, const char *name) { struct devlink_trap_item *trap_item; list_for_each_entry(trap_item, &devlink->trap_list, list) { if (!strcmp(trap_item->trap->name, name)) return trap_item; } return NULL; } static struct devlink_trap_item * devlink_trap_item_get_from_info(struct devlink *devlink, struct genl_info *info) { struct nlattr *attr; if (!info->attrs[DEVLINK_ATTR_TRAP_NAME]) return NULL; attr = info->attrs[DEVLINK_ATTR_TRAP_NAME]; return devlink_trap_item_lookup(devlink, nla_data(attr)); } static int devlink_trap_action_get_from_info(struct genl_info *info, enum devlink_trap_action *p_trap_action) { u8 val; val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]); switch (val) { case DEVLINK_TRAP_ACTION_DROP: case DEVLINK_TRAP_ACTION_TRAP: case DEVLINK_TRAP_ACTION_MIRROR: *p_trap_action = val; break; default: return -EINVAL; } return 0; } static int devlink_trap_metadata_put(struct sk_buff *msg, const struct devlink_trap *trap) { struct nlattr *attr; attr = nla_nest_start(msg, DEVLINK_ATTR_TRAP_METADATA); if (!attr) return -EMSGSIZE; if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) && nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT)) goto nla_put_failure; if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE) && nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats, struct devlink_stats *stats) { int i; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(i) { struct devlink_stats *cpu_stats; u64 rx_packets, rx_bytes; unsigned int start; cpu_stats = per_cpu_ptr(trap_stats, i); do { start = u64_stats_fetch_begin(&cpu_stats->syncp); rx_packets = u64_stats_read(&cpu_stats->rx_packets); rx_bytes = u64_stats_read(&cpu_stats->rx_bytes); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->rx_packets, rx_packets); u64_stats_add(&stats->rx_bytes, rx_bytes); } } static int devlink_trap_group_stats_put(struct sk_buff *msg, struct devlink_stats __percpu *trap_stats) { struct devlink_stats stats; struct nlattr *attr; devlink_trap_stats_read(trap_stats, &stats); attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); if (!attr) return -EMSGSIZE; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, u64_stats_read(&stats.rx_packets), DEVLINK_ATTR_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, u64_stats_read(&stats.rx_bytes), DEVLINK_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int devlink_trap_stats_put(struct sk_buff *msg, struct devlink *devlink, const struct devlink_trap_item *trap_item) { struct devlink_stats stats; struct nlattr *attr; u64 drops = 0; int err; if (devlink->ops->trap_drop_counter_get) { err = devlink->ops->trap_drop_counter_get(devlink, trap_item->trap, &drops); if (err) return err; } devlink_trap_stats_read(trap_item->stats, &stats); attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); if (!attr) return -EMSGSIZE; if (devlink->ops->trap_drop_counter_get && nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops, DEVLINK_ATTR_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, u64_stats_read(&stats.rx_packets), DEVLINK_ATTR_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, u64_stats_read(&stats.rx_bytes), DEVLINK_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink, const struct devlink_trap_item *trap_item, enum devlink_command cmd, u32 portid, u32 seq, int flags) { struct devlink_trap_group_item *group_item = trap_item->group_item; void *hdr; int err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME, group_item->group->name)) goto nla_put_failure; if (nla_put_string(msg, DEVLINK_ATTR_TRAP_NAME, trap_item->trap->name)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_TYPE, trap_item->trap->type)) goto nla_put_failure; if (trap_item->trap->generic && nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_ACTION, trap_item->action)) goto nla_put_failure; err = devlink_trap_metadata_put(msg, trap_item->trap); if (err) goto nla_put_failure; err = devlink_trap_stats_put(msg, devlink, trap_item); if (err) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; struct devlink_trap_item *trap_item; struct sk_buff *msg; int err; if (list_empty(&devlink->trap_list)) return -EOPNOTSUPP; trap_item = devlink_trap_item_get_from_info(devlink, info); if (!trap_item) { NL_SET_ERR_MSG(extack, "Device did not register this trap"); return -ENOENT; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_trap_fill(msg, devlink, trap_item, DEVLINK_CMD_TRAP_NEW, info->snd_portid, info->snd_seq, 0); if (err) goto err_trap_fill; return genlmsg_reply(msg, info); err_trap_fill: nlmsg_free(msg); return err; } static int devlink_nl_trap_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_trap_item *trap_item; int idx = 0; int err = 0; list_for_each_entry(trap_item, &devlink->trap_list, list) { if (idx < state->idx) { idx++; continue; } err = devlink_nl_trap_fill(msg, devlink, trap_item, DEVLINK_CMD_TRAP_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) { state->idx = idx; break; } idx++; } return err; } int devlink_nl_trap_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_trap_get_dump_one); } static int __devlink_trap_action_set(struct devlink *devlink, struct devlink_trap_item *trap_item, enum devlink_trap_action trap_action, struct netlink_ext_ack *extack) { int err; if (trap_item->action != trap_action && trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) { NL_SET_ERR_MSG(extack, "Cannot change action of non-drop traps. Skipping"); return 0; } err = devlink->ops->trap_action_set(devlink, trap_item->trap, trap_action, extack); if (err) return err; trap_item->action = trap_action; return 0; } static int devlink_trap_action_set(struct devlink *devlink, struct devlink_trap_item *trap_item, struct genl_info *info) { enum devlink_trap_action trap_action; int err; if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION]) return 0; err = devlink_trap_action_get_from_info(info, &trap_action); if (err) { NL_SET_ERR_MSG(info->extack, "Invalid trap action"); return -EINVAL; } return __devlink_trap_action_set(devlink, trap_item, trap_action, info->extack); } int devlink_nl_trap_set_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; struct devlink_trap_item *trap_item; if (list_empty(&devlink->trap_list)) return -EOPNOTSUPP; trap_item = devlink_trap_item_get_from_info(devlink, info); if (!trap_item) { NL_SET_ERR_MSG(extack, "Device did not register this trap"); return -ENOENT; } return devlink_trap_action_set(devlink, trap_item, info); } static struct devlink_trap_group_item * devlink_trap_group_item_lookup(struct devlink *devlink, const char *name) { struct devlink_trap_group_item *group_item; list_for_each_entry(group_item, &devlink->trap_group_list, list) { if (!strcmp(group_item->group->name, name)) return group_item; } return NULL; } static struct devlink_trap_group_item * devlink_trap_group_item_lookup_by_id(struct devlink *devlink, u16 id) { struct devlink_trap_group_item *group_item; list_for_each_entry(group_item, &devlink->trap_group_list, list) { if (group_item->group->id == id) return group_item; } return NULL; } static struct devlink_trap_group_item * devlink_trap_group_item_get_from_info(struct devlink *devlink, struct genl_info *info) { char *name; if (!info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]) return NULL; name = nla_data(info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]); return devlink_trap_group_item_lookup(devlink, name); } static int devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink, const struct devlink_trap_group_item *group_item, enum devlink_command cmd, u32 portid, u32 seq, int flags) { void *hdr; int err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME, group_item->group->name)) goto nla_put_failure; if (group_item->group->generic && nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC)) goto nla_put_failure; if (group_item->policer_item && nla_put_u32(msg, DEVLINK_ATTR_TRAP_POLICER_ID, group_item->policer_item->policer->id)) goto nla_put_failure; err = devlink_trap_group_stats_put(msg, group_item->stats); if (err) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; struct devlink_trap_group_item *group_item; struct sk_buff *msg; int err; if (list_empty(&devlink->trap_group_list)) return -EOPNOTSUPP; group_item = devlink_trap_group_item_get_from_info(devlink, info); if (!group_item) { NL_SET_ERR_MSG(extack, "Device did not register this trap group"); return -ENOENT; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_trap_group_fill(msg, devlink, group_item, DEVLINK_CMD_TRAP_GROUP_NEW, info->snd_portid, info->snd_seq, 0); if (err) goto err_trap_group_fill; return genlmsg_reply(msg, info); err_trap_group_fill: nlmsg_free(msg); return err; } static int devlink_nl_trap_group_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_trap_group_item *group_item; int idx = 0; int err = 0; list_for_each_entry(group_item, &devlink->trap_group_list, list) { if (idx < state->idx) { idx++; continue; } err = devlink_nl_trap_group_fill(msg, devlink, group_item, DEVLINK_CMD_TRAP_GROUP_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) { state->idx = idx; break; } idx++; } return err; } int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_trap_group_get_dump_one); } static int __devlink_trap_group_action_set(struct devlink *devlink, struct devlink_trap_group_item *group_item, enum devlink_trap_action trap_action, struct netlink_ext_ack *extack) { const char *group_name = group_item->group->name; struct devlink_trap_item *trap_item; int err; if (devlink->ops->trap_group_action_set) { err = devlink->ops->trap_group_action_set(devlink, group_item->group, trap_action, extack); if (err) return err; list_for_each_entry(trap_item, &devlink->trap_list, list) { if (strcmp(trap_item->group_item->group->name, group_name)) continue; if (trap_item->action != trap_action && trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) continue; trap_item->action = trap_action; } return 0; } list_for_each_entry(trap_item, &devlink->trap_list, list) { if (strcmp(trap_item->group_item->group->name, group_name)) continue; err = __devlink_trap_action_set(devlink, trap_item, trap_action, extack); if (err) return err; } return 0; } static int devlink_trap_group_action_set(struct devlink *devlink, struct devlink_trap_group_item *group_item, struct genl_info *info, bool *p_modified) { enum devlink_trap_action trap_action; int err; if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION]) return 0; err = devlink_trap_action_get_from_info(info, &trap_action); if (err) { NL_SET_ERR_MSG(info->extack, "Invalid trap action"); return -EINVAL; } err = __devlink_trap_group_action_set(devlink, group_item, trap_action, info->extack); if (err) return err; *p_modified = true; return 0; } static int devlink_trap_group_set(struct devlink *devlink, struct devlink_trap_group_item *group_item, struct genl_info *info) { struct devlink_trap_policer_item *policer_item; struct netlink_ext_ack *extack = info->extack; const struct devlink_trap_policer *policer; struct nlattr **attrs = info->attrs; u32 policer_id; int err; if (!attrs[DEVLINK_ATTR_TRAP_POLICER_ID]) return 0; if (!devlink->ops->trap_group_set) return -EOPNOTSUPP; policer_id = nla_get_u32(attrs[DEVLINK_ATTR_TRAP_POLICER_ID]); policer_item = devlink_trap_policer_item_lookup(devlink, policer_id); if (policer_id && !policer_item) { NL_SET_ERR_MSG(extack, "Device did not register this trap policer"); return -ENOENT; } policer = policer_item ? policer_item->policer : NULL; err = devlink->ops->trap_group_set(devlink, group_item->group, policer, extack); if (err) return err; group_item->policer_item = policer_item; return 0; } int devlink_nl_trap_group_set_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; struct devlink_trap_group_item *group_item; bool modified = false; int err; if (list_empty(&devlink->trap_group_list)) return -EOPNOTSUPP; group_item = devlink_trap_group_item_get_from_info(devlink, info); if (!group_item) { NL_SET_ERR_MSG(extack, "Device did not register this trap group"); return -ENOENT; } err = devlink_trap_group_action_set(devlink, group_item, info, &modified); if (err) return err; err = devlink_trap_group_set(devlink, group_item, info); if (err) goto err_trap_group_set; return 0; err_trap_group_set: if (modified) NL_SET_ERR_MSG(extack, "Trap group set failed, but some changes were committed already"); return err; } static struct devlink_trap_policer_item * devlink_trap_policer_item_get_from_info(struct devlink *devlink, struct genl_info *info) { u32 id; if (!info->attrs[DEVLINK_ATTR_TRAP_POLICER_ID]) return NULL; id = nla_get_u32(info->attrs[DEVLINK_ATTR_TRAP_POLICER_ID]); return devlink_trap_policer_item_lookup(devlink, id); } static int devlink_trap_policer_stats_put(struct sk_buff *msg, struct devlink *devlink, const struct devlink_trap_policer *policer) { struct nlattr *attr; u64 drops; int err; if (!devlink->ops->trap_policer_counter_get) return 0; err = devlink->ops->trap_policer_counter_get(devlink, policer, &drops); if (err) return err; attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); if (!attr) return -EMSGSIZE; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops, DEVLINK_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int devlink_nl_trap_policer_fill(struct sk_buff *msg, struct devlink *devlink, const struct devlink_trap_policer_item *policer_item, enum devlink_command cmd, u32 portid, u32 seq, int flags) { void *hdr; int err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_TRAP_POLICER_ID, policer_item->policer->id)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_TRAP_POLICER_RATE, policer_item->rate, DEVLINK_ATTR_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_TRAP_POLICER_BURST, policer_item->burst, DEVLINK_ATTR_PAD)) goto nla_put_failure; err = devlink_trap_policer_stats_put(msg, devlink, policer_item->policer); if (err) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } int devlink_nl_trap_policer_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_trap_policer_item *policer_item; struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; struct sk_buff *msg; int err; if (list_empty(&devlink->trap_policer_list)) return -EOPNOTSUPP; policer_item = devlink_trap_policer_item_get_from_info(devlink, info); if (!policer_item) { NL_SET_ERR_MSG(extack, "Device did not register this trap policer"); return -ENOENT; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, DEVLINK_CMD_TRAP_POLICER_NEW, info->snd_portid, info->snd_seq, 0); if (err) goto err_trap_policer_fill; return genlmsg_reply(msg, info); err_trap_policer_fill: nlmsg_free(msg); return err; } static int devlink_nl_trap_policer_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_trap_policer_item *policer_item; int idx = 0; int err = 0; list_for_each_entry(policer_item, &devlink->trap_policer_list, list) { if (idx < state->idx) { idx++; continue; } err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, DEVLINK_CMD_TRAP_POLICER_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) { state->idx = idx; break; } idx++; } return err; } int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_trap_policer_get_dump_one); } static int devlink_trap_policer_set(struct devlink *devlink, struct devlink_trap_policer_item *policer_item, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct nlattr **attrs = info->attrs; u64 rate, burst; int err; rate = policer_item->rate; burst = policer_item->burst; if (attrs[DEVLINK_ATTR_TRAP_POLICER_RATE]) rate = nla_get_u64(attrs[DEVLINK_ATTR_TRAP_POLICER_RATE]); if (attrs[DEVLINK_ATTR_TRAP_POLICER_BURST]) burst = nla_get_u64(attrs[DEVLINK_ATTR_TRAP_POLICER_BURST]); if (rate < policer_item->policer->min_rate) { NL_SET_ERR_MSG(extack, "Policer rate lower than limit"); return -EINVAL; } if (rate > policer_item->policer->max_rate) { NL_SET_ERR_MSG(extack, "Policer rate higher than limit"); return -EINVAL; } if (burst < policer_item->policer->min_burst) { NL_SET_ERR_MSG(extack, "Policer burst size lower than limit"); return -EINVAL; } if (burst > policer_item->policer->max_burst) { NL_SET_ERR_MSG(extack, "Policer burst size higher than limit"); return -EINVAL; } err = devlink->ops->trap_policer_set(devlink, policer_item->policer, rate, burst, info->extack); if (err) return err; policer_item->rate = rate; policer_item->burst = burst; return 0; } int devlink_nl_trap_policer_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_trap_policer_item *policer_item; struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; if (list_empty(&devlink->trap_policer_list)) return -EOPNOTSUPP; if (!devlink->ops->trap_policer_set) return -EOPNOTSUPP; policer_item = devlink_trap_policer_item_get_from_info(devlink, info); if (!policer_item) { NL_SET_ERR_MSG(extack, "Device did not register this trap policer"); return -ENOENT; } return devlink_trap_policer_set(devlink, policer_item, info); } #define DEVLINK_TRAP(_id, _type) \ { \ .type = DEVLINK_TRAP_TYPE_##_type, \ .id = DEVLINK_TRAP_GENERIC_ID_##_id, \ .name = DEVLINK_TRAP_GENERIC_NAME_##_id, \ } static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(SMAC_MC, DROP), DEVLINK_TRAP(VLAN_TAG_MISMATCH, DROP), DEVLINK_TRAP(INGRESS_VLAN_FILTER, DROP), DEVLINK_TRAP(INGRESS_STP_FILTER, DROP), DEVLINK_TRAP(EMPTY_TX_LIST, DROP), DEVLINK_TRAP(PORT_LOOPBACK_FILTER, DROP), DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP), DEVLINK_TRAP(TTL_ERROR, EXCEPTION), DEVLINK_TRAP(TAIL_DROP, DROP), DEVLINK_TRAP(NON_IP_PACKET, DROP), DEVLINK_TRAP(UC_DIP_MC_DMAC, DROP), DEVLINK_TRAP(DIP_LB, DROP), DEVLINK_TRAP(SIP_MC, DROP), DEVLINK_TRAP(SIP_LB, DROP), DEVLINK_TRAP(CORRUPTED_IP_HDR, DROP), DEVLINK_TRAP(IPV4_SIP_BC, DROP), DEVLINK_TRAP(IPV6_MC_DIP_RESERVED_SCOPE, DROP), DEVLINK_TRAP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, DROP), DEVLINK_TRAP(MTU_ERROR, EXCEPTION), DEVLINK_TRAP(UNRESOLVED_NEIGH, EXCEPTION), DEVLINK_TRAP(RPF, EXCEPTION), DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION), DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION), DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION), DEVLINK_TRAP(NON_ROUTABLE, DROP), DEVLINK_TRAP(DECAP_ERROR, EXCEPTION), DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP), DEVLINK_TRAP(INGRESS_FLOW_ACTION_DROP, DROP), DEVLINK_TRAP(EGRESS_FLOW_ACTION_DROP, DROP), DEVLINK_TRAP(STP, CONTROL), DEVLINK_TRAP(LACP, CONTROL), DEVLINK_TRAP(LLDP, CONTROL), DEVLINK_TRAP(IGMP_QUERY, CONTROL), DEVLINK_TRAP(IGMP_V1_REPORT, CONTROL), DEVLINK_TRAP(IGMP_V2_REPORT, CONTROL), DEVLINK_TRAP(IGMP_V3_REPORT, CONTROL), DEVLINK_TRAP(IGMP_V2_LEAVE, CONTROL), DEVLINK_TRAP(MLD_QUERY, CONTROL), DEVLINK_TRAP(MLD_V1_REPORT, CONTROL), DEVLINK_TRAP(MLD_V2_REPORT, CONTROL), DEVLINK_TRAP(MLD_V1_DONE, CONTROL), DEVLINK_TRAP(IPV4_DHCP, CONTROL), DEVLINK_TRAP(IPV6_DHCP, CONTROL), DEVLINK_TRAP(ARP_REQUEST, CONTROL), DEVLINK_TRAP(ARP_RESPONSE, CONTROL), DEVLINK_TRAP(ARP_OVERLAY, CONTROL), DEVLINK_TRAP(IPV6_NEIGH_SOLICIT, CONTROL), DEVLINK_TRAP(IPV6_NEIGH_ADVERT, CONTROL), DEVLINK_TRAP(IPV4_BFD, CONTROL), DEVLINK_TRAP(IPV6_BFD, CONTROL), DEVLINK_TRAP(IPV4_OSPF, CONTROL), DEVLINK_TRAP(IPV6_OSPF, CONTROL), DEVLINK_TRAP(IPV4_BGP, CONTROL), DEVLINK_TRAP(IPV6_BGP, CONTROL), DEVLINK_TRAP(IPV4_VRRP, CONTROL), DEVLINK_TRAP(IPV6_VRRP, CONTROL), DEVLINK_TRAP(IPV4_PIM, CONTROL), DEVLINK_TRAP(IPV6_PIM, CONTROL), DEVLINK_TRAP(UC_LB, CONTROL), DEVLINK_TRAP(LOCAL_ROUTE, CONTROL), DEVLINK_TRAP(EXTERNAL_ROUTE, CONTROL), DEVLINK_TRAP(IPV6_UC_DIP_LINK_LOCAL_SCOPE, CONTROL), DEVLINK_TRAP(IPV6_DIP_ALL_NODES, CONTROL), DEVLINK_TRAP(IPV6_DIP_ALL_ROUTERS, CONTROL), DEVLINK_TRAP(IPV6_ROUTER_SOLICIT, CONTROL), DEVLINK_TRAP(IPV6_ROUTER_ADVERT, CONTROL), DEVLINK_TRAP(IPV6_REDIRECT, CONTROL), DEVLINK_TRAP(IPV4_ROUTER_ALERT, CONTROL), DEVLINK_TRAP(IPV6_ROUTER_ALERT, CONTROL), DEVLINK_TRAP(PTP_EVENT, CONTROL), DEVLINK_TRAP(PTP_GENERAL, CONTROL), DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL), DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL), DEVLINK_TRAP(EARLY_DROP, DROP), DEVLINK_TRAP(VXLAN_PARSING, DROP), DEVLINK_TRAP(LLC_SNAP_PARSING, DROP), DEVLINK_TRAP(VLAN_PARSING, DROP), DEVLINK_TRAP(PPPOE_PPP_PARSING, DROP), DEVLINK_TRAP(MPLS_PARSING, DROP), DEVLINK_TRAP(ARP_PARSING, DROP), DEVLINK_TRAP(IP_1_PARSING, DROP), DEVLINK_TRAP(IP_N_PARSING, DROP), DEVLINK_TRAP(GRE_PARSING, DROP), DEVLINK_TRAP(UDP_PARSING, DROP), DEVLINK_TRAP(TCP_PARSING, DROP), DEVLINK_TRAP(IPSEC_PARSING, DROP), DEVLINK_TRAP(SCTP_PARSING, DROP), DEVLINK_TRAP(DCCP_PARSING, DROP), DEVLINK_TRAP(GTP_PARSING, DROP), DEVLINK_TRAP(ESP_PARSING, DROP), DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP), DEVLINK_TRAP(DMAC_FILTER, DROP), DEVLINK_TRAP(EAPOL, CONTROL), DEVLINK_TRAP(LOCKED_PORT, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ { \ .id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id, \ .name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id, \ } static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(L2_DROPS), DEVLINK_TRAP_GROUP(L3_DROPS), DEVLINK_TRAP_GROUP(L3_EXCEPTIONS), DEVLINK_TRAP_GROUP(BUFFER_DROPS), DEVLINK_TRAP_GROUP(TUNNEL_DROPS), DEVLINK_TRAP_GROUP(ACL_DROPS), DEVLINK_TRAP_GROUP(STP), DEVLINK_TRAP_GROUP(LACP), DEVLINK_TRAP_GROUP(LLDP), DEVLINK_TRAP_GROUP(MC_SNOOPING), DEVLINK_TRAP_GROUP(DHCP), DEVLINK_TRAP_GROUP(NEIGH_DISCOVERY), DEVLINK_TRAP_GROUP(BFD), DEVLINK_TRAP_GROUP(OSPF), DEVLINK_TRAP_GROUP(BGP), DEVLINK_TRAP_GROUP(VRRP), DEVLINK_TRAP_GROUP(PIM), DEVLINK_TRAP_GROUP(UC_LB), DEVLINK_TRAP_GROUP(LOCAL_DELIVERY), DEVLINK_TRAP_GROUP(EXTERNAL_DELIVERY), DEVLINK_TRAP_GROUP(IPV6), DEVLINK_TRAP_GROUP(PTP_EVENT), DEVLINK_TRAP_GROUP(PTP_GENERAL), DEVLINK_TRAP_GROUP(ACL_SAMPLE), DEVLINK_TRAP_GROUP(ACL_TRAP), DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS), DEVLINK_TRAP_GROUP(EAPOL), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) { if (trap->id > DEVLINK_TRAP_GENERIC_ID_MAX) return -EINVAL; if (strcmp(trap->name, devlink_trap_generic[trap->id].name)) return -EINVAL; if (trap->type != devlink_trap_generic[trap->id].type) return -EINVAL; return 0; } static int devlink_trap_driver_verify(const struct devlink_trap *trap) { int i; if (trap->id <= DEVLINK_TRAP_GENERIC_ID_MAX) return -EINVAL; for (i = 0; i < ARRAY_SIZE(devlink_trap_generic); i++) { if (!strcmp(trap->name, devlink_trap_generic[i].name)) return -EEXIST; } return 0; } static int devlink_trap_verify(const struct devlink_trap *trap) { if (!trap || !trap->name) return -EINVAL; if (trap->generic) return devlink_trap_generic_verify(trap); else return devlink_trap_driver_verify(trap); } static int devlink_trap_group_generic_verify(const struct devlink_trap_group *group) { if (group->id > DEVLINK_TRAP_GROUP_GENERIC_ID_MAX) return -EINVAL; if (strcmp(group->name, devlink_trap_group_generic[group->id].name)) return -EINVAL; return 0; } static int devlink_trap_group_driver_verify(const struct devlink_trap_group *group) { int i; if (group->id <= DEVLINK_TRAP_GROUP_GENERIC_ID_MAX) return -EINVAL; for (i = 0; i < ARRAY_SIZE(devlink_trap_group_generic); i++) { if (!strcmp(group->name, devlink_trap_group_generic[i].name)) return -EEXIST; } return 0; } static int devlink_trap_group_verify(const struct devlink_trap_group *group) { if (group->generic) return devlink_trap_group_generic_verify(group); else return devlink_trap_group_driver_verify(group); } static void devlink_trap_group_notify(struct devlink *devlink, const struct devlink_trap_group_item *group_item, enum devlink_command cmd) { struct sk_buff *msg; int err; WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW && cmd != DEVLINK_CMD_TRAP_GROUP_DEL); if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_trap_group_fill(msg, devlink, group_item, cmd, 0, 0, 0); if (err) { nlmsg_free(msg); return; } devlink_nl_notify_send(devlink, msg); } void devlink_trap_groups_notify_register(struct devlink *devlink) { struct devlink_trap_group_item *group_item; list_for_each_entry(group_item, &devlink->trap_group_list, list) devlink_trap_group_notify(devlink, group_item, DEVLINK_CMD_TRAP_GROUP_NEW); } void devlink_trap_groups_notify_unregister(struct devlink *devlink) { struct devlink_trap_group_item *group_item; list_for_each_entry_reverse(group_item, &devlink->trap_group_list, list) devlink_trap_group_notify(devlink, group_item, DEVLINK_CMD_TRAP_GROUP_DEL); } static int devlink_trap_item_group_link(struct devlink *devlink, struct devlink_trap_item *trap_item) { u16 group_id = trap_item->trap->init_group_id; struct devlink_trap_group_item *group_item; group_item = devlink_trap_group_item_lookup_by_id(devlink, group_id); if (WARN_ON_ONCE(!group_item)) return -EINVAL; trap_item->group_item = group_item; return 0; } static void devlink_trap_notify(struct devlink *devlink, const struct devlink_trap_item *trap_item, enum devlink_command cmd) { struct sk_buff *msg; int err; WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW && cmd != DEVLINK_CMD_TRAP_DEL); if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_trap_fill(msg, devlink, trap_item, cmd, 0, 0, 0); if (err) { nlmsg_free(msg); return; } devlink_nl_notify_send(devlink, msg); } void devlink_traps_notify_register(struct devlink *devlink) { struct devlink_trap_item *trap_item; list_for_each_entry(trap_item, &devlink->trap_list, list) devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW); } void devlink_traps_notify_unregister(struct devlink *devlink) { struct devlink_trap_item *trap_item; list_for_each_entry_reverse(trap_item, &devlink->trap_list, list) devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL); } static int devlink_trap_register(struct devlink *devlink, const struct devlink_trap *trap, void *priv) { struct devlink_trap_item *trap_item; int err; if (devlink_trap_item_lookup(devlink, trap->name)) return -EEXIST; trap_item = kzalloc(sizeof(*trap_item), GFP_KERNEL); if (!trap_item) return -ENOMEM; trap_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats); if (!trap_item->stats) { err = -ENOMEM; goto err_stats_alloc; } trap_item->trap = trap; trap_item->action = trap->init_action; trap_item->priv = priv; err = devlink_trap_item_group_link(devlink, trap_item); if (err) goto err_group_link; err = devlink->ops->trap_init(devlink, trap, trap_item); if (err) goto err_trap_init; list_add_tail(&trap_item->list, &devlink->trap_list); devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW); return 0; err_trap_init: err_group_link: free_percpu(trap_item->stats); err_stats_alloc: kfree(trap_item); return err; } static void devlink_trap_unregister(struct devlink *devlink, const struct devlink_trap *trap) { struct devlink_trap_item *trap_item; trap_item = devlink_trap_item_lookup(devlink, trap->name); if (WARN_ON_ONCE(!trap_item)) return; devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL); list_del(&trap_item->list); if (devlink->ops->trap_fini) devlink->ops->trap_fini(devlink, trap, trap_item); free_percpu(trap_item->stats); kfree(trap_item); } static void devlink_trap_disable(struct devlink *devlink, const struct devlink_trap *trap) { struct devlink_trap_item *trap_item; trap_item = devlink_trap_item_lookup(devlink, trap->name); if (WARN_ON_ONCE(!trap_item)) return; devlink->ops->trap_action_set(devlink, trap, DEVLINK_TRAP_ACTION_DROP, NULL); trap_item->action = DEVLINK_TRAP_ACTION_DROP; } /** * devl_traps_register - Register packet traps with devlink. * @devlink: devlink. * @traps: Packet traps. * @traps_count: Count of provided packet traps. * @priv: Driver private information. * * Return: Non-zero value on failure. */ int devl_traps_register(struct devlink *devlink, const struct devlink_trap *traps, size_t traps_count, void *priv) { int i, err; if (!devlink->ops->trap_init || !devlink->ops->trap_action_set) return -EINVAL; devl_assert_locked(devlink); for (i = 0; i < traps_count; i++) { const struct devlink_trap *trap = &traps[i]; err = devlink_trap_verify(trap); if (err) goto err_trap_verify; err = devlink_trap_register(devlink, trap, priv); if (err) goto err_trap_register; } return 0; err_trap_register: err_trap_verify: for (i--; i >= 0; i--) devlink_trap_unregister(devlink, &traps[i]); return err; } EXPORT_SYMBOL_GPL(devl_traps_register); /** * devlink_traps_register - Register packet traps with devlink. * @devlink: devlink. * @traps: Packet traps. * @traps_count: Count of provided packet traps. * @priv: Driver private information. * * Context: Takes and release devlink->lock <mutex>. * * Return: Non-zero value on failure. */ int devlink_traps_register(struct devlink *devlink, const struct devlink_trap *traps, size_t traps_count, void *priv) { int err; devl_lock(devlink); err = devl_traps_register(devlink, traps, traps_count, priv); devl_unlock(devlink); return err; } EXPORT_SYMBOL_GPL(devlink_traps_register); /** * devl_traps_unregister - Unregister packet traps from devlink. * @devlink: devlink. * @traps: Packet traps. * @traps_count: Count of provided packet traps. */ void devl_traps_unregister(struct devlink *devlink, const struct devlink_trap *traps, size_t traps_count) { int i; devl_assert_locked(devlink); /* Make sure we do not have any packets in-flight while unregistering * traps by disabling all of them and waiting for a grace period. */ for (i = traps_count - 1; i >= 0; i--) devlink_trap_disable(devlink, &traps[i]); synchronize_rcu(); for (i = traps_count - 1; i >= 0; i--) devlink_trap_unregister(devlink, &traps[i]); } EXPORT_SYMBOL_GPL(devl_traps_unregister); /** * devlink_traps_unregister - Unregister packet traps from devlink. * @devlink: devlink. * @traps: Packet traps. * @traps_count: Count of provided packet traps. * * Context: Takes and release devlink->lock <mutex>. */ void devlink_traps_unregister(struct devlink *devlink, const struct devlink_trap *traps, size_t traps_count) { devl_lock(devlink); devl_traps_unregister(devlink, traps, traps_count); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_traps_unregister); static void devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, size_t skb_len) { struct devlink_stats *stats; stats = this_cpu_ptr(trap_stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->rx_bytes, skb_len); u64_stats_inc(&stats->rx_packets); u64_stats_update_end(&stats->syncp); } static void devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata, const struct devlink_trap_item *trap_item, struct devlink_port *in_devlink_port, const struct flow_action_cookie *fa_cookie) { metadata->trap_name = trap_item->trap->name; metadata->trap_group_name = trap_item->group_item->group->name; metadata->fa_cookie = fa_cookie; metadata->trap_type = trap_item->trap->type; spin_lock(&in_devlink_port->type_lock); if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) metadata->input_dev = in_devlink_port->type_eth.netdev; spin_unlock(&in_devlink_port->type_lock); } /** * devlink_trap_report - Report trapped packet to drop monitor. * @devlink: devlink. * @skb: Trapped packet. * @trap_ctx: Trap context. * @in_devlink_port: Input devlink port. * @fa_cookie: Flow action cookie. Could be NULL. */ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, void *trap_ctx, struct devlink_port *in_devlink_port, const struct flow_action_cookie *fa_cookie) { struct devlink_trap_item *trap_item = trap_ctx; devlink_trap_stats_update(trap_item->stats, skb->len); devlink_trap_stats_update(trap_item->group_item->stats, skb->len); if (tracepoint_enabled(devlink_trap_report)) { struct devlink_trap_metadata metadata = {}; devlink_trap_report_metadata_set(&metadata, trap_item, in_devlink_port, fa_cookie); trace_devlink_trap_report(devlink, skb, &metadata); } } EXPORT_SYMBOL_GPL(devlink_trap_report); /** * devlink_trap_ctx_priv - Trap context to driver private information. * @trap_ctx: Trap context. * * Return: Driver private information passed during registration. */ void *devlink_trap_ctx_priv(void *trap_ctx) { struct devlink_trap_item *trap_item = trap_ctx; return trap_item->priv; } EXPORT_SYMBOL_GPL(devlink_trap_ctx_priv); static int devlink_trap_group_item_policer_link(struct devlink *devlink, struct devlink_trap_group_item *group_item) { u32 policer_id = group_item->group->init_policer_id; struct devlink_trap_policer_item *policer_item; if (policer_id == 0) return 0; policer_item = devlink_trap_policer_item_lookup(devlink, policer_id); if (WARN_ON_ONCE(!policer_item)) return -EINVAL; group_item->policer_item = policer_item; return 0; } static int devlink_trap_group_register(struct devlink *devlink, const struct devlink_trap_group *group) { struct devlink_trap_group_item *group_item; int err; if (devlink_trap_group_item_lookup(devlink, group->name)) return -EEXIST; group_item = kzalloc(sizeof(*group_item), GFP_KERNEL); if (!group_item) return -ENOMEM; group_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats); if (!group_item->stats) { err = -ENOMEM; goto err_stats_alloc; } group_item->group = group; err = devlink_trap_group_item_policer_link(devlink, group_item); if (err) goto err_policer_link; if (devlink->ops->trap_group_init) { err = devlink->ops->trap_group_init(devlink, group); if (err) goto err_group_init; } list_add_tail(&group_item->list, &devlink->trap_group_list); devlink_trap_group_notify(devlink, group_item, DEVLINK_CMD_TRAP_GROUP_NEW); return 0; err_group_init: err_policer_link: free_percpu(group_item->stats); err_stats_alloc: kfree(group_item); return err; } static void devlink_trap_group_unregister(struct devlink *devlink, const struct devlink_trap_group *group) { struct devlink_trap_group_item *group_item; group_item = devlink_trap_group_item_lookup(devlink, group->name); if (WARN_ON_ONCE(!group_item)) return; devlink_trap_group_notify(devlink, group_item, DEVLINK_CMD_TRAP_GROUP_DEL); list_del(&group_item->list); free_percpu(group_item->stats); kfree(group_item); } /** * devl_trap_groups_register - Register packet trap groups with devlink. * @devlink: devlink. * @groups: Packet trap groups. * @groups_count: Count of provided packet trap groups. * * Return: Non-zero value on failure. */ int devl_trap_groups_register(struct devlink *devlink, const struct devlink_trap_group *groups, size_t groups_count) { int i, err; devl_assert_locked(devlink); for (i = 0; i < groups_count; i++) { const struct devlink_trap_group *group = &groups[i]; err = devlink_trap_group_verify(group); if (err) goto err_trap_group_verify; err = devlink_trap_group_register(devlink, group); if (err) goto err_trap_group_register; } return 0; err_trap_group_register: err_trap_group_verify: for (i--; i >= 0; i--) devlink_trap_group_unregister(devlink, &groups[i]); return err; } EXPORT_SYMBOL_GPL(devl_trap_groups_register); /** * devlink_trap_groups_register - Register packet trap groups with devlink. * @devlink: devlink. * @groups: Packet trap groups. * @groups_count: Count of provided packet trap groups. * * Context: Takes and release devlink->lock <mutex>. * * Return: Non-zero value on failure. */ int devlink_trap_groups_register(struct devlink *devlink, const struct devlink_trap_group *groups, size_t groups_count) { int err; devl_lock(devlink); err = devl_trap_groups_register(devlink, groups, groups_count); devl_unlock(devlink); return err; } EXPORT_SYMBOL_GPL(devlink_trap_groups_register); /** * devl_trap_groups_unregister - Unregister packet trap groups from devlink. * @devlink: devlink. * @groups: Packet trap groups. * @groups_count: Count of provided packet trap groups. */ void devl_trap_groups_unregister(struct devlink *devlink, const struct devlink_trap_group *groups, size_t groups_count) { int i; devl_assert_locked(devlink); for (i = groups_count - 1; i >= 0; i--) devlink_trap_group_unregister(devlink, &groups[i]); } EXPORT_SYMBOL_GPL(devl_trap_groups_unregister); /** * devlink_trap_groups_unregister - Unregister packet trap groups from devlink. * @devlink: devlink. * @groups: Packet trap groups. * @groups_count: Count of provided packet trap groups. * * Context: Takes and release devlink->lock <mutex>. */ void devlink_trap_groups_unregister(struct devlink *devlink, const struct devlink_trap_group *groups, size_t groups_count) { devl_lock(devlink); devl_trap_groups_unregister(devlink, groups, groups_count); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_trap_groups_unregister); static void devlink_trap_policer_notify(struct devlink *devlink, const struct devlink_trap_policer_item *policer_item, enum devlink_command cmd) { struct sk_buff *msg; int err; WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_POLICER_NEW && cmd != DEVLINK_CMD_TRAP_POLICER_DEL); if (!devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_trap_policer_fill(msg, devlink, policer_item, cmd, 0, 0, 0); if (err) { nlmsg_free(msg); return; } devlink_nl_notify_send(devlink, msg); } void devlink_trap_policers_notify_register(struct devlink *devlink) { struct devlink_trap_policer_item *policer_item; list_for_each_entry(policer_item, &devlink->trap_policer_list, list) devlink_trap_policer_notify(devlink, policer_item, DEVLINK_CMD_TRAP_POLICER_NEW); } void devlink_trap_policers_notify_unregister(struct devlink *devlink) { struct devlink_trap_policer_item *policer_item; list_for_each_entry_reverse(policer_item, &devlink->trap_policer_list, list) devlink_trap_policer_notify(devlink, policer_item, DEVLINK_CMD_TRAP_POLICER_DEL); } static int devlink_trap_policer_register(struct devlink *devlink, const struct devlink_trap_policer *policer) { struct devlink_trap_policer_item *policer_item; int err; if (devlink_trap_policer_item_lookup(devlink, policer->id)) return -EEXIST; policer_item = kzalloc(sizeof(*policer_item), GFP_KERNEL); if (!policer_item) return -ENOMEM; policer_item->policer = policer; policer_item->rate = policer->init_rate; policer_item->burst = policer->init_burst; if (devlink->ops->trap_policer_init) { err = devlink->ops->trap_policer_init(devlink, policer); if (err) goto err_policer_init; } list_add_tail(&policer_item->list, &devlink->trap_policer_list); devlink_trap_policer_notify(devlink, policer_item, DEVLINK_CMD_TRAP_POLICER_NEW); return 0; err_policer_init: kfree(policer_item); return err; } static void devlink_trap_policer_unregister(struct devlink *devlink, const struct devlink_trap_policer *policer) { struct devlink_trap_policer_item *policer_item; policer_item = devlink_trap_policer_item_lookup(devlink, policer->id); if (WARN_ON_ONCE(!policer_item)) return; devlink_trap_policer_notify(devlink, policer_item, DEVLINK_CMD_TRAP_POLICER_DEL); list_del(&policer_item->list); if (devlink->ops->trap_policer_fini) devlink->ops->trap_policer_fini(devlink, policer); kfree(policer_item); } /** * devl_trap_policers_register - Register packet trap policers with devlink. * @devlink: devlink. * @policers: Packet trap policers. * @policers_count: Count of provided packet trap policers. * * Return: Non-zero value on failure. */ int devl_trap_policers_register(struct devlink *devlink, const struct devlink_trap_policer *policers, size_t policers_count) { int i, err; devl_assert_locked(devlink); for (i = 0; i < policers_count; i++) { const struct devlink_trap_policer *policer = &policers[i]; if (WARN_ON(policer->id == 0 || policer->max_rate < policer->min_rate || policer->max_burst < policer->min_burst)) { err = -EINVAL; goto err_trap_policer_verify; } err = devlink_trap_policer_register(devlink, policer); if (err) goto err_trap_policer_register; } return 0; err_trap_policer_register: err_trap_policer_verify: for (i--; i >= 0; i--) devlink_trap_policer_unregister(devlink, &policers[i]); return err; } EXPORT_SYMBOL_GPL(devl_trap_policers_register); /** * devl_trap_policers_unregister - Unregister packet trap policers from devlink. * @devlink: devlink. * @policers: Packet trap policers. * @policers_count: Count of provided packet trap policers. */ void devl_trap_policers_unregister(struct devlink *devlink, const struct devlink_trap_policer *policers, size_t policers_count) { int i; devl_assert_locked(devlink); for (i = policers_count - 1; i >= 0; i--) devlink_trap_policer_unregister(devlink, &policers[i]); } EXPORT_SYMBOL_GPL(devl_trap_policers_unregister); |
| 22 9984 52 11442 3942 5 32 7442 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * kref.h - library routines for handling generic reference counted objects * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Corp. * * based on kobject.h which was: * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (C) 2002-2003 Open Source Development Labs */ #ifndef _KREF_H_ #define _KREF_H_ #include <linux/spinlock.h> #include <linux/refcount.h> struct kref { refcount_t refcount; }; #define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { refcount_set(&kref->refcount, 1); } static inline unsigned int kref_read(const struct kref *kref) { return refcount_read(&kref->refcount); } /** * kref_get - increment refcount for object. * @kref: object. */ static inline void kref_get(struct kref *kref) { refcount_inc(&kref->refcount); } /** * kref_put - decrement refcount for object. * @kref: object. * @release: pointer to the function that will clean up the object when the * last reference to the object is released. * This pointer is required, and it is not acceptable to pass kfree * in as this function. * * Decrement the refcount, and if 0, call release(). * Return 1 if the object was removed, otherwise return 0. Beware, if this * function returns 0, you still can not count on the kref from remaining in * memory. Only use the return value if you want to see if the kref is now * gone, not present. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { if (refcount_dec_and_test(&kref->refcount)) { release(kref); return 1; } return 0; } static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) { if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } static inline int kref_put_lock(struct kref *kref, void (*release)(struct kref *kref), spinlock_t *lock) { if (refcount_dec_and_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } /** * kref_get_unless_zero - Increment refcount for object unless it is zero. * @kref: object. * * Return non-zero if the increment succeeded. Otherwise return 0. * * This function is intended to simplify locking around refcounting for * objects that can be looked up from a lookup structure, and which are * removed from that lookup structure in the object destructor. * Operations on such objects require at least a read lock around * lookup + kref_get, and a write lock around kref_put + remove from lookup * structure. Furthermore, RCU implementations become extremely tricky. * With a lookup followed by a kref_get_unless_zero *with return value check* * locking in the kref_put path can be deferred to the actual removal from * the lookup structure and RCU lookups become trivial. */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { return refcount_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 | /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * include/uapi/linux/tipc_config.h: Header for TIPC configuration interface * * Copyright (c) 2003-2006, Ericsson AB * Copyright (c) 2005-2007, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _LINUX_TIPC_CONFIG_H_ #define _LINUX_TIPC_CONFIG_H_ #include <linux/types.h> #include <linux/string.h> #include <linux/tipc.h> #include <asm/byteorder.h> /* * Configuration * * All configuration management messaging involves sending a request message * to the TIPC configuration service on a node, which sends a reply message * back. (In the future multi-message replies may be supported.) * * Both request and reply messages consist of a transport header and payload. * The transport header contains info about the desired operation; * the payload consists of zero or more type/length/value (TLV) items * which specify parameters or results for the operation. * * For many operations, the request and reply messages have a fixed number * of TLVs (usually zero or one); however, some reply messages may return * a variable number of TLVs. A failed request is denoted by the presence * of an "error string" TLV in the reply message instead of the TLV(s) the * reply should contain if the request succeeds. */ /* * Public commands: * May be issued by any process. * Accepted by own node, or by remote node only if remote management enabled. */ #define TIPC_CMD_NOOP 0x0000 /* tx none, rx none */ #define TIPC_CMD_GET_NODES 0x0001 /* tx net_addr, rx node_info(s) */ #define TIPC_CMD_GET_MEDIA_NAMES 0x0002 /* tx none, rx media_name(s) */ #define TIPC_CMD_GET_BEARER_NAMES 0x0003 /* tx none, rx bearer_name(s) */ #define TIPC_CMD_GET_LINKS 0x0004 /* tx net_addr, rx link_info(s) */ #define TIPC_CMD_SHOW_NAME_TABLE 0x0005 /* tx name_tbl_query, rx ultra_string */ #define TIPC_CMD_SHOW_PORTS 0x0006 /* tx none, rx ultra_string */ #define TIPC_CMD_SHOW_LINK_STATS 0x000B /* tx link_name, rx ultra_string */ #define TIPC_CMD_SHOW_STATS 0x000F /* tx unsigned, rx ultra_string */ /* * Protected commands: * May only be issued by "network administration capable" process. * Accepted by own node, or by remote node only if remote management enabled * and this node is zone manager. */ #define TIPC_CMD_GET_REMOTE_MNG 0x4003 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_PORTS 0x4004 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_PUBL 0x4005 /* obsoleted */ #define TIPC_CMD_GET_MAX_SUBSCR 0x4006 /* obsoleted */ #define TIPC_CMD_GET_MAX_ZONES 0x4007 /* obsoleted */ #define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* obsoleted */ #define TIPC_CMD_GET_MAX_NODES 0x4009 /* obsoleted */ #define TIPC_CMD_GET_MAX_SLAVES 0x400A /* obsoleted */ #define TIPC_CMD_GET_NETID 0x400B /* tx none, rx unsigned */ #define TIPC_CMD_ENABLE_BEARER 0x4101 /* tx bearer_config, rx none */ #define TIPC_CMD_DISABLE_BEARER 0x4102 /* tx bearer_name, rx none */ #define TIPC_CMD_SET_LINK_TOL 0x4107 /* tx link_config, rx none */ #define TIPC_CMD_SET_LINK_PRI 0x4108 /* tx link_config, rx none */ #define TIPC_CMD_SET_LINK_WINDOW 0x4109 /* tx link_config, rx none */ #define TIPC_CMD_SET_LOG_SIZE 0x410A /* obsoleted */ #define TIPC_CMD_DUMP_LOG 0x410B /* obsoleted */ #define TIPC_CMD_RESET_LINK_STATS 0x410C /* tx link_name, rx none */ /* * Private commands: * May only be issued by "network administration capable" process. * Accepted by own node only; cannot be used on a remote node. */ #define TIPC_CMD_SET_NODE_ADDR 0x8001 /* tx net_addr, rx none */ #define TIPC_CMD_SET_REMOTE_MNG 0x8003 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PORTS 0x8004 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PUBL 0x8005 /* obsoleted */ #define TIPC_CMD_SET_MAX_SUBSCR 0x8006 /* obsoleted */ #define TIPC_CMD_SET_MAX_ZONES 0x8007 /* obsoleted */ #define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* obsoleted */ #define TIPC_CMD_SET_MAX_NODES 0x8009 /* obsoleted */ #define TIPC_CMD_SET_MAX_SLAVES 0x800A /* obsoleted */ #define TIPC_CMD_SET_NETID 0x800B /* tx unsigned, rx none */ /* * Reserved commands: * May not be issued by any process. * Used internally by TIPC. */ #define TIPC_CMD_NOT_NET_ADMIN 0xC001 /* tx none, rx none */ /* * TLV types defined for TIPC */ #define TIPC_TLV_NONE 0 /* no TLV present */ #define TIPC_TLV_VOID 1 /* empty TLV (0 data bytes)*/ #define TIPC_TLV_UNSIGNED 2 /* 32-bit integer */ #define TIPC_TLV_STRING 3 /* char[128] (max) */ #define TIPC_TLV_LARGE_STRING 4 /* char[2048] (max) */ #define TIPC_TLV_ULTRA_STRING 5 /* char[32768] (max) */ #define TIPC_TLV_ERROR_STRING 16 /* char[128] containing "error code" */ #define TIPC_TLV_NET_ADDR 17 /* 32-bit integer denoting <Z.C.N> */ #define TIPC_TLV_MEDIA_NAME 18 /* char[TIPC_MAX_MEDIA_NAME] */ #define TIPC_TLV_BEARER_NAME 19 /* char[TIPC_MAX_BEARER_NAME] */ #define TIPC_TLV_LINK_NAME 20 /* char[TIPC_MAX_LINK_NAME] */ #define TIPC_TLV_NODE_INFO 21 /* struct tipc_node_info */ #define TIPC_TLV_LINK_INFO 22 /* struct tipc_link_info */ #define TIPC_TLV_BEARER_CONFIG 23 /* struct tipc_bearer_config */ #define TIPC_TLV_LINK_CONFIG 24 /* struct tipc_link_config */ #define TIPC_TLV_NAME_TBL_QUERY 25 /* struct tipc_name_table_query */ #define TIPC_TLV_PORT_REF 26 /* 32-bit port reference */ /* * Link priority limits (min, default, max, media default) */ #define TIPC_MIN_LINK_PRI 0 #define TIPC_DEF_LINK_PRI 10 #define TIPC_MAX_LINK_PRI 31 #define TIPC_MEDIA_LINK_PRI (TIPC_MAX_LINK_PRI + 1) /* * Link tolerance limits (min, default, max), in ms */ #define TIPC_MIN_LINK_TOL 50 #define TIPC_DEF_LINK_TOL 1500 #define TIPC_MAX_LINK_TOL 30000 #if (TIPC_MIN_LINK_TOL < 16) #error "TIPC_MIN_LINK_TOL is too small (abort limit may be NaN)" #endif /* * Link window limits (min, default, max), in packets */ #define TIPC_MIN_LINK_WIN 16 #define TIPC_DEF_LINK_WIN 50 #define TIPC_MAX_LINK_WIN 8191 /* * Default MTU for UDP media */ #define TIPC_DEF_LINK_UDP_MTU 14000 struct tipc_node_info { __be32 addr; /* network address of node */ __be32 up; /* 0=down, 1= up */ }; struct tipc_link_info { __be32 dest; /* network address of peer node */ __be32 up; /* 0=down, 1=up */ char str[TIPC_MAX_LINK_NAME]; /* link name */ }; struct tipc_bearer_config { __be32 priority; /* Range [1,31]. Override per link */ __be32 disc_domain; /* <Z.C.N> describing desired nodes */ char name[TIPC_MAX_BEARER_NAME]; }; struct tipc_link_config { __be32 value; char name[TIPC_MAX_LINK_NAME]; }; #define TIPC_NTQ_ALLTYPES 0x80000000 struct tipc_name_table_query { __be32 depth; /* 1:type, 2:+name info, 3:+port info, 4+:+debug info */ __be32 type; /* {t,l,u} info ignored if high bit of "depth" is set */ __be32 lowbound; /* (i.e. displays all entries of name table) */ __be32 upbound; }; /* * The error string TLV is a null-terminated string describing the cause * of the request failure. To simplify error processing (and to save space) * the first character of the string can be a special error code character * (lying by the range 0x80 to 0xFF) which represents a pre-defined reason. */ #define TIPC_CFG_TLV_ERROR "\x80" /* request contains incorrect TLV(s) */ #define TIPC_CFG_NOT_NET_ADMIN "\x81" /* must be network administrator */ #define TIPC_CFG_NOT_ZONE_MSTR "\x82" /* must be zone master */ #define TIPC_CFG_NO_REMOTE "\x83" /* remote management not enabled */ #define TIPC_CFG_NOT_SUPPORTED "\x84" /* request is not supported by TIPC */ #define TIPC_CFG_INVALID_VALUE "\x85" /* request has invalid argument value */ /* * A TLV consists of a descriptor, followed by the TLV value. * TLV descriptor fields are stored in network byte order; * TLV values must also be stored in network byte order (where applicable). * TLV descriptors must be aligned to addresses which are multiple of 4, * so up to 3 bytes of padding may exist at the end of the TLV value area. * There must not be any padding between the TLV descriptor and its value. */ struct tlv_desc { __be16 tlv_len; /* TLV length (descriptor + value) */ __be16 tlv_type; /* TLV identifier */ }; #define TLV_ALIGNTO 4 #define TLV_ALIGN(datalen) (((datalen)+(TLV_ALIGNTO-1)) & ~(TLV_ALIGNTO-1)) #define TLV_LENGTH(datalen) (sizeof(struct tlv_desc) + (datalen)) #define TLV_SPACE(datalen) (TLV_ALIGN(TLV_LENGTH(datalen))) #define TLV_DATA(tlv) ((void *)((char *)(tlv) + TLV_LENGTH(0))) static inline int TLV_OK(const void *tlv, __u16 space) { /* * Would also like to check that "tlv" is a multiple of 4, * but don't know how to do this in a portable way. * - Tried doing (!(tlv & (TLV_ALIGNTO-1))), but GCC compiler * won't allow binary "&" with a pointer. * - Tried casting "tlv" to integer type, but causes warning about size * mismatch when pointer is bigger than chosen type (int, long, ...). */ return (space >= TLV_SPACE(0)) && (__be16_to_cpu(((struct tlv_desc *)tlv)->tlv_len) <= space); } static inline int TLV_CHECK(const void *tlv, __u16 space, __u16 exp_type) { return TLV_OK(tlv, space) && (__be16_to_cpu(((struct tlv_desc *)tlv)->tlv_type) == exp_type); } static inline int TLV_GET_LEN(struct tlv_desc *tlv) { return __be16_to_cpu(tlv->tlv_len); } static inline void TLV_SET_LEN(struct tlv_desc *tlv, __u16 len) { tlv->tlv_len = __cpu_to_be16(len); } static inline int TLV_CHECK_TYPE(struct tlv_desc *tlv, __u16 type) { return (__be16_to_cpu(tlv->tlv_type) == type); } static inline void TLV_SET_TYPE(struct tlv_desc *tlv, __u16 type) { tlv->tlv_type = __cpu_to_be16(type); } static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len) { struct tlv_desc *tlv_ptr; int tlv_len; tlv_len = TLV_LENGTH(len); tlv_ptr = (struct tlv_desc *)tlv; tlv_ptr->tlv_type = __cpu_to_be16(type); tlv_ptr->tlv_len = __cpu_to_be16(tlv_len); if (len && data) { memcpy(TLV_DATA(tlv_ptr), data, len); memset((char *)TLV_DATA(tlv_ptr) + len, 0, TLV_SPACE(len) - tlv_len); } return TLV_SPACE(len); } /* * A TLV list descriptor simplifies processing of messages * containing multiple TLVs. */ struct tlv_list_desc { struct tlv_desc *tlv_ptr; /* ptr to current TLV */ __u32 tlv_space; /* # bytes from curr TLV to list end */ }; static inline void TLV_LIST_INIT(struct tlv_list_desc *list, void *data, __u32 space) { list->tlv_ptr = (struct tlv_desc *)data; list->tlv_space = space; } static inline int TLV_LIST_EMPTY(struct tlv_list_desc *list) { return (list->tlv_space == 0); } static inline int TLV_LIST_CHECK(struct tlv_list_desc *list, __u16 exp_type) { return TLV_CHECK(list->tlv_ptr, list->tlv_space, exp_type); } static inline void *TLV_LIST_DATA(struct tlv_list_desc *list) { return TLV_DATA(list->tlv_ptr); } static inline void TLV_LIST_STEP(struct tlv_list_desc *list) { __u16 tlv_space = TLV_ALIGN(__be16_to_cpu(list->tlv_ptr->tlv_len)); list->tlv_ptr = (struct tlv_desc *)((char *)list->tlv_ptr + tlv_space); list->tlv_space -= tlv_space; } /* * Configuration messages exchanged via NETLINK_GENERIC use the following * family id, name, version and command. */ #define TIPC_GENL_NAME "TIPC" #define TIPC_GENL_VERSION 0x1 #define TIPC_GENL_CMD 0x1 /* * TIPC specific header used in NETLINK_GENERIC requests. */ struct tipc_genlmsghdr { __u32 dest; /* Destination address */ __u16 cmd; /* Command */ __u16 reserved; /* Unused */ }; #define TIPC_GENL_HDRLEN NLMSG_ALIGN(sizeof(struct tipc_genlmsghdr)) /* * Configuration messages exchanged via TIPC sockets use the TIPC configuration * message header, which is defined below. This structure is analogous * to the Netlink message header, but fields are stored in network byte order * and no padding is permitted between the header and the message data * that follows. */ struct tipc_cfg_msg_hdr { __be32 tcm_len; /* Message length (including header) */ __be16 tcm_type; /* Command type */ __be16 tcm_flags; /* Additional flags */ char tcm_reserved[8]; /* Unused */ }; #define TCM_F_REQUEST 0x1 /* Flag: Request message */ #define TCM_F_MORE 0x2 /* Flag: Message to be continued */ #define TCM_ALIGN(datalen) (((datalen)+3) & ~3) #define TCM_LENGTH(datalen) (sizeof(struct tipc_cfg_msg_hdr) + datalen) #define TCM_SPACE(datalen) (TCM_ALIGN(TCM_LENGTH(datalen))) #define TCM_DATA(tcm_hdr) ((void *)((char *)(tcm_hdr) + TCM_LENGTH(0))) static inline int TCM_SET(void *msg, __u16 cmd, __u16 flags, void *data, __u16 data_len) { struct tipc_cfg_msg_hdr *tcm_hdr; int msg_len; msg_len = TCM_LENGTH(data_len); tcm_hdr = (struct tipc_cfg_msg_hdr *)msg; tcm_hdr->tcm_len = __cpu_to_be32(msg_len); tcm_hdr->tcm_type = __cpu_to_be16(cmd); tcm_hdr->tcm_flags = __cpu_to_be16(flags); if (data_len && data) { memcpy(TCM_DATA(msg), data, data_len); memset((char *)TCM_DATA(msg) + data_len, 0, TCM_SPACE(data_len) - msg_len); } return TCM_SPACE(data_len); } #endif |
| 21 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PACKET_INTERNAL_H__ #define __PACKET_INTERNAL_H__ #include <linux/refcount.h> struct packet_mclist { struct packet_mclist *next; int ifindex; int count; unsigned short type; unsigned short alen; unsigned char addr[MAX_ADDR_LEN]; }; /* kbdq - kernel block descriptor queue */ struct tpacket_kbdq_core { struct pgv *pkbdq; unsigned int feature_req_word; unsigned int hdrlen; unsigned char reset_pending_on_curr_blk; unsigned char delete_blk_timer; unsigned short kactive_blk_num; unsigned short blk_sizeof_priv; /* last_kactive_blk_num: * trick to see if user-space has caught up * in order to avoid refreshing timer when every single pkt arrives. */ unsigned short last_kactive_blk_num; char *pkblk_start; char *pkblk_end; int kblk_size; unsigned int max_frame_len; unsigned int knum_blocks; uint64_t knxt_seq_num; char *prev; char *nxt_offset; struct sk_buff *skb; rwlock_t blk_fill_in_prog_lock; /* Default is set to 8ms */ #define DEFAULT_PRB_RETIRE_TOV (8) unsigned short retire_blk_tov; unsigned short version; unsigned long tov_in_jiffies; /* timer to retire an outstanding block */ struct timer_list retire_blk_timer; }; struct pgv { char *buffer; }; struct packet_ring_buffer { struct pgv *pg_vec; unsigned int head; unsigned int frames_per_block; unsigned int frame_size; unsigned int frame_max; unsigned int pg_vec_order; unsigned int pg_vec_pages; unsigned int pg_vec_len; unsigned int __percpu *pending_refcnt; union { unsigned long *rx_owner_map; struct tpacket_kbdq_core prb_bdqc; }; }; extern struct mutex fanout_mutex; #define PACKET_FANOUT_MAX (1 << 16) struct packet_fanout { possible_net_t net; unsigned int num_members; u32 max_num_members; u16 id; u8 type; u8 flags; union { atomic_t rr_cur; struct bpf_prog __rcu *bpf_prog; }; struct list_head list; spinlock_t lock; refcount_t sk_ref; struct packet_type prot_hook ____cacheline_aligned_in_smp; struct sock __rcu *arr[] __counted_by(max_num_members); }; struct packet_rollover { int sock; atomic_long_t num; atomic_long_t num_huge; atomic_long_t num_failed; #define ROLLOVER_HLEN (L1_CACHE_BYTES / sizeof(u32)) u32 history[ROLLOVER_HLEN] ____cacheline_aligned; } ____cacheline_aligned_in_smp; struct packet_sock { /* struct sock has to be the first member of packet_sock */ struct sock sk; struct packet_fanout *fanout; union tpacket_stats_u stats; struct packet_ring_buffer rx_ring; struct packet_ring_buffer tx_ring; int copy_thresh; spinlock_t bind_lock; struct mutex pg_vec_lock; unsigned long flags; int ifindex; /* bound device */ u8 vnet_hdr_sz; __be16 num; struct packet_rollover *rollover; struct packet_mclist *mclist; atomic_long_t mapped; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; unsigned int tp_tstamp; struct completion skb_completion; struct net_device __rcu *cached_dev; struct packet_type prot_hook ____cacheline_aligned_in_smp; atomic_t tp_drops ____cacheline_aligned_in_smp; }; #define pkt_sk(ptr) container_of_const(ptr, struct packet_sock, sk) enum packet_sock_flags { PACKET_SOCK_ORIGDEV, PACKET_SOCK_AUXDATA, PACKET_SOCK_TX_HAS_OFF, PACKET_SOCK_TP_LOSS, PACKET_SOCK_RUNNING, PACKET_SOCK_PRESSURE, PACKET_SOCK_QDISC_BYPASS, }; static inline void packet_sock_flag_set(struct packet_sock *po, enum packet_sock_flags flag, bool val) { if (val) set_bit(flag, &po->flags); else clear_bit(flag, &po->flags); } static inline bool packet_sock_flag(const struct packet_sock *po, enum packet_sock_flags flag) { return test_bit(flag, &po->flags); } #endif |
| 93 67 90 14997 3001 2971 45 1737 1693 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/bug.h> #include <linux/atomic.h> #include <linux/errseq.h> #include <linux/log2.h> /* * An errseq_t is a way of recording errors in one place, and allowing any * number of "subscribers" to tell whether it has changed since a previous * point where it was sampled. * * It's implemented as an unsigned 32-bit value. The low order bits are * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits * are used as a counter. This is done with atomics instead of locking so that * these functions can be called from any context. * * The general idea is for consumers to sample an errseq_t value. That value * can later be used to tell whether any new errors have occurred since that * sampling was done. * * Note that there is a risk of collisions if new errors are being recorded * frequently, since we have so few bits to use as a counter. * * To mitigate this, one bit is used as a flag to tell whether the value has * been sampled since a new value was recorded. That allows us to avoid bumping * the counter if no one has sampled it since the last time an error was * recorded. * * A new errseq_t should always be zeroed out. A errseq_t value of all zeroes * is the special (but common) case where there has never been an error. An all * zero value thus serves as the "epoch" if one wishes to know whether there * has ever been an error set since it was first initialized. */ /* The low bits are designated for error code (max of MAX_ERRNO) */ #define ERRSEQ_SHIFT ilog2(MAX_ERRNO + 1) /* This bit is used as a flag to indicate whether the value has been seen */ #define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT) /* The lowest bit of the counter */ #define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1)) /** * errseq_set - set a errseq_t for later reporting * @eseq: errseq_t field that should be set * @err: error to set (must be between -1 and -MAX_ERRNO) * * This function sets the error in @eseq, and increments the sequence counter * if the last sequence was sampled at some point in the past. * * Any error set will always overwrite an existing error. * * Return: The previous value, primarily for debugging purposes. The * return value should not be used as a previously sampled value in later * calls as it will not have the SEEN flag set. */ errseq_t errseq_set(errseq_t *eseq, int err) { errseq_t cur, old; /* MAX_ERRNO must be able to serve as a mask */ BUILD_BUG_ON_NOT_POWER_OF_2(MAX_ERRNO + 1); /* * Ensure the error code actually fits where we want it to go. If it * doesn't then just throw a warning and don't record anything. We * also don't accept zero here as that would effectively clear a * previous error. */ old = READ_ONCE(*eseq); if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO), "err = %d\n", err)) return old; for (;;) { errseq_t new; /* Clear out error bits and set new error */ new = (old & ~(MAX_ERRNO|ERRSEQ_SEEN)) | -err; /* Only increment if someone has looked at it */ if (old & ERRSEQ_SEEN) new += ERRSEQ_CTR_INC; /* If there would be no change, then call it done */ if (new == old) { cur = new; break; } /* Try to swap the new value into place */ cur = cmpxchg(eseq, old, new); /* * Call it success if we did the swap or someone else beat us * to it for the same value. */ if (likely(cur == old || cur == new)) break; /* Raced with an update, try again */ old = cur; } return cur; } EXPORT_SYMBOL(errseq_set); /** * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * * This function allows callers to initialise their errseq_t variable. * If the error has been "seen", new callers will not see an old error. * If there is an unseen error in @eseq, the caller of this function will * see it the next time it checks for an error. * * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); /* If nobody has seen this error yet, then we can be the first. */ if (!(old & ERRSEQ_SEEN)) old = 0; return old; } EXPORT_SYMBOL(errseq_sample); /** * errseq_check() - Has an error occurred since a particular sample point? * @eseq: Pointer to errseq_t value to be checked. * @since: Previously-sampled errseq_t from which to check. * * Grab the value that eseq points to, and see if it has changed @since * the given value was sampled. The @since value is not advanced, so there * is no need to mark the value as seen. * * Return: The latest error set in the errseq_t or 0 if it hasn't changed. */ int errseq_check(errseq_t *eseq, errseq_t since) { errseq_t cur = READ_ONCE(*eseq); if (likely(cur == since)) return 0; return -(cur & MAX_ERRNO); } EXPORT_SYMBOL(errseq_check); /** * errseq_check_and_advance() - Check an errseq_t and advance to current value. * @eseq: Pointer to value being checked and reported. * @since: Pointer to previously-sampled errseq_t to check against and advance. * * Grab the eseq value, and see whether it matches the value that @since * points to. If it does, then just return 0. * * If it doesn't, then the value has changed. Set the "seen" flag, and try to * swap it into place as the new eseq value. Then, set that value as the new * "since" value, and return whatever the error portion is set to. * * Note that no locking is provided here for concurrent updates to the "since" * value. The caller must provide that if necessary. Because of this, callers * may want to do a lockless errseq_check before taking the lock and calling * this. * * Return: Negative errno if one has been stored, or 0 if no new error has * occurred. */ int errseq_check_and_advance(errseq_t *eseq, errseq_t *since) { int err = 0; errseq_t old, new; /* * Most callers will want to use the inline wrapper to check this, * so that the common case of no error is handled without needing * to take the lock that protects the "since" value. */ old = READ_ONCE(*eseq); if (old != *since) { /* * Set the flag and try to swap it into place if it has * changed. * * We don't care about the outcome of the swap here. If the * swap doesn't occur, then it has either been updated by a * writer who is altering the value in some way (updating * counter or resetting the error), or another reader who is * just setting the "seen" flag. Either outcome is OK, and we * can advance "since" and return an error based on what we * have. */ new = old | ERRSEQ_SEEN; if (new != old) cmpxchg(eseq, old, new); *since = new; err = -(new & MAX_ERRNO); } return err; } EXPORT_SYMBOL(errseq_check_and_advance); |
| 7 1 5 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 | // SPDX-License-Identifier: GPL-2.0-only /* * xt_u32 - kernel module to match u32 packet content * * Original author: Don Cohen <don@isis.cs3-inc.com> * (C) CC Computer Consultants GmbH, 2007 */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/spinlock.h> #include <linux/skbuff.h> #include <linux/types.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_u32.h> static bool u32_match_it(const struct xt_u32 *data, const struct sk_buff *skb) { const struct xt_u32_test *ct; unsigned int testind; unsigned int nnums; unsigned int nvals; unsigned int i; __be32 n; u_int32_t pos; u_int32_t val; u_int32_t at; /* * Small example: "0 >> 28 == 4 && 8 & 0xFF0000 >> 16 = 6, 17" * (=IPv4 and (TCP or UDP)). Outer loop runs over the "&&" operands. */ for (testind = 0; testind < data->ntests; ++testind) { ct = &data->tests[testind]; at = 0; pos = ct->location[0].number; if (skb->len < 4 || pos > skb->len - 4) return false; if (skb_copy_bits(skb, pos, &n, sizeof(n)) < 0) BUG(); val = ntohl(n); nnums = ct->nnums; /* Inner loop runs over "&", "<<", ">>" and "@" operands */ for (i = 1; i < nnums; ++i) { u_int32_t number = ct->location[i].number; switch (ct->location[i].nextop) { case XT_U32_AND: val &= number; break; case XT_U32_LEFTSH: val <<= number; break; case XT_U32_RIGHTSH: val >>= number; break; case XT_U32_AT: if (at + val < at) return false; at += val; pos = number; if (at + 4 < at || skb->len < at + 4 || pos > skb->len - at - 4) return false; if (skb_copy_bits(skb, at + pos, &n, sizeof(n)) < 0) BUG(); val = ntohl(n); break; } } /* Run over the "," and ":" operands */ nvals = ct->nvalues; for (i = 0; i < nvals; ++i) if (ct->value[i].min <= val && val <= ct->value[i].max) break; if (i >= ct->nvalues) return false; } return true; } static bool u32_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_u32 *data = par->matchinfo; bool ret; ret = u32_match_it(data, skb); return ret ^ data->invert; } static int u32_mt_checkentry(const struct xt_mtchk_param *par) { const struct xt_u32 *data = par->matchinfo; const struct xt_u32_test *ct; unsigned int i; if (data->ntests > ARRAY_SIZE(data->tests)) return -EINVAL; for (i = 0; i < data->ntests; ++i) { ct = &data->tests[i]; if (ct->nnums > ARRAY_SIZE(ct->location) || ct->nvalues > ARRAY_SIZE(ct->value)) return -EINVAL; } return 0; } static struct xt_match xt_u32_mt_reg __read_mostly = { .name = "u32", .revision = 0, .family = NFPROTO_UNSPEC, .match = u32_mt, .checkentry = u32_mt_checkentry, .matchsize = sizeof(struct xt_u32), .me = THIS_MODULE, }; static int __init u32_mt_init(void) { return xt_register_match(&xt_u32_mt_reg); } static void __exit u32_mt_exit(void) { xt_unregister_match(&xt_u32_mt_reg); } module_init(u32_mt_init); module_exit(u32_mt_exit); MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); MODULE_DESCRIPTION("Xtables: arbitrary byte matching"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_u32"); MODULE_ALIAS("ip6t_u32"); |
| 40 1 41 40 6 41 41 41 41 36 41 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 36 6 41 49 1 48 44 48 45 45 45 45 45 44 44 45 44 45 45 45 45 44 45 45 45 44 45 44 45 45 45 45 45 45 45 45 43 34 15 45 39 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/dim.h> #include "netlink.h" #include "common.h" struct coalesce_req_info { struct ethnl_req_info base; }; struct coalesce_reply_data { struct ethnl_reply_data base; struct ethtool_coalesce coalesce; struct kernel_ethtool_coalesce kernel_coalesce; u32 supported_params; }; #define COALESCE_REPDATA(__reply_base) \ container_of(__reply_base, struct coalesce_reply_data, base) #define __SUPPORTED_OFFSET ETHTOOL_A_COALESCE_RX_USECS static u32 attr_to_mask(unsigned int attr_type) { return BIT(attr_type - __SUPPORTED_OFFSET); } /* build time check that indices in ethtool_ops::supported_coalesce_params * match corresponding attribute types with an offset */ #define __CHECK_SUPPORTED_OFFSET(x) \ static_assert((ETHTOOL_ ## x) == \ BIT((ETHTOOL_A_ ## x) - __SUPPORTED_OFFSET)) __CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS_IRQ); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES_IRQ); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_IRQ); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_IRQ); __CHECK_SUPPORTED_OFFSET(COALESCE_STATS_BLOCK_USECS); __CHECK_SUPPORTED_OFFSET(COALESCE_USE_ADAPTIVE_RX); __CHECK_SUPPORTED_OFFSET(COALESCE_USE_ADAPTIVE_TX); __CHECK_SUPPORTED_OFFSET(COALESCE_PKT_RATE_LOW); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS_LOW); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES_LOW); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_LOW); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_LOW); __CHECK_SUPPORTED_OFFSET(COALESCE_PKT_RATE_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_RATE_SAMPLE_INTERVAL); const struct nla_policy ethnl_coalesce_get_policy[] = { [ETHTOOL_A_COALESCE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int coalesce_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; if (!dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; data->supported_params = dev->ethtool_ops->supported_coalesce_params; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = dev->ethtool_ops->get_coalesce(dev, &data->coalesce, &data->kernel_coalesce, info->extack); ethnl_ops_complete(dev); return ret; } static int coalesce_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { int modersz = nla_total_size(0) + /* _PROFILE_IRQ_MODERATION, nest */ nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_USEC */ nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_PKTS */ nla_total_size(sizeof(u32)); /* _IRQ_MODERATION_COMPS */ int total_modersz = nla_total_size(0) + /* _{R,T}X_PROFILE, nest */ modersz * NET_DIM_PARAMS_NUM_PROFILES; return nla_total_size(sizeof(u32)) + /* _RX_USECS */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _RX_USECS_IRQ */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_IRQ */ nla_total_size(sizeof(u32)) + /* _TX_USECS */ nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _TX_USECS_IRQ */ nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_IRQ */ nla_total_size(sizeof(u32)) + /* _STATS_BLOCK_USECS */ nla_total_size(sizeof(u8)) + /* _USE_ADAPTIVE_RX */ nla_total_size(sizeof(u8)) + /* _USE_ADAPTIVE_TX */ nla_total_size(sizeof(u32)) + /* _PKT_RATE_LOW */ nla_total_size(sizeof(u32)) + /* _RX_USECS_LOW */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_LOW */ nla_total_size(sizeof(u32)) + /* _TX_USECS_LOW */ nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_LOW */ nla_total_size(sizeof(u32)) + /* _PKT_RATE_HIGH */ nla_total_size(sizeof(u32)) + /* _RX_USECS_HIGH */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_HIGH */ nla_total_size(sizeof(u32)) + /* _TX_USECS_HIGH */ nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_HIGH */ nla_total_size(sizeof(u32)) + /* _RATE_SAMPLE_INTERVAL */ nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_TX */ nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_RX */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_BYTES */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_TIME_USECS */ total_modersz * 2; /* _{R,T}X_PROFILE */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, u32 supported_params) { if (!val && !(supported_params & attr_to_mask(attr_type))) return false; return nla_put_u32(skb, attr_type, val); } static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val, u32 supported_params) { if (!val && !(supported_params & attr_to_mask(attr_type))) return false; return nla_put_u8(skb, attr_type, !!val); } /** * coalesce_put_profile - fill reply with a nla nest with four child nla nests. * @skb: socket buffer the message is stored in * @attr_type: nest attr type ETHTOOL_A_COALESCE_*X_PROFILE * @profile: data passed to userspace * @coal_flags: modifiable parameters supported by the driver * * Put a dim profile nest attribute. Refer to ETHTOOL_A_PROFILE_IRQ_MODERATION. * * Return: 0 on success or a negative error code. */ static int coalesce_put_profile(struct sk_buff *skb, u16 attr_type, const struct dim_cq_moder *profile, u8 coal_flags) { struct nlattr *profile_attr, *moder_attr; int i, ret; if (!profile || !coal_flags) return 0; profile_attr = nla_nest_start(skb, attr_type); if (!profile_attr) return -EMSGSIZE; for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) { moder_attr = nla_nest_start(skb, ETHTOOL_A_PROFILE_IRQ_MODERATION); if (!moder_attr) { ret = -EMSGSIZE; goto cancel_profile; } if (coal_flags & DIM_COALESCE_USEC) { ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_USEC, profile[i].usec); if (ret) goto cancel_moder; } if (coal_flags & DIM_COALESCE_PKTS) { ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_PKTS, profile[i].pkts); if (ret) goto cancel_moder; } if (coal_flags & DIM_COALESCE_COMPS) { ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_COMPS, profile[i].comps); if (ret) goto cancel_moder; } nla_nest_end(skb, moder_attr); } nla_nest_end(skb, profile_attr); return 0; cancel_moder: nla_nest_cancel(skb, moder_attr); cancel_profile: nla_nest_cancel(skb, profile_attr); return ret; } static int coalesce_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce; const struct ethtool_coalesce *coal = &data->coalesce; u32 supported = data->supported_params; struct dim_irq_moder *moder; int ret = 0; if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS, coal->rx_coalesce_usecs, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES, coal->rx_max_coalesced_frames, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS_IRQ, coal->rx_coalesce_usecs_irq, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ, coal->rx_max_coalesced_frames_irq, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS, coal->tx_coalesce_usecs, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES, coal->tx_max_coalesced_frames, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS_IRQ, coal->tx_coalesce_usecs_irq, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ, coal->tx_max_coalesced_frames_irq, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_STATS_BLOCK_USECS, coal->stats_block_coalesce_usecs, supported) || coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX, coal->use_adaptive_rx_coalesce, supported) || coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX, coal->use_adaptive_tx_coalesce, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_PKT_RATE_LOW, coal->pkt_rate_low, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS_LOW, coal->rx_coalesce_usecs_low, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW, coal->rx_max_coalesced_frames_low, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS_LOW, coal->tx_coalesce_usecs_low, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW, coal->tx_max_coalesced_frames_low, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_PKT_RATE_HIGH, coal->pkt_rate_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS_HIGH, coal->rx_coalesce_usecs_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH, coal->rx_max_coalesced_frames_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS_HIGH, coal->tx_coalesce_usecs_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, coal->tx_max_coalesced_frames_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, coal->rate_sample_interval, supported) || coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, kcoal->use_cqe_mode_tx, supported) || coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, kcoal->use_cqe_mode_rx, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, kcoal->tx_aggr_max_bytes, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, kcoal->tx_aggr_max_frames, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, kcoal->tx_aggr_time_usecs, supported)) return -EMSGSIZE; if (!req_base->dev || !req_base->dev->irq_moder) return 0; moder = req_base->dev->irq_moder; rcu_read_lock(); if (moder->profile_flags & DIM_PROFILE_RX) { ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_RX_PROFILE, rcu_dereference(moder->rx_profile), moder->coal_flags); if (ret) goto out; } if (moder->profile_flags & DIM_PROFILE_TX) ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_TX_PROFILE, rcu_dereference(moder->tx_profile), moder->coal_flags); out: rcu_read_unlock(); return ret; } /* COALESCE_SET */ static const struct nla_policy coalesce_irq_moderation_policy[] = { [ETHTOOL_A_IRQ_MODERATION_USEC] = { .type = NLA_U32 }, [ETHTOOL_A_IRQ_MODERATION_PKTS] = { .type = NLA_U32 }, [ETHTOOL_A_IRQ_MODERATION_COMPS] = { .type = NLA_U32 }, }; static const struct nla_policy coalesce_profile_policy[] = { [ETHTOOL_A_PROFILE_IRQ_MODERATION] = NLA_POLICY_NESTED(coalesce_irq_moderation_policy), }; const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_COALESCE_RX_USECS] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_USECS_IRQ] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_USECS] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_USECS_IRQ] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_STATS_BLOCK_USECS] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX] = { .type = NLA_U8 }, [ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX] = { .type = NLA_U8 }, [ETHTOOL_A_COALESCE_PKT_RATE_LOW] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_USECS_LOW] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_USECS_LOW] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_PKT_RATE_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_USECS_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_USECS_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_USE_CQE_MODE_TX] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_COALESCE_USE_CQE_MODE_RX] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_PROFILE] = NLA_POLICY_NESTED(coalesce_profile_policy), [ETHTOOL_A_COALESCE_TX_PROFILE] = NLA_POLICY_NESTED(coalesce_profile_policy), }; static int ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; struct dim_irq_moder *irq_moder = req_info->dev->irq_moder; struct nlattr **tb = info->attrs; u32 supported_params; u16 a; if (!ops->get_coalesce || !ops->set_coalesce) return -EOPNOTSUPP; /* make sure that only supported parameters are present */ supported_params = ops->supported_coalesce_params; if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_RX) supported_params |= ETHTOOL_COALESCE_RX_PROFILE; if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_TX) supported_params |= ETHTOOL_COALESCE_TX_PROFILE; for (a = ETHTOOL_A_COALESCE_RX_USECS; a < __ETHTOOL_A_COALESCE_CNT; a++) if (tb[a] && !(supported_params & attr_to_mask(a))) { NL_SET_ERR_MSG_ATTR(info->extack, tb[a], "cannot modify an unsupported parameter"); return -EINVAL; } return 1; } /** * ethnl_update_irq_moder - update a specific field in the given profile * @irq_moder: place that collects dim related information * @irq_field: field in profile to modify * @attr_type: attr type ETHTOOL_A_IRQ_MODERATION_* * @tb: netlink attribute with new values or null * @coal_bit: DIM_COALESCE_* bit from coal_flags * @mod: pointer to bool for modification tracking * @extack: netlink extended ack * * Return: 0 on success or a negative error code. */ static int ethnl_update_irq_moder(struct dim_irq_moder *irq_moder, u16 *irq_field, u16 attr_type, struct nlattr **tb, u8 coal_bit, bool *mod, struct netlink_ext_ack *extack) { int ret = 0; u32 val; if (!tb[attr_type]) return 0; if (irq_moder->coal_flags & coal_bit) { val = nla_get_u32(tb[attr_type]); if (*irq_field == val) return 0; *irq_field = val; *mod = true; } else { NL_SET_BAD_ATTR(extack, tb[attr_type]); ret = -EOPNOTSUPP; } return ret; } /** * ethnl_update_profile - get a profile nest with child nests from userspace. * @dev: netdevice to update the profile * @dst: profile get from the driver and modified by ethnl_update_profile. * @nests: nest attr ETHTOOL_A_COALESCE_*X_PROFILE to set profile. * @mod: pointer to bool for modification tracking * @extack: Netlink extended ack * * Layout of nests: * Nested ETHTOOL_A_COALESCE_*X_PROFILE attr * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr * ETHTOOL_A_IRQ_MODERATION_USEC attr * ETHTOOL_A_IRQ_MODERATION_PKTS attr * ETHTOOL_A_IRQ_MODERATION_COMPS attr * ... * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr * ETHTOOL_A_IRQ_MODERATION_USEC attr * ETHTOOL_A_IRQ_MODERATION_PKTS attr * ETHTOOL_A_IRQ_MODERATION_COMPS attr * * Return: 0 on success or a negative error code. */ static int ethnl_update_profile(struct net_device *dev, struct dim_cq_moder __rcu **dst, const struct nlattr *nests, bool *mod, struct netlink_ext_ack *extack) { int len_irq_moder = ARRAY_SIZE(coalesce_irq_moderation_policy); struct nlattr *tb[ARRAY_SIZE(coalesce_irq_moderation_policy)]; struct dim_irq_moder *irq_moder = dev->irq_moder; struct dim_cq_moder *new_profile, *old_profile; int ret, rem, i = 0, len; struct nlattr *nest; if (!nests) return 0; if (!*dst) return -EOPNOTSUPP; old_profile = rtnl_dereference(*dst); len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*old_profile); new_profile = kmemdup(old_profile, len, GFP_KERNEL); if (!new_profile) return -ENOMEM; nla_for_each_nested_type(nest, ETHTOOL_A_PROFILE_IRQ_MODERATION, nests, rem) { ret = nla_parse_nested(tb, len_irq_moder - 1, nest, coalesce_irq_moderation_policy, extack); if (ret) goto err_out; ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].usec, ETHTOOL_A_IRQ_MODERATION_USEC, tb, DIM_COALESCE_USEC, mod, extack); if (ret) goto err_out; ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].pkts, ETHTOOL_A_IRQ_MODERATION_PKTS, tb, DIM_COALESCE_PKTS, mod, extack); if (ret) goto err_out; ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].comps, ETHTOOL_A_IRQ_MODERATION_COMPS, tb, DIM_COALESCE_COMPS, mod, extack); if (ret) goto err_out; i++; } /* After the profile is modified, dim itself is a dynamic * mechanism and will quickly fit to the appropriate * coalescing parameters according to the new profile. */ rcu_assign_pointer(*dst, new_profile); kfree_rcu(old_profile, rcu); return 0; err_out: kfree(new_profile); return ret; } static int __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, bool *dual_change) { struct kernel_ethtool_coalesce kernel_coalesce = {}; struct net_device *dev = req_info->dev; struct ethtool_coalesce coalesce = {}; bool mod_mode = false, mod = false; struct nlattr **tb = info->attrs; int ret; ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce, info->extack); if (ret < 0) return ret; /* Update values */ ethnl_update_u32(&coalesce.rx_coalesce_usecs, tb[ETHTOOL_A_COALESCE_RX_USECS], &mod); ethnl_update_u32(&coalesce.rx_max_coalesced_frames, tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES], &mod); ethnl_update_u32(&coalesce.rx_coalesce_usecs_irq, tb[ETHTOOL_A_COALESCE_RX_USECS_IRQ], &mod); ethnl_update_u32(&coalesce.rx_max_coalesced_frames_irq, tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ], &mod); ethnl_update_u32(&coalesce.tx_coalesce_usecs, tb[ETHTOOL_A_COALESCE_TX_USECS], &mod); ethnl_update_u32(&coalesce.tx_max_coalesced_frames, tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES], &mod); ethnl_update_u32(&coalesce.tx_coalesce_usecs_irq, tb[ETHTOOL_A_COALESCE_TX_USECS_IRQ], &mod); ethnl_update_u32(&coalesce.tx_max_coalesced_frames_irq, tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ], &mod); ethnl_update_u32(&coalesce.stats_block_coalesce_usecs, tb[ETHTOOL_A_COALESCE_STATS_BLOCK_USECS], &mod); ethnl_update_u32(&coalesce.pkt_rate_low, tb[ETHTOOL_A_COALESCE_PKT_RATE_LOW], &mod); ethnl_update_u32(&coalesce.rx_coalesce_usecs_low, tb[ETHTOOL_A_COALESCE_RX_USECS_LOW], &mod); ethnl_update_u32(&coalesce.rx_max_coalesced_frames_low, tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW], &mod); ethnl_update_u32(&coalesce.tx_coalesce_usecs_low, tb[ETHTOOL_A_COALESCE_TX_USECS_LOW], &mod); ethnl_update_u32(&coalesce.tx_max_coalesced_frames_low, tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW], &mod); ethnl_update_u32(&coalesce.pkt_rate_high, tb[ETHTOOL_A_COALESCE_PKT_RATE_HIGH], &mod); ethnl_update_u32(&coalesce.rx_coalesce_usecs_high, tb[ETHTOOL_A_COALESCE_RX_USECS_HIGH], &mod); ethnl_update_u32(&coalesce.rx_max_coalesced_frames_high, tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH], &mod); ethnl_update_u32(&coalesce.tx_coalesce_usecs_high, tb[ETHTOOL_A_COALESCE_TX_USECS_HIGH], &mod); ethnl_update_u32(&coalesce.tx_max_coalesced_frames_high, tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH], &mod); ethnl_update_u32(&coalesce.rate_sample_interval, tb[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL], &mod); ethnl_update_u32(&kernel_coalesce.tx_aggr_max_bytes, tb[ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES], &mod); ethnl_update_u32(&kernel_coalesce.tx_aggr_max_frames, tb[ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES], &mod); ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs, tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod); if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_RX) { ret = ethnl_update_profile(dev, &dev->irq_moder->rx_profile, tb[ETHTOOL_A_COALESCE_RX_PROFILE], &mod, info->extack); if (ret < 0) return ret; } if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_TX) { ret = ethnl_update_profile(dev, &dev->irq_moder->tx_profile, tb[ETHTOOL_A_COALESCE_TX_PROFILE], &mod, info->extack); if (ret < 0) return ret; } /* Update operation modes */ ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce, tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod_mode); ethnl_update_bool32(&coalesce.use_adaptive_tx_coalesce, tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX], &mod_mode); ethnl_update_u8(&kernel_coalesce.use_cqe_mode_tx, tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_TX], &mod_mode); ethnl_update_u8(&kernel_coalesce.use_cqe_mode_rx, tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_RX], &mod_mode); *dual_change = mod && mod_mode; if (!mod && !mod_mode) return 0; ret = dev->ethtool_ops->set_coalesce(dev, &coalesce, &kernel_coalesce, info->extack); return ret < 0 ? ret : 1; } static int ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info) { bool dual_change; int err, ret; /* SET_COALESCE may change operation mode and parameters in one call. * Changing operation mode may cause the driver to reset the parameter * values, and therefore ignore user input (driver does not know which * parameters come from user and which are echoed back from ->get). * To not complicate the drivers if user tries to change both the mode * and parameters at once - call the driver twice. */ err = __ethnl_set_coalesce(req_info, info, &dual_change); if (err < 0) return err; ret = err; if (ret && dual_change) { err = __ethnl_set_coalesce(req_info, info, &dual_change); if (err < 0) return err; } return ret; } const struct ethnl_request_ops ethnl_coalesce_request_ops = { .request_cmd = ETHTOOL_MSG_COALESCE_GET, .reply_cmd = ETHTOOL_MSG_COALESCE_GET_REPLY, .hdr_attr = ETHTOOL_A_COALESCE_HEADER, .req_info_size = sizeof(struct coalesce_req_info), .reply_data_size = sizeof(struct coalesce_reply_data), .prepare_data = coalesce_prepare_data, .reply_size = coalesce_reply_size, .fill_reply = coalesce_fill_reply, .set_validate = ethnl_set_coalesce_validate, .set = ethnl_set_coalesce, .set_ntf_cmd = ETHTOOL_MSG_COALESCE_NTF, }; |
| 20 4 7 1 15 15 2 11 2 9 2 2 7 7 13 13 7 12 12 12 12 12 11 1 17 1 1 1 2 13 15 14 3 13 9 1 2 1 3 3 3 2 2 1 3 1 1 1 7 7 21 17 6 3 18 6 14 14 2 13 2 12 1 4 1 9 1 9 6 3 2 7 8 1 7 3 1 3 359 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 | // SPDX-License-Identifier: GPL-2.0-or-later /* L2TPv3 IP encapsulation support * * Copyright (c) 2008,2009,2010 Katalix Systems Ltd */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/ioctls.h> #include <linux/icmp.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/random.h> #include <linux/socket.h> #include <linux/l2tp.h> #include <linux/in.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include "l2tp_core.h" /* per-net private data for this module */ static unsigned int l2tp_ip_net_id; struct l2tp_ip_net { rwlock_t l2tp_ip_lock; struct hlist_head l2tp_ip_table; struct hlist_head l2tp_ip_bind_table; }; struct l2tp_ip_sock { /* inet_sock has to be the first member of l2tp_ip_sock */ struct inet_sock inet; u32 conn_id; u32 peer_conn_id; }; static struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) { return (struct l2tp_ip_sock *)sk; } static struct l2tp_ip_net *l2tp_ip_pernet(const struct net *net) { return net_generic(net, l2tp_ip_net_id); } static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr, __be32 raddr, int dif, u32 tunnel_id) { struct l2tp_ip_net *pn = l2tp_ip_pernet(net); struct sock *sk; sk_for_each_bound(sk, &pn->l2tp_ip_bind_table) { const struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk); const struct inet_sock *inet = inet_sk(sk); int bound_dev_if; if (!net_eq(sock_net(sk), net)) continue; bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); if (bound_dev_if && dif && bound_dev_if != dif) continue; if (inet->inet_rcv_saddr && laddr && inet->inet_rcv_saddr != laddr) continue; if (inet->inet_daddr && raddr && inet->inet_daddr != raddr) continue; if (l2tp->conn_id != tunnel_id) continue; goto found; } sk = NULL; found: return sk; } /* When processing receive frames, there are two cases to * consider. Data frames consist of a non-zero session-id and an * optional cookie. Control frames consist of a regular L2TP header * preceded by 32-bits of zeros. * * L2TPv3 Session Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Cookie (optional, maximum 64 bits)... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 Control Message Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | (32 bits of zeros) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |T|L|x|x|S|x|x|x|x|x|x|x| Ver | Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Control Connection ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ns | Nr | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * All control frames are passed to userspace. */ static int l2tp_ip_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct l2tp_ip_net *pn; struct sock *sk; u32 session_id; u32 tunnel_id; unsigned char *ptr, *optr; struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct iphdr *iph; pn = l2tp_ip_pernet(net); if (!pskb_may_pull(skb, 4)) goto discard; /* Point to L2TP header */ optr = skb->data; ptr = skb->data; session_id = ntohl(*((__be32 *)ptr)); ptr += 4; /* RFC3931: L2TP/IP packets have the first 4 bytes containing * the session_id. If it is 0, the packet is a L2TP control * frame and the session_id value can be discarded. */ if (session_id == 0) { __skb_pull(skb, 4); goto pass_up; } /* Ok, this is a data packet. Lookup the session. */ session = l2tp_v3_session_get(net, NULL, session_id); if (!session) goto discard; tunnel = session->tunnel; if (!tunnel) goto discard_sess; if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_put(session); return 0; pass_up: /* Get the tunnel_id from the L2TP header */ if (!pskb_may_pull(skb, 12)) goto discard; if ((skb->data[0] & 0xc0) != 0xc0) goto discard; tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = (struct iphdr *)skb_network_header(skb); read_lock_bh(&pn->l2tp_ip_lock); sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb), tunnel_id); if (!sk) { read_unlock_bh(&pn->l2tp_ip_lock); goto discard; } sock_hold(sk); read_unlock_bh(&pn->l2tp_ip_lock); if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; nf_reset_ct(skb); return sk_receive_skb(sk, skb, 1); discard_sess: l2tp_session_put(session); goto discard; discard_put: sock_put(sk); discard: kfree_skb(skb); return 0; } static int l2tp_ip_hash(struct sock *sk) { struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); if (sk_unhashed(sk)) { write_lock_bh(&pn->l2tp_ip_lock); sk_add_node(sk, &pn->l2tp_ip_table); write_unlock_bh(&pn->l2tp_ip_lock); } return 0; } static void l2tp_ip_unhash(struct sock *sk) { struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); if (sk_unhashed(sk)) return; write_lock_bh(&pn->l2tp_ip_lock); sk_del_node_init(sk); write_unlock_bh(&pn->l2tp_ip_lock); } static int l2tp_ip_open(struct sock *sk) { /* Prevent autobind. We don't have ports. */ inet_sk(sk)->inet_num = IPPROTO_L2TP; l2tp_ip_hash(sk); return 0; } static void l2tp_ip_close(struct sock *sk, long timeout) { struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); write_lock_bh(&pn->l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); write_unlock_bh(&pn->l2tp_ip_lock); sk_common_release(sk); } static void l2tp_ip_destroy_sock(struct sock *sk) { struct l2tp_tunnel *tunnel; __skb_queue_purge(&sk->sk_write_queue); tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { l2tp_tunnel_delete(tunnel); l2tp_tunnel_put(tunnel); } } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *)uaddr; struct net *net = sock_net(sk); struct l2tp_ip_net *pn; int ret; int chk_addr_ret; if (addr_len < sizeof(struct sockaddr_l2tpip)) return -EINVAL; if (addr->l2tp_family != AF_INET) return -EINVAL; lock_sock(sk); ret = -EINVAL; if (!sock_flag(sk, SOCK_ZAPPED)) goto out; if (sk->sk_state != TCP_CLOSE) goto out; chk_addr_ret = inet_addr_type(net, addr->l2tp_addr.s_addr); ret = -EADDRNOTAVAIL; if (addr->l2tp_addr.s_addr && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) goto out; if (addr->l2tp_addr.s_addr) { inet->inet_rcv_saddr = addr->l2tp_addr.s_addr; inet->inet_saddr = addr->l2tp_addr.s_addr; } if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ pn = l2tp_ip_pernet(net); write_lock_bh(&pn->l2tp_ip_lock); if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, 0, sk->sk_bound_dev_if, addr->l2tp_conn_id)) { write_unlock_bh(&pn->l2tp_ip_lock); ret = -EADDRINUSE; goto out; } sk_dst_reset(sk); l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; sk_add_bind_node(sk, &pn->l2tp_ip_bind_table); sk_del_node_init(sk); write_unlock_bh(&pn->l2tp_ip_lock); ret = 0; sock_reset_flag(sk, SOCK_ZAPPED); out: release_sock(sk); return ret; } static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); int rc; if (addr_len < sizeof(*lsa)) return -EINVAL; if (ipv4_is_multicast(lsa->l2tp_addr.s_addr)) return -EINVAL; lock_sock(sk); /* Must bind first - autobinding does not work */ if (sock_flag(sk, SOCK_ZAPPED)) { rc = -EINVAL; goto out_sk; } rc = __ip4_datagram_connect(sk, uaddr, addr_len); if (rc < 0) goto out_sk; l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; write_lock_bh(&pn->l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_add_bind_node(sk, &pn->l2tp_ip_bind_table); write_unlock_bh(&pn->l2tp_ip_lock); out_sk: release_sock(sk); return rc; } static int l2tp_ip_disconnect(struct sock *sk, int flags) { if (sock_flag(sk, SOCK_ZAPPED)) return 0; return __udp_disconnect(sk, flags); } static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct l2tp_ip_sock *lsk = l2tp_ip_sk(sk); struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; memset(lsa, 0, sizeof(*lsa)); lsa->l2tp_family = AF_INET; if (peer) { if (!inet->inet_dport) return -ENOTCONN; lsa->l2tp_conn_id = lsk->peer_conn_id; lsa->l2tp_addr.s_addr = inet->inet_daddr; } else { __be32 addr = inet->inet_rcv_saddr; if (!addr) addr = inet->inet_saddr; lsa->l2tp_conn_id = lsk->conn_id; lsa->l2tp_addr.s_addr = addr; } return sizeof(*lsa); } static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) { int rc; /* Charge it to the socket, dropping if the queue is full. */ rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) goto drop; return 0; drop: IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS); kfree_skb(skb); return 0; } /* Userspace will call sendmsg() on the tunnel socket to send L2TP * control frames. */ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct sk_buff *skb; int rc; struct inet_sock *inet = inet_sk(sk); struct rtable *rt = NULL; struct flowi4 *fl4; int connected = 0; __be32 daddr; lock_sock(sk); rc = -ENOTCONN; if (sock_flag(sk, SOCK_DEAD)) goto out; /* Get and verify the address. */ if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_l2tpip *, lip, msg->msg_name); rc = -EINVAL; if (msg->msg_namelen < sizeof(*lip)) goto out; if (lip->l2tp_family != AF_INET) { rc = -EAFNOSUPPORT; if (lip->l2tp_family != AF_UNSPEC) goto out; } daddr = lip->l2tp_addr.s_addr; } else { rc = -EDESTADDRREQ; if (sk->sk_state != TCP_ESTABLISHED) goto out; daddr = inet->inet_daddr; connected = 1; } /* Allocate a socket buffer */ rc = -ENOMEM; skb = sock_wmalloc(sk, 2 + NET_SKB_PAD + sizeof(struct iphdr) + 4 + len, 0, GFP_KERNEL); if (!skb) goto error; /* Reserve space for headers, putting IP header on 4-byte boundary. */ skb_reserve(skb, 2 + NET_SKB_PAD); skb_reset_network_header(skb); skb_reserve(skb, sizeof(struct iphdr)); skb_reset_transport_header(skb); /* Insert 0 session_id */ *((__be32 *)skb_put(skb, 4)) = 0; /* Copy user data into skb */ rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc < 0) { kfree_skb(skb); goto error; } fl4 = &inet->cork.fl.u.ip4; if (connected) rt = dst_rtable(__sk_dst_check(sk, 0)); rcu_read_lock(); if (!rt) { const struct ip_options_rcu *inet_opt; inet_opt = rcu_dereference(inet->inet_opt); /* Use correct destination address if we have options. */ if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; if (connected) { sk_setup_caps(sk, &rt->dst); } else { skb_dst_set(skb, &rt->dst); goto xmit; } } /* We don't need to clone dst here, it is guaranteed to not disappear. * __dev_xmit_skb() might force a refcount if needed. */ skb_dst_set_noref(skb, &rt->dst); xmit: /* Queue the packet to IP for output */ rc = ip_queue_xmit(sk, skb, &inet->cork.fl); rcu_read_unlock(); error: if (rc >= 0) rc = len; out: release_sock(sk); return rc; no_route: rcu_read_unlock(); IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); rc = -EHOSTUNREACH; goto out; } static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); size_t copied = 0; int err = -EOPNOTSUPP; DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; if (flags & MSG_OOB) goto out; skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto out; copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto done; sock_recv_timestamp(msg, sk, skb); /* Copy the address. */ if (sin) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } if (inet_cmsg_flags(inet)) ip_cmsg_recv(msg, skb); if (flags & MSG_TRUNC) copied = skb->len; done: skb_free_datagram(sk, skb); out: return err ? err : copied; } int l2tp_ioctl(struct sock *sk, int cmd, int *karg) { struct sk_buff *skb; switch (cmd) { case SIOCOUTQ: *karg = sk_wmem_alloc_get(sk); break; case SIOCINQ: spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); *karg = skb ? skb->len : 0; spin_unlock_bh(&sk->sk_receive_queue.lock); break; default: return -ENOIOCTLCMD; } return 0; } EXPORT_SYMBOL_GPL(l2tp_ioctl); static struct proto l2tp_ip_prot = { .name = "L2TP/IP", .owner = THIS_MODULE, .init = l2tp_ip_open, .close = l2tp_ip_close, .bind = l2tp_ip_bind, .connect = l2tp_ip_connect, .disconnect = l2tp_ip_disconnect, .ioctl = l2tp_ioctl, .destroy = l2tp_ip_destroy_sock, .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .sendmsg = l2tp_ip_sendmsg, .recvmsg = l2tp_ip_recvmsg, .backlog_rcv = l2tp_ip_backlog_recv, .hash = l2tp_ip_hash, .unhash = l2tp_ip_unhash, .obj_size = sizeof(struct l2tp_ip_sock), }; static const struct proto_ops l2tp_ip_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = l2tp_ip_getname, .poll = datagram_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, }; static struct inet_protosw l2tp_ip_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_L2TP, .prot = &l2tp_ip_prot, .ops = &l2tp_ip_ops, }; static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, }; static __net_init int l2tp_ip_init_net(struct net *net) { struct l2tp_ip_net *pn = net_generic(net, l2tp_ip_net_id); rwlock_init(&pn->l2tp_ip_lock); INIT_HLIST_HEAD(&pn->l2tp_ip_table); INIT_HLIST_HEAD(&pn->l2tp_ip_bind_table); return 0; } static __net_exit void l2tp_ip_exit_net(struct net *net) { struct l2tp_ip_net *pn = l2tp_ip_pernet(net); write_lock_bh(&pn->l2tp_ip_lock); WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip_table) != 0); WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip_bind_table) != 0); write_unlock_bh(&pn->l2tp_ip_lock); } static struct pernet_operations l2tp_ip_net_ops = { .init = l2tp_ip_init_net, .exit = l2tp_ip_exit_net, .id = &l2tp_ip_net_id, .size = sizeof(struct l2tp_ip_net), }; static int __init l2tp_ip_init(void) { int err; pr_info("L2TP IP encapsulation support (L2TPv3)\n"); err = register_pernet_device(&l2tp_ip_net_ops); if (err) goto out; err = proto_register(&l2tp_ip_prot, 1); if (err != 0) goto out1; err = inet_add_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); if (err) goto out2; inet_register_protosw(&l2tp_ip_protosw); return 0; out2: proto_unregister(&l2tp_ip_prot); out1: unregister_pernet_device(&l2tp_ip_net_ops); out: return err; } static void __exit l2tp_ip_exit(void) { inet_unregister_protosw(&l2tp_ip_protosw); inet_del_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip_prot); unregister_pernet_device(&l2tp_ip_net_ops); } module_init(l2tp_ip_init); module_exit(l2tp_ip_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); /* Use the values of SOCK_DGRAM (2) as type and IPPROTO_L2TP (115) as protocol, * because __stringify doesn't like enums */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 115, 2); MODULE_ALIAS_NET_PF_PROTO(PF_INET, 115); |
| 99 9 28 95 94 28 28 2 2 1 2 45 1 1 17 34 3 6 11 1 28 18 13 8 40 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 | /* * net/tipc/net.c: TIPC network routing code * * Copyright (c) 1995-2006, 2014, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "core.h" #include "net.h" #include "name_distr.h" #include "subscr.h" #include "socket.h" #include "node.h" #include "bcast.h" #include "link.h" #include "netlink.h" #include "monitor.h" /* * The TIPC locking policy is designed to ensure a very fine locking * granularity, permitting complete parallel access to individual * port and node/link instances. The code consists of four major * locking domains, each protected with their own disjunct set of locks. * * 1: The bearer level. * RTNL lock is used to serialize the process of configuring bearer * on update side, and RCU lock is applied on read side to make * bearer instance valid on both paths of message transmission and * reception. * * 2: The node and link level. * All node instances are saved into two tipc_node_list and node_htable * lists. The two lists are protected by node_list_lock on write side, * and they are guarded with RCU lock on read side. Especially node * instance is destroyed only when TIPC module is removed, and we can * confirm that there has no any user who is accessing the node at the * moment. Therefore, Except for iterating the two lists within RCU * protection, it's no needed to hold RCU that we access node instance * in other places. * * In addition, all members in node structure including link instances * are protected by node spin lock. * * 3: The transport level of the protocol. * This consists of the structures port, (and its user level * representations, such as user_port and tipc_sock), reference and * tipc_user (port.c, reg.c, socket.c). * * This layer has four different locks: * - The tipc_port spin_lock. This is protecting each port instance * from parallel data access and removal. Since we can not place * this lock in the port itself, it has been placed in the * corresponding reference table entry, which has the same life * cycle as the module. This entry is difficult to access from * outside the TIPC core, however, so a pointer to the lock has * been added in the port instance, -to be used for unlocking * only. * - A read/write lock to protect the reference table itself (teg.c). * (Nobody is using read-only access to this, so it can just as * well be changed to a spin_lock) * - A spin lock to protect the registry of kernel/driver users (reg.c) * - A global spin_lock (tipc_port_lock), which only task is to ensure * consistency where more than one port is involved in an operation, * i.e., when a port is part of a linked list of ports. * There are two such lists; 'port_list', which is used for management, * and 'wait_list', which is used to queue ports during congestion. * * 4: The name table (name_table.c, name_distr.c, subscription.c) * - There is one big read/write-lock (tipc_nametbl_lock) protecting the * overall name table structure. Nothing must be added/removed to * this structure without holding write access to it. * - There is one local spin_lock per sub_sequence, which can be seen * as a sub-domain to the tipc_nametbl_lock domain. It is used only * for translation operations, and is needed because a translation * steps the root of the 'publication' linked list between each lookup. * This is always used within the scope of a tipc_nametbl_lock(read). * - A local spin_lock protecting the queue of subscriber events. */ static void tipc_net_finalize(struct net *net, u32 addr); int tipc_net_init(struct net *net, u8 *node_id, u32 addr) { if (tipc_own_id(net)) { pr_info("Cannot configure node identity twice\n"); return -1; } pr_info("Started in network mode\n"); if (node_id) tipc_set_node_id(net, node_id); if (addr) tipc_net_finalize(net, addr); return 0; } static void tipc_net_finalize(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); struct tipc_socket_addr sk = {0, addr}; struct tipc_uaddr ua; tipc_uaddr(&ua, TIPC_SERVICE_RANGE, TIPC_CLUSTER_SCOPE, TIPC_NODE_STATE, addr, addr); if (cmpxchg(&tn->node_addr, 0, addr)) return; tipc_set_node_addr(net, addr); tipc_named_reinit(net); tipc_sk_reinit(net); tipc_mon_reinit_self(net); tipc_nametbl_publish(net, &ua, &sk, addr); } void tipc_net_finalize_work(struct work_struct *work) { struct tipc_net *tn = container_of(work, struct tipc_net, work); tipc_net_finalize(tipc_link_net(tn->bcl), tn->trial_addr); } void tipc_net_stop(struct net *net) { if (!tipc_own_id(net)) return; rtnl_lock(); tipc_bearer_stop(net); tipc_node_stop(net); rtnl_unlock(); pr_info("Left network mode\n"); } static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg) { struct tipc_net *tn = net_generic(net, tipc_net_id); u64 *w0 = (u64 *)&tn->node_id[0]; u64 *w1 = (u64 *)&tn->node_id[8]; struct nlattr *attrs; void *hdr; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_NET_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NET); if (!attrs) goto msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_NET_ID, tn->net_id)) goto attr_msg_full; if (nla_put_u64_64bit(msg->skb, TIPC_NLA_NET_NODEID, *w0, 0)) goto attr_msg_full; if (nla_put_u64_64bit(msg->skb, TIPC_NLA_NET_NODEID_W1, *w1, 0)) goto attr_msg_full; nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int err; int done = cb->args[0]; struct tipc_nl_msg msg; if (done) return 0; msg.skb = skb; msg.portid = NETLINK_CB(cb->skb).portid; msg.seq = cb->nlh->nlmsg_seq; err = __tipc_nl_add_net(net, &msg); if (err) goto out; done = 1; out: cb->args[0] = done; return skb->len; } int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attrs[TIPC_NLA_NET_MAX + 1]; struct net *net = sock_net(skb->sk); struct tipc_net *tn = tipc_net(net); int err; if (!info->attrs[TIPC_NLA_NET]) return -EINVAL; err = nla_parse_nested_deprecated(attrs, TIPC_NLA_NET_MAX, info->attrs[TIPC_NLA_NET], tipc_nl_net_policy, info->extack); if (err) return err; /* Can't change net id once TIPC has joined a network */ if (tipc_own_addr(net)) return -EPERM; if (attrs[TIPC_NLA_NET_ID]) { u32 val; val = nla_get_u32(attrs[TIPC_NLA_NET_ID]); if (val < 1 || val > 9999) return -EINVAL; tn->net_id = val; } if (attrs[TIPC_NLA_NET_ADDR]) { u32 addr; addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]); if (!addr) return -EINVAL; tn->legacy_addr_format = true; tipc_net_init(net, NULL, addr); } if (attrs[TIPC_NLA_NET_NODEID]) { u8 node_id[NODE_ID_LEN]; u64 *w0 = (u64 *)&node_id[0]; u64 *w1 = (u64 *)&node_id[8]; if (!attrs[TIPC_NLA_NET_NODEID_W1]) return -EINVAL; *w0 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID]); *w1 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID_W1]); tipc_net_init(net, node_id, 0); } return 0; } int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) { int err; rtnl_lock(); err = __tipc_nl_net_set(skb, info); rtnl_unlock(); return err; } static int __tipc_nl_addr_legacy_get(struct net *net, struct tipc_nl_msg *msg) { struct tipc_net *tn = tipc_net(net); struct nlattr *attrs; void *hdr; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, 0, TIPC_NL_ADDR_LEGACY_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start(msg->skb, TIPC_NLA_NET); if (!attrs) goto msg_full; if (tn->legacy_addr_format) if (nla_put_flag(msg->skb, TIPC_NLA_NET_ADDR_LEGACY)) goto attr_msg_full; nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_net_addr_legacy_get(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); struct tipc_nl_msg msg; struct sk_buff *rep; int err; rep = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!rep) return -ENOMEM; msg.skb = rep; msg.portid = info->snd_portid; msg.seq = info->snd_seq; err = __tipc_nl_addr_legacy_get(net, &msg); if (err) { nlmsg_free(msg.skb); return err; } return genlmsg_reply(msg.skb, info); } |
| 3 51 2 1 4 7 15 39 18 1 1 2 2 3 1 1 1 3 16 1 13 13 2 2 2 2 2 1 1 4 2 2 2 3 83 1 4 1 80 38 15 23 3 24 4 1 1 17 2 1 2 53 4 1 1 27 2 21 156 3 132 23 19 2 17 29 5 5 6 17 1 2 1 18 22 22 1 21 28 1 27 18 2 2 17 116 3 1 44 6 2 109 2 17 2 2 10 3 1 3 3 3 5 5 5 2 5 5 5 5 5 1 2 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 | // SPDX-License-Identifier: GPL-2.0-only /* Updated: Karl MacMillan <kmacmillan@tresys.com> * * Added conditional policy language extensions * * Updated: Hewlett-Packard <paul@paul-moore.com> * * Added support for the policy capability bitmap * * Copyright (C) 2007 Hewlett-Packard Development Company, L.P. * Copyright (C) 2003 - 2004 Tresys Technology, LLC * Copyright (C) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/kernel.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/mount.h> #include <linux/mutex.h> #include <linux/namei.h> #include <linux/init.h> #include <linux/string.h> #include <linux/security.h> #include <linux/major.h> #include <linux/seq_file.h> #include <linux/percpu.h> #include <linux/audit.h> #include <linux/uaccess.h> #include <linux/kobject.h> #include <linux/ctype.h> /* selinuxfs pseudo filesystem for exporting the security policy API. Based on the proc code and the fs/nfsd/nfsctl.c code. */ #include "flask.h" #include "avc.h" #include "avc_ss.h" #include "security.h" #include "objsec.h" #include "conditional.h" #include "ima.h" enum sel_inos { SEL_ROOT_INO = 2, SEL_LOAD, /* load policy */ SEL_ENFORCE, /* get or set enforcing status */ SEL_CONTEXT, /* validate context */ SEL_ACCESS, /* compute access decision */ SEL_CREATE, /* compute create labeling decision */ SEL_RELABEL, /* compute relabeling decision */ SEL_USER, /* compute reachable user contexts */ SEL_POLICYVERS, /* return policy version for this kernel */ SEL_COMMIT_BOOLS, /* commit new boolean values */ SEL_MLS, /* return if MLS policy is enabled */ SEL_DISABLE, /* disable SELinux until next reboot */ SEL_MEMBER, /* compute polyinstantiation membership decision */ SEL_CHECKREQPROT, /* check requested protection, not kernel-applied one */ SEL_COMPAT_NET, /* whether to use old compat network packet controls */ SEL_REJECT_UNKNOWN, /* export unknown reject handling to userspace */ SEL_DENY_UNKNOWN, /* export unknown deny handling to userspace */ SEL_STATUS, /* export current status using mmap() */ SEL_POLICY, /* allow userspace to read the in kernel policy */ SEL_VALIDATE_TRANS, /* compute validatetrans decision */ SEL_INO_NEXT, /* The next inode number to use */ }; struct selinux_fs_info { struct dentry *bool_dir; unsigned int bool_num; char **bool_pending_names; int *bool_pending_values; struct dentry *class_dir; unsigned long last_class_ino; bool policy_opened; struct dentry *policycap_dir; unsigned long last_ino; struct super_block *sb; }; static int selinux_fs_info_create(struct super_block *sb) { struct selinux_fs_info *fsi; fsi = kzalloc(sizeof(*fsi), GFP_KERNEL); if (!fsi) return -ENOMEM; fsi->last_ino = SEL_INO_NEXT - 1; fsi->sb = sb; sb->s_fs_info = fsi; return 0; } static void selinux_fs_info_free(struct super_block *sb) { struct selinux_fs_info *fsi = sb->s_fs_info; unsigned int i; if (fsi) { for (i = 0; i < fsi->bool_num; i++) kfree(fsi->bool_pending_names[i]); kfree(fsi->bool_pending_names); kfree(fsi->bool_pending_values); } kfree(sb->s_fs_info); sb->s_fs_info = NULL; } #define SEL_INITCON_INO_OFFSET 0x01000000 #define SEL_BOOL_INO_OFFSET 0x02000000 #define SEL_CLASS_INO_OFFSET 0x04000000 #define SEL_POLICYCAP_INO_OFFSET 0x08000000 #define SEL_INO_MASK 0x00ffffff #define BOOL_DIR_NAME "booleans" #define CLASS_DIR_NAME "class" #define POLICYCAP_DIR_NAME "policy_capabilities" #define TMPBUFLEN 12 static ssize_t sel_read_enforce(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { char tmpbuf[TMPBUFLEN]; ssize_t length; length = scnprintf(tmpbuf, TMPBUFLEN, "%d", enforcing_enabled()); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } #ifdef CONFIG_SECURITY_SELINUX_DEVELOP static ssize_t sel_write_enforce(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *page = NULL; ssize_t length; int scan_value; bool old_value, new_value; if (count >= PAGE_SIZE) return -ENOMEM; /* No partial writes. */ if (*ppos != 0) return -EINVAL; page = memdup_user_nul(buf, count); if (IS_ERR(page)) return PTR_ERR(page); length = -EINVAL; if (sscanf(page, "%d", &scan_value) != 1) goto out; new_value = !!scan_value; old_value = enforcing_enabled(); if (new_value != old_value) { length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__SETENFORCE, NULL); if (length) goto out; audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_STATUS, "enforcing=%d old_enforcing=%d auid=%u ses=%u" " enabled=1 old-enabled=1 lsm=selinux res=1", new_value, old_value, from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); enforcing_set(new_value); if (new_value) avc_ss_reset(0); selnl_notify_setenforce(new_value); selinux_status_update_setenforce(new_value); if (!new_value) call_blocking_lsm_notifier(LSM_POLICY_CHANGE, NULL); selinux_ima_measure_state(); } length = count; out: kfree(page); return length; } #else #define sel_write_enforce NULL #endif static const struct file_operations sel_enforce_ops = { .read = sel_read_enforce, .write = sel_write_enforce, .llseek = generic_file_llseek, }; static ssize_t sel_read_handle_unknown(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { char tmpbuf[TMPBUFLEN]; ssize_t length; ino_t ino = file_inode(filp)->i_ino; int handle_unknown = (ino == SEL_REJECT_UNKNOWN) ? security_get_reject_unknown() : !security_get_allow_unknown(); length = scnprintf(tmpbuf, TMPBUFLEN, "%d", handle_unknown); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static const struct file_operations sel_handle_unknown_ops = { .read = sel_read_handle_unknown, .llseek = generic_file_llseek, }; static int sel_open_handle_status(struct inode *inode, struct file *filp) { struct page *status = selinux_kernel_status_page(); if (!status) return -ENOMEM; filp->private_data = status; return 0; } static ssize_t sel_read_handle_status(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct page *status = filp->private_data; BUG_ON(!status); return simple_read_from_buffer(buf, count, ppos, page_address(status), sizeof(struct selinux_kernel_status)); } static int sel_mmap_handle_status(struct file *filp, struct vm_area_struct *vma) { struct page *status = filp->private_data; unsigned long size = vma->vm_end - vma->vm_start; BUG_ON(!status); /* only allows one page from the head */ if (vma->vm_pgoff > 0 || size != PAGE_SIZE) return -EIO; /* disallow writable mapping */ if (vma->vm_flags & VM_WRITE) return -EPERM; /* disallow mprotect() turns it into writable */ vm_flags_clear(vma, VM_MAYWRITE); return remap_pfn_range(vma, vma->vm_start, page_to_pfn(status), size, vma->vm_page_prot); } static const struct file_operations sel_handle_status_ops = { .open = sel_open_handle_status, .read = sel_read_handle_status, .mmap = sel_mmap_handle_status, .llseek = generic_file_llseek, }; static ssize_t sel_write_disable(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *page; ssize_t length; int new_value; if (count >= PAGE_SIZE) return -ENOMEM; /* No partial writes. */ if (*ppos != 0) return -EINVAL; page = memdup_user_nul(buf, count); if (IS_ERR(page)) return PTR_ERR(page); if (sscanf(page, "%d", &new_value) != 1) { length = -EINVAL; goto out; } length = count; if (new_value) { pr_err("SELinux: https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-runtime-disable\n"); pr_err("SELinux: Runtime disable is not supported, use selinux=0 on the kernel cmdline.\n"); } out: kfree(page); return length; } static const struct file_operations sel_disable_ops = { .write = sel_write_disable, .llseek = generic_file_llseek, }; static ssize_t sel_read_policyvers(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { char tmpbuf[TMPBUFLEN]; ssize_t length; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", POLICYDB_VERSION_MAX); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static const struct file_operations sel_policyvers_ops = { .read = sel_read_policyvers, .llseek = generic_file_llseek, }; /* declaration for sel_write_load */ static int sel_make_bools(struct selinux_policy *newpolicy, struct dentry *bool_dir, unsigned int *bool_num, char ***bool_pending_names, int **bool_pending_values); static int sel_make_classes(struct selinux_policy *newpolicy, struct dentry *class_dir, unsigned long *last_class_ino); /* declaration for sel_make_class_dirs */ static struct dentry *sel_make_dir(struct dentry *dir, const char *name, unsigned long *ino); /* declaration for sel_make_policy_nodes */ static struct dentry *sel_make_swapover_dir(struct super_block *sb, unsigned long *ino); static ssize_t sel_read_mls(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { char tmpbuf[TMPBUFLEN]; ssize_t length; length = scnprintf(tmpbuf, TMPBUFLEN, "%d", security_mls_enabled()); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static const struct file_operations sel_mls_ops = { .read = sel_read_mls, .llseek = generic_file_llseek, }; struct policy_load_memory { size_t len; void *data; }; static int sel_open_policy(struct inode *inode, struct file *filp) { struct selinux_fs_info *fsi = inode->i_sb->s_fs_info; struct policy_load_memory *plm = NULL; int rc; BUG_ON(filp->private_data); mutex_lock(&selinux_state.policy_mutex); rc = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__READ_POLICY, NULL); if (rc) goto err; rc = -EBUSY; if (fsi->policy_opened) goto err; rc = -ENOMEM; plm = kzalloc(sizeof(*plm), GFP_KERNEL); if (!plm) goto err; rc = security_read_policy(&plm->data, &plm->len); if (rc) goto err; if ((size_t)i_size_read(inode) != plm->len) { inode_lock(inode); i_size_write(inode, plm->len); inode_unlock(inode); } fsi->policy_opened = 1; filp->private_data = plm; mutex_unlock(&selinux_state.policy_mutex); return 0; err: mutex_unlock(&selinux_state.policy_mutex); if (plm) vfree(plm->data); kfree(plm); return rc; } static int sel_release_policy(struct inode *inode, struct file *filp) { struct selinux_fs_info *fsi = inode->i_sb->s_fs_info; struct policy_load_memory *plm = filp->private_data; BUG_ON(!plm); fsi->policy_opened = 0; vfree(plm->data); kfree(plm); return 0; } static ssize_t sel_read_policy(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { struct policy_load_memory *plm = filp->private_data; int ret; ret = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__READ_POLICY, NULL); if (ret) return ret; return simple_read_from_buffer(buf, count, ppos, plm->data, plm->len); } static vm_fault_t sel_mmap_policy_fault(struct vm_fault *vmf) { struct policy_load_memory *plm = vmf->vma->vm_file->private_data; unsigned long offset; struct page *page; if (vmf->flags & (FAULT_FLAG_MKWRITE | FAULT_FLAG_WRITE)) return VM_FAULT_SIGBUS; offset = vmf->pgoff << PAGE_SHIFT; if (offset >= roundup(plm->len, PAGE_SIZE)) return VM_FAULT_SIGBUS; page = vmalloc_to_page(plm->data + offset); get_page(page); vmf->page = page; return 0; } static const struct vm_operations_struct sel_mmap_policy_ops = { .fault = sel_mmap_policy_fault, .page_mkwrite = sel_mmap_policy_fault, }; static int sel_mmap_policy(struct file *filp, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHARED) { /* do not allow mprotect to make mapping writable */ vm_flags_clear(vma, VM_MAYWRITE); if (vma->vm_flags & VM_WRITE) return -EACCES; } vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &sel_mmap_policy_ops; return 0; } static const struct file_operations sel_policy_ops = { .open = sel_open_policy, .read = sel_read_policy, .mmap = sel_mmap_policy, .release = sel_release_policy, .llseek = generic_file_llseek, }; static void sel_remove_old_bool_data(unsigned int bool_num, char **bool_names, int *bool_values) { u32 i; /* bool_dir cleanup */ for (i = 0; i < bool_num; i++) kfree(bool_names[i]); kfree(bool_names); kfree(bool_values); } static int sel_make_policy_nodes(struct selinux_fs_info *fsi, struct selinux_policy *newpolicy) { int ret = 0; struct dentry *tmp_parent, *tmp_bool_dir, *tmp_class_dir; unsigned int bool_num = 0; char **bool_names = NULL; int *bool_values = NULL; unsigned long tmp_ino = fsi->last_ino; /* Don't increment last_ino in this function */ tmp_parent = sel_make_swapover_dir(fsi->sb, &tmp_ino); if (IS_ERR(tmp_parent)) return PTR_ERR(tmp_parent); tmp_ino = fsi->bool_dir->d_inode->i_ino - 1; /* sel_make_dir will increment and set */ tmp_bool_dir = sel_make_dir(tmp_parent, BOOL_DIR_NAME, &tmp_ino); if (IS_ERR(tmp_bool_dir)) { ret = PTR_ERR(tmp_bool_dir); goto out; } tmp_ino = fsi->class_dir->d_inode->i_ino - 1; /* sel_make_dir will increment and set */ tmp_class_dir = sel_make_dir(tmp_parent, CLASS_DIR_NAME, &tmp_ino); if (IS_ERR(tmp_class_dir)) { ret = PTR_ERR(tmp_class_dir); goto out; } ret = sel_make_bools(newpolicy, tmp_bool_dir, &bool_num, &bool_names, &bool_values); if (ret) goto out; ret = sel_make_classes(newpolicy, tmp_class_dir, &fsi->last_class_ino); if (ret) goto out; lock_rename(tmp_parent, fsi->sb->s_root); /* booleans */ d_exchange(tmp_bool_dir, fsi->bool_dir); swap(fsi->bool_num, bool_num); swap(fsi->bool_pending_names, bool_names); swap(fsi->bool_pending_values, bool_values); fsi->bool_dir = tmp_bool_dir; /* classes */ d_exchange(tmp_class_dir, fsi->class_dir); fsi->class_dir = tmp_class_dir; unlock_rename(tmp_parent, fsi->sb->s_root); out: sel_remove_old_bool_data(bool_num, bool_names, bool_values); /* Since the other temporary dirs are children of tmp_parent * this will handle all the cleanup in the case of a failure before * the swapover */ simple_recursive_removal(tmp_parent, NULL); return ret; } static ssize_t sel_write_load(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct selinux_fs_info *fsi; struct selinux_load_state load_state; ssize_t length; void *data = NULL; /* no partial writes */ if (*ppos) return -EINVAL; /* no empty policies */ if (!count) return -EINVAL; mutex_lock(&selinux_state.policy_mutex); length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__LOAD_POLICY, NULL); if (length) goto out; data = vmalloc(count); if (!data) { length = -ENOMEM; goto out; } if (copy_from_user(data, buf, count) != 0) { length = -EFAULT; goto out; } length = security_load_policy(data, count, &load_state); if (length) { pr_warn_ratelimited("SELinux: failed to load policy\n"); goto out; } fsi = file_inode(file)->i_sb->s_fs_info; length = sel_make_policy_nodes(fsi, load_state.policy); if (length) { pr_warn_ratelimited("SELinux: failed to initialize selinuxfs\n"); selinux_policy_cancel(&load_state); goto out; } selinux_policy_commit(&load_state); length = count; audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_POLICY_LOAD, "auid=%u ses=%u lsm=selinux res=1", from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); out: mutex_unlock(&selinux_state.policy_mutex); vfree(data); return length; } static const struct file_operations sel_load_ops = { .write = sel_write_load, .llseek = generic_file_llseek, }; static ssize_t sel_write_context(struct file *file, char *buf, size_t size) { char *canon = NULL; u32 sid, len; ssize_t length; length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__CHECK_CONTEXT, NULL); if (length) goto out; length = security_context_to_sid(buf, size, &sid, GFP_KERNEL); if (length) goto out; length = security_sid_to_context(sid, &canon, &len); if (length) goto out; length = -ERANGE; if (len > SIMPLE_TRANSACTION_LIMIT) { pr_err("SELinux: %s: context size (%u) exceeds " "payload max\n", __func__, len); goto out; } memcpy(buf, canon, len); length = len; out: kfree(canon); return length; } static ssize_t sel_read_checkreqprot(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { char tmpbuf[TMPBUFLEN]; ssize_t length; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", checkreqprot_get()); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static ssize_t sel_write_checkreqprot(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *page; ssize_t length; unsigned int new_value; length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__SETCHECKREQPROT, NULL); if (length) return length; if (count >= PAGE_SIZE) return -ENOMEM; /* No partial writes. */ if (*ppos != 0) return -EINVAL; page = memdup_user_nul(buf, count); if (IS_ERR(page)) return PTR_ERR(page); if (sscanf(page, "%u", &new_value) != 1) { length = -EINVAL; goto out; } length = count; if (new_value) { char comm[sizeof(current->comm)]; memcpy(comm, current->comm, sizeof(comm)); pr_err("SELinux: %s (%d) set checkreqprot to 1. This is no longer supported.\n", comm, current->pid); } selinux_ima_measure_state(); out: kfree(page); return length; } static const struct file_operations sel_checkreqprot_ops = { .read = sel_read_checkreqprot, .write = sel_write_checkreqprot, .llseek = generic_file_llseek, }; static ssize_t sel_write_validatetrans(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *oldcon = NULL, *newcon = NULL, *taskcon = NULL; char *req = NULL; u32 osid, nsid, tsid; u16 tclass; int rc; rc = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__VALIDATE_TRANS, NULL); if (rc) goto out; rc = -ENOMEM; if (count >= PAGE_SIZE) goto out; /* No partial writes. */ rc = -EINVAL; if (*ppos != 0) goto out; req = memdup_user_nul(buf, count); if (IS_ERR(req)) { rc = PTR_ERR(req); req = NULL; goto out; } rc = -ENOMEM; oldcon = kzalloc(count + 1, GFP_KERNEL); if (!oldcon) goto out; newcon = kzalloc(count + 1, GFP_KERNEL); if (!newcon) goto out; taskcon = kzalloc(count + 1, GFP_KERNEL); if (!taskcon) goto out; rc = -EINVAL; if (sscanf(req, "%s %s %hu %s", oldcon, newcon, &tclass, taskcon) != 4) goto out; rc = security_context_str_to_sid(oldcon, &osid, GFP_KERNEL); if (rc) goto out; rc = security_context_str_to_sid(newcon, &nsid, GFP_KERNEL); if (rc) goto out; rc = security_context_str_to_sid(taskcon, &tsid, GFP_KERNEL); if (rc) goto out; rc = security_validate_transition_user(osid, nsid, tsid, tclass); if (!rc) rc = count; out: kfree(req); kfree(oldcon); kfree(newcon); kfree(taskcon); return rc; } static const struct file_operations sel_transition_ops = { .write = sel_write_validatetrans, .llseek = generic_file_llseek, }; /* * Remaining nodes use transaction based IO methods like nfsd/nfsctl.c */ static ssize_t sel_write_access(struct file *file, char *buf, size_t size); static ssize_t sel_write_create(struct file *file, char *buf, size_t size); static ssize_t sel_write_relabel(struct file *file, char *buf, size_t size); static ssize_t sel_write_user(struct file *file, char *buf, size_t size); static ssize_t sel_write_member(struct file *file, char *buf, size_t size); static ssize_t (*const write_op[])(struct file *, char *, size_t) = { [SEL_ACCESS] = sel_write_access, [SEL_CREATE] = sel_write_create, [SEL_RELABEL] = sel_write_relabel, [SEL_USER] = sel_write_user, [SEL_MEMBER] = sel_write_member, [SEL_CONTEXT] = sel_write_context, }; static ssize_t selinux_transaction_write(struct file *file, const char __user *buf, size_t size, loff_t *pos) { ino_t ino = file_inode(file)->i_ino; char *data; ssize_t rv; if (ino >= ARRAY_SIZE(write_op) || !write_op[ino]) return -EINVAL; data = simple_transaction_get(file, buf, size); if (IS_ERR(data)) return PTR_ERR(data); rv = write_op[ino](file, data, size); if (rv > 0) { simple_transaction_set(file, rv); rv = size; } return rv; } static const struct file_operations transaction_ops = { .write = selinux_transaction_write, .read = simple_transaction_read, .release = simple_transaction_release, .llseek = generic_file_llseek, }; /* * payload - write methods * If the method has a response, the response should be put in buf, * and the length returned. Otherwise return 0 or and -error. */ static ssize_t sel_write_access(struct file *file, char *buf, size_t size) { char *scon = NULL, *tcon = NULL; u32 ssid, tsid; u16 tclass; struct av_decision avd; ssize_t length; length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__COMPUTE_AV, NULL); if (length) goto out; length = -ENOMEM; scon = kzalloc(size + 1, GFP_KERNEL); if (!scon) goto out; length = -ENOMEM; tcon = kzalloc(size + 1, GFP_KERNEL); if (!tcon) goto out; length = -EINVAL; if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3) goto out; length = security_context_str_to_sid(scon, &ssid, GFP_KERNEL); if (length) goto out; length = security_context_str_to_sid(tcon, &tsid, GFP_KERNEL); if (length) goto out; security_compute_av_user(ssid, tsid, tclass, &avd); length = scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%x %x %x %x %u %x", avd.allowed, 0xffffffff, avd.auditallow, avd.auditdeny, avd.seqno, avd.flags); out: kfree(tcon); kfree(scon); return length; } static ssize_t sel_write_create(struct file *file, char *buf, size_t size) { char *scon = NULL, *tcon = NULL; char *namebuf = NULL, *objname = NULL; u32 ssid, tsid, newsid; u16 tclass; ssize_t length; char *newcon = NULL; u32 len; int nargs; length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__COMPUTE_CREATE, NULL); if (length) goto out; length = -ENOMEM; scon = kzalloc(size + 1, GFP_KERNEL); if (!scon) goto out; length = -ENOMEM; tcon = kzalloc(size + 1, GFP_KERNEL); if (!tcon) goto out; length = -ENOMEM; namebuf = kzalloc(size + 1, GFP_KERNEL); if (!namebuf) goto out; length = -EINVAL; nargs = sscanf(buf, "%s %s %hu %s", scon, tcon, &tclass, namebuf); if (nargs < 3 || nargs > 4) goto out; if (nargs == 4) { /* * If and when the name of new object to be queried contains * either whitespace or multibyte characters, they shall be * encoded based on the percentage-encoding rule. * If not encoded, the sscanf logic picks up only left-half * of the supplied name; split by a whitespace unexpectedly. */ char *r, *w; int c1, c2; r = w = namebuf; do { c1 = *r++; if (c1 == '+') c1 = ' '; else if (c1 == '%') { c1 = hex_to_bin(*r++); if (c1 < 0) goto out; c2 = hex_to_bin(*r++); if (c2 < 0) goto out; c1 = (c1 << 4) | c2; } *w++ = c1; } while (c1 != '\0'); objname = namebuf; } length = security_context_str_to_sid(scon, &ssid, GFP_KERNEL); if (length) goto out; length = security_context_str_to_sid(tcon, &tsid, GFP_KERNEL); if (length) goto out; length = security_transition_sid_user(ssid, tsid, tclass, objname, &newsid); if (length) goto out; length = security_sid_to_context(newsid, &newcon, &len); if (length) goto out; length = -ERANGE; if (len > SIMPLE_TRANSACTION_LIMIT) { pr_err("SELinux: %s: context size (%u) exceeds " "payload max\n", __func__, len); goto out; } memcpy(buf, newcon, len); length = len; out: kfree(newcon); kfree(namebuf); kfree(tcon); kfree(scon); return length; } static ssize_t sel_write_relabel(struct file *file, char *buf, size_t size) { char *scon = NULL, *tcon = NULL; u32 ssid, tsid, newsid; u16 tclass; ssize_t length; char *newcon = NULL; u32 len; length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__COMPUTE_RELABEL, NULL); if (length) goto out; length = -ENOMEM; scon = kzalloc(size + 1, GFP_KERNEL); if (!scon) goto out; length = -ENOMEM; tcon = kzalloc(size + 1, GFP_KERNEL); if (!tcon) goto out; length = -EINVAL; if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3) goto out; length = security_context_str_to_sid(scon, &ssid, GFP_KERNEL); if (length) goto out; length = security_context_str_to_sid(tcon, &tsid, GFP_KERNEL); if (length) goto out; length = security_change_sid(ssid, tsid, tclass, &newsid); if (length) goto out; length = security_sid_to_context(newsid, &newcon, &len); if (length) goto out; length = -ERANGE; if (len > SIMPLE_TRANSACTION_LIMIT) goto out; memcpy(buf, newcon, len); length = len; out: kfree(newcon); kfree(tcon); kfree(scon); return length; } static ssize_t sel_write_user(struct file *file, char *buf, size_t size) { char *con = NULL, *user = NULL, *ptr; u32 sid, *sids = NULL; ssize_t length; char *newcon; int rc; u32 i, len, nsids; length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__COMPUTE_USER, NULL); if (length) goto out; length = -ENOMEM; con = kzalloc(size + 1, GFP_KERNEL); if (!con) goto out; length = -ENOMEM; user = kzalloc(size + 1, GFP_KERNEL); if (!user) goto out; length = -EINVAL; if (sscanf(buf, "%s %s", con, user) != 2) goto out; length = security_context_str_to_sid(con, &sid, GFP_KERNEL); if (length) goto out; length = security_get_user_sids(sid, user, &sids, &nsids); if (length) goto out; length = sprintf(buf, "%u", nsids) + 1; ptr = buf + length; for (i = 0; i < nsids; i++) { rc = security_sid_to_context(sids[i], &newcon, &len); if (rc) { length = rc; goto out; } if ((length + len) >= SIMPLE_TRANSACTION_LIMIT) { kfree(newcon); length = -ERANGE; goto out; } memcpy(ptr, newcon, len); kfree(newcon); ptr += len; length += len; } out: kfree(sids); kfree(user); kfree(con); return length; } static ssize_t sel_write_member(struct file *file, char *buf, size_t size) { char *scon = NULL, *tcon = NULL; u32 ssid, tsid, newsid; u16 tclass; ssize_t length; char *newcon = NULL; u32 len; length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__COMPUTE_MEMBER, NULL); if (length) goto out; length = -ENOMEM; scon = kzalloc(size + 1, GFP_KERNEL); if (!scon) goto out; length = -ENOMEM; tcon = kzalloc(size + 1, GFP_KERNEL); if (!tcon) goto out; length = -EINVAL; if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3) goto out; length = security_context_str_to_sid(scon, &ssid, GFP_KERNEL); if (length) goto out; length = security_context_str_to_sid(tcon, &tsid, GFP_KERNEL); if (length) goto out; length = security_member_sid(ssid, tsid, tclass, &newsid); if (length) goto out; length = security_sid_to_context(newsid, &newcon, &len); if (length) goto out; length = -ERANGE; if (len > SIMPLE_TRANSACTION_LIMIT) { pr_err("SELinux: %s: context size (%u) exceeds " "payload max\n", __func__, len); goto out; } memcpy(buf, newcon, len); length = len; out: kfree(newcon); kfree(tcon); kfree(scon); return length; } static struct inode *sel_make_inode(struct super_block *sb, umode_t mode) { struct inode *ret = new_inode(sb); if (ret) { ret->i_mode = mode; simple_inode_init_ts(ret); } return ret; } static ssize_t sel_read_bool(struct file *filep, char __user *buf, size_t count, loff_t *ppos) { struct selinux_fs_info *fsi = file_inode(filep)->i_sb->s_fs_info; char *page = NULL; ssize_t length; ssize_t ret; int cur_enforcing; unsigned index = file_inode(filep)->i_ino & SEL_INO_MASK; const char *name = filep->f_path.dentry->d_name.name; mutex_lock(&selinux_state.policy_mutex); ret = -EINVAL; if (index >= fsi->bool_num || strcmp(name, fsi->bool_pending_names[index])) goto out_unlock; ret = -ENOMEM; page = (char *)get_zeroed_page(GFP_KERNEL); if (!page) goto out_unlock; cur_enforcing = security_get_bool_value(index); if (cur_enforcing < 0) { ret = cur_enforcing; goto out_unlock; } length = scnprintf(page, PAGE_SIZE, "%d %d", cur_enforcing, fsi->bool_pending_values[index]); mutex_unlock(&selinux_state.policy_mutex); ret = simple_read_from_buffer(buf, count, ppos, page, length); out_free: free_page((unsigned long)page); return ret; out_unlock: mutex_unlock(&selinux_state.policy_mutex); goto out_free; } static ssize_t sel_write_bool(struct file *filep, const char __user *buf, size_t count, loff_t *ppos) { struct selinux_fs_info *fsi = file_inode(filep)->i_sb->s_fs_info; char *page = NULL; ssize_t length; int new_value; unsigned index = file_inode(filep)->i_ino & SEL_INO_MASK; const char *name = filep->f_path.dentry->d_name.name; if (count >= PAGE_SIZE) return -ENOMEM; /* No partial writes. */ if (*ppos != 0) return -EINVAL; page = memdup_user_nul(buf, count); if (IS_ERR(page)) return PTR_ERR(page); mutex_lock(&selinux_state.policy_mutex); length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__SETBOOL, NULL); if (length) goto out; length = -EINVAL; if (index >= fsi->bool_num || strcmp(name, fsi->bool_pending_names[index])) goto out; length = -EINVAL; if (sscanf(page, "%d", &new_value) != 1) goto out; if (new_value) new_value = 1; fsi->bool_pending_values[index] = new_value; length = count; out: mutex_unlock(&selinux_state.policy_mutex); kfree(page); return length; } static const struct file_operations sel_bool_ops = { .read = sel_read_bool, .write = sel_write_bool, .llseek = generic_file_llseek, }; static ssize_t sel_commit_bools_write(struct file *filep, const char __user *buf, size_t count, loff_t *ppos) { struct selinux_fs_info *fsi = file_inode(filep)->i_sb->s_fs_info; char *page = NULL; ssize_t length; int new_value; if (count >= PAGE_SIZE) return -ENOMEM; /* No partial writes. */ if (*ppos != 0) return -EINVAL; page = memdup_user_nul(buf, count); if (IS_ERR(page)) return PTR_ERR(page); mutex_lock(&selinux_state.policy_mutex); length = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__SETBOOL, NULL); if (length) goto out; length = -EINVAL; if (sscanf(page, "%d", &new_value) != 1) goto out; length = 0; if (new_value && fsi->bool_pending_values) length = security_set_bools(fsi->bool_num, fsi->bool_pending_values); if (!length) length = count; out: mutex_unlock(&selinux_state.policy_mutex); kfree(page); return length; } static const struct file_operations sel_commit_bools_ops = { .write = sel_commit_bools_write, .llseek = generic_file_llseek, }; static int sel_make_bools(struct selinux_policy *newpolicy, struct dentry *bool_dir, unsigned int *bool_num, char ***bool_pending_names, int **bool_pending_values) { int ret; char **names, *page; u32 i, num; page = (char *)get_zeroed_page(GFP_KERNEL); if (!page) return -ENOMEM; ret = security_get_bools(newpolicy, &num, &names, bool_pending_values); if (ret) goto out; *bool_num = num; *bool_pending_names = names; for (i = 0; i < num; i++) { struct dentry *dentry; struct inode *inode; struct inode_security_struct *isec; ssize_t len; u32 sid; len = snprintf(page, PAGE_SIZE, "/%s/%s", BOOL_DIR_NAME, names[i]); if (len >= PAGE_SIZE) { ret = -ENAMETOOLONG; break; } dentry = d_alloc_name(bool_dir, names[i]); if (!dentry) { ret = -ENOMEM; break; } inode = sel_make_inode(bool_dir->d_sb, S_IFREG | S_IRUGO | S_IWUSR); if (!inode) { dput(dentry); ret = -ENOMEM; break; } isec = selinux_inode(inode); ret = selinux_policy_genfs_sid(newpolicy, "selinuxfs", page, SECCLASS_FILE, &sid); if (ret) { pr_warn_ratelimited("SELinux: no sid found, defaulting to security isid for %s\n", page); sid = SECINITSID_SECURITY; } isec->sid = sid; isec->initialized = LABEL_INITIALIZED; inode->i_fop = &sel_bool_ops; inode->i_ino = i|SEL_BOOL_INO_OFFSET; d_add(dentry, inode); } out: free_page((unsigned long)page); return ret; } static ssize_t sel_read_avc_cache_threshold(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { char tmpbuf[TMPBUFLEN]; ssize_t length; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", avc_get_cache_threshold()); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static ssize_t sel_write_avc_cache_threshold(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *page; ssize_t ret; unsigned int new_value; ret = avc_has_perm(current_sid(), SECINITSID_SECURITY, SECCLASS_SECURITY, SECURITY__SETSECPARAM, NULL); if (ret) return ret; if (count >= PAGE_SIZE) return -ENOMEM; /* No partial writes. */ if (*ppos != 0) return -EINVAL; page = memdup_user_nul(buf, count); if (IS_ERR(page)) return PTR_ERR(page); ret = -EINVAL; if (sscanf(page, "%u", &new_value) != 1) goto out; avc_set_cache_threshold(new_value); ret = count; out: kfree(page); return ret; } static ssize_t sel_read_avc_hash_stats(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { char *page; ssize_t length; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; length = avc_get_hash_stats(page); if (length >= 0) length = simple_read_from_buffer(buf, count, ppos, page, length); free_page((unsigned long)page); return length; } static ssize_t sel_read_sidtab_hash_stats(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { char *page; ssize_t length; page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; length = security_sidtab_hash_stats(page); if (length >= 0) length = simple_read_from_buffer(buf, count, ppos, page, length); free_page((unsigned long)page); return length; } static const struct file_operations sel_sidtab_hash_stats_ops = { .read = sel_read_sidtab_hash_stats, .llseek = generic_file_llseek, }; static const struct file_operations sel_avc_cache_threshold_ops = { .read = sel_read_avc_cache_threshold, .write = sel_write_avc_cache_threshold, .llseek = generic_file_llseek, }; static const struct file_operations sel_avc_hash_stats_ops = { .read = sel_read_avc_hash_stats, .llseek = generic_file_llseek, }; #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS static struct avc_cache_stats *sel_avc_get_stat_idx(loff_t *idx) { int cpu; for (cpu = *idx; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *idx = cpu + 1; return &per_cpu(avc_cache_stats, cpu); } (*idx)++; return NULL; } static void *sel_avc_stats_seq_start(struct seq_file *seq, loff_t *pos) { loff_t n = *pos - 1; if (*pos == 0) return SEQ_START_TOKEN; return sel_avc_get_stat_idx(&n); } static void *sel_avc_stats_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return sel_avc_get_stat_idx(pos); } static int sel_avc_stats_seq_show(struct seq_file *seq, void *v) { struct avc_cache_stats *st = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, "lookups hits misses allocations reclaims frees\n"); } else { unsigned int lookups = st->lookups; unsigned int misses = st->misses; unsigned int hits = lookups - misses; seq_printf(seq, "%u %u %u %u %u %u\n", lookups, hits, misses, st->allocations, st->reclaims, st->frees); } return 0; } static void sel_avc_stats_seq_stop(struct seq_file *seq, void *v) { } static const struct seq_operations sel_avc_cache_stats_seq_ops = { .start = sel_avc_stats_seq_start, .next = sel_avc_stats_seq_next, .show = sel_avc_stats_seq_show, .stop = sel_avc_stats_seq_stop, }; static int sel_open_avc_cache_stats(struct inode *inode, struct file *file) { return seq_open(file, &sel_avc_cache_stats_seq_ops); } static const struct file_operations sel_avc_cache_stats_ops = { .open = sel_open_avc_cache_stats, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; #endif static int sel_make_avc_files(struct dentry *dir) { struct super_block *sb = dir->d_sb; struct selinux_fs_info *fsi = sb->s_fs_info; unsigned int i; static const struct tree_descr files[] = { { "cache_threshold", &sel_avc_cache_threshold_ops, S_IRUGO|S_IWUSR }, { "hash_stats", &sel_avc_hash_stats_ops, S_IRUGO }, #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS { "cache_stats", &sel_avc_cache_stats_ops, S_IRUGO }, #endif }; for (i = 0; i < ARRAY_SIZE(files); i++) { struct inode *inode; struct dentry *dentry; dentry = d_alloc_name(dir, files[i].name); if (!dentry) return -ENOMEM; inode = sel_make_inode(dir->d_sb, S_IFREG|files[i].mode); if (!inode) { dput(dentry); return -ENOMEM; } inode->i_fop = files[i].ops; inode->i_ino = ++fsi->last_ino; d_add(dentry, inode); } return 0; } static int sel_make_ss_files(struct dentry *dir) { struct super_block *sb = dir->d_sb; struct selinux_fs_info *fsi = sb->s_fs_info; unsigned int i; static const struct tree_descr files[] = { { "sidtab_hash_stats", &sel_sidtab_hash_stats_ops, S_IRUGO }, }; for (i = 0; i < ARRAY_SIZE(files); i++) { struct inode *inode; struct dentry *dentry; dentry = d_alloc_name(dir, files[i].name); if (!dentry) return -ENOMEM; inode = sel_make_inode(dir->d_sb, S_IFREG|files[i].mode); if (!inode) { dput(dentry); return -ENOMEM; } inode->i_fop = files[i].ops; inode->i_ino = ++fsi->last_ino; d_add(dentry, inode); } return 0; } static ssize_t sel_read_initcon(struct file *file, char __user *buf, size_t count, loff_t *ppos) { char *con; u32 sid, len; ssize_t ret; sid = file_inode(file)->i_ino&SEL_INO_MASK; ret = security_sid_to_context(sid, &con, &len); if (ret) return ret; ret = simple_read_from_buffer(buf, count, ppos, con, len); kfree(con); return ret; } static const struct file_operations sel_initcon_ops = { .read = sel_read_initcon, .llseek = generic_file_llseek, }; static int sel_make_initcon_files(struct dentry *dir) { unsigned int i; for (i = 1; i <= SECINITSID_NUM; i++) { struct inode *inode; struct dentry *dentry; const char *s = security_get_initial_sid_context(i); if (!s) continue; dentry = d_alloc_name(dir, s); if (!dentry) return -ENOMEM; inode = sel_make_inode(dir->d_sb, S_IFREG|S_IRUGO); if (!inode) { dput(dentry); return -ENOMEM; } inode->i_fop = &sel_initcon_ops; inode->i_ino = i|SEL_INITCON_INO_OFFSET; d_add(dentry, inode); } return 0; } static inline unsigned long sel_class_to_ino(u16 class) { return (class * (SEL_VEC_MAX + 1)) | SEL_CLASS_INO_OFFSET; } static inline u16 sel_ino_to_class(unsigned long ino) { return (ino & SEL_INO_MASK) / (SEL_VEC_MAX + 1); } static inline unsigned long sel_perm_to_ino(u16 class, u32 perm) { return (class * (SEL_VEC_MAX + 1) + perm) | SEL_CLASS_INO_OFFSET; } static inline u32 sel_ino_to_perm(unsigned long ino) { return (ino & SEL_INO_MASK) % (SEL_VEC_MAX + 1); } static ssize_t sel_read_class(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long ino = file_inode(file)->i_ino; char res[TMPBUFLEN]; ssize_t len = scnprintf(res, sizeof(res), "%d", sel_ino_to_class(ino)); return simple_read_from_buffer(buf, count, ppos, res, len); } static const struct file_operations sel_class_ops = { .read = sel_read_class, .llseek = generic_file_llseek, }; static ssize_t sel_read_perm(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long ino = file_inode(file)->i_ino; char res[TMPBUFLEN]; ssize_t len = scnprintf(res, sizeof(res), "%d", sel_ino_to_perm(ino)); return simple_read_from_buffer(buf, count, ppos, res, len); } static const struct file_operations sel_perm_ops = { .read = sel_read_perm, .llseek = generic_file_llseek, }; static ssize_t sel_read_policycap(struct file *file, char __user *buf, size_t count, loff_t *ppos) { int value; char tmpbuf[TMPBUFLEN]; ssize_t length; unsigned long i_ino = file_inode(file)->i_ino; value = security_policycap_supported(i_ino & SEL_INO_MASK); length = scnprintf(tmpbuf, TMPBUFLEN, "%d", value); return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); } static const struct file_operations sel_policycap_ops = { .read = sel_read_policycap, .llseek = generic_file_llseek, }; static int sel_make_perm_files(struct selinux_policy *newpolicy, char *objclass, int classvalue, struct dentry *dir) { u32 i, nperms; int rc; char **perms; rc = security_get_permissions(newpolicy, objclass, &perms, &nperms); if (rc) return rc; for (i = 0; i < nperms; i++) { struct inode *inode; struct dentry *dentry; rc = -ENOMEM; dentry = d_alloc_name(dir, perms[i]); if (!dentry) goto out; rc = -ENOMEM; inode = sel_make_inode(dir->d_sb, S_IFREG|S_IRUGO); if (!inode) { dput(dentry); goto out; } inode->i_fop = &sel_perm_ops; /* i+1 since perm values are 1-indexed */ inode->i_ino = sel_perm_to_ino(classvalue, i + 1); d_add(dentry, inode); } rc = 0; out: for (i = 0; i < nperms; i++) kfree(perms[i]); kfree(perms); return rc; } static int sel_make_class_dir_entries(struct selinux_policy *newpolicy, char *classname, int index, struct dentry *dir) { struct super_block *sb = dir->d_sb; struct selinux_fs_info *fsi = sb->s_fs_info; struct dentry *dentry = NULL; struct inode *inode = NULL; dentry = d_alloc_name(dir, "index"); if (!dentry) return -ENOMEM; inode = sel_make_inode(dir->d_sb, S_IFREG|S_IRUGO); if (!inode) { dput(dentry); return -ENOMEM; } inode->i_fop = &sel_class_ops; inode->i_ino = sel_class_to_ino(index); d_add(dentry, inode); dentry = sel_make_dir(dir, "perms", &fsi->last_class_ino); if (IS_ERR(dentry)) return PTR_ERR(dentry); return sel_make_perm_files(newpolicy, classname, index, dentry); } static int sel_make_classes(struct selinux_policy *newpolicy, struct dentry *class_dir, unsigned long *last_class_ino) { u32 i, nclasses; int rc; char **classes; rc = security_get_classes(newpolicy, &classes, &nclasses); if (rc) return rc; /* +2 since classes are 1-indexed */ *last_class_ino = sel_class_to_ino(nclasses + 2); for (i = 0; i < nclasses; i++) { struct dentry *class_name_dir; class_name_dir = sel_make_dir(class_dir, classes[i], last_class_ino); if (IS_ERR(class_name_dir)) { rc = PTR_ERR(class_name_dir); goto out; } /* i+1 since class values are 1-indexed */ rc = sel_make_class_dir_entries(newpolicy, classes[i], i + 1, class_name_dir); if (rc) goto out; } rc = 0; out: for (i = 0; i < nclasses; i++) kfree(classes[i]); kfree(classes); return rc; } static int sel_make_policycap(struct selinux_fs_info *fsi) { unsigned int iter; struct dentry *dentry = NULL; struct inode *inode = NULL; for (iter = 0; iter <= POLICYDB_CAP_MAX; iter++) { if (iter < ARRAY_SIZE(selinux_policycap_names)) dentry = d_alloc_name(fsi->policycap_dir, selinux_policycap_names[iter]); else dentry = d_alloc_name(fsi->policycap_dir, "unknown"); if (dentry == NULL) return -ENOMEM; inode = sel_make_inode(fsi->sb, S_IFREG | 0444); if (inode == NULL) { dput(dentry); return -ENOMEM; } inode->i_fop = &sel_policycap_ops; inode->i_ino = iter | SEL_POLICYCAP_INO_OFFSET; d_add(dentry, inode); } return 0; } static struct dentry *sel_make_dir(struct dentry *dir, const char *name, unsigned long *ino) { struct dentry *dentry = d_alloc_name(dir, name); struct inode *inode; if (!dentry) return ERR_PTR(-ENOMEM); inode = sel_make_inode(dir->d_sb, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) { dput(dentry); return ERR_PTR(-ENOMEM); } inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; inode->i_ino = ++(*ino); /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_add(dentry, inode); /* bump link count on parent directory, too */ inc_nlink(d_inode(dir)); return dentry; } static int reject_all(struct mnt_idmap *idmap, struct inode *inode, int mask) { return -EPERM; // no access for anyone, root or no root. } static const struct inode_operations swapover_dir_inode_operations = { .lookup = simple_lookup, .permission = reject_all, }; static struct dentry *sel_make_swapover_dir(struct super_block *sb, unsigned long *ino) { struct dentry *dentry = d_alloc_name(sb->s_root, ".swapover"); struct inode *inode; if (!dentry) return ERR_PTR(-ENOMEM); inode = sel_make_inode(sb, S_IFDIR); if (!inode) { dput(dentry); return ERR_PTR(-ENOMEM); } inode->i_op = &swapover_dir_inode_operations; inode->i_ino = ++(*ino); /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); inode_lock(sb->s_root->d_inode); d_add(dentry, inode); inc_nlink(sb->s_root->d_inode); inode_unlock(sb->s_root->d_inode); return dentry; } #define NULL_FILE_NAME "null" static int sel_fill_super(struct super_block *sb, struct fs_context *fc) { struct selinux_fs_info *fsi; int ret; struct dentry *dentry; struct inode *inode; struct inode_security_struct *isec; static const struct tree_descr selinux_files[] = { [SEL_LOAD] = {"load", &sel_load_ops, S_IRUSR|S_IWUSR}, [SEL_ENFORCE] = {"enforce", &sel_enforce_ops, S_IRUGO|S_IWUSR}, [SEL_CONTEXT] = {"context", &transaction_ops, S_IRUGO|S_IWUGO}, [SEL_ACCESS] = {"access", &transaction_ops, S_IRUGO|S_IWUGO}, [SEL_CREATE] = {"create", &transaction_ops, S_IRUGO|S_IWUGO}, [SEL_RELABEL] = {"relabel", &transaction_ops, S_IRUGO|S_IWUGO}, [SEL_USER] = {"user", &transaction_ops, S_IRUGO|S_IWUGO}, [SEL_POLICYVERS] = {"policyvers", &sel_policyvers_ops, S_IRUGO}, [SEL_COMMIT_BOOLS] = {"commit_pending_bools", &sel_commit_bools_ops, S_IWUSR}, [SEL_MLS] = {"mls", &sel_mls_ops, S_IRUGO}, [SEL_DISABLE] = {"disable", &sel_disable_ops, S_IWUSR}, [SEL_MEMBER] = {"member", &transaction_ops, S_IRUGO|S_IWUGO}, [SEL_CHECKREQPROT] = {"checkreqprot", &sel_checkreqprot_ops, S_IRUGO|S_IWUSR}, [SEL_REJECT_UNKNOWN] = {"reject_unknown", &sel_handle_unknown_ops, S_IRUGO}, [SEL_DENY_UNKNOWN] = {"deny_unknown", &sel_handle_unknown_ops, S_IRUGO}, [SEL_STATUS] = {"status", &sel_handle_status_ops, S_IRUGO}, [SEL_POLICY] = {"policy", &sel_policy_ops, S_IRUGO}, [SEL_VALIDATE_TRANS] = {"validatetrans", &sel_transition_ops, S_IWUGO}, /* last one */ {""} }; ret = selinux_fs_info_create(sb); if (ret) goto err; ret = simple_fill_super(sb, SELINUX_MAGIC, selinux_files); if (ret) goto err; fsi = sb->s_fs_info; fsi->bool_dir = sel_make_dir(sb->s_root, BOOL_DIR_NAME, &fsi->last_ino); if (IS_ERR(fsi->bool_dir)) { ret = PTR_ERR(fsi->bool_dir); fsi->bool_dir = NULL; goto err; } ret = -ENOMEM; dentry = d_alloc_name(sb->s_root, NULL_FILE_NAME); if (!dentry) goto err; ret = -ENOMEM; inode = sel_make_inode(sb, S_IFCHR | S_IRUGO | S_IWUGO); if (!inode) { dput(dentry); goto err; } inode->i_ino = ++fsi->last_ino; isec = selinux_inode(inode); isec->sid = SECINITSID_DEVNULL; isec->sclass = SECCLASS_CHR_FILE; isec->initialized = LABEL_INITIALIZED; init_special_inode(inode, S_IFCHR | S_IRUGO | S_IWUGO, MKDEV(MEM_MAJOR, 3)); d_add(dentry, inode); dentry = sel_make_dir(sb->s_root, "avc", &fsi->last_ino); if (IS_ERR(dentry)) { ret = PTR_ERR(dentry); goto err; } ret = sel_make_avc_files(dentry); if (ret) goto err; dentry = sel_make_dir(sb->s_root, "ss", &fsi->last_ino); if (IS_ERR(dentry)) { ret = PTR_ERR(dentry); goto err; } ret = sel_make_ss_files(dentry); if (ret) goto err; dentry = sel_make_dir(sb->s_root, "initial_contexts", &fsi->last_ino); if (IS_ERR(dentry)) { ret = PTR_ERR(dentry); goto err; } ret = sel_make_initcon_files(dentry); if (ret) goto err; fsi->class_dir = sel_make_dir(sb->s_root, CLASS_DIR_NAME, &fsi->last_ino); if (IS_ERR(fsi->class_dir)) { ret = PTR_ERR(fsi->class_dir); fsi->class_dir = NULL; goto err; } fsi->policycap_dir = sel_make_dir(sb->s_root, POLICYCAP_DIR_NAME, &fsi->last_ino); if (IS_ERR(fsi->policycap_dir)) { ret = PTR_ERR(fsi->policycap_dir); fsi->policycap_dir = NULL; goto err; } ret = sel_make_policycap(fsi); if (ret) { pr_err("SELinux: failed to load policy capabilities\n"); goto err; } return 0; err: pr_err("SELinux: %s: failed while creating inodes\n", __func__); selinux_fs_info_free(sb); return ret; } static int sel_get_tree(struct fs_context *fc) { return get_tree_single(fc, sel_fill_super); } static const struct fs_context_operations sel_context_ops = { .get_tree = sel_get_tree, }; static int sel_init_fs_context(struct fs_context *fc) { fc->ops = &sel_context_ops; return 0; } static void sel_kill_sb(struct super_block *sb) { selinux_fs_info_free(sb); kill_litter_super(sb); } static struct file_system_type sel_fs_type = { .name = "selinuxfs", .init_fs_context = sel_init_fs_context, .kill_sb = sel_kill_sb, }; struct path selinux_null __ro_after_init; static int __init init_sel_fs(void) { struct qstr null_name = QSTR_INIT(NULL_FILE_NAME, sizeof(NULL_FILE_NAME)-1); int err; if (!selinux_enabled_boot) return 0; err = sysfs_create_mount_point(fs_kobj, "selinux"); if (err) return err; err = register_filesystem(&sel_fs_type); if (err) { sysfs_remove_mount_point(fs_kobj, "selinux"); return err; } selinux_null.mnt = kern_mount(&sel_fs_type); if (IS_ERR(selinux_null.mnt)) { pr_err("selinuxfs: could not mount!\n"); err = PTR_ERR(selinux_null.mnt); selinux_null.mnt = NULL; return err; } selinux_null.dentry = d_hash_and_lookup(selinux_null.mnt->mnt_root, &null_name); if (IS_ERR(selinux_null.dentry)) { pr_err("selinuxfs: could not lookup null!\n"); err = PTR_ERR(selinux_null.dentry); selinux_null.dentry = NULL; return err; } /* * Try to pre-allocate the status page, so the sequence number of the * initial policy load can be stored. */ (void) selinux_kernel_status_page(); return err; } __initcall(init_sel_fs); |
| 10 3 3 1 2 2 2 7 7 7 1 3 3 3 1 8 1 7 30 1 27 3 7 2 1 2 1 1 11 11 1 6 4 4 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 | // SPDX-License-Identifier: GPL-2.0-only /* * CMOS/NV-RAM driver for Linux * * Copyright (C) 1997 Roman Hodek <Roman.Hodek@informatik.uni-erlangen.de> * idea by and with help from Richard Jelinek <rj@suse.de> * Portions copyright (c) 2001,2002 Sun Microsystems (thockin@sun.com) * * This driver allows you to access the contents of the non-volatile memory in * the mc146818rtc.h real-time clock. This chip is built into all PCs and into * many Atari machines. In the former it's called "CMOS-RAM", in the latter * "NVRAM" (NV stands for non-volatile). * * The data are supplied as a (seekable) character device, /dev/nvram. The * size of this file is dependent on the controller. The usual size is 114, * the number of freely available bytes in the memory (i.e., not used by the * RTC itself). * * Checksums over the NVRAM contents are managed by this driver. In case of a * bad checksum, reads and writes return -EIO. The checksum can be initialized * to a sane state either by ioctl(NVRAM_INIT) (clear whole NVRAM) or * ioctl(NVRAM_SETCKS) (doesn't change contents, just makes checksum valid * again; use with care!) * * 1.1 Cesar Barros: SMP locking fixes * added changelog * 1.2 Erik Gilling: Cobalt Networks support * Tim Hockin: general cleanup, Cobalt support * 1.3 Wim Van Sebroeck: convert PRINT_PROC to seq_file */ #define NVRAM_VERSION "1.3" #include <linux/module.h> #include <linux/nvram.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/miscdevice.h> #include <linux/ioport.h> #include <linux/fcntl.h> #include <linux/mc146818rtc.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/io.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/pagemap.h> #ifdef CONFIG_PPC #include <asm/nvram.h> #endif static DEFINE_MUTEX(nvram_mutex); static DEFINE_SPINLOCK(nvram_state_lock); static int nvram_open_cnt; /* #times opened */ static int nvram_open_mode; /* special open modes */ static ssize_t nvram_size; #define NVRAM_WRITE 1 /* opened for writing (exclusive) */ #define NVRAM_EXCL 2 /* opened with O_EXCL */ #ifdef CONFIG_X86 /* * These functions are provided to be called internally or by other parts of * the kernel. It's up to the caller to ensure correct checksum before reading * or after writing (needs to be done only once). * * It is worth noting that these functions all access bytes of general * purpose memory in the NVRAM - that is to say, they all add the * NVRAM_FIRST_BYTE offset. Pass them offsets into NVRAM as if you did not * know about the RTC cruft. */ #define NVRAM_BYTES (128 - NVRAM_FIRST_BYTE) /* Note that *all* calls to CMOS_READ and CMOS_WRITE must be done with * rtc_lock held. Due to the index-port/data-port design of the RTC, we * don't want two different things trying to get to it at once. (e.g. the * periodic 11 min sync from kernel/time/ntp.c vs. this driver.) */ static unsigned char __nvram_read_byte(int i) { return CMOS_READ(NVRAM_FIRST_BYTE + i); } static unsigned char pc_nvram_read_byte(int i) { unsigned long flags; unsigned char c; spin_lock_irqsave(&rtc_lock, flags); c = __nvram_read_byte(i); spin_unlock_irqrestore(&rtc_lock, flags); return c; } /* This races nicely with trying to read with checksum checking (nvram_read) */ static void __nvram_write_byte(unsigned char c, int i) { CMOS_WRITE(c, NVRAM_FIRST_BYTE + i); } static void pc_nvram_write_byte(unsigned char c, int i) { unsigned long flags; spin_lock_irqsave(&rtc_lock, flags); __nvram_write_byte(c, i); spin_unlock_irqrestore(&rtc_lock, flags); } /* On PCs, the checksum is built only over bytes 2..31 */ #define PC_CKS_RANGE_START 2 #define PC_CKS_RANGE_END 31 #define PC_CKS_LOC 32 static int __nvram_check_checksum(void) { int i; unsigned short sum = 0; unsigned short expect; for (i = PC_CKS_RANGE_START; i <= PC_CKS_RANGE_END; ++i) sum += __nvram_read_byte(i); expect = __nvram_read_byte(PC_CKS_LOC)<<8 | __nvram_read_byte(PC_CKS_LOC+1); return (sum & 0xffff) == expect; } static void __nvram_set_checksum(void) { int i; unsigned short sum = 0; for (i = PC_CKS_RANGE_START; i <= PC_CKS_RANGE_END; ++i) sum += __nvram_read_byte(i); __nvram_write_byte(sum >> 8, PC_CKS_LOC); __nvram_write_byte(sum & 0xff, PC_CKS_LOC + 1); } static long pc_nvram_set_checksum(void) { spin_lock_irq(&rtc_lock); __nvram_set_checksum(); spin_unlock_irq(&rtc_lock); return 0; } static long pc_nvram_initialize(void) { ssize_t i; spin_lock_irq(&rtc_lock); for (i = 0; i < NVRAM_BYTES; ++i) __nvram_write_byte(0, i); __nvram_set_checksum(); spin_unlock_irq(&rtc_lock); return 0; } static ssize_t pc_nvram_get_size(void) { return NVRAM_BYTES; } static ssize_t pc_nvram_read(char *buf, size_t count, loff_t *ppos) { char *p = buf; loff_t i; spin_lock_irq(&rtc_lock); if (!__nvram_check_checksum()) { spin_unlock_irq(&rtc_lock); return -EIO; } for (i = *ppos; count > 0 && i < NVRAM_BYTES; --count, ++i, ++p) *p = __nvram_read_byte(i); spin_unlock_irq(&rtc_lock); *ppos = i; return p - buf; } static ssize_t pc_nvram_write(char *buf, size_t count, loff_t *ppos) { char *p = buf; loff_t i; spin_lock_irq(&rtc_lock); if (!__nvram_check_checksum()) { spin_unlock_irq(&rtc_lock); return -EIO; } for (i = *ppos; count > 0 && i < NVRAM_BYTES; --count, ++i, ++p) __nvram_write_byte(*p, i); __nvram_set_checksum(); spin_unlock_irq(&rtc_lock); *ppos = i; return p - buf; } const struct nvram_ops arch_nvram_ops = { .read = pc_nvram_read, .write = pc_nvram_write, .read_byte = pc_nvram_read_byte, .write_byte = pc_nvram_write_byte, .get_size = pc_nvram_get_size, .set_checksum = pc_nvram_set_checksum, .initialize = pc_nvram_initialize, }; EXPORT_SYMBOL(arch_nvram_ops); #endif /* CONFIG_X86 */ /* * The are the file operation function for user access to /dev/nvram */ static loff_t nvram_misc_llseek(struct file *file, loff_t offset, int origin) { return generic_file_llseek_size(file, offset, origin, MAX_LFS_FILESIZE, nvram_size); } static ssize_t nvram_misc_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { char *tmp; ssize_t ret; if (*ppos >= nvram_size) return 0; count = min_t(size_t, count, nvram_size - *ppos); count = min_t(size_t, count, PAGE_SIZE); tmp = kmalloc(count, GFP_KERNEL); if (!tmp) return -ENOMEM; ret = nvram_read(tmp, count, ppos); if (ret <= 0) goto out; if (copy_to_user(buf, tmp, ret)) { *ppos -= ret; ret = -EFAULT; } out: kfree(tmp); return ret; } static ssize_t nvram_misc_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *tmp; ssize_t ret; if (*ppos >= nvram_size) return 0; count = min_t(size_t, count, nvram_size - *ppos); count = min_t(size_t, count, PAGE_SIZE); tmp = memdup_user(buf, count); if (IS_ERR(tmp)) return PTR_ERR(tmp); ret = nvram_write(tmp, count, ppos); kfree(tmp); return ret; } static long nvram_misc_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { long ret = -ENOTTY; switch (cmd) { #ifdef CONFIG_PPC case OBSOLETE_PMAC_NVRAM_GET_OFFSET: pr_warn("nvram: Using obsolete PMAC_NVRAM_GET_OFFSET ioctl\n"); fallthrough; case IOC_NVRAM_GET_OFFSET: ret = -EINVAL; #ifdef CONFIG_PPC_PMAC if (machine_is(powermac)) { int part, offset; if (copy_from_user(&part, (void __user *)arg, sizeof(part)) != 0) return -EFAULT; if (part < pmac_nvram_OF || part > pmac_nvram_NR) return -EINVAL; offset = pmac_get_partition(part); if (offset < 0) return -EINVAL; if (copy_to_user((void __user *)arg, &offset, sizeof(offset)) != 0) return -EFAULT; ret = 0; } #endif break; #ifdef CONFIG_PPC32 case IOC_NVRAM_SYNC: if (ppc_md.nvram_sync != NULL) { mutex_lock(&nvram_mutex); ppc_md.nvram_sync(); mutex_unlock(&nvram_mutex); } ret = 0; break; #endif #elif defined(CONFIG_X86) || defined(CONFIG_M68K) case NVRAM_INIT: /* initialize NVRAM contents and checksum */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (arch_nvram_ops.initialize != NULL) { mutex_lock(&nvram_mutex); ret = arch_nvram_ops.initialize(); mutex_unlock(&nvram_mutex); } break; case NVRAM_SETCKS: /* just set checksum, contents unchanged (maybe useful after * checksum garbaged somehow...) */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (arch_nvram_ops.set_checksum != NULL) { mutex_lock(&nvram_mutex); ret = arch_nvram_ops.set_checksum(); mutex_unlock(&nvram_mutex); } break; #endif /* CONFIG_X86 || CONFIG_M68K */ } return ret; } static int nvram_misc_open(struct inode *inode, struct file *file) { spin_lock(&nvram_state_lock); /* Prevent multiple readers/writers if desired. */ if ((nvram_open_cnt && (file->f_flags & O_EXCL)) || (nvram_open_mode & NVRAM_EXCL)) { spin_unlock(&nvram_state_lock); return -EBUSY; } #if defined(CONFIG_X86) || defined(CONFIG_M68K) /* Prevent multiple writers if the set_checksum ioctl is implemented. */ if ((arch_nvram_ops.set_checksum != NULL) && (file->f_mode & FMODE_WRITE) && (nvram_open_mode & NVRAM_WRITE)) { spin_unlock(&nvram_state_lock); return -EBUSY; } #endif if (file->f_flags & O_EXCL) nvram_open_mode |= NVRAM_EXCL; if (file->f_mode & FMODE_WRITE) nvram_open_mode |= NVRAM_WRITE; nvram_open_cnt++; spin_unlock(&nvram_state_lock); return 0; } static int nvram_misc_release(struct inode *inode, struct file *file) { spin_lock(&nvram_state_lock); nvram_open_cnt--; /* if only one instance is open, clear the EXCL bit */ if (nvram_open_mode & NVRAM_EXCL) nvram_open_mode &= ~NVRAM_EXCL; if (file->f_mode & FMODE_WRITE) nvram_open_mode &= ~NVRAM_WRITE; spin_unlock(&nvram_state_lock); return 0; } #if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) static const char * const floppy_types[] = { "none", "5.25'' 360k", "5.25'' 1.2M", "3.5'' 720k", "3.5'' 1.44M", "3.5'' 2.88M", "3.5'' 2.88M" }; static const char * const gfx_types[] = { "EGA, VGA, ... (with BIOS)", "CGA (40 cols)", "CGA (80 cols)", "monochrome", }; static void pc_nvram_proc_read(unsigned char *nvram, struct seq_file *seq, void *offset) { int checksum; int type; spin_lock_irq(&rtc_lock); checksum = __nvram_check_checksum(); spin_unlock_irq(&rtc_lock); seq_printf(seq, "Checksum status: %svalid\n", checksum ? "" : "not "); seq_printf(seq, "# floppies : %d\n", (nvram[6] & 1) ? (nvram[6] >> 6) + 1 : 0); seq_printf(seq, "Floppy 0 type : "); type = nvram[2] >> 4; if (type < ARRAY_SIZE(floppy_types)) seq_printf(seq, "%s\n", floppy_types[type]); else seq_printf(seq, "%d (unknown)\n", type); seq_printf(seq, "Floppy 1 type : "); type = nvram[2] & 0x0f; if (type < ARRAY_SIZE(floppy_types)) seq_printf(seq, "%s\n", floppy_types[type]); else seq_printf(seq, "%d (unknown)\n", type); seq_printf(seq, "HD 0 type : "); type = nvram[4] >> 4; if (type) seq_printf(seq, "%02x\n", type == 0x0f ? nvram[11] : type); else seq_printf(seq, "none\n"); seq_printf(seq, "HD 1 type : "); type = nvram[4] & 0x0f; if (type) seq_printf(seq, "%02x\n", type == 0x0f ? nvram[12] : type); else seq_printf(seq, "none\n"); seq_printf(seq, "HD type 48 data: %d/%d/%d C/H/S, precomp %d, lz %d\n", nvram[18] | (nvram[19] << 8), nvram[20], nvram[25], nvram[21] | (nvram[22] << 8), nvram[23] | (nvram[24] << 8)); seq_printf(seq, "HD type 49 data: %d/%d/%d C/H/S, precomp %d, lz %d\n", nvram[39] | (nvram[40] << 8), nvram[41], nvram[46], nvram[42] | (nvram[43] << 8), nvram[44] | (nvram[45] << 8)); seq_printf(seq, "DOS base memory: %d kB\n", nvram[7] | (nvram[8] << 8)); seq_printf(seq, "Extended memory: %d kB (configured), %d kB (tested)\n", nvram[9] | (nvram[10] << 8), nvram[34] | (nvram[35] << 8)); seq_printf(seq, "Gfx adapter : %s\n", gfx_types[(nvram[6] >> 4) & 3]); seq_printf(seq, "FPU : %sinstalled\n", (nvram[6] & 2) ? "" : "not "); return; } static int nvram_proc_read(struct seq_file *seq, void *offset) { unsigned char contents[NVRAM_BYTES]; int i = 0; spin_lock_irq(&rtc_lock); for (i = 0; i < NVRAM_BYTES; ++i) contents[i] = __nvram_read_byte(i); spin_unlock_irq(&rtc_lock); pc_nvram_proc_read(contents, seq, offset); return 0; } #endif /* CONFIG_X86 && CONFIG_PROC_FS */ static const struct file_operations nvram_misc_fops = { .owner = THIS_MODULE, .llseek = nvram_misc_llseek, .read = nvram_misc_read, .write = nvram_misc_write, .unlocked_ioctl = nvram_misc_ioctl, .open = nvram_misc_open, .release = nvram_misc_release, }; static struct miscdevice nvram_misc = { NVRAM_MINOR, "nvram", &nvram_misc_fops, }; static int __init nvram_module_init(void) { int ret; nvram_size = nvram_get_size(); if (nvram_size < 0) return nvram_size; ret = misc_register(&nvram_misc); if (ret) { pr_err("nvram: can't misc_register on minor=%d\n", NVRAM_MINOR); return ret; } #if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) if (!proc_create_single("driver/nvram", 0, NULL, nvram_proc_read)) { pr_err("nvram: can't create /proc/driver/nvram\n"); misc_deregister(&nvram_misc); return -ENOMEM; } #endif pr_info("Non-volatile memory driver v" NVRAM_VERSION "\n"); return 0; } static void __exit nvram_module_exit(void) { #if defined(CONFIG_X86) && defined(CONFIG_PROC_FS) remove_proc_entry("driver/nvram", NULL); #endif misc_deregister(&nvram_misc); } module_init(nvram_module_init); module_exit(nvram_module_exit); MODULE_DESCRIPTION("CMOS/NV-RAM driver for Linux"); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(NVRAM_MINOR); MODULE_ALIAS("devname:nvram"); |
| 7 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_SCHED_RED_H #define __NET_SCHED_RED_H #include <linux/types.h> #include <linux/bug.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> #include <net/dsfield.h> #include <linux/reciprocal_div.h> /* Random Early Detection (RED) algorithm. ======================================= Source: Sally Floyd and Van Jacobson, "Random Early Detection Gateways for Congestion Avoidance", 1993, IEEE/ACM Transactions on Networking. This file codes a "divisionless" version of RED algorithm as written down in Fig.17 of the paper. Short description. ------------------ When a new packet arrives we calculate the average queue length: avg = (1-W)*avg + W*current_queue_len, W is the filter time constant (chosen as 2^(-Wlog)), it controls the inertia of the algorithm. To allow larger bursts, W should be decreased. if (avg > th_max) -> packet marked (dropped). if (avg < th_min) -> packet passes. if (th_min < avg < th_max) we calculate probability: Pb = max_P * (avg - th_min)/(th_max-th_min) and mark (drop) packet with this probability. Pb changes from 0 (at avg==th_min) to max_P (avg==th_max). max_P should be small (not 1), usually 0.01..0.02 is good value. max_P is chosen as a number, so that max_P/(th_max-th_min) is a negative power of two in order arithmetic to contain only shifts. Parameters, settable by user: ----------------------------- qth_min - bytes (should be < qth_max/2) qth_max - bytes (should be at least 2*qth_min and less limit) Wlog - bits (<32) log(1/W). Plog - bits (<32) Plog is related to max_P by formula: max_P = (qth_max-qth_min)/2^Plog; F.e. if qth_max=128K and qth_min=32K, then Plog=22 corresponds to max_P=0.02 Scell_log Stab Lookup table for log((1-W)^(t/t_ave). NOTES: Upper bound on W. ----------------- If you want to allow bursts of L packets of size S, you should choose W: L + 1 - th_min/S < (1-(1-W)^L)/W th_min/S = 32 th_min/S = 4 log(W) L -1 33 -2 35 -3 39 -4 46 -5 57 -6 75 -7 101 -8 135 -9 190 etc. */ /* * Adaptative RED : An Algorithm for Increasing the Robustness of RED's AQM * (Sally FLoyd, Ramakrishna Gummadi, and Scott Shenker) August 2001 * * Every 500 ms: * if (avg > target and max_p <= 0.5) * increase max_p : max_p += alpha; * else if (avg < target and max_p >= 0.01) * decrease max_p : max_p *= beta; * * target :[qth_min + 0.4*(qth_min - qth_max), * qth_min + 0.6*(qth_min - qth_max)]. * alpha : min(0.01, max_p / 4) * beta : 0.9 * max_P is a Q0.32 fixed point number (with 32 bits mantissa) * max_P between 0.01 and 0.5 (1% - 50%) [ Its no longer a negative power of two ] */ #define RED_ONE_PERCENT ((u32)DIV_ROUND_CLOSEST(1ULL<<32, 100)) #define MAX_P_MIN (1 * RED_ONE_PERCENT) #define MAX_P_MAX (50 * RED_ONE_PERCENT) #define MAX_P_ALPHA(val) min(MAX_P_MIN, val / 4) #define RED_STAB_SIZE 256 #define RED_STAB_MASK (RED_STAB_SIZE - 1) struct red_stats { u32 prob_drop; /* Early probability drops */ u32 prob_mark; /* Early probability marks */ u32 forced_drop; /* Forced drops, qavg > max_thresh */ u32 forced_mark; /* Forced marks, qavg > max_thresh */ u32 pdrop; /* Drops due to queue limits */ }; struct red_parms { /* Parameters */ u32 qth_min; /* Min avg length threshold: Wlog scaled */ u32 qth_max; /* Max avg length threshold: Wlog scaled */ u32 Scell_max; u32 max_P; /* probability, [0 .. 1.0] 32 scaled */ /* reciprocal_value(max_P / qth_delta) */ struct reciprocal_value max_P_reciprocal; u32 qth_delta; /* max_th - min_th */ u32 target_min; /* min_th + 0.4*(max_th - min_th) */ u32 target_max; /* min_th + 0.6*(max_th - min_th) */ u8 Scell_log; u8 Wlog; /* log(W) */ u8 Plog; /* random number bits */ u8 Stab[RED_STAB_SIZE]; }; struct red_vars { /* Variables */ int qcount; /* Number of packets since last random number generation */ u32 qR; /* Cached random number */ unsigned long qavg; /* Average queue length: Wlog scaled */ ktime_t qidlestart; /* Start of current idle period */ }; static inline u32 red_maxp(u8 Plog) { return Plog < 32 ? (~0U >> Plog) : ~0U; } static inline void red_set_vars(struct red_vars *v) { /* Reset average queue length, the value is strictly bound * to the parameters below, resetting hurts a bit but leaving * it might result in an unreasonable qavg for a while. --TGR */ v->qavg = 0; v->qcount = -1; } static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log, u8 *stab) { if (fls(qth_min) + Wlog >= 32) return false; if (fls(qth_max) + Wlog >= 32) return false; if (Scell_log >= 32) return false; if (qth_max < qth_min) return false; if (stab) { int i; for (i = 0; i < RED_STAB_SIZE; i++) if (stab[i] >= 32) return false; } return true; } static inline int red_get_flags(unsigned char qopt_flags, unsigned char historic_mask, struct nlattr *flags_attr, unsigned char supported_mask, struct nla_bitfield32 *p_flags, unsigned char *p_userbits, struct netlink_ext_ack *extack) { struct nla_bitfield32 flags; if (qopt_flags && flags_attr) { NL_SET_ERR_MSG_MOD(extack, "flags should be passed either through qopt, or through a dedicated attribute"); return -EINVAL; } if (flags_attr) { flags = nla_get_bitfield32(flags_attr); } else { flags.selector = historic_mask; flags.value = qopt_flags & historic_mask; } *p_flags = flags; *p_userbits = qopt_flags & ~historic_mask; return 0; } static inline int red_validate_flags(unsigned char flags, struct netlink_ext_ack *extack) { if ((flags & TC_RED_NODROP) && !(flags & TC_RED_ECN)) { NL_SET_ERR_MSG_MOD(extack, "nodrop mode is only meaningful with ECN"); return -EINVAL; } return 0; } static inline void red_set_parms(struct red_parms *p, u32 qth_min, u32 qth_max, u8 Wlog, u8 Plog, u8 Scell_log, u8 *stab, u32 max_P) { int delta = qth_max - qth_min; u32 max_p_delta; WRITE_ONCE(p->qth_min, qth_min << Wlog); WRITE_ONCE(p->qth_max, qth_max << Wlog); WRITE_ONCE(p->Wlog, Wlog); WRITE_ONCE(p->Plog, Plog); if (delta <= 0) delta = 1; p->qth_delta = delta; if (!max_P) { max_P = red_maxp(Plog); max_P *= delta; /* max_P = (qth_max - qth_min)/2^Plog */ } WRITE_ONCE(p->max_P, max_P); max_p_delta = max_P / delta; max_p_delta = max(max_p_delta, 1U); p->max_P_reciprocal = reciprocal_value(max_p_delta); /* RED Adaptative target : * [min_th + 0.4*(min_th - max_th), * min_th + 0.6*(min_th - max_th)]. */ delta /= 5; p->target_min = qth_min + 2*delta; p->target_max = qth_min + 3*delta; WRITE_ONCE(p->Scell_log, Scell_log); p->Scell_max = (255 << Scell_log); if (stab) memcpy(p->Stab, stab, sizeof(p->Stab)); } static inline int red_is_idling(const struct red_vars *v) { return v->qidlestart != 0; } static inline void red_start_of_idle_period(struct red_vars *v) { v->qidlestart = ktime_get(); } static inline void red_end_of_idle_period(struct red_vars *v) { v->qidlestart = 0; } static inline void red_restart(struct red_vars *v) { red_end_of_idle_period(v); v->qavg = 0; v->qcount = -1; } static inline unsigned long red_calc_qavg_from_idle_time(const struct red_parms *p, const struct red_vars *v) { s64 delta = ktime_us_delta(ktime_get(), v->qidlestart); long us_idle = min_t(s64, delta, p->Scell_max); int shift; /* * The problem: ideally, average length queue recalculation should * be done over constant clock intervals. This is too expensive, so * that the calculation is driven by outgoing packets. * When the queue is idle we have to model this clock by hand. * * SF+VJ proposed to "generate": * * m = idletime / (average_pkt_size / bandwidth) * * dummy packets as a burst after idle time, i.e. * * v->qavg *= (1-W)^m * * This is an apparently overcomplicated solution (f.e. we have to * precompute a table to make this calculation in reasonable time) * I believe that a simpler model may be used here, * but it is field for experiments. */ shift = p->Stab[(us_idle >> p->Scell_log) & RED_STAB_MASK]; if (shift) return v->qavg >> shift; else { /* Approximate initial part of exponent with linear function: * * (1-W)^m ~= 1-mW + ... * * Seems, it is the best solution to * problem of too coarse exponent tabulation. */ us_idle = (v->qavg * (u64)us_idle) >> p->Scell_log; if (us_idle < (v->qavg >> 1)) return v->qavg - us_idle; else return v->qavg >> 1; } } static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p, const struct red_vars *v, unsigned int backlog) { /* * NOTE: v->qavg is fixed point number with point at Wlog. * The formula below is equivalent to floating point * version: * * qavg = qavg*(1-W) + backlog*W; * * --ANK (980924) */ return v->qavg + (backlog - (v->qavg >> p->Wlog)); } static inline unsigned long red_calc_qavg(const struct red_parms *p, const struct red_vars *v, unsigned int backlog) { if (!red_is_idling(v)) return red_calc_qavg_no_idle_time(p, v, backlog); else return red_calc_qavg_from_idle_time(p, v); } static inline u32 red_random(const struct red_parms *p) { return reciprocal_divide(get_random_u32(), p->max_P_reciprocal); } static inline int red_mark_probability(const struct red_parms *p, const struct red_vars *v, unsigned long qavg) { /* The formula used below causes questions. OK. qR is random number in the interval (0..1/max_P)*(qth_max-qth_min) i.e. 0..(2^Plog). If we used floating point arithmetic, it would be: (2^Plog)*rnd_num, where rnd_num is less 1. Taking into account, that qavg have fixed point at Wlog, two lines below have the following floating point equivalent: max_P*(qavg - qth_min)/(qth_max-qth_min) < rnd/qcount Any questions? --ANK (980924) */ return !(((qavg - p->qth_min) >> p->Wlog) * v->qcount < v->qR); } enum { RED_BELOW_MIN_THRESH, RED_BETWEEN_TRESH, RED_ABOVE_MAX_TRESH, }; static inline int red_cmp_thresh(const struct red_parms *p, unsigned long qavg) { if (qavg < p->qth_min) return RED_BELOW_MIN_THRESH; else if (qavg >= p->qth_max) return RED_ABOVE_MAX_TRESH; else return RED_BETWEEN_TRESH; } enum { RED_DONT_MARK, RED_PROB_MARK, RED_HARD_MARK, }; static inline int red_action(const struct red_parms *p, struct red_vars *v, unsigned long qavg) { switch (red_cmp_thresh(p, qavg)) { case RED_BELOW_MIN_THRESH: v->qcount = -1; return RED_DONT_MARK; case RED_BETWEEN_TRESH: if (++v->qcount) { if (red_mark_probability(p, v, qavg)) { v->qcount = 0; v->qR = red_random(p); return RED_PROB_MARK; } } else v->qR = red_random(p); return RED_DONT_MARK; case RED_ABOVE_MAX_TRESH: v->qcount = -1; return RED_HARD_MARK; } BUG(); return RED_DONT_MARK; } static inline void red_adaptative_algo(struct red_parms *p, struct red_vars *v) { unsigned long qavg; u32 max_p_delta; qavg = v->qavg; if (red_is_idling(v)) qavg = red_calc_qavg_from_idle_time(p, v); /* v->qavg is fixed point number with point at Wlog */ qavg >>= p->Wlog; if (qavg > p->target_max && p->max_P <= MAX_P_MAX) p->max_P += MAX_P_ALPHA(p->max_P); /* maxp = maxp + alpha */ else if (qavg < p->target_min && p->max_P >= MAX_P_MIN) p->max_P = (p->max_P/10)*9; /* maxp = maxp * Beta */ max_p_delta = DIV_ROUND_CLOSEST(p->max_P, p->qth_delta); max_p_delta = max(max_p_delta, 1U); p->max_P_reciprocal = reciprocal_value(max_p_delta); } #endif |
| 3 3 3 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Virtual PTP 1588 clock for use with KVM guests * * Copyright (C) 2017 Red Hat Inc. */ #include <linux/device.h> #include <linux/err.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/ptp_kvm.h> #include <uapi/linux/kvm_para.h> #include <asm/kvm_para.h> #include <uapi/asm/kvm_para.h> #include <linux/ptp_clock_kernel.h> struct kvm_ptp_clock { struct ptp_clock *ptp_clock; struct ptp_clock_info caps; }; static DEFINE_SPINLOCK(kvm_ptp_lock); static int ptp_kvm_get_time_fn(ktime_t *device_time, struct system_counterval_t *system_counter, void *ctx) { enum clocksource_ids cs_id; struct timespec64 tspec; u64 cycle; int ret; spin_lock(&kvm_ptp_lock); preempt_disable_notrace(); ret = kvm_arch_ptp_get_crosststamp(&cycle, &tspec, &cs_id); if (ret) { spin_unlock(&kvm_ptp_lock); preempt_enable_notrace(); return ret; } preempt_enable_notrace(); system_counter->cycles = cycle; system_counter->cs_id = cs_id; *device_time = timespec64_to_ktime(tspec); spin_unlock(&kvm_ptp_lock); return 0; } static int ptp_kvm_getcrosststamp(struct ptp_clock_info *ptp, struct system_device_crosststamp *xtstamp) { return get_device_system_crosststamp(ptp_kvm_get_time_fn, NULL, NULL, xtstamp); } /* * PTP clock operations */ static int ptp_kvm_adjfine(struct ptp_clock_info *ptp, long delta) { return -EOPNOTSUPP; } static int ptp_kvm_adjtime(struct ptp_clock_info *ptp, s64 delta) { return -EOPNOTSUPP; } static int ptp_kvm_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts) { return -EOPNOTSUPP; } static int ptp_kvm_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { long ret; struct timespec64 tspec; spin_lock(&kvm_ptp_lock); ret = kvm_arch_ptp_get_clock(&tspec); if (ret) { spin_unlock(&kvm_ptp_lock); return ret; } spin_unlock(&kvm_ptp_lock); memcpy(ts, &tspec, sizeof(struct timespec64)); return 0; } static int ptp_kvm_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { return -EOPNOTSUPP; } static const struct ptp_clock_info ptp_kvm_caps = { .owner = THIS_MODULE, .name = "KVM virtual PTP", .max_adj = 0, .n_ext_ts = 0, .n_pins = 0, .pps = 0, .adjfine = ptp_kvm_adjfine, .adjtime = ptp_kvm_adjtime, .gettime64 = ptp_kvm_gettime, .settime64 = ptp_kvm_settime, .enable = ptp_kvm_enable, .getcrosststamp = ptp_kvm_getcrosststamp, }; /* module operations */ static struct kvm_ptp_clock kvm_ptp_clock; static void __exit ptp_kvm_exit(void) { ptp_clock_unregister(kvm_ptp_clock.ptp_clock); kvm_arch_ptp_exit(); } static int __init ptp_kvm_init(void) { long ret; ret = kvm_arch_ptp_init(); if (ret) { if (ret != -EOPNOTSUPP) pr_err("fail to initialize ptp_kvm"); return ret; } kvm_ptp_clock.caps = ptp_kvm_caps; kvm_ptp_clock.ptp_clock = ptp_clock_register(&kvm_ptp_clock.caps, NULL); return PTR_ERR_OR_ZERO(kvm_ptp_clock.ptp_clock); } module_init(ptp_kvm_init); module_exit(ptp_kvm_exit); MODULE_AUTHOR("Marcelo Tosatti <mtosatti@redhat.com>"); MODULE_DESCRIPTION("PTP clock using KVMCLOCK"); MODULE_LICENSE("GPL"); |
| 4 4 4 4 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 | // SPDX-License-Identifier: GPL-2.0-only // // ethtool interface for Ethernet PSE (Power Sourcing Equipment) // and PD (Powered Device) // // Copyright (c) 2022 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> // #include "common.h" #include "linux/pse-pd/pse.h" #include "netlink.h" #include <linux/ethtool_netlink.h> #include <linux/ethtool.h> #include <linux/phy.h> struct pse_req_info { struct ethnl_req_info base; }; struct pse_reply_data { struct ethnl_reply_data base; struct pse_control_status status; }; #define PSE_REPDATA(__reply_base) \ container_of(__reply_base, struct pse_reply_data, base) /* PSE_GET */ const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1] = { [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int pse_get_pse_attributes(struct phy_device *phydev, struct netlink_ext_ack *extack, struct pse_reply_data *data) { if (!phydev) { NL_SET_ERR_MSG(extack, "No PHY found"); return -EOPNOTSUPP; } if (!phydev->psec) { NL_SET_ERR_MSG(extack, "No PSE is attached"); return -EOPNOTSUPP; } memset(&data->status, 0, sizeof(data->status)); return pse_ethtool_get_status(phydev->psec, extack, &data->status); } static int pse_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct pse_reply_data *data = PSE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PSE_HEADER], info->extack); if (IS_ERR(phydev)) return -ENODEV; ret = pse_get_pse_attributes(phydev, info->extack, data); ethnl_ops_complete(dev); return ret; } static int pse_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct pse_reply_data *data = PSE_REPDATA(reply_base); const struct pse_control_status *st = &data->status; int len = 0; if (st->podl_admin_state > 0) len += nla_total_size(sizeof(u32)); /* _PODL_PSE_ADMIN_STATE */ if (st->podl_pw_status > 0) len += nla_total_size(sizeof(u32)); /* _PODL_PSE_PW_D_STATUS */ if (st->c33_admin_state > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_ADMIN_STATE */ if (st->c33_pw_status > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_D_STATUS */ if (st->c33_pw_class > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_CLASS */ if (st->c33_actual_pw > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_ACTUAL_PW */ if (st->c33_ext_state_info.c33_pse_ext_state > 0) { len += nla_total_size(sizeof(u32)); /* _C33_PSE_EXT_STATE */ if (st->c33_ext_state_info.__c33_pse_ext_substate > 0) /* _C33_PSE_EXT_SUBSTATE */ len += nla_total_size(sizeof(u32)); } if (st->c33_avail_pw_limit > 0) /* _C33_AVAIL_PSE_PW_LIMIT */ len += nla_total_size(sizeof(u32)); if (st->c33_pw_limit_nb_ranges > 0) /* _C33_PSE_PW_LIMIT_RANGES */ len += st->c33_pw_limit_nb_ranges * (nla_total_size(0) + nla_total_size(sizeof(u32)) * 2); return len; } static int pse_put_pw_limit_ranges(struct sk_buff *skb, const struct pse_control_status *st) { const struct ethtool_c33_pse_pw_limit_range *pw_limit_ranges; int i; pw_limit_ranges = st->c33_pw_limit_ranges; for (i = 0; i < st->c33_pw_limit_nb_ranges; i++) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_MIN, pw_limit_ranges->min) || nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_MAX, pw_limit_ranges->max)) { nla_nest_cancel(skb, nest); return -EMSGSIZE; } nla_nest_end(skb, nest); pw_limit_ranges++; } return 0; } static int pse_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct pse_reply_data *data = PSE_REPDATA(reply_base); const struct pse_control_status *st = &data->status; if (st->podl_admin_state > 0 && nla_put_u32(skb, ETHTOOL_A_PODL_PSE_ADMIN_STATE, st->podl_admin_state)) return -EMSGSIZE; if (st->podl_pw_status > 0 && nla_put_u32(skb, ETHTOOL_A_PODL_PSE_PW_D_STATUS, st->podl_pw_status)) return -EMSGSIZE; if (st->c33_admin_state > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_ADMIN_STATE, st->c33_admin_state)) return -EMSGSIZE; if (st->c33_pw_status > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_D_STATUS, st->c33_pw_status)) return -EMSGSIZE; if (st->c33_pw_class > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_CLASS, st->c33_pw_class)) return -EMSGSIZE; if (st->c33_actual_pw > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_ACTUAL_PW, st->c33_actual_pw)) return -EMSGSIZE; if (st->c33_ext_state_info.c33_pse_ext_state > 0) { if (nla_put_u32(skb, ETHTOOL_A_C33_PSE_EXT_STATE, st->c33_ext_state_info.c33_pse_ext_state)) return -EMSGSIZE; if (st->c33_ext_state_info.__c33_pse_ext_substate > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_EXT_SUBSTATE, st->c33_ext_state_info.__c33_pse_ext_substate)) return -EMSGSIZE; } if (st->c33_avail_pw_limit > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT, st->c33_avail_pw_limit)) return -EMSGSIZE; if (st->c33_pw_limit_nb_ranges > 0 && pse_put_pw_limit_ranges(skb, st)) return -EMSGSIZE; return 0; } static void pse_cleanup_data(struct ethnl_reply_data *reply_base) { const struct pse_reply_data *data = PSE_REPDATA(reply_base); kfree(data->status.c33_pw_limit_ranges); } /* PSE_SET */ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED, ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED), [ETHTOOL_A_C33_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED, ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED), [ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT] = { .type = NLA_U32 }, }; static int ethnl_set_pse_validate(struct phy_device *phydev, struct genl_info *info) { struct nlattr **tb = info->attrs; if (IS_ERR_OR_NULL(phydev)) { NL_SET_ERR_MSG(info->extack, "No PHY is attached"); return -EOPNOTSUPP; } if (!phydev->psec) { NL_SET_ERR_MSG(info->extack, "No PSE is attached"); return -EOPNOTSUPP; } if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] && !pse_has_podl(phydev->psec)) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL], "setting PoDL PSE admin control not supported"); return -EOPNOTSUPP; } if (tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL] && !pse_has_c33(phydev->psec)) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL], "setting C33 PSE admin control not supported"); return -EOPNOTSUPP; } return 0; } static int ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) { struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER], info->extack); ret = ethnl_set_pse_validate(phydev, info); if (ret) return ret; if (tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]) { unsigned int pw_limit; pw_limit = nla_get_u32(tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]); ret = pse_ethtool_set_pw_limit(phydev->psec, info->extack, pw_limit); if (ret) return ret; } /* These values are already validated by the ethnl_pse_set_policy */ if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] || tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]) { struct pse_control_config config = {}; if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]) config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); if (tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]) config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]); /* pse_ethtool_set_config() will do nothing if the config * is zero */ ret = pse_ethtool_set_config(phydev->psec, info->extack, &config); if (ret) return ret; } /* Return errno or zero - PSE has no notification */ return ret; } const struct ethnl_request_ops ethnl_pse_request_ops = { .request_cmd = ETHTOOL_MSG_PSE_GET, .reply_cmd = ETHTOOL_MSG_PSE_GET_REPLY, .hdr_attr = ETHTOOL_A_PSE_HEADER, .req_info_size = sizeof(struct pse_req_info), .reply_data_size = sizeof(struct pse_reply_data), .prepare_data = pse_prepare_data, .reply_size = pse_reply_size, .fill_reply = pse_fill_reply, .cleanup_data = pse_cleanup_data, .set = ethnl_set_pse, /* PSE has no notification */ }; |
| 53 53 53 53 60 60 60 60 60 22 22 22 22 84 60 60 60 60 84 60 22 22 22 22 9 9 9 9 9 9 9 9 9 9 9 84 83 84 84 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "send.h" #include "main.h" #include <linux/atomic.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/container_of.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if.h> #include <linux/if_ether.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/workqueue.h> #include "distributed-arp-table.h" #include "fragmentation.h" #include "gateway_client.h" #include "hard-interface.h" #include "log.h" #include "network-coding.h" #include "originator.h" #include "routing.h" #include "soft-interface.h" #include "translation-table.h" static void batadv_send_outstanding_bcast_packet(struct work_struct *work); /** * batadv_send_skb_packet() - send an already prepared packet * @skb: the packet to send * @hard_iface: the interface to use to send the broadcast packet * @dst_addr: the payload destination * * Send out an already prepared packet to the given neighbor or broadcast it * using the specified interface. Either hard_iface or neigh_node must be not * NULL. * If neigh_node is NULL, then the packet is broadcasted using hard_iface, * otherwise it is sent as unicast to the given neighbor. * * Regardless of the return value, the skb is consumed. * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_skb_packet(struct sk_buff *skb, struct batadv_hard_iface *hard_iface, const u8 *dst_addr) { struct batadv_priv *bat_priv; struct ethhdr *ethhdr; int ret; bat_priv = netdev_priv(hard_iface->soft_iface); if (hard_iface->if_status != BATADV_IF_ACTIVE) goto send_skb_err; if (unlikely(!hard_iface->net_dev)) goto send_skb_err; if (!(hard_iface->net_dev->flags & IFF_UP)) { pr_warn("Interface %s is not up - can't send packet via that interface!\n", hard_iface->net_dev->name); goto send_skb_err; } /* push to the ethernet header. */ if (batadv_skb_head_push(skb, ETH_HLEN) < 0) goto send_skb_err; skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); ether_addr_copy(ethhdr->h_source, hard_iface->net_dev->dev_addr); ether_addr_copy(ethhdr->h_dest, dst_addr); ethhdr->h_proto = htons(ETH_P_BATMAN); skb_set_network_header(skb, ETH_HLEN); skb->protocol = htons(ETH_P_BATMAN); skb->dev = hard_iface->net_dev; /* Save a clone of the skb to use when decoding coded packets */ batadv_nc_skb_store_for_decoding(bat_priv, skb); /* dev_queue_xmit() returns a negative result on error. However on * congestion and traffic shaping, it drops and returns NET_XMIT_DROP * (which is > 0). This will not be treated as an error. */ ret = dev_queue_xmit(skb); return net_xmit_eval(ret); send_skb_err: kfree_skb(skb); return NET_XMIT_DROP; } /** * batadv_send_broadcast_skb() - Send broadcast packet via hard interface * @skb: packet to be transmitted (with batadv header and no outer eth header) * @hard_iface: outgoing interface * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_broadcast_skb(struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { return batadv_send_skb_packet(skb, hard_iface, batadv_broadcast_addr); } /** * batadv_send_unicast_skb() - Send unicast packet to neighbor * @skb: packet to be transmitted (with batadv header and no outer eth header) * @neigh: neighbor which is used as next hop to destination * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_unicast_skb(struct sk_buff *skb, struct batadv_neigh_node *neigh) { #ifdef CONFIG_BATMAN_ADV_BATMAN_V struct batadv_hardif_neigh_node *hardif_neigh; #endif int ret; ret = batadv_send_skb_packet(skb, neigh->if_incoming, neigh->addr); #ifdef CONFIG_BATMAN_ADV_BATMAN_V hardif_neigh = batadv_hardif_neigh_get(neigh->if_incoming, neigh->addr); if (hardif_neigh && ret != NET_XMIT_DROP) hardif_neigh->bat_v.last_unicast_tx = jiffies; batadv_hardif_neigh_put(hardif_neigh); #endif return ret; } /** * batadv_send_skb_to_orig() - Lookup next-hop and transmit skb. * @skb: Packet to be transmitted. * @orig_node: Final destination of the packet. * @recv_if: Interface used when receiving the packet (can be NULL). * * Looks up the best next-hop towards the passed originator and passes the * skb on for preparation of MAC header. If the packet originated from this * host, NULL can be passed as recv_if and no interface alternating is * attempted. * * Return: negative errno code on a failure, -EINPROGRESS if the skb is * buffered for later transmit or the NET_XMIT status returned by the * lower routine if the packet has been passed down. */ int batadv_send_skb_to_orig(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_hard_iface *recv_if) { struct batadv_priv *bat_priv = orig_node->bat_priv; struct batadv_neigh_node *neigh_node; int ret; /* batadv_find_router() increases neigh_nodes refcount if found. */ neigh_node = batadv_find_router(bat_priv, orig_node, recv_if); if (!neigh_node) { ret = -EINVAL; goto free_skb; } /* Check if the skb is too large to send in one piece and fragment * it if needed. */ if (atomic_read(&bat_priv->fragmentation) && skb->len > neigh_node->if_incoming->net_dev->mtu) { /* Fragment and send packet. */ ret = batadv_frag_send_packet(skb, orig_node, neigh_node); /* skb was consumed */ skb = NULL; goto put_neigh_node; } /* try to network code the packet, if it is received on an interface * (i.e. being forwarded). If the packet originates from this node or if * network coding fails, then send the packet as usual. */ if (recv_if && batadv_nc_skb_forward(skb, neigh_node)) ret = -EINPROGRESS; else ret = batadv_send_unicast_skb(skb, neigh_node); /* skb was consumed */ skb = NULL; put_neigh_node: batadv_neigh_node_put(neigh_node); free_skb: kfree_skb(skb); return ret; } /** * batadv_send_skb_push_fill_unicast() - extend the buffer and initialize the * common fields for unicast packets * @skb: the skb carrying the unicast header to initialize * @hdr_size: amount of bytes to push at the beginning of the skb * @orig_node: the destination node * * Return: false if the buffer extension was not possible or true otherwise. */ static bool batadv_send_skb_push_fill_unicast(struct sk_buff *skb, int hdr_size, struct batadv_orig_node *orig_node) { struct batadv_unicast_packet *unicast_packet; u8 ttvn = (u8)atomic_read(&orig_node->last_ttvn); if (batadv_skb_head_push(skb, hdr_size) < 0) return false; unicast_packet = (struct batadv_unicast_packet *)skb->data; unicast_packet->version = BATADV_COMPAT_VERSION; /* batman packet type: unicast */ unicast_packet->packet_type = BATADV_UNICAST; /* set unicast ttl */ unicast_packet->ttl = BATADV_TTL; /* copy the destination for faster routing */ ether_addr_copy(unicast_packet->dest, orig_node->orig); /* set the destination tt version number */ unicast_packet->ttvn = ttvn; return true; } /** * batadv_send_skb_prepare_unicast() - encapsulate an skb with a unicast header * @skb: the skb containing the payload to encapsulate * @orig_node: the destination node * * Return: false if the payload could not be encapsulated or true otherwise. */ static bool batadv_send_skb_prepare_unicast(struct sk_buff *skb, struct batadv_orig_node *orig_node) { size_t uni_size = sizeof(struct batadv_unicast_packet); return batadv_send_skb_push_fill_unicast(skb, uni_size, orig_node); } /** * batadv_send_skb_prepare_unicast_4addr() - encapsulate an skb with a * unicast 4addr header * @bat_priv: the bat priv with all the soft interface information * @skb: the skb containing the payload to encapsulate * @orig: the destination node * @packet_subtype: the unicast 4addr packet subtype to use * * Return: false if the payload could not be encapsulated or true otherwise. */ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node *orig, int packet_subtype) { struct batadv_hard_iface *primary_if; struct batadv_unicast_4addr_packet *uc_4addr_packet; bool ret = false; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* Pull the header space and fill the unicast_packet substructure. * We can do that because the first member of the uc_4addr_packet * is of type struct unicast_packet */ if (!batadv_send_skb_push_fill_unicast(skb, sizeof(*uc_4addr_packet), orig)) goto out; uc_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; uc_4addr_packet->u.packet_type = BATADV_UNICAST_4ADDR; ether_addr_copy(uc_4addr_packet->src, primary_if->net_dev->dev_addr); uc_4addr_packet->subtype = packet_subtype; uc_4addr_packet->reserved = 0; ret = true; out: batadv_hardif_put(primary_if); return ret; } /** * batadv_send_skb_unicast() - encapsulate and send an skb via unicast * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) * @orig_node: the originator to send the packet to * @vid: the vid to be used to search the translation table * * Wrap the given skb into a batman-adv unicast or unicast-4addr header * depending on whether BATADV_UNICAST or BATADV_UNICAST_4ADDR was supplied * as packet_type. Then send this frame to the given orig_node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, struct batadv_orig_node *orig_node, unsigned short vid) { struct batadv_unicast_packet *unicast_packet; struct ethhdr *ethhdr; int ret = NET_XMIT_DROP; if (!orig_node) goto out; switch (packet_type) { case BATADV_UNICAST: if (!batadv_send_skb_prepare_unicast(skb, orig_node)) goto out; break; case BATADV_UNICAST_4ADDR: if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb, orig_node, packet_subtype)) goto out; break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It * should never be invoked with any other packet type */ goto out; } /* skb->data might have been reallocated by * batadv_send_skb_prepare_unicast{,_4addr}() */ ethhdr = eth_hdr(skb); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route * for this client. The destination will receive this packet and will * try to reroute it because the ttvn contained in the header is less * than the current one */ if (batadv_tt_global_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) unicast_packet->ttvn = unicast_packet->ttvn - 1; ret = batadv_send_skb_to_orig(skb, orig_node, NULL); /* skb was consumed */ skb = NULL; out: kfree_skb(skb); return ret; } /** * batadv_send_skb_via_tt_generic() - send an skb via TT lookup * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) * @dst_hint: can be used to override the destination contained in the skb * @vid: the vid to be used to search the translation table * * Look up the recipient node for the destination address in the ethernet * header via the translation table. Wrap the given skb into a batman-adv * unicast or unicast-4addr header depending on whether BATADV_UNICAST or * BATADV_UNICAST_4ADDR was supplied as packet_type. Then send this frame * to the according destination node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, u8 *dst_hint, unsigned short vid) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct batadv_orig_node *orig_node; u8 *src, *dst; int ret; src = ethhdr->h_source; dst = ethhdr->h_dest; /* if we got an hint! let's send the packet to this client (if any) */ if (dst_hint) { src = NULL; dst = dst_hint; } orig_node = batadv_transtable_search(bat_priv, src, dst, vid); ret = batadv_send_skb_unicast(bat_priv, skb, packet_type, packet_subtype, orig_node, vid); batadv_orig_node_put(orig_node); return ret; } /** * batadv_send_skb_via_gw() - send an skb via gateway lookup * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @vid: the vid to be used to search the translation table * * Look up the currently selected gateway. Wrap the given skb into a batman-adv * unicast header and send this frame to this gateway node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret; orig_node = batadv_gw_get_selected_orig(bat_priv); ret = batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, BATADV_P_DATA, orig_node, vid); batadv_orig_node_put(orig_node); return ret; } /** * batadv_forw_packet_free() - free a forwarding packet * @forw_packet: The packet to free * @dropped: whether the packet is freed because is dropped * * This frees a forwarding packet and releases any resources it might * have claimed. */ void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet, bool dropped) { if (dropped) kfree_skb(forw_packet->skb); else consume_skb(forw_packet->skb); batadv_hardif_put(forw_packet->if_incoming); batadv_hardif_put(forw_packet->if_outgoing); if (forw_packet->queue_left) atomic_inc(forw_packet->queue_left); kfree(forw_packet); } /** * batadv_forw_packet_alloc() - allocate a forwarding packet * @if_incoming: The (optional) if_incoming to be grabbed * @if_outgoing: The (optional) if_outgoing to be grabbed * @queue_left: The (optional) queue counter to decrease * @bat_priv: The bat_priv for the mesh of this forw_packet * @skb: The raw packet this forwarding packet shall contain * * Allocates a forwarding packet and tries to get a reference to the * (optional) if_incoming, if_outgoing and queue_left. If queue_left * is NULL then bat_priv is optional, too. * * Return: An allocated forwarding packet on success, NULL otherwise. */ struct batadv_forw_packet * batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming, struct batadv_hard_iface *if_outgoing, atomic_t *queue_left, struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_forw_packet *forw_packet; const char *qname; if (queue_left && !batadv_atomic_dec_not_zero(queue_left)) { qname = "unknown"; if (queue_left == &bat_priv->bcast_queue_left) qname = "bcast"; if (queue_left == &bat_priv->batman_queue_left) qname = "batman"; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s queue is full\n", qname); return NULL; } forw_packet = kmalloc(sizeof(*forw_packet), GFP_ATOMIC); if (!forw_packet) goto err; if (if_incoming) kref_get(&if_incoming->refcount); if (if_outgoing) kref_get(&if_outgoing->refcount); INIT_HLIST_NODE(&forw_packet->list); INIT_HLIST_NODE(&forw_packet->cleanup_list); forw_packet->skb = skb; forw_packet->queue_left = queue_left; forw_packet->if_incoming = if_incoming; forw_packet->if_outgoing = if_outgoing; forw_packet->num_packets = 0; return forw_packet; err: if (queue_left) atomic_inc(queue_left); return NULL; } /** * batadv_forw_packet_was_stolen() - check whether someone stole this packet * @forw_packet: the forwarding packet to check * * This function checks whether the given forwarding packet was claimed by * someone else for free(). * * Return: True if someone stole it, false otherwise. */ static bool batadv_forw_packet_was_stolen(struct batadv_forw_packet *forw_packet) { return !hlist_unhashed(&forw_packet->cleanup_list); } /** * batadv_forw_packet_steal() - claim a forw_packet for free() * @forw_packet: the forwarding packet to steal * @lock: a key to the store to steal from (e.g. forw_{bat,bcast}_list_lock) * * This function tries to steal a specific forw_packet from global * visibility for the purpose of getting it for free(). That means * the caller is *not* allowed to requeue it afterwards. * * Return: True if stealing was successful. False if someone else stole it * before us. */ bool batadv_forw_packet_steal(struct batadv_forw_packet *forw_packet, spinlock_t *lock) { /* did purging routine steal it earlier? */ spin_lock_bh(lock); if (batadv_forw_packet_was_stolen(forw_packet)) { spin_unlock_bh(lock); return false; } hlist_del_init(&forw_packet->list); /* Just to spot misuse of this function */ hlist_add_fake(&forw_packet->cleanup_list); spin_unlock_bh(lock); return true; } /** * batadv_forw_packet_list_steal() - claim a list of forward packets for free() * @forw_list: the to be stolen forward packets * @cleanup_list: a backup pointer, to be able to dispose the packet later * @hard_iface: the interface to steal forward packets from * * This function claims responsibility to free any forw_packet queued on the * given hard_iface. If hard_iface is NULL forwarding packets on all hard * interfaces will be claimed. * * The packets are being moved from the forw_list to the cleanup_list. This * makes it possible for already running threads to notice the claim. */ static void batadv_forw_packet_list_steal(struct hlist_head *forw_list, struct hlist_head *cleanup_list, const struct batadv_hard_iface *hard_iface) { struct batadv_forw_packet *forw_packet; struct hlist_node *safe_tmp_node; hlist_for_each_entry_safe(forw_packet, safe_tmp_node, forw_list, list) { /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ if (hard_iface && forw_packet->if_incoming != hard_iface && forw_packet->if_outgoing != hard_iface) continue; hlist_del(&forw_packet->list); hlist_add_head(&forw_packet->cleanup_list, cleanup_list); } } /** * batadv_forw_packet_list_free() - free a list of forward packets * @head: a list of to be freed forw_packets * * This function cancels the scheduling of any packet in the provided list, * waits for any possibly running packet forwarding thread to finish and * finally, safely frees this forward packet. * * This function might sleep. */ static void batadv_forw_packet_list_free(struct hlist_head *head) { struct batadv_forw_packet *forw_packet; struct hlist_node *safe_tmp_node; hlist_for_each_entry_safe(forw_packet, safe_tmp_node, head, cleanup_list) { cancel_delayed_work_sync(&forw_packet->delayed_work); hlist_del(&forw_packet->cleanup_list); batadv_forw_packet_free(forw_packet, true); } } /** * batadv_forw_packet_queue() - try to queue a forwarding packet * @forw_packet: the forwarding packet to queue * @lock: a key to the store (e.g. forw_{bat,bcast}_list_lock) * @head: the shelve to queue it on (e.g. forw_{bat,bcast}_list) * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue a forwarding packet. Requeuing * is prevented if the according interface is shutting down * (e.g. if batadv_forw_packet_list_steal() was called for this * packet earlier). * * Calling batadv_forw_packet_queue() after a call to * batadv_forw_packet_steal() is forbidden! * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ static void batadv_forw_packet_queue(struct batadv_forw_packet *forw_packet, spinlock_t *lock, struct hlist_head *head, unsigned long send_time) { spin_lock_bh(lock); /* did purging routine steal it from us? */ if (batadv_forw_packet_was_stolen(forw_packet)) { /* If you got it for free() without trouble, then * don't get back into the queue after stealing... */ WARN_ONCE(hlist_fake(&forw_packet->cleanup_list), "Requeuing after batadv_forw_packet_steal() not allowed!\n"); spin_unlock_bh(lock); return; } hlist_del_init(&forw_packet->list); hlist_add_head(&forw_packet->list, head); queue_delayed_work(batadv_event_workqueue, &forw_packet->delayed_work, send_time - jiffies); spin_unlock_bh(lock); } /** * batadv_forw_packet_bcast_queue() - try to queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @forw_packet: the forwarding packet to queue * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue a broadcast packet. * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ static void batadv_forw_packet_bcast_queue(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { batadv_forw_packet_queue(forw_packet, &bat_priv->forw_bcast_list_lock, &bat_priv->forw_bcast_list, send_time); } /** * batadv_forw_packet_ogmv1_queue() - try to queue an OGMv1 packet * @bat_priv: the bat priv with all the soft interface information * @forw_packet: the forwarding packet to queue * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue an OGMv1 packet. * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { batadv_forw_packet_queue(forw_packet, &bat_priv->forw_bat_list_lock, &bat_priv->forw_bat_list, send_time); } /** * batadv_forw_bcast_packet_to_list() - queue broadcast packet for transmissions * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * @if_in: the interface where the packet was received on * @if_out: the outgoing interface to queue on * * Adds a broadcast packet to the queue and sets up timers. Broadcast packets * are sent multiple times to increase probability for being received. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the original skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet, struct batadv_hard_iface *if_in, struct batadv_hard_iface *if_out) { struct batadv_forw_packet *forw_packet; unsigned long send_time = jiffies; struct sk_buff *newskb; newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) goto err; forw_packet = batadv_forw_packet_alloc(if_in, if_out, &bat_priv->bcast_queue_left, bat_priv, newskb); if (!forw_packet) goto err_packet_free; forw_packet->own = own_packet; INIT_DELAYED_WORK(&forw_packet->delayed_work, batadv_send_outstanding_bcast_packet); send_time += delay ? delay : msecs_to_jiffies(5); batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return NETDEV_TX_OK; err_packet_free: kfree_skb(newskb); err: return NETDEV_TX_BUSY; } /** * batadv_forw_bcast_packet_if() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * @if_in: the interface where the packet was received on * @if_out: the outgoing interface to forward to * * Transmits a broadcast packet on the specified interface either immediately * or if a delay is given after that. Furthermore, queues additional * retransmissions if this interface is a wireless one. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the original skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet, struct batadv_hard_iface *if_in, struct batadv_hard_iface *if_out) { unsigned int num_bcasts = if_out->num_bcasts; struct sk_buff *newskb; int ret = NETDEV_TX_OK; if (!delay) { newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) return NETDEV_TX_BUSY; batadv_send_broadcast_skb(newskb, if_out); num_bcasts--; } /* delayed broadcast or rebroadcasts? */ if (num_bcasts >= 1) { BATADV_SKB_CB(skb)->num_bcasts = num_bcasts; ret = batadv_forw_bcast_packet_to_list(bat_priv, skb, delay, own_packet, if_in, if_out); } return ret; } /** * batadv_send_no_broadcast() - check whether (re)broadcast is necessary * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to check * @own_packet: true if it is a self-generated broadcast packet * @if_out: the outgoing interface checked and considered for (re)broadcast * * Return: False if a packet needs to be (re)broadcasted on the given interface, * true otherwise. */ static bool batadv_send_no_broadcast(struct batadv_priv *bat_priv, struct sk_buff *skb, bool own_packet, struct batadv_hard_iface *if_out) { struct batadv_hardif_neigh_node *neigh_node = NULL; struct batadv_bcast_packet *bcast_packet; u8 *orig_neigh; u8 *neigh_addr; char *type; int ret; if (!own_packet) { neigh_addr = eth_hdr(skb)->h_source; neigh_node = batadv_hardif_neigh_get(if_out, neigh_addr); } bcast_packet = (struct batadv_bcast_packet *)skb->data; orig_neigh = neigh_node ? neigh_node->orig : NULL; ret = batadv_hardif_no_broadcast(if_out, bcast_packet->orig, orig_neigh); batadv_hardif_neigh_put(neigh_node); /* ok, may broadcast */ if (!ret) return false; /* no broadcast */ switch (ret) { case BATADV_HARDIF_BCAST_NORECIPIENT: type = "no neighbor"; break; case BATADV_HARDIF_BCAST_DUPFWD: type = "single neighbor is source"; break; case BATADV_HARDIF_BCAST_DUPORIG: type = "single neighbor is originator"; break; default: type = "unknown"; } batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "BCAST packet from orig %pM on %s suppressed: %s\n", bcast_packet->orig, if_out->net_dev->name, type); return true; } /** * __batadv_forw_bcast_packet() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the given skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int __batadv_forw_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { struct batadv_hard_iface *hard_iface; struct batadv_hard_iface *primary_if; int ret = NETDEV_TX_OK; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return NETDEV_TX_BUSY; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != bat_priv->soft_iface) continue; if (!kref_get_unless_zero(&hard_iface->refcount)) continue; if (batadv_send_no_broadcast(bat_priv, skb, own_packet, hard_iface)) { batadv_hardif_put(hard_iface); continue; } ret = batadv_forw_bcast_packet_if(bat_priv, skb, delay, own_packet, primary_if, hard_iface); batadv_hardif_put(hard_iface); if (ret == NETDEV_TX_BUSY) break; } rcu_read_unlock(); batadv_hardif_put(primary_if); return ret; } /** * batadv_forw_bcast_packet() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ int batadv_forw_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { return __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); } /** * batadv_send_bcast_packet() - send and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * Consumes the provided skb. */ void batadv_send_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); consume_skb(skb); } /** * batadv_forw_packet_bcasts_left() - check if a retransmission is necessary * @forw_packet: the forwarding packet to check * * Checks whether a given packet has any (re)transmissions left on the provided * interface. * * hard_iface may be NULL: In that case the number of transmissions this skb had * so far is compared with the maximum amount of retransmissions independent of * any interface instead. * * Return: True if (re)transmissions are left, false otherwise. */ static bool batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet) { return BATADV_SKB_CB(forw_packet->skb)->num_bcasts; } /** * batadv_forw_packet_bcasts_dec() - decrement retransmission counter of a * packet * @forw_packet: the packet to decrease the counter for */ static void batadv_forw_packet_bcasts_dec(struct batadv_forw_packet *forw_packet) { BATADV_SKB_CB(forw_packet->skb)->num_bcasts--; } /** * batadv_forw_packet_is_rebroadcast() - check packet for previous transmissions * @forw_packet: the packet to check * * Return: True if this packet was transmitted before, false otherwise. */ bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet) { unsigned char num_bcasts = BATADV_SKB_CB(forw_packet->skb)->num_bcasts; return num_bcasts != forw_packet->if_outgoing->num_bcasts; } /** * batadv_send_outstanding_bcast_packet() - transmit a queued broadcast packet * @work: work queue item * * Transmits a queued broadcast packet and if necessary reschedules it. */ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) { unsigned long send_time = jiffies + msecs_to_jiffies(5); struct batadv_forw_packet *forw_packet; struct delayed_work *delayed_work; struct batadv_priv *bat_priv; struct sk_buff *skb1; bool dropped = false; delayed_work = to_delayed_work(work); forw_packet = container_of(delayed_work, struct batadv_forw_packet, delayed_work); bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface); if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) { dropped = true; goto out; } if (batadv_dat_drop_broadcast_packet(bat_priv, forw_packet)) { dropped = true; goto out; } /* send a copy of the saved skb */ skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); if (!skb1) goto out; batadv_send_broadcast_skb(skb1, forw_packet->if_outgoing); batadv_forw_packet_bcasts_dec(forw_packet); if (batadv_forw_packet_bcasts_left(forw_packet)) { batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return; } out: /* do we get something for free()? */ if (batadv_forw_packet_steal(forw_packet, &bat_priv->forw_bcast_list_lock)) batadv_forw_packet_free(forw_packet, dropped); } /** * batadv_purge_outstanding_packets() - stop/purge scheduled bcast/OGMv1 packets * @bat_priv: the bat priv with all the soft interface information * @hard_iface: the hard interface to cancel and purge bcast/ogm packets on * * This method cancels and purges any broadcast and OGMv1 packet on the given * hard_iface. If hard_iface is NULL, broadcast and OGMv1 packets on all hard * interfaces will be canceled and purged. * * This function might sleep. */ void batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, const struct batadv_hard_iface *hard_iface) { struct hlist_head head = HLIST_HEAD_INIT; if (hard_iface) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s(): %s\n", __func__, hard_iface->net_dev->name); else batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s()\n", __func__); /* claim bcast list for free() */ spin_lock_bh(&bat_priv->forw_bcast_list_lock); batadv_forw_packet_list_steal(&bat_priv->forw_bcast_list, &head, hard_iface); spin_unlock_bh(&bat_priv->forw_bcast_list_lock); /* claim batman packet list for free() */ spin_lock_bh(&bat_priv->forw_bat_list_lock); batadv_forw_packet_list_steal(&bat_priv->forw_bat_list, &head, hard_iface); spin_unlock_bh(&bat_priv->forw_bat_list_lock); /* then cancel or wait for packet workers to finish and free */ batadv_forw_packet_list_free(&head); } |
| 744 370 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __VDSO_MATH64_H #define __VDSO_MATH64_H static __always_inline u32 __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) { u32 ret = 0; while (dividend >= divisor) { /* The following asm() prevents the compiler from optimising this loop into a modulo operation. */ asm("" : "+rm"(dividend)); dividend -= divisor; ret++; } *remainder = dividend; return ret; } #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__) #ifndef mul_u64_u32_add_u64_shr static __always_inline u64 mul_u64_u32_add_u64_shr(u64 a, u32 mul, u64 b, unsigned int shift) { return (u64)((((unsigned __int128)a * mul) + b) >> shift); } #endif /* mul_u64_u32_add_u64_shr */ #else #ifndef mul_u64_u32_add_u64_shr #ifndef mul_u32_u32 static inline u64 mul_u32_u32(u32 a, u32 b) { return (u64)a * b; } #define mul_u32_u32 mul_u32_u32 #endif static __always_inline u64 mul_u64_u32_add_u64_shr(u64 a, u32 mul, u64 b, unsigned int shift) { u32 ah = a >> 32, al = a; bool ovf; u64 ret; ovf = __builtin_add_overflow(mul_u32_u32(al, mul), b, &ret); ret >>= shift; if (ovf && shift) ret += 1ULL << (64 - shift); if (ah) ret += mul_u32_u32(ah, mul) << (32 - shift); return ret; } #endif /* mul_u64_u32_add_u64_shr */ #endif #endif /* __VDSO_MATH64_H */ |
| 14 14 7 7 7 134 134 133 129 129 41 106 19 122 81 35 113 37 129 129 6 3 6 4 4 1 4 49 36 115 36 12 79 7 26 3 29 12 36 36 36 2 2 2 12 12 12 6 12 12 126 126 97 84 126 84 29 39 124 9 126 3 127 1 40 98 125 3 21 106 127 127 36 6 89 2 34 35 116 2 2 5 4 2 2 2 2 2 2 2 5 2 2 1 1 1 1 129 90 49 1 50 127 |