| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * thermal_core.h * * Copyright (C) 2012 Intel Corp * Author: Durgadoss R <durgadoss.r@intel.com> */ #ifndef __THERMAL_CORE_H__ #define __THERMAL_CORE_H__ #include <linux/cleanup.h> #include <linux/device.h> #include <linux/thermal.h> #include "thermal_netlink.h" #include "thermal_thresholds.h" #include "thermal_debugfs.h" struct thermal_attr { struct device_attribute attr; char name[THERMAL_NAME_LENGTH]; }; struct thermal_trip_attrs { struct thermal_attr type; struct thermal_attr temp; struct thermal_attr hyst; }; struct thermal_trip_desc { struct thermal_trip trip; struct thermal_trip_attrs trip_attrs; struct list_head list_node; struct list_head thermal_instances; int threshold; }; /** * struct thermal_governor - structure that holds thermal governor information * @name: name of the governor * @bind_to_tz: callback called when binding to a thermal zone. If it * returns 0, the governor is bound to the thermal zone, * otherwise it fails. * @unbind_from_tz: callback called when a governor is unbound from a * thermal zone. * @trip_crossed: called for trip points that have just been crossed * @manage: called on thermal zone temperature updates * @update_tz: callback called when thermal zone internals have changed, e.g. * thermal cooling instance was added/removed * @governor_list: node in thermal_governor_list (in thermal_core.c) */ struct thermal_governor { const char *name; int (*bind_to_tz)(struct thermal_zone_device *tz); void (*unbind_from_tz)(struct thermal_zone_device *tz); void (*trip_crossed)(struct thermal_zone_device *tz, const struct thermal_trip *trip, bool upward); void (*manage)(struct thermal_zone_device *tz); void (*update_tz)(struct thermal_zone_device *tz, enum thermal_notify_event reason); struct list_head governor_list; }; #define TZ_STATE_FLAG_SUSPENDED BIT(0) #define TZ_STATE_FLAG_RESUMING BIT(1) #define TZ_STATE_FLAG_INIT BIT(2) #define TZ_STATE_FLAG_EXIT BIT(3) #define TZ_STATE_READY 0 /** * struct thermal_zone_device - structure for a thermal zone * @id: unique id number for each thermal zone * @type: the thermal zone device type * @device: &struct device for this thermal zone * @removal: removal completion * @resume: resume completion * @trips_high: trips above the current zone temperature * @trips_reached: trips below or at the current zone temperature * @trips_invalid: trips with invalid temperature * @mode: current mode of this thermal zone * @devdata: private pointer for device private data * @num_trips: number of trip points the thermal zone supports * @passive_delay_jiffies: number of jiffies to wait between polls when * performing passive cooling. * @polling_delay_jiffies: number of jiffies to wait between polls when * checking whether trip points have been crossed (0 for * interrupt driven systems) * @recheck_delay_jiffies: delay after a failed attempt to determine the zone * temperature before trying again * @temperature: current temperature. This is only for core code, * drivers should use thermal_zone_get_temp() to get the * current temperature * @last_temperature: previous temperature read * @emul_temperature: emulated temperature when using CONFIG_THERMAL_EMULATION * @passive: 1 if you've crossed a passive trip point, 0 otherwise. * @prev_low_trip: the low current temperature if you've crossed a passive trip point. * @prev_high_trip: the above current temperature if you've crossed a passive trip point. * @ops: operations this &thermal_zone_device supports * @tzp: thermal zone parameters * @governor: pointer to the governor for this thermal zone * @governor_data: private pointer for governor data * @ida: &struct ida to generate unique id for this zone's cooling * devices * @lock: lock to protect thermal_instances list * @node: node in thermal_tz_list (in thermal_core.c) * @poll_queue: delayed work for polling * @notify_event: Last notification event * @state: current state of the thermal zone * @trips: array of struct thermal_trip objects */ struct thermal_zone_device { int id; char type[THERMAL_NAME_LENGTH]; struct device device; struct completion removal; struct completion resume; struct attribute_group trips_attribute_group; struct list_head trips_high; struct list_head trips_reached; struct list_head trips_invalid; enum thermal_device_mode mode; void *devdata; int num_trips; unsigned long passive_delay_jiffies; unsigned long polling_delay_jiffies; unsigned long recheck_delay_jiffies; int temperature; int last_temperature; int emul_temperature; int passive; int prev_low_trip; int prev_high_trip; struct thermal_zone_device_ops ops; struct thermal_zone_params *tzp; struct thermal_governor *governor; void *governor_data; struct ida ida; struct mutex lock; struct list_head node; struct delayed_work poll_queue; enum thermal_notify_event notify_event; u8 state; #ifdef CONFIG_THERMAL_DEBUGFS struct thermal_debugfs *debugfs; #endif struct list_head user_thresholds; struct thermal_trip_desc trips[] __counted_by(num_trips); }; DEFINE_GUARD(thermal_zone, struct thermal_zone_device *, mutex_lock(&_T->lock), mutex_unlock(&_T->lock)) DEFINE_GUARD(thermal_zone_reverse, struct thermal_zone_device *, mutex_unlock(&_T->lock), mutex_lock(&_T->lock)) /* Initial thermal zone temperature. */ #define THERMAL_TEMP_INIT INT_MIN /* * Default and maximum delay after a failed thermal zone temperature check * before attempting to check it again (in jiffies). */ #define THERMAL_RECHECK_DELAY msecs_to_jiffies(250) #define THERMAL_MAX_RECHECK_DELAY (120 * HZ) /* Default Thermal Governor */ #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE) #define DEFAULT_THERMAL_GOVERNOR "step_wise" #elif defined(CONFIG_THERMAL_DEFAULT_GOV_FAIR_SHARE) #define DEFAULT_THERMAL_GOVERNOR "fair_share" #elif defined(CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE) #define DEFAULT_THERMAL_GOVERNOR "user_space" #elif defined(CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR) #define DEFAULT_THERMAL_GOVERNOR "power_allocator" #elif defined(CONFIG_THERMAL_DEFAULT_GOV_BANG_BANG) #define DEFAULT_THERMAL_GOVERNOR "bang_bang" #endif /* Initial state of a cooling device during binding */ #define THERMAL_NO_TARGET -1UL /* Init section thermal table */ extern struct thermal_governor *__governor_thermal_table[]; extern struct thermal_governor *__governor_thermal_table_end[]; #define THERMAL_TABLE_ENTRY(table, name) \ static typeof(name) *__thermal_table_entry_##name \ __used __section("__" #table "_thermal_table") = &name #define THERMAL_GOVERNOR_DECLARE(name) THERMAL_TABLE_ENTRY(governor, name) #define for_each_governor_table(__governor) \ for (__governor = __governor_thermal_table; \ __governor < __governor_thermal_table_end; \ __governor++) int for_each_thermal_zone(int (*cb)(struct thermal_zone_device *, void *), void *); int for_each_thermal_cooling_device(int (*cb)(struct thermal_cooling_device *, void *), void *); int for_each_thermal_governor(int (*cb)(struct thermal_governor *, void *), void *thermal_governor); struct thermal_zone_device *thermal_zone_get_by_id(int id); DEFINE_CLASS(thermal_zone_get_by_id, struct thermal_zone_device *, if (_T) put_device(&_T->device), thermal_zone_get_by_id(id), int id) static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) { return cdev->ops->get_requested_power && cdev->ops->state2power && cdev->ops->power2state; } void thermal_cdev_update(struct thermal_cooling_device *); void thermal_cdev_update_nocheck(struct thermal_cooling_device *cdev); void __thermal_cdev_update(struct thermal_cooling_device *cdev); int get_tz_trend(struct thermal_zone_device *tz, const struct thermal_trip *trip); /* * This structure is used to describe the behavior of * a certain cooling device on a certain trip point * in a certain thermal zone */ struct thermal_instance { int id; char name[THERMAL_NAME_LENGTH]; struct thermal_cooling_device *cdev; const struct thermal_trip *trip; bool initialized; unsigned long upper; /* Highest cooling state for this trip point */ unsigned long lower; /* Lowest cooling state for this trip point */ unsigned long target; /* expected cooling state */ char attr_name[THERMAL_NAME_LENGTH]; struct device_attribute attr; char weight_attr_name[THERMAL_NAME_LENGTH]; struct device_attribute weight_attr; struct list_head trip_node; /* node in trip->thermal_instances */ struct list_head cdev_node; /* node in cdev->thermal_instances */ unsigned int weight; /* The weight of the cooling device */ bool upper_no_limit; }; #define to_thermal_zone(_dev) \ container_of(_dev, struct thermal_zone_device, device) #define to_cooling_device(_dev) \ container_of(_dev, struct thermal_cooling_device, device) int thermal_register_governor(struct thermal_governor *); void thermal_unregister_governor(struct thermal_governor *); int thermal_zone_device_set_policy(struct thermal_zone_device *, char *); int thermal_build_list_of_policies(char *buf); void __thermal_zone_device_update(struct thermal_zone_device *tz, enum thermal_notify_event event); void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz); void thermal_zone_device_critical_shutdown(struct thermal_zone_device *tz); void thermal_governor_update_tz(struct thermal_zone_device *tz, enum thermal_notify_event reason); /* Helpers */ #define for_each_trip_desc(__tz, __td) \ for (__td = __tz->trips; __td - __tz->trips < __tz->num_trips; __td++) #define trip_to_trip_desc(__trip) \ container_of(__trip, struct thermal_trip_desc, trip) const char *thermal_trip_type_name(enum thermal_trip_type trip_type); void thermal_zone_set_trips(struct thermal_zone_device *tz, int low, int high); int thermal_zone_trip_id(const struct thermal_zone_device *tz, const struct thermal_trip *trip); int __thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); void thermal_zone_set_trip_hyst(struct thermal_zone_device *tz, struct thermal_trip *trip, int hyst); /* sysfs I/F */ int thermal_zone_create_device_groups(struct thermal_zone_device *tz); void thermal_zone_destroy_device_groups(struct thermal_zone_device *); void thermal_cooling_device_setup_sysfs(struct thermal_cooling_device *); void thermal_cooling_device_destroy_sysfs(struct thermal_cooling_device *cdev); void thermal_cooling_device_stats_reinit(struct thermal_cooling_device *cdev); /* used only at binding time */ ssize_t trip_point_show(struct device *, struct device_attribute *, char *); ssize_t weight_show(struct device *, struct device_attribute *, char *); ssize_t weight_store(struct device *, struct device_attribute *, const char *, size_t); #ifdef CONFIG_THERMAL_STATISTICS void thermal_cooling_device_stats_update(struct thermal_cooling_device *cdev, unsigned long new_state); #else static inline void thermal_cooling_device_stats_update(struct thermal_cooling_device *cdev, unsigned long new_state) {} #endif /* CONFIG_THERMAL_STATISTICS */ #endif /* __THERMAL_CORE_H__ */ |
| 11 11 13 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) International Business Machines Corp., 2006 * * Author: Artem Bityutskiy (Битюцкий Артём) */ /* Here we keep miscellaneous functions which are used all over the UBI code */ #include "ubi.h" /** * ubi_calc_data_len - calculate how much real data is stored in a buffer. * @ubi: UBI device description object * @buf: a buffer with the contents of the physical eraseblock * @length: the buffer length * * This function calculates how much "real data" is stored in @buf and returnes * the length. Continuous 0xFF bytes at the end of the buffer are not * considered as "real data". */ int ubi_calc_data_len(const struct ubi_device *ubi, const void *buf, int length) { int i; ubi_assert(!(length & (ubi->min_io_size - 1))); for (i = length - 1; i >= 0; i--) if (((const uint8_t *)buf)[i] != 0xFF) break; /* The resulting length must be aligned to the minimum flash I/O size */ length = ALIGN(i + 1, ubi->min_io_size); return length; } /** * ubi_check_volume - check the contents of a static volume. * @ubi: UBI device description object * @vol_id: ID of the volume to check * * This function checks if static volume @vol_id is corrupted by fully reading * it and checking data CRC. This function returns %0 if the volume is not * corrupted, %1 if it is corrupted and a negative error code in case of * failure. Dynamic volumes are not checked and zero is returned immediately. */ int ubi_check_volume(struct ubi_device *ubi, int vol_id) { void *buf; int err = 0, i; struct ubi_volume *vol = ubi->volumes[vol_id]; if (vol->vol_type != UBI_STATIC_VOLUME) return 0; buf = vmalloc(vol->usable_leb_size); if (!buf) return -ENOMEM; for (i = 0; i < vol->used_ebs; i++) { int size; cond_resched(); if (i == vol->used_ebs - 1) size = vol->last_eb_bytes; else size = vol->usable_leb_size; err = ubi_eba_read_leb(ubi, vol, i, buf, 0, size, 1); if (err) { if (mtd_is_eccerr(err)) err = 1; break; } } vfree(buf); return err; } /** * ubi_update_reserved - update bad eraseblock handling accounting data. * @ubi: UBI device description object * * This function calculates the gap between current number of PEBs reserved for * bad eraseblock handling and the required level of PEBs that must be * reserved, and if necessary, reserves more PEBs to fill that gap, according * to availability. Should be called with ubi->volumes_lock held. */ void ubi_update_reserved(struct ubi_device *ubi) { int need = ubi->beb_rsvd_level - ubi->beb_rsvd_pebs; if (need <= 0 || ubi->avail_pebs == 0) return; need = min_t(int, need, ubi->avail_pebs); ubi->avail_pebs -= need; ubi->rsvd_pebs += need; ubi->beb_rsvd_pebs += need; ubi_msg(ubi, "reserved more %d PEBs for bad PEB handling", need); } /** * ubi_calculate_reserved - calculate how many PEBs must be reserved for bad * eraseblock handling. * @ubi: UBI device description object */ void ubi_calculate_reserved(struct ubi_device *ubi) { /* * Calculate the actual number of PEBs currently needed to be reserved * for future bad eraseblock handling. */ ubi->beb_rsvd_level = ubi->bad_peb_limit - ubi->bad_peb_count; if (ubi->beb_rsvd_level < 0) { ubi->beb_rsvd_level = 0; ubi_warn(ubi, "number of bad PEBs (%d) is above the expected limit (%d), not reserving any PEBs for bad PEB handling, will use available PEBs (if any)", ubi->bad_peb_count, ubi->bad_peb_limit); } } /** * ubi_check_pattern - check if buffer contains only a certain byte pattern. * @buf: buffer to check * @patt: the pattern to check * @size: buffer size in bytes * * This function returns %1 in there are only @patt bytes in @buf, and %0 if * something else was also found. */ int ubi_check_pattern(const void *buf, uint8_t patt, int size) { int i; for (i = 0; i < size; i++) if (((const uint8_t *)buf)[i] != patt) return 0; return 1; } /* Normal UBI messages */ void ubi_msg(const struct ubi_device *ubi, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_notice(UBI_NAME_STR "%d: %pV\n", ubi->ubi_num, &vaf); va_end(args); } /* UBI warning messages */ void ubi_warn(const struct ubi_device *ubi, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_warn(UBI_NAME_STR "%d warning: %ps: %pV\n", ubi->ubi_num, __builtin_return_address(0), &vaf); va_end(args); } /* UBI error messages */ void ubi_err(const struct ubi_device *ubi, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_err(UBI_NAME_STR "%d error: %ps: %pV\n", ubi->ubi_num, __builtin_return_address(0), &vaf); va_end(args); } |
| 7 1 3 1 1 62 1 37 26 6 36 1 5 1 2 2 2 2 11 1 4 2 5 62 2 60 9 4 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 | /* * FUSE: Filesystem in Userspace * Copyright (C) 2001-2016 Miklos Szeredi <miklos@szeredi.hu> * * This program can be distributed under the terms of the GNU GPL. * See the file COPYING. */ #include "fuse_i.h" #include <linux/xattr.h> #include <linux/posix_acl_xattr.h> int fuse_setxattr(struct inode *inode, const char *name, const void *value, size_t size, int flags, unsigned int extra_flags) { struct fuse_mount *fm = get_fuse_mount(inode); FUSE_ARGS(args); struct fuse_setxattr_in inarg; int err; if (fm->fc->no_setxattr) return -EOPNOTSUPP; memset(&inarg, 0, sizeof(inarg)); inarg.size = size; inarg.flags = flags; inarg.setxattr_flags = extra_flags; args.opcode = FUSE_SETXATTR; args.nodeid = get_node_id(inode); args.in_numargs = 3; args.in_args[0].size = fm->fc->setxattr_ext ? sizeof(inarg) : FUSE_COMPAT_SETXATTR_IN_SIZE; args.in_args[0].value = &inarg; args.in_args[1].size = strlen(name) + 1; args.in_args[1].value = name; args.in_args[2].size = size; args.in_args[2].value = value; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fm->fc->no_setxattr = 1; err = -EOPNOTSUPP; } if (!err) fuse_update_ctime(inode); return err; } ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value, size_t size) { struct fuse_mount *fm = get_fuse_mount(inode); FUSE_ARGS(args); struct fuse_getxattr_in inarg; struct fuse_getxattr_out outarg; ssize_t ret; if (fm->fc->no_getxattr) return -EOPNOTSUPP; memset(&inarg, 0, sizeof(inarg)); inarg.size = size; args.opcode = FUSE_GETXATTR; args.nodeid = get_node_id(inode); args.in_numargs = 2; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.in_args[1].size = strlen(name) + 1; args.in_args[1].value = name; /* This is really two different operations rolled into one */ args.out_numargs = 1; if (size) { args.out_argvar = true; args.out_args[0].size = size; args.out_args[0].value = value; } else { args.out_args[0].size = sizeof(outarg); args.out_args[0].value = &outarg; } ret = fuse_simple_request(fm, &args); if (!ret && !size) ret = min_t(size_t, outarg.size, XATTR_SIZE_MAX); if (ret == -ENOSYS) { fm->fc->no_getxattr = 1; ret = -EOPNOTSUPP; } return ret; } static int fuse_verify_xattr_list(char *list, size_t size) { size_t origsize = size; while (size) { size_t thislen = strnlen(list, size); if (!thislen || thislen == size) return -EIO; size -= thislen + 1; list += thislen + 1; } return origsize; } ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size) { struct inode *inode = d_inode(entry); struct fuse_mount *fm = get_fuse_mount(inode); FUSE_ARGS(args); struct fuse_getxattr_in inarg; struct fuse_getxattr_out outarg; ssize_t ret; if (fuse_is_bad(inode)) return -EIO; if (!fuse_allow_current_process(fm->fc)) return -EACCES; if (fm->fc->no_listxattr) return -EOPNOTSUPP; memset(&inarg, 0, sizeof(inarg)); inarg.size = size; args.opcode = FUSE_LISTXATTR; args.nodeid = get_node_id(inode); args.in_numargs = 1; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; /* This is really two different operations rolled into one */ args.out_numargs = 1; if (size) { args.out_argvar = true; args.out_args[0].size = size; args.out_args[0].value = list; } else { args.out_args[0].size = sizeof(outarg); args.out_args[0].value = &outarg; } ret = fuse_simple_request(fm, &args); if (!ret && !size) ret = min_t(size_t, outarg.size, XATTR_LIST_MAX); if (ret > 0 && size) ret = fuse_verify_xattr_list(list, ret); if (ret == -ENOSYS) { fm->fc->no_listxattr = 1; ret = -EOPNOTSUPP; } return ret; } int fuse_removexattr(struct inode *inode, const char *name) { struct fuse_mount *fm = get_fuse_mount(inode); FUSE_ARGS(args); int err; if (fm->fc->no_removexattr) return -EOPNOTSUPP; args.opcode = FUSE_REMOVEXATTR; args.nodeid = get_node_id(inode); args.in_numargs = 2; fuse_set_zero_arg0(&args); args.in_args[1].size = strlen(name) + 1; args.in_args[1].value = name; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fm->fc->no_removexattr = 1; err = -EOPNOTSUPP; } if (!err) fuse_update_ctime(inode); return err; } static int fuse_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { if (fuse_is_bad(inode)) return -EIO; return fuse_getxattr(inode, name, value, size); } static int fuse_xattr_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { if (fuse_is_bad(inode)) return -EIO; if (!value) return fuse_removexattr(inode, name); return fuse_setxattr(inode, name, value, size, flags, 0); } static const struct xattr_handler fuse_xattr_handler = { .prefix = "", .get = fuse_xattr_get, .set = fuse_xattr_set, }; const struct xattr_handler * const fuse_xattr_handlers[] = { &fuse_xattr_handler, NULL }; |
| 20 2 2 2 2 2 2 20 20 20 20 413 360 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 | // SPDX-License-Identifier: GPL-2.0-only /* * async.c: Asynchronous function calls for boot performance * * (C) Copyright 2009 Intel Corporation * Author: Arjan van de Ven <arjan@linux.intel.com> */ /* Goals and Theory of Operation The primary goal of this feature is to reduce the kernel boot time, by doing various independent hardware delays and discovery operations decoupled and not strictly serialized. More specifically, the asynchronous function call concept allows certain operations (primarily during system boot) to happen asynchronously, out of order, while these operations still have their externally visible parts happen sequentially and in-order. (not unlike how out-of-order CPUs retire their instructions in order) Key to the asynchronous function call implementation is the concept of a "sequence cookie" (which, although it has an abstracted type, can be thought of as a monotonically incrementing number). The async core will assign each scheduled event such a sequence cookie and pass this to the called functions. The asynchronously called function should before doing a globally visible operation, such as registering device numbers, call the async_synchronize_cookie() function and pass in its own cookie. The async_synchronize_cookie() function will make sure that all asynchronous operations that were scheduled prior to the operation corresponding with the cookie have completed. Subsystem/driver initialization code that scheduled asynchronous probe functions, but which shares global resources with other drivers/subsystems that do not use the asynchronous call feature, need to do a full synchronization with the async_synchronize_full() function, before returning from their init function. This is to maintain strict ordering between the asynchronous and synchronous parts of the kernel. */ #include <linux/async.h> #include <linux/atomic.h> #include <linux/export.h> #include <linux/ktime.h> #include <linux/pid.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/workqueue.h> #include "workqueue_internal.h" static async_cookie_t next_cookie = 1; #define MAX_WORK 32768 #define ASYNC_COOKIE_MAX ULLONG_MAX /* infinity cookie */ static LIST_HEAD(async_global_pending); /* pending from all registered doms */ static ASYNC_DOMAIN(async_dfl_domain); static DEFINE_SPINLOCK(async_lock); static struct workqueue_struct *async_wq; struct async_entry { struct list_head domain_list; struct list_head global_list; struct work_struct work; async_cookie_t cookie; async_func_t func; void *data; struct async_domain *domain; }; static DECLARE_WAIT_QUEUE_HEAD(async_done); static atomic_t entry_count; static long long microseconds_since(ktime_t start) { ktime_t now = ktime_get(); return ktime_to_ns(ktime_sub(now, start)) >> 10; } static async_cookie_t lowest_in_progress(struct async_domain *domain) { struct async_entry *first = NULL; async_cookie_t ret = ASYNC_COOKIE_MAX; unsigned long flags; spin_lock_irqsave(&async_lock, flags); if (domain) { if (!list_empty(&domain->pending)) first = list_first_entry(&domain->pending, struct async_entry, domain_list); } else { if (!list_empty(&async_global_pending)) first = list_first_entry(&async_global_pending, struct async_entry, global_list); } if (first) ret = first->cookie; spin_unlock_irqrestore(&async_lock, flags); return ret; } /* * pick the first pending entry and run it */ static void async_run_entry_fn(struct work_struct *work) { struct async_entry *entry = container_of(work, struct async_entry, work); unsigned long flags; ktime_t calltime; /* 1) run (and print duration) */ pr_debug("calling %lli_%pS @ %i\n", (long long)entry->cookie, entry->func, task_pid_nr(current)); calltime = ktime_get(); entry->func(entry->data, entry->cookie); pr_debug("initcall %lli_%pS returned after %lld usecs\n", (long long)entry->cookie, entry->func, microseconds_since(calltime)); /* 2) remove self from the pending queues */ spin_lock_irqsave(&async_lock, flags); list_del_init(&entry->domain_list); list_del_init(&entry->global_list); /* 3) free the entry */ kfree(entry); atomic_dec(&entry_count); spin_unlock_irqrestore(&async_lock, flags); /* 4) wake up any waiters */ wake_up(&async_done); } static async_cookie_t __async_schedule_node_domain(async_func_t func, void *data, int node, struct async_domain *domain, struct async_entry *entry) { async_cookie_t newcookie; unsigned long flags; INIT_LIST_HEAD(&entry->domain_list); INIT_LIST_HEAD(&entry->global_list); INIT_WORK(&entry->work, async_run_entry_fn); entry->func = func; entry->data = data; entry->domain = domain; spin_lock_irqsave(&async_lock, flags); /* allocate cookie and queue */ newcookie = entry->cookie = next_cookie++; list_add_tail(&entry->domain_list, &domain->pending); if (domain->registered) list_add_tail(&entry->global_list, &async_global_pending); atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); /* schedule for execution */ queue_work_node(node, async_wq, &entry->work); return newcookie; } /** * async_schedule_node_domain - NUMA specific version of async_schedule_domain * @func: function to execute asynchronously * @data: data pointer to pass to the function * @node: NUMA node that we want to schedule this on or close to * @domain: the domain * * Returns an async_cookie_t that may be used for checkpointing later. * @domain may be used in the async_synchronize_*_domain() functions to * wait within a certain synchronization domain rather than globally. * * Note: This function may be called from atomic or non-atomic contexts. * * The node requested will be honored on a best effort basis. If the node * has no CPUs associated with it then the work is distributed among all * available CPUs. */ async_cookie_t async_schedule_node_domain(async_func_t func, void *data, int node, struct async_domain *domain) { struct async_entry *entry; unsigned long flags; async_cookie_t newcookie; /* allow irq-off callers */ entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC); /* * If we're out of memory or if there's too much work * pending already, we execute synchronously. */ if (!entry || atomic_read(&entry_count) > MAX_WORK) { kfree(entry); spin_lock_irqsave(&async_lock, flags); newcookie = next_cookie++; spin_unlock_irqrestore(&async_lock, flags); /* low on memory.. run synchronously */ func(data, newcookie); return newcookie; } return __async_schedule_node_domain(func, data, node, domain, entry); } EXPORT_SYMBOL_GPL(async_schedule_node_domain); /** * async_schedule_node - NUMA specific version of async_schedule * @func: function to execute asynchronously * @data: data pointer to pass to the function * @node: NUMA node that we want to schedule this on or close to * * Returns an async_cookie_t that may be used for checkpointing later. * Note: This function may be called from atomic or non-atomic contexts. * * The node requested will be honored on a best effort basis. If the node * has no CPUs associated with it then the work is distributed among all * available CPUs. */ async_cookie_t async_schedule_node(async_func_t func, void *data, int node) { return async_schedule_node_domain(func, data, node, &async_dfl_domain); } EXPORT_SYMBOL_GPL(async_schedule_node); /** * async_schedule_dev_nocall - A simplified variant of async_schedule_dev() * @func: function to execute asynchronously * @dev: device argument to be passed to function * * @dev is used as both the argument for the function and to provide NUMA * context for where to run the function. * * If the asynchronous execution of @func is scheduled successfully, return * true. Otherwise, do nothing and return false, unlike async_schedule_dev() * that will run the function synchronously then. */ bool async_schedule_dev_nocall(async_func_t func, struct device *dev) { struct async_entry *entry; entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL); /* Give up if there is no memory or too much work. */ if (!entry || atomic_read(&entry_count) > MAX_WORK) { kfree(entry); return false; } __async_schedule_node_domain(func, dev, dev_to_node(dev), &async_dfl_domain, entry); return true; } /** * async_synchronize_full - synchronize all asynchronous function calls * * This function waits until all asynchronous function calls have been done. */ void async_synchronize_full(void) { async_synchronize_full_domain(NULL); } EXPORT_SYMBOL_GPL(async_synchronize_full); /** * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain * @domain: the domain to synchronize * * This function waits until all asynchronous function calls for the * synchronization domain specified by @domain have been done. */ void async_synchronize_full_domain(struct async_domain *domain) { async_synchronize_cookie_domain(ASYNC_COOKIE_MAX, domain); } EXPORT_SYMBOL_GPL(async_synchronize_full_domain); /** * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing * @cookie: async_cookie_t to use as checkpoint * @domain: the domain to synchronize (%NULL for all registered domains) * * This function waits until all asynchronous function calls for the * synchronization domain specified by @domain submitted prior to @cookie * have been done. */ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain) { ktime_t starttime; pr_debug("async_waiting @ %i\n", task_pid_nr(current)); starttime = ktime_get(); wait_event(async_done, lowest_in_progress(domain) >= cookie); pr_debug("async_continuing @ %i after %lli usec\n", task_pid_nr(current), microseconds_since(starttime)); } EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain); /** * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing * @cookie: async_cookie_t to use as checkpoint * * This function waits until all asynchronous function calls prior to @cookie * have been done. */ void async_synchronize_cookie(async_cookie_t cookie) { async_synchronize_cookie_domain(cookie, &async_dfl_domain); } EXPORT_SYMBOL_GPL(async_synchronize_cookie); /** * current_is_async - is %current an async worker task? * * Returns %true if %current is an async worker task. */ bool current_is_async(void) { struct worker *worker = current_wq_worker(); return worker && worker->current_func == async_run_entry_fn; } EXPORT_SYMBOL_GPL(current_is_async); void __init async_init(void) { /* * Async can schedule a number of interdependent work items. However, * unbound workqueues can handle only upto min_active interdependent * work items. The default min_active of 8 isn't sufficient for async * and can lead to stalls. Let's use a dedicated workqueue with raised * min_active. */ async_wq = alloc_workqueue("async", WQ_UNBOUND, 0); BUG_ON(!async_wq); workqueue_set_min_active(async_wq, WQ_DFL_ACTIVE); } |
| 8 8 8 8 8 8 8 8 8 9 9 9 15 15 14 8 8 8 8 8 8 8 8 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 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 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 | // SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> #include <linux/module.h> #include <linux/err.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/uaccess.h> #ifdef CONFIG_BLOCK #include <linux/bio.h> #endif #include <linux/ceph/ceph_features.h> #include <linux/ceph/libceph.h> #include <linux/ceph/osd_client.h> #include <linux/ceph/messenger.h> #include <linux/ceph/decode.h> #include <linux/ceph/auth.h> #include <linux/ceph/pagelist.h> #include <linux/ceph/striper.h> #define OSD_OPREPLY_FRONT_LEN 512 static struct kmem_cache *ceph_osd_request_cache; static const struct ceph_connection_operations osd_con_ops; /* * Implement client access to distributed object storage cluster. * * All data objects are stored within a cluster/cloud of OSDs, or * "object storage devices." (Note that Ceph OSDs have _nothing_ to * do with the T10 OSD extensions to SCSI.) Ceph OSDs are simply * remote daemons serving up and coordinating consistent and safe * access to storage. * * Cluster membership and the mapping of data objects onto storage devices * are described by the osd map. * * We keep track of pending OSD requests (read, write), resubmit * requests to different OSDs when the cluster topology/data layout * change, or retry the affected requests when the communications * channel with an OSD is reset. */ static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req); static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req); static void link_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq); static void unlink_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq); static void clear_backoffs(struct ceph_osd *osd); #if 1 static inline bool rwsem_is_wrlocked(struct rw_semaphore *sem) { bool wrlocked = true; if (unlikely(down_read_trylock(sem))) { wrlocked = false; up_read(sem); } return wrlocked; } static inline void verify_osdc_locked(struct ceph_osd_client *osdc) { WARN_ON(!rwsem_is_locked(&osdc->lock)); } static inline void verify_osdc_wrlocked(struct ceph_osd_client *osdc) { WARN_ON(!rwsem_is_wrlocked(&osdc->lock)); } static inline void verify_osd_locked(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; WARN_ON(!(mutex_is_locked(&osd->lock) && rwsem_is_locked(&osdc->lock)) && !rwsem_is_wrlocked(&osdc->lock)); } static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq) { WARN_ON(!mutex_is_locked(&lreq->lock)); } #else static inline void verify_osdc_locked(struct ceph_osd_client *osdc) { } static inline void verify_osdc_wrlocked(struct ceph_osd_client *osdc) { } static inline void verify_osd_locked(struct ceph_osd *osd) { } static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq) { } #endif /* * calculate the mapping of a file extent onto an object, and fill out the * request accordingly. shorten extent as necessary if it crosses an * object boundary. * * fill osd op in request message. */ static int calc_layout(struct ceph_file_layout *layout, u64 off, u64 *plen, u64 *objnum, u64 *objoff, u64 *objlen) { u64 orig_len = *plen; u32 xlen; /* object extent? */ ceph_calc_file_object_mapping(layout, off, orig_len, objnum, objoff, &xlen); *objlen = xlen; if (*objlen < orig_len) { *plen = *objlen; dout(" skipping last %llu, final file extent %llu~%llu\n", orig_len - *plen, off, *plen); } dout("calc_layout objnum=%llx %llu~%llu\n", *objnum, *objoff, *objlen); return 0; } static void ceph_osd_data_init(struct ceph_osd_data *osd_data) { memset(osd_data, 0, sizeof (*osd_data)); osd_data->type = CEPH_OSD_DATA_TYPE_NONE; } /* * Consumes @pages if @own_pages is true. */ static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { osd_data->type = CEPH_OSD_DATA_TYPE_PAGES; osd_data->pages = pages; osd_data->length = length; osd_data->alignment = alignment; osd_data->pages_from_pool = pages_from_pool; osd_data->own_pages = own_pages; } /* * Consumes a ref on @pagelist. */ static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data, struct ceph_pagelist *pagelist) { osd_data->type = CEPH_OSD_DATA_TYPE_PAGELIST; osd_data->pagelist = pagelist; } #ifdef CONFIG_BLOCK static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, struct ceph_bio_iter *bio_pos, u32 bio_length) { osd_data->type = CEPH_OSD_DATA_TYPE_BIO; osd_data->bio_pos = *bio_pos; osd_data->bio_length = bio_length; } #endif /* CONFIG_BLOCK */ static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data, struct ceph_bvec_iter *bvec_pos, u32 num_bvecs) { osd_data->type = CEPH_OSD_DATA_TYPE_BVECS; osd_data->bvec_pos = *bvec_pos; osd_data->num_bvecs = num_bvecs; } static void ceph_osd_iter_init(struct ceph_osd_data *osd_data, struct iov_iter *iter) { osd_data->type = CEPH_OSD_DATA_TYPE_ITER; osd_data->iter = *iter; } static struct ceph_osd_data * osd_req_op_raw_data_in(struct ceph_osd_request *osd_req, unsigned int which) { BUG_ON(which >= osd_req->r_num_ops); return &osd_req->r_ops[which].raw_data_in; } struct ceph_osd_data * osd_req_op_extent_osd_data(struct ceph_osd_request *osd_req, unsigned int which) { return osd_req_op_data(osd_req, which, extent, osd_data); } EXPORT_SYMBOL(osd_req_op_extent_osd_data); void osd_req_op_raw_data_in_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_raw_data_in(osd_req, which); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); } EXPORT_SYMBOL(osd_req_op_raw_data_in_pages); void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_pages); #ifdef CONFIG_BLOCK void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_bio_iter *bio_pos, u32 bio_length) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_bio_init(osd_data, bio_pos, bio_length); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio); #endif /* CONFIG_BLOCK */ void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req, unsigned int which, struct bio_vec *bvecs, u32 num_bvecs, u32 bytes) { struct ceph_osd_data *osd_data; struct ceph_bvec_iter it = { .bvecs = bvecs, .iter = { .bi_size = bytes }, }; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvecs); void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_bvec_iter *bvec_pos) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_bvecs_init(osd_data, bvec_pos, 0); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos); /** * osd_req_op_extent_osd_iter - Set up an operation with an iterator buffer * @osd_req: The request to set up * @which: Index of the operation in which to set the iter * @iter: The buffer iterator */ void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req, unsigned int which, struct iov_iter *iter) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_iter_init(osd_data, iter); } EXPORT_SYMBOL(osd_req_op_extent_osd_iter); static void osd_req_op_cls_request_info_pagelist( struct ceph_osd_request *osd_req, unsigned int which, struct ceph_pagelist *pagelist) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, request_info); ceph_osd_data_pagelist_init(osd_data, pagelist); } void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, request_data); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); osd_req->r_ops[which].cls.indata_len += length; osd_req->r_ops[which].indata_len += length; } EXPORT_SYMBOL(osd_req_op_cls_request_data_pages); void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req, unsigned int which, struct bio_vec *bvecs, u32 num_bvecs, u32 bytes) { struct ceph_osd_data *osd_data; struct ceph_bvec_iter it = { .bvecs = bvecs, .iter = { .bi_size = bytes }, }; osd_data = osd_req_op_data(osd_req, which, cls, request_data); ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs); osd_req->r_ops[which].cls.indata_len += bytes; osd_req->r_ops[which].indata_len += bytes; } EXPORT_SYMBOL(osd_req_op_cls_request_data_bvecs); void osd_req_op_cls_response_data_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, response_data); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); } EXPORT_SYMBOL(osd_req_op_cls_response_data_pages); static u64 ceph_osd_data_length(struct ceph_osd_data *osd_data) { switch (osd_data->type) { case CEPH_OSD_DATA_TYPE_NONE: return 0; case CEPH_OSD_DATA_TYPE_PAGES: return osd_data->length; case CEPH_OSD_DATA_TYPE_PAGELIST: return (u64)osd_data->pagelist->length; #ifdef CONFIG_BLOCK case CEPH_OSD_DATA_TYPE_BIO: return (u64)osd_data->bio_length; #endif /* CONFIG_BLOCK */ case CEPH_OSD_DATA_TYPE_BVECS: return osd_data->bvec_pos.iter.bi_size; case CEPH_OSD_DATA_TYPE_ITER: return iov_iter_count(&osd_data->iter); default: WARN(true, "unrecognized data type %d\n", (int)osd_data->type); return 0; } } static void ceph_osd_data_release(struct ceph_osd_data *osd_data) { if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES && osd_data->own_pages) { int num_pages; num_pages = calc_pages_for((u64)osd_data->alignment, (u64)osd_data->length); ceph_release_page_vector(osd_data->pages, num_pages); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) { ceph_pagelist_release(osd_data->pagelist); } ceph_osd_data_init(osd_data); } static void osd_req_op_data_release(struct ceph_osd_request *osd_req, unsigned int which) { struct ceph_osd_req_op *op; BUG_ON(which >= osd_req->r_num_ops); op = &osd_req->r_ops[which]; switch (op->op) { case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: kfree(op->extent.sparse_ext); ceph_osd_data_release(&op->extent.osd_data); break; case CEPH_OSD_OP_CALL: ceph_osd_data_release(&op->cls.request_info); ceph_osd_data_release(&op->cls.request_data); ceph_osd_data_release(&op->cls.response_data); break; case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: ceph_osd_data_release(&op->xattr.osd_data); break; case CEPH_OSD_OP_STAT: ceph_osd_data_release(&op->raw_data_in); break; case CEPH_OSD_OP_NOTIFY_ACK: ceph_osd_data_release(&op->notify_ack.request_data); break; case CEPH_OSD_OP_NOTIFY: ceph_osd_data_release(&op->notify.request_data); ceph_osd_data_release(&op->notify.response_data); break; case CEPH_OSD_OP_LIST_WATCHERS: ceph_osd_data_release(&op->list_watchers.response_data); break; case CEPH_OSD_OP_COPY_FROM2: ceph_osd_data_release(&op->copy_from.osd_data); break; default: break; } } /* * Assumes @t is zero-initialized. */ static void target_init(struct ceph_osd_request_target *t) { ceph_oid_init(&t->base_oid); ceph_oloc_init(&t->base_oloc); ceph_oid_init(&t->target_oid); ceph_oloc_init(&t->target_oloc); ceph_osds_init(&t->acting); ceph_osds_init(&t->up); t->size = -1; t->min_size = -1; t->osd = CEPH_HOMELESS_OSD; } static void target_copy(struct ceph_osd_request_target *dest, const struct ceph_osd_request_target *src) { ceph_oid_copy(&dest->base_oid, &src->base_oid); ceph_oloc_copy(&dest->base_oloc, &src->base_oloc); ceph_oid_copy(&dest->target_oid, &src->target_oid); ceph_oloc_copy(&dest->target_oloc, &src->target_oloc); dest->pgid = src->pgid; /* struct */ dest->spgid = src->spgid; /* struct */ dest->pg_num = src->pg_num; dest->pg_num_mask = src->pg_num_mask; ceph_osds_copy(&dest->acting, &src->acting); ceph_osds_copy(&dest->up, &src->up); dest->size = src->size; dest->min_size = src->min_size; dest->sort_bitwise = src->sort_bitwise; dest->recovery_deletes = src->recovery_deletes; dest->flags = src->flags; dest->used_replica = src->used_replica; dest->paused = src->paused; dest->epoch = src->epoch; dest->last_force_resend = src->last_force_resend; dest->osd = src->osd; } static void target_destroy(struct ceph_osd_request_target *t) { ceph_oid_destroy(&t->base_oid); ceph_oloc_destroy(&t->base_oloc); ceph_oid_destroy(&t->target_oid); ceph_oloc_destroy(&t->target_oloc); } /* * requests */ static void request_release_checks(struct ceph_osd_request *req) { WARN_ON(!RB_EMPTY_NODE(&req->r_node)); WARN_ON(!RB_EMPTY_NODE(&req->r_mc_node)); WARN_ON(!list_empty(&req->r_private_item)); WARN_ON(req->r_osd); } static void ceph_osdc_release_request(struct kref *kref) { struct ceph_osd_request *req = container_of(kref, struct ceph_osd_request, r_kref); unsigned int which; dout("%s %p (r_request %p r_reply %p)\n", __func__, req, req->r_request, req->r_reply); request_release_checks(req); if (req->r_request) ceph_msg_put(req->r_request); if (req->r_reply) ceph_msg_put(req->r_reply); for (which = 0; which < req->r_num_ops; which++) osd_req_op_data_release(req, which); target_destroy(&req->r_t); ceph_put_snap_context(req->r_snapc); if (req->r_mempool) mempool_free(req, req->r_osdc->req_mempool); else if (req->r_num_ops <= CEPH_OSD_SLAB_OPS) kmem_cache_free(ceph_osd_request_cache, req); else kfree(req); } void ceph_osdc_get_request(struct ceph_osd_request *req) { dout("%s %p (was %d)\n", __func__, req, kref_read(&req->r_kref)); kref_get(&req->r_kref); } EXPORT_SYMBOL(ceph_osdc_get_request); void ceph_osdc_put_request(struct ceph_osd_request *req) { if (req) { dout("%s %p (was %d)\n", __func__, req, kref_read(&req->r_kref)); kref_put(&req->r_kref, ceph_osdc_release_request); } } EXPORT_SYMBOL(ceph_osdc_put_request); static void request_init(struct ceph_osd_request *req) { /* req only, each op is zeroed in osd_req_op_init() */ memset(req, 0, sizeof(*req)); kref_init(&req->r_kref); init_completion(&req->r_completion); RB_CLEAR_NODE(&req->r_node); RB_CLEAR_NODE(&req->r_mc_node); INIT_LIST_HEAD(&req->r_private_item); target_init(&req->r_t); } struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_ops, bool use_mempool, gfp_t gfp_flags) { struct ceph_osd_request *req; if (use_mempool) { BUG_ON(num_ops > CEPH_OSD_SLAB_OPS); req = mempool_alloc(osdc->req_mempool, gfp_flags); } else if (num_ops <= CEPH_OSD_SLAB_OPS) { req = kmem_cache_alloc(ceph_osd_request_cache, gfp_flags); } else { BUG_ON(num_ops > CEPH_OSD_MAX_OPS); req = kmalloc(struct_size(req, r_ops, num_ops), gfp_flags); } if (unlikely(!req)) return NULL; request_init(req); req->r_osdc = osdc; req->r_mempool = use_mempool; req->r_num_ops = num_ops; req->r_snapid = CEPH_NOSNAP; req->r_snapc = ceph_get_snap_context(snapc); dout("%s req %p\n", __func__, req); return req; } EXPORT_SYMBOL(ceph_osdc_alloc_request); static int ceph_oloc_encoding_size(const struct ceph_object_locator *oloc) { return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0); } static int __ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp, int num_request_data_items, int num_reply_data_items) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_msg *msg; int msg_size; WARN_ON(req->r_request || req->r_reply); WARN_ON(ceph_oid_empty(&req->r_base_oid)); WARN_ON(ceph_oloc_empty(&req->r_base_oloc)); /* create request message */ msg_size = CEPH_ENCODING_START_BLK_LEN + CEPH_PGID_ENCODING_LEN + 1; /* spgid */ msg_size += 4 + 4 + 4; /* hash, osdmap_epoch, flags */ msg_size += CEPH_ENCODING_START_BLK_LEN + sizeof(struct ceph_osd_reqid); /* reqid */ msg_size += sizeof(struct ceph_blkin_trace_info); /* trace */ msg_size += 4 + sizeof(struct ceph_timespec); /* client_inc, mtime */ msg_size += CEPH_ENCODING_START_BLK_LEN + ceph_oloc_encoding_size(&req->r_base_oloc); /* oloc */ msg_size += 4 + req->r_base_oid.name_len; /* oid */ msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op); msg_size += 8; /* snapid */ msg_size += 8; /* snap_seq */ msg_size += 4 + 8 * (req->r_snapc ? req->r_snapc->num_snaps : 0); msg_size += 4 + 8; /* retry_attempt, features */ if (req->r_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op, msg_size, num_request_data_items); else msg = ceph_msg_new2(CEPH_MSG_OSD_OP, msg_size, num_request_data_items, gfp, true); if (!msg) return -ENOMEM; memset(msg->front.iov_base, 0, msg->front.iov_len); req->r_request = msg; /* create reply message */ msg_size = OSD_OPREPLY_FRONT_LEN; msg_size += req->r_base_oid.name_len; msg_size += req->r_num_ops * sizeof(struct ceph_osd_op); if (req->r_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op_reply, msg_size, num_reply_data_items); else msg = ceph_msg_new2(CEPH_MSG_OSD_OPREPLY, msg_size, num_reply_data_items, gfp, true); if (!msg) return -ENOMEM; req->r_reply = msg; return 0; } static bool osd_req_opcode_valid(u16 opcode) { switch (opcode) { #define GENERATE_CASE(op, opcode, str) case CEPH_OSD_OP_##op: return true; __CEPH_FORALL_OSD_OPS(GENERATE_CASE) #undef GENERATE_CASE default: return false; } } static void get_num_data_items(struct ceph_osd_request *req, int *num_request_data_items, int *num_reply_data_items) { struct ceph_osd_req_op *op; *num_request_data_items = 0; *num_reply_data_items = 0; for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) { switch (op->op) { /* request */ case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: case CEPH_OSD_OP_NOTIFY_ACK: case CEPH_OSD_OP_COPY_FROM2: *num_request_data_items += 1; break; /* reply */ case CEPH_OSD_OP_STAT: case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: case CEPH_OSD_OP_LIST_WATCHERS: *num_reply_data_items += 1; break; /* both */ case CEPH_OSD_OP_NOTIFY: *num_request_data_items += 1; *num_reply_data_items += 1; break; case CEPH_OSD_OP_CALL: *num_request_data_items += 2; *num_reply_data_items += 1; break; default: WARN_ON(!osd_req_opcode_valid(op->op)); break; } } } /* * oid, oloc and OSD op opcode(s) must be filled in before this function * is called. */ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp) { int num_request_data_items, num_reply_data_items; get_num_data_items(req, &num_request_data_items, &num_reply_data_items); return __ceph_osdc_alloc_messages(req, gfp, num_request_data_items, num_reply_data_items); } EXPORT_SYMBOL(ceph_osdc_alloc_messages); /* * This is an osd op init function for opcodes that have no data or * other information associated with them. It also serves as a * common init routine for all the other init functions, below. */ struct ceph_osd_req_op * osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u32 flags) { struct ceph_osd_req_op *op; BUG_ON(which >= osd_req->r_num_ops); BUG_ON(!osd_req_opcode_valid(opcode)); op = &osd_req->r_ops[which]; memset(op, 0, sizeof (*op)); op->op = opcode; op->flags = flags; return op; } EXPORT_SYMBOL(osd_req_op_init); void osd_req_op_extent_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 offset, u64 length, u64 truncate_size, u32 truncate_seq) { struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which, opcode, 0); size_t payload_len = 0; BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE && opcode != CEPH_OSD_OP_SPARSE_READ); op->extent.offset = offset; op->extent.length = length; op->extent.truncate_size = truncate_size; op->extent.truncate_seq = truncate_seq; if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL) payload_len += length; op->indata_len = payload_len; } EXPORT_SYMBOL(osd_req_op_extent_init); void osd_req_op_extent_update(struct ceph_osd_request *osd_req, unsigned int which, u64 length) { struct ceph_osd_req_op *op; u64 previous; BUG_ON(which >= osd_req->r_num_ops); op = &osd_req->r_ops[which]; previous = op->extent.length; if (length == previous) return; /* Nothing to do */ BUG_ON(length > previous); op->extent.length = length; if (op->op == CEPH_OSD_OP_WRITE || op->op == CEPH_OSD_OP_WRITEFULL) op->indata_len -= previous - length; } EXPORT_SYMBOL(osd_req_op_extent_update); void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req, unsigned int which, u64 offset_inc) { struct ceph_osd_req_op *op, *prev_op; BUG_ON(which + 1 >= osd_req->r_num_ops); prev_op = &osd_req->r_ops[which]; op = osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags); /* dup previous one */ op->indata_len = prev_op->indata_len; op->outdata_len = prev_op->outdata_len; op->extent = prev_op->extent; /* adjust offset */ op->extent.offset += offset_inc; op->extent.length -= offset_inc; if (op->op == CEPH_OSD_OP_WRITE || op->op == CEPH_OSD_OP_WRITEFULL) op->indata_len -= offset_inc; } EXPORT_SYMBOL(osd_req_op_extent_dup_last); int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, const char *class, const char *method) { struct ceph_osd_req_op *op; struct ceph_pagelist *pagelist; size_t payload_len = 0; size_t size; int ret; op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0); pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!pagelist) return -ENOMEM; op->cls.class_name = class; size = strlen(class); BUG_ON(size > (size_t) U8_MAX); op->cls.class_len = size; ret = ceph_pagelist_append(pagelist, class, size); if (ret) goto err_pagelist_free; payload_len += size; op->cls.method_name = method; size = strlen(method); BUG_ON(size > (size_t) U8_MAX); op->cls.method_len = size; ret = ceph_pagelist_append(pagelist, method, size); if (ret) goto err_pagelist_free; payload_len += size; osd_req_op_cls_request_info_pagelist(osd_req, which, pagelist); op->indata_len = payload_len; return 0; err_pagelist_free: ceph_pagelist_release(pagelist); return ret; } EXPORT_SYMBOL(osd_req_op_cls_init); int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *name, const void *value, size_t size, u8 cmp_op, u8 cmp_mode) { struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which, opcode, 0); struct ceph_pagelist *pagelist; size_t payload_len; int ret; BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR); pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!pagelist) return -ENOMEM; payload_len = strlen(name); op->xattr.name_len = payload_len; ret = ceph_pagelist_append(pagelist, name, payload_len); if (ret) goto err_pagelist_free; op->xattr.value_len = size; ret = ceph_pagelist_append(pagelist, value, size); if (ret) goto err_pagelist_free; payload_len += size; op->xattr.cmp_op = cmp_op; op->xattr.cmp_mode = cmp_mode; ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist); op->indata_len = payload_len; return 0; err_pagelist_free: ceph_pagelist_release(pagelist); return ret; } EXPORT_SYMBOL(osd_req_op_xattr_init); /* * @watch_opcode: CEPH_OSD_WATCH_OP_* */ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which, u8 watch_opcode, u64 cookie, u32 gen) { struct ceph_osd_req_op *op; op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0); op->watch.cookie = cookie; op->watch.op = watch_opcode; op->watch.gen = gen; } /* * prot_ver, timeout and notify payload (may be empty) should already be * encoded in @request_pl */ static void osd_req_op_notify_init(struct ceph_osd_request *req, int which, u64 cookie, struct ceph_pagelist *request_pl) { struct ceph_osd_req_op *op; op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); op->notify.cookie = cookie; ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl); op->indata_len = request_pl->length; } /* * @flags: CEPH_OSD_OP_ALLOC_HINT_FLAG_* */ void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req, unsigned int which, u64 expected_object_size, u64 expected_write_size, u32 flags) { struct ceph_osd_req_op *op; op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_SETALLOCHINT, 0); op->alloc_hint.expected_object_size = expected_object_size; op->alloc_hint.expected_write_size = expected_write_size; op->alloc_hint.flags = flags; /* * CEPH_OSD_OP_SETALLOCHINT op is advisory and therefore deemed * not worth a feature bit. Set FAILOK per-op flag to make * sure older osds don't trip over an unsupported opcode. */ op->flags |= CEPH_OSD_OP_FLAG_FAILOK; } EXPORT_SYMBOL(osd_req_op_alloc_hint_init); static void ceph_osdc_msg_data_add(struct ceph_msg *msg, struct ceph_osd_data *osd_data) { u64 length = ceph_osd_data_length(osd_data); if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) { BUG_ON(length > (u64) SIZE_MAX); if (length) ceph_msg_data_add_pages(msg, osd_data->pages, length, osd_data->alignment, false); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) { BUG_ON(!length); ceph_msg_data_add_pagelist(msg, osd_data->pagelist); #ifdef CONFIG_BLOCK } else if (osd_data->type == CEPH_OSD_DATA_TYPE_BIO) { ceph_msg_data_add_bio(msg, &osd_data->bio_pos, length); #endif } else if (osd_data->type == CEPH_OSD_DATA_TYPE_BVECS) { ceph_msg_data_add_bvecs(msg, &osd_data->bvec_pos); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_ITER) { ceph_msg_data_add_iter(msg, &osd_data->iter); } else { BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_NONE); } } static u32 osd_req_encode_op(struct ceph_osd_op *dst, const struct ceph_osd_req_op *src) { switch (src->op) { case CEPH_OSD_OP_STAT: break; case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: case CEPH_OSD_OP_ZERO: case CEPH_OSD_OP_TRUNCATE: dst->extent.offset = cpu_to_le64(src->extent.offset); dst->extent.length = cpu_to_le64(src->extent.length); dst->extent.truncate_size = cpu_to_le64(src->extent.truncate_size); dst->extent.truncate_seq = cpu_to_le32(src->extent.truncate_seq); break; case CEPH_OSD_OP_CALL: dst->cls.class_len = src->cls.class_len; dst->cls.method_len = src->cls.method_len; dst->cls.indata_len = cpu_to_le32(src->cls.indata_len); break; case CEPH_OSD_OP_WATCH: dst->watch.cookie = cpu_to_le64(src->watch.cookie); dst->watch.ver = cpu_to_le64(0); dst->watch.op = src->watch.op; dst->watch.gen = cpu_to_le32(src->watch.gen); break; case CEPH_OSD_OP_NOTIFY_ACK: break; case CEPH_OSD_OP_NOTIFY: dst->notify.cookie = cpu_to_le64(src->notify.cookie); break; case CEPH_OSD_OP_LIST_WATCHERS: break; case CEPH_OSD_OP_SETALLOCHINT: dst->alloc_hint.expected_object_size = cpu_to_le64(src->alloc_hint.expected_object_size); dst->alloc_hint.expected_write_size = cpu_to_le64(src->alloc_hint.expected_write_size); dst->alloc_hint.flags = cpu_to_le32(src->alloc_hint.flags); break; case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: dst->xattr.name_len = cpu_to_le32(src->xattr.name_len); dst->xattr.value_len = cpu_to_le32(src->xattr.value_len); dst->xattr.cmp_op = src->xattr.cmp_op; dst->xattr.cmp_mode = src->xattr.cmp_mode; break; case CEPH_OSD_OP_CREATE: case CEPH_OSD_OP_DELETE: break; case CEPH_OSD_OP_COPY_FROM2: dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid); dst->copy_from.src_version = cpu_to_le64(src->copy_from.src_version); dst->copy_from.flags = src->copy_from.flags; dst->copy_from.src_fadvise_flags = cpu_to_le32(src->copy_from.src_fadvise_flags); break; case CEPH_OSD_OP_ASSERT_VER: dst->assert_ver.unused = cpu_to_le64(0); dst->assert_ver.ver = cpu_to_le64(src->assert_ver.ver); break; default: pr_err("unsupported osd opcode %s\n", ceph_osd_op_name(src->op)); WARN_ON(1); return 0; } dst->op = cpu_to_le16(src->op); dst->flags = cpu_to_le32(src->flags); dst->payload_len = cpu_to_le32(src->indata_len); return src->indata_len; } /* * build new request AND message, calculate layout, and adjust file * extent as needed. * * if the file was recently truncated, we include information about its * old and new size so that the object can be updated appropriately. (we * avoid synchronously deleting truncated objects because it's slow.) */ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, struct ceph_file_layout *layout, struct ceph_vino vino, u64 off, u64 *plen, unsigned int which, int num_ops, int opcode, int flags, struct ceph_snap_context *snapc, u32 truncate_seq, u64 truncate_size, bool use_mempool) { struct ceph_osd_request *req; u64 objnum = 0; u64 objoff = 0; u64 objlen = 0; int r; BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE && opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_SPARSE_READ); req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool, GFP_NOFS); if (!req) { r = -ENOMEM; goto fail; } /* calculate max write size */ r = calc_layout(layout, off, plen, &objnum, &objoff, &objlen); if (r) goto fail; if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) { osd_req_op_init(req, which, opcode, 0); } else { u32 object_size = layout->object_size; u32 object_base = off - objoff; if (!(truncate_seq == 1 && truncate_size == -1ULL)) { if (truncate_size <= object_base) { truncate_size = 0; } else { truncate_size -= object_base; if (truncate_size > object_size) truncate_size = object_size; } } osd_req_op_extent_init(req, which, opcode, objoff, objlen, truncate_size, truncate_seq); } req->r_base_oloc.pool = layout->pool_id; req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns); ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum); req->r_flags = flags | osdc->client->options->read_from_replica; req->r_snapid = vino.snap; if (flags & CEPH_OSD_FLAG_WRITE) req->r_data_offset = off; if (num_ops > 1) { int num_req_ops, num_rep_ops; /* * If this is a multi-op write request, assume that we'll need * request ops. If it's a multi-op read then assume we'll need * reply ops. Anything else and call it -EINVAL. */ if (flags & CEPH_OSD_FLAG_WRITE) { num_req_ops = num_ops; num_rep_ops = 0; } else if (flags & CEPH_OSD_FLAG_READ) { num_req_ops = 0; num_rep_ops = num_ops; } else { r = -EINVAL; goto fail; } r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_req_ops, num_rep_ops); } else { r = ceph_osdc_alloc_messages(req, GFP_NOFS); } if (r) goto fail; return req; fail: ceph_osdc_put_request(req); return ERR_PTR(r); } EXPORT_SYMBOL(ceph_osdc_new_request); int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt) { WARN_ON(op->op != CEPH_OSD_OP_SPARSE_READ); op->extent.sparse_ext_cnt = cnt; op->extent.sparse_ext = kmalloc_array(cnt, sizeof(*op->extent.sparse_ext), GFP_NOFS); if (!op->extent.sparse_ext) return -ENOMEM; return 0; } EXPORT_SYMBOL(__ceph_alloc_sparse_ext_map); /* * We keep osd requests in an rbtree, sorted by ->r_tid. */ DEFINE_RB_FUNCS(request, struct ceph_osd_request, r_tid, r_node) DEFINE_RB_FUNCS(request_mc, struct ceph_osd_request, r_tid, r_mc_node) /* * Call @fn on each OSD request as long as @fn returns 0. */ static void for_each_request(struct ceph_osd_client *osdc, int (*fn)(struct ceph_osd_request *req, void *arg), void *arg) { struct rb_node *n, *p; for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); for (p = rb_first(&osd->o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); if (fn(req, arg)) return; } } for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); if (fn(req, arg)) return; } } static bool osd_homeless(struct ceph_osd *osd) { return osd->o_osd == CEPH_HOMELESS_OSD; } static bool osd_registered(struct ceph_osd *osd) { verify_osdc_locked(osd->o_osdc); return !RB_EMPTY_NODE(&osd->o_node); } /* * Assumes @osd is zero-initialized. */ static void osd_init(struct ceph_osd *osd) { refcount_set(&osd->o_ref, 1); RB_CLEAR_NODE(&osd->o_node); spin_lock_init(&osd->o_requests_lock); osd->o_requests = RB_ROOT; osd->o_linger_requests = RB_ROOT; osd->o_backoff_mappings = RB_ROOT; osd->o_backoffs_by_id = RB_ROOT; INIT_LIST_HEAD(&osd->o_osd_lru); INIT_LIST_HEAD(&osd->o_keepalive_item); osd->o_incarnation = 1; mutex_init(&osd->lock); } static void ceph_init_sparse_read(struct ceph_sparse_read *sr) { kfree(sr->sr_extent); memset(sr, '\0', sizeof(*sr)); sr->sr_state = CEPH_SPARSE_READ_HDR; } static void osd_cleanup(struct ceph_osd *osd) { WARN_ON(!RB_EMPTY_NODE(&osd->o_node)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoff_mappings)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoffs_by_id)); WARN_ON(!list_empty(&osd->o_osd_lru)); WARN_ON(!list_empty(&osd->o_keepalive_item)); ceph_init_sparse_read(&osd->o_sparse_read); if (osd->o_auth.authorizer) { WARN_ON(osd_homeless(osd)); ceph_auth_destroy_authorizer(osd->o_auth.authorizer); } } /* * Track open sessions with osds. */ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) { struct ceph_osd *osd; WARN_ON(onum == CEPH_HOMELESS_OSD); osd = kzalloc(sizeof(*osd), GFP_NOIO | __GFP_NOFAIL); osd_init(osd); osd->o_osdc = osdc; osd->o_osd = onum; osd->o_sparse_op_idx = -1; ceph_init_sparse_read(&osd->o_sparse_read); ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr); return osd; } static struct ceph_osd *get_osd(struct ceph_osd *osd) { if (refcount_inc_not_zero(&osd->o_ref)) { dout("get_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref)-1, refcount_read(&osd->o_ref)); return osd; } else { dout("get_osd %p FAIL\n", osd); return NULL; } } static void put_osd(struct ceph_osd *osd) { dout("put_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref), refcount_read(&osd->o_ref) - 1); if (refcount_dec_and_test(&osd->o_ref)) { osd_cleanup(osd); kfree(osd); } } DEFINE_RB_FUNCS(osd, struct ceph_osd, o_osd, o_node) static void __move_osd_to_lru(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); BUG_ON(!list_empty(&osd->o_osd_lru)); spin_lock(&osdc->osd_lru_lock); list_add_tail(&osd->o_osd_lru, &osdc->osd_lru); spin_unlock(&osdc->osd_lru_lock); osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl; } static void maybe_move_osd_to_lru(struct ceph_osd *osd) { if (RB_EMPTY_ROOT(&osd->o_requests) && RB_EMPTY_ROOT(&osd->o_linger_requests)) __move_osd_to_lru(osd); } static void __remove_osd_from_lru(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); spin_lock(&osdc->osd_lru_lock); if (!list_empty(&osd->o_osd_lru)) list_del_init(&osd->o_osd_lru); spin_unlock(&osdc->osd_lru_lock); } /* * Close the connection and assign any leftover requests to the * homeless session. */ static void close_osd(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; struct rb_node *n; verify_osdc_wrlocked(osdc); dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); ceph_con_close(&osd->o_con); for (n = rb_first(&osd->o_requests); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); n = rb_next(n); /* unlink_request() */ dout(" reassigning req %p tid %llu\n", req, req->r_tid); unlink_request(osd, req); link_request(&osdc->homeless_osd, req); } for (n = rb_first(&osd->o_linger_requests); n; ) { struct ceph_osd_linger_request *lreq = rb_entry(n, struct ceph_osd_linger_request, node); n = rb_next(n); /* unlink_linger() */ dout(" reassigning lreq %p linger_id %llu\n", lreq, lreq->linger_id); unlink_linger(osd, lreq); link_linger(&osdc->homeless_osd, lreq); } clear_backoffs(osd); __remove_osd_from_lru(osd); erase_osd(&osdc->osds, osd); put_osd(osd); } /* * reset osd connect */ static int reopen_osd(struct ceph_osd *osd) { struct ceph_entity_addr *peer_addr; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); if (RB_EMPTY_ROOT(&osd->o_requests) && RB_EMPTY_ROOT(&osd->o_linger_requests)) { close_osd(osd); return -ENODEV; } peer_addr = &osd->o_osdc->osdmap->osd_addr[osd->o_osd]; if (!memcmp(peer_addr, &osd->o_con.peer_addr, sizeof (*peer_addr)) && !ceph_con_opened(&osd->o_con)) { struct rb_node *n; dout("osd addr hasn't changed and connection never opened, " "letting msgr retry\n"); /* touch each r_stamp for handle_timeout()'s benfit */ for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); req->r_stamp = jiffies; } return -EAGAIN; } ceph_con_close(&osd->o_con); ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, peer_addr); osd->o_incarnation++; return 0; } static struct ceph_osd *lookup_create_osd(struct ceph_osd_client *osdc, int o, bool wrlocked) { struct ceph_osd *osd; if (wrlocked) verify_osdc_wrlocked(osdc); else verify_osdc_locked(osdc); if (o != CEPH_HOMELESS_OSD) osd = lookup_osd(&osdc->osds, o); else osd = &osdc->homeless_osd; if (!osd) { if (!wrlocked) return ERR_PTR(-EAGAIN); osd = create_osd(osdc, o); insert_osd(&osdc->osds, osd); ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, &osdc->osdmap->osd_addr[osd->o_osd]); } dout("%s osdc %p osd%d -> osd %p\n", __func__, osdc, o, osd); return osd; } /* * Create request <-> OSD session relation. * * @req has to be assigned a tid, @osd may be homeless. */ static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req) { verify_osd_locked(osd); WARN_ON(!req->r_tid || req->r_osd); dout("%s osd %p osd%d req %p tid %llu\n", __func__, osd, osd->o_osd, req, req->r_tid); if (!osd_homeless(osd)) __remove_osd_from_lru(osd); else atomic_inc(&osd->o_osdc->num_homeless); get_osd(osd); spin_lock(&osd->o_requests_lock); insert_request(&osd->o_requests, req); spin_unlock(&osd->o_requests_lock); req->r_osd = osd; } static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req) { verify_osd_locked(osd); WARN_ON(req->r_osd != osd); dout("%s osd %p osd%d req %p tid %llu\n", __func__, osd, osd->o_osd, req, req->r_tid); req->r_osd = NULL; spin_lock(&osd->o_requests_lock); erase_request(&osd->o_requests, req); spin_unlock(&osd->o_requests_lock); put_osd(osd); if (!osd_homeless(osd)) maybe_move_osd_to_lru(osd); else atomic_dec(&osd->o_osdc->num_homeless); } static bool __pool_full(struct ceph_pg_pool_info *pi) { return pi->flags & CEPH_POOL_FLAG_FULL; } static bool have_pool_full(struct ceph_osd_client *osdc) { struct rb_node *n; for (n = rb_first(&osdc->osdmap->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = rb_entry(n, struct ceph_pg_pool_info, node); if (__pool_full(pi)) return true; } return false; } static bool pool_full(struct ceph_osd_client *osdc, s64 pool_id) { struct ceph_pg_pool_info *pi; pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id); if (!pi) return false; return __pool_full(pi); } /* * Returns whether a request should be blocked from being sent * based on the current osdmap and osd_client settings. */ static bool target_should_be_paused(struct ceph_osd_client *osdc, const struct ceph_osd_request_target *t, struct ceph_pg_pool_info *pi) { bool pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD); bool pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || __pool_full(pi); WARN_ON(pi->id != t->target_oloc.pool); return ((t->flags & CEPH_OSD_FLAG_READ) && pauserd) || ((t->flags & CEPH_OSD_FLAG_WRITE) && pausewr) || (osdc->osdmap->epoch < osdc->epoch_barrier); } static int pick_random_replica(const struct ceph_osds *acting) { int i = get_random_u32_below(acting->size); dout("%s picked osd%d, primary osd%d\n", __func__, acting->osds[i], acting->primary); return i; } /* * Picks the closest replica based on client's location given by * crush_location option. Prefers the primary if the locality is * the same. */ static int pick_closest_replica(struct ceph_osd_client *osdc, const struct ceph_osds *acting) { struct ceph_options *opt = osdc->client->options; int best_i, best_locality; int i = 0, locality; do { locality = ceph_get_crush_locality(osdc->osdmap, acting->osds[i], &opt->crush_locs); if (i == 0 || (locality >= 0 && best_locality < 0) || (locality >= 0 && best_locality >= 0 && locality < best_locality)) { best_i = i; best_locality = locality; } } while (++i < acting->size); dout("%s picked osd%d with locality %d, primary osd%d\n", __func__, acting->osds[best_i], best_locality, acting->primary); return best_i; } enum calc_target_result { CALC_TARGET_NO_ACTION = 0, CALC_TARGET_NEED_RESEND, CALC_TARGET_POOL_DNE, }; static enum calc_target_result calc_target(struct ceph_osd_client *osdc, struct ceph_osd_request_target *t, bool any_change) { struct ceph_pg_pool_info *pi; struct ceph_pg pgid, last_pgid; struct ceph_osds up, acting; bool is_read = t->flags & CEPH_OSD_FLAG_READ; bool is_write = t->flags & CEPH_OSD_FLAG_WRITE; bool force_resend = false; bool unpaused = false; bool legacy_change = false; bool split = false; bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE); bool recovery_deletes = ceph_osdmap_flag(osdc, CEPH_OSDMAP_RECOVERY_DELETES); enum calc_target_result ct_res; t->epoch = osdc->osdmap->epoch; pi = ceph_pg_pool_by_id(osdc->osdmap, t->base_oloc.pool); if (!pi) { t->osd = CEPH_HOMELESS_OSD; ct_res = CALC_TARGET_POOL_DNE; goto out; } if (osdc->osdmap->epoch == pi->last_force_request_resend) { if (t->last_force_resend < pi->last_force_request_resend) { t->last_force_resend = pi->last_force_request_resend; force_resend = true; } else if (t->last_force_resend == 0) { force_resend = true; } } /* apply tiering */ ceph_oid_copy(&t->target_oid, &t->base_oid); ceph_oloc_copy(&t->target_oloc, &t->base_oloc); if ((t->flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) { if (is_read && pi->read_tier >= 0) t->target_oloc.pool = pi->read_tier; if (is_write && pi->write_tier >= 0) t->target_oloc.pool = pi->write_tier; pi = ceph_pg_pool_by_id(osdc->osdmap, t->target_oloc.pool); if (!pi) { t->osd = CEPH_HOMELESS_OSD; ct_res = CALC_TARGET_POOL_DNE; goto out; } } __ceph_object_locator_to_pg(pi, &t->target_oid, &t->target_oloc, &pgid); last_pgid.pool = pgid.pool; last_pgid.seed = ceph_stable_mod(pgid.seed, t->pg_num, t->pg_num_mask); ceph_pg_to_up_acting_osds(osdc->osdmap, pi, &pgid, &up, &acting); if (any_change && ceph_is_new_interval(&t->acting, &acting, &t->up, &up, t->size, pi->size, t->min_size, pi->min_size, t->pg_num, pi->pg_num, t->sort_bitwise, sort_bitwise, t->recovery_deletes, recovery_deletes, &last_pgid)) force_resend = true; if (t->paused && !target_should_be_paused(osdc, t, pi)) { t->paused = false; unpaused = true; } legacy_change = ceph_pg_compare(&t->pgid, &pgid) || ceph_osds_changed(&t->acting, &acting, t->used_replica || any_change); if (t->pg_num) split = ceph_pg_is_split(&last_pgid, t->pg_num, pi->pg_num); if (legacy_change || force_resend || split) { t->pgid = pgid; /* struct */ ceph_pg_to_primary_shard(osdc->osdmap, pi, &pgid, &t->spgid); ceph_osds_copy(&t->acting, &acting); ceph_osds_copy(&t->up, &up); t->size = pi->size; t->min_size = pi->min_size; t->pg_num = pi->pg_num; t->pg_num_mask = pi->pg_num_mask; t->sort_bitwise = sort_bitwise; t->recovery_deletes = recovery_deletes; if ((t->flags & (CEPH_OSD_FLAG_BALANCE_READS | CEPH_OSD_FLAG_LOCALIZE_READS)) && !is_write && pi->type == CEPH_POOL_TYPE_REP && acting.size > 1) { int pos; WARN_ON(!is_read || acting.osds[0] != acting.primary); if (t->flags & CEPH_OSD_FLAG_BALANCE_READS) { pos = pick_random_replica(&acting); } else { pos = pick_closest_replica(osdc, &acting); } t->osd = acting.osds[pos]; t->used_replica = pos > 0; } else { t->osd = acting.primary; t->used_replica = false; } } if (unpaused || legacy_change || force_resend || split) ct_res = CALC_TARGET_NEED_RESEND; else ct_res = CALC_TARGET_NO_ACTION; out: dout("%s t %p -> %d%d%d%d ct_res %d osd%d\n", __func__, t, unpaused, legacy_change, force_resend, split, ct_res, t->osd); return ct_res; } static struct ceph_spg_mapping *alloc_spg_mapping(void) { struct ceph_spg_mapping *spg; spg = kmalloc(sizeof(*spg), GFP_NOIO); if (!spg) return NULL; RB_CLEAR_NODE(&spg->node); spg->backoffs = RB_ROOT; return spg; } static void free_spg_mapping(struct ceph_spg_mapping *spg) { WARN_ON(!RB_EMPTY_NODE(&spg->node)); WARN_ON(!RB_EMPTY_ROOT(&spg->backoffs)); kfree(spg); } /* * rbtree of ceph_spg_mapping for handling map<spg_t, ...>, similar to * ceph_pg_mapping. Used to track OSD backoffs -- a backoff [range] is * defined only within a specific spgid; it does not pass anything to * children on split, or to another primary. */ DEFINE_RB_FUNCS2(spg_mapping, struct ceph_spg_mapping, spgid, ceph_spg_compare, RB_BYPTR, const struct ceph_spg *, node) static u64 hoid_get_bitwise_key(const struct ceph_hobject_id *hoid) { return hoid->is_max ? 0x100000000ull : hoid->hash_reverse_bits; } static void hoid_get_effective_key(const struct ceph_hobject_id *hoid, void **pkey, size_t *pkey_len) { if (hoid->key_len) { *pkey = hoid->key; *pkey_len = hoid->key_len; } else { *pkey = hoid->oid; *pkey_len = hoid->oid_len; } } static int compare_names(const void *name1, size_t name1_len, const void *name2, size_t name2_len) { int ret; ret = memcmp(name1, name2, min(name1_len, name2_len)); if (!ret) { if (name1_len < name2_len) ret = -1; else if (name1_len > name2_len) ret = 1; } return ret; } static int hoid_compare(const struct ceph_hobject_id *lhs, const struct ceph_hobject_id *rhs) { void *effective_key1, *effective_key2; size_t effective_key1_len, effective_key2_len; int ret; if (lhs->is_max < rhs->is_max) return -1; if (lhs->is_max > rhs->is_max) return 1; if (lhs->pool < rhs->pool) return -1; if (lhs->pool > rhs->pool) return 1; if (hoid_get_bitwise_key(lhs) < hoid_get_bitwise_key(rhs)) return -1; if (hoid_get_bitwise_key(lhs) > hoid_get_bitwise_key(rhs)) return 1; ret = compare_names(lhs->nspace, lhs->nspace_len, rhs->nspace, rhs->nspace_len); if (ret) return ret; hoid_get_effective_key(lhs, &effective_key1, &effective_key1_len); hoid_get_effective_key(rhs, &effective_key2, &effective_key2_len); ret = compare_names(effective_key1, effective_key1_len, effective_key2, effective_key2_len); if (ret) return ret; ret = compare_names(lhs->oid, lhs->oid_len, rhs->oid, rhs->oid_len); if (ret) return ret; if (lhs->snapid < rhs->snapid) return -1; if (lhs->snapid > rhs->snapid) return 1; return 0; } /* * For decoding ->begin and ->end of MOSDBackoff only -- no MIN/MAX * compat stuff here. * * Assumes @hoid is zero-initialized. */ static int decode_hoid(void **p, void *end, struct ceph_hobject_id *hoid) { u8 struct_v; u32 struct_len; int ret; ret = ceph_start_decoding(p, end, 4, "hobject_t", &struct_v, &struct_len); if (ret) return ret; if (struct_v < 4) { pr_err("got struct_v %d < 4 of hobject_t\n", struct_v); goto e_inval; } hoid->key = ceph_extract_encoded_string(p, end, &hoid->key_len, GFP_NOIO); if (IS_ERR(hoid->key)) { ret = PTR_ERR(hoid->key); hoid->key = NULL; return ret; } hoid->oid = ceph_extract_encoded_string(p, end, &hoid->oid_len, GFP_NOIO); if (IS_ERR(hoid->oid)) { ret = PTR_ERR(hoid->oid); hoid->oid = NULL; return ret; } ceph_decode_64_safe(p, end, hoid->snapid, e_inval); ceph_decode_32_safe(p, end, hoid->hash, e_inval); ceph_decode_8_safe(p, end, hoid->is_max, e_inval); hoid->nspace = ceph_extract_encoded_string(p, end, &hoid->nspace_len, GFP_NOIO); if (IS_ERR(hoid->nspace)) { ret = PTR_ERR(hoid->nspace); hoid->nspace = NULL; return ret; } ceph_decode_64_safe(p, end, hoid->pool, e_inval); ceph_hoid_build_hash_cache(hoid); return 0; e_inval: return -EINVAL; } static int hoid_encoding_size(const struct ceph_hobject_id *hoid) { return 8 + 4 + 1 + 8 + /* snapid, hash, is_max, pool */ 4 + hoid->key_len + 4 + hoid->oid_len + 4 + hoid->nspace_len; } static void encode_hoid(void **p, void *end, const struct ceph_hobject_id *hoid) { ceph_start_encoding(p, 4, 3, hoid_encoding_size(hoid)); ceph_encode_string(p, end, hoid->key, hoid->key_len); ceph_encode_string(p, end, hoid->oid, hoid->oid_len); ceph_encode_64(p, hoid->snapid); ceph_encode_32(p, hoid->hash); ceph_encode_8(p, hoid->is_max); ceph_encode_string(p, end, hoid->nspace, hoid->nspace_len); ceph_encode_64(p, hoid->pool); } static void free_hoid(struct ceph_hobject_id *hoid) { if (hoid) { kfree(hoid->key); kfree(hoid->oid); kfree(hoid->nspace); kfree(hoid); } } static struct ceph_osd_backoff *alloc_backoff(void) { struct ceph_osd_backoff *backoff; backoff = kzalloc(sizeof(*backoff), GFP_NOIO); if (!backoff) return NULL; RB_CLEAR_NODE(&backoff->spg_node); RB_CLEAR_NODE(&backoff->id_node); return backoff; } static void free_backoff(struct ceph_osd_backoff *backoff) { WARN_ON(!RB_EMPTY_NODE(&backoff->spg_node)); WARN_ON(!RB_EMPTY_NODE(&backoff->id_node)); free_hoid(backoff->begin); free_hoid(backoff->end); kfree(backoff); } /* * Within a specific spgid, backoffs are managed by ->begin hoid. */ DEFINE_RB_INSDEL_FUNCS2(backoff, struct ceph_osd_backoff, begin, hoid_compare, RB_BYVAL, spg_node); static struct ceph_osd_backoff *lookup_containing_backoff(struct rb_root *root, const struct ceph_hobject_id *hoid) { struct rb_node *n = root->rb_node; while (n) { struct ceph_osd_backoff *cur = rb_entry(n, struct ceph_osd_backoff, spg_node); int cmp; cmp = hoid_compare(hoid, cur->begin); if (cmp < 0) { n = n->rb_left; } else if (cmp > 0) { if (hoid_compare(hoid, cur->end) < 0) return cur; n = n->rb_right; } else { return cur; } } return NULL; } /* * Each backoff has a unique id within its OSD session. */ DEFINE_RB_FUNCS(backoff_by_id, struct ceph_osd_backoff, id, id_node) static void clear_backoffs(struct ceph_osd *osd) { while (!RB_EMPTY_ROOT(&osd->o_backoff_mappings)) { struct ceph_spg_mapping *spg = rb_entry(rb_first(&osd->o_backoff_mappings), struct ceph_spg_mapping, node); while (!RB_EMPTY_ROOT(&spg->backoffs)) { struct ceph_osd_backoff *backoff = rb_entry(rb_first(&spg->backoffs), struct ceph_osd_backoff, spg_node); erase_backoff(&spg->backoffs, backoff); erase_backoff_by_id(&osd->o_backoffs_by_id, backoff); free_backoff(backoff); } erase_spg_mapping(&osd->o_backoff_mappings, spg); free_spg_mapping(spg); } } /* * Set up a temporary, non-owning view into @t. */ static void hoid_fill_from_target(struct ceph_hobject_id *hoid, const struct ceph_osd_request_target *t) { hoid->key = NULL; hoid->key_len = 0; hoid->oid = t->target_oid.name; hoid->oid_len = t->target_oid.name_len; hoid->snapid = CEPH_NOSNAP; hoid->hash = t->pgid.seed; hoid->is_max = false; if (t->target_oloc.pool_ns) { hoid->nspace = t->target_oloc.pool_ns->str; hoid->nspace_len = t->target_oloc.pool_ns->len; } else { hoid->nspace = NULL; hoid->nspace_len = 0; } hoid->pool = t->target_oloc.pool; ceph_hoid_build_hash_cache(hoid); } static bool should_plug_request(struct ceph_osd_request *req) { struct ceph_osd *osd = req->r_osd; struct ceph_spg_mapping *spg; struct ceph_osd_backoff *backoff; struct ceph_hobject_id hoid; spg = lookup_spg_mapping(&osd->o_backoff_mappings, &req->r_t.spgid); if (!spg) return false; hoid_fill_from_target(&hoid, &req->r_t); backoff = lookup_containing_backoff(&spg->backoffs, &hoid); if (!backoff) return false; dout("%s req %p tid %llu backoff osd%d spgid %llu.%xs%d id %llu\n", __func__, req, req->r_tid, osd->o_osd, backoff->spgid.pgid.pool, backoff->spgid.pgid.seed, backoff->spgid.shard, backoff->id); return true; } /* * Keep get_num_data_items() in sync with this function. */ static void setup_request_data(struct ceph_osd_request *req) { struct ceph_msg *request_msg = req->r_request; struct ceph_msg *reply_msg = req->r_reply; struct ceph_osd_req_op *op; if (req->r_request->num_data_items || req->r_reply->num_data_items) return; WARN_ON(request_msg->data_length || reply_msg->data_length); for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) { switch (op->op) { /* request */ case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: WARN_ON(op->indata_len != op->extent.length); ceph_osdc_msg_data_add(request_msg, &op->extent.osd_data); break; case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: WARN_ON(op->indata_len != op->xattr.name_len + op->xattr.value_len); ceph_osdc_msg_data_add(request_msg, &op->xattr.osd_data); break; case CEPH_OSD_OP_NOTIFY_ACK: ceph_osdc_msg_data_add(request_msg, &op->notify_ack.request_data); break; case CEPH_OSD_OP_COPY_FROM2: ceph_osdc_msg_data_add(request_msg, &op->copy_from.osd_data); break; /* reply */ case CEPH_OSD_OP_STAT: ceph_osdc_msg_data_add(reply_msg, &op->raw_data_in); break; case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: ceph_osdc_msg_data_add(reply_msg, &op->extent.osd_data); break; case CEPH_OSD_OP_LIST_WATCHERS: ceph_osdc_msg_data_add(reply_msg, &op->list_watchers.response_data); break; /* both */ case CEPH_OSD_OP_CALL: WARN_ON(op->indata_len != op->cls.class_len + op->cls.method_len + op->cls.indata_len); ceph_osdc_msg_data_add(request_msg, &op->cls.request_info); /* optional, can be NONE */ ceph_osdc_msg_data_add(request_msg, &op->cls.request_data); /* optional, can be NONE */ ceph_osdc_msg_data_add(reply_msg, &op->cls.response_data); break; case CEPH_OSD_OP_NOTIFY: ceph_osdc_msg_data_add(request_msg, &op->notify.request_data); ceph_osdc_msg_data_add(reply_msg, &op->notify.response_data); break; } } } static void encode_pgid(void **p, const struct ceph_pg *pgid) { ceph_encode_8(p, 1); ceph_encode_64(p, pgid->pool); ceph_encode_32(p, pgid->seed); ceph_encode_32(p, -1); /* preferred */ } static void encode_spgid(void **p, const struct ceph_spg *spgid) { ceph_start_encoding(p, 1, 1, CEPH_PGID_ENCODING_LEN + 1); encode_pgid(p, &spgid->pgid); ceph_encode_8(p, spgid->shard); } static void encode_oloc(void **p, void *end, const struct ceph_object_locator *oloc) { ceph_start_encoding(p, 5, 4, ceph_oloc_encoding_size(oloc)); ceph_encode_64(p, oloc->pool); ceph_encode_32(p, -1); /* preferred */ ceph_encode_32(p, 0); /* key len */ if (oloc->pool_ns) ceph_encode_string(p, end, oloc->pool_ns->str, oloc->pool_ns->len); else ceph_encode_32(p, 0); } static void encode_request_partial(struct ceph_osd_request *req, struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const end = p + msg->front_alloc_len; u32 data_len = 0; int i; if (req->r_flags & CEPH_OSD_FLAG_WRITE) { /* snapshots aren't writeable */ WARN_ON(req->r_snapid != CEPH_NOSNAP); } else { WARN_ON(req->r_mtime.tv_sec || req->r_mtime.tv_nsec || req->r_data_offset || req->r_snapc); } setup_request_data(req); encode_spgid(&p, &req->r_t.spgid); /* actual spg */ ceph_encode_32(&p, req->r_t.pgid.seed); /* raw hash */ ceph_encode_32(&p, req->r_osdc->osdmap->epoch); ceph_encode_32(&p, req->r_flags); /* reqid */ ceph_start_encoding(&p, 2, 2, sizeof(struct ceph_osd_reqid)); memset(p, 0, sizeof(struct ceph_osd_reqid)); p += sizeof(struct ceph_osd_reqid); /* trace */ memset(p, 0, sizeof(struct ceph_blkin_trace_info)); p += sizeof(struct ceph_blkin_trace_info); ceph_encode_32(&p, 0); /* client_inc, always 0 */ ceph_encode_timespec64(p, &req->r_mtime); p += sizeof(struct ceph_timespec); encode_oloc(&p, end, &req->r_t.target_oloc); ceph_encode_string(&p, end, req->r_t.target_oid.name, req->r_t.target_oid.name_len); /* ops, can imply data */ ceph_encode_16(&p, req->r_num_ops); for (i = 0; i < req->r_num_ops; i++) { data_len += osd_req_encode_op(p, &req->r_ops[i]); p += sizeof(struct ceph_osd_op); } ceph_encode_64(&p, req->r_snapid); /* snapid */ if (req->r_snapc) { ceph_encode_64(&p, req->r_snapc->seq); ceph_encode_32(&p, req->r_snapc->num_snaps); for (i = 0; i < req->r_snapc->num_snaps; i++) ceph_encode_64(&p, req->r_snapc->snaps[i]); } else { ceph_encode_64(&p, 0); /* snap_seq */ ceph_encode_32(&p, 0); /* snaps len */ } ceph_encode_32(&p, req->r_attempts); /* retry_attempt */ BUG_ON(p > end - 8); /* space for features */ msg->hdr.version = cpu_to_le16(8); /* MOSDOp v8 */ /* front_len is finalized in encode_request_finish() */ msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); msg->hdr.data_len = cpu_to_le32(data_len); /* * The header "data_off" is a hint to the receiver allowing it * to align received data into its buffers such that there's no * need to re-copy it before writing it to disk (direct I/O). */ msg->hdr.data_off = cpu_to_le16(req->r_data_offset); dout("%s req %p msg %p oid %s oid_len %d\n", __func__, req, msg, req->r_t.target_oid.name, req->r_t.target_oid.name_len); } static void encode_request_finish(struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const partial_end = p + msg->front.iov_len; void *const end = p + msg->front_alloc_len; if (CEPH_HAVE_FEATURE(msg->con->peer_features, RESEND_ON_SPLIT)) { /* luminous OSD -- encode features and be done */ p = partial_end; ceph_encode_64(&p, msg->con->peer_features); } else { struct { char spgid[CEPH_ENCODING_START_BLK_LEN + CEPH_PGID_ENCODING_LEN + 1]; __le32 hash; __le32 epoch; __le32 flags; char reqid[CEPH_ENCODING_START_BLK_LEN + sizeof(struct ceph_osd_reqid)]; char trace[sizeof(struct ceph_blkin_trace_info)]; __le32 client_inc; struct ceph_timespec mtime; } __packed head; struct ceph_pg pgid; void *oloc, *oid, *tail; int oloc_len, oid_len, tail_len; int len; /* * Pre-luminous OSD -- reencode v8 into v4 using @head * as a temporary buffer. Encode the raw PG; the rest * is just a matter of moving oloc, oid and tail blobs * around. */ memcpy(&head, p, sizeof(head)); p += sizeof(head); oloc = p; p += CEPH_ENCODING_START_BLK_LEN; pgid.pool = ceph_decode_64(&p); p += 4 + 4; /* preferred, key len */ len = ceph_decode_32(&p); p += len; /* nspace */ oloc_len = p - oloc; oid = p; len = ceph_decode_32(&p); p += len; oid_len = p - oid; tail = p; tail_len = partial_end - p; p = msg->front.iov_base; ceph_encode_copy(&p, &head.client_inc, sizeof(head.client_inc)); ceph_encode_copy(&p, &head.epoch, sizeof(head.epoch)); ceph_encode_copy(&p, &head.flags, sizeof(head.flags)); ceph_encode_copy(&p, &head.mtime, sizeof(head.mtime)); /* reassert_version */ memset(p, 0, sizeof(struct ceph_eversion)); p += sizeof(struct ceph_eversion); BUG_ON(p >= oloc); memmove(p, oloc, oloc_len); p += oloc_len; pgid.seed = le32_to_cpu(head.hash); encode_pgid(&p, &pgid); /* raw pg */ BUG_ON(p >= oid); memmove(p, oid, oid_len); p += oid_len; /* tail -- ops, snapid, snapc, retry_attempt */ BUG_ON(p >= tail); memmove(p, tail, tail_len); p += tail_len; msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */ } BUG_ON(p > end); msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); dout("%s msg %p tid %llu %u+%u+%u v%d\n", __func__, msg, le64_to_cpu(msg->hdr.tid), le32_to_cpu(msg->hdr.front_len), le32_to_cpu(msg->hdr.middle_len), le32_to_cpu(msg->hdr.data_len), le16_to_cpu(msg->hdr.version)); } /* * @req has to be assigned a tid and registered. */ static void send_request(struct ceph_osd_request *req) { struct ceph_osd *osd = req->r_osd; verify_osd_locked(osd); WARN_ON(osd->o_osd != req->r_t.osd); /* backoff? */ if (should_plug_request(req)) return; /* * We may have a previously queued request message hanging * around. Cancel it to avoid corrupting the msgr. */ if (req->r_sent) ceph_msg_revoke(req->r_request); req->r_flags |= CEPH_OSD_FLAG_KNOWN_REDIR; if (req->r_attempts) req->r_flags |= CEPH_OSD_FLAG_RETRY; else WARN_ON(req->r_flags & CEPH_OSD_FLAG_RETRY); encode_request_partial(req, req->r_request); dout("%s req %p tid %llu to pgid %llu.%x spgid %llu.%xs%d osd%d e%u flags 0x%x attempt %d\n", __func__, req, req->r_tid, req->r_t.pgid.pool, req->r_t.pgid.seed, req->r_t.spgid.pgid.pool, req->r_t.spgid.pgid.seed, req->r_t.spgid.shard, osd->o_osd, req->r_t.epoch, req->r_flags, req->r_attempts); req->r_t.paused = false; req->r_stamp = jiffies; req->r_attempts++; req->r_sent = osd->o_incarnation; req->r_request->hdr.tid = cpu_to_le64(req->r_tid); ceph_con_send(&osd->o_con, ceph_msg_get(req->r_request)); } static void maybe_request_map(struct ceph_osd_client *osdc) { bool continuous = false; verify_osdc_locked(osdc); WARN_ON(!osdc->osdmap->epoch); if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) { dout("%s osdc %p continuous\n", __func__, osdc); continuous = true; } else { dout("%s osdc %p onetime\n", __func__, osdc); } if (ceph_monc_want_map(&osdc->client->monc, CEPH_SUB_OSDMAP, osdc->osdmap->epoch + 1, continuous)) ceph_monc_renew_subs(&osdc->client->monc); } static void complete_request(struct ceph_osd_request *req, int err); static void send_map_check(struct ceph_osd_request *req); static void __submit_request(struct ceph_osd_request *req, bool wrlocked) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osd *osd; enum calc_target_result ct_res; int err = 0; bool need_send = false; bool promoted = false; WARN_ON(req->r_tid); dout("%s req %p wrlocked %d\n", __func__, req, wrlocked); again: ct_res = calc_target(osdc, &req->r_t, false); if (ct_res == CALC_TARGET_POOL_DNE && !wrlocked) goto promote; osd = lookup_create_osd(osdc, req->r_t.osd, wrlocked); if (IS_ERR(osd)) { WARN_ON(PTR_ERR(osd) != -EAGAIN || wrlocked); goto promote; } if (osdc->abort_err) { dout("req %p abort_err %d\n", req, osdc->abort_err); err = osdc->abort_err; } else if (osdc->osdmap->epoch < osdc->epoch_barrier) { dout("req %p epoch %u barrier %u\n", req, osdc->osdmap->epoch, osdc->epoch_barrier); req->r_t.paused = true; maybe_request_map(osdc); } else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) { dout("req %p pausewr\n", req); req->r_t.paused = true; maybe_request_map(osdc); } else if ((req->r_flags & CEPH_OSD_FLAG_READ) && ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("req %p pauserd\n", req); req->r_t.paused = true; maybe_request_map(osdc); } else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && !(req->r_flags & (CEPH_OSD_FLAG_FULL_TRY | CEPH_OSD_FLAG_FULL_FORCE)) && (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || pool_full(osdc, req->r_t.base_oloc.pool))) { dout("req %p full/pool_full\n", req); if (ceph_test_opt(osdc->client, ABORT_ON_FULL)) { err = -ENOSPC; } else { if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) pr_warn_ratelimited("cluster is full (osdmap FULL)\n"); else pr_warn_ratelimited("pool %lld is full or reached quota\n", req->r_t.base_oloc.pool); req->r_t.paused = true; maybe_request_map(osdc); } } else if (!osd_homeless(osd)) { need_send = true; } else { maybe_request_map(osdc); } mutex_lock(&osd->lock); /* * Assign the tid atomically with send_request() to protect * multiple writes to the same object from racing with each * other, resulting in out of order ops on the OSDs. */ req->r_tid = atomic64_inc_return(&osdc->last_tid); link_request(osd, req); if (need_send) send_request(req); else if (err) complete_request(req, err); mutex_unlock(&osd->lock); if (!err && ct_res == CALC_TARGET_POOL_DNE) send_map_check(req); if (promoted) downgrade_write(&osdc->lock); return; promote: up_read(&osdc->lock); down_write(&osdc->lock); wrlocked = true; promoted = true; goto again; } static void account_request(struct ceph_osd_request *req) { WARN_ON(req->r_flags & (CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK)); WARN_ON(!(req->r_flags & (CEPH_OSD_FLAG_READ | CEPH_OSD_FLAG_WRITE))); req->r_flags |= CEPH_OSD_FLAG_ONDISK; atomic_inc(&req->r_osdc->num_requests); req->r_start_stamp = jiffies; req->r_start_latency = ktime_get(); } static void submit_request(struct ceph_osd_request *req, bool wrlocked) { ceph_osdc_get_request(req); account_request(req); __submit_request(req, wrlocked); } static void finish_request(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid)); dout("%s req %p tid %llu\n", __func__, req, req->r_tid); req->r_end_latency = ktime_get(); if (req->r_osd) { ceph_init_sparse_read(&req->r_osd->o_sparse_read); unlink_request(req->r_osd, req); } atomic_dec(&osdc->num_requests); /* * If an OSD has failed or returned and a request has been sent * twice, it's possible to get a reply and end up here while the * request message is queued for delivery. We will ignore the * reply, so not a big deal, but better to try and catch it. */ ceph_msg_revoke(req->r_request); ceph_msg_revoke_incoming(req->r_reply); } static void __complete_request(struct ceph_osd_request *req) { dout("%s req %p tid %llu cb %ps result %d\n", __func__, req, req->r_tid, req->r_callback, req->r_result); if (req->r_callback) req->r_callback(req); complete_all(&req->r_completion); ceph_osdc_put_request(req); } static void complete_request_workfn(struct work_struct *work) { struct ceph_osd_request *req = container_of(work, struct ceph_osd_request, r_complete_work); __complete_request(req); } /* * This is open-coded in handle_reply(). */ static void complete_request(struct ceph_osd_request *req, int err) { dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err); req->r_result = err; finish_request(req); INIT_WORK(&req->r_complete_work, complete_request_workfn); queue_work(req->r_osdc->completion_wq, &req->r_complete_work); } static void cancel_map_check(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osd_request *lookup_req; verify_osdc_wrlocked(osdc); lookup_req = lookup_request_mc(&osdc->map_checks, req->r_tid); if (!lookup_req) return; WARN_ON(lookup_req != req); erase_request_mc(&osdc->map_checks, req); ceph_osdc_put_request(req); } static void cancel_request(struct ceph_osd_request *req) { dout("%s req %p tid %llu\n", __func__, req, req->r_tid); cancel_map_check(req); finish_request(req); complete_all(&req->r_completion); ceph_osdc_put_request(req); } static void abort_request(struct ceph_osd_request *req, int err) { dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err); cancel_map_check(req); complete_request(req, err); } static int abort_fn(struct ceph_osd_request *req, void *arg) { int err = *(int *)arg; abort_request(req, err); return 0; /* continue iteration */ } /* * Abort all in-flight requests with @err and arrange for all future * requests to be failed immediately. */ void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err) { dout("%s osdc %p err %d\n", __func__, osdc, err); down_write(&osdc->lock); for_each_request(osdc, abort_fn, &err); osdc->abort_err = err; up_write(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_abort_requests); void ceph_osdc_clear_abort_err(struct ceph_osd_client *osdc) { down_write(&osdc->lock); osdc->abort_err = 0; up_write(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_clear_abort_err); static void update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb) { if (likely(eb > osdc->epoch_barrier)) { dout("updating epoch_barrier from %u to %u\n", osdc->epoch_barrier, eb); osdc->epoch_barrier = eb; /* Request map if we're not to the barrier yet */ if (eb > osdc->osdmap->epoch) maybe_request_map(osdc); } } void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb) { down_read(&osdc->lock); if (unlikely(eb > osdc->epoch_barrier)) { up_read(&osdc->lock); down_write(&osdc->lock); update_epoch_barrier(osdc, eb); up_write(&osdc->lock); } else { up_read(&osdc->lock); } } EXPORT_SYMBOL(ceph_osdc_update_epoch_barrier); /* * We can end up releasing caps as a result of abort_request(). * In that case, we probably want to ensure that the cap release message * has an updated epoch barrier in it, so set the epoch barrier prior to * aborting the first request. */ static int abort_on_full_fn(struct ceph_osd_request *req, void *arg) { struct ceph_osd_client *osdc = req->r_osdc; bool *victims = arg; if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || pool_full(osdc, req->r_t.base_oloc.pool))) { if (!*victims) { update_epoch_barrier(osdc, osdc->osdmap->epoch); *victims = true; } abort_request(req, -ENOSPC); } return 0; /* continue iteration */ } /* * Drop all pending requests that are stalled waiting on a full condition to * clear, and complete them with ENOSPC as the return code. Set the * osdc->epoch_barrier to the latest map epoch that we've seen if any were * cancelled. */ static void ceph_osdc_abort_on_full(struct ceph_osd_client *osdc) { bool victims = false; if (ceph_test_opt(osdc->client, ABORT_ON_FULL) && (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc))) for_each_request(osdc, abort_on_full_fn, &victims); } static void check_pool_dne(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osdmap *map = osdc->osdmap; verify_osdc_wrlocked(osdc); WARN_ON(!map->epoch); if (req->r_attempts) { /* * We sent a request earlier, which means that * previously the pool existed, and now it does not * (i.e., it was deleted). */ req->r_map_dne_bound = map->epoch; dout("%s req %p tid %llu pool disappeared\n", __func__, req, req->r_tid); } else { dout("%s req %p tid %llu map_dne_bound %u have %u\n", __func__, req, req->r_tid, req->r_map_dne_bound, map->epoch); } if (req->r_map_dne_bound) { if (map->epoch >= req->r_map_dne_bound) { /* we had a new enough map */ pr_info_ratelimited("tid %llu pool does not exist\n", req->r_tid); complete_request(req, -ENOENT); } } else { send_map_check(req); } } static void map_check_cb(struct ceph_mon_generic_request *greq) { struct ceph_osd_client *osdc = &greq->monc->client->osdc; struct ceph_osd_request *req; u64 tid = greq->private_data; WARN_ON(greq->result || !greq->u.newest); down_write(&osdc->lock); req = lookup_request_mc(&osdc->map_checks, tid); if (!req) { dout("%s tid %llu dne\n", __func__, tid); goto out_unlock; } dout("%s req %p tid %llu map_dne_bound %u newest %llu\n", __func__, req, req->r_tid, req->r_map_dne_bound, greq->u.newest); if (!req->r_map_dne_bound) req->r_map_dne_bound = greq->u.newest; erase_request_mc(&osdc->map_checks, req); check_pool_dne(req); ceph_osdc_put_request(req); out_unlock: up_write(&osdc->lock); } static void send_map_check(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osd_request *lookup_req; int ret; verify_osdc_wrlocked(osdc); lookup_req = lookup_request_mc(&osdc->map_checks, req->r_tid); if (lookup_req) { WARN_ON(lookup_req != req); return; } ceph_osdc_get_request(req); insert_request_mc(&osdc->map_checks, req); ret = ceph_monc_get_version_async(&osdc->client->monc, "osdmap", map_check_cb, req->r_tid); WARN_ON(ret); } /* * lingering requests, watch/notify v2 infrastructure */ static void linger_release(struct kref *kref) { struct ceph_osd_linger_request *lreq = container_of(kref, struct ceph_osd_linger_request, kref); dout("%s lreq %p reg_req %p ping_req %p\n", __func__, lreq, lreq->reg_req, lreq->ping_req); WARN_ON(!RB_EMPTY_NODE(&lreq->node)); WARN_ON(!RB_EMPTY_NODE(&lreq->osdc_node)); WARN_ON(!RB_EMPTY_NODE(&lreq->mc_node)); WARN_ON(!list_empty(&lreq->scan_item)); WARN_ON(!list_empty(&lreq->pending_lworks)); WARN_ON(lreq->osd); if (lreq->request_pl) ceph_pagelist_release(lreq->request_pl); if (lreq->notify_id_pages) ceph_release_page_vector(lreq->notify_id_pages, 1); ceph_osdc_put_request(lreq->reg_req); ceph_osdc_put_request(lreq->ping_req); target_destroy(&lreq->t); kfree(lreq); } static void linger_put(struct ceph_osd_linger_request *lreq) { if (lreq) kref_put(&lreq->kref, linger_release); } static struct ceph_osd_linger_request * linger_get(struct ceph_osd_linger_request *lreq) { kref_get(&lreq->kref); return lreq; } static struct ceph_osd_linger_request * linger_alloc(struct ceph_osd_client *osdc) { struct ceph_osd_linger_request *lreq; lreq = kzalloc(sizeof(*lreq), GFP_NOIO); if (!lreq) return NULL; kref_init(&lreq->kref); mutex_init(&lreq->lock); RB_CLEAR_NODE(&lreq->node); RB_CLEAR_NODE(&lreq->osdc_node); RB_CLEAR_NODE(&lreq->mc_node); INIT_LIST_HEAD(&lreq->scan_item); INIT_LIST_HEAD(&lreq->pending_lworks); init_completion(&lreq->reg_commit_wait); init_completion(&lreq->notify_finish_wait); lreq->osdc = osdc; target_init(&lreq->t); dout("%s lreq %p\n", __func__, lreq); return lreq; } DEFINE_RB_INSDEL_FUNCS(linger, struct ceph_osd_linger_request, linger_id, node) DEFINE_RB_FUNCS(linger_osdc, struct ceph_osd_linger_request, linger_id, osdc_node) DEFINE_RB_FUNCS(linger_mc, struct ceph_osd_linger_request, linger_id, mc_node) /* * Create linger request <-> OSD session relation. * * @lreq has to be registered, @osd may be homeless. */ static void link_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq) { verify_osd_locked(osd); WARN_ON(!lreq->linger_id || lreq->osd); dout("%s osd %p osd%d lreq %p linger_id %llu\n", __func__, osd, osd->o_osd, lreq, lreq->linger_id); if (!osd_homeless(osd)) __remove_osd_from_lru(osd); else atomic_inc(&osd->o_osdc->num_homeless); get_osd(osd); insert_linger(&osd->o_linger_requests, lreq); lreq->osd = osd; } static void unlink_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq) { verify_osd_locked(osd); WARN_ON(lreq->osd != osd); dout("%s osd %p osd%d lreq %p linger_id %llu\n", __func__, osd, osd->o_osd, lreq, lreq->linger_id); lreq->osd = NULL; erase_linger(&osd->o_linger_requests, lreq); put_osd(osd); if (!osd_homeless(osd)) maybe_move_osd_to_lru(osd); else atomic_dec(&osd->o_osdc->num_homeless); } static bool __linger_registered(struct ceph_osd_linger_request *lreq) { verify_osdc_locked(lreq->osdc); return !RB_EMPTY_NODE(&lreq->osdc_node); } static bool linger_registered(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; bool registered; down_read(&osdc->lock); registered = __linger_registered(lreq); up_read(&osdc->lock); return registered; } static void linger_register(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; verify_osdc_wrlocked(osdc); WARN_ON(lreq->linger_id); linger_get(lreq); lreq->linger_id = ++osdc->last_linger_id; insert_linger_osdc(&osdc->linger_requests, lreq); } static void linger_unregister(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; verify_osdc_wrlocked(osdc); erase_linger_osdc(&osdc->linger_requests, lreq); linger_put(lreq); } static void cancel_linger_request(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; WARN_ON(!req->r_linger); cancel_request(req); linger_put(lreq); } struct linger_work { struct work_struct work; struct ceph_osd_linger_request *lreq; struct list_head pending_item; unsigned long queued_stamp; union { struct { u64 notify_id; u64 notifier_id; void *payload; /* points into @msg front */ size_t payload_len; struct ceph_msg *msg; /* for ceph_msg_put() */ } notify; struct { int err; } error; }; }; static struct linger_work *lwork_alloc(struct ceph_osd_linger_request *lreq, work_func_t workfn) { struct linger_work *lwork; lwork = kzalloc(sizeof(*lwork), GFP_NOIO); if (!lwork) return NULL; INIT_WORK(&lwork->work, workfn); INIT_LIST_HEAD(&lwork->pending_item); lwork->lreq = linger_get(lreq); return lwork; } static void lwork_free(struct linger_work *lwork) { struct ceph_osd_linger_request *lreq = lwork->lreq; mutex_lock(&lreq->lock); list_del(&lwork->pending_item); mutex_unlock(&lreq->lock); linger_put(lreq); kfree(lwork); } static void lwork_queue(struct linger_work *lwork) { struct ceph_osd_linger_request *lreq = lwork->lreq; struct ceph_osd_client *osdc = lreq->osdc; verify_lreq_locked(lreq); WARN_ON(!list_empty(&lwork->pending_item)); lwork->queued_stamp = jiffies; list_add_tail(&lwork->pending_item, &lreq->pending_lworks); queue_work(osdc->notify_wq, &lwork->work); } static void do_watch_notify(struct work_struct *w) { struct linger_work *lwork = container_of(w, struct linger_work, work); struct ceph_osd_linger_request *lreq = lwork->lreq; if (!linger_registered(lreq)) { dout("%s lreq %p not registered\n", __func__, lreq); goto out; } WARN_ON(!lreq->is_watch); dout("%s lreq %p notify_id %llu notifier_id %llu payload_len %zu\n", __func__, lreq, lwork->notify.notify_id, lwork->notify.notifier_id, lwork->notify.payload_len); lreq->wcb(lreq->data, lwork->notify.notify_id, lreq->linger_id, lwork->notify.notifier_id, lwork->notify.payload, lwork->notify.payload_len); out: ceph_msg_put(lwork->notify.msg); lwork_free(lwork); } static void do_watch_error(struct work_struct *w) { struct linger_work *lwork = container_of(w, struct linger_work, work); struct ceph_osd_linger_request *lreq = lwork->lreq; if (!linger_registered(lreq)) { dout("%s lreq %p not registered\n", __func__, lreq); goto out; } dout("%s lreq %p err %d\n", __func__, lreq, lwork->error.err); lreq->errcb(lreq->data, lreq->linger_id, lwork->error.err); out: lwork_free(lwork); } static void queue_watch_error(struct ceph_osd_linger_request *lreq) { struct linger_work *lwork; lwork = lwork_alloc(lreq, do_watch_error); if (!lwork) { pr_err("failed to allocate error-lwork\n"); return; } lwork->error.err = lreq->last_error; lwork_queue(lwork); } static void linger_reg_commit_complete(struct ceph_osd_linger_request *lreq, int result) { if (!completion_done(&lreq->reg_commit_wait)) { lreq->reg_commit_error = (result <= 0 ? result : 0); complete_all(&lreq->reg_commit_wait); } } static void linger_commit_cb(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); if (req != lreq->reg_req) { dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", __func__, lreq, lreq->linger_id, req, lreq->reg_req); goto out; } dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq, lreq->linger_id, req->r_result); linger_reg_commit_complete(lreq, req->r_result); lreq->committed = true; if (!lreq->is_watch) { struct ceph_osd_data *osd_data = osd_req_op_data(req, 0, notify, response_data); void *p = page_address(osd_data->pages[0]); WARN_ON(req->r_ops[0].op != CEPH_OSD_OP_NOTIFY || osd_data->type != CEPH_OSD_DATA_TYPE_PAGES); /* make note of the notify_id */ if (req->r_ops[0].outdata_len >= sizeof(u64)) { lreq->notify_id = ceph_decode_64(&p); dout("lreq %p notify_id %llu\n", lreq, lreq->notify_id); } else { dout("lreq %p no notify_id\n", lreq); } } out: mutex_unlock(&lreq->lock); linger_put(lreq); } static int normalize_watch_error(int err) { /* * Translate ENOENT -> ENOTCONN so that a delete->disconnection * notification and a failure to reconnect because we raced with * the delete appear the same to the user. */ if (err == -ENOENT) err = -ENOTCONN; return err; } static void linger_reconnect_cb(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); if (req != lreq->reg_req) { dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", __func__, lreq, lreq->linger_id, req, lreq->reg_req); goto out; } dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->last_error); if (req->r_result < 0) { if (!lreq->last_error) { lreq->last_error = normalize_watch_error(req->r_result); queue_watch_error(lreq); } } out: mutex_unlock(&lreq->lock); linger_put(lreq); } static void send_linger(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_request *req; int ret; verify_osdc_wrlocked(osdc); mutex_lock(&lreq->lock); dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); if (lreq->reg_req) { if (lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); ceph_osdc_put_request(lreq->reg_req); } req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); BUG_ON(!req); target_copy(&req->r_t, &lreq->t); req->r_mtime = lreq->mtime; if (lreq->is_watch && lreq->committed) { osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT, lreq->linger_id, ++lreq->register_gen); dout("lreq %p reconnect register_gen %u\n", lreq, req->r_ops[0].watch.gen); req->r_callback = linger_reconnect_cb; } else { if (lreq->is_watch) { osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH, lreq->linger_id, 0); } else { lreq->notify_id = 0; refcount_inc(&lreq->request_pl->refcnt); osd_req_op_notify_init(req, 0, lreq->linger_id, lreq->request_pl); ceph_osd_data_pages_init( osd_req_op_data(req, 0, notify, response_data), lreq->notify_id_pages, PAGE_SIZE, 0, false, false); } dout("lreq %p register\n", lreq); req->r_callback = linger_commit_cb; } ret = ceph_osdc_alloc_messages(req, GFP_NOIO); BUG_ON(ret); req->r_priv = linger_get(lreq); req->r_linger = true; lreq->reg_req = req; mutex_unlock(&lreq->lock); submit_request(req, true); } static void linger_ping_cb(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); if (req != lreq->ping_req) { dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", __func__, lreq, lreq->linger_id, req, lreq->ping_req); goto out; } dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent, lreq->last_error); if (lreq->register_gen == req->r_ops[0].watch.gen) { if (!req->r_result) { lreq->watch_valid_thru = lreq->ping_sent; } else if (!lreq->last_error) { lreq->last_error = normalize_watch_error(req->r_result); queue_watch_error(lreq); } } else { dout("lreq %p register_gen %u ignoring old pong %u\n", lreq, lreq->register_gen, req->r_ops[0].watch.gen); } out: mutex_unlock(&lreq->lock); linger_put(lreq); } static void send_linger_ping(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_request *req; int ret; if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("%s PAUSERD\n", __func__); return; } lreq->ping_sent = jiffies; dout("%s lreq %p linger_id %llu ping_sent %lu register_gen %u\n", __func__, lreq, lreq->linger_id, lreq->ping_sent, lreq->register_gen); if (lreq->ping_req) { if (lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); ceph_osdc_put_request(lreq->ping_req); } req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); BUG_ON(!req); target_copy(&req->r_t, &lreq->t); osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id, lreq->register_gen); req->r_callback = linger_ping_cb; ret = ceph_osdc_alloc_messages(req, GFP_NOIO); BUG_ON(ret); req->r_priv = linger_get(lreq); req->r_linger = true; lreq->ping_req = req; ceph_osdc_get_request(req); account_request(req); req->r_tid = atomic64_inc_return(&osdc->last_tid); link_request(lreq->osd, req); send_request(req); } static void linger_submit(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd *osd; down_write(&osdc->lock); linger_register(lreq); calc_target(osdc, &lreq->t, false); osd = lookup_create_osd(osdc, lreq->t.osd, true); link_linger(osd, lreq); send_linger(lreq); up_write(&osdc->lock); } static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_linger_request *lookup_lreq; verify_osdc_wrlocked(osdc); lookup_lreq = lookup_linger_mc(&osdc->linger_map_checks, lreq->linger_id); if (!lookup_lreq) return; WARN_ON(lookup_lreq != lreq); erase_linger_mc(&osdc->linger_map_checks, lreq); linger_put(lreq); } /* * @lreq has to be both registered and linked. */ static void __linger_cancel(struct ceph_osd_linger_request *lreq) { if (lreq->ping_req && lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); if (lreq->reg_req && lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); cancel_linger_map_check(lreq); unlink_linger(lreq->osd, lreq); linger_unregister(lreq); } static void linger_cancel(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; down_write(&osdc->lock); if (__linger_registered(lreq)) __linger_cancel(lreq); up_write(&osdc->lock); } static void send_linger_map_check(struct ceph_osd_linger_request *lreq); static void check_linger_pool_dne(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osdmap *map = osdc->osdmap; verify_osdc_wrlocked(osdc); WARN_ON(!map->epoch); if (lreq->register_gen) { lreq->map_dne_bound = map->epoch; dout("%s lreq %p linger_id %llu pool disappeared\n", __func__, lreq, lreq->linger_id); } else { dout("%s lreq %p linger_id %llu map_dne_bound %u have %u\n", __func__, lreq, lreq->linger_id, lreq->map_dne_bound, map->epoch); } if (lreq->map_dne_bound) { if (map->epoch >= lreq->map_dne_bound) { /* we had a new enough map */ pr_info("linger_id %llu pool does not exist\n", lreq->linger_id); linger_reg_commit_complete(lreq, -ENOENT); __linger_cancel(lreq); } } else { send_linger_map_check(lreq); } } static void linger_map_check_cb(struct ceph_mon_generic_request *greq) { struct ceph_osd_client *osdc = &greq->monc->client->osdc; struct ceph_osd_linger_request *lreq; u64 linger_id = greq->private_data; WARN_ON(greq->result || !greq->u.newest); down_write(&osdc->lock); lreq = lookup_linger_mc(&osdc->linger_map_checks, linger_id); if (!lreq) { dout("%s linger_id %llu dne\n", __func__, linger_id); goto out_unlock; } dout("%s lreq %p linger_id %llu map_dne_bound %u newest %llu\n", __func__, lreq, lreq->linger_id, lreq->map_dne_bound, greq->u.newest); if (!lreq->map_dne_bound) lreq->map_dne_bound = greq->u.newest; erase_linger_mc(&osdc->linger_map_checks, lreq); check_linger_pool_dne(lreq); linger_put(lreq); out_unlock: up_write(&osdc->lock); } static void send_linger_map_check(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_linger_request *lookup_lreq; int ret; verify_osdc_wrlocked(osdc); lookup_lreq = lookup_linger_mc(&osdc->linger_map_checks, lreq->linger_id); if (lookup_lreq) { WARN_ON(lookup_lreq != lreq); return; } linger_get(lreq); insert_linger_mc(&osdc->linger_map_checks, lreq); ret = ceph_monc_get_version_async(&osdc->client->monc, "osdmap", linger_map_check_cb, lreq->linger_id); WARN_ON(ret); } static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq) { int ret; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); ret = wait_for_completion_killable(&lreq->reg_commit_wait); return ret ?: lreq->reg_commit_error; } static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq, unsigned long timeout) { long left; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait, ceph_timeout_jiffies(timeout)); if (left <= 0) left = left ?: -ETIMEDOUT; else left = lreq->notify_finish_error; /* completed */ return left; } /* * Timeout callback, called every N seconds. When 1 or more OSD * requests has been active for more than N seconds, we send a keepalive * (tag + timestamp) to its OSD to ensure any communications channel * reset is detected. */ static void handle_timeout(struct work_struct *work) { struct ceph_osd_client *osdc = container_of(work, struct ceph_osd_client, timeout_work.work); struct ceph_options *opts = osdc->client->options; unsigned long cutoff = jiffies - opts->osd_keepalive_timeout; unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout; LIST_HEAD(slow_osds); struct rb_node *n, *p; dout("%s osdc %p\n", __func__, osdc); down_write(&osdc->lock); /* * ping osds that are a bit slow. this ensures that if there * is a break in the TCP connection we will notice, and reopen * a connection with that osd (from the fault callback). */ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); bool found = false; for (p = rb_first(&osd->o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); /* abort_request() */ if (time_before(req->r_stamp, cutoff)) { dout(" req %p tid %llu on osd%d is laggy\n", req, req->r_tid, osd->o_osd); found = true; } if (opts->osd_request_timeout && time_before(req->r_start_stamp, expiry_cutoff)) { pr_err_ratelimited("tid %llu on osd%d timeout\n", req->r_tid, osd->o_osd); abort_request(req, -ETIMEDOUT); } } for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) { struct ceph_osd_linger_request *lreq = rb_entry(p, struct ceph_osd_linger_request, node); dout(" lreq %p linger_id %llu is served by osd%d\n", lreq, lreq->linger_id, osd->o_osd); found = true; mutex_lock(&lreq->lock); if (lreq->is_watch && lreq->committed && !lreq->last_error) send_linger_ping(lreq); mutex_unlock(&lreq->lock); } if (found) list_move_tail(&osd->o_keepalive_item, &slow_osds); } if (opts->osd_request_timeout) { for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); /* abort_request() */ if (time_before(req->r_start_stamp, expiry_cutoff)) { pr_err_ratelimited("tid %llu on osd%d timeout\n", req->r_tid, osdc->homeless_osd.o_osd); abort_request(req, -ETIMEDOUT); } } } if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds)) maybe_request_map(osdc); while (!list_empty(&slow_osds)) { struct ceph_osd *osd = list_first_entry(&slow_osds, struct ceph_osd, o_keepalive_item); list_del_init(&osd->o_keepalive_item); ceph_con_keepalive(&osd->o_con); } up_write(&osdc->lock); schedule_delayed_work(&osdc->timeout_work, osdc->client->options->osd_keepalive_timeout); } static void handle_osds_timeout(struct work_struct *work) { struct ceph_osd_client *osdc = container_of(work, struct ceph_osd_client, osds_timeout_work.work); unsigned long delay = osdc->client->options->osd_idle_ttl / 4; struct ceph_osd *osd, *nosd; dout("%s osdc %p\n", __func__, osdc); down_write(&osdc->lock); list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) { if (time_before(jiffies, osd->lru_ttl)) break; WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests)); close_osd(osd); } up_write(&osdc->lock); schedule_delayed_work(&osdc->osds_timeout_work, round_jiffies_relative(delay)); } static int ceph_oloc_decode(void **p, void *end, struct ceph_object_locator *oloc) { u8 struct_v, struct_cv; u32 len; void *struct_end; int ret = 0; ceph_decode_need(p, end, 1 + 1 + 4, e_inval); struct_v = ceph_decode_8(p); struct_cv = ceph_decode_8(p); if (struct_v < 3) { pr_warn("got v %d < 3 cv %d of ceph_object_locator\n", struct_v, struct_cv); goto e_inval; } if (struct_cv > 6) { pr_warn("got v %d cv %d > 6 of ceph_object_locator\n", struct_v, struct_cv); goto e_inval; } len = ceph_decode_32(p); ceph_decode_need(p, end, len, e_inval); struct_end = *p + len; oloc->pool = ceph_decode_64(p); *p += 4; /* skip preferred */ len = ceph_decode_32(p); if (len > 0) { pr_warn("ceph_object_locator::key is set\n"); goto e_inval; } if (struct_v >= 5) { bool changed = false; len = ceph_decode_32(p); if (len > 0) { ceph_decode_need(p, end, len, e_inval); if (!oloc->pool_ns || ceph_compare_string(oloc->pool_ns, *p, len)) changed = true; *p += len; } else { if (oloc->pool_ns) changed = true; } if (changed) { /* redirect changes namespace */ pr_warn("ceph_object_locator::nspace is changed\n"); goto e_inval; } } if (struct_v >= 6) { s64 hash = ceph_decode_64(p); if (hash != -1) { pr_warn("ceph_object_locator::hash is set\n"); goto e_inval; } } /* skip the rest */ *p = struct_end; out: return ret; e_inval: ret = -EINVAL; goto out; } static int ceph_redirect_decode(void **p, void *end, struct ceph_request_redirect *redir) { u8 struct_v, struct_cv; u32 len; void *struct_end; int ret; ceph_decode_need(p, end, 1 + 1 + 4, e_inval); struct_v = ceph_decode_8(p); struct_cv = ceph_decode_8(p); if (struct_cv > 1) { pr_warn("got v %d cv %d > 1 of ceph_request_redirect\n", struct_v, struct_cv); goto e_inval; } len = ceph_decode_32(p); ceph_decode_need(p, end, len, e_inval); struct_end = *p + len; ret = ceph_oloc_decode(p, end, &redir->oloc); if (ret) goto out; len = ceph_decode_32(p); if (len > 0) { pr_warn("ceph_request_redirect::object_name is set\n"); goto e_inval; } /* skip the rest */ *p = struct_end; out: return ret; e_inval: ret = -EINVAL; goto out; } struct MOSDOpReply { struct ceph_pg pgid; u64 flags; int result; u32 epoch; int num_ops; u32 outdata_len[CEPH_OSD_MAX_OPS]; s32 rval[CEPH_OSD_MAX_OPS]; int retry_attempt; struct ceph_eversion replay_version; u64 user_version; struct ceph_request_redirect redirect; }; static int decode_MOSDOpReply(const struct ceph_msg *msg, struct MOSDOpReply *m) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; u16 version = le16_to_cpu(msg->hdr.version); struct ceph_eversion bad_replay_version; u8 decode_redir; u32 len; int ret; int i; ceph_decode_32_safe(&p, end, len, e_inval); ceph_decode_need(&p, end, len, e_inval); p += len; /* skip oid */ ret = ceph_decode_pgid(&p, end, &m->pgid); if (ret) return ret; ceph_decode_64_safe(&p, end, m->flags, e_inval); ceph_decode_32_safe(&p, end, m->result, e_inval); ceph_decode_need(&p, end, sizeof(bad_replay_version), e_inval); memcpy(&bad_replay_version, p, sizeof(bad_replay_version)); p += sizeof(bad_replay_version); ceph_decode_32_safe(&p, end, m->epoch, e_inval); ceph_decode_32_safe(&p, end, m->num_ops, e_inval); if (m->num_ops > ARRAY_SIZE(m->outdata_len)) goto e_inval; ceph_decode_need(&p, end, m->num_ops * sizeof(struct ceph_osd_op), e_inval); for (i = 0; i < m->num_ops; i++) { struct ceph_osd_op *op = p; m->outdata_len[i] = le32_to_cpu(op->payload_len); p += sizeof(*op); } ceph_decode_32_safe(&p, end, m->retry_attempt, e_inval); for (i = 0; i < m->num_ops; i++) ceph_decode_32_safe(&p, end, m->rval[i], e_inval); if (version >= 5) { ceph_decode_need(&p, end, sizeof(m->replay_version), e_inval); memcpy(&m->replay_version, p, sizeof(m->replay_version)); p += sizeof(m->replay_version); ceph_decode_64_safe(&p, end, m->user_version, e_inval); } else { m->replay_version = bad_replay_version; /* struct */ m->user_version = le64_to_cpu(m->replay_version.version); } if (version >= 6) { if (version >= 7) ceph_decode_8_safe(&p, end, decode_redir, e_inval); else decode_redir = 1; } else { decode_redir = 0; } if (decode_redir) { ret = ceph_redirect_decode(&p, end, &m->redirect); if (ret) return ret; } else { ceph_oloc_init(&m->redirect.oloc); } return 0; e_inval: return -EINVAL; } /* * Handle MOSDOpReply. Set ->r_result and call the callback if it is * specified. */ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg) { struct ceph_osd_client *osdc = osd->o_osdc; struct ceph_osd_request *req; struct MOSDOpReply m; u64 tid = le64_to_cpu(msg->hdr.tid); u32 data_len = 0; int ret; int i; dout("%s msg %p tid %llu\n", __func__, msg, tid); down_read(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown\n", __func__, osd->o_osd); goto out_unlock_osdc; } WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num)); mutex_lock(&osd->lock); req = lookup_request(&osd->o_requests, tid); if (!req) { dout("%s osd%d tid %llu unknown\n", __func__, osd->o_osd, tid); goto out_unlock_session; } m.redirect.oloc.pool_ns = req->r_t.target_oloc.pool_ns; ret = decode_MOSDOpReply(msg, &m); m.redirect.oloc.pool_ns = NULL; if (ret) { pr_err("failed to decode MOSDOpReply for tid %llu: %d\n", req->r_tid, ret); ceph_msg_dump(msg); goto fail_request; } dout("%s req %p tid %llu flags 0x%llx pgid %llu.%x epoch %u attempt %d v %u'%llu uv %llu\n", __func__, req, req->r_tid, m.flags, m.pgid.pool, m.pgid.seed, m.epoch, m.retry_attempt, le32_to_cpu(m.replay_version.epoch), le64_to_cpu(m.replay_version.version), m.user_version); if (m.retry_attempt >= 0) { if (m.retry_attempt != req->r_attempts - 1) { dout("req %p tid %llu retry_attempt %d != %d, ignoring\n", req, req->r_tid, m.retry_attempt, req->r_attempts - 1); goto out_unlock_session; } } else { WARN_ON(1); /* MOSDOpReply v4 is assumed */ } if (!ceph_oloc_empty(&m.redirect.oloc)) { dout("req %p tid %llu redirect pool %lld\n", req, req->r_tid, m.redirect.oloc.pool); unlink_request(osd, req); mutex_unlock(&osd->lock); /* * Not ceph_oloc_copy() - changing pool_ns is not * supported. */ req->r_t.target_oloc.pool = m.redirect.oloc.pool; req->r_flags |= CEPH_OSD_FLAG_REDIRECTED | CEPH_OSD_FLAG_IGNORE_OVERLAY | CEPH_OSD_FLAG_IGNORE_CACHE; req->r_tid = 0; __submit_request(req, false); goto out_unlock_osdc; } if (m.result == -EAGAIN) { dout("req %p tid %llu EAGAIN\n", req, req->r_tid); unlink_request(osd, req); mutex_unlock(&osd->lock); /* * The object is missing on the replica or not (yet) * readable. Clear pgid to force a resend to the primary * via legacy_change. */ req->r_t.pgid.pool = 0; req->r_t.pgid.seed = 0; WARN_ON(!req->r_t.used_replica); req->r_flags &= ~(CEPH_OSD_FLAG_BALANCE_READS | CEPH_OSD_FLAG_LOCALIZE_READS); req->r_tid = 0; __submit_request(req, false); goto out_unlock_osdc; } if (m.num_ops != req->r_num_ops) { pr_err("num_ops %d != %d for tid %llu\n", m.num_ops, req->r_num_ops, req->r_tid); goto fail_request; } for (i = 0; i < req->r_num_ops; i++) { dout(" req %p tid %llu op %d rval %d len %u\n", req, req->r_tid, i, m.rval[i], m.outdata_len[i]); req->r_ops[i].rval = m.rval[i]; req->r_ops[i].outdata_len = m.outdata_len[i]; data_len += m.outdata_len[i]; } if (data_len != le32_to_cpu(msg->hdr.data_len)) { pr_err("sum of lens %u != %u for tid %llu\n", data_len, le32_to_cpu(msg->hdr.data_len), req->r_tid); goto fail_request; } dout("%s req %p tid %llu result %d data_len %u\n", __func__, req, req->r_tid, m.result, data_len); /* * Since we only ever request ONDISK, we should only ever get * one (type of) reply back. */ WARN_ON(!(m.flags & CEPH_OSD_FLAG_ONDISK)); req->r_version = m.user_version; req->r_result = m.result ?: data_len; finish_request(req); mutex_unlock(&osd->lock); up_read(&osdc->lock); __complete_request(req); return; fail_request: complete_request(req, -EIO); out_unlock_session: mutex_unlock(&osd->lock); out_unlock_osdc: up_read(&osdc->lock); } static void set_pool_was_full(struct ceph_osd_client *osdc) { struct rb_node *n; for (n = rb_first(&osdc->osdmap->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = rb_entry(n, struct ceph_pg_pool_info, node); pi->was_full = __pool_full(pi); } } static bool pool_cleared_full(struct ceph_osd_client *osdc, s64 pool_id) { struct ceph_pg_pool_info *pi; pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id); if (!pi) return false; return pi->was_full && !__pool_full(pi); } static enum calc_target_result recalc_linger_target(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; enum calc_target_result ct_res; ct_res = calc_target(osdc, &lreq->t, true); if (ct_res == CALC_TARGET_NEED_RESEND) { struct ceph_osd *osd; osd = lookup_create_osd(osdc, lreq->t.osd, true); if (osd != lreq->osd) { unlink_linger(lreq->osd, lreq); link_linger(osd, lreq); } } return ct_res; } /* * Requeue requests whose mapping to an OSD has changed. */ static void scan_requests(struct ceph_osd *osd, bool force_resend, bool cleared_full, bool check_pool_cleared_full, struct rb_root *need_resend, struct list_head *need_resend_linger) { struct ceph_osd_client *osdc = osd->o_osdc; struct rb_node *n; bool force_resend_writes; for (n = rb_first(&osd->o_linger_requests); n; ) { struct ceph_osd_linger_request *lreq = rb_entry(n, struct ceph_osd_linger_request, node); enum calc_target_result ct_res; n = rb_next(n); /* recalc_linger_target() */ dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); ct_res = recalc_linger_target(lreq); switch (ct_res) { case CALC_TARGET_NO_ACTION: force_resend_writes = cleared_full || (check_pool_cleared_full && pool_cleared_full(osdc, lreq->t.base_oloc.pool)); if (!force_resend && !force_resend_writes) break; fallthrough; case CALC_TARGET_NEED_RESEND: cancel_linger_map_check(lreq); /* * scan_requests() for the previous epoch(s) * may have already added it to the list, since * it's not unlinked here. */ if (list_empty(&lreq->scan_item)) list_add_tail(&lreq->scan_item, need_resend_linger); break; case CALC_TARGET_POOL_DNE: list_del_init(&lreq->scan_item); check_linger_pool_dne(lreq); break; } } for (n = rb_first(&osd->o_requests); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); enum calc_target_result ct_res; n = rb_next(n); /* unlink_request(), check_pool_dne() */ dout("%s req %p tid %llu\n", __func__, req, req->r_tid); ct_res = calc_target(osdc, &req->r_t, false); switch (ct_res) { case CALC_TARGET_NO_ACTION: force_resend_writes = cleared_full || (check_pool_cleared_full && pool_cleared_full(osdc, req->r_t.base_oloc.pool)); if (!force_resend && (!(req->r_flags & CEPH_OSD_FLAG_WRITE) || !force_resend_writes)) break; fallthrough; case CALC_TARGET_NEED_RESEND: cancel_map_check(req); unlink_request(osd, req); insert_request(need_resend, req); break; case CALC_TARGET_POOL_DNE: check_pool_dne(req); break; } } } static int handle_one_map(struct ceph_osd_client *osdc, void *p, void *end, bool incremental, struct rb_root *need_resend, struct list_head *need_resend_linger) { struct ceph_osdmap *newmap; struct rb_node *n; bool skipped_map = false; bool was_full; was_full = ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL); set_pool_was_full(osdc); if (incremental) newmap = osdmap_apply_incremental(&p, end, ceph_msgr2(osdc->client), osdc->osdmap); else newmap = ceph_osdmap_decode(&p, end, ceph_msgr2(osdc->client)); if (IS_ERR(newmap)) return PTR_ERR(newmap); if (newmap != osdc->osdmap) { /* * Preserve ->was_full before destroying the old map. * For pools that weren't in the old map, ->was_full * should be false. */ for (n = rb_first(&newmap->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = rb_entry(n, struct ceph_pg_pool_info, node); struct ceph_pg_pool_info *old_pi; old_pi = ceph_pg_pool_by_id(osdc->osdmap, pi->id); if (old_pi) pi->was_full = old_pi->was_full; else WARN_ON(pi->was_full); } if (osdc->osdmap->epoch && osdc->osdmap->epoch + 1 < newmap->epoch) { WARN_ON(incremental); skipped_map = true; } ceph_osdmap_destroy(osdc->osdmap); osdc->osdmap = newmap; } was_full &= !ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL); scan_requests(&osdc->homeless_osd, skipped_map, was_full, true, need_resend, need_resend_linger); for (n = rb_first(&osdc->osds); n; ) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); n = rb_next(n); /* close_osd() */ scan_requests(osd, skipped_map, was_full, true, need_resend, need_resend_linger); if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) || memcmp(&osd->o_con.peer_addr, ceph_osd_addr(osdc->osdmap, osd->o_osd), sizeof(struct ceph_entity_addr))) close_osd(osd); } return 0; } static void kick_requests(struct ceph_osd_client *osdc, struct rb_root *need_resend, struct list_head *need_resend_linger) { struct ceph_osd_linger_request *lreq, *nlreq; enum calc_target_result ct_res; struct rb_node *n; /* make sure need_resend targets reflect latest map */ for (n = rb_first(need_resend); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); n = rb_next(n); if (req->r_t.epoch < osdc->osdmap->epoch) { ct_res = calc_target(osdc, &req->r_t, false); if (ct_res == CALC_TARGET_POOL_DNE) { erase_request(need_resend, req); check_pool_dne(req); } } } for (n = rb_first(need_resend); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); struct ceph_osd *osd; n = rb_next(n); erase_request(need_resend, req); /* before link_request() */ osd = lookup_create_osd(osdc, req->r_t.osd, true); link_request(osd, req); if (!req->r_linger) { if (!osd_homeless(osd) && !req->r_t.paused) send_request(req); } else { cancel_linger_request(req); } } list_for_each_entry_safe(lreq, nlreq, need_resend_linger, scan_item) { if (!osd_homeless(lreq->osd)) send_linger(lreq); list_del_init(&lreq->scan_item); } } /* * Process updated osd map. * * The message contains any number of incremental and full maps, normally * indicating some sort of topology change in the cluster. Kick requests * off to different OSDs as needed. */ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; u32 nr_maps, maplen; u32 epoch; struct ceph_fsid fsid; struct rb_root need_resend = RB_ROOT; LIST_HEAD(need_resend_linger); bool handled_incremental = false; bool was_pauserd, was_pausewr; bool pauserd, pausewr; int err; dout("%s have %u\n", __func__, osdc->osdmap->epoch); down_write(&osdc->lock); /* verify fsid */ ceph_decode_need(&p, end, sizeof(fsid), bad); ceph_decode_copy(&p, &fsid, sizeof(fsid)); if (ceph_check_fsid(osdc->client, &fsid) < 0) goto bad; was_pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD); was_pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc); /* incremental maps */ ceph_decode_32_safe(&p, end, nr_maps, bad); dout(" %d inc maps\n", nr_maps); while (nr_maps > 0) { ceph_decode_need(&p, end, 2*sizeof(u32), bad); epoch = ceph_decode_32(&p); maplen = ceph_decode_32(&p); ceph_decode_need(&p, end, maplen, bad); if (osdc->osdmap->epoch && osdc->osdmap->epoch + 1 == epoch) { dout("applying incremental map %u len %d\n", epoch, maplen); err = handle_one_map(osdc, p, p + maplen, true, &need_resend, &need_resend_linger); if (err) goto bad; handled_incremental = true; } else { dout("ignoring incremental map %u len %d\n", epoch, maplen); } p += maplen; nr_maps--; } if (handled_incremental) goto done; /* full maps */ ceph_decode_32_safe(&p, end, nr_maps, bad); dout(" %d full maps\n", nr_maps); while (nr_maps) { ceph_decode_need(&p, end, 2*sizeof(u32), bad); epoch = ceph_decode_32(&p); maplen = ceph_decode_32(&p); ceph_decode_need(&p, end, maplen, bad); if (nr_maps > 1) { dout("skipping non-latest full map %u len %d\n", epoch, maplen); } else if (osdc->osdmap->epoch >= epoch) { dout("skipping full map %u len %d, " "older than our %u\n", epoch, maplen, osdc->osdmap->epoch); } else { dout("taking full map %u len %d\n", epoch, maplen); err = handle_one_map(osdc, p, p + maplen, false, &need_resend, &need_resend_linger); if (err) goto bad; } p += maplen; nr_maps--; } done: /* * subscribe to subsequent osdmap updates if full to ensure * we find out when we are no longer full and stop returning * ENOSPC. */ pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD); pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc); if (was_pauserd || was_pausewr || pauserd || pausewr || osdc->osdmap->epoch < osdc->epoch_barrier) maybe_request_map(osdc); kick_requests(osdc, &need_resend, &need_resend_linger); ceph_osdc_abort_on_full(osdc); ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP, osdc->osdmap->epoch); up_write(&osdc->lock); wake_up_all(&osdc->client->auth_wq); return; bad: pr_err("osdc handle_map corrupt msg\n"); ceph_msg_dump(msg); up_write(&osdc->lock); } /* * Resubmit requests pending on the given osd. */ static void kick_osd_requests(struct ceph_osd *osd) { struct rb_node *n; clear_backoffs(osd); for (n = rb_first(&osd->o_requests); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); n = rb_next(n); /* cancel_linger_request() */ if (!req->r_linger) { if (!req->r_t.paused) send_request(req); } else { cancel_linger_request(req); } } for (n = rb_first(&osd->o_linger_requests); n; n = rb_next(n)) { struct ceph_osd_linger_request *lreq = rb_entry(n, struct ceph_osd_linger_request, node); send_linger(lreq); } } /* * If the osd connection drops, we need to resubmit all requests. */ static void osd_fault(struct ceph_connection *con) { struct ceph_osd *osd = con->private; struct ceph_osd_client *osdc = osd->o_osdc; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); down_write(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown\n", __func__, osd->o_osd); goto out_unlock; } if (!reopen_osd(osd)) kick_osd_requests(osd); maybe_request_map(osdc); out_unlock: up_write(&osdc->lock); } struct MOSDBackoff { struct ceph_spg spgid; u32 map_epoch; u8 op; u64 id; struct ceph_hobject_id *begin; struct ceph_hobject_id *end; }; static int decode_MOSDBackoff(const struct ceph_msg *msg, struct MOSDBackoff *m) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; u8 struct_v; u32 struct_len; int ret; ret = ceph_start_decoding(&p, end, 1, "spg_t", &struct_v, &struct_len); if (ret) return ret; ret = ceph_decode_pgid(&p, end, &m->spgid.pgid); if (ret) return ret; ceph_decode_8_safe(&p, end, m->spgid.shard, e_inval); ceph_decode_32_safe(&p, end, m->map_epoch, e_inval); ceph_decode_8_safe(&p, end, m->op, e_inval); ceph_decode_64_safe(&p, end, m->id, e_inval); m->begin = kzalloc(sizeof(*m->begin), GFP_NOIO); if (!m->begin) return -ENOMEM; ret = decode_hoid(&p, end, m->begin); if (ret) { free_hoid(m->begin); return ret; } m->end = kzalloc(sizeof(*m->end), GFP_NOIO); if (!m->end) { free_hoid(m->begin); return -ENOMEM; } ret = decode_hoid(&p, end, m->end); if (ret) { free_hoid(m->begin); free_hoid(m->end); return ret; } return 0; e_inval: return -EINVAL; } static struct ceph_msg *create_backoff_message( const struct ceph_osd_backoff *backoff, u32 map_epoch) { struct ceph_msg *msg; void *p, *end; int msg_size; msg_size = CEPH_ENCODING_START_BLK_LEN + CEPH_PGID_ENCODING_LEN + 1; /* spgid */ msg_size += 4 + 1 + 8; /* map_epoch, op, id */ msg_size += CEPH_ENCODING_START_BLK_LEN + hoid_encoding_size(backoff->begin); msg_size += CEPH_ENCODING_START_BLK_LEN + hoid_encoding_size(backoff->end); msg = ceph_msg_new(CEPH_MSG_OSD_BACKOFF, msg_size, GFP_NOIO, true); if (!msg) return NULL; p = msg->front.iov_base; end = p + msg->front_alloc_len; encode_spgid(&p, &backoff->spgid); ceph_encode_32(&p, map_epoch); ceph_encode_8(&p, CEPH_OSD_BACKOFF_OP_ACK_BLOCK); ceph_encode_64(&p, backoff->id); encode_hoid(&p, end, backoff->begin); encode_hoid(&p, end, backoff->end); BUG_ON(p != end); msg->front.iov_len = p - msg->front.iov_base; msg->hdr.version = cpu_to_le16(1); /* MOSDBackoff v1 */ msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); return msg; } static void handle_backoff_block(struct ceph_osd *osd, struct MOSDBackoff *m) { struct ceph_spg_mapping *spg; struct ceph_osd_backoff *backoff; struct ceph_msg *msg; dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); spg = lookup_spg_mapping(&osd->o_backoff_mappings, &m->spgid); if (!spg) { spg = alloc_spg_mapping(); if (!spg) { pr_err("%s failed to allocate spg\n", __func__); return; } spg->spgid = m->spgid; /* struct */ insert_spg_mapping(&osd->o_backoff_mappings, spg); } backoff = alloc_backoff(); if (!backoff) { pr_err("%s failed to allocate backoff\n", __func__); return; } backoff->spgid = m->spgid; /* struct */ backoff->id = m->id; backoff->begin = m->begin; m->begin = NULL; /* backoff now owns this */ backoff->end = m->end; m->end = NULL; /* ditto */ insert_backoff(&spg->backoffs, backoff); insert_backoff_by_id(&osd->o_backoffs_by_id, backoff); /* * Ack with original backoff's epoch so that the OSD can * discard this if there was a PG split. */ msg = create_backoff_message(backoff, m->map_epoch); if (!msg) { pr_err("%s failed to allocate msg\n", __func__); return; } ceph_con_send(&osd->o_con, msg); } static bool target_contained_by(const struct ceph_osd_request_target *t, const struct ceph_hobject_id *begin, const struct ceph_hobject_id *end) { struct ceph_hobject_id hoid; int cmp; hoid_fill_from_target(&hoid, t); cmp = hoid_compare(&hoid, begin); return !cmp || (cmp > 0 && hoid_compare(&hoid, end) < 0); } static void handle_backoff_unblock(struct ceph_osd *osd, const struct MOSDBackoff *m) { struct ceph_spg_mapping *spg; struct ceph_osd_backoff *backoff; struct rb_node *n; dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); backoff = lookup_backoff_by_id(&osd->o_backoffs_by_id, m->id); if (!backoff) { pr_err("%s osd%d spgid %llu.%xs%d id %llu backoff dne\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); return; } if (hoid_compare(backoff->begin, m->begin) && hoid_compare(backoff->end, m->end)) { pr_err("%s osd%d spgid %llu.%xs%d id %llu bad range?\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); /* unblock it anyway... */ } spg = lookup_spg_mapping(&osd->o_backoff_mappings, &backoff->spgid); BUG_ON(!spg); erase_backoff(&spg->backoffs, backoff); erase_backoff_by_id(&osd->o_backoffs_by_id, backoff); free_backoff(backoff); if (RB_EMPTY_ROOT(&spg->backoffs)) { erase_spg_mapping(&osd->o_backoff_mappings, spg); free_spg_mapping(spg); } for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); if (!ceph_spg_compare(&req->r_t.spgid, &m->spgid)) { /* * Match against @m, not @backoff -- the PG may * have split on the OSD. */ if (target_contained_by(&req->r_t, m->begin, m->end)) { /* * If no other installed backoff applies, * resend. */ send_request(req); } } } } static void handle_backoff(struct ceph_osd *osd, struct ceph_msg *msg) { struct ceph_osd_client *osdc = osd->o_osdc; struct MOSDBackoff m; int ret; down_read(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown\n", __func__, osd->o_osd); up_read(&osdc->lock); return; } WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num)); mutex_lock(&osd->lock); ret = decode_MOSDBackoff(msg, &m); if (ret) { pr_err("failed to decode MOSDBackoff: %d\n", ret); ceph_msg_dump(msg); goto out_unlock; } switch (m.op) { case CEPH_OSD_BACKOFF_OP_BLOCK: handle_backoff_block(osd, &m); break; case CEPH_OSD_BACKOFF_OP_UNBLOCK: handle_backoff_unblock(osd, &m); break; default: pr_err("%s osd%d unknown op %d\n", __func__, osd->o_osd, m.op); } free_hoid(m.begin); free_hoid(m.end); out_unlock: mutex_unlock(&osd->lock); up_read(&osdc->lock); } /* * Process osd watch notifications */ static void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; struct ceph_osd_linger_request *lreq; struct linger_work *lwork; u8 proto_ver, opcode; u64 cookie, notify_id; u64 notifier_id = 0; s32 return_code = 0; void *payload = NULL; u32 payload_len = 0; ceph_decode_8_safe(&p, end, proto_ver, bad); ceph_decode_8_safe(&p, end, opcode, bad); ceph_decode_64_safe(&p, end, cookie, bad); p += 8; /* skip ver */ ceph_decode_64_safe(&p, end, notify_id, bad); if (proto_ver >= 1) { ceph_decode_32_safe(&p, end, payload_len, bad); ceph_decode_need(&p, end, payload_len, bad); payload = p; p += payload_len; } if (le16_to_cpu(msg->hdr.version) >= 2) ceph_decode_32_safe(&p, end, return_code, bad); if (le16_to_cpu(msg->hdr.version) >= 3) ceph_decode_64_safe(&p, end, notifier_id, bad); down_read(&osdc->lock); lreq = lookup_linger_osdc(&osdc->linger_requests, cookie); if (!lreq) { dout("%s opcode %d cookie %llu dne\n", __func__, opcode, cookie); goto out_unlock_osdc; } mutex_lock(&lreq->lock); dout("%s opcode %d cookie %llu lreq %p is_watch %d\n", __func__, opcode, cookie, lreq, lreq->is_watch); if (opcode == CEPH_WATCH_EVENT_DISCONNECT) { if (!lreq->last_error) { lreq->last_error = -ENOTCONN; queue_watch_error(lreq); } } else if (!lreq->is_watch) { /* CEPH_WATCH_EVENT_NOTIFY_COMPLETE */ if (lreq->notify_id && lreq->notify_id != notify_id) { dout("lreq %p notify_id %llu != %llu, ignoring\n", lreq, lreq->notify_id, notify_id); } else if (!completion_done(&lreq->notify_finish_wait)) { struct ceph_msg_data *data = msg->num_data_items ? &msg->data[0] : NULL; if (data) { if (lreq->preply_pages) { WARN_ON(data->type != CEPH_MSG_DATA_PAGES); *lreq->preply_pages = data->pages; *lreq->preply_len = data->length; data->own_pages = false; } } lreq->notify_finish_error = return_code; complete_all(&lreq->notify_finish_wait); } } else { /* CEPH_WATCH_EVENT_NOTIFY */ lwork = lwork_alloc(lreq, do_watch_notify); if (!lwork) { pr_err("failed to allocate notify-lwork\n"); goto out_unlock_lreq; } lwork->notify.notify_id = notify_id; lwork->notify.notifier_id = notifier_id; lwork->notify.payload = payload; lwork->notify.payload_len = payload_len; lwork->notify.msg = ceph_msg_get(msg); lwork_queue(lwork); } out_unlock_lreq: mutex_unlock(&lreq->lock); out_unlock_osdc: up_read(&osdc->lock); return; bad: pr_err("osdc handle_watch_notify corrupt msg\n"); } /* * Register request, send initial attempt. */ void ceph_osdc_start_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { down_read(&osdc->lock); submit_request(req, false); up_read(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_start_request); /* * Unregister request. If @req was registered, it isn't completed: * r_result isn't set and __complete_request() isn't invoked. * * If @req wasn't registered, this call may have raced with * handle_reply(), in which case r_result would already be set and * __complete_request() would be getting invoked, possibly even * concurrently with this call. */ void ceph_osdc_cancel_request(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; down_write(&osdc->lock); if (req->r_osd) cancel_request(req); up_write(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_cancel_request); /* * @timeout: in jiffies, 0 means "wait forever" */ static int wait_request_timeout(struct ceph_osd_request *req, unsigned long timeout) { long left; dout("%s req %p tid %llu\n", __func__, req, req->r_tid); left = wait_for_completion_killable_timeout(&req->r_completion, ceph_timeout_jiffies(timeout)); if (left <= 0) { left = left ?: -ETIMEDOUT; ceph_osdc_cancel_request(req); } else { left = req->r_result; /* completed */ } return left; } /* * wait for a request to complete */ int ceph_osdc_wait_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { return wait_request_timeout(req, 0); } EXPORT_SYMBOL(ceph_osdc_wait_request); /* * sync - wait for all in-flight requests to flush. avoid starvation. */ void ceph_osdc_sync(struct ceph_osd_client *osdc) { struct rb_node *n, *p; u64 last_tid = atomic64_read(&osdc->last_tid); again: down_read(&osdc->lock); for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); mutex_lock(&osd->lock); for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); if (req->r_tid > last_tid) break; if (!(req->r_flags & CEPH_OSD_FLAG_WRITE)) continue; ceph_osdc_get_request(req); mutex_unlock(&osd->lock); up_read(&osdc->lock); dout("%s waiting on req %p tid %llu last_tid %llu\n", __func__, req, req->r_tid, last_tid); wait_for_completion(&req->r_completion); ceph_osdc_put_request(req); goto again; } mutex_unlock(&osd->lock); } up_read(&osdc->lock); dout("%s done last_tid %llu\n", __func__, last_tid); } EXPORT_SYMBOL(ceph_osdc_sync); /* * Returns a handle, caller owns a ref. */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, rados_watchcb2_t wcb, rados_watcherrcb_t errcb, void *data) { struct ceph_osd_linger_request *lreq; int ret; lreq = linger_alloc(osdc); if (!lreq) return ERR_PTR(-ENOMEM); lreq->is_watch = true; lreq->wcb = wcb; lreq->errcb = errcb; lreq->data = data; lreq->watch_valid_thru = jiffies; ceph_oid_copy(&lreq->t.base_oid, oid); ceph_oloc_copy(&lreq->t.base_oloc, oloc); lreq->t.flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&lreq->mtime); linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (ret) { linger_cancel(lreq); goto err_put_lreq; } return lreq; err_put_lreq: linger_put(lreq); return ERR_PTR(ret); } EXPORT_SYMBOL(ceph_osdc_watch); /* * Releases a ref. * * Times out after mount_timeout to preserve rbd unmap behaviour * introduced in 2894e1d76974 ("rbd: timeout watch teardown on unmap * with mount_timeout"). */ int ceph_osdc_unwatch(struct ceph_osd_client *osdc, struct ceph_osd_linger_request *lreq) { struct ceph_options *opts = osdc->client->options; struct ceph_osd_request *req; int ret; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid); ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); req->r_flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&req->r_mtime); osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH, lreq->linger_id, 0); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); linger_cancel(lreq); linger_put(lreq); ret = wait_request_timeout(req, opts->mount_timeout); out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_unwatch); static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which, u64 notify_id, u64 cookie, void *payload, u32 payload_len) { struct ceph_osd_req_op *op; struct ceph_pagelist *pl; int ret; op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0); pl = ceph_pagelist_alloc(GFP_NOIO); if (!pl) return -ENOMEM; ret = ceph_pagelist_encode_64(pl, notify_id); ret |= ceph_pagelist_encode_64(pl, cookie); if (payload) { ret |= ceph_pagelist_encode_32(pl, payload_len); ret |= ceph_pagelist_append(pl, payload, payload_len); } else { ret |= ceph_pagelist_encode_32(pl, 0); } if (ret) { ceph_pagelist_release(pl); return -ENOMEM; } ceph_osd_data_pagelist_init(&op->notify_ack.request_data, pl); op->indata_len = pl->length; return 0; } int ceph_osdc_notify_ack(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, u64 notify_id, u64 cookie, void *payload, u32 payload_len) { struct ceph_osd_request *req; int ret; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, oid); ceph_oloc_copy(&req->r_base_oloc, oloc); req->r_flags = CEPH_OSD_FLAG_READ; ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload, payload_len); if (ret) goto out_put_req; ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_notify_ack); /* * @timeout: in seconds * * @preply_{pages,len} are initialized both on success and error. * The caller is responsible for: * * ceph_release_page_vector(reply_pages, calc_pages_for(0, reply_len)) */ int ceph_osdc_notify(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, void *payload, u32 payload_len, u32 timeout, struct page ***preply_pages, size_t *preply_len) { struct ceph_osd_linger_request *lreq; int ret; WARN_ON(!timeout); if (preply_pages) { *preply_pages = NULL; *preply_len = 0; } lreq = linger_alloc(osdc); if (!lreq) return -ENOMEM; lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO); if (!lreq->request_pl) { ret = -ENOMEM; goto out_put_lreq; } ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */ ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout); ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len); ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len); if (ret) { ret = -ENOMEM; goto out_put_lreq; } /* for notify_id */ lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO); if (IS_ERR(lreq->notify_id_pages)) { ret = PTR_ERR(lreq->notify_id_pages); lreq->notify_id_pages = NULL; goto out_put_lreq; } lreq->preply_pages = preply_pages; lreq->preply_len = preply_len; ceph_oid_copy(&lreq->t.base_oid, oid); ceph_oloc_copy(&lreq->t.base_oloc, oloc); lreq->t.flags = CEPH_OSD_FLAG_READ; linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (!ret) ret = linger_notify_finish_wait(lreq, msecs_to_jiffies(2 * timeout * MSEC_PER_SEC)); else dout("lreq %p failed to initiate notify %d\n", lreq, ret); linger_cancel(lreq); out_put_lreq: linger_put(lreq); return ret; } EXPORT_SYMBOL(ceph_osdc_notify); static int decode_watcher(void **p, void *end, struct ceph_watch_item *item) { u8 struct_v; u32 struct_len; int ret; ret = ceph_start_decoding(p, end, 2, "watch_item_t", &struct_v, &struct_len); if (ret) goto bad; ret = -EINVAL; ceph_decode_copy_safe(p, end, &item->name, sizeof(item->name), bad); ceph_decode_64_safe(p, end, item->cookie, bad); ceph_decode_skip_32(p, end, bad); /* skip timeout seconds */ if (struct_v >= 2) { ret = ceph_decode_entity_addr(p, end, &item->addr); if (ret) goto bad; } else { ret = 0; } dout("%s %s%llu cookie %llu addr %s\n", __func__, ENTITY_NAME(item->name), item->cookie, ceph_pr_addr(&item->addr)); bad: return ret; } static int decode_watchers(void **p, void *end, struct ceph_watch_item **watchers, u32 *num_watchers) { u8 struct_v; u32 struct_len; int i; int ret; ret = ceph_start_decoding(p, end, 1, "obj_list_watch_response_t", &struct_v, &struct_len); if (ret) return ret; *num_watchers = ceph_decode_32(p); *watchers = kcalloc(*num_watchers, sizeof(**watchers), GFP_NOIO); if (!*watchers) return -ENOMEM; for (i = 0; i < *num_watchers; i++) { ret = decode_watcher(p, end, *watchers + i); if (ret) { kfree(*watchers); return ret; } } return 0; } /* * On success, the caller is responsible for: * * kfree(watchers); */ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, struct ceph_watch_item **watchers, u32 *num_watchers) { struct ceph_osd_request *req; struct page **pages; int ret; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, oid); ceph_oloc_copy(&req->r_base_oloc, oloc); req->r_flags = CEPH_OSD_FLAG_READ; pages = ceph_alloc_page_vector(1, GFP_NOIO); if (IS_ERR(pages)) { ret = PTR_ERR(pages); goto out_put_req; } osd_req_op_init(req, 0, CEPH_OSD_OP_LIST_WATCHERS, 0); ceph_osd_data_pages_init(osd_req_op_data(req, 0, list_watchers, response_data), pages, PAGE_SIZE, 0, false, true); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); if (ret >= 0) { void *p = page_address(pages[0]); void *const end = p + req->r_ops[0].outdata_len; ret = decode_watchers(&p, end, watchers, num_watchers); } out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_list_watchers); /* * Call all pending notify callbacks - for use after a watch is * unregistered, to make sure no more callbacks for it will be invoked */ void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc) { dout("%s osdc %p\n", __func__, osdc); flush_workqueue(osdc->notify_wq); } EXPORT_SYMBOL(ceph_osdc_flush_notifies); void ceph_osdc_maybe_request_map(struct ceph_osd_client *osdc) { down_read(&osdc->lock); maybe_request_map(osdc); up_read(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_maybe_request_map); /* * Execute an OSD class method on an object. * * @flags: CEPH_OSD_FLAG_* * @resp_len: in/out param for reply length */ int ceph_osdc_call(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, const char *class, const char *method, unsigned int flags, struct page *req_page, size_t req_len, struct page **resp_pages, size_t *resp_len) { struct ceph_osd_request *req; int ret; if (req_len > PAGE_SIZE) return -E2BIG; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, oid); ceph_oloc_copy(&req->r_base_oloc, oloc); req->r_flags = flags; ret = osd_req_op_cls_init(req, 0, class, method); if (ret) goto out_put_req; if (req_page) osd_req_op_cls_request_data_pages(req, 0, &req_page, req_len, 0, false, false); if (resp_pages) osd_req_op_cls_response_data_pages(req, 0, resp_pages, *resp_len, 0, false, false); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); if (ret >= 0) { ret = req->r_ops[0].rval; if (resp_pages) *resp_len = req->r_ops[0].outdata_len; } out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_call); /* * reset all osd connections */ void ceph_osdc_reopen_osds(struct ceph_osd_client *osdc) { struct rb_node *n; down_write(&osdc->lock); for (n = rb_first(&osdc->osds); n; ) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); n = rb_next(n); if (!reopen_osd(osd)) kick_osd_requests(osd); } up_write(&osdc->lock); } /* * init, shutdown */ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) { int err; dout("init\n"); osdc->client = client; init_rwsem(&osdc->lock); osdc->osds = RB_ROOT; INIT_LIST_HEAD(&osdc->osd_lru); spin_lock_init(&osdc->osd_lru_lock); osd_init(&osdc->homeless_osd); osdc->homeless_osd.o_osdc = osdc; osdc->homeless_osd.o_osd = CEPH_HOMELESS_OSD; osdc->last_linger_id = CEPH_LINGER_ID_START; osdc->linger_requests = RB_ROOT; osdc->map_checks = RB_ROOT; osdc->linger_map_checks = RB_ROOT; INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout); INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout); err = -ENOMEM; osdc->osdmap = ceph_osdmap_alloc(); if (!osdc->osdmap) goto out; osdc->req_mempool = mempool_create_slab_pool(10, ceph_osd_request_cache); if (!osdc->req_mempool) goto out_map; err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP, PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op"); if (err < 0) goto out_mempool; err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY, PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op_reply"); if (err < 0) goto out_msgpool; err = -ENOMEM; osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify"); if (!osdc->notify_wq) goto out_msgpool_reply; osdc->completion_wq = create_singlethread_workqueue("ceph-completion"); if (!osdc->completion_wq) goto out_notify_wq; schedule_delayed_work(&osdc->timeout_work, osdc->client->options->osd_keepalive_timeout); schedule_delayed_work(&osdc->osds_timeout_work, round_jiffies_relative(osdc->client->options->osd_idle_ttl)); return 0; out_notify_wq: destroy_workqueue(osdc->notify_wq); out_msgpool_reply: ceph_msgpool_destroy(&osdc->msgpool_op_reply); out_msgpool: ceph_msgpool_destroy(&osdc->msgpool_op); out_mempool: mempool_destroy(osdc->req_mempool); out_map: ceph_osdmap_destroy(osdc->osdmap); out: return err; } void ceph_osdc_stop(struct ceph_osd_client *osdc) { destroy_workqueue(osdc->completion_wq); destroy_workqueue(osdc->notify_wq); cancel_delayed_work_sync(&osdc->timeout_work); cancel_delayed_work_sync(&osdc->osds_timeout_work); down_write(&osdc->lock); while (!RB_EMPTY_ROOT(&osdc->osds)) { struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds), struct ceph_osd, o_node); close_osd(osd); } up_write(&osdc->lock); WARN_ON(refcount_read(&osdc->homeless_osd.o_ref) != 1); osd_cleanup(&osdc->homeless_osd); WARN_ON(!list_empty(&osdc->osd_lru)); WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_requests)); WARN_ON(!RB_EMPTY_ROOT(&osdc->map_checks)); WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_map_checks)); WARN_ON(atomic_read(&osdc->num_requests)); WARN_ON(atomic_read(&osdc->num_homeless)); ceph_osdmap_destroy(osdc->osdmap); mempool_destroy(osdc->req_mempool); ceph_msgpool_destroy(&osdc->msgpool_op); ceph_msgpool_destroy(&osdc->msgpool_op_reply); } int osd_req_op_copy_from_init(struct ceph_osd_request *req, u64 src_snapid, u64 src_version, struct ceph_object_id *src_oid, struct ceph_object_locator *src_oloc, u32 src_fadvise_flags, u32 dst_fadvise_flags, u32 truncate_seq, u64 truncate_size, u8 copy_from_flags) { struct ceph_osd_req_op *op; struct page **pages; void *p, *end; pages = ceph_alloc_page_vector(1, GFP_KERNEL); if (IS_ERR(pages)) return PTR_ERR(pages); op = osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM2, dst_fadvise_flags); op->copy_from.snapid = src_snapid; op->copy_from.src_version = src_version; op->copy_from.flags = copy_from_flags; op->copy_from.src_fadvise_flags = src_fadvise_flags; p = page_address(pages[0]); end = p + PAGE_SIZE; ceph_encode_string(&p, end, src_oid->name, src_oid->name_len); encode_oloc(&p, end, src_oloc); ceph_encode_32(&p, truncate_seq); ceph_encode_64(&p, truncate_size); op->indata_len = PAGE_SIZE - (end - p); ceph_osd_data_pages_init(&op->copy_from.osd_data, pages, op->indata_len, 0, false, true); return 0; } EXPORT_SYMBOL(osd_req_op_copy_from_init); int __init ceph_osdc_setup(void) { size_t size = sizeof(struct ceph_osd_request) + CEPH_OSD_SLAB_OPS * sizeof(struct ceph_osd_req_op); BUG_ON(ceph_osd_request_cache); ceph_osd_request_cache = kmem_cache_create("ceph_osd_request", size, 0, 0, NULL); return ceph_osd_request_cache ? 0 : -ENOMEM; } void ceph_osdc_cleanup(void) { BUG_ON(!ceph_osd_request_cache); kmem_cache_destroy(ceph_osd_request_cache); ceph_osd_request_cache = NULL; } /* * handle incoming message */ static void osd_dispatch(struct ceph_connection *con, struct ceph_msg *msg) { struct ceph_osd *osd = con->private; struct ceph_osd_client *osdc = osd->o_osdc; int type = le16_to_cpu(msg->hdr.type); switch (type) { case CEPH_MSG_OSD_MAP: ceph_osdc_handle_map(osdc, msg); break; case CEPH_MSG_OSD_OPREPLY: handle_reply(osd, msg); break; case CEPH_MSG_OSD_BACKOFF: handle_backoff(osd, msg); break; case CEPH_MSG_WATCH_NOTIFY: handle_watch_notify(osdc, msg); break; default: pr_err("received unknown message type %d %s\n", type, ceph_msg_type_name(type)); } ceph_msg_put(msg); } /* How much sparse data was requested? */ static u64 sparse_data_requested(struct ceph_osd_request *req) { u64 len = 0; if (req->r_flags & CEPH_OSD_FLAG_READ) { int i; for (i = 0; i < req->r_num_ops; ++i) { struct ceph_osd_req_op *op = &req->r_ops[i]; if (op->op == CEPH_OSD_OP_SPARSE_READ) len += op->extent.length; } } return len; } /* * Lookup and return message for incoming reply. Don't try to do * anything about a larger than preallocated data portion of the * message at the moment - for now, just skip the message. */ static struct ceph_msg *get_reply(struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip) { struct ceph_osd *osd = con->private; struct ceph_osd_client *osdc = osd->o_osdc; struct ceph_msg *m = NULL; struct ceph_osd_request *req; int front_len = le32_to_cpu(hdr->front_len); int data_len = le32_to_cpu(hdr->data_len); u64 tid = le64_to_cpu(hdr->tid); u64 srlen; down_read(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown, skipping\n", __func__, osd->o_osd); *skip = 1; goto out_unlock_osdc; } WARN_ON(osd->o_osd != le64_to_cpu(hdr->src.num)); mutex_lock(&osd->lock); req = lookup_request(&osd->o_requests, tid); if (!req) { dout("%s osd%d tid %llu unknown, skipping\n", __func__, osd->o_osd, tid); *skip = 1; goto out_unlock_session; } ceph_msg_revoke_incoming(req->r_reply); if (front_len > req->r_reply->front_alloc_len) { pr_warn("%s osd%d tid %llu front %d > preallocated %d\n", __func__, osd->o_osd, req->r_tid, front_len, req->r_reply->front_alloc_len); m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS, false); if (!m) goto out_unlock_session; ceph_msg_put(req->r_reply); req->r_reply = m; } srlen = sparse_data_requested(req); if (!srlen && data_len > req->r_reply->data_length) { pr_warn("%s osd%d tid %llu data %d > preallocated %zu, skipping\n", __func__, osd->o_osd, req->r_tid, data_len, req->r_reply->data_length); m = NULL; *skip = 1; goto out_unlock_session; } m = ceph_msg_get(req->r_reply); m->sparse_read_total = srlen; dout("get_reply tid %lld %p\n", tid, m); out_unlock_session: mutex_unlock(&osd->lock); out_unlock_osdc: up_read(&osdc->lock); return m; } static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) { struct ceph_msg *m; int type = le16_to_cpu(hdr->type); u32 front_len = le32_to_cpu(hdr->front_len); u32 data_len = le32_to_cpu(hdr->data_len); m = ceph_msg_new2(type, front_len, 1, GFP_NOIO, false); if (!m) return NULL; if (data_len) { struct page **pages; pages = ceph_alloc_page_vector(calc_pages_for(0, data_len), GFP_NOIO); if (IS_ERR(pages)) { ceph_msg_put(m); return NULL; } ceph_msg_data_add_pages(m, pages, data_len, 0, true); } return m; } static struct ceph_msg *osd_alloc_msg(struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip) { struct ceph_osd *osd = con->private; int type = le16_to_cpu(hdr->type); *skip = 0; switch (type) { case CEPH_MSG_OSD_MAP: case CEPH_MSG_OSD_BACKOFF: case CEPH_MSG_WATCH_NOTIFY: return alloc_msg_with_page_vector(hdr); case CEPH_MSG_OSD_OPREPLY: return get_reply(con, hdr, skip); default: pr_warn("%s osd%d unknown msg type %d, skipping\n", __func__, osd->o_osd, type); *skip = 1; return NULL; } } /* * Wrappers to refcount containing ceph_osd struct */ static struct ceph_connection *osd_get_con(struct ceph_connection *con) { struct ceph_osd *osd = con->private; if (get_osd(osd)) return con; return NULL; } static void osd_put_con(struct ceph_connection *con) { struct ceph_osd *osd = con->private; put_osd(osd); } /* * authentication */ /* * Note: returned pointer is the address of a structure that's * managed separately. Caller must *not* attempt to free it. */ static struct ceph_auth_handshake * osd_get_authorizer(struct ceph_connection *con, int *proto, int force_new) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; int ret; ret = __ceph_auth_get_authorizer(ac, auth, CEPH_ENTITY_TYPE_OSD, force_new, proto, NULL, NULL); if (ret) return ERR_PTR(ret); return auth; } static int osd_add_authorizer_challenge(struct ceph_connection *con, void *challenge_buf, int challenge_buf_len) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; return ceph_auth_add_authorizer_challenge(ac, o->o_auth.authorizer, challenge_buf, challenge_buf_len); } static int osd_verify_authorizer_reply(struct ceph_connection *con) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_verify_authorizer_reply(ac, auth->authorizer, auth->authorizer_reply_buf, auth->authorizer_reply_buf_len, NULL, NULL, NULL, NULL); } static int osd_invalidate_authorizer(struct ceph_connection *con) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; ceph_auth_invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD); return ceph_monc_validate_auth(&osdc->client->monc); } static int osd_get_auth_request(struct ceph_connection *con, void *buf, int *buf_len, void **authorizer, int *authorizer_len) { struct ceph_osd *o = con->private; struct ceph_auth_client *ac = o->o_osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; int ret; ret = ceph_auth_get_authorizer(ac, auth, CEPH_ENTITY_TYPE_OSD, buf, buf_len); if (ret) return ret; *authorizer = auth->authorizer_buf; *authorizer_len = auth->authorizer_buf_len; return 0; } static int osd_handle_auth_reply_more(struct ceph_connection *con, void *reply, int reply_len, void *buf, int *buf_len, void **authorizer, int *authorizer_len) { struct ceph_osd *o = con->private; struct ceph_auth_client *ac = o->o_osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; int ret; ret = ceph_auth_handle_svc_reply_more(ac, auth, reply, reply_len, buf, buf_len); if (ret) return ret; *authorizer = auth->authorizer_buf; *authorizer_len = auth->authorizer_buf_len; return 0; } static int osd_handle_auth_done(struct ceph_connection *con, u64 global_id, void *reply, int reply_len, u8 *session_key, int *session_key_len, u8 *con_secret, int *con_secret_len) { struct ceph_osd *o = con->private; struct ceph_auth_client *ac = o->o_osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_handle_svc_reply_done(ac, auth, reply, reply_len, session_key, session_key_len, con_secret, con_secret_len); } static int osd_handle_auth_bad_method(struct ceph_connection *con, int used_proto, int result, const int *allowed_protos, int proto_cnt, const int *allowed_modes, int mode_cnt) { struct ceph_osd *o = con->private; struct ceph_mon_client *monc = &o->o_osdc->client->monc; int ret; if (ceph_auth_handle_bad_authorizer(monc->auth, CEPH_ENTITY_TYPE_OSD, used_proto, result, allowed_protos, proto_cnt, allowed_modes, mode_cnt)) { ret = ceph_monc_validate_auth(monc); if (ret) return ret; } return -EACCES; } static void osd_reencode_message(struct ceph_msg *msg) { int type = le16_to_cpu(msg->hdr.type); if (type == CEPH_MSG_OSD_OP) encode_request_finish(msg); } static int osd_sign_message(struct ceph_msg *msg) { struct ceph_osd *o = msg->con->private; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_sign_message(auth, msg); } static int osd_check_message_signature(struct ceph_msg *msg) { struct ceph_osd *o = msg->con->private; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_check_message_signature(auth, msg); } static void advance_cursor(struct ceph_msg_data_cursor *cursor, size_t len, bool zero) { while (len) { struct page *page; size_t poff, plen; page = ceph_msg_data_next(cursor, &poff, &plen); if (plen > len) plen = len; if (zero) zero_user_segment(page, poff, poff + plen); len -= plen; ceph_msg_data_advance(cursor, plen); } } static int prep_next_sparse_read(struct ceph_connection *con, struct ceph_msg_data_cursor *cursor) { struct ceph_osd *o = con->private; struct ceph_sparse_read *sr = &o->o_sparse_read; struct ceph_osd_request *req; struct ceph_osd_req_op *op; spin_lock(&o->o_requests_lock); req = lookup_request(&o->o_requests, le64_to_cpu(con->in_msg->hdr.tid)); if (!req) { spin_unlock(&o->o_requests_lock); return -EBADR; } if (o->o_sparse_op_idx < 0) { dout("%s: [%d] starting new sparse read req\n", __func__, o->o_osd); } else { u64 end; op = &req->r_ops[o->o_sparse_op_idx]; WARN_ON_ONCE(op->extent.sparse_ext); /* hand back buffer we took earlier */ op->extent.sparse_ext = sr->sr_extent; sr->sr_extent = NULL; op->extent.sparse_ext_cnt = sr->sr_count; sr->sr_ext_len = 0; dout("%s: [%d] completed extent array len %d cursor->resid %zd\n", __func__, o->o_osd, op->extent.sparse_ext_cnt, cursor->resid); /* Advance to end of data for this operation */ end = ceph_sparse_ext_map_end(op); if (end < sr->sr_req_len) advance_cursor(cursor, sr->sr_req_len - end, false); } ceph_init_sparse_read(sr); /* find next op in this request (if any) */ while (++o->o_sparse_op_idx < req->r_num_ops) { op = &req->r_ops[o->o_sparse_op_idx]; if (op->op == CEPH_OSD_OP_SPARSE_READ) goto found; } /* reset for next sparse read request */ spin_unlock(&o->o_requests_lock); o->o_sparse_op_idx = -1; return 0; found: sr->sr_req_off = op->extent.offset; sr->sr_req_len = op->extent.length; sr->sr_pos = sr->sr_req_off; dout("%s: [%d] new sparse read op at idx %d 0x%llx~0x%llx\n", __func__, o->o_osd, o->o_sparse_op_idx, sr->sr_req_off, sr->sr_req_len); /* hand off request's sparse extent map buffer */ sr->sr_ext_len = op->extent.sparse_ext_cnt; op->extent.sparse_ext_cnt = 0; sr->sr_extent = op->extent.sparse_ext; op->extent.sparse_ext = NULL; spin_unlock(&o->o_requests_lock); return 1; } #ifdef __BIG_ENDIAN static inline void convert_extent_map(struct ceph_sparse_read *sr) { int i; for (i = 0; i < sr->sr_count; i++) { struct ceph_sparse_extent *ext = &sr->sr_extent[i]; ext->off = le64_to_cpu((__force __le64)ext->off); ext->len = le64_to_cpu((__force __le64)ext->len); } } #else static inline void convert_extent_map(struct ceph_sparse_read *sr) { } #endif static int osd_sparse_read(struct ceph_connection *con, struct ceph_msg_data_cursor *cursor, char **pbuf) { struct ceph_osd *o = con->private; struct ceph_sparse_read *sr = &o->o_sparse_read; u32 count = sr->sr_count; u64 eoff, elen, len = 0; int i, ret; switch (sr->sr_state) { case CEPH_SPARSE_READ_HDR: next_op: ret = prep_next_sparse_read(con, cursor); if (ret <= 0) return ret; /* number of extents */ ret = sizeof(sr->sr_count); *pbuf = (char *)&sr->sr_count; sr->sr_state = CEPH_SPARSE_READ_EXTENTS; break; case CEPH_SPARSE_READ_EXTENTS: /* Convert sr_count to host-endian */ count = le32_to_cpu((__force __le32)sr->sr_count); sr->sr_count = count; dout("[%d] got %u extents\n", o->o_osd, count); if (count > 0) { if (!sr->sr_extent || count > sr->sr_ext_len) { /* no extent array provided, or too short */ kfree(sr->sr_extent); sr->sr_extent = kmalloc_array(count, sizeof(*sr->sr_extent), GFP_NOIO); if (!sr->sr_extent) { pr_err("%s: failed to allocate %u extents\n", __func__, count); return -ENOMEM; } sr->sr_ext_len = count; } ret = count * sizeof(*sr->sr_extent); *pbuf = (char *)sr->sr_extent; sr->sr_state = CEPH_SPARSE_READ_DATA_LEN; break; } /* No extents? Read data len */ fallthrough; case CEPH_SPARSE_READ_DATA_LEN: convert_extent_map(sr); ret = sizeof(sr->sr_datalen); *pbuf = (char *)&sr->sr_datalen; sr->sr_state = CEPH_SPARSE_READ_DATA_PRE; break; case CEPH_SPARSE_READ_DATA_PRE: /* Convert sr_datalen to host-endian */ sr->sr_datalen = le32_to_cpu((__force __le32)sr->sr_datalen); for (i = 0; i < count; i++) len += sr->sr_extent[i].len; if (sr->sr_datalen != len) { pr_warn_ratelimited("data len %u != extent len %llu\n", sr->sr_datalen, len); return -EREMOTEIO; } sr->sr_state = CEPH_SPARSE_READ_DATA; fallthrough; case CEPH_SPARSE_READ_DATA: if (sr->sr_index >= count) { sr->sr_state = CEPH_SPARSE_READ_HDR; goto next_op; } eoff = sr->sr_extent[sr->sr_index].off; elen = sr->sr_extent[sr->sr_index].len; dout("[%d] ext %d off 0x%llx len 0x%llx\n", o->o_osd, sr->sr_index, eoff, elen); if (elen > INT_MAX) { dout("Sparse read extent length too long (0x%llx)\n", elen); return -EREMOTEIO; } /* zero out anything from sr_pos to start of extent */ if (sr->sr_pos < eoff) advance_cursor(cursor, eoff - sr->sr_pos, true); /* Set position to end of extent */ sr->sr_pos = eoff + elen; /* send back the new length and nullify the ptr */ cursor->sr_resid = elen; ret = elen; *pbuf = NULL; /* Bump the array index */ ++sr->sr_index; break; } return ret; } static const struct ceph_connection_operations osd_con_ops = { .get = osd_get_con, .put = osd_put_con, .sparse_read = osd_sparse_read, .alloc_msg = osd_alloc_msg, .dispatch = osd_dispatch, .fault = osd_fault, .reencode_message = osd_reencode_message, .get_authorizer = osd_get_authorizer, .add_authorizer_challenge = osd_add_authorizer_challenge, .verify_authorizer_reply = osd_verify_authorizer_reply, .invalidate_authorizer = osd_invalidate_authorizer, .sign_message = osd_sign_message, .check_message_signature = osd_check_message_signature, .get_auth_request = osd_get_auth_request, .handle_auth_reply_more = osd_handle_auth_reply_more, .handle_auth_done = osd_handle_auth_done, .handle_auth_bad_method = osd_handle_auth_bad_method, }; |
| 220 10 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* */ #include <linux/init.h> #include <linux/usb.h> #include <sound/core.h> #include <sound/info.h> #include <sound/pcm.h> #include "usbaudio.h" #include "helper.h" #include "card.h" #include "endpoint.h" #include "proc.h" /* convert our full speed USB rate into sampling rate in Hz */ static inline unsigned get_full_speed_hz(unsigned int usb_rate) { return (usb_rate * 125 + (1 << 12)) >> 13; } /* convert our high speed USB rate into sampling rate in Hz */ static inline unsigned get_high_speed_hz(unsigned int usb_rate) { return (usb_rate * 125 + (1 << 9)) >> 10; } /* * common proc files to show the usb device info */ static void proc_audio_usbbus_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_usb_audio *chip = entry->private_data; if (!atomic_read(&chip->shutdown)) snd_iprintf(buffer, "%03d/%03d\n", chip->dev->bus->busnum, chip->dev->devnum); } static void proc_audio_usbid_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_usb_audio *chip = entry->private_data; if (!atomic_read(&chip->shutdown)) snd_iprintf(buffer, "%04x:%04x\n", USB_ID_VENDOR(chip->usb_id), USB_ID_PRODUCT(chip->usb_id)); } void snd_usb_audio_create_proc(struct snd_usb_audio *chip) { snd_card_ro_proc_new(chip->card, "usbbus", chip, proc_audio_usbbus_read); snd_card_ro_proc_new(chip->card, "usbid", chip, proc_audio_usbid_read); } static const char * const channel_labels[] = { [SNDRV_CHMAP_NA] = "N/A", [SNDRV_CHMAP_MONO] = "MONO", [SNDRV_CHMAP_FL] = "FL", [SNDRV_CHMAP_FR] = "FR", [SNDRV_CHMAP_FC] = "FC", [SNDRV_CHMAP_LFE] = "LFE", [SNDRV_CHMAP_RL] = "RL", [SNDRV_CHMAP_RR] = "RR", [SNDRV_CHMAP_FLC] = "FLC", [SNDRV_CHMAP_FRC] = "FRC", [SNDRV_CHMAP_RC] = "RC", [SNDRV_CHMAP_SL] = "SL", [SNDRV_CHMAP_SR] = "SR", [SNDRV_CHMAP_TC] = "TC", [SNDRV_CHMAP_TFL] = "TFL", [SNDRV_CHMAP_TFC] = "TFC", [SNDRV_CHMAP_TFR] = "TFR", [SNDRV_CHMAP_TRL] = "TRL", [SNDRV_CHMAP_TRC] = "TRC", [SNDRV_CHMAP_TRR] = "TRR", [SNDRV_CHMAP_TFLC] = "TFLC", [SNDRV_CHMAP_TFRC] = "TFRC", [SNDRV_CHMAP_LLFE] = "LLFE", [SNDRV_CHMAP_RLFE] = "RLFE", [SNDRV_CHMAP_TSL] = "TSL", [SNDRV_CHMAP_TSR] = "TSR", [SNDRV_CHMAP_BC] = "BC", [SNDRV_CHMAP_RLC] = "RLC", [SNDRV_CHMAP_RRC] = "RRC", }; /* * proc interface for list the supported pcm formats */ static void proc_dump_substream_formats(struct snd_usb_substream *subs, struct snd_info_buffer *buffer) { struct audioformat *fp; static const char * const sync_types[4] = { "NONE", "ASYNC", "ADAPTIVE", "SYNC" }; list_for_each_entry(fp, &subs->fmt_list, list) { snd_pcm_format_t fmt; snd_iprintf(buffer, " Interface %d\n", fp->iface); snd_iprintf(buffer, " Altset %d\n", fp->altsetting); snd_iprintf(buffer, " Format:"); pcm_for_each_format(fmt) if (fp->formats & pcm_format_to_bits(fmt)) snd_iprintf(buffer, " %s", snd_pcm_format_name(fmt)); snd_iprintf(buffer, "\n"); snd_iprintf(buffer, " Channels: %d\n", fp->channels); snd_iprintf(buffer, " Endpoint: 0x%02x (%d %s) (%s)\n", fp->endpoint, fp->endpoint & USB_ENDPOINT_NUMBER_MASK, fp->endpoint & USB_DIR_IN ? "IN" : "OUT", sync_types[(fp->ep_attr & USB_ENDPOINT_SYNCTYPE) >> 2]); if (fp->rates & SNDRV_PCM_RATE_CONTINUOUS) { snd_iprintf(buffer, " Rates: %d - %d (continuous)\n", fp->rate_min, fp->rate_max); } else { unsigned int i; snd_iprintf(buffer, " Rates: "); for (i = 0; i < fp->nr_rates; i++) { if (i > 0) snd_iprintf(buffer, ", "); snd_iprintf(buffer, "%d", fp->rate_table[i]); } snd_iprintf(buffer, "\n"); } if (subs->speed != USB_SPEED_FULL) snd_iprintf(buffer, " Data packet interval: %d us\n", 125 * (1 << fp->datainterval)); snd_iprintf(buffer, " Bits: %d\n", fp->fmt_bits); if (fp->dsd_raw) snd_iprintf(buffer, " DSD raw: DOP=%d, bitrev=%d\n", fp->dsd_dop, fp->dsd_bitrev); if (fp->chmap) { const struct snd_pcm_chmap_elem *map = fp->chmap; int c; snd_iprintf(buffer, " Channel map:"); for (c = 0; c < map->channels; c++) { if (map->map[c] >= ARRAY_SIZE(channel_labels) || !channel_labels[map->map[c]]) snd_iprintf(buffer, " --"); else snd_iprintf(buffer, " %s", channel_labels[map->map[c]]); } snd_iprintf(buffer, "\n"); } if (fp->sync_ep) { snd_iprintf(buffer, " Sync Endpoint: 0x%02x (%d %s)\n", fp->sync_ep, fp->sync_ep & USB_ENDPOINT_NUMBER_MASK, fp->sync_ep & USB_DIR_IN ? "IN" : "OUT"); snd_iprintf(buffer, " Sync EP Interface: %d\n", fp->sync_iface); snd_iprintf(buffer, " Sync EP Altset: %d\n", fp->sync_altsetting); snd_iprintf(buffer, " Implicit Feedback Mode: %s\n", fp->implicit_fb ? "Yes" : "No"); } // snd_iprintf(buffer, " Max Packet Size = %d\n", fp->maxpacksize); // snd_iprintf(buffer, " EP Attribute = %#x\n", fp->attributes); } } static void proc_dump_ep_status(struct snd_usb_substream *subs, struct snd_usb_endpoint *data_ep, struct snd_usb_endpoint *sync_ep, struct snd_info_buffer *buffer) { if (!data_ep) return; snd_iprintf(buffer, " Packet Size = %d\n", data_ep->curpacksize); snd_iprintf(buffer, " Momentary freq = %u Hz (%#x.%04x)\n", subs->speed == USB_SPEED_FULL ? get_full_speed_hz(data_ep->freqm) : get_high_speed_hz(data_ep->freqm), data_ep->freqm >> 16, data_ep->freqm & 0xffff); if (sync_ep && data_ep->freqshift != INT_MIN) { int res = 16 - data_ep->freqshift; snd_iprintf(buffer, " Feedback Format = %d.%d\n", (sync_ep->syncmaxsize > 3 ? 32 : 24) - res, res); } } static void proc_dump_substream_status(struct snd_usb_audio *chip, struct snd_usb_substream *subs, struct snd_info_buffer *buffer) { guard(mutex)(&chip->mutex); if (subs->running) { snd_iprintf(buffer, " Status: Running\n"); if (subs->cur_audiofmt) { snd_iprintf(buffer, " Interface = %d\n", subs->cur_audiofmt->iface); snd_iprintf(buffer, " Altset = %d\n", subs->cur_audiofmt->altsetting); } proc_dump_ep_status(subs, subs->data_endpoint, subs->sync_endpoint, buffer); } else { snd_iprintf(buffer, " Status: Stop\n"); } } static void proc_pcm_format_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_usb_stream *stream = entry->private_data; struct snd_usb_audio *chip = stream->chip; snd_iprintf(buffer, "%s : %s\n", chip->card->longname, stream->pcm->name); if (stream->substream[SNDRV_PCM_STREAM_PLAYBACK].num_formats) { snd_iprintf(buffer, "\nPlayback:\n"); proc_dump_substream_status(chip, &stream->substream[SNDRV_PCM_STREAM_PLAYBACK], buffer); proc_dump_substream_formats(&stream->substream[SNDRV_PCM_STREAM_PLAYBACK], buffer); } if (stream->substream[SNDRV_PCM_STREAM_CAPTURE].num_formats) { snd_iprintf(buffer, "\nCapture:\n"); proc_dump_substream_status(chip, &stream->substream[SNDRV_PCM_STREAM_CAPTURE], buffer); proc_dump_substream_formats(&stream->substream[SNDRV_PCM_STREAM_CAPTURE], buffer); } } void snd_usb_proc_pcm_format_add(struct snd_usb_stream *stream) { char name[32]; struct snd_card *card = stream->chip->card; scnprintf(name, sizeof(name), "stream%d", stream->pcm_index); snd_card_ro_proc_new(card, name, stream, proc_pcm_format_read); } |
| 7 2 1 1 3 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ASIX AX88172A based USB 2.0 Ethernet Devices * Copyright (C) 2012 OMICRON electronics GmbH * * Supports external PHYs via phylib. Based on the driver for the * AX88772. Original copyrights follow: * * Copyright (C) 2003-2006 David Hollis <dhollis@davehollis.com> * Copyright (C) 2005 Phil Chang <pchang23@sbcglobal.net> * Copyright (C) 2006 James Painter <jamie.painter@iname.com> * Copyright (c) 2002-2003 TiVo Inc. */ #include "asix.h" #include <linux/phy.h> struct ax88172a_private { struct mii_bus *mdio; struct phy_device *phydev; char phy_name[PHY_ID_SIZE]; u8 phy_addr; u16 oldmode; int use_embdphy; struct asix_rx_fixup_info rx_fixup_info; }; /* set MAC link settings according to information from phylib */ static void ax88172a_adjust_link(struct net_device *netdev) { struct phy_device *phydev = netdev->phydev; struct usbnet *dev = netdev_priv(netdev); struct ax88172a_private *priv = dev->driver_priv; u16 mode = 0; if (phydev->link) { mode = AX88772_MEDIUM_DEFAULT; if (phydev->duplex == DUPLEX_HALF) mode &= ~AX_MEDIUM_FD; if (phydev->speed != SPEED_100) mode &= ~AX_MEDIUM_PS; } if (mode != priv->oldmode) { asix_write_medium_mode(dev, mode, 0); priv->oldmode = mode; netdev_dbg(netdev, "speed %u duplex %d, setting mode to 0x%04x\n", phydev->speed, phydev->duplex, mode); phy_print_status(phydev); } } static void ax88172a_status(struct usbnet *dev, struct urb *urb) { /* link changes are detected by polling the phy */ } /* use phylib infrastructure */ static int ax88172a_init_mdio(struct usbnet *dev) { struct ax88172a_private *priv = dev->driver_priv; int ret; priv->mdio = mdiobus_alloc(); if (!priv->mdio) { netdev_err(dev->net, "Could not allocate MDIO bus\n"); return -ENOMEM; } priv->mdio->priv = (void *)dev; priv->mdio->read = &asix_mdio_bus_read; priv->mdio->write = &asix_mdio_bus_write; priv->mdio->name = "Asix MDIO Bus"; /* mii bus name is usb-<usb bus number>-<usb device number> */ snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); ret = mdiobus_register(priv->mdio); if (ret) { netdev_err(dev->net, "Could not register MDIO bus\n"); goto mfree; } netdev_info(dev->net, "registered mdio bus %s\n", priv->mdio->id); return 0; mfree: mdiobus_free(priv->mdio); return ret; } static void ax88172a_remove_mdio(struct usbnet *dev) { struct ax88172a_private *priv = dev->driver_priv; netdev_info(dev->net, "deregistering mdio bus %s\n", priv->mdio->id); mdiobus_unregister(priv->mdio); mdiobus_free(priv->mdio); } static const struct net_device_ops ax88172a_netdev_ops = { .ndo_open = usbnet_open, .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, .ndo_change_mtu = usbnet_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = asix_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_rx_mode = asix_set_multicast, }; static const struct ethtool_ops ax88172a_ethtool_ops = { .get_drvinfo = asix_get_drvinfo, .get_link = usbnet_get_link, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, .get_wol = asix_get_wol, .set_wol = asix_set_wol, .get_eeprom_len = asix_get_eeprom_len, .get_eeprom = asix_get_eeprom, .set_eeprom = asix_set_eeprom, .nway_reset = phy_ethtool_nway_reset, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, }; static int ax88172a_reset_phy(struct usbnet *dev, int embd_phy) { int ret; ret = asix_sw_reset(dev, AX_SWRESET_IPPD, 0); if (ret < 0) goto err; msleep(150); ret = asix_sw_reset(dev, AX_SWRESET_CLEAR, 0); if (ret < 0) goto err; msleep(150); ret = asix_sw_reset(dev, embd_phy ? AX_SWRESET_IPRL : AX_SWRESET_IPPD, 0); if (ret < 0) goto err; return 0; err: return ret; } static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) { int ret; u8 buf[ETH_ALEN]; struct ax88172a_private *priv; ret = usbnet_get_endpoints(dev, intf); if (ret) return ret; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; dev->driver_priv = priv; /* Get the MAC address */ ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0); if (ret < ETH_ALEN) { netdev_err(dev->net, "Failed to read MAC address: %d\n", ret); ret = -EIO; goto free; } eth_hw_addr_set(dev->net, buf); dev->net->netdev_ops = &ax88172a_netdev_ops; dev->net->ethtool_ops = &ax88172a_ethtool_ops; /* are we using the internal or the external phy? */ ret = asix_read_cmd(dev, AX_CMD_SW_PHY_STATUS, 0, 0, 1, buf, 0); if (ret < 0) { netdev_err(dev->net, "Failed to read software interface selection register: %d\n", ret); goto free; } netdev_dbg(dev->net, "AX_CMD_SW_PHY_STATUS = 0x%02x\n", buf[0]); switch (buf[0] & AX_PHY_SELECT_MASK) { case AX_PHY_SELECT_INTERNAL: netdev_dbg(dev->net, "use internal phy\n"); priv->use_embdphy = 1; break; case AX_PHY_SELECT_EXTERNAL: netdev_dbg(dev->net, "use external phy\n"); priv->use_embdphy = 0; break; default: netdev_err(dev->net, "Interface mode not supported by driver\n"); ret = -ENOTSUPP; goto free; } ret = asix_read_phy_addr(dev, priv->use_embdphy); if (ret < 0) goto free; if (ret >= PHY_MAX_ADDR) { netdev_err(dev->net, "Invalid PHY address %#x\n", ret); ret = -ENODEV; goto free; } priv->phy_addr = ret; ax88172a_reset_phy(dev, priv->use_embdphy); /* Asix framing packs multiple eth frames into a 2K usb bulk transfer */ if (dev->driver_info->flags & FLAG_FRAMING_AX) { /* hard_mtu is still the default - the device does not support jumbo eth frames */ dev->rx_urb_size = 2048; } /* init MDIO bus */ ret = ax88172a_init_mdio(dev); if (ret) goto free; return 0; free: kfree(priv); return ret; } static int ax88172a_stop(struct usbnet *dev) { struct ax88172a_private *priv = dev->driver_priv; netdev_dbg(dev->net, "Stopping interface\n"); if (priv->phydev) { netdev_info(dev->net, "Disconnecting from phy %s\n", priv->phy_name); phy_stop(priv->phydev); phy_disconnect(priv->phydev); } return 0; } static void ax88172a_unbind(struct usbnet *dev, struct usb_interface *intf) { struct ax88172a_private *priv = dev->driver_priv; ax88172a_remove_mdio(dev); kfree(priv); } static int ax88172a_reset(struct usbnet *dev) { struct asix_data *data = (struct asix_data *)&dev->data; struct ax88172a_private *priv = dev->driver_priv; int ret; u16 rx_ctl; ax88172a_reset_phy(dev, priv->use_embdphy); msleep(150); rx_ctl = asix_read_rx_ctl(dev, 0); netdev_dbg(dev->net, "RX_CTL is 0x%04x after software reset\n", rx_ctl); ret = asix_write_rx_ctl(dev, 0x0000, 0); if (ret < 0) goto out; rx_ctl = asix_read_rx_ctl(dev, 0); netdev_dbg(dev->net, "RX_CTL is 0x%04x setting to 0x0000\n", rx_ctl); msleep(150); ret = asix_write_cmd(dev, AX_CMD_WRITE_IPG0, AX88772_IPG0_DEFAULT | AX88772_IPG1_DEFAULT, AX88772_IPG2_DEFAULT, 0, NULL, 0); if (ret < 0) { netdev_err(dev->net, "Write IPG,IPG1,IPG2 failed: %d\n", ret); goto out; } /* Rewrite MAC address */ memcpy(data->mac_addr, dev->net->dev_addr, ETH_ALEN); ret = asix_write_cmd(dev, AX_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN, data->mac_addr, 0); if (ret < 0) goto out; /* Set RX_CTL to default values with 2k buffer, and enable cactus */ ret = asix_write_rx_ctl(dev, AX_DEFAULT_RX_CTL, 0); if (ret < 0) goto out; rx_ctl = asix_read_rx_ctl(dev, 0); netdev_dbg(dev->net, "RX_CTL is 0x%04x after all initializations\n", rx_ctl); rx_ctl = asix_read_medium_status(dev, 0); netdev_dbg(dev->net, "Medium Status is 0x%04x after all initializations\n", rx_ctl); /* Connect to PHY */ snprintf(priv->phy_name, sizeof(priv->phy_name), PHY_ID_FMT, priv->mdio->id, priv->phy_addr); priv->phydev = phy_connect(dev->net, priv->phy_name, &ax88172a_adjust_link, PHY_INTERFACE_MODE_MII); if (IS_ERR(priv->phydev)) { netdev_err(dev->net, "Could not connect to PHY device %s\n", priv->phy_name); ret = PTR_ERR(priv->phydev); goto out; } netdev_info(dev->net, "Connected to phy %s\n", priv->phy_name); /* During power-up, the AX88172A set the power down (BMCR_PDOWN) * bit of the PHY. Bring the PHY up again. */ genphy_resume(priv->phydev); phy_start(priv->phydev); return 0; out: return ret; } static int ax88172a_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { struct ax88172a_private *dp = dev->driver_priv; struct asix_rx_fixup_info *rx = &dp->rx_fixup_info; return asix_rx_fixup_internal(dev, skb, rx); } const struct driver_info ax88172a_info = { .description = "ASIX AX88172A USB 2.0 Ethernet", .bind = ax88172a_bind, .reset = ax88172a_reset, .stop = ax88172a_stop, .unbind = ax88172a_unbind, .status = ax88172a_status, .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET, .rx_fixup = ax88172a_rx_fixup, .tx_fixup = asix_tx_fixup, }; |
| 3 2 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 | /* * CoreChip-sz SR9700 one chip USB 1.1 Ethernet Devices * * Author : Liu Junliang <liujunliang_ljl@163.com> * * Based on dm9601.c * * This file is licensed under the terms of the GNU General Public License * version 2. This program is licensed "as is" without any warranty of any * kind, whether express or implied. */ #include <linux/module.h> #include <linux/sched.h> #include <linux/stddef.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/mii.h> #include <linux/usb.h> #include <linux/crc32.h> #include <linux/usb/usbnet.h> #include "sr9700.h" static int sr_read(struct usbnet *dev, u8 reg, u16 length, void *data) { int err; err = usbnet_read_cmd(dev, SR_RD_REGS, SR_REQ_RD_REG, 0, reg, data, length); if ((err != length) && (err >= 0)) err = -EINVAL; return err; } static int sr_write(struct usbnet *dev, u8 reg, u16 length, void *data) { int err; err = usbnet_write_cmd(dev, SR_WR_REGS, SR_REQ_WR_REG, 0, reg, data, length); if ((err >= 0) && (err < length)) err = -EINVAL; return err; } static int sr_read_reg(struct usbnet *dev, u8 reg, u8 *value) { return sr_read(dev, reg, 1, value); } static int sr_write_reg(struct usbnet *dev, u8 reg, u8 value) { return usbnet_write_cmd(dev, SR_WR_REGS, SR_REQ_WR_REG, value, reg, NULL, 0); } static void sr_write_async(struct usbnet *dev, u8 reg, u16 length, const void *data) { usbnet_write_cmd_async(dev, SR_WR_REGS, SR_REQ_WR_REG, 0, reg, data, length); } static void sr_write_reg_async(struct usbnet *dev, u8 reg, u8 value) { usbnet_write_cmd_async(dev, SR_WR_REGS, SR_REQ_WR_REG, value, reg, NULL, 0); } static int wait_phy_eeprom_ready(struct usbnet *dev, int phy) { int i; for (i = 0; i < SR_SHARE_TIMEOUT; i++) { u8 tmp = 0; int ret; udelay(1); ret = sr_read_reg(dev, SR_EPCR, &tmp); if (ret < 0) return ret; /* ready */ if (!(tmp & EPCR_ERRE)) return 0; } netdev_err(dev->net, "%s write timed out!\n", phy ? "phy" : "eeprom"); return -EIO; } static int sr_share_read_word(struct usbnet *dev, int phy, u8 reg, __le16 *value) { int ret; mutex_lock(&dev->phy_mutex); sr_write_reg(dev, SR_EPAR, phy ? (reg | EPAR_PHY_ADR) : reg); sr_write_reg(dev, SR_EPCR, phy ? (EPCR_EPOS | EPCR_ERPRR) : EPCR_ERPRR); ret = wait_phy_eeprom_ready(dev, phy); if (ret < 0) goto out_unlock; sr_write_reg(dev, SR_EPCR, 0x0); ret = sr_read(dev, SR_EPDR, 2, value); netdev_dbg(dev->net, "read shared %d 0x%02x returned 0x%04x, %d\n", phy, reg, *value, ret); out_unlock: mutex_unlock(&dev->phy_mutex); return ret; } static int sr_share_write_word(struct usbnet *dev, int phy, u8 reg, __le16 value) { int ret; mutex_lock(&dev->phy_mutex); ret = sr_write(dev, SR_EPDR, 2, &value); if (ret < 0) goto out_unlock; sr_write_reg(dev, SR_EPAR, phy ? (reg | EPAR_PHY_ADR) : reg); sr_write_reg(dev, SR_EPCR, phy ? (EPCR_WEP | EPCR_EPOS | EPCR_ERPRW) : (EPCR_WEP | EPCR_ERPRW)); ret = wait_phy_eeprom_ready(dev, phy); if (ret < 0) goto out_unlock; sr_write_reg(dev, SR_EPCR, 0x0); out_unlock: mutex_unlock(&dev->phy_mutex); return ret; } static int sr_read_eeprom_word(struct usbnet *dev, u8 offset, void *value) { return sr_share_read_word(dev, 0, offset, value); } static int sr9700_get_eeprom_len(struct net_device *netdev) { return SR_EEPROM_LEN; } static int sr9700_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom, u8 *data) { struct usbnet *dev = netdev_priv(netdev); __le16 *buf = (__le16 *)data; int ret = 0; int i; /* access is 16bit */ if ((eeprom->offset & 0x01) || (eeprom->len & 0x01)) return -EINVAL; for (i = 0; i < eeprom->len / 2; i++) { ret = sr_read_eeprom_word(dev, eeprom->offset / 2 + i, buf + i); if (ret < 0) break; } return ret; } static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc) { struct usbnet *dev = netdev_priv(netdev); int err, res; __le16 word; int rc = 0; if (phy_id) { netdev_dbg(netdev, "Only internal phy supported\n"); return 0; } /* Access NSR_LINKST bit for link status instead of MII_BMSR */ if (loc == MII_BMSR) { u8 value; err = sr_read_reg(dev, SR_NSR, &value); if (err < 0) return err; if (value & NSR_LINKST) rc = 1; } err = sr_share_read_word(dev, 1, loc, &word); if (err < 0) return err; if (rc == 1) res = le16_to_cpu(word) | BMSR_LSTATUS; else res = le16_to_cpu(word) & ~BMSR_LSTATUS; netdev_dbg(netdev, "sr_mdio_read() phy_id=0x%02x, loc=0x%02x, returns=0x%04x\n", phy_id, loc, res); return res; } static void sr_mdio_write(struct net_device *netdev, int phy_id, int loc, int val) { struct usbnet *dev = netdev_priv(netdev); __le16 res = cpu_to_le16(val); if (phy_id) { netdev_dbg(netdev, "Only internal phy supported\n"); return; } netdev_dbg(netdev, "sr_mdio_write() phy_id=0x%02x, loc=0x%02x, val=0x%04x\n", phy_id, loc, val); sr_share_write_word(dev, 1, loc, res); } static u32 sr9700_get_link(struct net_device *netdev) { struct usbnet *dev = netdev_priv(netdev); u8 value = 0; int rc = 0; /* Get the Link Status directly */ sr_read_reg(dev, SR_NSR, &value); if (value & NSR_LINKST) rc = 1; return rc; } static int sr9700_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) { struct usbnet *dev = netdev_priv(netdev); return generic_mii_ioctl(&dev->mii, if_mii(rq), cmd, NULL); } static const struct ethtool_ops sr9700_ethtool_ops = { .get_drvinfo = usbnet_get_drvinfo, .get_link = sr9700_get_link, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, .get_eeprom_len = sr9700_get_eeprom_len, .get_eeprom = sr9700_get_eeprom, .nway_reset = usbnet_nway_reset, .get_link_ksettings = usbnet_get_link_ksettings_mii, .set_link_ksettings = usbnet_set_link_ksettings_mii, }; static void sr9700_set_multicast(struct net_device *netdev) { struct usbnet *dev = netdev_priv(netdev); /* We use the 20 byte dev->data for our 8 byte filter buffer * to avoid allocating memory that is tricky to free later */ u8 *hashes = (u8 *)&dev->data; /* rx_ctl setting : enable, disable_long, disable_crc */ u8 rx_ctl = RCR_RXEN | RCR_DIS_CRC | RCR_DIS_LONG; memset(hashes, 0x00, SR_MCAST_SIZE); /* broadcast address */ hashes[SR_MCAST_SIZE - 1] |= SR_MCAST_ADDR_FLAG; if (netdev->flags & IFF_PROMISC) { rx_ctl |= RCR_PRMSC; } else if (netdev->flags & IFF_ALLMULTI || netdev_mc_count(netdev) > SR_MCAST_MAX) { rx_ctl |= RCR_RUNT; } else if (!netdev_mc_empty(netdev)) { struct netdev_hw_addr *ha; netdev_for_each_mc_addr(ha, netdev) { u32 crc = ether_crc(ETH_ALEN, ha->addr) >> 26; hashes[crc >> 3] |= 1 << (crc & 0x7); } } sr_write_async(dev, SR_MAR, SR_MCAST_SIZE, hashes); sr_write_reg_async(dev, SR_RCR, rx_ctl); } static int sr9700_set_mac_address(struct net_device *netdev, void *p) { struct usbnet *dev = netdev_priv(netdev); struct sockaddr *addr = p; if (!is_valid_ether_addr(addr->sa_data)) { netdev_err(netdev, "not setting invalid mac address %pM\n", addr->sa_data); return -EINVAL; } eth_hw_addr_set(netdev, addr->sa_data); sr_write_async(dev, SR_PAR, 6, netdev->dev_addr); return 0; } static const struct net_device_ops sr9700_netdev_ops = { .ndo_open = usbnet_open, .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, .ndo_change_mtu = usbnet_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_validate_addr = eth_validate_addr, .ndo_eth_ioctl = sr9700_ioctl, .ndo_set_rx_mode = sr9700_set_multicast, .ndo_set_mac_address = sr9700_set_mac_address, }; static int sr9700_bind(struct usbnet *dev, struct usb_interface *intf) { struct net_device *netdev; struct mii_if_info *mii; u8 addr[ETH_ALEN]; int ret; ret = usbnet_get_endpoints(dev, intf); if (ret) goto out; netdev = dev->net; netdev->netdev_ops = &sr9700_netdev_ops; netdev->ethtool_ops = &sr9700_ethtool_ops; netdev->hard_header_len += SR_TX_OVERHEAD; dev->hard_mtu = netdev->mtu + netdev->hard_header_len; /* bulkin buffer is preferably not less than 3K */ dev->rx_urb_size = 3072; mii = &dev->mii; mii->dev = netdev; mii->mdio_read = sr_mdio_read; mii->mdio_write = sr_mdio_write; mii->phy_id_mask = 0x1f; mii->reg_num_mask = 0x1f; sr_write_reg(dev, SR_NCR, NCR_RST); udelay(20); /* read MAC * After Chip Power on, the Chip will reload the MAC from * EEPROM automatically to PAR. In case there is no EEPROM externally, * a default MAC address is stored in PAR for making chip work properly. */ if (sr_read(dev, SR_PAR, ETH_ALEN, addr) < 0) { netdev_err(netdev, "Error reading MAC address\n"); ret = -ENODEV; goto out; } eth_hw_addr_set(netdev, addr); /* power up and reset phy */ sr_write_reg(dev, SR_PRR, PRR_PHY_RST); /* at least 10ms, here 20ms for safe */ msleep(20); sr_write_reg(dev, SR_PRR, 0); /* at least 1ms, here 2ms for reading right register */ udelay(2 * 1000); /* receive broadcast packets */ sr9700_set_multicast(netdev); sr_mdio_write(netdev, mii->phy_id, MII_BMCR, BMCR_RESET); sr_mdio_write(netdev, mii->phy_id, MII_ADVERTISE, ADVERTISE_ALL | ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP); mii_nway_restart(mii); out: return ret; } static int sr9700_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { struct sk_buff *sr_skb; int len; /* skb content (packets) format : * p0 p1 p2 ...... pm * / \ * / \ * / \ * / \ * p0b0 p0b1 p0b2 p0b3 ...... p0b(n-4) p0b(n-3)...p0bn * * p0 : packet 0 * p0b0 : packet 0 byte 0 * * b0: rx status * b1: packet length (incl crc) low * b2: packet length (incl crc) high * b3..n-4: packet data * bn-3..bn: ethernet packet crc */ if (unlikely(skb->len < SR_RX_OVERHEAD)) { netdev_err(dev->net, "unexpected tiny rx frame\n"); return 0; } /* one skb may contains multiple packets */ while (skb->len > SR_RX_OVERHEAD) { if (skb->data[0] != 0x40) return 0; /* ignore the CRC length */ len = (skb->data[1] | (skb->data[2] << 8)) - 4; if (len > ETH_FRAME_LEN || len > skb->len || len < 0) return 0; /* the last packet of current skb */ if (skb->len == (len + SR_RX_OVERHEAD)) { skb_pull(skb, 3); skb->len = len; skb_set_tail_pointer(skb, len); return 2; } sr_skb = netdev_alloc_skb_ip_align(dev->net, len); if (!sr_skb) return 0; skb_put(sr_skb, len); memcpy(sr_skb->data, skb->data + 3, len); usbnet_skb_return(dev, sr_skb); skb_pull(skb, len + SR_RX_OVERHEAD); } return 0; } static struct sk_buff *sr9700_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) { int len; /* SR9700 can only send out one ethernet packet at once. * * b0 b1 b2 b3 ...... b(n-4) b(n-3)...bn * * b0: rx status * b1: packet length (incl crc) low * b2: packet length (incl crc) high * b3..n-4: packet data * bn-3..bn: ethernet packet crc */ len = skb->len; if (skb_cow_head(skb, SR_TX_OVERHEAD)) { dev_kfree_skb_any(skb); return NULL; } __skb_push(skb, SR_TX_OVERHEAD); /* usbnet adds padding if length is a multiple of packet size * if so, adjust length value in header */ if ((skb->len % dev->maxpacket) == 0) len++; skb->data[0] = len; skb->data[1] = len >> 8; return skb; } static void sr9700_status(struct usbnet *dev, struct urb *urb) { int link; u8 *buf; /* format: b0: net status b1: tx status 1 b2: tx status 2 b3: rx status b4: rx overflow b5: rx count b6: tx count b7: gpr */ if (urb->actual_length < 8) return; buf = urb->transfer_buffer; link = !!(buf[0] & 0x40); if (netif_carrier_ok(dev->net) != link) { usbnet_link_change(dev, link, 1); netdev_dbg(dev->net, "Link Status is: %d\n", link); } } static int sr9700_link_reset(struct usbnet *dev) { struct ethtool_cmd ecmd; mii_check_media(&dev->mii, 1, 1); mii_ethtool_gset(&dev->mii, &ecmd); netdev_dbg(dev->net, "link_reset() speed: %d duplex: %d\n", ecmd.speed, ecmd.duplex); return 0; } static const struct driver_info sr9700_driver_info = { .description = "CoreChip SR9700 USB Ethernet", .flags = FLAG_ETHER, .bind = sr9700_bind, .rx_fixup = sr9700_rx_fixup, .tx_fixup = sr9700_tx_fixup, .status = sr9700_status, .link_reset = sr9700_link_reset, .reset = sr9700_link_reset, }; static const struct usb_device_id products[] = { { USB_DEVICE(0x0fe6, 0x9700), /* SR9700 device */ .driver_info = (unsigned long)&sr9700_driver_info, }, {}, /* END */ }; MODULE_DEVICE_TABLE(usb, products); static struct usb_driver sr9700_usb_driver = { .name = "sr9700", .id_table = products, .probe = usbnet_probe, .disconnect = usbnet_disconnect, .suspend = usbnet_suspend, .resume = usbnet_resume, .disable_hub_initiated_lpm = 1, }; module_usb_driver(sr9700_usb_driver); MODULE_AUTHOR("liujl <liujunliang_ljl@163.com>"); MODULE_DESCRIPTION("SR9700 one chip USB 1.1 USB to Ethernet device from http://www.corechip-sz.com/"); MODULE_LICENSE("GPL"); |
| 344 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* SCTP kernel implementation * (C) Copyright 2007 Hewlett-Packard Development Company, L.P. * * This file is part of the SCTP kernel implementation * * 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: * Vlad Yasevich <vladislav.yasevich@hp.com> */ #ifndef __sctp_auth_h__ #define __sctp_auth_h__ #include <linux/list.h> #include <linux/refcount.h> struct sctp_endpoint; struct sctp_association; struct sctp_authkey; struct sctp_hmacalgo; /* Defines an HMAC algorithm supported by SCTP chunk authentication */ struct sctp_hmac { __u16 hmac_id; /* one of SCTP_AUTH_HMAC_ID_* */ __u16 hmac_len; /* length of the HMAC value in bytes */ }; /* This is generic structure that containst authentication bytes used * as keying material. It's a what is referred to as byte-vector all * over SCTP-AUTH */ struct sctp_auth_bytes { refcount_t refcnt; __u32 len; __u8 data[]; }; /* Definition for a shared key, weather endpoint or association */ struct sctp_shared_key { struct list_head key_list; struct sctp_auth_bytes *key; refcount_t refcnt; __u16 key_id; __u8 deactivated; }; #define key_for_each(__key, __list_head) \ list_for_each_entry(__key, __list_head, key_list) #define key_for_each_safe(__key, __tmp, __list_head) \ list_for_each_entry_safe(__key, __tmp, __list_head, key_list) static inline void sctp_auth_key_hold(struct sctp_auth_bytes *key) { if (!key) return; refcount_inc(&key->refcnt); } void sctp_auth_key_put(struct sctp_auth_bytes *key); struct sctp_shared_key *sctp_auth_shkey_create(__u16 key_id, gfp_t gfp); void sctp_auth_destroy_keys(struct list_head *keys); int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp); struct sctp_shared_key *sctp_auth_get_shkey( const struct sctp_association *asoc, __u16 key_id); int sctp_auth_asoc_copy_shkeys(const struct sctp_endpoint *ep, struct sctp_association *asoc, gfp_t gfp); int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp); const struct sctp_hmac *sctp_auth_get_hmac(__u16 hmac_id); const struct sctp_hmac * sctp_auth_asoc_get_hmac(const struct sctp_association *asoc); void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc, struct sctp_hmac_algo_param *hmacs); int sctp_auth_asoc_verify_hmac_id(const struct sctp_association *asoc, __be16 hmac_id); int sctp_auth_send_cid(enum sctp_cid chunk, const struct sctp_association *asoc); int sctp_auth_recv_cid(enum sctp_cid chunk, const struct sctp_association *asoc); void sctp_auth_calculate_hmac(const struct sctp_association *asoc, struct sk_buff *skb, struct sctp_auth_chunk *auth, struct sctp_shared_key *ep_key, gfp_t gfp); void sctp_auth_shkey_release(struct sctp_shared_key *sh_key); void sctp_auth_shkey_hold(struct sctp_shared_key *sh_key); /* API Helpers */ int sctp_auth_ep_add_chunkid(struct sctp_endpoint *ep, __u8 chunk_id); int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep, struct sctp_hmacalgo *hmacs); int sctp_auth_set_key(struct sctp_endpoint *ep, struct sctp_association *asoc, struct sctp_authkey *auth_key); int sctp_auth_set_active_key(struct sctp_endpoint *ep, struct sctp_association *asoc, __u16 key_id); int sctp_auth_del_key_id(struct sctp_endpoint *ep, struct sctp_association *asoc, __u16 key_id); int sctp_auth_deact_key_id(struct sctp_endpoint *ep, struct sctp_association *asoc, __u16 key_id); int sctp_auth_init(struct sctp_endpoint *ep, gfp_t gfp); void sctp_auth_free(struct sctp_endpoint *ep); #endif |
| 8 8 8 1 1 1 1 2 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2015 Patrick McHardy <kaber@trash.net> */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> struct nft_dynset { struct nft_set *set; struct nft_set_ext_tmpl tmpl; enum nft_dynset_ops op:8; u8 sreg_key; u8 sreg_data; bool invert; bool expr; u8 num_exprs; u64 timeout; struct nft_expr *expr_array[NFT_SET_EXPR_MAX]; struct nft_set_binding binding; }; static int nft_dynset_expr_setup(const struct nft_dynset *priv, const struct nft_set_ext *ext) { struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext); struct nft_expr *expr; int i; for (i = 0; i < priv->num_exprs; i++) { expr = nft_setelem_expr_at(elem_expr, elem_expr->size); if (nft_expr_clone(expr, priv->expr_array[i], GFP_ATOMIC) < 0) return -1; elem_expr->size += priv->expr_array[i]->ops->size; } return 0; } struct nft_elem_priv *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, struct nft_regs *regs) { const struct nft_dynset *priv = nft_expr_priv(expr); struct nft_set_ext *ext; void *elem_priv; u64 timeout; if (!atomic_add_unless(&set->nelems, 1, set->size)) return NULL; timeout = priv->timeout ? : READ_ONCE(set->timeout); elem_priv = nft_set_elem_init(set, &priv->tmpl, ®s->data[priv->sreg_key], NULL, ®s->data[priv->sreg_data], timeout, 0, GFP_ATOMIC); if (IS_ERR(elem_priv)) goto err1; ext = nft_set_elem_ext(set, elem_priv); if (priv->num_exprs && nft_dynset_expr_setup(priv, ext) < 0) goto err2; return elem_priv; err2: nft_set_elem_destroy(set, elem_priv, false); err1: if (set->size) atomic_dec(&set->nelems); return NULL; } void nft_dynset_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_dynset *priv = nft_expr_priv(expr); struct nft_set *set = priv->set; const struct nft_set_ext *ext; u64 timeout; if (priv->op == NFT_DYNSET_OP_DELETE) { set->ops->delete(set, ®s->data[priv->sreg_key]); return; } ext = set->ops->update(set, ®s->data[priv->sreg_key], expr, regs); if (ext) { if (priv->op == NFT_DYNSET_OP_UPDATE && nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && READ_ONCE(nft_set_ext_timeout(ext)->timeout) != 0) { timeout = priv->timeout ? : READ_ONCE(set->timeout); WRITE_ONCE(nft_set_ext_timeout(ext)->expiration, get_jiffies_64() + timeout); } nft_set_elem_update_expr(ext, regs, pkt); if (priv->invert) regs->verdict.code = NFT_BREAK; return; } if (!priv->invert) regs->verdict.code = NFT_BREAK; } static void nft_dynset_ext_add_expr(struct nft_dynset *priv) { u8 size = 0; int i; for (i = 0; i < priv->num_exprs; i++) size += priv->expr_array[i]->ops->size; nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_EXPRESSIONS, sizeof(struct nft_set_elem_expr) + size); } static struct nft_expr * nft_dynset_expr_alloc(const struct nft_ctx *ctx, const struct nft_set *set, const struct nlattr *attr, int pos) { struct nft_expr *expr; int err; expr = nft_set_elem_expr_alloc(ctx, set, attr); if (IS_ERR(expr)) return expr; if (set->exprs[pos] && set->exprs[pos]->ops != expr->ops) { err = -EOPNOTSUPP; goto err_dynset_expr; } return expr; err_dynset_expr: nft_expr_destroy(ctx, expr); return ERR_PTR(err); } static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = { [NFTA_DYNSET_SET_NAME] = { .type = NLA_STRING, .len = NFT_SET_MAXNAMELEN - 1 }, [NFTA_DYNSET_SET_ID] = { .type = NLA_U32 }, [NFTA_DYNSET_OP] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_DYNSET_SREG_KEY] = { .type = NLA_U32 }, [NFTA_DYNSET_SREG_DATA] = { .type = NLA_U32 }, [NFTA_DYNSET_TIMEOUT] = { .type = NLA_U64 }, [NFTA_DYNSET_EXPR] = { .type = NLA_NESTED }, [NFTA_DYNSET_FLAGS] = { .type = NLA_U32 }, [NFTA_DYNSET_EXPRESSIONS] = { .type = NLA_NESTED }, }; static int nft_dynset_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct nft_dynset *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_set *set; u64 timeout; int err, i; lockdep_assert_held(&nft_net->commit_mutex); if (tb[NFTA_DYNSET_SET_NAME] == NULL || tb[NFTA_DYNSET_OP] == NULL || tb[NFTA_DYNSET_SREG_KEY] == NULL) return -EINVAL; if (tb[NFTA_DYNSET_FLAGS]) { u32 flags = ntohl(nla_get_be32(tb[NFTA_DYNSET_FLAGS])); if (flags & ~(NFT_DYNSET_F_INV | NFT_DYNSET_F_EXPR)) return -EOPNOTSUPP; if (flags & NFT_DYNSET_F_INV) priv->invert = true; if (flags & NFT_DYNSET_F_EXPR) priv->expr = true; } set = nft_set_lookup_global(ctx->net, ctx->table, tb[NFTA_DYNSET_SET_NAME], tb[NFTA_DYNSET_SET_ID], genmask); if (IS_ERR(set)) return PTR_ERR(set); if (set->flags & NFT_SET_OBJECT) return -EOPNOTSUPP; if (set->ops->update == NULL) return -EOPNOTSUPP; if (set->flags & NFT_SET_CONSTANT) return -EBUSY; priv->op = ntohl(nla_get_be32(tb[NFTA_DYNSET_OP])); if (priv->op > NFT_DYNSET_OP_DELETE) return -EOPNOTSUPP; timeout = 0; if (tb[NFTA_DYNSET_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EOPNOTSUPP; err = nf_msecs_to_jiffies64(tb[NFTA_DYNSET_TIMEOUT], &timeout); if (err) return err; } err = nft_parse_register_load(ctx, tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key, set->klen); if (err < 0) return err; if (tb[NFTA_DYNSET_SREG_DATA] != NULL) { if (!(set->flags & NFT_SET_MAP)) return -EOPNOTSUPP; if (set->dtype == NFT_DATA_VERDICT) return -EOPNOTSUPP; err = nft_parse_register_load(ctx, tb[NFTA_DYNSET_SREG_DATA], &priv->sreg_data, set->dlen); if (err < 0) return err; } else if (set->flags & NFT_SET_MAP) return -EINVAL; if ((tb[NFTA_DYNSET_EXPR] || tb[NFTA_DYNSET_EXPRESSIONS]) && !(set->flags & NFT_SET_EVAL)) return -EINVAL; if (tb[NFTA_DYNSET_EXPR]) { struct nft_expr *dynset_expr; dynset_expr = nft_dynset_expr_alloc(ctx, set, tb[NFTA_DYNSET_EXPR], 0); if (IS_ERR(dynset_expr)) return PTR_ERR(dynset_expr); priv->num_exprs++; priv->expr_array[0] = dynset_expr; if (set->num_exprs > 1 || (set->num_exprs == 1 && dynset_expr->ops != set->exprs[0]->ops)) { err = -EOPNOTSUPP; goto err_expr_free; } } else if (tb[NFTA_DYNSET_EXPRESSIONS]) { struct nft_expr *dynset_expr; struct nlattr *tmp; int left; if (!priv->expr) return -EINVAL; i = 0; nla_for_each_nested(tmp, tb[NFTA_DYNSET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { err = -E2BIG; goto err_expr_free; } if (nla_type(tmp) != NFTA_LIST_ELEM) { err = -EINVAL; goto err_expr_free; } dynset_expr = nft_dynset_expr_alloc(ctx, set, tmp, i); if (IS_ERR(dynset_expr)) { err = PTR_ERR(dynset_expr); goto err_expr_free; } priv->expr_array[i] = dynset_expr; priv->num_exprs++; if (set->num_exprs) { if (i >= set->num_exprs) { err = -EINVAL; goto err_expr_free; } if (dynset_expr->ops != set->exprs[i]->ops) { err = -EOPNOTSUPP; goto err_expr_free; } } i++; } if (set->num_exprs && set->num_exprs != i) { err = -EOPNOTSUPP; goto err_expr_free; } } else if (set->num_exprs > 0) { err = nft_set_elem_expr_clone(ctx, set, priv->expr_array); if (err < 0) return err; priv->num_exprs = set->num_exprs; } nft_set_ext_prepare(&priv->tmpl); nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_KEY, set->klen); if (set->flags & NFT_SET_MAP) nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_DATA, set->dlen); if (priv->num_exprs) nft_dynset_ext_add_expr(priv); if (set->flags & NFT_SET_TIMEOUT && (timeout || READ_ONCE(set->timeout))) nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_TIMEOUT); priv->timeout = timeout; err = nf_tables_bind_set(ctx, set, &priv->binding); if (err < 0) goto err_expr_free; if (set->size == 0) set->size = 0xffff; priv->set = set; return 0; err_expr_free: for (i = 0; i < priv->num_exprs; i++) nft_expr_destroy(ctx, priv->expr_array[i]); return err; } static void nft_dynset_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { struct nft_dynset *priv = nft_expr_priv(expr); nf_tables_deactivate_set(ctx, priv->set, &priv->binding, phase); } static void nft_dynset_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_dynset *priv = nft_expr_priv(expr); nf_tables_activate_set(ctx, priv->set); } static void nft_dynset_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_dynset *priv = nft_expr_priv(expr); int i; for (i = 0; i < priv->num_exprs; i++) nft_expr_destroy(ctx, priv->expr_array[i]); nf_tables_destroy_set(ctx, priv->set); } static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_dynset *priv = nft_expr_priv(expr); u32 flags = priv->invert ? NFT_DYNSET_F_INV : 0; int i; if (nft_dump_register(skb, NFTA_DYNSET_SREG_KEY, priv->sreg_key)) goto nla_put_failure; if (priv->set->flags & NFT_SET_MAP && nft_dump_register(skb, NFTA_DYNSET_SREG_DATA, priv->sreg_data)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_DYNSET_OP, htonl(priv->op))) goto nla_put_failure; if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, nf_jiffies64_to_msecs(priv->timeout), NFTA_DYNSET_PAD)) goto nla_put_failure; if (priv->set->num_exprs == 0) { if (priv->num_exprs == 1) { if (nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr_array[0], reset)) goto nla_put_failure; } else if (priv->num_exprs > 1) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, NFTA_DYNSET_EXPRESSIONS); if (!nest) goto nla_put_failure; for (i = 0; i < priv->num_exprs; i++) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, priv->expr_array[i], reset)) goto nla_put_failure; } nla_nest_end(skb, nest); } } if (nla_put_be32(skb, NFTA_DYNSET_FLAGS, htonl(flags))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static const struct nft_expr_ops nft_dynset_ops = { .type = &nft_dynset_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_dynset)), .eval = nft_dynset_eval, .init = nft_dynset_init, .destroy = nft_dynset_destroy, .activate = nft_dynset_activate, .deactivate = nft_dynset_deactivate, .dump = nft_dynset_dump, .reduce = NFT_REDUCE_READONLY, }; struct nft_expr_type nft_dynset_type __read_mostly = { .name = "dynset", .ops = &nft_dynset_ops, .policy = nft_dynset_policy, .maxattr = NFTA_DYNSET_MAX, .owner = THIS_MODULE, }; |
| 15 101 46 6 3 116 65 1 30 30 21 21 7 8 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_UDP_TUNNEL_H #define __NET_UDP_TUNNEL_H #include <net/ip_tunnels.h> #include <net/udp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ipv6_stubs.h> #endif struct udp_port_cfg { u8 family; /* Used only for kernel-created sockets */ union { struct in_addr local_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr local_ip6; #endif }; union { struct in_addr peer_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr peer_ip6; #endif }; __be16 local_udp_port; __be16 peer_udp_port; int bind_ifindex; unsigned int use_udp_checksums:1, use_udp6_tx_checksums:1, use_udp6_rx_checksums:1, ipv6_v6only:1; }; int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #if IS_ENABLED(CONFIG_IPV6) int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #else static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { return 0; } #endif static inline int udp_sock_create(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { if (cfg->family == AF_INET) return udp_sock_create4(net, cfg, sockp); if (cfg->family == AF_INET6) return udp_sock_create6(net, cfg, sockp); return -EPFNOSUPPORT; } typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, struct sk_buff *skb); typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb, int nhoff); struct udp_tunnel_sock_cfg { void *sk_user_data; /* user data used by encap_rcv call back */ /* Used for setting up udp_sock fields, see udp.h for details */ __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; udp_tunnel_encap_err_lookup_t encap_err_lookup; udp_tunnel_encap_err_rcv_t encap_err_rcv; udp_tunnel_encap_destroy_t encap_destroy; udp_tunnel_gro_receive_t gro_receive; udp_tunnel_gro_complete_t gro_complete; }; /* Setup the given (UDP) sock to receive UDP encapsulated packets */ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); /* -- List of parsable UDP tunnel types -- * * Adding to this list will result in serious debate. The main issue is * that this list is essentially a list of workarounds for either poorly * designed tunnels, or poorly designed device offloads. * * The parsing supported via these types should really be used for Rx * traffic only as the network stack will have already inserted offsets for * the location of the headers in the skb. In addition any ports that are * pushed should be kept within the namespace without leaking to other * devices such as VFs or other ports on the same device. * * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the * need to use this for Rx checksum offload. It should not be necessary to * call this function to perform Tx offloads on outgoing traffic. */ enum udp_parsable_tunnel_type { UDP_TUNNEL_TYPE_VXLAN = BIT(0), /* RFC 7348 */ UDP_TUNNEL_TYPE_GENEVE = BIT(1), /* draft-ietf-nvo3-geneve */ UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */ }; struct udp_tunnel_info { unsigned short type; sa_family_t sa_family; __be16 port; u8 hw_priv; }; /* Notify network devices of offloadable types */ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck, u16 ipcb_flags); void udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck, u16 ip6cb_flags); void udp_tunnel_sock_release(struct socket *sock); struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, int oif, __be32 *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 tos, struct dst_cache *dst_cache); struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, struct socket *sock, int oif, struct in6_addr *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 dsfield, struct dst_cache *dst_cache); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, const unsigned long *flags, __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; return iptunnel_handle_offloads(skb, type); } #endif #if IS_ENABLED(CONFIG_NET_UDP_TUNNEL) void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add); void udp_tunnel_update_gro_rcv(struct sock *sk, bool add); #else static inline void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add) {} static inline void udp_tunnel_update_gro_rcv(struct sock *sk, bool add) {} #endif static inline void udp_tunnel_cleanup_gro(struct sock *sk) { udp_tunnel_update_gro_rcv(sk, false); udp_tunnel_update_gro_lookup(sock_net(sk), sk, false); } static inline void udp_tunnel_encap_enable(struct sock *sk) { if (udp_test_and_set_bit(ENCAP_ENABLED, sk)) return; #if IS_ENABLED(CONFIG_IPV6) if (READ_ONCE(sk->sk_family) == PF_INET6) ipv6_stub->udpv6_encap_enable(); #endif udp_encap_enable(); } #define UDP_TUNNEL_NIC_MAX_TABLES 4 enum udp_tunnel_nic_info_flags { /* Device only supports offloads when it's open, all ports * will be removed before close and re-added after open. */ UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(0), /* Device supports only IPv4 tunnels */ UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(1), /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN. * This port must not be counted towards n_entries of any table. * Driver will not receive any callback associated with port 4789. */ UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(2), }; struct udp_tunnel_nic; #define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2) struct udp_tunnel_nic_shared { struct udp_tunnel_nic *udp_tunnel_nic_info; struct list_head devices; }; struct udp_tunnel_nic_shared_node { struct net_device *dev; struct list_head list; }; /** * struct udp_tunnel_nic_info - driver UDP tunnel offload information * @set_port: callback for adding a new port * @unset_port: callback for removing a port * @sync_table: callback for syncing the entire port table at once * @shared: reference to device global state (optional) * @flags: device flags from enum udp_tunnel_nic_info_flags * @tables: UDP port tables this device has * @tables.n_entries: number of entries in this table * @tables.tunnel_types: types of tunnels this table accepts * * Drivers are expected to provide either @set_port and @unset_port callbacks * or the @sync_table callback. Callbacks are invoked with rtnl lock held. * * Devices which (misguidedly) share the UDP tunnel port table across multiple * netdevs should allocate an instance of struct udp_tunnel_nic_shared and * point @shared at it. * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices * sharing a table. * * Known limitations: * - UDP tunnel port notifications are fundamentally best-effort - * it is likely the driver will both see skbs which use a UDP tunnel port, * while not being a tunneled skb, and tunnel skbs from other ports - * drivers should only use these ports for non-critical RX-side offloads, * e.g. the checksum offload; * - none of the devices care about the socket family at present, so we don't * track it. Please extend this code if you care. */ struct udp_tunnel_nic_info { /* one-by-one */ int (*set_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); int (*unset_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); /* all at once */ int (*sync_table)(struct net_device *dev, unsigned int table); struct udp_tunnel_nic_shared *shared; unsigned int flags; struct udp_tunnel_nic_table_info { unsigned int n_entries; unsigned int tunnel_types; } tables[UDP_TUNNEL_NIC_MAX_TABLES]; }; /* UDP tunnel module dependencies * * Tunnel drivers are expected to have a hard dependency on the udp_tunnel * module. NIC drivers are not, they just attach their * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come. * Loading a tunnel driver will cause the udp_tunnel module to be loaded * and only then will all the required state structures be allocated. * Since we want a weak dependency from the drivers and the core to udp_tunnel * we call things through the following stubs. */ struct udp_tunnel_nic_ops { void (*get_port)(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); void (*set_port_priv)(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv); void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*reset_ntf)(struct net_device *dev); size_t (*dump_size)(struct net_device *dev, unsigned int table); int (*dump_write)(struct net_device *dev, unsigned int table, struct sk_buff *skb); void (*assert_locked)(struct net_device *dev); void (*lock)(struct net_device *dev); void (*unlock)(struct net_device *dev); }; #ifdef CONFIG_INET extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops; #else #define udp_tunnel_nic_ops ((struct udp_tunnel_nic_ops *)NULL) #endif static inline void udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { /* This helper is used from .sync_table, we indicate empty entries * by zero'ed @ti. Drivers which need to know the details of a port * when it gets deleted should use the .set_port / .unset_port * callbacks. * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings. */ memset(ti, 0, sizeof(*ti)); if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->get_port(dev, table, idx, ti); } static inline void udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { if (udp_tunnel_nic_ops) { udp_tunnel_nic_ops->assert_locked(dev); udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv); } } static inline void udp_tunnel_nic_assert_locked(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->assert_locked(dev); } static inline void udp_tunnel_nic_lock(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->lock(dev); } static inline void udp_tunnel_nic_unlock(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->unlock(dev); } static inline void udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->add_port(dev, ti); } static inline void udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->del_port(dev, ti); } /** * udp_tunnel_nic_reset_ntf() - device-originating reset notification * @dev: network interface device structure * * Called by the driver to inform the core that the entire UDP tunnel port * state has been lost, usually due to device reset. Core will assume device * forgot all the ports and issue .set_port and .sync_table callbacks as * necessary. * * This function must be called with rtnl lock held, and will issue all * the callbacks before returning. */ static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->reset_ntf(dev); } static inline size_t udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { size_t ret; if (!udp_tunnel_nic_ops) return 0; udp_tunnel_nic_ops->lock(dev); ret = udp_tunnel_nic_ops->dump_size(dev, table); udp_tunnel_nic_ops->unlock(dev); return ret; } static inline int udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { int ret; if (!udp_tunnel_nic_ops) return 0; udp_tunnel_nic_ops->lock(dev); ret = udp_tunnel_nic_ops->dump_write(dev, table, skb); udp_tunnel_nic_ops->unlock(dev); return ret; } static inline void udp_tunnel_get_rx_info(struct net_device *dev) { ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; udp_tunnel_nic_assert_locked(dev); call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); } static inline void udp_tunnel_drop_rx_info(struct net_device *dev) { ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; udp_tunnel_nic_assert_locked(dev); call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); } #endif |
| 16 20 105 111 111 111 114 26 83 3 20 91 81 31 11 100 111 111 92 19 111 37 73 90 20 26 85 19 92 26 85 111 35 76 111 111 111 26 81 3 85 85 6 6 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to setting various queue properties from drivers */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bio.h> #include <linux/blk-integrity.h> #include <linux/pagemap.h> #include <linux/backing-dev-defs.h> #include <linux/gcd.h> #include <linux/lcm.h> #include <linux/jiffies.h> #include <linux/gfp.h> #include <linux/dma-mapping.h> #include <linux/t10-pi.h> #include <linux/crc64.h> #include "blk.h" #include "blk-rq-qos.h" #include "blk-wbt.h" void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout) { WRITE_ONCE(q->rq_timeout, timeout); } EXPORT_SYMBOL_GPL(blk_queue_rq_timeout); /** * blk_set_stacking_limits - set default limits for stacking devices * @lim: the queue_limits structure to reset * * Prepare queue limits for applying limits from underlying devices using * blk_stack_limits(). */ void blk_set_stacking_limits(struct queue_limits *lim) { memset(lim, 0, sizeof(*lim)); lim->logical_block_size = SECTOR_SIZE; lim->physical_block_size = SECTOR_SIZE; lim->io_min = SECTOR_SIZE; lim->discard_granularity = SECTOR_SIZE; lim->dma_alignment = SECTOR_SIZE - 1; lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; /* Inherit limits from component devices */ lim->max_segments = USHRT_MAX; lim->max_discard_segments = USHRT_MAX; lim->max_hw_sectors = UINT_MAX; lim->max_segment_size = UINT_MAX; lim->max_sectors = UINT_MAX; lim->max_dev_sectors = UINT_MAX; lim->max_write_zeroes_sectors = UINT_MAX; lim->max_hw_wzeroes_unmap_sectors = UINT_MAX; lim->max_user_wzeroes_unmap_sectors = UINT_MAX; lim->max_hw_zone_append_sectors = UINT_MAX; lim->max_user_discard_sectors = UINT_MAX; lim->atomic_write_hw_max = UINT_MAX; } EXPORT_SYMBOL(blk_set_stacking_limits); void blk_apply_bdi_limits(struct backing_dev_info *bdi, struct queue_limits *lim) { u64 io_opt = lim->io_opt; /* * For read-ahead of large files to be effective, we need to read ahead * at least twice the optimal I/O size. For rotational devices that do * not report an optimal I/O size (e.g. ATA HDDs), use the maximum I/O * size to avoid falling back to the (rather inefficient) small default * read-ahead size. * * There is no hardware limitation for the read-ahead size and the user * might have increased the read-ahead size through sysfs, so don't ever * decrease it. */ if (!io_opt && (lim->features & BLK_FEAT_ROTATIONAL)) io_opt = (u64)lim->max_sectors << SECTOR_SHIFT; bdi->ra_pages = max3(bdi->ra_pages, io_opt * 2 >> PAGE_SHIFT, VM_READAHEAD_PAGES); bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT; } static int blk_validate_zoned_limits(struct queue_limits *lim) { if (!(lim->features & BLK_FEAT_ZONED)) { if (WARN_ON_ONCE(lim->max_open_zones) || WARN_ON_ONCE(lim->max_active_zones) || WARN_ON_ONCE(lim->zone_write_granularity) || WARN_ON_ONCE(lim->max_zone_append_sectors)) return -EINVAL; return 0; } if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED))) return -EINVAL; /* * Given that active zones include open zones, the maximum number of * open zones cannot be larger than the maximum number of active zones. */ if (lim->max_active_zones && lim->max_open_zones > lim->max_active_zones) return -EINVAL; if (lim->zone_write_granularity < lim->logical_block_size) lim->zone_write_granularity = lim->logical_block_size; /* * The Zone Append size is limited by the maximum I/O size and the zone * size given that it can't span zones. * * If no max_hw_zone_append_sectors limit is provided, the block layer * will emulated it, else we're also bound by the hardware limit. */ lim->max_zone_append_sectors = min_not_zero(lim->max_hw_zone_append_sectors, min(lim->chunk_sectors, lim->max_hw_sectors)); return 0; } static int blk_validate_integrity_limits(struct queue_limits *lim) { struct blk_integrity *bi = &lim->integrity; if (!bi->metadata_size) { if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE || bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) { pr_warn("invalid PI settings.\n"); return -EINVAL; } bi->flags |= BLK_INTEGRITY_NOGENERATE | BLK_INTEGRITY_NOVERIFY; return 0; } if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) { pr_warn("integrity support disabled.\n"); return -EINVAL; } if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE && (bi->flags & BLK_INTEGRITY_REF_TAG)) { pr_warn("ref tag not support without checksum.\n"); return -EINVAL; } if (bi->pi_tuple_size > bi->metadata_size) { pr_warn("pi_tuple_size (%u) exceeds metadata_size (%u)\n", bi->pi_tuple_size, bi->metadata_size); return -EINVAL; } switch (bi->csum_type) { case BLK_INTEGRITY_CSUM_NONE: if (bi->pi_tuple_size) { pr_warn("pi_tuple_size must be 0 when checksum type is none\n"); return -EINVAL; } break; case BLK_INTEGRITY_CSUM_CRC: case BLK_INTEGRITY_CSUM_IP: if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) { pr_warn("pi_tuple_size mismatch for T10 PI: expected %zu, got %u\n", sizeof(struct t10_pi_tuple), bi->pi_tuple_size); return -EINVAL; } break; case BLK_INTEGRITY_CSUM_CRC64: if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) { pr_warn("pi_tuple_size mismatch for CRC64 PI: expected %zu, got %u\n", sizeof(struct crc64_pi_tuple), bi->pi_tuple_size); return -EINVAL; } break; } if (!bi->interval_exp) bi->interval_exp = ilog2(lim->logical_block_size); /* * The PI generation / validation helpers do not expect intervals to * straddle multiple bio_vecs. Enforce alignment so that those are * never generated, and that each buffer is aligned as expected. */ if (bi->csum_type) { lim->dma_alignment = max(lim->dma_alignment, (1U << bi->interval_exp) - 1); } return 0; } /* * Returns max guaranteed bytes which we can fit in a bio. * * We request that an atomic_write is ITER_UBUF iov_iter (so a single vector), * so we assume that we can fit in at least PAGE_SIZE in a segment, apart from * the first and last segments. */ static unsigned int blk_queue_max_guaranteed_bio(struct queue_limits *lim) { unsigned int max_segments = min(BIO_MAX_VECS, lim->max_segments); unsigned int length; length = min(max_segments, 2) * lim->logical_block_size; if (max_segments > 2) length += (max_segments - 2) * PAGE_SIZE; return length; } static void blk_atomic_writes_update_limits(struct queue_limits *lim) { unsigned int unit_limit = min(lim->max_hw_sectors << SECTOR_SHIFT, blk_queue_max_guaranteed_bio(lim)); unit_limit = rounddown_pow_of_two(unit_limit); lim->atomic_write_max_sectors = min(lim->atomic_write_hw_max >> SECTOR_SHIFT, lim->max_hw_sectors); lim->atomic_write_unit_min = min(lim->atomic_write_hw_unit_min, unit_limit); lim->atomic_write_unit_max = min(lim->atomic_write_hw_unit_max, unit_limit); lim->atomic_write_boundary_sectors = lim->atomic_write_hw_boundary >> SECTOR_SHIFT; } /* * Test whether any boundary is aligned with any chunk size. Stacked * devices store any stripe size in t->chunk_sectors. */ static bool blk_valid_atomic_writes_boundary(unsigned int chunk_sectors, unsigned int boundary_sectors) { if (!chunk_sectors || !boundary_sectors) return true; if (boundary_sectors > chunk_sectors && boundary_sectors % chunk_sectors) return false; if (chunk_sectors > boundary_sectors && chunk_sectors % boundary_sectors) return false; return true; } static void blk_validate_atomic_write_limits(struct queue_limits *lim) { unsigned int boundary_sectors; unsigned int atomic_write_hw_max_sectors = lim->atomic_write_hw_max >> SECTOR_SHIFT; if (!(lim->features & BLK_FEAT_ATOMIC_WRITES)) goto unsupported; /* UINT_MAX indicates stacked limits in initial state */ if (lim->atomic_write_hw_max == UINT_MAX) goto unsupported; if (!lim->atomic_write_hw_max) goto unsupported; if (WARN_ON_ONCE(!is_power_of_2(lim->atomic_write_hw_unit_min))) goto unsupported; if (WARN_ON_ONCE(!is_power_of_2(lim->atomic_write_hw_unit_max))) goto unsupported; if (WARN_ON_ONCE(lim->atomic_write_hw_unit_min > lim->atomic_write_hw_unit_max)) goto unsupported; if (WARN_ON_ONCE(lim->atomic_write_hw_unit_max > lim->atomic_write_hw_max)) goto unsupported; if (WARN_ON_ONCE(lim->chunk_sectors && atomic_write_hw_max_sectors > lim->chunk_sectors)) goto unsupported; boundary_sectors = lim->atomic_write_hw_boundary >> SECTOR_SHIFT; if (boundary_sectors) { if (WARN_ON_ONCE(lim->atomic_write_hw_max > lim->atomic_write_hw_boundary)) goto unsupported; if (WARN_ON_ONCE(!blk_valid_atomic_writes_boundary( lim->chunk_sectors, boundary_sectors))) goto unsupported; /* * The boundary size just needs to be a multiple of unit_max * (and not necessarily a power-of-2), so this following check * could be relaxed in future. * Furthermore, if needed, unit_max could even be reduced so * that it is compliant with a !power-of-2 boundary. */ if (!is_power_of_2(boundary_sectors)) goto unsupported; } blk_atomic_writes_update_limits(lim); return; unsupported: lim->atomic_write_max_sectors = 0; lim->atomic_write_boundary_sectors = 0; lim->atomic_write_unit_min = 0; lim->atomic_write_unit_max = 0; } /* * Check that the limits in lim are valid, initialize defaults for unset * values, and cap values based on others where needed. */ int blk_validate_limits(struct queue_limits *lim) { unsigned int max_hw_sectors; unsigned int logical_block_sectors; unsigned long seg_size; int err; /* * Unless otherwise specified, default to 512 byte logical blocks and a * physical block size equal to the logical block size. */ if (!lim->logical_block_size) lim->logical_block_size = SECTOR_SIZE; else if (blk_validate_block_size(lim->logical_block_size)) { pr_warn("Invalid logical block size (%d)\n", lim->logical_block_size); return -EINVAL; } if (lim->physical_block_size < lim->logical_block_size) { lim->physical_block_size = lim->logical_block_size; } else if (!is_power_of_2(lim->physical_block_size)) { pr_warn("Invalid physical block size (%d)\n", lim->physical_block_size); return -EINVAL; } /* * The minimum I/O size defaults to the physical block size unless * explicitly overridden. */ if (lim->io_min < lim->physical_block_size) lim->io_min = lim->physical_block_size; /* * The optimal I/O size may not be aligned to physical block size * (because it may be limited by dma engines which have no clue about * block size of the disks attached to them), so we round it down here. */ lim->io_opt = round_down(lim->io_opt, lim->physical_block_size); /* * max_hw_sectors has a somewhat weird default for historical reason, * but driver really should set their own instead of relying on this * value. * * The block layer relies on the fact that every driver can * handle at lest a page worth of data per I/O, and needs the value * aligned to the logical block size. */ if (!lim->max_hw_sectors) lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS; if (WARN_ON_ONCE(lim->max_hw_sectors < PAGE_SECTORS)) return -EINVAL; logical_block_sectors = lim->logical_block_size >> SECTOR_SHIFT; if (WARN_ON_ONCE(logical_block_sectors > lim->max_hw_sectors)) return -EINVAL; lim->max_hw_sectors = round_down(lim->max_hw_sectors, logical_block_sectors); /* * The actual max_sectors value is a complex beast and also takes the * max_dev_sectors value (set by SCSI ULPs) and a user configurable * value into account. The ->max_sectors value is always calculated * from these, so directly setting it won't have any effect. */ max_hw_sectors = min_not_zero(lim->max_hw_sectors, lim->max_dev_sectors); if (lim->max_user_sectors) { if (lim->max_user_sectors < BLK_MIN_SEGMENT_SIZE / SECTOR_SIZE) return -EINVAL; lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors); } else if (lim->io_opt > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) { lim->max_sectors = min(max_hw_sectors, lim->io_opt >> SECTOR_SHIFT); } else if (lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) { lim->max_sectors = min(max_hw_sectors, lim->io_min >> SECTOR_SHIFT); } else { lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP); } lim->max_sectors = round_down(lim->max_sectors, logical_block_sectors); /* * Random default for the maximum number of segments. Driver should not * rely on this and set their own. */ if (!lim->max_segments) lim->max_segments = BLK_MAX_SEGMENTS; if (lim->max_hw_wzeroes_unmap_sectors && lim->max_hw_wzeroes_unmap_sectors != lim->max_write_zeroes_sectors) return -EINVAL; lim->max_wzeroes_unmap_sectors = min(lim->max_hw_wzeroes_unmap_sectors, lim->max_user_wzeroes_unmap_sectors); lim->max_discard_sectors = min(lim->max_hw_discard_sectors, lim->max_user_discard_sectors); /* * When discard is not supported, discard_granularity should be reported * as 0 to userspace. */ if (lim->max_discard_sectors) lim->discard_granularity = max(lim->discard_granularity, lim->physical_block_size); else lim->discard_granularity = 0; if (!lim->max_discard_segments) lim->max_discard_segments = 1; /* * By default there is no limit on the segment boundary alignment, * but if there is one it can't be smaller than the page size as * that would break all the normal I/O patterns. */ if (!lim->seg_boundary_mask) lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; if (WARN_ON_ONCE(lim->seg_boundary_mask < BLK_MIN_SEGMENT_SIZE - 1)) return -EINVAL; /* * Stacking device may have both virtual boundary and max segment * size limit, so allow this setting now, and long-term the two * might need to move out of stacking limits since we have immutable * bvec and lower layer bio splitting is supposed to handle the two * correctly. */ if (lim->virt_boundary_mask) { if (!lim->max_segment_size) lim->max_segment_size = UINT_MAX; } else { /* * The maximum segment size has an odd historic 64k default that * drivers probably should override. Just like the I/O size we * require drivers to at least handle a full page per segment. */ if (!lim->max_segment_size) lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; if (WARN_ON_ONCE(lim->max_segment_size < BLK_MIN_SEGMENT_SIZE)) return -EINVAL; } /* setup min segment size for building new segment in fast path */ if (lim->seg_boundary_mask > lim->max_segment_size - 1) seg_size = lim->max_segment_size; else seg_size = lim->seg_boundary_mask + 1; lim->min_segment_size = min_t(unsigned int, seg_size, PAGE_SIZE); /* * We require drivers to at least do logical block aligned I/O, but * historically could not check for that due to the separate calls * to set the limits. Once the transition is finished the check * below should be narrowed down to check the logical block size. */ if (!lim->dma_alignment) lim->dma_alignment = SECTOR_SIZE - 1; if (WARN_ON_ONCE(lim->dma_alignment > PAGE_SIZE)) return -EINVAL; if (lim->alignment_offset) { lim->alignment_offset &= (lim->physical_block_size - 1); lim->flags &= ~BLK_FLAG_MISALIGNED; } if (!(lim->features & BLK_FEAT_WRITE_CACHE)) lim->features &= ~BLK_FEAT_FUA; blk_validate_atomic_write_limits(lim); err = blk_validate_integrity_limits(lim); if (err) return err; return blk_validate_zoned_limits(lim); } EXPORT_SYMBOL_GPL(blk_validate_limits); /* * Set the default limits for a newly allocated queue. @lim contains the * initial limits set by the driver, which could be no limit in which case * all fields are cleared to zero. */ int blk_set_default_limits(struct queue_limits *lim) { /* * Most defaults are set by capping the bounds in blk_validate_limits, * but these limits are special and need an explicit initialization to * the max value here. */ lim->max_user_discard_sectors = UINT_MAX; lim->max_user_wzeroes_unmap_sectors = UINT_MAX; return blk_validate_limits(lim); } /** * queue_limits_commit_update - commit an atomic update of queue limits * @q: queue to update * @lim: limits to apply * * Apply the limits in @lim that were obtained from queue_limits_start_update() * and updated by the caller to @q. The caller must have frozen the queue or * ensure that there are no outstanding I/Os by other means. * * Returns 0 if successful, else a negative error code. */ int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim) { int error; error = blk_validate_limits(lim); if (error) goto out_unlock; #ifdef CONFIG_BLK_INLINE_ENCRYPTION if (q->crypto_profile && lim->integrity.tag_size) { pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together.\n"); error = -EINVAL; goto out_unlock; } #endif q->limits = *lim; if (q->disk) blk_apply_bdi_limits(q->disk->bdi, lim); out_unlock: mutex_unlock(&q->limits_lock); return error; } EXPORT_SYMBOL_GPL(queue_limits_commit_update); /** * queue_limits_commit_update_frozen - commit an atomic update of queue limits * @q: queue to update * @lim: limits to apply * * Apply the limits in @lim that were obtained from queue_limits_start_update() * and updated with the new values by the caller to @q. Freezes the queue * before the update and unfreezes it after. * * Returns 0 if successful, else a negative error code. */ int queue_limits_commit_update_frozen(struct request_queue *q, struct queue_limits *lim) { unsigned int memflags; int ret; memflags = blk_mq_freeze_queue(q); ret = queue_limits_commit_update(q, lim); blk_mq_unfreeze_queue(q, memflags); return ret; } EXPORT_SYMBOL_GPL(queue_limits_commit_update_frozen); /** * queue_limits_set - apply queue limits to queue * @q: queue to update * @lim: limits to apply * * Apply the limits in @lim that were freshly initialized to @q. * To update existing limits use queue_limits_start_update() and * queue_limits_commit_update() instead. * * Returns 0 if successful, else a negative error code. */ int queue_limits_set(struct request_queue *q, struct queue_limits *lim) { mutex_lock(&q->limits_lock); return queue_limits_commit_update(q, lim); } EXPORT_SYMBOL_GPL(queue_limits_set); static int queue_limit_alignment_offset(const struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) << SECTOR_SHIFT; return (granularity + lim->alignment_offset - alignment) % granularity; } static unsigned int queue_limit_discard_alignment( const struct queue_limits *lim, sector_t sector) { unsigned int alignment, granularity, offset; if (!lim->max_discard_sectors) return 0; /* Why are these in bytes, not sectors? */ alignment = lim->discard_alignment >> SECTOR_SHIFT; granularity = lim->discard_granularity >> SECTOR_SHIFT; /* Offset of the partition start in 'granularity' sectors */ offset = sector_div(sector, granularity); /* And why do we do this modulus *again* in blkdev_issue_discard()? */ offset = (granularity + alignment - offset) % granularity; /* Turn it back into bytes, gaah */ return offset << SECTOR_SHIFT; } static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lbs) { sectors = round_down(sectors, lbs >> SECTOR_SHIFT); if (sectors < PAGE_SIZE >> SECTOR_SHIFT) sectors = PAGE_SIZE >> SECTOR_SHIFT; return sectors; } /* Check if second and later bottom devices are compliant */ static bool blk_stack_atomic_writes_tail(struct queue_limits *t, struct queue_limits *b) { /* We're not going to support different boundary sizes.. yet */ if (t->atomic_write_hw_boundary != b->atomic_write_hw_boundary) return false; /* Can't support this */ if (t->atomic_write_hw_unit_min > b->atomic_write_hw_unit_max) return false; /* Or this */ if (t->atomic_write_hw_unit_max < b->atomic_write_hw_unit_min) return false; t->atomic_write_hw_max = min(t->atomic_write_hw_max, b->atomic_write_hw_max); t->atomic_write_hw_unit_min = max(t->atomic_write_hw_unit_min, b->atomic_write_hw_unit_min); t->atomic_write_hw_unit_max = min(t->atomic_write_hw_unit_max, b->atomic_write_hw_unit_max); return true; } static void blk_stack_atomic_writes_chunk_sectors(struct queue_limits *t) { unsigned int chunk_bytes; if (!t->chunk_sectors) return; /* * If chunk sectors is so large that its value in bytes overflows * UINT_MAX, then just shift it down so it definitely will fit. * We don't support atomic writes of such a large size anyway. */ if (check_shl_overflow(t->chunk_sectors, SECTOR_SHIFT, &chunk_bytes)) chunk_bytes = t->chunk_sectors; /* * Find values for limits which work for chunk size. * b->atomic_write_hw_unit_{min, max} may not be aligned with chunk * size, as the chunk size is not restricted to a power-of-2. * So we need to find highest power-of-2 which works for the chunk * size. * As an example scenario, we could have t->unit_max = 16K and * t->chunk_sectors = 24KB. For this case, reduce t->unit_max to a * value aligned with both limits, i.e. 8K in this example. */ t->atomic_write_hw_unit_max = min(t->atomic_write_hw_unit_max, max_pow_of_two_factor(chunk_bytes)); t->atomic_write_hw_unit_min = min(t->atomic_write_hw_unit_min, t->atomic_write_hw_unit_max); t->atomic_write_hw_max = min(t->atomic_write_hw_max, chunk_bytes); } /* Check stacking of first bottom device */ static bool blk_stack_atomic_writes_head(struct queue_limits *t, struct queue_limits *b) { if (!blk_valid_atomic_writes_boundary(t->chunk_sectors, b->atomic_write_hw_boundary >> SECTOR_SHIFT)) return false; t->atomic_write_hw_unit_max = b->atomic_write_hw_unit_max; t->atomic_write_hw_unit_min = b->atomic_write_hw_unit_min; t->atomic_write_hw_max = b->atomic_write_hw_max; t->atomic_write_hw_boundary = b->atomic_write_hw_boundary; return true; } static void blk_stack_atomic_writes_limits(struct queue_limits *t, struct queue_limits *b, sector_t start) { if (!(b->features & BLK_FEAT_ATOMIC_WRITES)) goto unsupported; if (!b->atomic_write_hw_unit_min) goto unsupported; if (!blk_atomic_write_start_sect_aligned(start, b)) goto unsupported; /* UINT_MAX indicates no stacking of bottom devices yet */ if (t->atomic_write_hw_max == UINT_MAX) { if (!blk_stack_atomic_writes_head(t, b)) goto unsupported; } else { if (!blk_stack_atomic_writes_tail(t, b)) goto unsupported; } blk_stack_atomic_writes_chunk_sectors(t); return; unsupported: t->atomic_write_hw_max = 0; t->atomic_write_hw_unit_max = 0; t->atomic_write_hw_unit_min = 0; t->atomic_write_hw_boundary = 0; } /** * blk_stack_limits - adjust queue_limits for stacked devices * @t: the stacking driver limits (top device) * @b: the underlying queue limits (bottom, component device) * @start: first data sector within component device * * Description: * This function is used by stacking drivers like MD and DM to ensure * that all component devices have compatible block sizes and * alignments. The stacking driver must provide a queue_limits * struct (top) and then iteratively call the stacking function for * all component (bottom) devices. The stacking function will * attempt to combine the values and ensure proper alignment. * * Returns 0 if the top and bottom queue_limits are compatible. The * top device's block sizes and alignment offsets may be adjusted to * ensure alignment with the bottom device. If no compatible sizes * and alignments exist, -1 is returned and the resulting top * queue_limits will have the misaligned flag set to indicate that * the alignment_offset is undefined. */ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t start) { unsigned int top, bottom, alignment; int ret = 0; t->features |= (b->features & BLK_FEAT_INHERIT_MASK); /* * Some feaures need to be supported both by the stacking driver and all * underlying devices. The stacking driver sets these flags before * stacking the limits, and this will clear the flags if any of the * underlying devices does not support it. */ if (!(b->features & BLK_FEAT_NOWAIT)) t->features &= ~BLK_FEAT_NOWAIT; if (!(b->features & BLK_FEAT_POLL)) t->features &= ~BLK_FEAT_POLL; t->flags |= (b->flags & BLK_FLAG_MISALIGNED); t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors); t->max_user_sectors = min_not_zero(t->max_user_sectors, b->max_user_sectors); t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors); t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors); t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors, b->max_write_zeroes_sectors); t->max_user_wzeroes_unmap_sectors = min(t->max_user_wzeroes_unmap_sectors, b->max_user_wzeroes_unmap_sectors); t->max_hw_wzeroes_unmap_sectors = min(t->max_hw_wzeroes_unmap_sectors, b->max_hw_wzeroes_unmap_sectors); t->max_hw_zone_append_sectors = min(t->max_hw_zone_append_sectors, b->max_hw_zone_append_sectors); t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, b->seg_boundary_mask); t->virt_boundary_mask = min_not_zero(t->virt_boundary_mask, b->virt_boundary_mask); t->max_segments = min_not_zero(t->max_segments, b->max_segments); t->max_discard_segments = min_not_zero(t->max_discard_segments, b->max_discard_segments); t->max_integrity_segments = min_not_zero(t->max_integrity_segments, b->max_integrity_segments); t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size); alignment = queue_limit_alignment_offset(b, start); /* Bottom device has different alignment. Check that it is * compatible with the current top alignment. */ if (t->alignment_offset != alignment) { top = max(t->physical_block_size, t->io_min) + t->alignment_offset; bottom = max(b->physical_block_size, b->io_min) + alignment; /* Verify that top and bottom intervals line up */ if (max(top, bottom) % min(top, bottom)) { t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } } t->logical_block_size = max(t->logical_block_size, b->logical_block_size); t->physical_block_size = max(t->physical_block_size, b->physical_block_size); t->io_min = max(t->io_min, b->io_min); t->io_opt = lcm_not_zero(t->io_opt, b->io_opt); t->dma_alignment = max(t->dma_alignment, b->dma_alignment); /* Set non-power-of-2 compatible chunk_sectors boundary */ if (b->chunk_sectors) t->chunk_sectors = gcd(t->chunk_sectors, b->chunk_sectors); /* Physical block size a multiple of the logical block size? */ if (t->physical_block_size & (t->logical_block_size - 1)) { t->physical_block_size = t->logical_block_size; t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* Minimum I/O a multiple of the physical block size? */ if (t->io_min & (t->physical_block_size - 1)) { t->io_min = t->physical_block_size; t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* Optimal I/O a multiple of the physical block size? */ if (t->io_opt & (t->physical_block_size - 1)) { t->io_opt = 0; t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* chunk_sectors a multiple of the physical block size? */ if (t->chunk_sectors % (t->physical_block_size >> SECTOR_SHIFT)) { t->chunk_sectors = 0; t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } /* Find lowest common alignment_offset */ t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment) % max(t->physical_block_size, t->io_min); /* Verify that new alignment_offset is on a logical block boundary */ if (t->alignment_offset & (t->logical_block_size - 1)) { t->flags |= BLK_FLAG_MISALIGNED; ret = -1; } t->max_sectors = blk_round_down_sectors(t->max_sectors, t->logical_block_size); t->max_hw_sectors = blk_round_down_sectors(t->max_hw_sectors, t->logical_block_size); t->max_dev_sectors = blk_round_down_sectors(t->max_dev_sectors, t->logical_block_size); /* Discard alignment and granularity */ if (b->discard_granularity) { alignment = queue_limit_discard_alignment(b, start); t->max_discard_sectors = min_not_zero(t->max_discard_sectors, b->max_discard_sectors); t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors, b->max_hw_discard_sectors); t->discard_granularity = max(t->discard_granularity, b->discard_granularity); t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) % t->discard_granularity; } t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors, b->max_secure_erase_sectors); t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); if (!(t->features & BLK_FEAT_ZONED)) { t->zone_write_granularity = 0; t->max_zone_append_sectors = 0; } blk_stack_atomic_writes_limits(t, b, start); return ret; } EXPORT_SYMBOL(blk_stack_limits); /** * queue_limits_stack_bdev - adjust queue_limits for stacked devices * @t: the stacking driver limits (top device) * @bdev: the underlying block device (bottom) * @offset: offset to beginning of data within component device * @pfx: prefix to use for warnings logged * * Description: * This function is used by stacking drivers like MD and DM to ensure * that all component devices have compatible block sizes and * alignments. The stacking driver must provide a queue_limits * struct (top) and then iteratively call the stacking function for * all component (bottom) devices. The stacking function will * attempt to combine the values and ensure proper alignment. */ void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, sector_t offset, const char *pfx) { if (blk_stack_limits(t, bdev_limits(bdev), get_start_sect(bdev) + offset)) pr_notice("%s: Warning: Device %pg is misaligned\n", pfx, bdev); } EXPORT_SYMBOL_GPL(queue_limits_stack_bdev); /** * queue_limits_stack_integrity - stack integrity profile * @t: target queue limits * @b: base queue limits * * Check if the integrity profile in the @b can be stacked into the * target @t. Stacking is possible if either: * * a) does not have any integrity information stacked into it yet * b) the integrity profile in @b is identical to the one in @t * * If @b can be stacked into @t, return %true. Else return %false and clear the * integrity information in @t. */ bool queue_limits_stack_integrity(struct queue_limits *t, struct queue_limits *b) { struct blk_integrity *ti = &t->integrity; struct blk_integrity *bi = &b->integrity; if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) return true; if (ti->flags & BLK_INTEGRITY_STACKED) { if (ti->metadata_size != bi->metadata_size) goto incompatible; if (ti->interval_exp != bi->interval_exp) goto incompatible; if (ti->tag_size != bi->tag_size) goto incompatible; if (ti->csum_type != bi->csum_type) goto incompatible; if (ti->pi_tuple_size != bi->pi_tuple_size) goto incompatible; if ((ti->flags & BLK_INTEGRITY_REF_TAG) != (bi->flags & BLK_INTEGRITY_REF_TAG)) goto incompatible; } else { ti->flags = BLK_INTEGRITY_STACKED; ti->flags |= (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) | (bi->flags & BLK_INTEGRITY_REF_TAG); ti->csum_type = bi->csum_type; ti->pi_tuple_size = bi->pi_tuple_size; ti->metadata_size = bi->metadata_size; ti->pi_offset = bi->pi_offset; ti->interval_exp = bi->interval_exp; ti->tag_size = bi->tag_size; } return true; incompatible: memset(ti, 0, sizeof(*ti)); return false; } EXPORT_SYMBOL_GPL(queue_limits_stack_integrity); /** * blk_set_queue_depth - tell the block layer about the device queue depth * @q: the request queue for the device * @depth: queue depth * */ void blk_set_queue_depth(struct request_queue *q, unsigned int depth) { q->queue_depth = depth; rq_qos_queue_depth_changed(q); } EXPORT_SYMBOL(blk_set_queue_depth); int bdev_alignment_offset(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q->limits.flags & BLK_FLAG_MISALIGNED) return -1; if (bdev_is_partition(bdev)) return queue_limit_alignment_offset(&q->limits, bdev->bd_start_sect); return q->limits.alignment_offset; } EXPORT_SYMBOL_GPL(bdev_alignment_offset); unsigned int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (bdev_is_partition(bdev)) return queue_limit_discard_alignment(&q->limits, bdev->bd_start_sect); return q->limits.discard_alignment; } EXPORT_SYMBOL_GPL(bdev_discard_alignment); |
| 16 5 1 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 1 9 9 1 8 9 9 9 9 9 8 9 8 9 8 9 9 9 9 9 1 1 1 1 1 1 9 9 9 9 9 9 2 2 1 2 2 2 2 1 1 1 2 1 2 1 1 1 15 15 28 27 1 28 2 1 1 16 16 16 1 1 1 1 1 2 2 2 2 2 1 1 2 2 17 1 1 1 1 1 36 29 45 43 1 1 41 2 1 3 36 3 1 36 2 1 36 1 8 10 1 16 16 16 1 16 16 16 14 2 16 16 1 16 16 16 1 8 10 15 1 15 8 8 10 30 30 3 17 2 10 9 33 18 1 3 13 9 25 2 4 28 6 26 4 28 30 9 30 3 29 28 1 28 2 29 13 33 13 1 26 2 28 9 28 7 2 7 1 3 3 37 6 2 8 1 36 34 2 37 37 37 37 37 4 36 35 2 36 1 36 1 35 2 34 3 34 3 1 34 2 1 3 36 36 1 36 1 37 37 37 37 2 2 35 34 1 35 34 1 34 33 1 1 36 36 2 33 4 1 3 3 3 3 1 3 3 2 2 2 30 49 42 8 8 49 47 2 2 1 1 1 49 49 49 49 49 49 300 102 1411 1414 300 1 169 168 3 3 3 17 15 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 | // SPDX-License-Identifier: GPL-2.0-only /* * VXLAN: Virtual eXtensible Local Area Network * * Copyright (c) 2012-2013 Vyatta Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/udp.h> #include <linux/igmp.h> #include <linux/if_ether.h> #include <linux/ethtool.h> #include <linux/rhashtable.h> #include <net/arp.h> #include <net/ndisc.h> #include <net/gro.h> #include <net/ipv6_stubs.h> #include <net/ip.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netdev_lock.h> #include <net/tun_proto.h> #include <net/vxlan.h> #include <net/nexthop.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> #endif #include "vxlan_private.h" #define VXLAN_VERSION "0.1" #define FDB_AGE_DEFAULT 300 /* 5 min */ #define FDB_AGE_INTERVAL (10 * HZ) /* rescan interval */ /* UDP port for VXLAN traffic. * The IANA assigned port is 4789, but the Linux default is 8472 * for compatibility with early adopters. */ static unsigned short vxlan_port __read_mostly = 8472; module_param_named(udp_port, vxlan_port, ushort, 0444); MODULE_PARM_DESC(udp_port, "Destination UDP port"); 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"); unsigned int vxlan_net_id; const u8 all_zeros_mac[ETH_ALEN + 2]; static struct rtnl_link_ops vxlan_link_ops; static int vxlan_sock_add(struct vxlan_dev *vxlan); static void vxlan_vs_del_dev(struct vxlan_dev *vxlan); static const struct rhashtable_params vxlan_fdb_rht_params = { .head_offset = offsetof(struct vxlan_fdb, rhnode), .key_offset = offsetof(struct vxlan_fdb, key), .key_len = sizeof(struct vxlan_fdb_key), .automatic_shrinking = true, }; static inline bool vxlan_collect_metadata(struct vxlan_sock *vs) { return vs->flags & VXLAN_F_COLLECT_METADATA || ip_tunnel_collect_metadata(); } /* Find VXLAN socket based on network namespace, address family, UDP port, * enabled unshareable flags and socket device binding (see l3mdev with * non-default VRF). */ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family, __be16 port, u32 flags, int ifindex) { struct vxlan_sock *vs; flags &= VXLAN_F_RCV_FLAGS; hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) { if (inet_sk(vs->sock->sk)->inet_sport == port && vxlan_get_sk_family(vs) == family && vs->flags == flags && vs->sock->sk->sk_bound_dev_if == ifindex) return vs; } return NULL; } static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, int ifindex, __be32 vni, struct vxlan_vni_node **vninode) { struct vxlan_vni_node *vnode; struct vxlan_dev_node *node; /* For flow based devices, map all packets to VNI 0 */ if (vs->flags & VXLAN_F_COLLECT_METADATA && !(vs->flags & VXLAN_F_VNIFILTER)) vni = 0; hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) { if (!node->vxlan) continue; vnode = NULL; if (node->vxlan->cfg.flags & VXLAN_F_VNIFILTER) { vnode = vxlan_vnifilter_lookup(node->vxlan, vni); if (!vnode) continue; } else if (node->vxlan->default_dst.remote_vni != vni) { continue; } if (IS_ENABLED(CONFIG_IPV6)) { const struct vxlan_config *cfg = &node->vxlan->cfg; if ((cfg->flags & VXLAN_F_IPV6_LINKLOCAL) && cfg->remote_ifindex != ifindex) continue; } if (vninode) *vninode = vnode; return node->vxlan; } return NULL; } /* Look up VNI in a per net namespace table */ static struct vxlan_dev *vxlan_find_vni(struct net *net, int ifindex, __be32 vni, sa_family_t family, __be16 port, u32 flags) { struct vxlan_sock *vs; vs = vxlan_find_sock(net, family, port, flags, ifindex); if (!vs) return NULL; return vxlan_vs_find_vni(vs, ifindex, vni, NULL); } /* Fill in neighbour message in skbuff. */ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, u32 portid, u32 seq, int type, unsigned int flags, const struct vxlan_rdst *rdst) { unsigned long now = jiffies; struct nda_cacheinfo ci; bool send_ip, send_eth; struct nlmsghdr *nlh; struct nexthop *nh; struct ndmsg *ndm; int nh_family; u32 nh_id; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; ndm = nlmsg_data(nlh); memset(ndm, 0, sizeof(*ndm)); send_eth = send_ip = true; rcu_read_lock(); nh = rcu_dereference(fdb->nh); if (nh) { nh_family = nexthop_get_family(nh); nh_id = nh->id; } rcu_read_unlock(); if (type == RTM_GETNEIGH) { if (rdst) { send_ip = !vxlan_addr_any(&rdst->remote_ip); ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET; } else if (nh) { ndm->ndm_family = nh_family; } send_eth = !is_zero_ether_addr(fdb->key.eth_addr); } else ndm->ndm_family = AF_BRIDGE; ndm->ndm_state = fdb->state; ndm->ndm_ifindex = vxlan->dev->ifindex; ndm->ndm_flags = fdb->flags; if (rdst && rdst->offloaded) ndm->ndm_flags |= NTF_OFFLOADED; ndm->ndm_type = RTN_UNICAST; if (!net_eq(dev_net(vxlan->dev), vxlan->net) && nla_put_s32(skb, NDA_LINK_NETNSID, peernet2id(dev_net(vxlan->dev), vxlan->net))) goto nla_put_failure; if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.eth_addr)) goto nla_put_failure; if (nh) { if (nla_put_u32(skb, NDA_NH_ID, nh_id)) goto nla_put_failure; } else if (rdst) { if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip)) goto nla_put_failure; if (rdst->remote_port && rdst->remote_port != vxlan->cfg.dst_port && nla_put_be16(skb, NDA_PORT, rdst->remote_port)) goto nla_put_failure; if (rdst->remote_vni != vxlan->default_dst.remote_vni && nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) goto nla_put_failure; if (rdst->remote_ifindex && nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) goto nla_put_failure; } if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->key.vni && nla_put_u32(skb, NDA_SRC_VNI, be32_to_cpu(fdb->key.vni))) goto nla_put_failure; ci.ndm_used = jiffies_to_clock_t(now - READ_ONCE(fdb->used)); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - READ_ONCE(fdb->updated)); ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static inline size_t vxlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct in6_addr)) /* NDA_DST */ + nla_total_size(sizeof(__be16)) /* NDA_PORT */ + nla_total_size(sizeof(__be32)) /* NDA_VNI */ + nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */ + nla_total_size(sizeof(__s32)) /* NDA_LINK_NETNSID */ + nla_total_size(sizeof(struct nda_cacheinfo)); } static void __vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, int type) { struct net *net = dev_net(vxlan->dev); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(vxlan_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, rd); if (err < 0) { /* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, const struct vxlan_rdst *rd, struct netlink_ext_ack *extack, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { fdb_info->info.dev = vxlan->dev; fdb_info->info.extack = extack; fdb_info->remote_ip = rd->remote_ip; fdb_info->remote_port = rd->remote_port; fdb_info->remote_vni = rd->remote_vni; fdb_info->remote_ifindex = rd->remote_ifindex; memcpy(fdb_info->eth_addr, fdb->key.eth_addr, ETH_ALEN); fdb_info->vni = fdb->key.vni; fdb_info->offloaded = rd->offloaded; fdb_info->added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER; } static int vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, bool adding, struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info info; enum switchdev_notifier_type notifier_type; int ret; if (WARN_ON(!rd)) return 0; notifier_type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE : SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE; vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, NULL, &info); ret = call_switchdev_notifiers(notifier_type, vxlan->dev, &info.info, extack); return notifier_to_errno(ret); } static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, int type, bool swdev_notify, struct netlink_ext_ack *extack) { int err; if (swdev_notify && rd) { switch (type) { case RTM_NEWNEIGH: err = vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, true, extack); if (err) return err; break; case RTM_DELNEIGH: vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, false, extack); break; } } __vxlan_fdb_notify(vxlan, fdb, rd, type); return 0; } static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb f = { .state = NUD_STALE, }; struct vxlan_rdst remote = { .remote_ip = *ipa, /* goes to NDA_DST */ .remote_vni = cpu_to_be32(VXLAN_N_VID), }; vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN]) { struct vxlan_fdb f = { .state = NUD_STALE, }; struct vxlan_rdst remote = { }; memcpy(f.key.eth_addr, eth_addr, ETH_ALEN); vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } /* Look up Ethernet address in forwarding table */ static struct vxlan_fdb *vxlan_find_mac_rcu(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct vxlan_fdb_key key; memset(&key, 0, sizeof(key)); memcpy(key.eth_addr, mac, sizeof(key.eth_addr)); if (!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) key.vni = vxlan->default_dst.remote_vni; else key.vni = vni; return rhashtable_lookup(&vxlan->fdb_hash_tbl, &key, vxlan_fdb_rht_params); } static struct vxlan_fdb *vxlan_find_mac_tx(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct vxlan_fdb *f; f = vxlan_find_mac_rcu(vxlan, mac, vni); if (f) { unsigned long now = jiffies; if (READ_ONCE(f->used) != now) WRITE_ONCE(f->used, now); } return f; } static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct vxlan_fdb *f; lockdep_assert_held_once(&vxlan->hash_lock); rcu_read_lock(); f = vxlan_find_mac_rcu(vxlan, mac, vni); rcu_read_unlock(); return f; } /* caller should hold vxlan->hash_lock */ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex) { struct vxlan_rdst *rd; list_for_each_entry(rd, &f->remotes, list) { if (vxlan_addr_equal(&rd->remote_ip, ip) && rd->remote_port == port && rd->remote_vni == vni && rd->remote_ifindex == ifindex) return rd; } return NULL; } int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); u8 eth_addr[ETH_ALEN + 2] = { 0 }; struct vxlan_rdst *rdst = NULL; struct vxlan_fdb *f; int rc = 0; if (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)) return -EINVAL; ether_addr_copy(eth_addr, mac); rcu_read_lock(); f = vxlan_find_mac_rcu(vxlan, eth_addr, vni); if (f) rdst = first_remote_rcu(f); if (!rdst) { rc = -ENOENT; goto out; } vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, NULL, fdb_info); out: rcu_read_unlock(); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_find_uc); static int vxlan_fdb_notify_one(struct notifier_block *nb, const struct vxlan_dev *vxlan, const struct vxlan_fdb *f, const struct vxlan_rdst *rdst, struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info fdb_info; int rc; vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, extack, &fdb_info); rc = nb->notifier_call(nb, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, &fdb_info); return notifier_to_errno(rc); } int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; struct vxlan_fdb *f; int rc = 0; if (!netif_is_vxlan(dev)) return -EINVAL; vxlan = netdev_priv(dev); spin_lock_bh(&vxlan->hash_lock); hlist_for_each_entry(f, &vxlan->fdb_list, fdb_node) { if (f->key.vni == vni) { list_for_each_entry(rdst, &f->remotes, list) { rc = vxlan_fdb_notify_one(nb, vxlan, f, rdst, extack); if (rc) goto unlock; } } } spin_unlock_bh(&vxlan->hash_lock); return 0; unlock: spin_unlock_bh(&vxlan->hash_lock); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_replay); void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; struct vxlan_fdb *f; if (!netif_is_vxlan(dev)) return; vxlan = netdev_priv(dev); spin_lock_bh(&vxlan->hash_lock); hlist_for_each_entry(f, &vxlan->fdb_list, fdb_node) { if (f->key.vni == vni) { list_for_each_entry(rdst, &f->remotes, list) rdst->offloaded = false; } } spin_unlock_bh(&vxlan->hash_lock); } EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload); /* Replace destination of unicast mac */ static int vxlan_fdb_replace(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst *oldrd) { struct vxlan_rdst *rd; rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); if (rd) return 0; rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list); if (!rd) return 0; *oldrd = *rd; dst_cache_reset(&rd->dst_cache); rd->remote_ip = *ip; rd->remote_port = port; rd->remote_vni = vni; rd->remote_ifindex = ifindex; rd->offloaded = false; return 1; } /* Add/update destinations for multicast */ static int vxlan_fdb_append(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst **rdp) { struct vxlan_rdst *rd; rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); if (rd) return 0; rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) return -ENOMEM; /* The driver can work correctly without a dst cache, so do not treat * dst cache initialization errors as fatal. */ dst_cache_init(&rd->dst_cache, GFP_ATOMIC | __GFP_NOWARN); rd->remote_ip = *ip; rd->remote_port = port; rd->offloaded = false; rd->remote_vni = vni; rd->remote_ifindex = ifindex; list_add_tail_rcu(&rd->list, &f->remotes); *rdp = rd; return 1; } static bool vxlan_parse_gpe_proto(const struct vxlanhdr *hdr, __be16 *protocol) { const struct vxlanhdr_gpe *gpe = (const struct vxlanhdr_gpe *)hdr; /* Need to have Next Protocol set for interfaces in GPE mode. */ if (!gpe->np_applied) return false; /* "The initial version is 0. If a receiver does not support the * version indicated it MUST drop the packet. */ if (gpe->version != 0) return false; /* "When the O bit is set to 1, the packet is an OAM packet and OAM * processing MUST occur." However, we don't implement OAM * processing, thus drop the packet. */ if (gpe->oam_flag) return false; *protocol = tun_p_to_eth_p(gpe->next_protocol); if (!*protocol) return false; return true; } static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, unsigned int off, struct vxlanhdr *vh, size_t hdrlen, __be32 vni_field, struct gro_remcsum *grc, bool nopartial) { size_t start, offset; if (skb->remcsum_offload) return vh; if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; start = vxlan_rco_start(vni_field); offset = start + vxlan_rco_offset(vni_field); vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen, start, offset, grc, nopartial); skb->remcsum_offload = 1; return vh; } static struct vxlanhdr *vxlan_gro_prepare_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb, struct gro_remcsum *grc) { struct sk_buff *p; struct vxlanhdr *vh, *vh2; unsigned int hlen, off_vx; struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk); __be32 flags; skb_gro_remcsum_init(grc); off_vx = skb_gro_offset(skb); hlen = off_vx + sizeof(*vh); vh = skb_gro_header(skb, hlen, off_vx); if (unlikely(!vh)) return NULL; skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr)); flags = vh->vx_flags; if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr), vh->vx_vni, grc, !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL)); if (!vh) return NULL; } skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; vh2 = (struct vxlanhdr *)(p->data + off_vx); if (vh->vx_flags != vh2->vx_flags || vh->vx_vni != vh2->vx_vni) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } return vh; } static struct sk_buff *vxlan_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct gro_remcsum grc; int flush = 1; if (vxlan_gro_prepare_receive(sk, head, skb, &grc)) { pp = call_gro_receive(eth_gro_receive, head, skb); flush = 0; } skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static struct sk_buff *vxlan_gpe_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { const struct packet_offload *ptype; struct sk_buff *pp = NULL; struct gro_remcsum grc; struct vxlanhdr *vh; __be16 protocol; int flush = 1; vh = vxlan_gro_prepare_receive(sk, head, skb, &grc); if (vh) { if (!vxlan_parse_gpe_proto(vh, &protocol)) goto out; ptype = gro_find_receive_by_type(protocol); if (!ptype) goto out; pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; } out: skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { /* Sets 'skb->inner_mac_header' since we are always called with * 'skb->encapsulation' set. */ return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); } static int vxlan_gpe_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct vxlanhdr *vh = (struct vxlanhdr *)(skb->data + nhoff); const struct packet_offload *ptype; int err = -ENOSYS; __be16 protocol; if (!vxlan_parse_gpe_proto(vh, &protocol)) return err; ptype = gro_find_complete_by_type(protocol); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); return err; } static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, const u8 *mac, __u16 state, __be32 src_vni, __u16 ndm_flags) { struct vxlan_fdb *f; f = kmalloc(sizeof(*f), GFP_ATOMIC); if (!f) return NULL; memset(&f->key, 0, sizeof(f->key)); f->state = state; f->flags = ndm_flags; f->updated = f->used = jiffies; f->key.vni = src_vni; f->nh = NULL; RCU_INIT_POINTER(f->vdev, vxlan); INIT_LIST_HEAD(&f->nh_list); INIT_LIST_HEAD(&f->remotes); memcpy(f->key.eth_addr, mac, ETH_ALEN); return f; } static int vxlan_fdb_nh_update(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, u32 nhid, struct netlink_ext_ack *extack) { struct nexthop *old_nh = rtnl_dereference(fdb->nh); struct nexthop *nh; int err = -EINVAL; if (old_nh && old_nh->id == nhid) return 0; nh = nexthop_find_by_id(vxlan->net, nhid); if (!nh) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto err_inval; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); nh = NULL; goto err_inval; } if (!nexthop_is_fdb(nh)) { NL_SET_ERR_MSG(extack, "Nexthop is not a fdb nexthop"); goto err_inval; } if (!nexthop_is_multipath(nh)) { NL_SET_ERR_MSG(extack, "Nexthop is not a multipath group"); goto err_inval; } /* check nexthop group family */ switch (vxlan->default_dst.remote_ip.sa.sa_family) { case AF_INET: if (!nexthop_has_v4(nh)) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); goto err_inval; } break; case AF_INET6: if (nexthop_has_v4(nh)) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); goto err_inval; } } if (old_nh) { list_del_rcu(&fdb->nh_list); nexthop_put(old_nh); } rcu_assign_pointer(fdb->nh, nh); list_add_tail_rcu(&fdb->nh_list, &nh->fdb_list); return 1; err_inval: if (nh) nexthop_put(nh); return err; } int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, struct vxlan_fdb **fdb, struct netlink_ext_ack *extack) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int rc; if (vxlan->cfg.addrmax && vxlan->addrcnt >= vxlan->cfg.addrmax) return -ENOSPC; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags); if (!f) return -ENOMEM; if (nhid) rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); else rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) goto errout; rc = rhashtable_lookup_insert_fast(&vxlan->fdb_hash_tbl, &f->rhnode, vxlan_fdb_rht_params); if (rc) goto destroy_remote; ++vxlan->addrcnt; hlist_add_head_rcu(&f->fdb_node, &vxlan->fdb_list); *fdb = f; return 0; destroy_remote: if (rcu_access_pointer(f->nh)) { list_del_rcu(&f->nh_list); nexthop_put(rtnl_dereference(f->nh)); } else { list_del(&rd->list); dst_cache_destroy(&rd->dst_cache); kfree(rd); } errout: kfree(f); return rc; } static void __vxlan_fdb_free(struct vxlan_fdb *f) { struct vxlan_rdst *rd, *nd; struct nexthop *nh; nh = rcu_dereference_raw(f->nh); if (nh) { rcu_assign_pointer(f->nh, NULL); rcu_assign_pointer(f->vdev, NULL); nexthop_put(nh); } list_for_each_entry_safe(rd, nd, &f->remotes, list) { dst_cache_destroy(&rd->dst_cache); kfree(rd); } kfree(f); } static void vxlan_fdb_free(struct rcu_head *head) { struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); __vxlan_fdb_free(f); } static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, bool do_notify, bool swdev_notify) { struct vxlan_rdst *rd; netdev_dbg(vxlan->dev, "delete %pM\n", f->key.eth_addr); --vxlan->addrcnt; if (do_notify) { if (rcu_access_pointer(f->nh)) vxlan_fdb_notify(vxlan, f, NULL, RTM_DELNEIGH, swdev_notify, NULL); else list_for_each_entry(rd, &f->remotes, list) vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); } hlist_del_init_rcu(&f->fdb_node); rhashtable_remove_fast(&vxlan->fdb_hash_tbl, &f->rhnode, vxlan_fdb_rht_params); list_del_rcu(&f->nh_list); call_rcu(&f->rcu, vxlan_fdb_free); } static void vxlan_dst_free(struct rcu_head *head) { struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); dst_cache_destroy(&rd->dst_cache); kfree(rd); } static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 vni, __u32 ifindex, __u16 ndm_flags, struct vxlan_fdb *f, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_rdst *rd = NULL; struct vxlan_rdst oldrd; int notify = 0; int rc = 0; int err; if (nhid && !rcu_access_pointer(f->nh)) { NL_SET_ERR_MSG(extack, "Cannot replace an existing non nexthop fdb with a nexthop"); return -EOPNOTSUPP; } if (nhid && (flags & NLM_F_APPEND)) { NL_SET_ERR_MSG(extack, "Cannot append to a nexthop fdb"); return -EOPNOTSUPP; } /* Do not allow an externally learned entry to take over an entry added * by the user. */ if (!(fdb_flags & NTF_EXT_LEARNED) || !(f->flags & NTF_VXLAN_ADDED_BY_USER)) { if (f->state != state) { f->state = state; notify = 1; } if (f->flags != fdb_flags) { f->flags = fdb_flags; notify = 1; } } if ((flags & NLM_F_REPLACE)) { /* Only change unicasts */ if (!(is_multicast_ether_addr(f->key.eth_addr) || is_zero_ether_addr(f->key.eth_addr))) { if (nhid) { rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); if (rc < 0) return rc; } else { rc = vxlan_fdb_replace(f, ip, port, vni, ifindex, &oldrd); } notify |= rc; } else { NL_SET_ERR_MSG(extack, "Cannot replace non-unicast fdb entries"); return -EOPNOTSUPP; } } if ((flags & NLM_F_APPEND) && (is_multicast_ether_addr(f->key.eth_addr) || is_zero_ether_addr(f->key.eth_addr))) { rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) return rc; notify |= rc; } if (ndm_flags & NTF_USE) WRITE_ONCE(f->updated, jiffies); if (notify) { if (rd == NULL) rd = first_remote_rtnl(f); WRITE_ONCE(f->updated, jiffies); err = vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH, swdev_notify, extack); if (err) goto err_notify; } return 0; err_notify: if (nhid) return err; if ((flags & NLM_F_REPLACE) && rc) *rd = oldrd; else if ((flags & NLM_F_APPEND) && rc) { list_del_rcu(&rd->list); call_rcu(&rd->rcu, vxlan_dst_free); } return err; } static int vxlan_fdb_update_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_fdb *f; int rc; /* Disallow replace to add a multicast entry */ if ((flags & NLM_F_REPLACE) && (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) return -EOPNOTSUPP; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni, vni, ifindex, fdb_flags, nhid, &f, extack); if (rc < 0) return rc; rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, swdev_notify, extack); if (rc) goto err_notify; return 0; err_notify: vxlan_fdb_destroy(vxlan, f, false, false); return rc; } /* Add new entry to forwarding table -- assumes lock held */ int vxlan_fdb_update(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { struct vxlan_fdb *f; f = vxlan_find_mac(vxlan, mac, src_vni); if (f) { if (flags & NLM_F_EXCL) { netdev_dbg(vxlan->dev, "lost race to create %pM\n", mac); return -EEXIST; } return vxlan_fdb_update_existing(vxlan, ip, state, flags, port, vni, ifindex, ndm_flags, f, nhid, swdev_notify, extack); } else { if (!(flags & NLM_F_CREATE)) return -ENOENT; return vxlan_fdb_update_create(vxlan, mac, ip, state, flags, port, src_vni, vni, ifindex, ndm_flags, nhid, swdev_notify, extack); } } static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, struct vxlan_rdst *rd, bool swdev_notify) { list_del_rcu(&rd->list); vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); call_rcu(&rd->rcu, vxlan_dst_free); } static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, union vxlan_addr *ip, __be16 *port, __be32 *src_vni, __be32 *vni, u32 *ifindex, u32 *nhid, struct netlink_ext_ack *extack) { struct net *net = dev_net(vxlan->dev); int err; if (tb[NDA_NH_ID] && (tb[NDA_DST] || tb[NDA_VNI] || tb[NDA_IFINDEX] || tb[NDA_PORT])) { NL_SET_ERR_MSG(extack, "DST, VNI, ifindex and port are mutually exclusive with NH_ID"); return -EINVAL; } if (tb[NDA_DST]) { err = vxlan_nla_get_addr(ip, tb[NDA_DST]); if (err) { NL_SET_ERR_MSG(extack, "Unsupported address family"); return err; } } else { union vxlan_addr *remote = &vxlan->default_dst.remote_ip; if (remote->sa.sa_family == AF_INET) { ip->sin.sin_addr.s_addr = htonl(INADDR_ANY); ip->sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { ip->sin6.sin6_addr = in6addr_any; ip->sa.sa_family = AF_INET6; #endif } } if (tb[NDA_PORT]) { if (nla_len(tb[NDA_PORT]) != sizeof(__be16)) { NL_SET_ERR_MSG(extack, "Invalid vxlan port"); return -EINVAL; } *port = nla_get_be16(tb[NDA_PORT]); } else { *port = vxlan->cfg.dst_port; } if (tb[NDA_VNI]) { if (nla_len(tb[NDA_VNI]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid vni"); return -EINVAL; } *vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); } else { *vni = vxlan->default_dst.remote_vni; } if (tb[NDA_SRC_VNI]) { if (nla_len(tb[NDA_SRC_VNI]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid src vni"); return -EINVAL; } *src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); } else { *src_vni = vxlan->default_dst.remote_vni; } if (tb[NDA_IFINDEX]) { struct net_device *tdev; if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid ifindex"); return -EINVAL; } *ifindex = nla_get_u32(tb[NDA_IFINDEX]); tdev = __dev_get_by_index(net, *ifindex); if (!tdev) { NL_SET_ERR_MSG(extack, "Device not found"); return -EADDRNOTAVAIL; } } else { *ifindex = 0; } *nhid = nla_get_u32_default(tb[NDA_NH_ID], 0); return 0; } /* Add static entry (via netlink) */ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, bool *notified, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); /* struct net *net = dev_net(vxlan->dev); */ union vxlan_addr ip; __be16 port; __be32 src_vni, vni; u32 ifindex, nhid; int err; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) { pr_info("RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); return -EINVAL; } if (!tb || (!tb[NDA_DST] && !tb[NDA_NH_ID])) return -EINVAL; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, &nhid, extack); if (err) return err; if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) return -EAFNOSUPPORT; spin_lock_bh(&vxlan->hash_lock); err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER, nhid, true, extack); spin_unlock_bh(&vxlan->hash_lock); if (!err) *notified = true; return err; } int __vxlan_fdb_delete(struct vxlan_dev *vxlan, const unsigned char *addr, union vxlan_addr ip, __be16 port, __be32 src_vni, __be32 vni, u32 ifindex, bool swdev_notify) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int err = -ENOENT; f = vxlan_find_mac(vxlan, addr, src_vni); if (!f) return err; if (!vxlan_addr_any(&ip)) { rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex); if (!rd) goto out; } /* remove a destination if it's not the only one on the list, * otherwise destroy the fdb entry */ if (rd && !list_is_singular(&f->remotes)) { vxlan_fdb_dst_destroy(vxlan, f, rd, swdev_notify); goto out; } vxlan_fdb_destroy(vxlan, f, true, swdev_notify); out: return 0; } /* Delete entry (via netlink) */ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, bool *notified, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); union vxlan_addr ip; __be32 src_vni, vni; u32 ifindex, nhid; __be16 port; int err; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, &nhid, extack); if (err) return err; spin_lock_bh(&vxlan->hash_lock); err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex, true); spin_unlock_bh(&vxlan->hash_lock); if (!err) *notified = true; return err; } /* Dump forwarding table */ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct ndo_fdb_dump_context *ctx = (void *)cb->ctx; struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; int err = 0; rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_list, fdb_node) { struct vxlan_rdst *rd; if (rcu_access_pointer(f->nh)) { if (*idx < ctx->fdb_idx) goto skip_nh; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, NULL); if (err < 0) { rcu_read_unlock(); goto out; } skip_nh: *idx += 1; continue; } list_for_each_entry_rcu(rd, &f->remotes, list) { if (*idx < ctx->fdb_idx) goto skip; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); if (err < 0) { rcu_read_unlock(); goto out; } skip: *idx += 1; } } rcu_read_unlock(); out: return err; } static int vxlan_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; __be32 vni; int err; if (tb[NDA_VNI]) vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); else vni = vxlan->default_dst.remote_vni; rcu_read_lock(); f = vxlan_find_mac_rcu(vxlan, addr, vni); if (!f) { NL_SET_ERR_MSG(extack, "Fdb entry not found"); err = -ENOENT; goto errout; } err = vxlan_fdb_info(skb, vxlan, f, portid, seq, RTM_NEWNEIGH, 0, first_remote_rcu(f)); errout: rcu_read_unlock(); return err; } /* Watch incoming packets to learn mapping between Ethernet address * and Tunnel endpoint. */ static enum skb_drop_reason vxlan_snoop(struct net_device *dev, union vxlan_addr *src_ip, const u8 *src_mac, u32 src_ifindex, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; u32 ifindex = 0; /* Ignore packets from invalid src-address */ if (!is_valid_ether_addr(src_mac)) return SKB_DROP_REASON_MAC_INVALID_SOURCE; #if IS_ENABLED(CONFIG_IPV6) if (src_ip->sa.sa_family == AF_INET6 && (ipv6_addr_type(&src_ip->sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)) ifindex = src_ifindex; #endif f = vxlan_find_mac_rcu(vxlan, src_mac, vni); if (likely(f)) { struct vxlan_rdst *rdst = first_remote_rcu(f); unsigned long now = jiffies; if (READ_ONCE(f->updated) != now) WRITE_ONCE(f->updated, now); /* Don't override an fdb with nexthop with a learnt entry */ if (rcu_access_pointer(f->nh)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) && rdst->remote_ifindex == ifindex)) return SKB_NOT_DROPPED_YET; /* Don't migrate static entries, drop packets */ if (f->state & (NUD_PERMANENT | NUD_NOARP)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; if (net_ratelimit()) netdev_info(dev, "%pM migrated from %pIS to %pIS\n", src_mac, &rdst->remote_ip.sa, &src_ip->sa); rdst->remote_ip = *src_ip; vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL); } else { /* learned new entry */ spin_lock(&vxlan->hash_lock); /* close off race between vxlan_flush and incoming packets */ if (netif_running(dev)) vxlan_fdb_update(vxlan, src_mac, src_ip, NUD_REACHABLE, NLM_F_EXCL|NLM_F_CREATE, vxlan->cfg.dst_port, vni, vxlan->default_dst.remote_vni, ifindex, NTF_SELF, 0, true, NULL); spin_unlock(&vxlan->hash_lock); } return SKB_NOT_DROPPED_YET; } static bool __vxlan_sock_release_prep(struct vxlan_sock *vs) { ASSERT_RTNL(); if (!vs) return false; if (!refcount_dec_and_test(&vs->refcnt)) return false; hlist_del_rcu(&vs->hlist); udp_tunnel_notify_del_rx_port(vs->sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); return true; } static void vxlan_sock_release(struct vxlan_dev *vxlan) { struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock); #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock); RCU_INIT_POINTER(vxlan->vn6_sock, NULL); #endif RCU_INIT_POINTER(vxlan->vn4_sock, NULL); synchronize_net(); if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vs_del_vnigrp(vxlan); else vxlan_vs_del_dev(vxlan); if (__vxlan_sock_release_prep(sock4)) { udp_tunnel_sock_release(sock4->sock); kfree(sock4); } #if IS_ENABLED(CONFIG_IPV6) if (__vxlan_sock_release_prep(sock6)) { udp_tunnel_sock_release(sock6->sock); kfree(sock6); } #endif } static enum skb_drop_reason vxlan_remcsum(struct sk_buff *skb, u32 vxflags) { const struct vxlanhdr *vh = vxlan_hdr(skb); enum skb_drop_reason reason; size_t start, offset; if (!(vh->vx_flags & VXLAN_HF_RCO) || skb->remcsum_offload) return SKB_NOT_DROPPED_YET; start = vxlan_rco_start(vh->vx_vni); offset = start + vxlan_rco_offset(vh->vx_vni); reason = pskb_may_pull_reason(skb, offset + sizeof(u16)); if (reason) return reason; skb_remcsum_process(skb, (void *)(vxlan_hdr(skb) + 1), start, offset, !!(vxflags & VXLAN_F_REMCSUM_NOPARTIAL)); return SKB_NOT_DROPPED_YET; } static void vxlan_parse_gbp_hdr(struct sk_buff *skb, u32 vxflags, struct vxlan_metadata *md) { const struct vxlanhdr *vh = vxlan_hdr(skb); const struct vxlanhdr_gbp *gbp; struct metadata_dst *tun_dst; gbp = (const struct vxlanhdr_gbp *)vh; if (!(vh->vx_flags & VXLAN_HF_GBP)) return; md->gbp = ntohs(gbp->policy_id); tun_dst = (struct metadata_dst *)skb_dst(skb); if (tun_dst) { __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_dst->u.tun_info.key.tun_flags); tun_dst->u.tun_info.options_len = sizeof(*md); } if (gbp->dont_learn) md->gbp |= VXLAN_GBP_DONT_LEARN; if (gbp->policy_applied) md->gbp |= VXLAN_GBP_POLICY_APPLIED; /* In flow-based mode, GBP is carried in dst_metadata */ if (!(vxflags & VXLAN_F_COLLECT_METADATA)) skb->mark = md->gbp; } static enum skb_drop_reason vxlan_set_mac(struct vxlan_dev *vxlan, struct vxlan_sock *vs, struct sk_buff *skb, __be32 vni) { union vxlan_addr saddr; u32 ifindex = skb->dev->ifindex; skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, vxlan->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) return SKB_DROP_REASON_LOCAL_MAC; /* Get address from the outer IP header */ if (vxlan_get_sk_family(vs) == AF_INET) { saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; saddr.sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { saddr.sin6.sin6_addr = ipv6_hdr(skb)->saddr; saddr.sa.sa_family = AF_INET6; #endif } if (!(vxlan->cfg.flags & VXLAN_F_LEARN)) return SKB_NOT_DROPPED_YET; return vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source, ifindex, vni); } static bool vxlan_ecn_decapsulate(struct vxlan_sock *vs, void *oiph, struct sk_buff *skb) { int err = 0; if (vxlan_get_sk_family(vs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); #endif if (unlikely(err) && log_ecn_error) { if (vxlan_get_sk_family(vs) == AF_INET) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); } return err <= 1; } static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) { struct vxlan_vni_node *vninode = NULL; const struct vxlanhdr *vh; struct vxlan_dev *vxlan; struct vxlan_sock *vs; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 protocol = htons(ETH_P_TEB); enum skb_drop_reason reason; bool raw_proto = false; void *oiph; __be32 vni = 0; int nh; /* Need UDP and VXLAN header to be present */ reason = pskb_may_pull_reason(skb, VXLAN_HLEN); if (reason) goto drop; vh = vxlan_hdr(skb); /* VNI flag always required to be set */ if (!(vh->vx_flags & VXLAN_HF_VNI)) { netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n", ntohl(vh->vx_flags), ntohl(vh->vx_vni)); reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; /* Return non vxlan pkt */ goto drop; } vs = rcu_dereference_sk_user_data(sk); if (!vs) goto drop; vni = vxlan_vni(vh->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, &vninode); if (!vxlan) { reason = SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND; goto drop; } if (vh->vx_flags & vxlan->cfg.reserved_bits.vx_flags || vh->vx_vni & vxlan->cfg.reserved_bits.vx_vni) { /* If the header uses bits besides those enabled by the * netdevice configuration, treat this as a malformed packet. * This behavior diverges from VXLAN RFC (RFC7348) which * stipulates that bits in reserved in reserved fields are to be * ignored. The approach here maintains compatibility with * previous stack code, and also is more robust and provides a * little more security in adding extensions to VXLAN. */ reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; DEV_STATS_INC(vxlan->dev, rx_frame_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } if (vxlan->cfg.flags & VXLAN_F_GPE) { if (!vxlan_parse_gpe_proto(vh, &protocol)) goto drop; raw_proto = true; } if (__iptunnel_pull_header(skb, VXLAN_HLEN, protocol, raw_proto, !net_eq(vxlan->net, dev_net(vxlan->dev)))) { reason = SKB_DROP_REASON_NOMEM; goto drop; } if (vxlan->cfg.flags & VXLAN_F_REMCSUM_RX) { reason = vxlan_remcsum(skb, vxlan->cfg.flags); if (unlikely(reason)) goto drop; } if (vxlan_collect_metadata(vs)) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst; __set_bit(IP_TUNNEL_KEY_BIT, flags); tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), flags, key32_to_tunnel_id(vni), sizeof(*md)); if (!tun_dst) { reason = SKB_DROP_REASON_NOMEM; goto drop; } md = ip_tunnel_info_opts(&tun_dst->u.tun_info); skb_dst_set(skb, (struct dst_entry *)tun_dst); } else { memset(md, 0, sizeof(*md)); } if (vxlan->cfg.flags & VXLAN_F_GBP) vxlan_parse_gbp_hdr(skb, vxlan->cfg.flags, md); /* Note that GBP and GPE can never be active together. This is * ensured in vxlan_dev_configure. */ if (!raw_proto) { reason = vxlan_set_mac(vxlan, vs, skb, vni); if (reason) goto drop; } else { skb_reset_mac_header(skb); skb->dev = vxlan->dev; skb->pkt_type = PACKET_HOST; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); reason = pskb_inet_may_pull_reason(skb); if (reason) { DEV_STATS_INC(vxlan->dev, rx_length_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (!vxlan_ecn_decapsulate(vs, oiph, skb)) { reason = SKB_DROP_REASON_IP_TUNNEL_ECN; DEV_STATS_INC(vxlan->dev, rx_frame_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } rcu_read_lock(); if (unlikely(!(vxlan->dev->flags & IFF_UP))) { rcu_read_unlock(); dev_dstats_rx_dropped(vxlan->dev); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_DROPS, 0); reason = SKB_DROP_REASON_DEV_READY; goto drop; } dev_dstats_rx_add(vxlan->dev, skb->len); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX, skb->len); gro_cells_receive(&vxlan->gro_cells, skb); rcu_read_unlock(); return 0; drop: reason = reason ?: SKB_DROP_REASON_NOT_SPECIFIED; /* Consume bad packet */ kfree_skb_reason(skb, reason); return 0; } static int vxlan_err_lookup(struct sock *sk, struct sk_buff *skb) { struct vxlan_dev *vxlan; struct vxlan_sock *vs; struct vxlanhdr *hdr; __be32 vni; if (!pskb_may_pull(skb, skb_transport_offset(skb) + VXLAN_HLEN)) return -EINVAL; hdr = vxlan_hdr(skb); if (!(hdr->vx_flags & VXLAN_HF_VNI)) return -EINVAL; vs = rcu_dereference_sk_user_data(sk); if (!vs) return -ENOENT; vni = vxlan_vni(hdr->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, NULL); if (!vxlan) return -ENOENT; return 0; } static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct arphdr *parp; u8 *arpptr, *sha; __be32 sip, tip; struct neighbour *n; if (dev->flags & IFF_NOARP) goto out; if (!pskb_may_pull(skb, arp_hdr_len(dev))) { dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); goto out; } parp = arp_hdr(skb); if ((parp->ar_hrd != htons(ARPHRD_ETHER) && parp->ar_hrd != htons(ARPHRD_IEEE802)) || parp->ar_pro != htons(ETH_P_IP) || parp->ar_op != htons(ARPOP_REQUEST) || parp->ar_hln != dev->addr_len || parp->ar_pln != 4) goto out; arpptr = (u8 *)parp + sizeof(struct arphdr); sha = arpptr; arpptr += dev->addr_len; /* sha */ memcpy(&sip, arpptr, sizeof(sip)); arpptr += sizeof(sip); arpptr += dev->addr_len; /* tha */ memcpy(&tip, arpptr, sizeof(tip)); if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) goto out; n = neigh_lookup(&arp_tbl, &tip, dev); if (n) { struct vxlan_rdst *rdst = NULL; struct vxlan_fdb *f; struct sk_buff *reply; if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } rcu_read_lock(); f = vxlan_find_mac_tx(vxlan, n->ha, vni); if (f) rdst = first_remote_rcu(f); if (rdst && vxlan_addr_any(&rdst->remote_ip)) { /* bridge-local neighbor */ neigh_release(n); rcu_read_unlock(); goto out; } rcu_read_unlock(); reply = arp_create(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, n->ha, sha); neigh_release(n); if (reply == NULL) goto out; skb_reset_mac_header(reply); __skb_pull(reply, skb_network_offset(reply)); reply->ip_summed = CHECKSUM_UNNECESSARY; reply->pkt_type = PACKET_HOST; if (netif_rx(reply) == NET_RX_DROP) { dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); } out: consume_skb(skb); return NETDEV_TX_OK; } #if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *vxlan_na_create(struct sk_buff *request, struct neighbour *n, bool isrouter) { struct net_device *dev = request->dev; struct sk_buff *reply; struct nd_msg *ns, *na; struct ipv6hdr *pip6; u8 *daddr; int na_olen = 8; /* opt hdr + ETH_ALEN for target */ int ns_olen; int i, len; if (dev == NULL || !pskb_may_pull(request, request->len)) return NULL; len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + sizeof(*na) + na_olen + dev->needed_tailroom; reply = alloc_skb(len, GFP_ATOMIC); if (reply == NULL) return NULL; reply->protocol = htons(ETH_P_IPV6); reply->dev = dev; skb_reserve(reply, LL_RESERVED_SPACE(request->dev)); skb_push(reply, sizeof(struct ethhdr)); skb_reset_mac_header(reply); ns = (struct nd_msg *)(ipv6_hdr(request) + 1); daddr = eth_hdr(request)->h_source; ns_olen = request->len - skb_network_offset(request) - sizeof(struct ipv6hdr) - sizeof(*ns); for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) { if (!ns->opt[i + 1]) { kfree_skb(reply); return NULL; } if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { daddr = ns->opt + i + sizeof(struct nd_opt_hdr); break; } } /* Ethernet header */ ether_addr_copy(eth_hdr(reply)->h_dest, daddr); ether_addr_copy(eth_hdr(reply)->h_source, n->ha); eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); reply->protocol = htons(ETH_P_IPV6); skb_pull(reply, sizeof(struct ethhdr)); skb_reset_network_header(reply); skb_put(reply, sizeof(struct ipv6hdr)); /* IPv6 header */ pip6 = ipv6_hdr(reply); memset(pip6, 0, sizeof(struct ipv6hdr)); pip6->version = 6; pip6->priority = ipv6_hdr(request)->priority; pip6->nexthdr = IPPROTO_ICMPV6; pip6->hop_limit = 255; pip6->daddr = ipv6_hdr(request)->saddr; pip6->saddr = *(struct in6_addr *)n->primary_key; skb_pull(reply, sizeof(struct ipv6hdr)); skb_reset_transport_header(reply); /* Neighbor Advertisement */ na = skb_put_zero(reply, sizeof(*na) + na_olen); na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; na->icmph.icmp6_router = isrouter; na->icmph.icmp6_override = 1; na->icmph.icmp6_solicited = 1; na->target = ns->target; ether_addr_copy(&na->opt[2], n->ha); na->opt[0] = ND_OPT_TARGET_LL_ADDR; na->opt[1] = na_olen >> 3; na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6, csum_partial(na, sizeof(*na)+na_olen, 0)); pip6->payload_len = htons(sizeof(*na)+na_olen); skb_push(reply, sizeof(struct ipv6hdr)); reply->ip_summed = CHECKSUM_UNNECESSARY; return reply; } static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); const struct in6_addr *daddr; const struct ipv6hdr *iphdr; struct inet6_dev *in6_dev; struct neighbour *n; struct nd_msg *msg; rcu_read_lock(); in6_dev = __in6_dev_get(dev); if (!in6_dev) goto out; iphdr = ipv6_hdr(skb); daddr = &iphdr->daddr; msg = (struct nd_msg *)(iphdr + 1); if (ipv6_addr_loopback(daddr) || ipv6_addr_is_multicast(&msg->target)) goto out; n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev); if (n) { struct vxlan_rdst *rdst = NULL; struct vxlan_fdb *f; struct sk_buff *reply; if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } f = vxlan_find_mac_tx(vxlan, n->ha, vni); if (f) rdst = first_remote_rcu(f); if (rdst && vxlan_addr_any(&rdst->remote_ip)) { /* bridge-local neighbor */ neigh_release(n); goto out; } reply = vxlan_na_create(skb, n, !!(f ? f->flags & NTF_ROUTER : 0)); neigh_release(n); if (reply == NULL) goto out; if (netif_rx(reply) == NET_RX_DROP) { dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin6.sin6_addr = msg->target, .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); } out: rcu_read_unlock(); consume_skb(skb); return NETDEV_TX_OK; } #endif static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct neighbour *n; if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) return false; n = NULL; switch (ntohs(eth_hdr(skb)->h_proto)) { case ETH_P_IP: { struct iphdr *pip; if (!pskb_may_pull(skb, sizeof(struct iphdr))) return false; pip = ip_hdr(skb); n = neigh_lookup(&arp_tbl, &pip->daddr, dev); if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = pip->daddr, .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); return false; } break; } #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: { struct ipv6hdr *pip6; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return false; pip6 = ipv6_hdr(skb); n = neigh_lookup(ipv6_stub->nd_tbl, &pip6->daddr, dev); if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin6.sin6_addr = pip6->daddr, .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); return false; } break; } #endif default: return false; } if (n) { bool diff; diff = !ether_addr_equal(eth_hdr(skb)->h_dest, n->ha); if (diff) { memcpy(eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, dev->addr_len); memcpy(eth_hdr(skb)->h_dest, n->ha, dev->addr_len); } neigh_release(n); return diff; } return false; } static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, __be16 protocol) { struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh; gpe->np_applied = 1; gpe->next_protocol = tun_p_from_eth_p(protocol); if (!gpe->next_protocol) return -EPFNOSUPPORT; return 0; } static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, int iphdr_len, __be32 vni, struct vxlan_metadata *md, u32 vxflags, bool udp_sum) { struct vxlanhdr *vxh; int min_headroom; int err; int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; __be16 inner_protocol = htons(ETH_P_TEB); if ((vxflags & VXLAN_F_REMCSUM_TX) && skb->ip_summed == CHECKSUM_PARTIAL) { int csum_start = skb_checksum_start_offset(skb); if (csum_start <= VXLAN_MAX_REMCSUM_START && !(csum_start & VXLAN_RCO_SHIFT_MASK) && (skb->csum_offset == offsetof(struct udphdr, check) || skb->csum_offset == offsetof(struct tcphdr, check))) type |= SKB_GSO_TUNNEL_REMCSUM; } min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + VXLAN_HLEN + iphdr_len; /* Need space for new headers (invalidates iph ptr) */ err = skb_cow_head(skb, min_headroom); if (unlikely(err)) return err; err = iptunnel_handle_offloads(skb, type); if (err) return err; vxh = __skb_push(skb, sizeof(*vxh)); vxh->vx_flags = VXLAN_HF_VNI; vxh->vx_vni = vxlan_vni_field(vni); if (type & SKB_GSO_TUNNEL_REMCSUM) { unsigned int start; start = skb_checksum_start_offset(skb) - sizeof(struct vxlanhdr); vxh->vx_vni |= vxlan_compute_rco(start, skb->csum_offset); vxh->vx_flags |= VXLAN_HF_RCO; if (!skb_is_gso(skb)) { skb->ip_summed = CHECKSUM_NONE; skb->encapsulation = 0; } } if (vxflags & VXLAN_F_GBP) vxlan_build_gbp_hdr(vxh, md); if (vxflags & VXLAN_F_GPE) { err = vxlan_build_gpe_hdr(vxh, skb->protocol); if (err < 0) return err; inner_protocol = skb->protocol; } skb_set_inner_protocol(skb, inner_protocol); return 0; } /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan, __be32 vni, bool snoop) { union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; unsigned int len = skb->len; struct net_device *dev; skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; skb->dev = dst_vxlan->dev; __skb_pull(skb, skb_network_offset(skb)); if (remote_ip->sa.sa_family == AF_INET) { loopback.sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK); loopback.sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { loopback.sin6.sin6_addr = in6addr_loopback; loopback.sa.sa_family = AF_INET6; #endif } rcu_read_lock(); dev = skb->dev; if (unlikely(!(dev->flags & IFF_UP))) { kfree_skb_reason(skb, SKB_DROP_REASON_DEV_READY); goto drop; } if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop) vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); dev_dstats_tx_add(src_vxlan->dev, len); vxlan_vnifilter_count(src_vxlan, vni, NULL, VXLAN_VNI_STATS_TX, len); if (__netif_rx(skb) == NET_RX_SUCCESS) { dev_dstats_rx_add(dst_vxlan->dev, len); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX, len); } else { drop: dev_dstats_rx_dropped(dev); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } rcu_read_unlock(); } static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *vxlan, int addr_family, __be16 dst_port, int dst_ifindex, __be32 vni, struct dst_entry *dst, u32 rt_flags) { #if IS_ENABLED(CONFIG_IPV6) /* IPv6 rt-flags are checked against RTF_LOCAL, but the value of * RTF_LOCAL is equal to RTCF_LOCAL. So to keep code simple * we can use RTCF_LOCAL which works for ipv4 and ipv6 route entry. */ BUILD_BUG_ON(RTCF_LOCAL != RTF_LOCAL); #endif /* Bypass encapsulation if the destination is local */ if (rt_flags & RTCF_LOCAL && !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && vxlan->cfg.flags & VXLAN_F_LOCALBYPASS) { struct vxlan_dev *dst_vxlan; dst_release(dst); dst_vxlan = vxlan_find_vni(vxlan->net, dst_ifindex, vni, addr_family, dst_port, vxlan->cfg.flags); if (!dst_vxlan) { DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND); return -ENOENT; } vxlan_encap_bypass(skb, vxlan, dst_vxlan, vni, true); return 1; } return 0; } void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, __be32 default_vni, struct vxlan_rdst *rdst, bool did_rsc) { struct dst_cache *dst_cache; struct ip_tunnel_info *info; struct ip_tunnel_key *pkey; struct ip_tunnel_key key; struct vxlan_dev *vxlan = netdev_priv(dev); const struct iphdr *old_iph; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; unsigned int pkt_len = skb->len; __be16 src_port = 0, dst_port; struct dst_entry *ndst = NULL; int addr_family; __u8 tos, ttl; int ifindex; int err; u32 flags = vxlan->cfg.flags; bool use_cache; bool udp_sum = false; bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev)); enum skb_drop_reason reason; bool no_eth_encap; __be32 vni = 0; no_eth_encap = flags & VXLAN_F_GPE && skb->protocol != htons(ETH_P_TEB); reason = skb_vlan_inet_prepare(skb, no_eth_encap); if (reason) goto drop; reason = SKB_DROP_REASON_NOT_SPECIFIED; old_iph = ip_hdr(skb); info = skb_tunnel_info(skb); use_cache = ip_tunnel_dst_cache_usable(skb, info); if (rdst) { memset(&key, 0, sizeof(key)); pkey = &key; if (vxlan_addr_any(&rdst->remote_ip)) { if (did_rsc) { /* short-circuited back to local bridge */ vxlan_encap_bypass(skb, vxlan, vxlan, default_vni, true); return; } goto drop; } addr_family = vxlan->cfg.saddr.sa.sa_family; dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; vni = (rdst->remote_vni) ? : default_vni; ifindex = rdst->remote_ifindex; if (addr_family == AF_INET) { key.u.ipv4.src = vxlan->cfg.saddr.sin.sin_addr.s_addr; key.u.ipv4.dst = rdst->remote_ip.sin.sin_addr.s_addr; } else { key.u.ipv6.src = vxlan->cfg.saddr.sin6.sin6_addr; key.u.ipv6.dst = rdst->remote_ip.sin6.sin6_addr; } dst_cache = &rdst->dst_cache; md->gbp = skb->mark; if (flags & VXLAN_F_TTL_INHERIT) { ttl = ip_tunnel_get_ttl(old_iph, skb); } else { ttl = vxlan->cfg.ttl; if (!ttl && vxlan_addr_multicast(&rdst->remote_ip)) ttl = 1; } tos = vxlan->cfg.tos; if (tos == 1) tos = ip_tunnel_get_dsfield(old_iph, skb); if (tos && !info) use_cache = false; if (addr_family == AF_INET) udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX); else udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX); #if IS_ENABLED(CONFIG_IPV6) switch (vxlan->cfg.label_policy) { case VXLAN_LABEL_FIXED: key.label = vxlan->cfg.label; break; case VXLAN_LABEL_INHERIT: key.label = ip_tunnel_get_flowlabel(old_iph, skb); break; default: DEBUG_NET_WARN_ON_ONCE(1); goto drop; } #endif } else { if (!info) { WARN_ONCE(1, "%s: Missing encapsulation instructions\n", dev->name); goto drop; } pkey = &info->key; addr_family = ip_tunnel_info_af(info); dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { if (info->options_len < sizeof(*md)) goto drop; md = ip_tunnel_info_opts(info); } ttl = info->key.ttl; tos = info->key.tos; udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); rcu_read_lock(); if (addr_family == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); u16 ipcb_flags = 0; struct rtable *rt; __be16 df = 0; __be32 saddr; if (!ifindex) ifindex = sock4->sock->sk->sk_bound_dev_if; rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, ifindex, &saddr, pkey, src_port, dst_port, tos, use_cache ? dst_cache : NULL); if (IS_ERR(rt)) { err = PTR_ERR(rt); reason = SKB_DROP_REASON_IP_OUTNOROUTES; goto tx_error; } if (flags & VXLAN_F_MC_ROUTE) ipcb_flags |= IPSKB_MCROUTE; if (!info) { /* Bypass encapsulation if the destination is local */ err = encap_bypass_if_local(skb, dev, vxlan, AF_INET, dst_port, ifindex, vni, &rt->dst, rt->rt_flags); if (err) goto out_unlock; if (vxlan->cfg.df == VXLAN_DF_SET) { df = htons(IP_DF); } else if (vxlan->cfg.df == VXLAN_DF_INHERIT) { struct ethhdr *eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_IPV6 || (ntohs(eth->h_proto) == ETH_P_IP && old_iph->frag_off & htons(IP_DF))) df = htons(IP_DF); } } else if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags)) { df = htons(IP_DF); } ndst = &rt->dst; err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom(flags & VXLAN_F_GPE), netif_is_any_bridge_port(dev)); if (err < 0) { goto tx_error; } else if (err) { if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; unclone->key.u.ipv4.src = pkey->u.ipv4.dst; unclone->key.u.ipv4.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), vni, md, flags, udp_sum); if (err < 0) { reason = SKB_DROP_REASON_NOMEM; goto tx_error; } udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, saddr, pkey->u.ipv4.dst, tos, ttl, df, src_port, dst_port, xnet, !udp_sum, ipcb_flags); #if IS_ENABLED(CONFIG_IPV6) } else { struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct in6_addr saddr; u16 ip6cb_flags = 0; if (!ifindex) ifindex = sock6->sock->sk->sk_bound_dev_if; ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, ifindex, &saddr, pkey, src_port, dst_port, tos, use_cache ? dst_cache : NULL); if (IS_ERR(ndst)) { err = PTR_ERR(ndst); ndst = NULL; reason = SKB_DROP_REASON_IP_OUTNOROUTES; goto tx_error; } if (flags & VXLAN_F_MC_ROUTE) ip6cb_flags |= IP6SKB_MCROUTE; if (!info) { u32 rt6i_flags = dst_rt6_info(ndst)->rt6i_flags; err = encap_bypass_if_local(skb, dev, vxlan, AF_INET6, dst_port, ifindex, vni, ndst, rt6i_flags); if (err) goto out_unlock; } err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom((flags & VXLAN_F_GPE) | VXLAN_F_IPV6), netif_is_any_bridge_port(dev)); if (err < 0) { goto tx_error; } else if (err) { if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; unclone->key.u.ipv6.src = pkey->u.ipv6.dst; unclone->key.u.ipv6.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr), vni, md, flags, udp_sum); if (err < 0) { reason = SKB_DROP_REASON_NOMEM; goto tx_error; } udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev, &saddr, &pkey->u.ipv6.dst, tos, ttl, pkey->label, src_port, dst_port, !udp_sum, ip6cb_flags); #endif } vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX, pkt_len); out_unlock: rcu_read_unlock(); return; drop: dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, reason); return; tx_error: rcu_read_unlock(); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); dst_release(ndst); DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb_reason(skb, reason); } static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, struct vxlan_fdb *f, __be32 vni, bool did_rsc) { struct vxlan_rdst nh_rdst; struct nexthop *nh; bool do_xmit; u32 hash; memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); hash = skb_get_hash(skb); nh = rcu_dereference(f->nh); if (!nh) goto drop; do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); if (likely(do_xmit)) vxlan_xmit_one(skb, dev, vni, &nh_rdst, did_rsc); else goto drop; return; drop: dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); } static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev, u32 nhid, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst nh_rdst; struct nexthop *nh; bool do_xmit; u32 hash; memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); hash = skb_get_hash(skb); rcu_read_lock(); nh = nexthop_find_by_id(dev_net(dev), nhid); if (unlikely(!nh || !nexthop_is_fdb(nh) || !nexthop_is_multipath(nh))) { rcu_read_unlock(); goto drop; } do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); rcu_read_unlock(); if (vxlan->cfg.saddr.sa.sa_family != nh_rdst.remote_ip.sa.sa_family) goto drop; if (likely(do_xmit)) vxlan_xmit_one(skb, dev, vni, &nh_rdst, false); else goto drop; return NETDEV_TX_OK; drop: dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); return NETDEV_TX_OK; } /* Transmit local packets over Vxlan * * Outer IP header inherits ECN and DF from inner header. * Outer UDP destination is the VXLAN assigned port. * source port is based on hash of flow */ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst, *fdst = NULL; const struct ip_tunnel_info *info; struct vxlan_fdb *f; struct ethhdr *eth; __be32 vni = 0; u32 nhid = 0; bool did_rsc; info = skb_tunnel_info(skb); skb_reset_mac_header(skb); if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (info && info->mode & IP_TUNNEL_INFO_BRIDGE && info->mode & IP_TUNNEL_INFO_TX) { vni = tunnel_id_to_key32(info->key.tun_id); nhid = info->key.nhid; } else { if (info && info->mode & IP_TUNNEL_INFO_TX) vxlan_xmit_one(skb, dev, vni, NULL, false); else kfree_skb_reason(skb, SKB_DROP_REASON_TUNNEL_TXINFO); return NETDEV_TX_OK; } } if (vxlan->cfg.flags & VXLAN_F_PROXY) { eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_ARP) return arp_reduce(dev, skb, vni); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(eth->h_proto) == ETH_P_IPV6 && pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1); if (m->icmph.icmp6_code == 0 && m->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return neigh_reduce(dev, skb, vni); } #endif } if (nhid) return vxlan_xmit_nhid(skb, dev, nhid, vni); if (vxlan->cfg.flags & VXLAN_F_MDB) { struct vxlan_mdb_entry *mdb_entry; rcu_read_lock(); mdb_entry = vxlan_mdb_entry_skb_get(vxlan, skb, vni); if (mdb_entry) { netdev_tx_t ret; ret = vxlan_mdb_xmit(vxlan, mdb_entry, skb); rcu_read_unlock(); return ret; } rcu_read_unlock(); } eth = eth_hdr(skb); rcu_read_lock(); f = vxlan_find_mac_tx(vxlan, eth->h_dest, vni); did_rsc = false; if (f && (f->flags & NTF_ROUTER) && (vxlan->cfg.flags & VXLAN_F_RSC) && (ntohs(eth->h_proto) == ETH_P_IP || ntohs(eth->h_proto) == ETH_P_IPV6)) { did_rsc = route_shortcircuit(dev, skb); if (did_rsc) f = vxlan_find_mac_tx(vxlan, eth->h_dest, vni); } if (f == NULL) { f = vxlan_find_mac_tx(vxlan, all_zeros_mac, vni); if (f == NULL) { if ((vxlan->cfg.flags & VXLAN_F_L2MISS) && !is_multicast_ether_addr(eth->h_dest)) vxlan_fdb_miss(vxlan, eth->h_dest); dev_dstats_tx_dropped(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET); goto out; } } if (rcu_access_pointer(f->nh)) { vxlan_xmit_nh(skb, dev, f, (vni ? : vxlan->default_dst.remote_vni), did_rsc); } else { list_for_each_entry_rcu(rdst, &f->remotes, list) { struct sk_buff *skb1; if (!fdst) { fdst = rdst; continue; } skb1 = skb_clone(skb, GFP_ATOMIC); if (skb1) vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc); } if (fdst) vxlan_xmit_one(skb, dev, vni, fdst, did_rsc); else kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET); } out: rcu_read_unlock(); return NETDEV_TX_OK; } /* Walk the forwarding table and purge stale entries */ static void vxlan_cleanup(struct timer_list *t) { struct vxlan_dev *vxlan = timer_container_of(vxlan, t, age_timer); unsigned long next_timer = jiffies + FDB_AGE_INTERVAL; struct vxlan_fdb *f; if (!netif_running(vxlan->dev)) return; rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_list, fdb_node) { unsigned long timeout; if (f->state & (NUD_PERMANENT | NUD_NOARP)) continue; if (f->flags & NTF_EXT_LEARNED) continue; timeout = READ_ONCE(f->updated) + vxlan->cfg.age_interval * HZ; if (time_before_eq(timeout, jiffies)) { spin_lock(&vxlan->hash_lock); if (!hlist_unhashed(&f->fdb_node)) { netdev_dbg(vxlan->dev, "garbage collect %pM\n", f->key.eth_addr); f->state = NUD_STALE; vxlan_fdb_destroy(vxlan, f, true, true); } spin_unlock(&vxlan->hash_lock); } else if (time_before(timeout, next_timer)) { next_timer = timeout; } } rcu_read_unlock(); mod_timer(&vxlan->age_timer, next_timer); } static void vxlan_vs_del_dev(struct vxlan_dev *vxlan) { ASSERT_RTNL(); hlist_del_init_rcu(&vxlan->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&vxlan->hlist6.hlist); #endif } static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan, struct vxlan_dev_node *node) { __be32 vni = vxlan->default_dst.remote_vni; ASSERT_RTNL(); node->vxlan = vxlan; hlist_add_head_rcu(&node->hlist, vni_head(vs, vni)); } /* Setup stats when device is created */ static int vxlan_init(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); int err; err = rhashtable_init(&vxlan->fdb_hash_tbl, &vxlan_fdb_rht_params); if (err) return err; if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) { err = vxlan_vnigroup_init(vxlan); if (err) goto err_rhashtable_destroy; } err = gro_cells_init(&vxlan->gro_cells, dev); if (err) goto err_vnigroup_uninit; err = vxlan_mdb_init(vxlan); if (err) goto err_gro_cells_destroy; netdev_lockdep_set_classes(dev); return 0; err_gro_cells_destroy: gro_cells_destroy(&vxlan->gro_cells); err_vnigroup_uninit: if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); err_rhashtable_destroy: rhashtable_destroy(&vxlan->fdb_hash_tbl); return err; } static void vxlan_uninit(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); vxlan_mdb_fini(vxlan); if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); gro_cells_destroy(&vxlan->gro_cells); rhashtable_destroy(&vxlan->fdb_hash_tbl); } /* Start ageing timer and join group when device is brought up */ static int vxlan_open(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); int ret; ret = vxlan_sock_add(vxlan); if (ret < 0) return ret; ret = vxlan_multicast_join(vxlan); if (ret) { vxlan_sock_release(vxlan); return ret; } if (vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL); return ret; } struct vxlan_fdb_flush_desc { bool ignore_default_entry; unsigned long state; unsigned long state_mask; unsigned long flags; unsigned long flags_mask; __be32 src_vni; u32 nhid; __be32 vni; __be16 port; union vxlan_addr dst_ip; }; static bool vxlan_fdb_is_default_entry(const struct vxlan_fdb *f, const struct vxlan_dev *vxlan) { return is_zero_ether_addr(f->key.eth_addr) && f->key.vni == vxlan->cfg.vni; } static bool vxlan_fdb_nhid_matches(const struct vxlan_fdb *f, u32 nhid) { struct nexthop *nh = rtnl_dereference(f->nh); return nh && nh->id == nhid; } static bool vxlan_fdb_flush_matches(const struct vxlan_fdb *f, const struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc) { if (desc->state_mask && (f->state & desc->state_mask) != desc->state) return false; if (desc->flags_mask && (f->flags & desc->flags_mask) != desc->flags) return false; if (desc->ignore_default_entry && vxlan_fdb_is_default_entry(f, vxlan)) return false; if (desc->src_vni && f->key.vni != desc->src_vni) return false; if (desc->nhid && !vxlan_fdb_nhid_matches(f, desc->nhid)) return false; return true; } static bool vxlan_fdb_flush_should_match_remotes(const struct vxlan_fdb_flush_desc *desc) { return desc->vni || desc->port || desc->dst_ip.sa.sa_family; } static bool vxlan_fdb_flush_remote_matches(const struct vxlan_fdb_flush_desc *desc, const struct vxlan_rdst *rd) { if (desc->vni && rd->remote_vni != desc->vni) return false; if (desc->port && rd->remote_port != desc->port) return false; if (desc->dst_ip.sa.sa_family && !vxlan_addr_equal(&rd->remote_ip, &desc->dst_ip)) return false; return true; } static void vxlan_fdb_flush_match_remotes(struct vxlan_fdb *f, struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc, bool *p_destroy_fdb) { bool remotes_flushed = false; struct vxlan_rdst *rd, *tmp; list_for_each_entry_safe(rd, tmp, &f->remotes, list) { if (!vxlan_fdb_flush_remote_matches(desc, rd)) continue; vxlan_fdb_dst_destroy(vxlan, f, rd, true); remotes_flushed = true; } *p_destroy_fdb = remotes_flushed && list_empty(&f->remotes); } /* Purge the forwarding table */ static void vxlan_flush(struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc) { bool match_remotes = vxlan_fdb_flush_should_match_remotes(desc); struct vxlan_fdb *f; rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_list, fdb_node) { if (!vxlan_fdb_flush_matches(f, vxlan, desc)) continue; spin_lock_bh(&vxlan->hash_lock); if (hlist_unhashed(&f->fdb_node)) goto unlock; if (match_remotes) { bool destroy_fdb = false; vxlan_fdb_flush_match_remotes(f, vxlan, desc, &destroy_fdb); if (!destroy_fdb) goto unlock; } vxlan_fdb_destroy(vxlan, f, true, true); unlock: spin_unlock_bh(&vxlan->hash_lock); } rcu_read_unlock(); } static const struct nla_policy vxlan_del_bulk_policy[NDA_MAX + 1] = { [NDA_SRC_VNI] = { .type = NLA_U32 }, [NDA_NH_ID] = { .type = NLA_U32 }, [NDA_VNI] = { .type = NLA_U32 }, [NDA_PORT] = { .type = NLA_U16 }, [NDA_DST] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [NDA_NDM_STATE_MASK] = { .type = NLA_U16 }, [NDA_NDM_FLAGS_MASK] = { .type = NLA_U8 }, }; #define VXLAN_FDB_FLUSH_IGNORED_NDM_FLAGS (NTF_MASTER | NTF_SELF) #define VXLAN_FDB_FLUSH_ALLOWED_NDM_STATES (NUD_PERMANENT | NUD_NOARP) #define VXLAN_FDB_FLUSH_ALLOWED_NDM_FLAGS (NTF_EXT_LEARNED | NTF_OFFLOADED | \ NTF_ROUTER) static int vxlan_fdb_delete_bulk(struct nlmsghdr *nlh, struct net_device *dev, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = {}; struct ndmsg *ndm = nlmsg_data(nlh); struct nlattr *tb[NDA_MAX + 1]; u8 ndm_flags; int err; ndm_flags = ndm->ndm_flags & ~VXLAN_FDB_FLUSH_IGNORED_NDM_FLAGS; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, vxlan_del_bulk_policy, extack); if (err) return err; if (ndm_flags & ~VXLAN_FDB_FLUSH_ALLOWED_NDM_FLAGS) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm flag bits set"); return -EINVAL; } if (ndm->ndm_state & ~VXLAN_FDB_FLUSH_ALLOWED_NDM_STATES) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm state bits set"); return -EINVAL; } desc.state = ndm->ndm_state; desc.flags = ndm_flags; if (tb[NDA_NDM_STATE_MASK]) desc.state_mask = nla_get_u16(tb[NDA_NDM_STATE_MASK]); if (tb[NDA_NDM_FLAGS_MASK]) desc.flags_mask = nla_get_u8(tb[NDA_NDM_FLAGS_MASK]); if (tb[NDA_SRC_VNI]) desc.src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); if (tb[NDA_NH_ID]) desc.nhid = nla_get_u32(tb[NDA_NH_ID]); if (tb[NDA_VNI]) desc.vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); if (tb[NDA_PORT]) desc.port = nla_get_be16(tb[NDA_PORT]); if (tb[NDA_DST]) { union vxlan_addr ip; err = vxlan_nla_get_addr(&ip, tb[NDA_DST]); if (err) { NL_SET_ERR_MSG_ATTR(extack, tb[NDA_DST], "Unsupported address family"); return err; } desc.dst_ip = ip; } vxlan_flush(vxlan, &desc); return 0; } /* Cleanup timer and forwarding table on shutdown */ static int vxlan_stop(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = { /* Default entry is deleted at vxlan_dellink. */ .ignore_default_entry = true, .state = 0, .state_mask = NUD_PERMANENT | NUD_NOARP, }; vxlan_multicast_leave(vxlan); timer_delete_sync(&vxlan->age_timer); vxlan_flush(vxlan, &desc); vxlan_sock_release(vxlan); return 0; } /* Stub, nothing needs to be done. */ static void vxlan_set_multicast_list(struct net_device *dev) { } static int vxlan_change_mtu(struct net_device *dev, int new_mtu) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); /* This check is different than dev->max_mtu, because it looks at * the lowerdev->mtu, rather than the static dev->max_mtu */ if (lowerdev) { int max_mtu = lowerdev->mtu - vxlan_headroom(vxlan->cfg.flags); if (new_mtu > max_mtu) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct ip_tunnel_info *info = skb_tunnel_info(skb); __be16 sport, dport; sport = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); dport = info->key.tp_dst ? : vxlan->cfg.dst_port; if (ip_tunnel_info_af(info) == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; if (!sock4) return -EIO; rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, 0, &info->key.u.ipv4.src, &info->key, sport, dport, info->key.tos, &info->dst_cache); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); } else { #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct dst_entry *ndst; if (!sock6) return -EIO; ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, 0, &info->key.u.ipv6.src, &info->key, sport, dport, info->key.tos, &info->dst_cache); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); #else /* !CONFIG_IPV6 */ return -EPFNOSUPPORT; #endif } info->key.tp_src = sport; info->key.tp_dst = dport; return 0; } static const struct net_device_ops vxlan_netdev_ether_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_set_rx_mode = vxlan_set_multicast_list, .ndo_change_mtu = vxlan_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fdb_add = vxlan_fdb_add, .ndo_fdb_del = vxlan_fdb_delete, .ndo_fdb_del_bulk = vxlan_fdb_delete_bulk, .ndo_fdb_dump = vxlan_fdb_dump, .ndo_fdb_get = vxlan_fdb_get, .ndo_mdb_add = vxlan_mdb_add, .ndo_mdb_del = vxlan_mdb_del, .ndo_mdb_del_bulk = vxlan_mdb_del_bulk, .ndo_mdb_dump = vxlan_mdb_dump, .ndo_mdb_get = vxlan_mdb_get, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; static const struct net_device_ops vxlan_netdev_raw_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_change_mtu = vxlan_change_mtu, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type vxlan_type = { .name = "vxlan", }; /* Calls the ndo_udp_tunnel_add of the caller in order to * supply the listening VXLAN udp ports. Callers are expected * to implement the ndo_udp_tunnel_add. */ static void vxlan_offload_rx_ports(struct net_device *dev, bool push) { struct vxlan_sock *vs; struct net *net = dev_net(dev); struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int i; ASSERT_RTNL(); for (i = 0; i < PORT_HASH_SIZE; ++i) { hlist_for_each_entry(vs, &vn->sock_list[i], hlist) { unsigned short type; if (vs->flags & VXLAN_F_GPE) type = UDP_TUNNEL_TYPE_VXLAN_GPE; else type = UDP_TUNNEL_TYPE_VXLAN; if (push) udp_tunnel_push_rx_port(dev, vs->sock, type); else udp_tunnel_drop_rx_port(dev, vs->sock, type); } } } /* Initialize the device structure. */ static void vxlan_setup(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); eth_hw_addr_random(dev); ether_setup(dev); dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &vxlan_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; dev->vlan_features = dev->features; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; netif_keep_dst(dev); dev->priv_flags |= IFF_NO_QUEUE; dev->change_proto_down = true; dev->lltx = true; /* MTU range: 68 - 65535 */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_MAX_MTU; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; INIT_LIST_HEAD(&vxlan->next); spin_lock_init(&vxlan->hash_lock); timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE); vxlan->dev = dev; INIT_HLIST_HEAD(&vxlan->fdb_list); } static void vxlan_ether_setup(struct net_device *dev) { dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->netdev_ops = &vxlan_netdev_ether_ops; } static void vxlan_raw_setup(struct net_device *dev) { dev->header_ops = NULL; dev->type = ARPHRD_NONE; dev->hard_header_len = 0; dev->addr_len = 0; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->netdev_ops = &vxlan_netdev_raw_ops; } static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_UNSPEC] = { .strict_start_type = IFLA_VXLAN_LOCALBYPASS }, [IFLA_VXLAN_ID] = { .type = NLA_U32 }, [IFLA_VXLAN_GROUP] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, [IFLA_VXLAN_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, [IFLA_VXLAN_LABEL] = { .type = NLA_U32 }, [IFLA_VXLAN_LEARNING] = { .type = NLA_U8 }, [IFLA_VXLAN_AGEING] = { .type = NLA_U32 }, [IFLA_VXLAN_LIMIT] = { .type = NLA_U32 }, [IFLA_VXLAN_PORT_RANGE] = { .len = sizeof(struct ifla_vxlan_port_range) }, [IFLA_VXLAN_PROXY] = { .type = NLA_U8 }, [IFLA_VXLAN_RSC] = { .type = NLA_U8 }, [IFLA_VXLAN_L2MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_L3MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_COLLECT_METADATA] = { .type = NLA_U8 }, [IFLA_VXLAN_PORT] = { .type = NLA_U16 }, [IFLA_VXLAN_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_GBP] = { .type = NLA_FLAG, }, [IFLA_VXLAN_GPE] = { .type = NLA_FLAG, }, [IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG }, [IFLA_VXLAN_TTL_INHERIT] = { .type = NLA_FLAG }, [IFLA_VXLAN_DF] = { .type = NLA_U8 }, [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_VXLAN_LABEL_POLICY] = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX), [IFLA_VXLAN_RESERVED_BITS] = NLA_POLICY_EXACT_LEN(sizeof(struct vxlanhdr)), [IFLA_VXLAN_MC_ROUTE] = NLA_POLICY_MAX(NLA_U8, 1), }; static int vxlan_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_ATTR(extack, tb[IFLA_ADDRESS], "Provided link layer address is not Ethernet"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided Ethernet address is not unicast"); return -EADDRNOTAVAIL; } } if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); if (mtu < ETH_MIN_MTU || mtu > ETH_MAX_MTU) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], "MTU must be between 68 and 65535"); return -EINVAL; } } if (!data) { NL_SET_ERR_MSG(extack, "Required attributes not provided to perform the operation"); return -EINVAL; } if (data[IFLA_VXLAN_ID]) { u32 id = nla_get_u32(data[IFLA_VXLAN_ID]); if (id >= VXLAN_N_VID) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID], "VXLAN ID must be lower than 16777216"); return -ERANGE; } } if (data[IFLA_VXLAN_PORT_RANGE]) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); if (ntohs(p->high) < ntohs(p->low)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE], "Invalid source port range"); return -EINVAL; } } if (data[IFLA_VXLAN_DF]) { enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]); if (df < 0 || df > VXLAN_DF_MAX) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF], "Invalid DF attribute"); return -EINVAL; } } return 0; } static void vxlan_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->version, VXLAN_VERSION, sizeof(drvinfo->version)); strscpy(drvinfo->driver, "vxlan", sizeof(drvinfo->driver)); } static int vxlan_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); if (!lowerdev) { cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; cmd->base.speed = SPEED_UNKNOWN; return 0; } return __ethtool_get_link_ksettings(lowerdev, cmd); } static const struct ethtool_ops vxlan_ethtool_ops = { .get_drvinfo = vxlan_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = vxlan_get_link_ksettings, }; static struct socket *vxlan_create_sock(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { struct socket *sock; struct udp_port_cfg udp_conf; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6) { udp_conf.family = AF_INET6; udp_conf.use_udp6_rx_checksums = !(flags & VXLAN_F_UDP_ZERO_CSUM6_RX); udp_conf.ipv6_v6only = 1; } else { udp_conf.family = AF_INET; } udp_conf.local_udp_port = port; udp_conf.bind_ifindex = ifindex; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock; } /* Create new listen socket if needed */ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { struct vxlan_sock *vs; struct socket *sock; unsigned int h; struct udp_tunnel_sock_cfg tunnel_cfg; ASSERT_RTNL(); vs = kzalloc(sizeof(*vs), GFP_KERNEL); if (!vs) return ERR_PTR(-ENOMEM); for (h = 0; h < VNI_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vs->vni_list[h]); sock = vxlan_create_sock(net, ipv6, port, flags, ifindex); if (IS_ERR(sock)) { kfree(vs); return ERR_CAST(sock); } vs->sock = sock; refcount_set(&vs->refcnt, 1); vs->flags = (flags & VXLAN_F_RCV_FLAGS); hlist_add_head_rcu(&vs->hlist, vs_head(net, port)); udp_tunnel_notify_add_rx_port(sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); /* Mark socket as an encapsulation socket. */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = vs; tunnel_cfg.encap_type = 1; tunnel_cfg.encap_rcv = vxlan_rcv; tunnel_cfg.encap_err_lookup = vxlan_err_lookup; tunnel_cfg.encap_destroy = NULL; if (vs->flags & VXLAN_F_GPE) { tunnel_cfg.gro_receive = vxlan_gpe_gro_receive; tunnel_cfg.gro_complete = vxlan_gpe_gro_complete; } else { tunnel_cfg.gro_receive = vxlan_gro_receive; tunnel_cfg.gro_complete = vxlan_gro_complete; } setup_udp_tunnel_sock(net, sock, &tunnel_cfg); return vs; } static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) { bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; struct vxlan_sock *vs = NULL; struct vxlan_dev_node *node; int l3mdev_index = 0; ASSERT_RTNL(); if (vxlan->cfg.remote_ifindex) l3mdev_index = l3mdev_master_upper_ifindex_by_index( vxlan->net, vxlan->cfg.remote_ifindex); if (!vxlan->cfg.no_share) { rcu_read_lock(); vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (vs && !refcount_inc_not_zero(&vs->refcnt)) { rcu_read_unlock(); return -EBUSY; } rcu_read_unlock(); } if (!vs) vs = vxlan_socket_create(vxlan->net, ipv6, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (IS_ERR(vs)) return PTR_ERR(vs); #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { rcu_assign_pointer(vxlan->vn6_sock, vs); node = &vxlan->hlist6; } else #endif { rcu_assign_pointer(vxlan->vn4_sock, vs); node = &vxlan->hlist4; } if (metadata && (vxlan->cfg.flags & VXLAN_F_VNIFILTER)) vxlan_vs_add_vnigrp(vxlan, vs, ipv6); else vxlan_vs_add_dev(vs, vxlan, node); return 0; } static int vxlan_sock_add(struct vxlan_dev *vxlan) { bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; bool ipv6 = vxlan->cfg.flags & VXLAN_F_IPV6 || metadata; bool ipv4 = !ipv6 || metadata; int ret = 0; RCU_INIT_POINTER(vxlan->vn4_sock, NULL); #if IS_ENABLED(CONFIG_IPV6) RCU_INIT_POINTER(vxlan->vn6_sock, NULL); if (ipv6) { ret = __vxlan_sock_add(vxlan, true); if (ret < 0 && ret != -EAFNOSUPPORT) ipv4 = false; } #endif if (ipv4) ret = __vxlan_sock_add(vxlan, false); if (ret < 0) vxlan_sock_release(vxlan); return ret; } int vxlan_vni_in_use(struct net *src_net, struct vxlan_dev *vxlan, struct vxlan_config *conf, __be32 vni) { struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); struct vxlan_dev *tmp; list_for_each_entry(tmp, &vn->vxlan_list, next) { if (tmp == vxlan) continue; if (tmp->cfg.flags & VXLAN_F_VNIFILTER) { if (!vxlan_vnifilter_lookup(tmp, vni)) continue; } else if (tmp->cfg.vni != vni) { continue; } if (tmp->cfg.dst_port != conf->dst_port) continue; if ((tmp->cfg.flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6)) != (conf->flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6))) continue; if ((conf->flags & VXLAN_F_IPV6_LINKLOCAL) && tmp->cfg.remote_ifindex != conf->remote_ifindex) continue; return -EEXIST; } return 0; } static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf, struct net_device **lower, struct vxlan_dev *old, struct netlink_ext_ack *extack) { bool use_ipv6 = false; if (conf->flags & VXLAN_F_GPE) { /* For now, allow GPE only together with * COLLECT_METADATA. This can be relaxed later; in such * case, the other side of the PtP link will have to be * provided. */ if ((conf->flags & ~VXLAN_F_ALLOWED_GPE) || !(conf->flags & VXLAN_F_COLLECT_METADATA)) { NL_SET_ERR_MSG(extack, "VXLAN GPE does not support this combination of attributes"); return -EINVAL; } } if (!conf->remote_ip.sa.sa_family && !conf->saddr.sa.sa_family) { /* Unless IPv6 is explicitly requested, assume IPv4 */ conf->remote_ip.sa.sa_family = AF_INET; conf->saddr.sa.sa_family = AF_INET; } else if (!conf->remote_ip.sa.sa_family) { conf->remote_ip.sa.sa_family = conf->saddr.sa.sa_family; } else if (!conf->saddr.sa.sa_family) { conf->saddr.sa.sa_family = conf->remote_ip.sa.sa_family; } if (conf->saddr.sa.sa_family != conf->remote_ip.sa.sa_family) { NL_SET_ERR_MSG(extack, "Local and remote address must be from the same family"); return -EINVAL; } if (vxlan_addr_multicast(&conf->saddr)) { NL_SET_ERR_MSG(extack, "Local address cannot be multicast"); return -EINVAL; } if (conf->saddr.sa.sa_family == AF_INET6) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG(extack, "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } use_ipv6 = true; conf->flags |= VXLAN_F_IPV6; if (!(conf->flags & VXLAN_F_COLLECT_METADATA)) { int local_type = ipv6_addr_type(&conf->saddr.sin6.sin6_addr); int remote_type = ipv6_addr_type(&conf->remote_ip.sin6.sin6_addr); if (local_type & IPV6_ADDR_LINKLOCAL) { if (!(remote_type & IPV6_ADDR_LINKLOCAL) && (remote_type != IPV6_ADDR_ANY)) { NL_SET_ERR_MSG(extack, "Invalid combination of local and remote address scopes"); return -EINVAL; } conf->flags |= VXLAN_F_IPV6_LINKLOCAL; } else { if (remote_type == (IPV6_ADDR_UNICAST | IPV6_ADDR_LINKLOCAL)) { NL_SET_ERR_MSG(extack, "Invalid combination of local and remote address scopes"); return -EINVAL; } conf->flags &= ~VXLAN_F_IPV6_LINKLOCAL; } } } if (conf->label && !use_ipv6) { NL_SET_ERR_MSG(extack, "Label attribute only applies to IPv6 VXLAN devices"); return -EINVAL; } if (conf->label_policy && !use_ipv6) { NL_SET_ERR_MSG(extack, "Label policy only applies to IPv6 VXLAN devices"); return -EINVAL; } if (conf->remote_ifindex) { struct net_device *lowerdev; lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex); if (!lowerdev) { NL_SET_ERR_MSG(extack, "Invalid local interface, device not found"); return -ENODEV; } #if IS_ENABLED(CONFIG_IPV6) if (use_ipv6) { struct inet6_dev *idev = __in6_dev_get(lowerdev); if (idev && idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 support disabled by administrator"); return -EPERM; } } #endif *lower = lowerdev; } else { if (vxlan_addr_multicast(&conf->remote_ip)) { NL_SET_ERR_MSG(extack, "Local interface required for multicast remote destination"); return -EINVAL; } #if IS_ENABLED(CONFIG_IPV6) if (conf->flags & VXLAN_F_IPV6_LINKLOCAL) { NL_SET_ERR_MSG(extack, "Local interface required for link-local local/remote addresses"); return -EINVAL; } #endif *lower = NULL; } if (!conf->dst_port) { if (conf->flags & VXLAN_F_GPE) conf->dst_port = htons(IANA_VXLAN_GPE_UDP_PORT); else conf->dst_port = htons(vxlan_port); } if (!conf->age_interval) conf->age_interval = FDB_AGE_DEFAULT; if (vxlan_vni_in_use(src_net, old, conf, conf->vni)) { NL_SET_ERR_MSG(extack, "A VXLAN device with the specified VNI already exists"); return -EEXIST; } return 0; } static void vxlan_config_apply(struct net_device *dev, struct vxlan_config *conf, struct net_device *lowerdev, struct net *src_net, bool changelink) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; unsigned short needed_headroom = ETH_HLEN; int max_mtu = ETH_MAX_MTU; u32 flags = conf->flags; if (!changelink) { if (flags & VXLAN_F_GPE) vxlan_raw_setup(dev); else vxlan_ether_setup(dev); if (conf->mtu) dev->mtu = conf->mtu; vxlan->net = src_net; } dst->remote_vni = conf->vni; memcpy(&dst->remote_ip, &conf->remote_ip, sizeof(conf->remote_ip)); if (lowerdev) { dst->remote_ifindex = conf->remote_ifindex; netif_inherit_tso_max(dev, lowerdev); needed_headroom = lowerdev->hard_header_len; needed_headroom += lowerdev->needed_headroom; dev->needed_tailroom = lowerdev->needed_tailroom; max_mtu = lowerdev->mtu - vxlan_headroom(flags); if (max_mtu < ETH_MIN_MTU) max_mtu = ETH_MIN_MTU; if (!changelink && !conf->mtu) dev->mtu = max_mtu; } if (dev->mtu > max_mtu) dev->mtu = max_mtu; if (flags & VXLAN_F_COLLECT_METADATA) flags |= VXLAN_F_IPV6; needed_headroom += vxlan_headroom(flags); dev->needed_headroom = needed_headroom; memcpy(&vxlan->cfg, conf, sizeof(*conf)); } static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, struct vxlan_config *conf, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *lowerdev; int ret; ret = vxlan_config_validate(src_net, conf, &lowerdev, vxlan, extack); if (ret) return ret; vxlan_config_apply(dev, conf, lowerdev, src_net, false); return 0; } static int __vxlan_dev_create(struct net *net, struct net_device *dev, struct vxlan_config *conf, struct netlink_ext_ack *extack) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *remote_dev = NULL; struct vxlan_rdst *dst; int err; dst = &vxlan->default_dst; err = vxlan_dev_configure(net, dev, conf, extack); if (err) return err; dev->ethtool_ops = &vxlan_ethtool_ops; err = register_netdevice(dev); if (err) return err; if (dst->remote_ifindex) { remote_dev = __dev_get_by_index(net, dst->remote_ifindex); if (!remote_dev) { err = -ENODEV; goto unregister; } err = netdev_upper_dev_link(remote_dev, dev, extack); if (err) goto unregister; dst->remote_dev = remote_dev; } err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto unlink; /* create an fdb entry for a valid default destination */ if (!vxlan_addr_any(&dst->remote_ip)) { spin_lock_bh(&vxlan->hash_lock); err = vxlan_fdb_update(vxlan, all_zeros_mac, &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, NLM_F_EXCL | NLM_F_CREATE, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, NTF_SELF, 0, true, extack); spin_unlock_bh(&vxlan->hash_lock); if (err) goto unlink; } list_add(&vxlan->next, &vn->vxlan_list); return 0; unlink: if (remote_dev) netdev_upper_dev_unlink(remote_dev, dev); unregister: unregister_netdevice(dev); return err; } /* Set/clear flags based on attribute */ static int vxlan_nl2flag(struct vxlan_config *conf, struct nlattr *tb[], int attrtype, unsigned long mask, bool changelink, bool changelink_supported, struct netlink_ext_ack *extack) { unsigned long flags; if (!tb[attrtype]) return 0; if (changelink && !changelink_supported) { vxlan_flag_attr_error(attrtype, extack); return -EOPNOTSUPP; } if (vxlan_policy[attrtype].type == NLA_FLAG) flags = conf->flags | mask; else if (nla_get_u8(tb[attrtype])) flags = conf->flags | mask; else flags = conf->flags & ~mask; conf->flags = flags; return 0; } static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], struct net_device *dev, struct vxlan_config *conf, bool changelink, struct netlink_ext_ack *extack) { struct vxlanhdr used_bits = { .vx_flags = VXLAN_HF_VNI, .vx_vni = VXLAN_VNI_MASK, }; struct vxlan_dev *vxlan = netdev_priv(dev); int err = 0; memset(conf, 0, sizeof(*conf)); /* if changelink operation, start with old existing cfg */ if (changelink) memcpy(conf, &vxlan->cfg, sizeof(*conf)); if (data[IFLA_VXLAN_ID]) { __be32 vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); if (changelink && (vni != conf->vni)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID], "Cannot change VNI"); return -EOPNOTSUPP; } conf->vni = vni; } if (data[IFLA_VXLAN_GROUP]) { if (changelink && (conf->remote_ip.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP], "New group address family does not match old group"); return -EOPNOTSUPP; } conf->remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); conf->remote_ip.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_GROUP6]) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } if (changelink && (conf->remote_ip.sa.sa_family != AF_INET6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "New group address family does not match old group"); return -EOPNOTSUPP; } conf->remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]); conf->remote_ip.sa.sa_family = AF_INET6; } if (data[IFLA_VXLAN_LOCAL]) { if (changelink && (conf->saddr.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL], "New local address family does not match old"); return -EOPNOTSUPP; } conf->saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]); conf->saddr.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_LOCAL6]) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } if (changelink && (conf->saddr.sa.sa_family != AF_INET6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "New local address family does not match old"); return -EOPNOTSUPP; } /* TODO: respect scope id */ conf->saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]); conf->saddr.sa.sa_family = AF_INET6; } if (data[IFLA_VXLAN_LINK]) conf->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]); if (data[IFLA_VXLAN_TOS]) conf->tos = nla_get_u8(data[IFLA_VXLAN_TOS]); if (data[IFLA_VXLAN_TTL]) conf->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); if (data[IFLA_VXLAN_TTL_INHERIT]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_TTL_INHERIT, VXLAN_F_TTL_INHERIT, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_LABEL]) conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) & IPV6_FLOWLABEL_MASK; if (data[IFLA_VXLAN_LABEL_POLICY]) conf->label_policy = nla_get_u32(data[IFLA_VXLAN_LABEL_POLICY]); if (data[IFLA_VXLAN_LEARNING]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING, VXLAN_F_LEARN, changelink, true, extack); if (err) return err; } else if (!changelink) { /* default to learn on a new device */ conf->flags |= VXLAN_F_LEARN; } if (data[IFLA_VXLAN_AGEING]) conf->age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]); if (data[IFLA_VXLAN_PROXY]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_PROXY, VXLAN_F_PROXY, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_RSC]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_RSC, VXLAN_F_RSC, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_L2MISS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L2MISS, VXLAN_F_L2MISS, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_L3MISS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L3MISS, VXLAN_F_L3MISS, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_LIMIT]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LIMIT], "Cannot change limit"); return -EOPNOTSUPP; } conf->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]); } if (data[IFLA_VXLAN_COLLECT_METADATA]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_COLLECT_METADATA, VXLAN_F_COLLECT_METADATA, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_PORT_RANGE]) { if (!changelink) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); conf->port_min = ntohs(p->low); conf->port_max = ntohs(p->high); } else { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE], "Cannot change port range"); return -EOPNOTSUPP; } } if (data[IFLA_VXLAN_PORT]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT], "Cannot change port"); return -EOPNOTSUPP; } conf->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); } if (data[IFLA_VXLAN_UDP_CSUM]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_UDP_CSUM], "Cannot change UDP_CSUM flag"); return -EOPNOTSUPP; } if (!nla_get_u8(data[IFLA_VXLAN_UDP_CSUM])) conf->flags |= VXLAN_F_UDP_ZERO_CSUM_TX; } if (data[IFLA_VXLAN_LOCALBYPASS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LOCALBYPASS, VXLAN_F_LOCALBYPASS, changelink, true, extack); if (err) return err; } else if (!changelink) { /* default to local bypass on a new device */ conf->flags |= VXLAN_F_LOCALBYPASS; } if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, VXLAN_F_UDP_ZERO_CSUM6_TX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, VXLAN_F_UDP_ZERO_CSUM6_RX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_TX, VXLAN_F_REMCSUM_TX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_RX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_RX, VXLAN_F_REMCSUM_RX, changelink, false, extack); if (err) return err; used_bits.vx_flags |= VXLAN_HF_RCO; used_bits.vx_vni |= ~VXLAN_VNI_MASK; } if (data[IFLA_VXLAN_GBP]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GBP, VXLAN_F_GBP, changelink, false, extack); if (err) return err; used_bits.vx_flags |= VXLAN_GBP_USED_BITS; } if (data[IFLA_VXLAN_GPE]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GPE, VXLAN_F_GPE, changelink, false, extack); if (err) return err; used_bits.vx_flags |= VXLAN_GPE_USED_BITS; } if (data[IFLA_VXLAN_RESERVED_BITS]) { struct vxlanhdr reserved_bits; if (changelink) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_RESERVED_BITS], "Cannot change reserved_bits"); return -EOPNOTSUPP; } nla_memcpy(&reserved_bits, data[IFLA_VXLAN_RESERVED_BITS], sizeof(reserved_bits)); if (used_bits.vx_flags & reserved_bits.vx_flags || used_bits.vx_vni & reserved_bits.vx_vni) { __be64 ub_be64, rb_be64; memcpy(&ub_be64, &used_bits, sizeof(ub_be64)); memcpy(&rb_be64, &reserved_bits, sizeof(rb_be64)); NL_SET_ERR_MSG_ATTR_FMT(extack, data[IFLA_VXLAN_RESERVED_BITS], "Used bits %#018llx cannot overlap reserved bits %#018llx", be64_to_cpu(ub_be64), be64_to_cpu(rb_be64)); return -EINVAL; } conf->reserved_bits = reserved_bits; } else { /* For backwards compatibility, only allow reserved fields to be * used by VXLAN extensions if explicitly requested. */ conf->reserved_bits = (struct vxlanhdr) { .vx_flags = ~used_bits.vx_flags, .vx_vni = ~used_bits.vx_vni, }; } if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_NOPARTIAL, VXLAN_F_REMCSUM_NOPARTIAL, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_MC_ROUTE]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_MC_ROUTE, VXLAN_F_MC_ROUTE, changelink, true, extack); if (err) return err; } if (tb[IFLA_MTU]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], "Cannot change mtu"); return -EOPNOTSUPP; } conf->mtu = nla_get_u32(tb[IFLA_MTU]); } if (data[IFLA_VXLAN_DF]) conf->df = nla_get_u8(data[IFLA_VXLAN_DF]); if (data[IFLA_VXLAN_VNIFILTER]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_VNIFILTER, VXLAN_F_VNIFILTER, changelink, false, extack); if (err) return err; if ((conf->flags & VXLAN_F_VNIFILTER) && !(conf->flags & VXLAN_F_COLLECT_METADATA)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_VNIFILTER], "vxlan vnifilter only valid in collect metadata mode"); return -EINVAL; } } return 0; } static int vxlan_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct vxlan_config conf; int err; err = vxlan_nl2conf(tb, data, dev, &conf, false, extack); if (err) return err; return __vxlan_dev_create(link_net, dev, &conf, extack); } static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); bool rem_ip_changed, change_igmp; struct net_device *lowerdev; struct vxlan_config conf; struct vxlan_rdst *dst; int err; dst = &vxlan->default_dst; err = vxlan_nl2conf(tb, data, dev, &conf, true, extack); if (err) return err; err = vxlan_config_validate(vxlan->net, &conf, &lowerdev, vxlan, extack); if (err) return err; if (dst->remote_dev == lowerdev) lowerdev = NULL; err = netdev_adjacent_change_prepare(dst->remote_dev, lowerdev, dev, extack); if (err) return err; rem_ip_changed = !vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip); change_igmp = vxlan->dev->flags & IFF_UP && (rem_ip_changed || dst->remote_ifindex != conf.remote_ifindex); /* handle default dst entry */ if (rem_ip_changed) { spin_lock_bh(&vxlan->hash_lock); if (!vxlan_addr_any(&conf.remote_ip)) { err = vxlan_fdb_update(vxlan, all_zeros_mac, &conf.remote_ip, NUD_REACHABLE | NUD_PERMANENT, NLM_F_APPEND | NLM_F_CREATE, vxlan->cfg.dst_port, conf.vni, conf.vni, conf.remote_ifindex, NTF_SELF, 0, true, extack); if (err) { spin_unlock_bh(&vxlan->hash_lock); netdev_adjacent_change_abort(dst->remote_dev, lowerdev, dev); return err; } } if (!vxlan_addr_any(&dst->remote_ip)) __vxlan_fdb_delete(vxlan, all_zeros_mac, dst->remote_ip, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, true); spin_unlock_bh(&vxlan->hash_lock); /* If vni filtering device, also update fdb entries of * all vnis that were using default remote ip */ if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) { err = vxlan_vnilist_update_group(vxlan, &dst->remote_ip, &conf.remote_ip, extack); if (err) { netdev_adjacent_change_abort(dst->remote_dev, lowerdev, dev); return err; } } } if (change_igmp && vxlan_addr_multicast(&dst->remote_ip)) err = vxlan_multicast_leave(vxlan); if (conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies); netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev); if (lowerdev && lowerdev != dst->remote_dev) dst->remote_dev = lowerdev; vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true); if (!err && change_igmp && vxlan_addr_multicast(&dst->remote_ip)) err = vxlan_multicast_join(vxlan); return err; } static void vxlan_dellink(struct net_device *dev, struct list_head *head) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = {}; vxlan_flush(vxlan, &desc); list_del(&vxlan->next); unregister_netdevice_queue(dev, head); if (vxlan->default_dst.remote_dev) netdev_upper_dev_unlink(vxlan->default_dst.remote_dev, dev); } static size_t vxlan_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_GROUP{6} */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL_INHERIT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LABEL_POLICY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_PROXY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L2MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L3MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_COLLECT_METADATA */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_AGEING */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LIMIT */ nla_total_size(sizeof(__be16)) + /* IFLA_VXLAN_PORT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LOCALBYPASS */ /* IFLA_VXLAN_PORT_RANGE */ nla_total_size(sizeof(struct ifla_vxlan_port_range)) + nla_total_size(0) + /* IFLA_VXLAN_GBP */ nla_total_size(0) + /* IFLA_VXLAN_GPE */ nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */ /* IFLA_VXLAN_RESERVED_BITS */ nla_total_size(sizeof(struct vxlanhdr)) + 0; } static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { const struct vxlan_dev *vxlan = netdev_priv(dev); const struct vxlan_rdst *dst = &vxlan->default_dst; struct ifla_vxlan_port_range ports = { .low = htons(vxlan->cfg.port_min), .high = htons(vxlan->cfg.port_max), }; if (nla_put_u32(skb, IFLA_VXLAN_ID, be32_to_cpu(dst->remote_vni))) goto nla_put_failure; if (!vxlan_addr_any(&dst->remote_ip)) { if (dst->remote_ip.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_GROUP, dst->remote_ip.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_GROUP6, &dst->remote_ip.sin6.sin6_addr)) goto nla_put_failure; #endif } } if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex)) goto nla_put_failure; if (!vxlan_addr_any(&vxlan->cfg.saddr)) { if (vxlan->cfg.saddr.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_LOCAL, vxlan->cfg.saddr.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_LOCAL6, &vxlan->cfg.saddr.sin6.sin6_addr)) goto nla_put_failure; #endif } } if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT, !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) || nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || nla_put_u32(skb, IFLA_VXLAN_LABEL_POLICY, vxlan->cfg.label_policy) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, !!(vxlan->cfg.flags & VXLAN_F_LEARN)) || nla_put_u8(skb, IFLA_VXLAN_PROXY, !!(vxlan->cfg.flags & VXLAN_F_PROXY)) || nla_put_u8(skb, IFLA_VXLAN_RSC, !!(vxlan->cfg.flags & VXLAN_F_RSC)) || nla_put_u8(skb, IFLA_VXLAN_L2MISS, !!(vxlan->cfg.flags & VXLAN_F_L2MISS)) || nla_put_u8(skb, IFLA_VXLAN_L3MISS, !!(vxlan->cfg.flags & VXLAN_F_L3MISS)) || nla_put_u8(skb, IFLA_VXLAN_COLLECT_METADATA, !!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) || nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->cfg.age_interval) || nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) || nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) || nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM, !(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_TX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_RX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_RX)) || nla_put_u8(skb, IFLA_VXLAN_LOCALBYPASS, !!(vxlan->cfg.flags & VXLAN_F_LOCALBYPASS))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_GBP && nla_put_flag(skb, IFLA_VXLAN_GBP)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_GPE && nla_put_flag(skb, IFLA_VXLAN_GPE)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_REMCSUM_NOPARTIAL && nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_VNIFILTER && nla_put_u8(skb, IFLA_VXLAN_VNIFILTER, !!(vxlan->cfg.flags & VXLAN_F_VNIFILTER))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_RESERVED_BITS, sizeof(vxlan->cfg.reserved_bits), &vxlan->cfg.reserved_bits)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct net *vxlan_get_link_net(const struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); return READ_ONCE(vxlan->net); } static struct rtnl_link_ops vxlan_link_ops __read_mostly = { .kind = "vxlan", .maxtype = IFLA_VXLAN_MAX, .policy = vxlan_policy, .priv_size = sizeof(struct vxlan_dev), .setup = vxlan_setup, .validate = vxlan_validate, .newlink = vxlan_newlink, .changelink = vxlan_changelink, .dellink = vxlan_dellink, .get_size = vxlan_get_size, .fill_info = vxlan_fill_info, .get_link_net = vxlan_get_link_net, }; struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; int err; memset(&tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &vxlan_link_ops, tb, NULL); if (IS_ERR(dev)) return dev; err = __vxlan_dev_create(net, dev, conf, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) { LIST_HEAD(list_kill); vxlan_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } return dev; } EXPORT_SYMBOL_GPL(vxlan_dev_create); static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn, struct net_device *dev) { struct vxlan_dev *vxlan, *next; LIST_HEAD(list_kill); list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) { struct vxlan_rdst *dst = &vxlan->default_dst; /* In case we created vxlan device with carrier * and we loose the carrier due to module unload * we also need to remove vxlan device. In other * cases, it's not necessary and remote_ifindex * is 0 here, so no matches. */ if (dst->remote_ifindex == dev->ifindex) vxlan_dellink(vxlan->dev, &list_kill); } unregister_netdevice_many(&list_kill); } static int vxlan_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); if (event == NETDEV_UNREGISTER) vxlan_handle_lowerdev_unregister(vn, dev); else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) vxlan_offload_rx_ports(dev, true); else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) vxlan_offload_rx_ports(dev, false); return NOTIFY_DONE; } static struct notifier_block vxlan_notifier_block __read_mostly = { .notifier_call = vxlan_netdevice_event, }; static void vxlan_fdb_offloaded_set(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst; struct vxlan_fdb *f; spin_lock_bh(&vxlan->hash_lock); f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) goto out; rdst = vxlan_fdb_find_rdst(f, &fdb_info->remote_ip, fdb_info->remote_port, fdb_info->remote_vni, fdb_info->remote_ifindex); if (!rdst) goto out; rdst->offloaded = fdb_info->offloaded; out: spin_unlock_bh(&vxlan->hash_lock); } static int vxlan_fdb_external_learn_add(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct netlink_ext_ack *extack; int err; extack = switchdev_notifier_info_to_extack(&fdb_info->info); spin_lock_bh(&vxlan->hash_lock); err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip, NUD_REACHABLE, NLM_F_CREATE | NLM_F_REPLACE, fdb_info->remote_port, fdb_info->vni, fdb_info->remote_vni, fdb_info->remote_ifindex, NTF_USE | NTF_SELF | NTF_EXT_LEARNED, 0, false, extack); spin_unlock_bh(&vxlan->hash_lock); return err; } static int vxlan_fdb_external_learn_del(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; int err = 0; spin_lock_bh(&vxlan->hash_lock); f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) err = -ENOENT; else if (f->flags & NTF_EXT_LEARNED) err = __vxlan_fdb_delete(vxlan, fdb_info->eth_addr, fdb_info->remote_ip, fdb_info->remote_port, fdb_info->vni, fdb_info->remote_vni, fdb_info->remote_ifindex, false); spin_unlock_bh(&vxlan->hash_lock); return err; } static int vxlan_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct switchdev_notifier_vxlan_fdb_info *fdb_info; int err = 0; switch (event) { case SWITCHDEV_VXLAN_FDB_OFFLOADED: vxlan_fdb_offloaded_set(dev, ptr); break; case SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = vxlan_fdb_external_learn_add(dev, fdb_info); if (err) { err = notifier_from_errno(err); break; } fdb_info->offloaded = true; vxlan_fdb_offloaded_set(dev, fdb_info); break; case SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = vxlan_fdb_external_learn_del(dev, fdb_info); if (err) { err = notifier_from_errno(err); break; } fdb_info->offloaded = false; vxlan_fdb_offloaded_set(dev, fdb_info); break; } return err; } static struct notifier_block vxlan_switchdev_notifier_block __read_mostly = { .notifier_call = vxlan_switchdev_event, }; static void vxlan_fdb_nh_flush(struct nexthop *nh) { struct vxlan_fdb *fdb; struct vxlan_dev *vxlan; rcu_read_lock(); list_for_each_entry_rcu(fdb, &nh->fdb_list, nh_list) { vxlan = rcu_dereference(fdb->vdev); WARN_ON(!vxlan); spin_lock_bh(&vxlan->hash_lock); if (!hlist_unhashed(&fdb->fdb_node)) vxlan_fdb_destroy(vxlan, fdb, false, false); spin_unlock_bh(&vxlan->hash_lock); } rcu_read_unlock(); } static int vxlan_nexthop_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct nh_notifier_info *info = ptr; struct nexthop *nh; if (event != NEXTHOP_EVENT_DEL) return NOTIFY_DONE; nh = nexthop_find_by_id(info->net, info->id); if (!nh) return NOTIFY_DONE; vxlan_fdb_nh_flush(nh); return NOTIFY_DONE; } static __net_init int vxlan_init_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int h; INIT_LIST_HEAD(&vn->vxlan_list); vn->nexthop_notifier_block.notifier_call = vxlan_nexthop_event; for (h = 0; h < PORT_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vn->sock_list[h]); return register_nexthop_notifier(net, &vn->nexthop_notifier_block, NULL); } static void __net_exit vxlan_destroy_tunnels(struct vxlan_net *vn, struct list_head *dev_to_kill) { struct vxlan_dev *vxlan, *next; list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) vxlan_dellink(vxlan->dev, dev_to_kill); } static void __net_exit vxlan_exit_rtnl(struct net *net, struct list_head *dev_to_kill) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); ASSERT_RTNL_NET(net); __unregister_nexthop_notifier(net, &vn->nexthop_notifier_block); vxlan_destroy_tunnels(vn, dev_to_kill); } static void __net_exit vxlan_exit_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int h; for (h = 0; h < PORT_HASH_SIZE; ++h) WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h])); } static struct pernet_operations vxlan_net_ops = { .init = vxlan_init_net, .exit_rtnl = vxlan_exit_rtnl, .exit = vxlan_exit_net, .id = &vxlan_net_id, .size = sizeof(struct vxlan_net), }; static int __init vxlan_init_module(void) { int rc; rc = register_pernet_subsys(&vxlan_net_ops); if (rc) goto out1; rc = register_netdevice_notifier(&vxlan_notifier_block); if (rc) goto out2; rc = register_switchdev_notifier(&vxlan_switchdev_notifier_block); if (rc) goto out3; rc = rtnl_link_register(&vxlan_link_ops); if (rc) goto out4; rc = vxlan_vnifilter_init(); if (rc) goto out5; return 0; out5: rtnl_link_unregister(&vxlan_link_ops); out4: unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); out3: unregister_netdevice_notifier(&vxlan_notifier_block); out2: unregister_pernet_subsys(&vxlan_net_ops); out1: return rc; } late_initcall(vxlan_init_module); static void __exit vxlan_cleanup_module(void) { vxlan_vnifilter_uninit(); rtnl_link_unregister(&vxlan_link_ops); unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); unregister_netdevice_notifier(&vxlan_notifier_block); unregister_pernet_subsys(&vxlan_net_ops); /* rcu_barrier() is called by netns */ } module_exit(vxlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(VXLAN_VERSION); MODULE_AUTHOR("Stephen Hemminger <stephen@networkplumber.org>"); MODULE_DESCRIPTION("Driver for VXLAN encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("vxlan"); |
| 8 1 1 1 6 6 5 1 1 1 1 1 5 5 1 5 6 1 1 1 14 1 13 1 11 11 3 12 12 11 13 6 7 11 11 3 11 11 21 21 | 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 | // SPDX-License-Identifier: GPL-2.0+ // // em28xx-i2c.c - driver for Empia EM2800/EM2820/2840 USB video capture devices // // Copyright (C) 2005 Ludovico Cavedon <cavedon@sssup.it> // Markus Rechberger <mrechberger@gmail.com> // Mauro Carvalho Chehab <mchehab@kernel.org> // Sascha Sommer <saschasommer@freenet.de> // Copyright (C) 2013 Frank Schäfer <fschaefer.oss@googlemail.com> #include "em28xx.h" #include <linux/module.h> #include <linux/kernel.h> #include <linux/usb.h> #include <linux/i2c.h> #include <linux/jiffies.h> #include "xc2028.h" #include <media/v4l2-common.h> #include <media/tuner.h> /* ----------------------------------------------------------- */ static unsigned int i2c_scan; module_param(i2c_scan, int, 0444); MODULE_PARM_DESC(i2c_scan, "scan i2c bus at insmod time"); static unsigned int i2c_debug; module_param(i2c_debug, int, 0644); MODULE_PARM_DESC(i2c_debug, "i2c debug message level (1: normal debug, 2: show I2C transfers)"); #define dprintk(level, fmt, arg...) do { \ if (i2c_debug > level) \ dev_printk(KERN_DEBUG, &dev->intf->dev, \ "i2c: %s: " fmt, __func__, ## arg); \ } while (0) /* * Time in msecs to wait for i2c xfers to finish. * 35ms is the maximum time a SMBUS device could wait when * clock stretching is used. As the transfer itself will take * some time to happen, set it to 35 ms. * * Ok, I2C doesn't specify any limit. So, eventually, we may need * to increase this timeout. */ #define EM28XX_I2C_XFER_TIMEOUT 35 /* ms */ static int em28xx_i2c_timeout(struct em28xx *dev) { int time = EM28XX_I2C_XFER_TIMEOUT; switch (dev->i2c_speed & 0x03) { case EM28XX_I2C_FREQ_25_KHZ: time += 4; /* Assume 4 ms for transfers */ break; case EM28XX_I2C_FREQ_100_KHZ: case EM28XX_I2C_FREQ_400_KHZ: time += 1; /* Assume 1 ms for transfers */ break; default: /* EM28XX_I2C_FREQ_1_5_MHZ */ break; } return msecs_to_jiffies(time); } /* * em2800_i2c_send_bytes() * send up to 4 bytes to the em2800 i2c device */ static int em2800_i2c_send_bytes(struct em28xx *dev, u8 addr, u8 *buf, u16 len) { unsigned long timeout = jiffies + em28xx_i2c_timeout(dev); int ret; u8 b2[6]; if (len < 1 || len > 4) return -EOPNOTSUPP; b2[5] = 0x80 + len - 1; b2[4] = addr; b2[3] = buf[0]; if (len > 1) b2[2] = buf[1]; if (len > 2) b2[1] = buf[2]; if (len > 3) b2[0] = buf[3]; /* trigger write */ ret = dev->em28xx_write_regs(dev, 4 - len, &b2[4 - len], 2 + len); if (ret != 2 + len) { dev_warn(&dev->intf->dev, "failed to trigger write to i2c address 0x%x (error=%i)\n", addr, ret); return (ret < 0) ? ret : -EIO; } /* wait for completion */ while (time_is_after_jiffies(timeout)) { ret = dev->em28xx_read_reg(dev, 0x05); if (ret == 0x80 + len - 1) return len; if (ret == 0x94 + len - 1) { dprintk(1, "R05 returned 0x%02x: I2C ACK error\n", ret); return -ENXIO; } if (ret < 0) { dev_warn(&dev->intf->dev, "failed to get i2c transfer status from bridge register (error=%i)\n", ret); return ret; } usleep_range(5000, 6000); } dprintk(0, "write to i2c device at 0x%x timed out\n", addr); return -ETIMEDOUT; } /* * em2800_i2c_recv_bytes() * read up to 4 bytes from the em2800 i2c device */ static int em2800_i2c_recv_bytes(struct em28xx *dev, u8 addr, u8 *buf, u16 len) { unsigned long timeout = jiffies + em28xx_i2c_timeout(dev); u8 buf2[4]; int ret; int i; if (len < 1 || len > 4) return -EOPNOTSUPP; /* trigger read */ buf2[1] = 0x84 + len - 1; buf2[0] = addr; ret = dev->em28xx_write_regs(dev, 0x04, buf2, 2); if (ret != 2) { dev_warn(&dev->intf->dev, "failed to trigger read from i2c address 0x%x (error=%i)\n", addr, ret); return (ret < 0) ? ret : -EIO; } /* wait for completion */ while (time_is_after_jiffies(timeout)) { ret = dev->em28xx_read_reg(dev, 0x05); if (ret == 0x84 + len - 1) break; if (ret == 0x94 + len - 1) { dprintk(1, "R05 returned 0x%02x: I2C ACK error\n", ret); return -ENXIO; } if (ret < 0) { dev_warn(&dev->intf->dev, "failed to get i2c transfer status from bridge register (error=%i)\n", ret); return ret; } usleep_range(5000, 6000); } if (ret != 0x84 + len - 1) dprintk(0, "read from i2c device at 0x%x timed out\n", addr); /* get the received message */ ret = dev->em28xx_read_reg_req_len(dev, 0x00, 4 - len, buf2, len); if (ret != len) { dev_warn(&dev->intf->dev, "reading from i2c device at 0x%x failed: couldn't get the received message from the bridge (error=%i)\n", addr, ret); return (ret < 0) ? ret : -EIO; } for (i = 0; i < len; i++) buf[i] = buf2[len - 1 - i]; return ret; } /* * em2800_i2c_check_for_device() * check if there is an i2c device at the supplied address */ static int em2800_i2c_check_for_device(struct em28xx *dev, u8 addr) { u8 buf; int ret; ret = em2800_i2c_recv_bytes(dev, addr, &buf, 1); if (ret == 1) return 0; return (ret < 0) ? ret : -EIO; } /* * em28xx_i2c_send_bytes() */ static int em28xx_i2c_send_bytes(struct em28xx *dev, u16 addr, u8 *buf, u16 len, int stop) { unsigned long timeout = jiffies + em28xx_i2c_timeout(dev); int ret; if (len < 1 || len > 64) return -EOPNOTSUPP; /* * NOTE: limited by the USB ctrl message constraints * Zero length reads always succeed, even if no device is connected */ /* Write to i2c device */ ret = dev->em28xx_write_regs_req(dev, stop ? 2 : 3, addr, buf, len); if (ret != len) { if (ret < 0) { dev_warn(&dev->intf->dev, "writing to i2c device at 0x%x failed (error=%i)\n", addr, ret); return ret; } dev_warn(&dev->intf->dev, "%i bytes write to i2c device at 0x%x requested, but %i bytes written\n", len, addr, ret); return -EIO; } /* wait for completion */ while (time_is_after_jiffies(timeout)) { ret = dev->em28xx_read_reg(dev, 0x05); if (ret == 0) /* success */ return len; if (ret == 0x10) { dprintk(1, "I2C ACK error on writing to addr 0x%02x\n", addr); return -ENXIO; } if (ret < 0) { dev_warn(&dev->intf->dev, "failed to get i2c transfer status from bridge register (error=%i)\n", ret); return ret; } usleep_range(5000, 6000); /* * NOTE: do we really have to wait for success ? * Never seen anything else than 0x00 or 0x10 * (even with high payload) ... */ } if (ret == 0x02 || ret == 0x04) { /* NOTE: these errors seem to be related to clock stretching */ dprintk(0, "write to i2c device at 0x%x timed out (status=%i)\n", addr, ret); return -ETIMEDOUT; } dev_warn(&dev->intf->dev, "write to i2c device at 0x%x failed with unknown error (status=%i)\n", addr, ret); return -EIO; } /* * em28xx_i2c_recv_bytes() * read a byte from the i2c device */ static int em28xx_i2c_recv_bytes(struct em28xx *dev, u16 addr, u8 *buf, u16 len) { int ret; if (len < 1 || len > 64) return -EOPNOTSUPP; /* * NOTE: limited by the USB ctrl message constraints * Zero length reads always succeed, even if no device is connected */ /* Read data from i2c device */ ret = dev->em28xx_read_reg_req_len(dev, 2, addr, buf, len); if (ret < 0) { dev_warn(&dev->intf->dev, "reading from i2c device at 0x%x failed (error=%i)\n", addr, ret); return ret; } else if (ret != len) { dev_dbg(&dev->intf->dev, "%i bytes read from i2c device at 0x%x requested, but %i bytes written\n", ret, addr, len); } /* * NOTE: some devices with two i2c buses have the bad habit to return 0 * bytes if we are on bus B AND there was no write attempt to the * specified slave address before AND no device is present at the * requested slave address. * Anyway, the next check will fail with -ENXIO in this case, so avoid * spamming the system log on device probing and do nothing here. */ /* Check success of the i2c operation */ ret = dev->em28xx_read_reg(dev, 0x05); if (ret == 0) /* success */ return len; if (ret < 0) { dev_warn(&dev->intf->dev, "failed to get i2c transfer status from bridge register (error=%i)\n", ret); return ret; } if (ret == 0x10) { dprintk(1, "I2C ACK error on writing to addr 0x%02x\n", addr); return -ENXIO; } if (ret == 0x02 || ret == 0x04) { /* NOTE: these errors seem to be related to clock stretching */ dprintk(0, "write to i2c device at 0x%x timed out (status=%i)\n", addr, ret); return -ETIMEDOUT; } dev_warn(&dev->intf->dev, "read from i2c device at 0x%x failed with unknown error (status=%i)\n", addr, ret); return -EIO; } /* * em28xx_i2c_check_for_device() * check if there is a i2c_device at the supplied address */ static int em28xx_i2c_check_for_device(struct em28xx *dev, u16 addr) { int ret; u8 buf; ret = em28xx_i2c_recv_bytes(dev, addr, &buf, 1); if (ret == 1) return 0; return (ret < 0) ? ret : -EIO; } /* * em25xx_bus_B_send_bytes * write bytes to the i2c device */ static int em25xx_bus_B_send_bytes(struct em28xx *dev, u16 addr, u8 *buf, u16 len) { int ret; if (len < 1 || len > 64) return -EOPNOTSUPP; /* * NOTE: limited by the USB ctrl message constraints * Zero length reads always succeed, even if no device is connected */ /* Set register and write value */ ret = dev->em28xx_write_regs_req(dev, 0x06, addr, buf, len); if (ret != len) { if (ret < 0) { dev_warn(&dev->intf->dev, "writing to i2c device at 0x%x failed (error=%i)\n", addr, ret); return ret; } dev_warn(&dev->intf->dev, "%i bytes write to i2c device at 0x%x requested, but %i bytes written\n", len, addr, ret); return -EIO; } /* Check success */ ret = dev->em28xx_read_reg_req(dev, 0x08, 0x0000); /* * NOTE: the only error we've seen so far is * 0x01 when the slave device is not present */ if (!ret) return len; if (ret > 0) { dprintk(1, "Bus B R08 returned 0x%02x: I2C ACK error\n", ret); return -ENXIO; } return ret; /* * NOTE: With chip types (other chip IDs) which actually don't support * this operation, it seems to succeed ALWAYS ! (even if there is no * slave device or even no second i2c bus provided) */ } /* * em25xx_bus_B_recv_bytes * read bytes from the i2c device */ static int em25xx_bus_B_recv_bytes(struct em28xx *dev, u16 addr, u8 *buf, u16 len) { int ret; if (len < 1 || len > 64) return -EOPNOTSUPP; /* * NOTE: limited by the USB ctrl message constraints * Zero length reads always succeed, even if no device is connected */ /* Read value */ ret = dev->em28xx_read_reg_req_len(dev, 0x06, addr, buf, len); if (ret < 0) { dev_warn(&dev->intf->dev, "reading from i2c device at 0x%x failed (error=%i)\n", addr, ret); return ret; } /* * NOTE: some devices with two i2c buses have the bad habit to return 0 * bytes if we are on bus B AND there was no write attempt to the * specified slave address before AND no device is present at the * requested slave address. * Anyway, the next check will fail with -ENXIO in this case, so avoid * spamming the system log on device probing and do nothing here. */ /* Check success */ ret = dev->em28xx_read_reg_req(dev, 0x08, 0x0000); /* * NOTE: the only error we've seen so far is * 0x01 when the slave device is not present */ if (!ret) return len; if (ret > 0) { dprintk(1, "Bus B R08 returned 0x%02x: I2C ACK error\n", ret); return -ENXIO; } return ret; /* * NOTE: With chip types (other chip IDs) which actually don't support * this operation, it seems to succeed ALWAYS ! (even if there is no * slave device or even no second i2c bus provided) */ } /* * em25xx_bus_B_check_for_device() * check if there is a i2c device at the supplied address */ static int em25xx_bus_B_check_for_device(struct em28xx *dev, u16 addr) { u8 buf; int ret; ret = em25xx_bus_B_recv_bytes(dev, addr, &buf, 1); if (ret < 0) return ret; return 0; /* * NOTE: With chips which do not support this operation, * it seems to succeed ALWAYS ! (even if no device connected) */ } static inline int i2c_check_for_device(struct em28xx_i2c_bus *i2c_bus, u16 addr) { struct em28xx *dev = i2c_bus->dev; int rc = -EOPNOTSUPP; if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM28XX) rc = em28xx_i2c_check_for_device(dev, addr); else if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM2800) rc = em2800_i2c_check_for_device(dev, addr); else if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM25XX_BUS_B) rc = em25xx_bus_B_check_for_device(dev, addr); return rc; } static inline int i2c_recv_bytes(struct em28xx_i2c_bus *i2c_bus, struct i2c_msg msg) { struct em28xx *dev = i2c_bus->dev; u16 addr = msg.addr << 1; int rc = -EOPNOTSUPP; if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM28XX) rc = em28xx_i2c_recv_bytes(dev, addr, msg.buf, msg.len); else if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM2800) rc = em2800_i2c_recv_bytes(dev, addr, msg.buf, msg.len); else if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM25XX_BUS_B) rc = em25xx_bus_B_recv_bytes(dev, addr, msg.buf, msg.len); return rc; } static inline int i2c_send_bytes(struct em28xx_i2c_bus *i2c_bus, struct i2c_msg msg, int stop) { struct em28xx *dev = i2c_bus->dev; u16 addr = msg.addr << 1; int rc = -EOPNOTSUPP; if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM28XX) rc = em28xx_i2c_send_bytes(dev, addr, msg.buf, msg.len, stop); else if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM2800) rc = em2800_i2c_send_bytes(dev, addr, msg.buf, msg.len); else if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM25XX_BUS_B) rc = em25xx_bus_B_send_bytes(dev, addr, msg.buf, msg.len); return rc; } /* * em28xx_i2c_xfer() * the main i2c transfer function */ static int em28xx_i2c_xfer(struct i2c_adapter *i2c_adap, struct i2c_msg msgs[], int num) { struct em28xx_i2c_bus *i2c_bus = i2c_adap->algo_data; struct em28xx *dev = i2c_bus->dev; unsigned int bus = i2c_bus->bus; int addr, rc, i; u8 reg; /* * prevent i2c xfer attempts after device is disconnected * some fe's try to do i2c writes/reads from their release * interfaces when called in disconnect path */ if (dev->disconnected) return -ENODEV; if (!rt_mutex_trylock(&dev->i2c_bus_lock)) return -EAGAIN; /* Switch I2C bus if needed */ if (bus != dev->cur_i2c_bus && i2c_bus->algo_type == EM28XX_I2C_ALGO_EM28XX) { if (bus == 1) reg = EM2874_I2C_SECONDARY_BUS_SELECT; else reg = 0; em28xx_write_reg_bits(dev, EM28XX_R06_I2C_CLK, reg, EM2874_I2C_SECONDARY_BUS_SELECT); dev->cur_i2c_bus = bus; } for (i = 0; i < num; i++) { addr = msgs[i].addr << 1; if (!msgs[i].len) { /* * no len: check only for device presence * This code is only called during device probe. */ rc = i2c_check_for_device(i2c_bus, addr); if (rc == -ENXIO) rc = -ENODEV; } else if (msgs[i].flags & I2C_M_RD) { /* read bytes */ rc = i2c_recv_bytes(i2c_bus, msgs[i]); } else { /* write bytes */ rc = i2c_send_bytes(i2c_bus, msgs[i], i == num - 1); } if (rc < 0) goto error; dprintk(2, "%s %s addr=%02x len=%d: %*ph\n", (msgs[i].flags & I2C_M_RD) ? "read" : "write", i == num - 1 ? "stop" : "nonstop", addr, msgs[i].len, msgs[i].len, msgs[i].buf); } rt_mutex_unlock(&dev->i2c_bus_lock); return num; error: dprintk(2, "%s %s addr=%02x len=%d: %sERROR: %i\n", (msgs[i].flags & I2C_M_RD) ? "read" : "write", i == num - 1 ? "stop" : "nonstop", addr, msgs[i].len, (rc == -ENODEV) ? "no device " : "", rc); rt_mutex_unlock(&dev->i2c_bus_lock); return rc; } /* * based on linux/sunrpc/svcauth.h and linux/hash.h * The original hash function returns a different value, if arch is x86_64 * or i386. */ static inline unsigned long em28xx_hash_mem(char *buf, int length, int bits) { unsigned long hash = 0; unsigned long l = 0; int len = 0; unsigned char c; do { if (len == length) { c = (char)len; len = -1; } else { c = *buf++; } l = (l << 8) | c; len++; if ((len & (32 / 8 - 1)) == 0) hash = ((hash ^ l) * 0x9e370001UL); } while (len); return (hash >> (32 - bits)) & 0xffffffffUL; } /* * Helper function to read data blocks from i2c clients with 8 or 16 bit * address width, 8 bit register width and auto incrementation been activated */ static int em28xx_i2c_read_block(struct em28xx *dev, unsigned int bus, u16 addr, bool addr_w16, u16 len, u8 *data) { int remain = len, rsize, rsize_max, ret; u8 buf[2]; /* Sanity check */ if (addr + remain > (addr_w16 * 0xff00 + 0xff + 1)) return -EINVAL; /* Select address */ buf[0] = addr >> 8; buf[1] = addr & 0xff; ret = i2c_master_send(&dev->i2c_client[bus], buf + !addr_w16, 1 + addr_w16); if (ret < 0) return ret; /* Read data */ if (dev->board.is_em2800) rsize_max = 4; else rsize_max = 64; while (remain > 0) { if (remain > rsize_max) rsize = rsize_max; else rsize = remain; ret = i2c_master_recv(&dev->i2c_client[bus], data, rsize); if (ret < 0) return ret; remain -= rsize; data += rsize; } return len; } static int em28xx_i2c_eeprom(struct em28xx *dev, unsigned int bus, u8 **eedata, u16 *eedata_len) { const u16 len = 256; /* * FIXME common length/size for bytes to read, to display, hash * calculation and returned device dataset. Simplifies the code a lot, * but we might have to deal with multiple sizes in the future ! */ int err; struct em28xx_eeprom *dev_config; u8 buf, *data; *eedata = NULL; *eedata_len = 0; /* EEPROM is always on i2c bus 0 on all known devices. */ dev->i2c_client[bus].addr = 0xa0 >> 1; /* Check if board has eeprom */ err = i2c_master_recv(&dev->i2c_client[bus], &buf, 0); if (err < 0) { dev_info(&dev->intf->dev, "board has no eeprom\n"); return -ENODEV; } data = kzalloc(len, GFP_KERNEL); if (!data) return -ENOMEM; /* Read EEPROM content */ err = em28xx_i2c_read_block(dev, bus, 0x0000, dev->eeprom_addrwidth_16bit, len, data); if (err != len) { dev_err(&dev->intf->dev, "failed to read eeprom (err=%d)\n", err); goto error; } if (i2c_debug) { /* Display eeprom content */ print_hex_dump(KERN_DEBUG, "em28xx eeprom ", DUMP_PREFIX_OFFSET, 16, 1, data, len, true); if (dev->eeprom_addrwidth_16bit) dev_info(&dev->intf->dev, "eeprom %06x: ... (skipped)\n", 256); } if (dev->eeprom_addrwidth_16bit && data[0] == 0x26 && data[3] == 0x00) { /* new eeprom format; size 4-64kb */ u16 mc_start; u16 hwconf_offset; dev->hash = em28xx_hash_mem(data, len, 32); mc_start = (data[1] << 8) + 4; /* usually 0x0004 */ dev_info(&dev->intf->dev, "EEPROM ID = %4ph, EEPROM hash = 0x%08lx\n", data, dev->hash); dev_info(&dev->intf->dev, "EEPROM info:\n"); dev_info(&dev->intf->dev, "\tmicrocode start address = 0x%04x, boot configuration = 0x%02x\n", mc_start, data[2]); /* * boot configuration (address 0x0002): * [0] microcode download speed: 1 = 400 kHz; 0 = 100 kHz * [1] always selects 12 kb RAM * [2] USB device speed: 1 = force Full Speed; 0 = auto detect * [4] 1 = force fast mode and no suspend for device testing * [5:7] USB PHY tuning registers; determined by device * characterization */ /* * Read hardware config dataset offset from address * (microcode start + 46) */ err = em28xx_i2c_read_block(dev, bus, mc_start + 46, 1, 2, data); if (err != 2) { dev_err(&dev->intf->dev, "failed to read hardware configuration data from eeprom (err=%d)\n", err); goto error; } /* Calculate hardware config dataset start address */ hwconf_offset = mc_start + data[0] + (data[1] << 8); /* Read hardware config dataset */ /* * NOTE: the microcode copy can be multiple pages long, but * we assume the hardware config dataset is the same as in * the old eeprom and not longer than 256 bytes. * tveeprom is currently also limited to 256 bytes. */ err = em28xx_i2c_read_block(dev, bus, hwconf_offset, 1, len, data); if (err != len) { dev_err(&dev->intf->dev, "failed to read hardware configuration data from eeprom (err=%d)\n", err); goto error; } /* Verify hardware config dataset */ /* NOTE: not all devices provide this type of dataset */ if (data[0] != 0x1a || data[1] != 0xeb || data[2] != 0x67 || data[3] != 0x95) { dev_info(&dev->intf->dev, "\tno hardware configuration dataset found in eeprom\n"); kfree(data); return 0; } /* * TODO: decrypt eeprom data for camera bridges * (em25xx, em276x+) */ } else if (!dev->eeprom_addrwidth_16bit && data[0] == 0x1a && data[1] == 0xeb && data[2] == 0x67 && data[3] == 0x95) { dev->hash = em28xx_hash_mem(data, len, 32); dev_info(&dev->intf->dev, "EEPROM ID = %4ph, EEPROM hash = 0x%08lx\n", data, dev->hash); dev_info(&dev->intf->dev, "EEPROM info:\n"); } else { dev_info(&dev->intf->dev, "unknown eeprom format or eeprom corrupted !\n"); err = -ENODEV; goto error; } *eedata = data; *eedata_len = len; dev_config = (void *)*eedata; switch (le16_to_cpu(dev_config->chip_conf) >> 4 & 0x3) { case 0: dev_info(&dev->intf->dev, "\tNo audio on board.\n"); break; case 1: dev_info(&dev->intf->dev, "\tAC97 audio (5 sample rates)\n"); break; case 2: if (dev->chip_id < CHIP_ID_EM2860) dev_info(&dev->intf->dev, "\tI2S audio, sample rate=32k\n"); else dev_info(&dev->intf->dev, "\tI2S audio, 3 sample rates\n"); break; case 3: if (dev->chip_id < CHIP_ID_EM2860) dev_info(&dev->intf->dev, "\tI2S audio, 3 sample rates\n"); else dev_info(&dev->intf->dev, "\tI2S audio, 5 sample rates\n"); break; } if (le16_to_cpu(dev_config->chip_conf) & 1 << 3) dev_info(&dev->intf->dev, "\tUSB Remote wakeup capable\n"); if (le16_to_cpu(dev_config->chip_conf) & 1 << 2) dev_info(&dev->intf->dev, "\tUSB Self power capable\n"); switch (le16_to_cpu(dev_config->chip_conf) & 0x3) { case 0: dev_info(&dev->intf->dev, "\t500mA max power\n"); break; case 1: dev_info(&dev->intf->dev, "\t400mA max power\n"); break; case 2: dev_info(&dev->intf->dev, "\t300mA max power\n"); break; case 3: dev_info(&dev->intf->dev, "\t200mA max power\n"); break; } dev_info(&dev->intf->dev, "\tTable at offset 0x%02x, strings=0x%04x, 0x%04x, 0x%04x\n", dev_config->string_idx_table, le16_to_cpu(dev_config->string1), le16_to_cpu(dev_config->string2), le16_to_cpu(dev_config->string3)); return 0; error: kfree(data); return err; } /* ----------------------------------------------------------- */ /* * functionality() */ static u32 functionality(struct i2c_adapter *i2c_adap) { struct em28xx_i2c_bus *i2c_bus = i2c_adap->algo_data; if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM28XX || i2c_bus->algo_type == EM28XX_I2C_ALGO_EM25XX_BUS_B) { return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; } else if (i2c_bus->algo_type == EM28XX_I2C_ALGO_EM2800) { return (I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL) & ~I2C_FUNC_SMBUS_WRITE_BLOCK_DATA; } WARN(1, "Unknown i2c bus algorithm.\n"); return 0; } static const struct i2c_algorithm em28xx_algo = { .master_xfer = em28xx_i2c_xfer, .functionality = functionality, }; static const struct i2c_adapter em28xx_adap_template = { .owner = THIS_MODULE, .name = "em28xx", .algo = &em28xx_algo, }; static const struct i2c_client em28xx_client_template = { .name = "em28xx internal", }; /* ----------------------------------------------------------- */ /* * i2c_devs * incomplete list of known devices */ static char *i2c_devs[128] = { [0x1c >> 1] = "lgdt330x", [0x3e >> 1] = "remote IR sensor", [0x4a >> 1] = "saa7113h", [0x52 >> 1] = "drxk", [0x60 >> 1] = "remote IR sensor", [0x8e >> 1] = "remote IR sensor", [0x86 >> 1] = "tda9887", [0x80 >> 1] = "msp34xx", [0x88 >> 1] = "msp34xx", [0xa0 >> 1] = "eeprom", [0xb0 >> 1] = "tda9874", [0xb8 >> 1] = "tvp5150a", [0xba >> 1] = "webcam sensor or tvp5150a", [0xc0 >> 1] = "tuner (analog)", [0xc2 >> 1] = "tuner (analog)", [0xc4 >> 1] = "tuner (analog)", [0xc6 >> 1] = "tuner (analog)", }; /* * do_i2c_scan() * check i2c address range for devices */ void em28xx_do_i2c_scan(struct em28xx *dev, unsigned int bus) { u8 i2c_devicelist[128]; unsigned char buf; int i, rc; memset(i2c_devicelist, 0, sizeof(i2c_devicelist)); for (i = 0; i < ARRAY_SIZE(i2c_devs); i++) { dev->i2c_client[bus].addr = i; rc = i2c_master_recv(&dev->i2c_client[bus], &buf, 0); if (rc < 0) continue; i2c_devicelist[i] = i; dev_info(&dev->intf->dev, "found i2c device @ 0x%x on bus %d [%s]\n", i << 1, bus, i2c_devs[i] ? i2c_devs[i] : "???"); } if (bus == dev->def_i2c_bus) dev->i2c_hash = em28xx_hash_mem(i2c_devicelist, sizeof(i2c_devicelist), 32); } /* * em28xx_i2c_register() * register i2c bus */ int em28xx_i2c_register(struct em28xx *dev, unsigned int bus, enum em28xx_i2c_algo_type algo_type) { int retval; if (WARN_ON(!dev->em28xx_write_regs || !dev->em28xx_read_reg || !dev->em28xx_write_regs_req || !dev->em28xx_read_reg_req)) return -ENODEV; if (bus >= NUM_I2C_BUSES) return -ENODEV; dev->i2c_adap[bus] = em28xx_adap_template; dev->i2c_adap[bus].dev.parent = &dev->intf->dev; strscpy(dev->i2c_adap[bus].name, dev_name(&dev->intf->dev), sizeof(dev->i2c_adap[bus].name)); dev->i2c_bus[bus].bus = bus; dev->i2c_bus[bus].algo_type = algo_type; dev->i2c_bus[bus].dev = dev; dev->i2c_adap[bus].algo_data = &dev->i2c_bus[bus]; retval = i2c_add_adapter(&dev->i2c_adap[bus]); if (retval < 0) { dev_err(&dev->intf->dev, "%s: i2c_add_adapter failed! retval [%d]\n", __func__, retval); return retval; } dev->i2c_client[bus] = em28xx_client_template; dev->i2c_client[bus].adapter = &dev->i2c_adap[bus]; /* Up to now, all eeproms are at bus 0 */ if (!bus) { retval = em28xx_i2c_eeprom(dev, bus, &dev->eedata, &dev->eedata_len); if (retval < 0 && retval != -ENODEV) { dev_err(&dev->intf->dev, "%s: em28xx_i2_eeprom failed! retval [%d]\n", __func__, retval); } } if (i2c_scan) em28xx_do_i2c_scan(dev, bus); return 0; } /* * em28xx_i2c_unregister() * unregister i2c_bus */ int em28xx_i2c_unregister(struct em28xx *dev, unsigned int bus) { if (bus >= NUM_I2C_BUSES) return -ENODEV; i2c_del_adapter(&dev->i2c_adap[bus]); return 0; } |
| 21 10 | 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 | /* * net/tipc/eth_media.c: Ethernet bearer support for TIPC * * Copyright (c) 2001-2007, 2013-2014, Ericsson AB * Copyright (c) 2005-2008, 2011-2013, 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 "bearer.h" /* Convert Ethernet address (media address format) to string */ static int tipc_eth_addr2str(struct tipc_media_addr *addr, char *strbuf, int bufsz) { if (bufsz < 18) /* 18 = strlen("aa:bb:cc:dd:ee:ff\0") */ return 1; sprintf(strbuf, "%pM", addr->value); return 0; } /* Convert from media address format to discovery message addr format */ static int tipc_eth_addr2msg(char *msg, struct tipc_media_addr *addr) { memset(msg, 0, TIPC_MEDIA_INFO_SIZE); msg[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_ETH; memcpy(msg + TIPC_MEDIA_ADDR_OFFSET, addr->value, ETH_ALEN); return 0; } /* Convert raw mac address format to media addr format */ static int tipc_eth_raw2addr(struct tipc_bearer *b, struct tipc_media_addr *addr, const char *msg) { memset(addr, 0, sizeof(*addr)); ether_addr_copy(addr->value, msg); addr->media_id = TIPC_MEDIA_TYPE_ETH; addr->broadcast = is_broadcast_ether_addr(addr->value); return 0; } /* Convert discovery msg addr format to Ethernet media addr format */ static int tipc_eth_msg2addr(struct tipc_bearer *b, struct tipc_media_addr *addr, char *msg) { /* Skip past preamble: */ msg += TIPC_MEDIA_ADDR_OFFSET; return tipc_eth_raw2addr(b, addr, msg); } /* Ethernet media registration info */ struct tipc_media eth_media_info = { .send_msg = tipc_l2_send_msg, .enable_media = tipc_enable_l2_media, .disable_media = tipc_disable_l2_media, .addr2str = tipc_eth_addr2str, .addr2msg = tipc_eth_addr2msg, .msg2addr = tipc_eth_msg2addr, .raw2addr = tipc_eth_raw2addr, .priority = TIPC_DEF_LINK_PRI, .tolerance = TIPC_DEF_LINK_TOL, .min_win = TIPC_DEF_LINK_WIN, .max_win = TIPC_MAX_LINK_WIN, .type_id = TIPC_MEDIA_TYPE_ETH, .hwaddr_len = ETH_ALEN, .name = "eth" }; |
| 7 7 1 1 2 2 1 1 2 1 2 1 2 2 1 1 1 9 1 2 1 3 1 4 1 5 1 3 3 3 3 3 1 3 3 3 1 1 1 3 3 3 3 3 3 3 38 5 6 6 6 14 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES */ #include <linux/file.h> #include <linux/interval_tree.h> #include <linux/iommu.h> #include <linux/iommufd.h> #include <linux/slab.h> #include <linux/vfio.h> #include <uapi/linux/vfio.h> #include <uapi/linux/iommufd.h> #include "iommufd_private.h" static struct iommufd_ioas *get_compat_ioas(struct iommufd_ctx *ictx) { struct iommufd_ioas *ioas = ERR_PTR(-ENODEV); xa_lock(&ictx->objects); if (!ictx->vfio_ioas || !iommufd_lock_obj(&ictx->vfio_ioas->obj)) goto out_unlock; ioas = ictx->vfio_ioas; out_unlock: xa_unlock(&ictx->objects); return ioas; } /** * iommufd_vfio_compat_ioas_get_id - Ensure a compat IOAS exists * @ictx: Context to operate on * @out_ioas_id: The IOAS ID of the compatibility IOAS * * Return the ID of the current compatibility IOAS. The ID can be passed into * other functions that take an ioas_id. */ int iommufd_vfio_compat_ioas_get_id(struct iommufd_ctx *ictx, u32 *out_ioas_id) { struct iommufd_ioas *ioas; ioas = get_compat_ioas(ictx); if (IS_ERR(ioas)) return PTR_ERR(ioas); *out_ioas_id = ioas->obj.id; iommufd_put_object(ictx, &ioas->obj); return 0; } EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_get_id, "IOMMUFD_VFIO"); /** * iommufd_vfio_compat_set_no_iommu - Called when a no-iommu device is attached * @ictx: Context to operate on * * This allows selecting the VFIO_NOIOMMU_IOMMU and blocks normal types. */ int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx) { int ret; xa_lock(&ictx->objects); if (!ictx->vfio_ioas) { ictx->no_iommu_mode = 1; ret = 0; } else { ret = -EINVAL; } xa_unlock(&ictx->objects); return ret; } EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_set_no_iommu, "IOMMUFD_VFIO"); /** * iommufd_vfio_compat_ioas_create - Ensure the compat IOAS is created * @ictx: Context to operate on * * The compatibility IOAS is the IOAS that the vfio compatibility ioctls operate * on since they do not have an IOAS ID input in their ABI. Only attaching a * group should cause a default creation of the internal ioas, this does nothing * if an existing ioas has already been assigned somehow. */ int iommufd_vfio_compat_ioas_create(struct iommufd_ctx *ictx) { struct iommufd_ioas *ioas = NULL; int ret; ioas = iommufd_ioas_alloc(ictx); if (IS_ERR(ioas)) return PTR_ERR(ioas); xa_lock(&ictx->objects); /* * VFIO won't allow attaching a container to both iommu and no iommu * operation */ if (ictx->no_iommu_mode) { ret = -EINVAL; goto out_abort; } if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) { ret = 0; iommufd_put_object(ictx, &ictx->vfio_ioas->obj); goto out_abort; } ictx->vfio_ioas = ioas; xa_unlock(&ictx->objects); /* * An automatically created compat IOAS is treated as a userspace * created object. Userspace can learn the ID via IOMMU_VFIO_IOAS_GET, * and if not manually destroyed it will be destroyed automatically * at iommufd release. */ iommufd_object_finalize(ictx, &ioas->obj); return 0; out_abort: xa_unlock(&ictx->objects); iommufd_object_abort(ictx, &ioas->obj); return ret; } EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_create, "IOMMUFD_VFIO"); int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd) { struct iommu_vfio_ioas *cmd = ucmd->cmd; struct iommufd_ioas *ioas; if (cmd->__reserved) return -EOPNOTSUPP; switch (cmd->op) { case IOMMU_VFIO_IOAS_GET: ioas = get_compat_ioas(ucmd->ictx); if (IS_ERR(ioas)) return PTR_ERR(ioas); cmd->ioas_id = ioas->obj.id; iommufd_put_object(ucmd->ictx, &ioas->obj); return iommufd_ucmd_respond(ucmd, sizeof(*cmd)); case IOMMU_VFIO_IOAS_SET: ioas = iommufd_get_ioas(ucmd->ictx, cmd->ioas_id); if (IS_ERR(ioas)) return PTR_ERR(ioas); xa_lock(&ucmd->ictx->objects); ucmd->ictx->vfio_ioas = ioas; xa_unlock(&ucmd->ictx->objects); iommufd_put_object(ucmd->ictx, &ioas->obj); return 0; case IOMMU_VFIO_IOAS_CLEAR: xa_lock(&ucmd->ictx->objects); ucmd->ictx->vfio_ioas = NULL; xa_unlock(&ucmd->ictx->objects); return 0; default: return -EOPNOTSUPP; } } static int iommufd_vfio_map_dma(struct iommufd_ctx *ictx, unsigned int cmd, void __user *arg) { u32 supported_flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE; size_t minsz = offsetofend(struct vfio_iommu_type1_dma_map, size); struct vfio_iommu_type1_dma_map map; int iommu_prot = IOMMU_CACHE; struct iommufd_ioas *ioas; unsigned long iova; int rc; if (copy_from_user(&map, arg, minsz)) return -EFAULT; if (map.argsz < minsz || map.flags & ~supported_flags) return -EINVAL; if (map.flags & VFIO_DMA_MAP_FLAG_READ) iommu_prot |= IOMMU_READ; if (map.flags & VFIO_DMA_MAP_FLAG_WRITE) iommu_prot |= IOMMU_WRITE; ioas = get_compat_ioas(ictx); if (IS_ERR(ioas)) return PTR_ERR(ioas); /* * Maps created through the legacy interface always use VFIO compatible * rlimit accounting. If the user wishes to use the faster user based * rlimit accounting then they must use the new interface. */ iova = map.iova; rc = iopt_map_user_pages(ictx, &ioas->iopt, &iova, u64_to_user_ptr(map.vaddr), map.size, iommu_prot, 0); iommufd_put_object(ictx, &ioas->obj); return rc; } static int iommufd_vfio_unmap_dma(struct iommufd_ctx *ictx, unsigned int cmd, void __user *arg) { size_t minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size); /* * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is obsoleted by the new * dirty tracking direction: * https://lore.kernel.org/kvm/20220731125503.142683-1-yishaih@nvidia.com/ * https://lore.kernel.org/kvm/20220428210933.3583-1-joao.m.martins@oracle.com/ */ u32 supported_flags = VFIO_DMA_UNMAP_FLAG_ALL; struct vfio_iommu_type1_dma_unmap unmap; unsigned long unmapped = 0; struct iommufd_ioas *ioas; int rc; if (copy_from_user(&unmap, arg, minsz)) return -EFAULT; if (unmap.argsz < minsz || unmap.flags & ~supported_flags) return -EINVAL; ioas = get_compat_ioas(ictx); if (IS_ERR(ioas)) return PTR_ERR(ioas); if (unmap.flags & VFIO_DMA_UNMAP_FLAG_ALL) { if (unmap.iova != 0 || unmap.size != 0) { rc = -EINVAL; goto err_put; } rc = iopt_unmap_all(&ioas->iopt, &unmapped); } else { if (READ_ONCE(ioas->iopt.disable_large_pages)) { /* * Create cuts at the start and last of the requested * range. If the start IOVA is 0 then it doesn't need to * be cut. */ unsigned long iovas[] = { unmap.iova + unmap.size - 1, unmap.iova - 1 }; rc = iopt_cut_iova(&ioas->iopt, iovas, unmap.iova ? 2 : 1); if (rc) goto err_put; } rc = iopt_unmap_iova(&ioas->iopt, unmap.iova, unmap.size, &unmapped); } unmap.size = unmapped; if (copy_to_user(arg, &unmap, minsz)) rc = -EFAULT; err_put: iommufd_put_object(ictx, &ioas->obj); return rc; } static int iommufd_vfio_cc_iommu(struct iommufd_ctx *ictx) { struct iommufd_hwpt_paging *hwpt_paging; struct iommufd_ioas *ioas; int rc = 1; ioas = get_compat_ioas(ictx); if (IS_ERR(ioas)) return PTR_ERR(ioas); mutex_lock(&ioas->mutex); list_for_each_entry(hwpt_paging, &ioas->hwpt_list, hwpt_item) { if (!hwpt_paging->enforce_cache_coherency) { rc = 0; break; } } mutex_unlock(&ioas->mutex); iommufd_put_object(ictx, &ioas->obj); return rc; } static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx, unsigned long type) { switch (type) { case VFIO_TYPE1_IOMMU: case VFIO_TYPE1v2_IOMMU: case VFIO_UNMAP_ALL: return 1; case VFIO_NOIOMMU_IOMMU: return IS_ENABLED(CONFIG_VFIO_NOIOMMU); case VFIO_DMA_CC_IOMMU: return iommufd_vfio_cc_iommu(ictx); case __VFIO_RESERVED_TYPE1_NESTING_IOMMU: return 0; /* * VFIO_DMA_MAP_FLAG_VADDR * https://lore.kernel.org/kvm/1611939252-7240-1-git-send-email-steven.sistare@oracle.com/ * https://lore.kernel.org/all/Yz777bJZjTyLrHEQ@nvidia.com/ * * It is hard to see how this could be implemented safely. */ case VFIO_UPDATE_VADDR: default: return 0; } } static int iommufd_vfio_set_iommu(struct iommufd_ctx *ictx, unsigned long type) { bool no_iommu_mode = READ_ONCE(ictx->no_iommu_mode); struct iommufd_ioas *ioas = NULL; int rc = 0; /* * Emulation for NOIOMMU is imperfect in that VFIO blocks almost all * other ioctls. We let them keep working but they mostly fail since no * IOAS should exist. */ if (IS_ENABLED(CONFIG_VFIO_NOIOMMU) && type == VFIO_NOIOMMU_IOMMU && no_iommu_mode) { if (!capable(CAP_SYS_RAWIO)) return -EPERM; return 0; } if ((type != VFIO_TYPE1_IOMMU && type != VFIO_TYPE1v2_IOMMU) || no_iommu_mode) return -EINVAL; /* VFIO fails the set_iommu if there is no group */ ioas = get_compat_ioas(ictx); if (IS_ERR(ioas)) return PTR_ERR(ioas); /* * The difference between TYPE1 and TYPE1v2 is the ability to unmap in * the middle of mapped ranges. This is complicated by huge page support * which creates single large IOPTEs that cannot be split by the iommu * driver. TYPE1 is very old at this point and likely nothing uses it, * however it is simple enough to emulate by simply disabling the * problematic large IOPTEs. Then we can safely unmap within any range. */ if (type == VFIO_TYPE1_IOMMU) rc = iopt_disable_large_pages(&ioas->iopt); iommufd_put_object(ictx, &ioas->obj); return rc; } static unsigned long iommufd_get_pagesizes(struct iommufd_ioas *ioas) { struct io_pagetable *iopt = &ioas->iopt; unsigned long pgsize_bitmap = ULONG_MAX; struct iommu_domain *domain; unsigned long index; down_read(&iopt->domains_rwsem); xa_for_each(&iopt->domains, index, domain) pgsize_bitmap &= domain->pgsize_bitmap; /* See vfio_update_pgsize_bitmap() */ if (pgsize_bitmap & ~PAGE_MASK) { pgsize_bitmap &= PAGE_MASK; pgsize_bitmap |= PAGE_SIZE; } pgsize_bitmap = max(pgsize_bitmap, ioas->iopt.iova_alignment); up_read(&iopt->domains_rwsem); return pgsize_bitmap; } static int iommufd_fill_cap_iova(struct iommufd_ioas *ioas, struct vfio_info_cap_header __user *cur, size_t avail) { struct vfio_iommu_type1_info_cap_iova_range __user *ucap_iovas = container_of(cur, struct vfio_iommu_type1_info_cap_iova_range __user, header); struct vfio_iommu_type1_info_cap_iova_range cap_iovas = { .header = { .id = VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE, .version = 1, }, }; struct interval_tree_span_iter span; interval_tree_for_each_span(&span, &ioas->iopt.reserved_itree, 0, ULONG_MAX) { struct vfio_iova_range range; if (!span.is_hole) continue; range.start = span.start_hole; range.end = span.last_hole; if (avail >= struct_size(&cap_iovas, iova_ranges, cap_iovas.nr_iovas + 1) && copy_to_user(&ucap_iovas->iova_ranges[cap_iovas.nr_iovas], &range, sizeof(range))) return -EFAULT; cap_iovas.nr_iovas++; } if (avail >= struct_size(&cap_iovas, iova_ranges, cap_iovas.nr_iovas) && copy_to_user(ucap_iovas, &cap_iovas, sizeof(cap_iovas))) return -EFAULT; return struct_size(&cap_iovas, iova_ranges, cap_iovas.nr_iovas); } static int iommufd_fill_cap_dma_avail(struct iommufd_ioas *ioas, struct vfio_info_cap_header __user *cur, size_t avail) { struct vfio_iommu_type1_info_dma_avail cap_dma = { .header = { .id = VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL, .version = 1, }, /* * iommufd's limit is based on the cgroup's memory limit. * Normally vfio would return U16_MAX here, and provide a module * parameter to adjust it. Since S390 qemu userspace actually * pays attention and needs a value bigger than U16_MAX return * U32_MAX. */ .avail = U32_MAX, }; if (avail >= sizeof(cap_dma) && copy_to_user(cur, &cap_dma, sizeof(cap_dma))) return -EFAULT; return sizeof(cap_dma); } static int iommufd_vfio_iommu_get_info(struct iommufd_ctx *ictx, void __user *arg) { typedef int (*fill_cap_fn)(struct iommufd_ioas *ioas, struct vfio_info_cap_header __user *cur, size_t avail); static const fill_cap_fn fill_fns[] = { iommufd_fill_cap_dma_avail, iommufd_fill_cap_iova, }; size_t minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes); struct vfio_info_cap_header __user *last_cap = NULL; struct vfio_iommu_type1_info info = {}; struct iommufd_ioas *ioas; size_t total_cap_size; int rc; int i; if (copy_from_user(&info, arg, minsz)) return -EFAULT; if (info.argsz < minsz) return -EINVAL; minsz = min_t(size_t, info.argsz, sizeof(info)); ioas = get_compat_ioas(ictx); if (IS_ERR(ioas)) return PTR_ERR(ioas); info.flags = VFIO_IOMMU_INFO_PGSIZES; info.iova_pgsizes = iommufd_get_pagesizes(ioas); info.cap_offset = 0; down_read(&ioas->iopt.iova_rwsem); total_cap_size = sizeof(info); for (i = 0; i != ARRAY_SIZE(fill_fns); i++) { int cap_size; if (info.argsz > total_cap_size) cap_size = fill_fns[i](ioas, arg + total_cap_size, info.argsz - total_cap_size); else cap_size = fill_fns[i](ioas, NULL, 0); if (cap_size < 0) { rc = cap_size; goto out_put; } cap_size = ALIGN(cap_size, sizeof(u64)); if (last_cap && info.argsz >= total_cap_size && put_user(total_cap_size, &last_cap->next)) { rc = -EFAULT; goto out_put; } last_cap = arg + total_cap_size; total_cap_size += cap_size; } /* * If the user did not provide enough space then only some caps are * returned and the argsz will be updated to the correct amount to get * all caps. */ if (info.argsz >= total_cap_size) info.cap_offset = sizeof(info); info.argsz = total_cap_size; info.flags |= VFIO_IOMMU_INFO_CAPS; if (copy_to_user(arg, &info, minsz)) { rc = -EFAULT; goto out_put; } rc = 0; out_put: up_read(&ioas->iopt.iova_rwsem); iommufd_put_object(ictx, &ioas->obj); return rc; } int iommufd_vfio_ioctl(struct iommufd_ctx *ictx, unsigned int cmd, unsigned long arg) { void __user *uarg = (void __user *)arg; switch (cmd) { case VFIO_GET_API_VERSION: return VFIO_API_VERSION; case VFIO_SET_IOMMU: return iommufd_vfio_set_iommu(ictx, arg); case VFIO_CHECK_EXTENSION: return iommufd_vfio_check_extension(ictx, arg); case VFIO_IOMMU_GET_INFO: return iommufd_vfio_iommu_get_info(ictx, uarg); case VFIO_IOMMU_MAP_DMA: return iommufd_vfio_map_dma(ictx, cmd, uarg); case VFIO_IOMMU_UNMAP_DMA: return iommufd_vfio_unmap_dma(ictx, cmd, uarg); case VFIO_IOMMU_DIRTY_PAGES: default: return -ENOIOCTLCMD; } return -ENOIOCTLCMD; } |
| 460 145 398 460 14 20 28 455 89 456 456 342 344 342 461 70 20 461 460 458 461 2 2 3 1 2 2 1 1 32 2 2 2 1 28 27 11 13 2 17 9 22 4 22 1 3 22 4 6 5 1 6 1 13 12 12 12 10 1 9 1 9 8 8 30 2 28 26 11 21 30 28 28 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 | // 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. * * IPv4 Forwarding Information Base: policy rules. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Thomas Graf <tgraf@suug.ch> * * Fixes: * Rani Assaf : local_rule cannot be deleted * Marc Boucher : routing by fwmark */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/inetdevice.h> #include <linux/init.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <net/flow.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/route.h> #include <net/tcp.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/fib_rules.h> #include <linux/indirect_call_wrapper.h> struct fib4_rule { struct fib_rule common; u8 dst_len; u8 src_len; dscp_t dscp; dscp_t dscp_mask; u8 dscp_full:1; /* DSCP or TOS selector */ __be32 src; __be32 srcmask; __be32 dst; __be32 dstmask; #ifdef CONFIG_IP_ROUTE_CLASSID u32 tclassid; #endif }; static bool fib4_rule_matchall(const struct fib_rule *rule) { struct fib4_rule *r = container_of(rule, struct fib4_rule, common); if (r->dst_len || r->src_len || r->dscp) return false; return fib_rule_matchall(rule); } bool fib4_rule_default(const struct fib_rule *rule) { if (!fib4_rule_matchall(rule) || rule->action != FR_ACT_TO_TBL || rule->l3mdev) return false; if (rule->table != RT_TABLE_LOCAL && rule->table != RT_TABLE_MAIN && rule->table != RT_TABLE_DEFAULT) return false; return true; } EXPORT_SYMBOL_GPL(fib4_rule_default); int fib4_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return fib_rules_dump(net, nb, AF_INET, extack); } unsigned int fib4_rules_seq_read(const struct net *net) { return fib_rules_seq_read(net, AF_INET); } int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_lookup_arg arg = { .result = res, .flags = flags, }; int err; /* update flow if oif or iif point to device enslaved to l3mdev */ l3mdev_update_flow(net, flowi4_to_flowi(flp)); err = fib_rules_lookup(net->ipv4.rules_ops, flowi4_to_flowi(flp), 0, &arg); #ifdef CONFIG_IP_ROUTE_CLASSID if (arg.rule) res->tclassid = ((struct fib4_rule *)arg.rule)->tclassid; else res->tclassid = 0; #endif if (err == -ESRCH) err = -ENETUNREACH; return err; } EXPORT_SYMBOL_GPL(__fib_lookup); INDIRECT_CALLABLE_SCOPE int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { int err = -EAGAIN; struct fib_table *tbl; u32 tb_id; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: return -ENETUNREACH; case FR_ACT_PROHIBIT: return -EACCES; case FR_ACT_BLACKHOLE: default: return -EINVAL; } rcu_read_lock(); tb_id = fib_rule_get_table(rule, arg); tbl = fib_get_table(rule->fr_net, tb_id); if (tbl) err = fib_table_lookup(tbl, &flp->u.ip4, (struct fib_result *)arg->result, arg->flags); rcu_read_unlock(); return err; } INDIRECT_CALLABLE_SCOPE bool fib4_rule_suppress(struct fib_rule *rule, int flags, struct fib_lookup_arg *arg) { struct fib_result *result = arg->result; struct net_device *dev = NULL; if (result->fi) { struct fib_nh_common *nhc = fib_info_nhc(result->fi, 0); dev = nhc->nhc_dev; } /* do not accept result if the route does * not meet the required prefix length */ if (result->prefixlen <= rule->suppress_prefixlen) goto suppress_route; /* do not accept result if the route uses a device * belonging to a forbidden interface group */ if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup) goto suppress_route; return false; suppress_route: if (!(arg->flags & FIB_LOOKUP_NOREF)) fib_info_put(result->fi); return true; } INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { struct fib4_rule *r = (struct fib4_rule *) rule; struct flowi4 *fl4 = &fl->u.ip4; __be32 daddr = fl4->daddr; __be32 saddr = fl4->saddr; if (((saddr ^ r->src) & r->srcmask) || ((daddr ^ r->dst) & r->dstmask)) return 0; /* When DSCP selector is used we need to match on the entire DSCP field * in the flow information structure. When TOS selector is used we need * to mask the upper three DSCP bits prior to matching to maintain * legacy behavior. */ if (r->dscp_full && (r->dscp ^ fl4->flowi4_dscp) & r->dscp_mask) return 0; else if (!r->dscp_full && r->dscp && !fib_dscp_masked_match(r->dscp, fl4)) return 0; if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) return 0; if (!fib_rule_port_match(&rule->sport_range, rule->sport_mask, fl4->fl4_sport)) return 0; if (!fib_rule_port_match(&rule->dport_range, rule->dport_mask, fl4->fl4_dport)) return 0; return 1; } static struct fib_table *fib_empty_table(struct net *net) { u32 id = 1; while (1) { if (!fib_get_table(net, id)) return fib_new_table(net, id); if (id++ == RT_TABLE_MAX) break; } return NULL; } static int fib4_nl2rule_dscp(const struct nlattr *nla, struct fib4_rule *rule4, struct netlink_ext_ack *extack) { if (rule4->dscp) { NL_SET_ERR_MSG(extack, "Cannot specify both TOS and DSCP"); return -EINVAL; } rule4->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2); rule4->dscp_mask = inet_dsfield_to_dscp(INET_DSCP_MASK); rule4->dscp_full = true; return 0; } static int fib4_nl2rule_dscp_mask(const struct nlattr *nla, struct fib4_rule *rule4, struct netlink_ext_ack *extack) { dscp_t dscp_mask; if (!rule4->dscp_full) { NL_SET_ERR_MSG_ATTR(extack, nla, "Cannot specify DSCP mask without DSCP value"); return -EINVAL; } dscp_mask = inet_dsfield_to_dscp(nla_get_u8(nla) << 2); if (rule4->dscp & ~dscp_mask) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid DSCP mask"); return -EINVAL; } rule4->dscp_mask = dscp_mask; return 0; } static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct fib4_rule *rule4 = (struct fib4_rule *)rule; struct net *net = rule->fr_net; int err = -EINVAL; if (tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) { NL_SET_ERR_MSG(extack, "Flow label cannot be specified for IPv4 FIB rules"); goto errout; } if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): ECN bits must be 0"); goto errout; } /* IPv4 currently doesn't handle high order DSCP bits correctly */ if (frh->tos & ~IPTOS_TOS_MASK) { NL_SET_ERR_MSG(extack, "Invalid tos"); goto errout; } rule4->dscp = inet_dsfield_to_dscp(frh->tos); if (tb[FRA_DSCP] && fib4_nl2rule_dscp(tb[FRA_DSCP], rule4, extack) < 0) goto errout; if (tb[FRA_DSCP_MASK] && fib4_nl2rule_dscp_mask(tb[FRA_DSCP_MASK], rule4, extack) < 0) goto errout; /* split local/main if they are not already split */ err = fib_unmerge(net); if (err) goto errout; if (rule->table == RT_TABLE_UNSPEC && !rule->l3mdev) { if (rule->action == FR_ACT_TO_TBL) { struct fib_table *table; table = fib_empty_table(net); if (!table) { err = -ENOBUFS; goto errout; } rule->table = table->tb_id; } } if (frh->src_len) rule4->src = nla_get_in_addr(tb[FRA_SRC]); if (frh->dst_len) rule4->dst = nla_get_in_addr(tb[FRA_DST]); #ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW]) { rule4->tclassid = nla_get_u32(tb[FRA_FLOW]); if (rule4->tclassid) atomic_inc(&net->ipv4.fib_num_tclassid_users); } #endif if (fib_rule_requires_fldissect(rule)) net->ipv4.fib_rules_require_fldissect++; rule4->src_len = frh->src_len; rule4->srcmask = inet_make_mask(rule4->src_len); rule4->dst_len = frh->dst_len; rule4->dstmask = inet_make_mask(rule4->dst_len); net->ipv4.fib_has_custom_rules = true; err = 0; errout: return err; } static int fib4_rule_delete(struct fib_rule *rule) { struct net *net = rule->fr_net; int err; /* split local/main if they are not already split */ err = fib_unmerge(net); if (err) goto errout; #ifdef CONFIG_IP_ROUTE_CLASSID if (((struct fib4_rule *)rule)->tclassid) atomic_dec(&net->ipv4.fib_num_tclassid_users); #endif net->ipv4.fib_has_custom_rules = true; if (net->ipv4.fib_rules_require_fldissect && fib_rule_requires_fldissect(rule)) net->ipv4.fib_rules_require_fldissect--; errout: return err; } static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { struct fib4_rule *rule4 = (struct fib4_rule *) rule; if (frh->src_len && (rule4->src_len != frh->src_len)) return 0; if (frh->dst_len && (rule4->dst_len != frh->dst_len)) return 0; if (frh->tos && (rule4->dscp_full || inet_dscp_to_dsfield(rule4->dscp) != frh->tos)) return 0; if (tb[FRA_DSCP]) { dscp_t dscp; dscp = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP]) << 2); if (!rule4->dscp_full || rule4->dscp != dscp) return 0; } if (tb[FRA_DSCP_MASK]) { dscp_t dscp_mask; dscp_mask = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP_MASK]) << 2); if (!rule4->dscp_full || rule4->dscp_mask != dscp_mask) return 0; } #ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW]))) return 0; #endif if (frh->src_len && (rule4->src != nla_get_in_addr(tb[FRA_SRC]))) return 0; if (frh->dst_len && (rule4->dst != nla_get_in_addr(tb[FRA_DST]))) return 0; return 1; } static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh) { struct fib4_rule *rule4 = (struct fib4_rule *) rule; frh->dst_len = rule4->dst_len; frh->src_len = rule4->src_len; if (rule4->dscp_full) { frh->tos = 0; if (nla_put_u8(skb, FRA_DSCP, inet_dscp_to_dsfield(rule4->dscp) >> 2) || nla_put_u8(skb, FRA_DSCP_MASK, inet_dscp_to_dsfield(rule4->dscp_mask) >> 2)) goto nla_put_failure; } else { frh->tos = inet_dscp_to_dsfield(rule4->dscp); } if ((rule4->dst_len && nla_put_in_addr(skb, FRA_DST, rule4->dst)) || (rule4->src_len && nla_put_in_addr(skb, FRA_SRC, rule4->src))) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (rule4->tclassid && nla_put_u32(skb, FRA_FLOW, rule4->tclassid)) goto nla_put_failure; #endif return 0; nla_put_failure: return -ENOBUFS; } static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(4) /* dst */ + nla_total_size(4) /* src */ + nla_total_size(4) /* flow */ + nla_total_size(1) /* dscp */ + nla_total_size(1); /* dscp mask */ } static void fib4_rule_flush_cache(struct fib_rules_ops *ops) { rt_cache_flush(ops->fro_net); } static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = { .family = AF_INET, .rule_size = sizeof(struct fib4_rule), .addr_size = sizeof(u32), .action = fib4_rule_action, .suppress = fib4_rule_suppress, .match = fib4_rule_match, .configure = fib4_rule_configure, .delete = fib4_rule_delete, .compare = fib4_rule_compare, .fill = fib4_rule_fill, .nlmsg_payload = fib4_rule_nlmsg_payload, .flush_cache = fib4_rule_flush_cache, .nlgroup = RTNLGRP_IPV4_RULE, .owner = THIS_MODULE, }; static int fib_default_rules_init(struct fib_rules_ops *ops) { int err; err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL); if (err < 0) return err; err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN); if (err < 0) return err; err = fib_default_rule_add(ops, 0x7FFF, RT_TABLE_DEFAULT); if (err < 0) return err; return 0; } int __net_init fib4_rules_init(struct net *net) { int err; struct fib_rules_ops *ops; ops = fib_rules_register(&fib4_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); err = fib_default_rules_init(ops); if (err < 0) goto fail; net->ipv4.rules_ops = ops; net->ipv4.fib_has_custom_rules = false; net->ipv4.fib_rules_require_fldissect = 0; return 0; fail: /* also cleans all rules already added */ fib_rules_unregister(ops); return err; } void __net_exit fib4_rules_exit(struct net *net) { fib_rules_unregister(net->ipv4.rules_ops); } |
| 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Behringer BCD2000 driver * * Copyright (C) 2014 Mario Kicherer (dev@kicherer.org) */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/bitmap.h> #include <linux/usb.h> #include <linux/usb/audio.h> #include <sound/core.h> #include <sound/initval.h> #include <sound/rawmidi.h> #define PREFIX "snd-bcd2000: " #define BUFSIZE 64 static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1397, 0x00bd) }, { }, }; static const unsigned char device_cmd_prefix[] = {0x03, 0x00}; static const unsigned char bcd2000_init_sequence[] = { 0x07, 0x00, 0x00, 0x00, 0x78, 0x48, 0x1c, 0x81, 0xc4, 0x00, 0x00, 0x00, 0x5e, 0x53, 0x4a, 0xf7, 0x18, 0xfa, 0x11, 0xff, 0x6c, 0xf3, 0x90, 0xff, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x18, 0xfa, 0x11, 0xff, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf2, 0x34, 0x4a, 0xf7, 0x18, 0xfa, 0x11, 0xff }; struct bcd2000 { struct usb_device *dev; struct snd_card *card; struct usb_interface *intf; int card_index; int midi_out_active; struct snd_rawmidi *rmidi; struct snd_rawmidi_substream *midi_receive_substream; struct snd_rawmidi_substream *midi_out_substream; unsigned char midi_in_buf[BUFSIZE]; unsigned char midi_out_buf[BUFSIZE]; struct urb *midi_out_urb; struct urb *midi_in_urb; struct usb_anchor anchor; }; static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; static DEFINE_MUTEX(devices_mutex); static DECLARE_BITMAP(devices_used, SNDRV_CARDS); static struct usb_driver bcd2000_driver; #ifdef CONFIG_SND_DEBUG static void bcd2000_dump_buffer(const char *prefix, const char *buf, int len) { print_hex_dump(KERN_DEBUG, prefix, DUMP_PREFIX_NONE, 16, 1, buf, len, false); } #else static void bcd2000_dump_buffer(const char *prefix, const char *buf, int len) {} #endif static int bcd2000_midi_input_open(struct snd_rawmidi_substream *substream) { return 0; } static int bcd2000_midi_input_close(struct snd_rawmidi_substream *substream) { return 0; } /* (de)register midi substream from client */ static void bcd2000_midi_input_trigger(struct snd_rawmidi_substream *substream, int up) { struct bcd2000 *bcd2k = substream->rmidi->private_data; bcd2k->midi_receive_substream = up ? substream : NULL; } static void bcd2000_midi_handle_input(struct bcd2000 *bcd2k, const unsigned char *buf, unsigned int buf_len) { unsigned int payload_length, tocopy; struct snd_rawmidi_substream *midi_receive_substream; midi_receive_substream = READ_ONCE(bcd2k->midi_receive_substream); if (!midi_receive_substream) return; bcd2000_dump_buffer(PREFIX "received from device: ", buf, buf_len); if (buf_len < 2) return; payload_length = buf[0]; /* ignore packets without payload */ if (payload_length == 0) return; tocopy = min(payload_length, buf_len-1); bcd2000_dump_buffer(PREFIX "sending to userspace: ", &buf[1], tocopy); snd_rawmidi_receive(midi_receive_substream, &buf[1], tocopy); } static void bcd2000_midi_send(struct bcd2000 *bcd2k) { int len, ret; struct snd_rawmidi_substream *midi_out_substream; BUILD_BUG_ON(sizeof(device_cmd_prefix) >= BUFSIZE); midi_out_substream = READ_ONCE(bcd2k->midi_out_substream); if (!midi_out_substream) return; /* copy command prefix bytes */ memcpy(bcd2k->midi_out_buf, device_cmd_prefix, sizeof(device_cmd_prefix)); /* * get MIDI packet and leave space for command prefix * and payload length */ len = snd_rawmidi_transmit(midi_out_substream, bcd2k->midi_out_buf + 3, BUFSIZE - 3); if (len < 0) dev_err(&bcd2k->dev->dev, "%s: snd_rawmidi_transmit error %d\n", __func__, len); if (len <= 0) return; /* set payload length */ bcd2k->midi_out_buf[2] = len; bcd2k->midi_out_urb->transfer_buffer_length = BUFSIZE; bcd2000_dump_buffer(PREFIX "sending to device: ", bcd2k->midi_out_buf, len+3); /* send packet to the BCD2000 */ ret = usb_submit_urb(bcd2k->midi_out_urb, GFP_ATOMIC); if (ret < 0) dev_err(&bcd2k->dev->dev, PREFIX "%s (%p): usb_submit_urb() failed, ret=%d, len=%d\n", __func__, midi_out_substream, ret, len); else bcd2k->midi_out_active = 1; } static int bcd2000_midi_output_open(struct snd_rawmidi_substream *substream) { return 0; } static int bcd2000_midi_output_close(struct snd_rawmidi_substream *substream) { struct bcd2000 *bcd2k = substream->rmidi->private_data; if (bcd2k->midi_out_active) { usb_kill_urb(bcd2k->midi_out_urb); bcd2k->midi_out_active = 0; } return 0; } /* (de)register midi substream from client */ static void bcd2000_midi_output_trigger(struct snd_rawmidi_substream *substream, int up) { struct bcd2000 *bcd2k = substream->rmidi->private_data; if (up) { bcd2k->midi_out_substream = substream; /* check if there is data userspace wants to send */ if (!bcd2k->midi_out_active) bcd2000_midi_send(bcd2k); } else { bcd2k->midi_out_substream = NULL; } } static void bcd2000_output_complete(struct urb *urb) { struct bcd2000 *bcd2k = urb->context; bcd2k->midi_out_active = 0; if (urb->status) dev_warn(&urb->dev->dev, PREFIX "output urb->status: %d\n", urb->status); if (urb->status == -ESHUTDOWN) return; /* check if there is more data userspace wants to send */ bcd2000_midi_send(bcd2k); } static void bcd2000_input_complete(struct urb *urb) { int ret; struct bcd2000 *bcd2k = urb->context; if (urb->status) dev_warn(&urb->dev->dev, PREFIX "input urb->status: %i\n", urb->status); if (!bcd2k || urb->status == -ESHUTDOWN) return; if (urb->actual_length > 0) bcd2000_midi_handle_input(bcd2k, urb->transfer_buffer, urb->actual_length); /* return URB to device */ ret = usb_submit_urb(bcd2k->midi_in_urb, GFP_ATOMIC); if (ret < 0) dev_err(&bcd2k->dev->dev, PREFIX "%s: usb_submit_urb() failed, ret=%d\n", __func__, ret); } static const struct snd_rawmidi_ops bcd2000_midi_output = { .open = bcd2000_midi_output_open, .close = bcd2000_midi_output_close, .trigger = bcd2000_midi_output_trigger, }; static const struct snd_rawmidi_ops bcd2000_midi_input = { .open = bcd2000_midi_input_open, .close = bcd2000_midi_input_close, .trigger = bcd2000_midi_input_trigger, }; static void bcd2000_init_device(struct bcd2000 *bcd2k) { int ret; init_usb_anchor(&bcd2k->anchor); usb_anchor_urb(bcd2k->midi_out_urb, &bcd2k->anchor); usb_anchor_urb(bcd2k->midi_in_urb, &bcd2k->anchor); /* copy init sequence into buffer */ memcpy(bcd2k->midi_out_buf, bcd2000_init_sequence, 52); bcd2k->midi_out_urb->transfer_buffer_length = 52; /* submit sequence */ ret = usb_submit_urb(bcd2k->midi_out_urb, GFP_KERNEL); if (ret < 0) dev_err(&bcd2k->dev->dev, PREFIX "%s: usb_submit_urb() out failed, ret=%d: ", __func__, ret); else bcd2k->midi_out_active = 1; /* pass URB to device to enable button and controller events */ ret = usb_submit_urb(bcd2k->midi_in_urb, GFP_KERNEL); if (ret < 0) dev_err(&bcd2k->dev->dev, PREFIX "%s: usb_submit_urb() in failed, ret=%d: ", __func__, ret); /* ensure initialization is finished */ usb_wait_anchor_empty_timeout(&bcd2k->anchor, 1000); } static int bcd2000_init_midi(struct bcd2000 *bcd2k) { int ret; struct snd_rawmidi *rmidi; ret = snd_rawmidi_new(bcd2k->card, bcd2k->card->shortname, 0, 1, /* output */ 1, /* input */ &rmidi); if (ret < 0) return ret; strscpy(rmidi->name, bcd2k->card->shortname, sizeof(rmidi->name)); rmidi->info_flags = SNDRV_RAWMIDI_INFO_DUPLEX; rmidi->private_data = bcd2k; rmidi->info_flags |= SNDRV_RAWMIDI_INFO_OUTPUT; snd_rawmidi_set_ops(rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT, &bcd2000_midi_output); rmidi->info_flags |= SNDRV_RAWMIDI_INFO_INPUT; snd_rawmidi_set_ops(rmidi, SNDRV_RAWMIDI_STREAM_INPUT, &bcd2000_midi_input); bcd2k->rmidi = rmidi; bcd2k->midi_in_urb = usb_alloc_urb(0, GFP_KERNEL); bcd2k->midi_out_urb = usb_alloc_urb(0, GFP_KERNEL); if (!bcd2k->midi_in_urb || !bcd2k->midi_out_urb) { dev_err(&bcd2k->dev->dev, PREFIX "usb_alloc_urb failed\n"); return -ENOMEM; } usb_fill_int_urb(bcd2k->midi_in_urb, bcd2k->dev, usb_rcvintpipe(bcd2k->dev, 0x81), bcd2k->midi_in_buf, BUFSIZE, bcd2000_input_complete, bcd2k, 1); usb_fill_int_urb(bcd2k->midi_out_urb, bcd2k->dev, usb_sndintpipe(bcd2k->dev, 0x1), bcd2k->midi_out_buf, BUFSIZE, bcd2000_output_complete, bcd2k, 1); /* sanity checks of EPs before actually submitting */ if (usb_urb_ep_type_check(bcd2k->midi_in_urb) || usb_urb_ep_type_check(bcd2k->midi_out_urb)) { dev_err(&bcd2k->dev->dev, "invalid MIDI EP\n"); return -EINVAL; } bcd2000_init_device(bcd2k); return 0; } static void bcd2000_free_usb_related_resources(struct bcd2000 *bcd2k, struct usb_interface *interface) { usb_kill_urb(bcd2k->midi_out_urb); usb_kill_urb(bcd2k->midi_in_urb); usb_free_urb(bcd2k->midi_out_urb); usb_free_urb(bcd2k->midi_in_urb); if (bcd2k->intf) { usb_set_intfdata(bcd2k->intf, NULL); bcd2k->intf = NULL; } } static int bcd2000_probe(struct usb_interface *interface, const struct usb_device_id *usb_id) { struct snd_card *card; struct bcd2000 *bcd2k; unsigned int card_index; char usb_path[32]; int err; guard(mutex)(&devices_mutex); for (card_index = 0; card_index < SNDRV_CARDS; ++card_index) if (!test_bit(card_index, devices_used)) break; if (card_index >= SNDRV_CARDS) return -ENOENT; err = snd_card_new(&interface->dev, index[card_index], id[card_index], THIS_MODULE, sizeof(*bcd2k), &card); if (err < 0) return err; bcd2k = card->private_data; bcd2k->dev = interface_to_usbdev(interface); bcd2k->card = card; bcd2k->card_index = card_index; bcd2k->intf = interface; snd_card_set_dev(card, &interface->dev); strscpy(card->driver, "snd-bcd2000", sizeof(card->driver)); strscpy(card->shortname, "BCD2000", sizeof(card->shortname)); usb_make_path(bcd2k->dev, usb_path, sizeof(usb_path)); snprintf(bcd2k->card->longname, sizeof(bcd2k->card->longname), "Behringer BCD2000 at %s", usb_path); err = bcd2000_init_midi(bcd2k); if (err < 0) goto probe_error; err = snd_card_register(card); if (err < 0) goto probe_error; usb_set_intfdata(interface, bcd2k); set_bit(card_index, devices_used); return 0; probe_error: dev_info(&bcd2k->dev->dev, PREFIX "error during probing"); bcd2000_free_usb_related_resources(bcd2k, interface); snd_card_free(card); return err; } static void bcd2000_disconnect(struct usb_interface *interface) { struct bcd2000 *bcd2k = usb_get_intfdata(interface); if (!bcd2k) return; guard(mutex)(&devices_mutex); /* make sure that userspace cannot create new requests */ snd_card_disconnect(bcd2k->card); bcd2000_free_usb_related_resources(bcd2k, interface); clear_bit(bcd2k->card_index, devices_used); snd_card_free_when_closed(bcd2k->card); } static struct usb_driver bcd2000_driver = { .name = "snd-bcd2000", .probe = bcd2000_probe, .disconnect = bcd2000_disconnect, .id_table = id_table, }; module_usb_driver(bcd2000_driver); MODULE_DEVICE_TABLE(usb, id_table); MODULE_AUTHOR("Mario Kicherer, dev@kicherer.org"); MODULE_DESCRIPTION("Behringer BCD2000 driver"); MODULE_LICENSE("GPL"); |
| 227 37 4601 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM notifier #if !defined(_TRACE_NOTIFIERS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NOTIFIERS_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(notifier_info, TP_PROTO(void *cb), TP_ARGS(cb), TP_STRUCT__entry( __field(void *, cb) ), TP_fast_assign( __entry->cb = cb; ), TP_printk("%ps", __entry->cb) ); /* * notifier_register - called upon notifier callback registration * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_register, TP_PROTO(void *cb), TP_ARGS(cb) ); /* * notifier_unregister - called upon notifier callback unregistration * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_unregister, TP_PROTO(void *cb), TP_ARGS(cb) ); /* * notifier_run - called upon notifier callback execution * * @cb: callback pointer * */ DEFINE_EVENT(notifier_info, notifier_run, TP_PROTO(void *cb), TP_ARGS(cb) ); #endif /* _TRACE_NOTIFIERS_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 17 703 9 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* linux/net/inet/arp.h */ #ifndef _ARP_H #define _ARP_H #include <linux/if_arp.h> #include <linux/hash.h> #include <net/neighbour.h> extern struct neigh_table arp_tbl; static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 *hash_rnd) { u32 key = *(const u32 *)pkey; u32 val = key ^ hash32_ptr(dev); return val * hash_rnd[0]; } #ifdef CONFIG_INET static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) key = INADDR_ANY; return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } #else static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { return NULL; } #endif static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key) { struct neighbour *n; rcu_read_lock(); n = __ipv4_neigh_lookup_noref(dev, key); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock(); return n; } static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key) { struct neighbour *n; rcu_read_lock(); n = __ipv4_neigh_lookup_noref(dev, key); neigh_confirm(n); rcu_read_unlock(); } void arp_init(void); int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg); void arp_send(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *th); int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir); void arp_ifdown(struct net_device *dev); int arp_invalidate(struct net_device *dev, __be32 ip, bool force); struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw); void arp_xmit(struct sk_buff *skb); #endif /* _ARP_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/ktime.h> #include <linux/list.h> #include <linux/math64.h> #include <linux/sizes.h> #include <linux/workqueue.h> #include "ctree.h" #include "block-group.h" #include "discard.h" #include "free-space-cache.h" #include "fs.h" /* * This contains the logic to handle async discard. * * Async discard manages trimming of free space outside of transaction commit. * Discarding is done by managing the block_groups on a LRU list based on free * space recency. Two passes are used to first prioritize discarding extents * and then allow for trimming in the bitmap the best opportunity to coalesce. * The block_groups are maintained on multiple lists to allow for multiple * passes with different discard filter requirements. A delayed work item is * used to manage discarding with timeout determined by a max of the delay * incurred by the iops rate limit, the byte rate limit, and the max delay of * BTRFS_DISCARD_MAX_DELAY. * * Note, this only keeps track of block_groups that are explicitly for data. * Mixed block_groups are not supported. * * The first list is special to manage discarding of fully free block groups. * This is necessary because we issue a final trim for a full free block group * after forgetting it. When a block group becomes unused, instead of directly * being added to the unused_bgs list, we add it to this first list. Then * from there, if it becomes fully discarded, we place it onto the unused_bgs * list. * * The in-memory free space cache serves as the backing state for discard. * Consequently this means there is no persistence. We opt to load all the * block groups in as not discarded, so the mount case degenerates to the * crashing case. * * As the free space cache uses bitmaps, there exists a tradeoff between * ease/efficiency for find_free_extent() and the accuracy of discard state. * Here we opt to let untrimmed regions merge with everything while only letting * trimmed regions merge with other trimmed regions. This can cause * overtrimming, but the coalescing benefit seems to be worth it. Additionally, * bitmap state is tracked as a whole. If we're able to fully trim a bitmap, * the trimmed flag is set on the bitmap. Otherwise, if an allocation comes in, * this resets the state and we will retry trimming the whole bitmap. This is a * tradeoff between discard state accuracy and the cost of accounting. */ /* This is an initial delay to give some chance for block reuse */ #define BTRFS_DISCARD_DELAY (120ULL * NSEC_PER_SEC) #define BTRFS_DISCARD_UNUSED_DELAY (10ULL * NSEC_PER_SEC) #define BTRFS_DISCARD_MIN_DELAY_MSEC (1UL) #define BTRFS_DISCARD_MAX_DELAY_MSEC (1000UL) #define BTRFS_DISCARD_MAX_IOPS (1000U) /* Monotonically decreasing minimum length filters after index 0 */ static int discard_minlen[BTRFS_NR_DISCARD_LISTS] = { 0, BTRFS_ASYNC_DISCARD_MAX_FILTER, BTRFS_ASYNC_DISCARD_MIN_FILTER }; static struct list_head *get_discard_list(struct btrfs_discard_ctl *discard_ctl, const struct btrfs_block_group *block_group) { return &discard_ctl->discard_list[block_group->discard_index]; } /* * Determine if async discard should be running. * * @discard_ctl: discard control * * Check if the file system is writeable and BTRFS_FS_DISCARD_RUNNING is set. */ static bool btrfs_run_discard_work(const struct btrfs_discard_ctl *discard_ctl) { struct btrfs_fs_info *fs_info = container_of(discard_ctl, struct btrfs_fs_info, discard_ctl); return (!(fs_info->sb->s_flags & SB_RDONLY) && test_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags)); } static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { lockdep_assert_held(&discard_ctl->lock); if (list_empty(&block_group->discard_list) || block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED) { if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED) block_group->discard_index = BTRFS_DISCARD_INDEX_START; block_group->discard_eligible_time = (ktime_get_ns() + BTRFS_DISCARD_DELAY); block_group->discard_state = BTRFS_DISCARD_RESET_CURSOR; } if (list_empty(&block_group->discard_list)) btrfs_get_block_group(block_group); list_move_tail(&block_group->discard_list, get_discard_list(discard_ctl, block_group)); } static void add_to_discard_list(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { if (!btrfs_is_block_group_data_only(block_group)) return; if (!btrfs_run_discard_work(discard_ctl)) return; spin_lock(&discard_ctl->lock); __add_to_discard_list(discard_ctl, block_group); spin_unlock(&discard_ctl->lock); } static void add_to_discard_unused_list(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { bool queued; spin_lock(&discard_ctl->lock); queued = !list_empty(&block_group->discard_list); if (!btrfs_run_discard_work(discard_ctl)) { spin_unlock(&discard_ctl->lock); return; } list_del_init(&block_group->discard_list); block_group->discard_index = BTRFS_DISCARD_INDEX_UNUSED; block_group->discard_eligible_time = (ktime_get_ns() + BTRFS_DISCARD_UNUSED_DELAY); block_group->discard_state = BTRFS_DISCARD_RESET_CURSOR; if (!queued) btrfs_get_block_group(block_group); list_add_tail(&block_group->discard_list, &discard_ctl->discard_list[BTRFS_DISCARD_INDEX_UNUSED]); spin_unlock(&discard_ctl->lock); } static bool remove_from_discard_list(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { bool running = false; bool queued = false; spin_lock(&discard_ctl->lock); if (block_group == discard_ctl->block_group) { running = true; discard_ctl->block_group = NULL; } block_group->discard_eligible_time = 0; queued = !list_empty(&block_group->discard_list); list_del_init(&block_group->discard_list); if (queued) btrfs_put_block_group(block_group); spin_unlock(&discard_ctl->lock); return running; } /* * Find block_group that's up next for discarding. * * @discard_ctl: discard control * @now: current time * * Iterate over the discard lists to find the next block_group up for * discarding checking the discard_eligible_time of block_group. */ static struct btrfs_block_group *find_next_block_group( struct btrfs_discard_ctl *discard_ctl, u64 now) { struct btrfs_block_group *ret_block_group = NULL, *block_group; int i; for (i = 0; i < BTRFS_NR_DISCARD_LISTS; i++) { struct list_head *discard_list = &discard_ctl->discard_list[i]; if (!list_empty(discard_list)) { block_group = list_first_entry(discard_list, struct btrfs_block_group, discard_list); if (!ret_block_group) ret_block_group = block_group; if (ret_block_group->discard_eligible_time < now) break; if (ret_block_group->discard_eligible_time > block_group->discard_eligible_time) ret_block_group = block_group; } } return ret_block_group; } /* * Look up next block group and set it for use. * * @discard_ctl: discard control * @discard_state: the discard_state of the block_group after state management * @discard_index: the discard_index of the block_group after state management * @now: time when discard was invoked, in ns * * Wrap find_next_block_group() and set the block_group to be in use. * @discard_state's control flow is managed here. Variables related to * @discard_state are reset here as needed (eg. @discard_cursor). @discard_state * and @discard_index are remembered as it may change while we're discarding, * but we want the discard to execute in the context determined here. */ static struct btrfs_block_group *peek_discard_list( struct btrfs_discard_ctl *discard_ctl, enum btrfs_discard_state *discard_state, int *discard_index, u64 now) { struct btrfs_block_group *block_group; spin_lock(&discard_ctl->lock); again: block_group = find_next_block_group(discard_ctl, now); if (block_group && now >= block_group->discard_eligible_time) { if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED && block_group->used != 0) { if (btrfs_is_block_group_data_only(block_group)) { __add_to_discard_list(discard_ctl, block_group); /* * The block group must have been moved to other * discard list even if discard was disabled in * the meantime or a transaction abort happened, * otherwise we can end up in an infinite loop, * always jumping into the 'again' label and * keep getting this block group over and over * in case there are no other block groups in * the discard lists. */ ASSERT(block_group->discard_index != BTRFS_DISCARD_INDEX_UNUSED, "discard_index=%d", block_group->discard_index); } else { list_del_init(&block_group->discard_list); btrfs_put_block_group(block_group); } goto again; } if (block_group->discard_state == BTRFS_DISCARD_RESET_CURSOR) { block_group->discard_cursor = block_group->start; block_group->discard_state = BTRFS_DISCARD_EXTENTS; } } if (block_group) { btrfs_get_block_group(block_group); discard_ctl->block_group = block_group; *discard_state = block_group->discard_state; *discard_index = block_group->discard_index; } spin_unlock(&discard_ctl->lock); return block_group; } /* * Update a block group's filters. * * @block_group: block group of interest * @bytes: recently freed region size after coalescing * * Async discard maintains multiple lists with progressively smaller filters * to prioritize discarding based on size. Should a free space that matches * a larger filter be returned to the free_space_cache, prioritize that discard * by moving @block_group to the proper filter. */ void btrfs_discard_check_filter(struct btrfs_block_group *block_group, u64 bytes) { struct btrfs_discard_ctl *discard_ctl; if (!block_group || !btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC)) return; discard_ctl = &block_group->fs_info->discard_ctl; if (block_group->discard_index > BTRFS_DISCARD_INDEX_START && bytes >= discard_minlen[block_group->discard_index - 1]) { int i; remove_from_discard_list(discard_ctl, block_group); for (i = BTRFS_DISCARD_INDEX_START; i < BTRFS_NR_DISCARD_LISTS; i++) { if (bytes >= discard_minlen[i]) { block_group->discard_index = i; add_to_discard_list(discard_ctl, block_group); break; } } } } /* * Move a block group along the discard lists. * * @discard_ctl: discard control * @block_group: block_group of interest * * Increment @block_group's discard_index. If it falls of the list, let it be. * Otherwise add it back to the appropriate list. */ static void btrfs_update_discard_index(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { block_group->discard_index++; if (block_group->discard_index == BTRFS_NR_DISCARD_LISTS) { block_group->discard_index = 1; return; } add_to_discard_list(discard_ctl, block_group); } /* * Remove a block_group from the discard lists. * * @discard_ctl: discard control * @block_group: block_group of interest * * Remove @block_group from the discard lists. If necessary, wait on the * current work and then reschedule the delayed work. */ void btrfs_discard_cancel_work(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { if (remove_from_discard_list(discard_ctl, block_group)) { cancel_delayed_work_sync(&discard_ctl->work); btrfs_discard_schedule_work(discard_ctl, true); } } /* * Handles queuing the block_groups. * * @discard_ctl: discard control * @block_group: block_group of interest * * Maintain the LRU order of the discard lists. */ void btrfs_discard_queue_work(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { if (!block_group || !btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC)) return; if (block_group->used == 0) add_to_discard_unused_list(discard_ctl, block_group); else add_to_discard_list(discard_ctl, block_group); if (!delayed_work_pending(&discard_ctl->work)) btrfs_discard_schedule_work(discard_ctl, false); } static void __btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, u64 now, bool override) { struct btrfs_block_group *block_group; if (!btrfs_run_discard_work(discard_ctl)) return; if (!override && delayed_work_pending(&discard_ctl->work)) return; block_group = find_next_block_group(discard_ctl, now); if (block_group) { u64 delay = discard_ctl->delay_ms * NSEC_PER_MSEC; u32 kbps_limit = READ_ONCE(discard_ctl->kbps_limit); /* * A single delayed workqueue item is responsible for * discarding, so we can manage the bytes rate limit by keeping * track of the previous discard. */ if (kbps_limit && discard_ctl->prev_discard) { u64 bps_limit = ((u64)kbps_limit) * SZ_1K; u64 bps_delay = div64_u64(discard_ctl->prev_discard * NSEC_PER_SEC, bps_limit); delay = max(delay, bps_delay); } /* * This timeout is to hopefully prevent immediate discarding * in a recently allocated block group. */ if (now < block_group->discard_eligible_time) { u64 bg_timeout = block_group->discard_eligible_time - now; delay = max(delay, bg_timeout); } if (override && discard_ctl->prev_discard) { u64 elapsed = now - discard_ctl->prev_discard_time; if (delay > elapsed) delay -= elapsed; else delay = 0; } mod_delayed_work(discard_ctl->discard_workers, &discard_ctl->work, nsecs_to_jiffies(delay)); } } /* * Responsible for scheduling the discard work. * * @discard_ctl: discard control * @override: override the current timer * * Discards are issued by a delayed workqueue item. @override is used to * update the current delay as the baseline delay interval is reevaluated on * transaction commit. This is also maxed with any other rate limit. */ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl, bool override) { const u64 now = ktime_get_ns(); spin_lock(&discard_ctl->lock); __btrfs_discard_schedule_work(discard_ctl, now, override); spin_unlock(&discard_ctl->lock); } /* * Determine next step of a block_group. * * @discard_ctl: discard control * @block_group: block_group of interest * * Determine the next step for a block group after it's finished going through * a pass on a discard list. If it is unused and fully trimmed, we can mark it * unused and send it to the unused_bgs path. Otherwise, pass it onto the * appropriate filter list or let it fall off. */ static void btrfs_finish_discard_pass(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { remove_from_discard_list(discard_ctl, block_group); if (block_group->used == 0) { if (btrfs_is_free_space_trimmed(block_group)) btrfs_mark_bg_unused(block_group); else add_to_discard_unused_list(discard_ctl, block_group); } else { btrfs_update_discard_index(discard_ctl, block_group); } } /* * Discard work queue callback * * @work: work * * Find the next block_group to start discarding and then discard a single * region. It does this in a two-pass fashion: first extents and second * bitmaps. Completely discarded block groups are sent to the unused_bgs path. */ static void btrfs_discard_workfn(struct work_struct *work) { struct btrfs_discard_ctl *discard_ctl; struct btrfs_block_group *block_group; enum btrfs_discard_state discard_state; int discard_index = 0; u64 trimmed = 0; u64 minlen = 0; u64 now = ktime_get_ns(); discard_ctl = container_of(work, struct btrfs_discard_ctl, work.work); block_group = peek_discard_list(discard_ctl, &discard_state, &discard_index, now); if (!block_group) return; if (!btrfs_run_discard_work(discard_ctl)) { spin_lock(&discard_ctl->lock); btrfs_put_block_group(block_group); discard_ctl->block_group = NULL; spin_unlock(&discard_ctl->lock); return; } if (now < block_group->discard_eligible_time) { spin_lock(&discard_ctl->lock); btrfs_put_block_group(block_group); discard_ctl->block_group = NULL; spin_unlock(&discard_ctl->lock); btrfs_discard_schedule_work(discard_ctl, false); return; } /* Perform discarding */ minlen = discard_minlen[discard_index]; if (discard_state == BTRFS_DISCARD_BITMAPS) { u64 maxlen = 0; /* * Use the previous levels minimum discard length as the max * length filter. In the case something is added to make a * region go beyond the max filter, the entire bitmap is set * back to BTRFS_TRIM_STATE_UNTRIMMED. */ if (discard_index != BTRFS_DISCARD_INDEX_UNUSED) maxlen = discard_minlen[discard_index - 1]; btrfs_trim_block_group_bitmaps(block_group, &trimmed, block_group->discard_cursor, btrfs_block_group_end(block_group), minlen, maxlen, true); discard_ctl->discard_bitmap_bytes += trimmed; } else { btrfs_trim_block_group_extents(block_group, &trimmed, block_group->discard_cursor, btrfs_block_group_end(block_group), minlen, true); discard_ctl->discard_extent_bytes += trimmed; } /* Determine next steps for a block_group */ if (block_group->discard_cursor >= btrfs_block_group_end(block_group)) { if (discard_state == BTRFS_DISCARD_BITMAPS) { btrfs_finish_discard_pass(discard_ctl, block_group); } else { block_group->discard_cursor = block_group->start; spin_lock(&discard_ctl->lock); if (block_group->discard_state != BTRFS_DISCARD_RESET_CURSOR) block_group->discard_state = BTRFS_DISCARD_BITMAPS; spin_unlock(&discard_ctl->lock); } } now = ktime_get_ns(); spin_lock(&discard_ctl->lock); discard_ctl->prev_discard = trimmed; discard_ctl->prev_discard_time = now; btrfs_put_block_group(block_group); discard_ctl->block_group = NULL; __btrfs_discard_schedule_work(discard_ctl, now, false); spin_unlock(&discard_ctl->lock); } /* * Recalculate the base delay. * * @discard_ctl: discard control * * Recalculate the base delay which is based off the total number of * discardable_extents. Clamp this between the lower_limit (iops_limit or 1ms) * and the upper_limit (BTRFS_DISCARD_MAX_DELAY_MSEC). */ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl) { s32 discardable_extents; s64 discardable_bytes; u32 iops_limit; unsigned long min_delay = BTRFS_DISCARD_MIN_DELAY_MSEC; unsigned long delay; discardable_extents = atomic_read(&discard_ctl->discardable_extents); if (!discardable_extents) return; spin_lock(&discard_ctl->lock); /* * The following is to fix a potential -1 discrepancy that we're not * sure how to reproduce. But given that this is the only place that * utilizes these numbers and this is only called by from * btrfs_finish_extent_commit() which is synchronized, we can correct * here. */ if (discardable_extents < 0) atomic_add(-discardable_extents, &discard_ctl->discardable_extents); discardable_bytes = atomic64_read(&discard_ctl->discardable_bytes); if (discardable_bytes < 0) atomic64_add(-discardable_bytes, &discard_ctl->discardable_bytes); if (discardable_extents <= 0) { spin_unlock(&discard_ctl->lock); return; } iops_limit = READ_ONCE(discard_ctl->iops_limit); if (iops_limit) { delay = MSEC_PER_SEC / iops_limit; } else { /* * Unset iops_limit means go as fast as possible, so allow a * delay of 0. */ delay = 0; min_delay = 0; } delay = clamp(delay, min_delay, BTRFS_DISCARD_MAX_DELAY_MSEC); discard_ctl->delay_ms = delay; spin_unlock(&discard_ctl->lock); } /* * Propagate discard counters. * * @block_group: block_group of interest * * Propagate deltas of counters up to the discard_ctl. It maintains a current * counter and a previous counter passing the delta up to the global stat. * Then the current counter value becomes the previous counter value. */ void btrfs_discard_update_discardable(struct btrfs_block_group *block_group) { struct btrfs_free_space_ctl *ctl; struct btrfs_discard_ctl *discard_ctl; s32 extents_delta; s64 bytes_delta; if (!block_group || !btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC) || !btrfs_is_block_group_data_only(block_group)) return; ctl = block_group->free_space_ctl; discard_ctl = &block_group->fs_info->discard_ctl; lockdep_assert_held(&ctl->tree_lock); extents_delta = ctl->discardable_extents[BTRFS_STAT_CURR] - ctl->discardable_extents[BTRFS_STAT_PREV]; if (extents_delta) { atomic_add(extents_delta, &discard_ctl->discardable_extents); ctl->discardable_extents[BTRFS_STAT_PREV] = ctl->discardable_extents[BTRFS_STAT_CURR]; } bytes_delta = ctl->discardable_bytes[BTRFS_STAT_CURR] - ctl->discardable_bytes[BTRFS_STAT_PREV]; if (bytes_delta) { atomic64_add(bytes_delta, &discard_ctl->discardable_bytes); ctl->discardable_bytes[BTRFS_STAT_PREV] = ctl->discardable_bytes[BTRFS_STAT_CURR]; } } /* * Punt unused_bgs list to discard lists. * * @fs_info: fs_info of interest * * The unused_bgs list needs to be punted to the discard lists because the * order of operations is changed. In the normal synchronous discard path, the * block groups are trimmed via a single large trim in transaction commit. This * is ultimately what we are trying to avoid with asynchronous discard. Thus, * it must be done before going down the unused_bgs path. */ void btrfs_discard_punt_unused_bgs_list(struct btrfs_fs_info *fs_info) { struct btrfs_block_group *block_group, *next; spin_lock(&fs_info->unused_bgs_lock); /* We enabled async discard, so punt all to the queue */ list_for_each_entry_safe(block_group, next, &fs_info->unused_bgs, bg_list) { list_del_init(&block_group->bg_list); btrfs_discard_queue_work(&fs_info->discard_ctl, block_group); /* * This put is for the get done by btrfs_mark_bg_unused. * Queueing discard incremented it for discard's reference. */ btrfs_put_block_group(block_group); } spin_unlock(&fs_info->unused_bgs_lock); } /* * Purge discard lists. * * @discard_ctl: discard control * * If we are disabling async discard, we may have intercepted block groups that * are completely free and ready for the unused_bgs path. As discarding will * now happen in transaction commit or not at all, we can safely mark the * corresponding block groups as unused and they will be sent on their merry * way to the unused_bgs list. */ static void btrfs_discard_purge_list(struct btrfs_discard_ctl *discard_ctl) { struct btrfs_block_group *block_group, *next; int i; spin_lock(&discard_ctl->lock); for (i = 0; i < BTRFS_NR_DISCARD_LISTS; i++) { list_for_each_entry_safe(block_group, next, &discard_ctl->discard_list[i], discard_list) { list_del_init(&block_group->discard_list); spin_unlock(&discard_ctl->lock); if (block_group->used == 0) btrfs_mark_bg_unused(block_group); spin_lock(&discard_ctl->lock); btrfs_put_block_group(block_group); } } spin_unlock(&discard_ctl->lock); } void btrfs_discard_resume(struct btrfs_fs_info *fs_info) { if (!btrfs_test_opt(fs_info, DISCARD_ASYNC)) { btrfs_discard_cleanup(fs_info); return; } btrfs_discard_punt_unused_bgs_list(fs_info); set_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags); } void btrfs_discard_stop(struct btrfs_fs_info *fs_info) { clear_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags); } void btrfs_discard_init(struct btrfs_fs_info *fs_info) { struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl; int i; spin_lock_init(&discard_ctl->lock); INIT_DELAYED_WORK(&discard_ctl->work, btrfs_discard_workfn); for (i = 0; i < BTRFS_NR_DISCARD_LISTS; i++) INIT_LIST_HEAD(&discard_ctl->discard_list[i]); discard_ctl->prev_discard = 0; discard_ctl->prev_discard_time = 0; atomic_set(&discard_ctl->discardable_extents, 0); atomic64_set(&discard_ctl->discardable_bytes, 0); discard_ctl->max_discard_size = BTRFS_ASYNC_DISCARD_DEFAULT_MAX_SIZE; discard_ctl->delay_ms = BTRFS_DISCARD_MAX_DELAY_MSEC; discard_ctl->iops_limit = BTRFS_DISCARD_MAX_IOPS; discard_ctl->kbps_limit = 0; discard_ctl->discard_extent_bytes = 0; discard_ctl->discard_bitmap_bytes = 0; atomic64_set(&discard_ctl->discard_bytes_saved, 0); } void btrfs_discard_cleanup(struct btrfs_fs_info *fs_info) { btrfs_discard_stop(fs_info); cancel_delayed_work_sync(&fs_info->discard_ctl.work); btrfs_discard_purge_list(&fs_info->discard_ctl); } |
| 3 1 27 1 23 3 19 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 | // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2010-2011 EIA Electronics, // Kurt Van Dijck <kurt.van.dijck@eia.be> // Copyright (c) 2010-2011 EIA Electronics, // Pieter Beyens <pieter.beyens@eia.be> // Copyright (c) 2017-2019 Pengutronix, // Marc Kleine-Budde <kernel@pengutronix.de> // Copyright (c) 2017-2019 Pengutronix, // Oleksij Rempel <kernel@pengutronix.de> /* J1939 Address Claiming. * Address Claiming in the kernel * - keeps track of the AC states of ECU's, * - resolves NAME<=>SA taking into account the AC states of ECU's. * * All Address Claim msgs (including host-originated msg) are processed * at the receive path (a sent msg is always received again via CAN echo). * As such, the processing of AC msgs is done in the order on which msgs * are sent on the bus. * * This module doesn't send msgs itself (e.g. replies on Address Claims), * this is the responsibility of a user space application or daemon. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/netdevice.h> #include <linux/skbuff.h> #include "j1939-priv.h" static inline name_t j1939_skb_to_name(const struct sk_buff *skb) { return le64_to_cpup((__le64 *)skb->data); } static inline bool j1939_ac_msg_is_request(struct sk_buff *skb) { struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); int req_pgn; if (skb->len < 3 || skcb->addr.pgn != J1939_PGN_REQUEST) return false; req_pgn = skb->data[0] | (skb->data[1] << 8) | (skb->data[2] << 16); return req_pgn == J1939_PGN_ADDRESS_CLAIMED; } static int j1939_ac_verify_outgoing(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); if (skb->len != 8) { netdev_notice(priv->ndev, "tx address claim with dlc %i\n", skb->len); return -EPROTO; } if (skcb->addr.src_name != j1939_skb_to_name(skb)) { netdev_notice(priv->ndev, "tx address claim with different name\n"); return -EPROTO; } if (skcb->addr.sa == J1939_NO_ADDR) { netdev_notice(priv->ndev, "tx address claim with broadcast sa\n"); return -EPROTO; } /* ac must always be a broadcast */ if (skcb->addr.dst_name || skcb->addr.da != J1939_NO_ADDR) { netdev_notice(priv->ndev, "tx address claim with dest, not broadcast\n"); return -EPROTO; } return 0; } int j1939_ac_fixup(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); int ret; u8 addr; /* network mgmt: address claiming msgs */ if (skcb->addr.pgn == J1939_PGN_ADDRESS_CLAIMED) { struct j1939_ecu *ecu; ret = j1939_ac_verify_outgoing(priv, skb); /* return both when failure & when successful */ if (ret < 0) return ret; ecu = j1939_ecu_get_by_name(priv, skcb->addr.src_name); if (!ecu) return -ENODEV; if (ecu->addr != skcb->addr.sa) /* hold further traffic for ecu, remove from parent */ j1939_ecu_unmap(ecu); j1939_ecu_put(ecu); } else if (skcb->addr.src_name) { /* assign source address */ addr = j1939_name_to_addr(priv, skcb->addr.src_name); if (!j1939_address_is_unicast(addr) && !j1939_ac_msg_is_request(skb)) { netdev_notice(priv->ndev, "tx drop: invalid sa for name 0x%016llx\n", skcb->addr.src_name); return -EADDRNOTAVAIL; } skcb->addr.sa = addr; } /* assign destination address */ if (skcb->addr.dst_name) { addr = j1939_name_to_addr(priv, skcb->addr.dst_name); if (!j1939_address_is_unicast(addr)) { netdev_notice(priv->ndev, "tx drop: invalid da for name 0x%016llx\n", skcb->addr.dst_name); return -EADDRNOTAVAIL; } skcb->addr.da = addr; } return 0; } static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); struct j1939_ecu *ecu, *prev; name_t name; if (skb->len != 8) { netdev_notice(priv->ndev, "rx address claim with wrong dlc %i\n", skb->len); return; } name = j1939_skb_to_name(skb); skcb->addr.src_name = name; if (!name) { netdev_notice(priv->ndev, "rx address claim without name\n"); return; } if (!j1939_address_is_valid(skcb->addr.sa)) { netdev_notice(priv->ndev, "rx address claim with broadcast sa\n"); return; } write_lock_bh(&priv->lock); /* Few words on the ECU ref counting: * * First we get an ECU handle, either with * j1939_ecu_get_by_name_locked() (increments the ref counter) * or j1939_ecu_create_locked() (initializes an ECU object * with a ref counter of 1). * * j1939_ecu_unmap_locked() will decrement the ref counter, * but only if the ECU was mapped before. So "ecu" still * belongs to us. * * j1939_ecu_timer_start() will increment the ref counter * before it starts the timer, so we can put the ecu when * leaving this function. */ ecu = j1939_ecu_get_by_name_locked(priv, name); if (ecu && ecu->addr == skcb->addr.sa) { /* The ISO 11783-5 standard, in "4.5.2 - Address claim * requirements", states: * d) No CF shall begin, or resume, transmission on the * network until 250 ms after it has successfully claimed * an address except when responding to a request for * address-claimed. * * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim * prioritization" show that the CF begins the transmission * after 250 ms from the first AC (address-claimed) message * even if it sends another AC message during that time window * to resolve the address contention with another CF. * * As stated in "4.4.2.3 - Address-claimed message": * In order to successfully claim an address, the CF sending * an address claimed message shall not receive a contending * claim from another CF for at least 250 ms. * * As stated in "4.4.3.2 - NAME management (NM) message": * 1) A commanding CF can * d) request that a CF with a specified NAME transmit * the address-claimed message with its current NAME. * 2) A target CF shall * d) send an address-claimed message in response to a * request for a matching NAME * * Taking the above arguments into account, the 250 ms wait is * requested only during network initialization. * * Do not restart the timer on AC message if both the NAME and * the address match and so if the address has already been * claimed (timer has expired) or the AC message has been sent * to resolve the contention with another CF (timer is still * running). */ goto out_ecu_put; } if (!ecu && j1939_address_is_unicast(skcb->addr.sa)) ecu = j1939_ecu_create_locked(priv, name); if (IS_ERR_OR_NULL(ecu)) goto out_unlock_bh; /* cancel pending (previous) address claim */ j1939_ecu_timer_cancel(ecu); if (j1939_address_is_idle(skcb->addr.sa)) { j1939_ecu_unmap_locked(ecu); goto out_ecu_put; } /* save new addr */ if (ecu->addr != skcb->addr.sa) j1939_ecu_unmap_locked(ecu); ecu->addr = skcb->addr.sa; prev = j1939_ecu_get_by_addr_locked(priv, skcb->addr.sa); if (prev) { if (ecu->name > prev->name) { j1939_ecu_unmap_locked(ecu); j1939_ecu_put(prev); goto out_ecu_put; } else { /* kick prev if less or equal */ j1939_ecu_unmap_locked(prev); j1939_ecu_put(prev); } } j1939_ecu_timer_start(ecu); out_ecu_put: j1939_ecu_put(ecu); out_unlock_bh: write_unlock_bh(&priv->lock); } void j1939_ac_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); struct j1939_ecu *ecu; /* network mgmt */ if (skcb->addr.pgn == J1939_PGN_ADDRESS_CLAIMED) { j1939_ac_process(priv, skb); } else if (j1939_address_is_unicast(skcb->addr.sa)) { /* assign source name */ ecu = j1939_ecu_get_by_addr(priv, skcb->addr.sa); if (ecu) { skcb->addr.src_name = ecu->name; j1939_ecu_put(ecu); } } /* assign destination name */ ecu = j1939_ecu_get_by_addr(priv, skcb->addr.da); if (ecu) { skcb->addr.dst_name = ecu->name; j1939_ecu_put(ecu); } } |
| 260 260 245 16 16 13 13 237 16 16 13 101 8 137 251 243 259 6 240 10 3 250 251 233 10 258 258 256 258 258 256 258 257 257 10 10 10 10 10 10 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005,2006,2007,2008 IBM Corporation * * Authors: * Mimi Zohar <zohar@us.ibm.com> * Kylene Hall <kjhall@us.ibm.com> * * File: ima_crypto.c * Calculates md5/sha1 file hash, template hash, boot-aggreate hash */ #include <linux/kernel.h> #include <linux/moduleparam.h> #include <linux/ratelimit.h> #include <linux/file.h> #include <linux/crypto.h> #include <linux/scatterlist.h> #include <linux/err.h> #include <linux/slab.h> #include <crypto/hash.h> #include "ima.h" /* minimum file size for ahash use */ static unsigned long ima_ahash_minsize; module_param_named(ahash_minsize, ima_ahash_minsize, ulong, 0644); MODULE_PARM_DESC(ahash_minsize, "Minimum file size for ahash use"); /* default is 0 - 1 page. */ static int ima_maxorder; static unsigned int ima_bufsize = PAGE_SIZE; static int param_set_bufsize(const char *val, const struct kernel_param *kp) { unsigned long long size; int order; size = memparse(val, NULL); order = get_order(size); if (order > MAX_PAGE_ORDER) return -EINVAL; ima_maxorder = order; ima_bufsize = PAGE_SIZE << order; return 0; } static const struct kernel_param_ops param_ops_bufsize = { .set = param_set_bufsize, .get = param_get_uint, }; #define param_check_bufsize(name, p) __param_check(name, p, unsigned int) module_param_named(ahash_bufsize, ima_bufsize, bufsize, 0644); MODULE_PARM_DESC(ahash_bufsize, "Maximum ahash buffer size"); static struct crypto_shash *ima_shash_tfm; static struct crypto_ahash *ima_ahash_tfm; int ima_sha1_idx __ro_after_init; int ima_hash_algo_idx __ro_after_init; /* * Additional number of slots reserved, as needed, for SHA1 * and IMA default algo. */ int ima_extra_slots __ro_after_init; struct ima_algo_desc *ima_algo_array __ro_after_init; static int __init ima_init_ima_crypto(void) { long rc; ima_shash_tfm = crypto_alloc_shash(hash_algo_name[ima_hash_algo], 0, 0); if (IS_ERR(ima_shash_tfm)) { rc = PTR_ERR(ima_shash_tfm); pr_err("Can not allocate %s (reason: %ld)\n", hash_algo_name[ima_hash_algo], rc); return rc; } pr_info("Allocated hash algorithm: %s\n", hash_algo_name[ima_hash_algo]); return 0; } static struct crypto_shash *ima_alloc_tfm(enum hash_algo algo) { struct crypto_shash *tfm = ima_shash_tfm; int rc, i; if (algo < 0 || algo >= HASH_ALGO__LAST) algo = ima_hash_algo; if (algo == ima_hash_algo) return tfm; for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++) if (ima_algo_array[i].tfm && ima_algo_array[i].algo == algo) return ima_algo_array[i].tfm; tfm = crypto_alloc_shash(hash_algo_name[algo], 0, 0); if (IS_ERR(tfm)) { rc = PTR_ERR(tfm); pr_err("Can not allocate %s (reason: %d)\n", hash_algo_name[algo], rc); } return tfm; } int __init ima_init_crypto(void) { enum hash_algo algo; long rc; int i; rc = ima_init_ima_crypto(); if (rc) return rc; ima_sha1_idx = -1; ima_hash_algo_idx = -1; for (i = 0; i < NR_BANKS(ima_tpm_chip); i++) { algo = ima_tpm_chip->allocated_banks[i].crypto_id; if (algo == HASH_ALGO_SHA1) ima_sha1_idx = i; if (algo == ima_hash_algo) ima_hash_algo_idx = i; } if (ima_sha1_idx < 0) { ima_sha1_idx = NR_BANKS(ima_tpm_chip) + ima_extra_slots++; if (ima_hash_algo == HASH_ALGO_SHA1) ima_hash_algo_idx = ima_sha1_idx; } if (ima_hash_algo_idx < 0) ima_hash_algo_idx = NR_BANKS(ima_tpm_chip) + ima_extra_slots++; ima_algo_array = kcalloc(NR_BANKS(ima_tpm_chip) + ima_extra_slots, sizeof(*ima_algo_array), GFP_KERNEL); if (!ima_algo_array) { rc = -ENOMEM; goto out; } for (i = 0; i < NR_BANKS(ima_tpm_chip); i++) { algo = ima_tpm_chip->allocated_banks[i].crypto_id; ima_algo_array[i].algo = algo; /* unknown TPM algorithm */ if (algo == HASH_ALGO__LAST) continue; if (algo == ima_hash_algo) { ima_algo_array[i].tfm = ima_shash_tfm; continue; } ima_algo_array[i].tfm = ima_alloc_tfm(algo); if (IS_ERR(ima_algo_array[i].tfm)) { if (algo == HASH_ALGO_SHA1) { rc = PTR_ERR(ima_algo_array[i].tfm); ima_algo_array[i].tfm = NULL; goto out_array; } ima_algo_array[i].tfm = NULL; } } if (ima_sha1_idx >= NR_BANKS(ima_tpm_chip)) { if (ima_hash_algo == HASH_ALGO_SHA1) { ima_algo_array[ima_sha1_idx].tfm = ima_shash_tfm; } else { ima_algo_array[ima_sha1_idx].tfm = ima_alloc_tfm(HASH_ALGO_SHA1); if (IS_ERR(ima_algo_array[ima_sha1_idx].tfm)) { rc = PTR_ERR(ima_algo_array[ima_sha1_idx].tfm); goto out_array; } } ima_algo_array[ima_sha1_idx].algo = HASH_ALGO_SHA1; } if (ima_hash_algo_idx >= NR_BANKS(ima_tpm_chip) && ima_hash_algo_idx != ima_sha1_idx) { ima_algo_array[ima_hash_algo_idx].tfm = ima_shash_tfm; ima_algo_array[ima_hash_algo_idx].algo = ima_hash_algo; } return 0; out_array: for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++) { if (!ima_algo_array[i].tfm || ima_algo_array[i].tfm == ima_shash_tfm) continue; crypto_free_shash(ima_algo_array[i].tfm); } kfree(ima_algo_array); out: crypto_free_shash(ima_shash_tfm); return rc; } static void ima_free_tfm(struct crypto_shash *tfm) { int i; if (tfm == ima_shash_tfm) return; for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++) if (ima_algo_array[i].tfm == tfm) return; crypto_free_shash(tfm); } /** * ima_alloc_pages() - Allocate contiguous pages. * @max_size: Maximum amount of memory to allocate. * @allocated_size: Returned size of actual allocation. * @last_warn: Should the min_size allocation warn or not. * * Tries to do opportunistic allocation for memory first trying to allocate * max_size amount of memory and then splitting that until zero order is * reached. Allocation is tried without generating allocation warnings unless * last_warn is set. Last_warn set affects only last allocation of zero order. * * By default, ima_maxorder is 0 and it is equivalent to kmalloc(GFP_KERNEL) * * Return pointer to allocated memory, or NULL on failure. */ static void *ima_alloc_pages(loff_t max_size, size_t *allocated_size, int last_warn) { void *ptr; int order = ima_maxorder; gfp_t gfp_mask = __GFP_RECLAIM | __GFP_NOWARN | __GFP_NORETRY; if (order) order = min(get_order(max_size), order); for (; order; order--) { ptr = (void *)__get_free_pages(gfp_mask, order); if (ptr) { *allocated_size = PAGE_SIZE << order; return ptr; } } /* order is zero - one page */ gfp_mask = GFP_KERNEL; if (!last_warn) gfp_mask |= __GFP_NOWARN; ptr = (void *)__get_free_pages(gfp_mask, 0); if (ptr) { *allocated_size = PAGE_SIZE; return ptr; } *allocated_size = 0; return NULL; } /** * ima_free_pages() - Free pages allocated by ima_alloc_pages(). * @ptr: Pointer to allocated pages. * @size: Size of allocated buffer. */ static void ima_free_pages(void *ptr, size_t size) { if (!ptr) return; free_pages((unsigned long)ptr, get_order(size)); } static struct crypto_ahash *ima_alloc_atfm(enum hash_algo algo) { struct crypto_ahash *tfm = ima_ahash_tfm; int rc; if (algo < 0 || algo >= HASH_ALGO__LAST) algo = ima_hash_algo; if (algo != ima_hash_algo || !tfm) { tfm = crypto_alloc_ahash(hash_algo_name[algo], 0, 0); if (!IS_ERR(tfm)) { if (algo == ima_hash_algo) ima_ahash_tfm = tfm; } else { rc = PTR_ERR(tfm); pr_err("Can not allocate %s (reason: %d)\n", hash_algo_name[algo], rc); } } return tfm; } static void ima_free_atfm(struct crypto_ahash *tfm) { if (tfm != ima_ahash_tfm) crypto_free_ahash(tfm); } static inline int ahash_wait(int err, struct crypto_wait *wait) { err = crypto_wait_req(err, wait); if (err) pr_crit_ratelimited("ahash calculation failed: err: %d\n", err); return err; } static int ima_calc_file_hash_atfm(struct file *file, struct ima_digest_data *hash, struct crypto_ahash *tfm) { loff_t i_size, offset; char *rbuf[2] = { NULL, }; int rc, rbuf_len, active = 0, ahash_rc = 0; struct ahash_request *req; struct scatterlist sg[1]; struct crypto_wait wait; size_t rbuf_size[2]; hash->length = crypto_ahash_digestsize(tfm); req = ahash_request_alloc(tfm, GFP_KERNEL); if (!req) return -ENOMEM; crypto_init_wait(&wait); ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &wait); rc = ahash_wait(crypto_ahash_init(req), &wait); if (rc) goto out1; i_size = i_size_read(file_inode(file)); if (i_size == 0) goto out2; /* * Try to allocate maximum size of memory. * Fail if even a single page cannot be allocated. */ rbuf[0] = ima_alloc_pages(i_size, &rbuf_size[0], 1); if (!rbuf[0]) { rc = -ENOMEM; goto out1; } /* Only allocate one buffer if that is enough. */ if (i_size > rbuf_size[0]) { /* * Try to allocate secondary buffer. If that fails fallback to * using single buffering. Use previous memory allocation size * as baseline for possible allocation size. */ rbuf[1] = ima_alloc_pages(i_size - rbuf_size[0], &rbuf_size[1], 0); } for (offset = 0; offset < i_size; offset += rbuf_len) { if (!rbuf[1] && offset) { /* Not using two buffers, and it is not the first * read/request, wait for the completion of the * previous ahash_update() request. */ rc = ahash_wait(ahash_rc, &wait); if (rc) goto out3; } /* read buffer */ rbuf_len = min_t(loff_t, i_size - offset, rbuf_size[active]); rc = integrity_kernel_read(file, offset, rbuf[active], rbuf_len); if (rc != rbuf_len) { if (rc >= 0) rc = -EINVAL; /* * Forward current rc, do not overwrite with return value * from ahash_wait() */ ahash_wait(ahash_rc, &wait); goto out3; } if (rbuf[1] && offset) { /* Using two buffers, and it is not the first * read/request, wait for the completion of the * previous ahash_update() request. */ rc = ahash_wait(ahash_rc, &wait); if (rc) goto out3; } sg_init_one(&sg[0], rbuf[active], rbuf_len); ahash_request_set_crypt(req, sg, NULL, rbuf_len); ahash_rc = crypto_ahash_update(req); if (rbuf[1]) active = !active; /* swap buffers, if we use two */ } /* wait for the last update request to complete */ rc = ahash_wait(ahash_rc, &wait); out3: ima_free_pages(rbuf[0], rbuf_size[0]); ima_free_pages(rbuf[1], rbuf_size[1]); out2: if (!rc) { ahash_request_set_crypt(req, NULL, hash->digest, 0); rc = ahash_wait(crypto_ahash_final(req), &wait); } out1: ahash_request_free(req); return rc; } static int ima_calc_file_ahash(struct file *file, struct ima_digest_data *hash) { struct crypto_ahash *tfm; int rc; tfm = ima_alloc_atfm(hash->algo); if (IS_ERR(tfm)) return PTR_ERR(tfm); rc = ima_calc_file_hash_atfm(file, hash, tfm); ima_free_atfm(tfm); return rc; } static int ima_calc_file_hash_tfm(struct file *file, struct ima_digest_data *hash, struct crypto_shash *tfm) { loff_t i_size, offset = 0; char *rbuf; int rc; SHASH_DESC_ON_STACK(shash, tfm); shash->tfm = tfm; hash->length = crypto_shash_digestsize(tfm); rc = crypto_shash_init(shash); if (rc != 0) return rc; i_size = i_size_read(file_inode(file)); if (i_size == 0) goto out; rbuf = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!rbuf) return -ENOMEM; while (offset < i_size) { int rbuf_len; rbuf_len = integrity_kernel_read(file, offset, rbuf, PAGE_SIZE); if (rbuf_len < 0) { rc = rbuf_len; break; } if (rbuf_len == 0) { /* unexpected EOF */ rc = -EINVAL; break; } offset += rbuf_len; rc = crypto_shash_update(shash, rbuf, rbuf_len); if (rc) break; } kfree(rbuf); out: if (!rc) rc = crypto_shash_final(shash, hash->digest); return rc; } static int ima_calc_file_shash(struct file *file, struct ima_digest_data *hash) { struct crypto_shash *tfm; int rc; tfm = ima_alloc_tfm(hash->algo); if (IS_ERR(tfm)) return PTR_ERR(tfm); rc = ima_calc_file_hash_tfm(file, hash, tfm); ima_free_tfm(tfm); return rc; } /* * ima_calc_file_hash - calculate file hash * * Asynchronous hash (ahash) allows using HW acceleration for calculating * a hash. ahash performance varies for different data sizes on different * crypto accelerators. shash performance might be better for smaller files. * The 'ima.ahash_minsize' module parameter allows specifying the best * minimum file size for using ahash on the system. * * If the ima.ahash_minsize parameter is not specified, this function uses * shash for the hash calculation. If ahash fails, it falls back to using * shash. */ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash) { loff_t i_size; int rc; struct file *f = file; bool new_file_instance = false; /* * For consistency, fail file's opened with the O_DIRECT flag on * filesystems mounted with/without DAX option. */ if (file->f_flags & O_DIRECT) { hash->length = hash_digest_size[ima_hash_algo]; hash->algo = ima_hash_algo; return -EINVAL; } /* Open a new file instance in O_RDONLY if we cannot read */ if (!(file->f_mode & FMODE_READ)) { int flags = file->f_flags & ~(O_WRONLY | O_APPEND | O_TRUNC | O_CREAT | O_NOCTTY | O_EXCL); flags |= O_RDONLY; f = dentry_open(&file->f_path, flags, file->f_cred); if (IS_ERR(f)) return PTR_ERR(f); new_file_instance = true; } i_size = i_size_read(file_inode(f)); if (ima_ahash_minsize && i_size >= ima_ahash_minsize) { rc = ima_calc_file_ahash(f, hash); if (!rc) goto out; } rc = ima_calc_file_shash(f, hash); out: if (new_file_instance) fput(f); return rc; } /* * Calculate the hash of template data */ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data, struct ima_template_entry *entry, int tfm_idx) { SHASH_DESC_ON_STACK(shash, ima_algo_array[tfm_idx].tfm); struct ima_template_desc *td = entry->template_desc; int num_fields = entry->template_desc->num_fields; int rc, i; shash->tfm = ima_algo_array[tfm_idx].tfm; rc = crypto_shash_init(shash); if (rc != 0) return rc; for (i = 0; i < num_fields; i++) { u8 buffer[IMA_EVENT_NAME_LEN_MAX + 1] = { 0 }; u8 *data_to_hash = field_data[i].data; u32 datalen = field_data[i].len; u32 datalen_to_hash = !ima_canonical_fmt ? datalen : (__force u32)cpu_to_le32(datalen); if (strcmp(td->name, IMA_TEMPLATE_IMA_NAME) != 0) { rc = crypto_shash_update(shash, (const u8 *) &datalen_to_hash, sizeof(datalen_to_hash)); if (rc) break; } else if (strcmp(td->fields[i]->field_id, "n") == 0) { memcpy(buffer, data_to_hash, datalen); data_to_hash = buffer; datalen = IMA_EVENT_NAME_LEN_MAX + 1; } rc = crypto_shash_update(shash, data_to_hash, datalen); if (rc) break; } if (!rc) rc = crypto_shash_final(shash, entry->digests[tfm_idx].digest); return rc; } int ima_calc_field_array_hash(struct ima_field_data *field_data, struct ima_template_entry *entry) { u16 alg_id; int rc, i; rc = ima_calc_field_array_hash_tfm(field_data, entry, ima_sha1_idx); if (rc) return rc; entry->digests[ima_sha1_idx].alg_id = TPM_ALG_SHA1; for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++) { if (i == ima_sha1_idx) continue; if (i < NR_BANKS(ima_tpm_chip)) { alg_id = ima_tpm_chip->allocated_banks[i].alg_id; entry->digests[i].alg_id = alg_id; } /* for unmapped TPM algorithms digest is still a padded SHA1 */ if (!ima_algo_array[i].tfm) { memcpy(entry->digests[i].digest, entry->digests[ima_sha1_idx].digest, TPM_DIGEST_SIZE); continue; } rc = ima_calc_field_array_hash_tfm(field_data, entry, i); if (rc) return rc; } return rc; } static int calc_buffer_ahash_atfm(const void *buf, loff_t len, struct ima_digest_data *hash, struct crypto_ahash *tfm) { struct ahash_request *req; struct scatterlist sg; struct crypto_wait wait; int rc, ahash_rc = 0; hash->length = crypto_ahash_digestsize(tfm); req = ahash_request_alloc(tfm, GFP_KERNEL); if (!req) return -ENOMEM; crypto_init_wait(&wait); ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &wait); rc = ahash_wait(crypto_ahash_init(req), &wait); if (rc) goto out; sg_init_one(&sg, buf, len); ahash_request_set_crypt(req, &sg, NULL, len); ahash_rc = crypto_ahash_update(req); /* wait for the update request to complete */ rc = ahash_wait(ahash_rc, &wait); if (!rc) { ahash_request_set_crypt(req, NULL, hash->digest, 0); rc = ahash_wait(crypto_ahash_final(req), &wait); } out: ahash_request_free(req); return rc; } static int calc_buffer_ahash(const void *buf, loff_t len, struct ima_digest_data *hash) { struct crypto_ahash *tfm; int rc; tfm = ima_alloc_atfm(hash->algo); if (IS_ERR(tfm)) return PTR_ERR(tfm); rc = calc_buffer_ahash_atfm(buf, len, hash, tfm); ima_free_atfm(tfm); return rc; } static int calc_buffer_shash_tfm(const void *buf, loff_t size, struct ima_digest_data *hash, struct crypto_shash *tfm) { SHASH_DESC_ON_STACK(shash, tfm); unsigned int len; int rc; shash->tfm = tfm; hash->length = crypto_shash_digestsize(tfm); rc = crypto_shash_init(shash); if (rc != 0) return rc; while (size) { len = size < PAGE_SIZE ? size : PAGE_SIZE; rc = crypto_shash_update(shash, buf, len); if (rc) break; buf += len; size -= len; } if (!rc) rc = crypto_shash_final(shash, hash->digest); return rc; } static int calc_buffer_shash(const void *buf, loff_t len, struct ima_digest_data *hash) { struct crypto_shash *tfm; int rc; tfm = ima_alloc_tfm(hash->algo); if (IS_ERR(tfm)) return PTR_ERR(tfm); rc = calc_buffer_shash_tfm(buf, len, hash, tfm); ima_free_tfm(tfm); return rc; } int ima_calc_buffer_hash(const void *buf, loff_t len, struct ima_digest_data *hash) { int rc; if (ima_ahash_minsize && len >= ima_ahash_minsize) { rc = calc_buffer_ahash(buf, len, hash); if (!rc) return 0; } return calc_buffer_shash(buf, len, hash); } static void ima_pcrread(u32 idx, struct tpm_digest *d) { if (!ima_tpm_chip) return; if (tpm_pcr_read(ima_tpm_chip, idx, d) != 0) pr_err("Error Communicating to TPM chip\n"); } /* * The boot_aggregate is a cumulative hash over TPM registers 0 - 7. With * TPM 1.2 the boot_aggregate was based on reading the SHA1 PCRs, but with * TPM 2.0 hash agility, TPM chips could support multiple TPM PCR banks, * allowing firmware to configure and enable different banks. * * Knowing which TPM bank is read to calculate the boot_aggregate digest * needs to be conveyed to a verifier. For this reason, use the same * hash algorithm for reading the TPM PCRs as for calculating the boot * aggregate digest as stored in the measurement list. */ static int ima_calc_boot_aggregate_tfm(char *digest, u16 alg_id, struct crypto_shash *tfm) { struct tpm_digest d = { .alg_id = alg_id, .digest = {0} }; int rc; u32 i; SHASH_DESC_ON_STACK(shash, tfm); shash->tfm = tfm; pr_devel("calculating the boot-aggregate based on TPM bank: %04x\n", d.alg_id); rc = crypto_shash_init(shash); if (rc != 0) return rc; /* cumulative digest over TPM registers 0-7 */ for (i = TPM_PCR0; i < TPM_PCR8; i++) { ima_pcrread(i, &d); /* now accumulate with current aggregate */ rc = crypto_shash_update(shash, d.digest, crypto_shash_digestsize(tfm)); if (rc != 0) return rc; } /* * Extend cumulative digest over TPM registers 8-9, which contain * measurement for the kernel command line (reg. 8) and image (reg. 9) * in a typical PCR allocation. Registers 8-9 are only included in * non-SHA1 boot_aggregate digests to avoid ambiguity. */ if (alg_id != TPM_ALG_SHA1) { for (i = TPM_PCR8; i < TPM_PCR10; i++) { ima_pcrread(i, &d); rc = crypto_shash_update(shash, d.digest, crypto_shash_digestsize(tfm)); } } if (!rc) crypto_shash_final(shash, digest); return rc; } int ima_calc_boot_aggregate(struct ima_digest_data *hash) { struct crypto_shash *tfm; u16 crypto_id, alg_id; int rc, i, bank_idx = -1; for (i = 0; i < ima_tpm_chip->nr_allocated_banks; i++) { crypto_id = ima_tpm_chip->allocated_banks[i].crypto_id; if (crypto_id == hash->algo) { bank_idx = i; break; } if (crypto_id == HASH_ALGO_SHA256) bank_idx = i; if (bank_idx == -1 && crypto_id == HASH_ALGO_SHA1) bank_idx = i; } if (bank_idx == -1) { pr_err("No suitable TPM algorithm for boot aggregate\n"); return 0; } hash->algo = ima_tpm_chip->allocated_banks[bank_idx].crypto_id; tfm = ima_alloc_tfm(hash->algo); if (IS_ERR(tfm)) return PTR_ERR(tfm); hash->length = crypto_shash_digestsize(tfm); alg_id = ima_tpm_chip->allocated_banks[bank_idx].alg_id; rc = ima_calc_boot_aggregate_tfm(hash->digest, alg_id, tfm); ima_free_tfm(tfm); return rc; } |
| 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2007, 2008 Karsten Wiese <fzu@wemgehoertderstaat.de> */ #include <linux/slab.h> #include <linux/usb.h> #include <linux/usb/audio.h> #include <linux/module.h> #include <sound/core.h> #include <sound/hwdep.h> #include <sound/pcm.h> #include <sound/initval.h> #define MODNAME "US122L" #include "usb_stream.c" #include "../usbaudio.h" #include "../midi.h" #include "us122l.h" MODULE_AUTHOR("Karsten Wiese <fzu@wemgehoertderstaat.de>"); MODULE_DESCRIPTION("TASCAM "NAME_ALLCAPS" Version 0.5"); MODULE_LICENSE("GPL"); static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-max */ static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* Id for this card */ /* Enable this card */ static bool enable[SNDRV_CARDS] = SNDRV_DEFAULT_ENABLE_PNP; module_param_array(index, int, NULL, 0444); MODULE_PARM_DESC(index, "Index value for "NAME_ALLCAPS"."); module_param_array(id, charp, NULL, 0444); MODULE_PARM_DESC(id, "ID string for "NAME_ALLCAPS"."); module_param_array(enable, bool, NULL, 0444); MODULE_PARM_DESC(enable, "Enable "NAME_ALLCAPS"."); /* driver_info flags */ #define US122L_FLAG_US144 BIT(0) static int snd_us122l_card_used[SNDRV_CARDS]; static int us122l_create_usbmidi(struct snd_card *card) { static const struct snd_usb_midi_endpoint_info quirk_data = { .out_ep = 4, .in_ep = 3, .out_cables = 0x001, .in_cables = 0x001 }; static const struct snd_usb_audio_quirk quirk = { .vendor_name = "US122L", .product_name = NAME_ALLCAPS, .ifnum = 1, .type = QUIRK_MIDI_US122L, .data = &quirk_data }; struct usb_device *dev = US122L(card)->dev; struct usb_interface *iface = usb_ifnum_to_if(dev, 1); return snd_usbmidi_create(card, iface, &US122L(card)->midi_list, &quirk); } static int us144_create_usbmidi(struct snd_card *card) { static const struct snd_usb_midi_endpoint_info quirk_data = { .out_ep = 4, .in_ep = 3, .out_cables = 0x001, .in_cables = 0x001 }; static const struct snd_usb_audio_quirk quirk = { .vendor_name = "US144", .product_name = NAME_ALLCAPS, .ifnum = 0, .type = QUIRK_MIDI_US122L, .data = &quirk_data }; struct usb_device *dev = US122L(card)->dev; struct usb_interface *iface = usb_ifnum_to_if(dev, 0); return snd_usbmidi_create(card, iface, &US122L(card)->midi_list, &quirk); } static void pt_info_set(struct usb_device *dev, u8 v) { usb_control_msg_send(dev, 0, 'I', USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, v, 0, NULL, 0, 1000, GFP_NOIO); } static vm_fault_t usb_stream_hwdep_vm_fault(struct vm_fault *vmf) { unsigned long offset; struct page *page; void *vaddr; struct us122l *us122l = vmf->vma->vm_private_data; struct usb_stream *s; guard(mutex)(&us122l->mutex); s = us122l->sk.s; if (!s) return VM_FAULT_SIGBUS; offset = vmf->pgoff << PAGE_SHIFT; if (offset < PAGE_ALIGN(s->read_size)) { vaddr = (char *)s + offset; } else { offset -= PAGE_ALIGN(s->read_size); if (offset >= PAGE_ALIGN(s->write_size)) return VM_FAULT_SIGBUS; vaddr = us122l->sk.write_page + offset; } page = virt_to_page(vaddr); get_page(page); vmf->page = page; return 0; } static const struct vm_operations_struct usb_stream_hwdep_vm_ops = { .fault = usb_stream_hwdep_vm_fault, }; static int usb_stream_hwdep_open(struct snd_hwdep *hw, struct file *file) { struct us122l *us122l = hw->private_data; struct usb_interface *iface; if (hw->used >= 2) return -EBUSY; if (!us122l->first) us122l->first = file; if (us122l->is_us144) { iface = usb_ifnum_to_if(us122l->dev, 0); usb_autopm_get_interface(iface); } iface = usb_ifnum_to_if(us122l->dev, 1); usb_autopm_get_interface(iface); return 0; } static int usb_stream_hwdep_release(struct snd_hwdep *hw, struct file *file) { struct us122l *us122l = hw->private_data; struct usb_interface *iface; if (us122l->is_us144) { iface = usb_ifnum_to_if(us122l->dev, 0); usb_autopm_put_interface(iface); } iface = usb_ifnum_to_if(us122l->dev, 1); usb_autopm_put_interface(iface); if (us122l->first == file) us122l->first = NULL; guard(mutex)(&us122l->mutex); if (us122l->master == file) us122l->master = us122l->slave; us122l->slave = NULL; return 0; } static int usb_stream_hwdep_mmap(struct snd_hwdep *hw, struct file *filp, struct vm_area_struct *area) { unsigned long size = area->vm_end - area->vm_start; struct us122l *us122l = hw->private_data; unsigned long offset; struct usb_stream *s; bool read; offset = area->vm_pgoff << PAGE_SHIFT; guard(mutex)(&us122l->mutex); s = us122l->sk.s; read = offset < s->read_size; if (read && area->vm_flags & VM_WRITE) return -EPERM; /* if userspace tries to mmap beyond end of our buffer, fail */ if (size > PAGE_ALIGN(read ? s->read_size : s->write_size)) { dev_warn(hw->card->dev, "%s: size %lu > %u\n", __func__, size, read ? s->read_size : s->write_size); return -EINVAL; } area->vm_ops = &usb_stream_hwdep_vm_ops; vm_flags_set(area, VM_DONTDUMP); if (!read) vm_flags_set(area, VM_DONTEXPAND); area->vm_private_data = us122l; return 0; } static __poll_t usb_stream_hwdep_poll(struct snd_hwdep *hw, struct file *file, poll_table *wait) { struct us122l *us122l = hw->private_data; unsigned int *polled; __poll_t mask; poll_wait(file, &us122l->sk.sleep, wait); mask = EPOLLIN | EPOLLOUT | EPOLLWRNORM | EPOLLERR; if (mutex_trylock(&us122l->mutex)) { struct usb_stream *s = us122l->sk.s; if (s && s->state == usb_stream_ready) { if (us122l->first == file) polled = &s->periods_polled; else polled = &us122l->second_periods_polled; if (*polled != s->periods_done) { *polled = s->periods_done; mask = EPOLLIN | EPOLLOUT | EPOLLWRNORM; } else { mask = 0; } } mutex_unlock(&us122l->mutex); } return mask; } static void us122l_stop(struct us122l *us122l) { struct list_head *p; list_for_each(p, &us122l->midi_list) snd_usbmidi_input_stop(p); usb_stream_stop(&us122l->sk); usb_stream_free(&us122l->sk); } static int us122l_set_sample_rate(struct usb_device *dev, int rate) { unsigned int ep = 0x81; unsigned char data[3]; int err; data[0] = rate; data[1] = rate >> 8; data[2] = rate >> 16; err = usb_control_msg_send(dev, 0, UAC_SET_CUR, USB_TYPE_CLASS | USB_RECIP_ENDPOINT | USB_DIR_OUT, UAC_EP_CS_ATTR_SAMPLE_RATE << 8, ep, data, 3, 1000, GFP_NOIO); if (err) dev_err(&dev->dev, "%d: cannot set freq %d to ep 0x%x\n", dev->devnum, rate, ep); return err; } static bool us122l_start(struct us122l *us122l, unsigned int rate, unsigned int period_frames) { struct list_head *p; int err; unsigned int use_packsize = 0; bool success = false; if (us122l->dev->speed == USB_SPEED_HIGH) { /* The us-122l's descriptor defaults to iso max_packsize 78, which isn't needed for samplerates <= 48000. Lets save some memory: */ switch (rate) { case 44100: use_packsize = 36; break; case 48000: use_packsize = 42; break; case 88200: use_packsize = 72; break; } } if (!usb_stream_new(&us122l->sk, us122l->dev, 1, 2, rate, use_packsize, period_frames, 6)) goto out; err = us122l_set_sample_rate(us122l->dev, rate); if (err < 0) { us122l_stop(us122l); dev_err(&us122l->dev->dev, "us122l_set_sample_rate error\n"); goto out; } err = usb_stream_start(&us122l->sk); if (err < 0) { us122l_stop(us122l); dev_err(&us122l->dev->dev, "%s error %i\n", __func__, err); goto out; } list_for_each(p, &us122l->midi_list) snd_usbmidi_input_start(p); success = true; out: return success; } static int usb_stream_hwdep_ioctl(struct snd_hwdep *hw, struct file *file, unsigned int cmd, unsigned long arg) { struct usb_stream_config cfg; struct us122l *us122l = hw->private_data; struct usb_stream *s; unsigned int min_period_frames; int err = 0; bool high_speed; if (cmd != SNDRV_USB_STREAM_IOCTL_SET_PARAMS) return -ENOTTY; if (copy_from_user(&cfg, (void __user *)arg, sizeof(cfg))) return -EFAULT; if (cfg.version != USB_STREAM_INTERFACE_VERSION) return -ENXIO; high_speed = us122l->dev->speed == USB_SPEED_HIGH; if ((cfg.sample_rate != 44100 && cfg.sample_rate != 48000 && (!high_speed || (cfg.sample_rate != 88200 && cfg.sample_rate != 96000))) || cfg.frame_size != 6 || cfg.period_frames > 0x3000) return -EINVAL; switch (cfg.sample_rate) { case 44100: min_period_frames = 48; break; case 48000: min_period_frames = 52; break; default: min_period_frames = 104; break; } if (!high_speed) min_period_frames <<= 1; if (cfg.period_frames < min_period_frames) return -EINVAL; snd_power_wait(hw->card); guard(mutex)(&us122l->mutex); s = us122l->sk.s; if (!us122l->master) { us122l->master = file; } else if (us122l->master != file) { if (!s || memcmp(&cfg, &s->cfg, sizeof(cfg))) { err = -EIO; goto unlock; } us122l->slave = file; } if (!s || memcmp(&cfg, &s->cfg, sizeof(cfg)) || s->state == usb_stream_xrun) { us122l_stop(us122l); if (!us122l_start(us122l, cfg.sample_rate, cfg.period_frames)) err = -EIO; else err = 1; } unlock: wake_up_all(&us122l->sk.sleep); return err; } #define SND_USB_STREAM_ID "USB STREAM" static int usb_stream_hwdep_new(struct snd_card *card) { int err; struct snd_hwdep *hw; struct usb_device *dev = US122L(card)->dev; err = snd_hwdep_new(card, SND_USB_STREAM_ID, 0, &hw); if (err < 0) return err; hw->iface = SNDRV_HWDEP_IFACE_USB_STREAM; hw->private_data = US122L(card); hw->ops.open = usb_stream_hwdep_open; hw->ops.release = usb_stream_hwdep_release; hw->ops.ioctl = usb_stream_hwdep_ioctl; hw->ops.ioctl_compat = usb_stream_hwdep_ioctl; hw->ops.mmap = usb_stream_hwdep_mmap; hw->ops.poll = usb_stream_hwdep_poll; sprintf(hw->name, "/dev/bus/usb/%03d/%03d/hwdeppcm", dev->bus->busnum, dev->devnum); return 0; } static bool us122l_create_card(struct snd_card *card) { int err; struct us122l *us122l = US122L(card); if (us122l->is_us144) { err = usb_set_interface(us122l->dev, 0, 1); if (err) { dev_err(card->dev, "usb_set_interface error\n"); return false; } } err = usb_set_interface(us122l->dev, 1, 1); if (err) { dev_err(card->dev, "usb_set_interface error\n"); return false; } pt_info_set(us122l->dev, 0x11); pt_info_set(us122l->dev, 0x10); if (!us122l_start(us122l, 44100, 256)) return false; if (us122l->is_us144) err = us144_create_usbmidi(card); else err = us122l_create_usbmidi(card); if (err < 0) { dev_err(card->dev, "us122l_create_usbmidi error %i\n", err); goto stop; } err = usb_stream_hwdep_new(card); if (err < 0) { /* release the midi resources */ struct list_head *p; list_for_each(p, &us122l->midi_list) snd_usbmidi_disconnect(p); goto stop; } return true; stop: us122l_stop(us122l); return false; } static void snd_us122l_free(struct snd_card *card) { struct us122l *us122l = US122L(card); int index = us122l->card_index; if (index >= 0 && index < SNDRV_CARDS) snd_us122l_card_used[index] = 0; } static int usx2y_create_card(struct usb_device *device, struct usb_interface *intf, struct snd_card **cardp, unsigned long flags) { int dev; struct snd_card *card; int err; for (dev = 0; dev < SNDRV_CARDS; ++dev) if (enable[dev] && !snd_us122l_card_used[dev]) break; if (dev >= SNDRV_CARDS) return -ENODEV; err = snd_card_new(&intf->dev, index[dev], id[dev], THIS_MODULE, sizeof(struct us122l), &card); if (err < 0) return err; snd_us122l_card_used[US122L(card)->card_index = dev] = 1; card->private_free = snd_us122l_free; US122L(card)->dev = device; mutex_init(&US122L(card)->mutex); US122L(card)->sk.dev = device; init_waitqueue_head(&US122L(card)->sk.sleep); US122L(card)->is_us144 = flags & US122L_FLAG_US144; INIT_LIST_HEAD(&US122L(card)->midi_list); strscpy(card->driver, "USB "NAME_ALLCAPS""); sprintf(card->shortname, "TASCAM "NAME_ALLCAPS""); sprintf(card->longname, "%s (%x:%x if %d at %03d/%03d)", card->shortname, le16_to_cpu(device->descriptor.idVendor), le16_to_cpu(device->descriptor.idProduct), 0, US122L(card)->dev->bus->busnum, US122L(card)->dev->devnum ); *cardp = card; return 0; } static int us122l_usb_probe(struct usb_interface *intf, const struct usb_device_id *device_id, struct snd_card **cardp) { struct usb_device *device = interface_to_usbdev(intf); struct snd_card *card; int err; err = usx2y_create_card(device, intf, &card, device_id->driver_info); if (err < 0) return err; if (!us122l_create_card(card)) { snd_card_free(card); return -EINVAL; } err = snd_card_register(card); if (err < 0) { snd_card_free(card); return err; } usb_get_intf(usb_ifnum_to_if(device, 0)); usb_get_dev(device); *cardp = card; return 0; } static int snd_us122l_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *device = interface_to_usbdev(intf); struct snd_card *card; int err; if (id->driver_info & US122L_FLAG_US144 && device->speed == USB_SPEED_HIGH) { dev_err(&device->dev, "disable ehci-hcd to run US-144\n"); return -ENODEV; } if (intf->cur_altsetting->desc.bInterfaceNumber != 1) return 0; err = us122l_usb_probe(usb_get_intf(intf), id, &card); if (err < 0) { usb_put_intf(intf); return err; } usb_set_intfdata(intf, card); return 0; } static void snd_us122l_disconnect(struct usb_interface *intf) { struct snd_card *card; struct us122l *us122l; struct list_head *p; card = usb_get_intfdata(intf); if (!card) return; snd_card_disconnect(card); us122l = US122L(card); scoped_guard(mutex, &us122l->mutex) { us122l_stop(us122l); } /* release the midi resources */ list_for_each(p, &us122l->midi_list) { snd_usbmidi_disconnect(p); } usb_put_intf(usb_ifnum_to_if(us122l->dev, 0)); usb_put_intf(usb_ifnum_to_if(us122l->dev, 1)); usb_put_dev(us122l->dev); snd_card_free_when_closed(card); } static int snd_us122l_suspend(struct usb_interface *intf, pm_message_t message) { struct snd_card *card; struct us122l *us122l; struct list_head *p; card = usb_get_intfdata(intf); if (!card) return 0; snd_power_change_state(card, SNDRV_CTL_POWER_D3hot); us122l = US122L(card); if (!us122l) return 0; list_for_each(p, &us122l->midi_list) snd_usbmidi_input_stop(p); guard(mutex)(&us122l->mutex); usb_stream_stop(&us122l->sk); return 0; } static int snd_us122l_resume(struct usb_interface *intf) { struct snd_card *card; struct us122l *us122l; struct list_head *p; int err; card = usb_get_intfdata(intf); if (!card) return 0; us122l = US122L(card); if (!us122l) return 0; guard(mutex)(&us122l->mutex); /* needed, doesn't restart without: */ if (us122l->is_us144) { err = usb_set_interface(us122l->dev, 0, 1); if (err) { dev_err(&us122l->dev->dev, "usb_set_interface error\n"); goto unlock; } } err = usb_set_interface(us122l->dev, 1, 1); if (err) { dev_err(&us122l->dev->dev, "usb_set_interface error\n"); goto unlock; } pt_info_set(us122l->dev, 0x11); pt_info_set(us122l->dev, 0x10); err = us122l_set_sample_rate(us122l->dev, us122l->sk.s->cfg.sample_rate); if (err < 0) { dev_err(&us122l->dev->dev, "us122l_set_sample_rate error\n"); goto unlock; } err = usb_stream_start(&us122l->sk); if (err) goto unlock; list_for_each(p, &us122l->midi_list) snd_usbmidi_input_start(p); unlock: snd_power_change_state(card, SNDRV_CTL_POWER_D0); return err; } static const struct usb_device_id snd_us122l_usb_id_table[] = { { .match_flags = USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x0644, .idProduct = USB_ID_US122L }, { /* US-144 only works at USB1.1! Disable module ehci-hcd. */ .match_flags = USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x0644, .idProduct = USB_ID_US144, .driver_info = US122L_FLAG_US144 }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x0644, .idProduct = USB_ID_US122MKII }, { /* terminator */ } }; MODULE_DEVICE_TABLE(usb, snd_us122l_usb_id_table); static struct usb_driver snd_us122l_usb_driver = { .name = "snd-usb-us122l", .probe = snd_us122l_probe, .disconnect = snd_us122l_disconnect, .suspend = snd_us122l_suspend, .resume = snd_us122l_resume, .reset_resume = snd_us122l_resume, .id_table = snd_us122l_usb_id_table, .supports_autosuspend = 1 }; module_usb_driver(snd_us122l_usb_driver); |
| 4 24 4 20 13 13 13 13 13 13 13 817 817 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 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PTRACE_H #define _LINUX_PTRACE_H #include <linux/compiler.h> /* For unlikely. */ #include <linux/sched.h> /* For struct task_struct. */ #include <linux/sched/signal.h> /* For send_sig(), same_thread_group(), etc. */ #include <linux/err.h> /* for IS_ERR_VALUE */ #include <linux/bug.h> /* For BUG_ON. */ #include <linux/pid_namespace.h> /* For task_active_pid_ns. */ #include <uapi/linux/ptrace.h> #include <linux/seccomp.h> /* Add sp to seccomp_data, as seccomp is user API, we don't want to modify it */ struct syscall_info { __u64 sp; struct seccomp_data data; }; extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); /* * Ptrace flags * * The owner ship rules for task->ptrace which holds the ptrace * flags is simple. When a task is running it owns it's task->ptrace * flags. When the a task is stopped the ptracer owns task->ptrace. */ #define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */ #define PT_PTRACED 0x00000001 #define PT_OPT_FLAG_SHIFT 3 /* PT_TRACE_* event enable flags */ #define PT_EVENT_FLAG(event) (1 << (PT_OPT_FLAG_SHIFT + (event))) #define PT_TRACESYSGOOD PT_EVENT_FLAG(0) #define PT_TRACE_FORK PT_EVENT_FLAG(PTRACE_EVENT_FORK) #define PT_TRACE_VFORK PT_EVENT_FLAG(PTRACE_EVENT_VFORK) #define PT_TRACE_CLONE PT_EVENT_FLAG(PTRACE_EVENT_CLONE) #define PT_TRACE_EXEC PT_EVENT_FLAG(PTRACE_EVENT_EXEC) #define PT_TRACE_VFORK_DONE PT_EVENT_FLAG(PTRACE_EVENT_VFORK_DONE) #define PT_TRACE_EXIT PT_EVENT_FLAG(PTRACE_EVENT_EXIT) #define PT_TRACE_SECCOMP PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP) #define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT) #define PT_SUSPEND_SECCOMP (PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT) extern long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len); extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len); extern void ptrace_disable(struct task_struct *); extern int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern int ptrace_notify(int exit_code, unsigned long message); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred); extern void __ptrace_unlink(struct task_struct *child); extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 #define PTRACE_MODE_ATTACH 0x02 #define PTRACE_MODE_NOAUDIT 0x04 #define PTRACE_MODE_FSCREDS 0x08 #define PTRACE_MODE_REALCREDS 0x10 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) /** * ptrace_may_access - check whether the caller is permitted to access * a target task. * @task: target task * @mode: selects type of access and caller credentials * * Returns true on success, false on denial. * * One of the flags PTRACE_MODE_FSCREDS and PTRACE_MODE_REALCREDS must * be set in @mode to specify whether the access was requested through * a filesystem syscall (should use effective capabilities and fsuid * of the caller) or through an explicit syscall such as * process_vm_writev or ptrace (and should use the real credentials). */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); static inline int ptrace_reparented(struct task_struct *child) { return !same_thread_group(child->real_parent, child->parent); } static inline void ptrace_unlink(struct task_struct *child) { if (unlikely(child->ptrace)) __ptrace_unlink(child); } int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, unsigned long data); int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data); /** * ptrace_parent - return the task that is tracing the given task * @task: task to consider * * Returns %NULL if no one is tracing @task, or the &struct task_struct * pointer to its tracer. * * Must called under rcu_read_lock(). The pointer returned might be kept * live only by RCU. During exec, this may be called with task_lock() held * on @task, still held from when check_unsafe_exec() was called. */ static inline struct task_struct *ptrace_parent(struct task_struct *task) { if (unlikely(task->ptrace)) return rcu_dereference(task->parent); return NULL; } /** * ptrace_event_enabled - test whether a ptrace event is enabled * @task: ptracee of interest * @event: %PTRACE_EVENT_* to test * * Test whether @event is enabled for ptracee @task. * * Returns %true if @event is enabled, %false otherwise. */ static inline bool ptrace_event_enabled(struct task_struct *task, int event) { return task->ptrace & PT_EVENT_FLAG(event); } /** * ptrace_event - possibly stop for a ptrace event notification * @event: %PTRACE_EVENT_* value to report * @message: value for %PTRACE_GETEVENTMSG to return * * Check whether @event is enabled and, if so, report @event and @message * to the ptrace parent. * * Called without locks. */ static inline void ptrace_event(int event, unsigned long message) { if (unlikely(ptrace_event_enabled(current, event))) { ptrace_notify((event << 8) | SIGTRAP, message); } else if (event == PTRACE_EVENT_EXEC) { /* legacy EXEC report via SIGTRAP */ if ((current->ptrace & (PT_PTRACED|PT_SEIZED)) == PT_PTRACED) send_sig(SIGTRAP, current, 0); } } /** * ptrace_event_pid - possibly stop for a ptrace event notification * @event: %PTRACE_EVENT_* value to report * @pid: process identifier for %PTRACE_GETEVENTMSG to return * * Check whether @event is enabled and, if so, report @event and @pid * to the ptrace parent. @pid is reported as the pid_t seen from the * ptrace parent's pid namespace. * * Called without locks. */ static inline void ptrace_event_pid(int event, struct pid *pid) { /* * FIXME: There's a potential race if a ptracer in a different pid * namespace than parent attaches between computing message below and * when we acquire tasklist_lock in ptrace_stop(). If this happens, * the ptracer will get a bogus pid from PTRACE_GETEVENTMSG. */ unsigned long message = 0; struct pid_namespace *ns; rcu_read_lock(); ns = task_active_pid_ns(rcu_dereference(current->parent)); if (ns) message = pid_nr_ns(pid, ns); rcu_read_unlock(); ptrace_event(event, message); } /** * ptrace_init_task - initialize ptrace state for a new child * @child: new child task * @ptrace: true if child should be ptrace'd by parent's tracer * * This is called immediately after adding @child to its parent's children * list. @ptrace is false in the normal case, and true to ptrace @child. * * Called with current's siglock and write_lock_irq(&tasklist_lock) held. */ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) { INIT_LIST_HEAD(&child->ptrace_entry); INIT_LIST_HEAD(&child->ptraced); child->jobctl = 0; child->ptrace = 0; child->parent = child->real_parent; if (unlikely(ptrace) && current->ptrace) { child->ptrace = current->ptrace; __ptrace_link(child, current->parent, current->ptracer_cred); if (child->ptrace & PT_SEIZED) task_set_jobctl_pending(child, JOBCTL_TRAP_STOP); else sigaddset(&child->pending.signal, SIGSTOP); } else child->ptracer_cred = NULL; } /** * ptrace_release_task - final ptrace-related cleanup of a zombie being reaped * @task: task in %EXIT_DEAD state * * Called with write_lock(&tasklist_lock) held. */ static inline void ptrace_release_task(struct task_struct *task) { BUG_ON(!list_empty(&task->ptraced)); ptrace_unlink(task); BUG_ON(!list_empty(&task->ptrace_entry)); } #ifndef force_successful_syscall_return /* * System call handlers that, upon successful completion, need to return a * negative value should call force_successful_syscall_return() right before * returning. On architectures where the syscall convention provides for a * separate error flag (e.g., alpha, ia64, ppc{,64}, sparc{,64}, possibly * others), this macro can be used to ensure that the error flag will not get * set. On architectures which do not support a separate error flag, the macro * is a no-op and the spurious error condition needs to be filtered out by some * other means (e.g., in user-level, by passing an extra argument to the * syscall handler, or something along those lines). */ #define force_successful_syscall_return() do { } while (0) #endif #ifndef is_syscall_success /* * On most systems we can tell if a syscall is a success based on if the retval * is an error value. On some systems like ia64 and powerpc they have different * indicators of success/failure and must define their own. */ #define is_syscall_success(regs) (!IS_ERR_VALUE((unsigned long)(regs_return_value(regs)))) #endif /* * <asm/ptrace.h> should define the following things inside #ifdef __KERNEL__. * * These do-nothing inlines are used when the arch does not * implement single-step. The kerneldoc comments are here * to document the interface for all arch definitions. */ #ifndef arch_has_single_step /** * arch_has_single_step - does this CPU support user-mode single-step? * * If this is defined, then there must be function declarations or * inlines for user_enable_single_step() and user_disable_single_step(). * arch_has_single_step() should evaluate to nonzero iff the machine * supports instruction single-step for user mode. * It can be a constant or it can test a CPU feature bit. */ #define arch_has_single_step() (0) /** * user_enable_single_step - single-step in user-mode task * @task: either current or a task stopped in %TASK_TRACED * * This can only be called when arch_has_single_step() has returned nonzero. * Set @task so that when it returns to user mode, it will trap after the * next single instruction executes. If arch_has_block_step() is defined, * this must clear the effects of user_enable_block_step() too. */ static inline void user_enable_single_step(struct task_struct *task) { BUG(); /* This can never be called. */ } /** * user_disable_single_step - cancel user-mode single-step * @task: either current or a task stopped in %TASK_TRACED * * Clear @task of the effects of user_enable_single_step() and * user_enable_block_step(). This can be called whether or not either * of those was ever called on @task, and even if arch_has_single_step() * returned zero. */ static inline void user_disable_single_step(struct task_struct *task) { } #else extern void user_enable_single_step(struct task_struct *); extern void user_disable_single_step(struct task_struct *); #endif /* arch_has_single_step */ #ifndef arch_has_block_step /** * arch_has_block_step - does this CPU support user-mode block-step? * * If this is defined, then there must be a function declaration or inline * for user_enable_block_step(), and arch_has_single_step() must be defined * too. arch_has_block_step() should evaluate to nonzero iff the machine * supports step-until-branch for user mode. It can be a constant or it * can test a CPU feature bit. */ #define arch_has_block_step() (0) /** * user_enable_block_step - step until branch in user-mode task * @task: either current or a task stopped in %TASK_TRACED * * This can only be called when arch_has_block_step() has returned nonzero, * and will never be called when single-instruction stepping is being used. * Set @task so that when it returns to user mode, it will trap after the * next branch or trap taken. */ static inline void user_enable_block_step(struct task_struct *task) { BUG(); /* This can never be called. */ } #else extern void user_enable_block_step(struct task_struct *); #endif /* arch_has_block_step */ #ifdef ARCH_HAS_USER_SINGLE_STEP_REPORT extern void user_single_step_report(struct pt_regs *regs); #else static inline void user_single_step_report(struct pt_regs *regs) { kernel_siginfo_t info; clear_siginfo(&info); info.si_signo = SIGTRAP; info.si_errno = 0; info.si_code = SI_USER; info.si_pid = 0; info.si_uid = 0; force_sig_info(&info); } #endif #ifndef arch_ptrace_stop_needed /** * arch_ptrace_stop_needed - Decide whether arch_ptrace_stop() should be called * * This is called with the siglock held, to decide whether or not it's * necessary to release the siglock and call arch_ptrace_stop(). It can be * defined to a constant if arch_ptrace_stop() is never required, or always * is. On machines where this makes sense, it should be defined to a quick * test to optimize out calling arch_ptrace_stop() when it would be * superfluous. For example, if the thread has not been back to user mode * since the last stop, the thread state might indicate that nothing needs * to be done. * * This is guaranteed to be invoked once before a task stops for ptrace and * may include arch-specific operations necessary prior to a ptrace stop. */ #define arch_ptrace_stop_needed() (0) #endif #ifndef arch_ptrace_stop /** * arch_ptrace_stop - Do machine-specific work before stopping for ptrace * * This is called with no locks held when arch_ptrace_stop_needed() has * just returned nonzero. It is allowed to block, e.g. for user memory * access. The arch can have machine-specific work to be done before * ptrace stops. On ia64, register backing store gets written back to user * memory here. Since this can be costly (requires dropping the siglock), * we only do it when the arch requires it for this particular stop, as * indicated by arch_ptrace_stop_needed(). */ #define arch_ptrace_stop() do { } while (0) #endif #ifndef current_pt_regs #define current_pt_regs() task_pt_regs(current) #endif #ifndef current_user_stack_pointer #define current_user_stack_pointer() user_stack_pointer(current_pt_regs()) #endif #ifndef exception_ip #define exception_ip(x) instruction_pointer(x) #endif extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); /* * ptrace report for syscall entry and exit looks identical. */ static inline int ptrace_report_syscall(unsigned long message) { int ptrace = current->ptrace; int signr; if (!(ptrace & PT_PTRACED)) return 0; signr = ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0), message); /* * this isn't the same as continuing with a signal, but it will do * for normal use. strace only continues with a signal if the * stopping signal is not SIGTRAP. -brl */ if (signr) send_sig(signr, current, 1); return fatal_signal_pending(current); } /** * ptrace_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or * %SYSCALL_WORK_SYSCALL_EMU have been set, when the current task has just * entered the kernel for a system call. Full user register state is * available here. Changing the values in @regs can affect the system * call number and arguments to be tried. It is safe to block here, * preventing the system call from beginning. * * Returns zero normally, or nonzero if the calling arch code should abort * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error * return. It should preserve enough information so that syscall_rollback() * can work (see asm-generic/syscall.h). * * Called without locks, just after entering kernel mode. */ static inline __must_check int ptrace_report_syscall_entry( struct pt_regs *regs) { return ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_ENTRY); } /** * ptrace_report_syscall_exit - task has just finished a system call * @regs: user register state of current task * @step: nonzero if simulating single-step or block-step * * This will be called if %SYSCALL_WORK_SYSCALL_TRACE has been set, when * the current task has just finished an attempted system call. Full * user register state is available here. It is safe to block here, * preventing signals from being processed. * * If @step is nonzero, this report is also in lieu of the normal * trap that would follow the system call instruction because * user_enable_block_step() or user_enable_single_step() was used. * In this case, %SYSCALL_WORK_SYSCALL_TRACE might not be set. * * Called without locks, just before checking for pending signals. */ static inline void ptrace_report_syscall_exit(struct pt_regs *regs, int step) { if (step) user_single_step_report(regs); else ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_EXIT); } #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0 #ifndef _MEDIA_FRAME_VECTOR_H #define _MEDIA_FRAME_VECTOR_H /* Container for pinned pfns / pages in frame_vector.c */ struct frame_vector { unsigned int nr_allocated; /* Number of frames we have space for */ unsigned int nr_frames; /* Number of frames stored in ptrs array */ bool got_ref; /* Did we pin pages by getting page ref? */ bool is_pfns; /* Does array contain pages or pfns? */ void *ptrs[]; /* Array of pinned pfns / pages. Use * pfns_vector_pages() or pfns_vector_pfns() * for access */ }; struct frame_vector *frame_vector_create(unsigned int nr_frames); void frame_vector_destroy(struct frame_vector *vec); int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, bool write, struct frame_vector *vec); void put_vaddr_frames(struct frame_vector *vec); int frame_vector_to_pages(struct frame_vector *vec); void frame_vector_to_pfns(struct frame_vector *vec); static inline unsigned int frame_vector_count(struct frame_vector *vec) { return vec->nr_frames; } static inline struct page **frame_vector_pages(struct frame_vector *vec) { if (vec->is_pfns) { int err = frame_vector_to_pages(vec); if (err) return ERR_PTR(err); } return (struct page **)(vec->ptrs); } static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) { if (!vec->is_pfns) frame_vector_to_pfns(vec); return (unsigned long *)(vec->ptrs); } #endif /* _MEDIA_FRAME_VECTOR_H */ |
| 3 3 1 3 3 3 3 3 3 1 3 2 3 3 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_skbprio.c SKB Priority Queue. * * Authors: Nishanth Devarajan, <ndev2021@gmail.com> * Cody Doucette, <doucette@bu.edu> * original idea by Michel Machado, Cody Doucette, and Qiaobin Fu */ #include <linux/string.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> #include <net/sch_generic.h> #include <net/inet_ecn.h> /* SKB Priority Queue * ================================= * * Skbprio (SKB Priority Queue) is a queueing discipline that prioritizes * packets according to their skb->priority field. Under congestion, * Skbprio drops already-enqueued lower priority packets to make space * available for higher priority packets; it was conceived as a solution * for denial-of-service defenses that need to route packets with different * priorities as a mean to overcome DoS attacks. */ struct skbprio_sched_data { /* Queue state. */ struct sk_buff_head qdiscs[SKBPRIO_MAX_PRIORITY]; struct gnet_stats_queue qstats[SKBPRIO_MAX_PRIORITY]; u16 highest_prio; u16 lowest_prio; }; static u16 calc_new_high_prio(const struct skbprio_sched_data *q) { int prio; for (prio = q->highest_prio - 1; prio >= q->lowest_prio; prio--) { if (!skb_queue_empty(&q->qdiscs[prio])) return prio; } /* SKB queue is empty, return 0 (default highest priority setting). */ return 0; } static u16 calc_new_low_prio(const struct skbprio_sched_data *q) { int prio; for (prio = q->lowest_prio + 1; prio <= q->highest_prio; prio++) { if (!skb_queue_empty(&q->qdiscs[prio])) return prio; } /* SKB queue is empty, return SKBPRIO_MAX_PRIORITY - 1 * (default lowest priority setting). */ return SKBPRIO_MAX_PRIORITY - 1; } static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { const unsigned int max_priority = SKBPRIO_MAX_PRIORITY - 1; struct skbprio_sched_data *q = qdisc_priv(sch); struct sk_buff_head *qdisc; struct sk_buff_head *lp_qdisc; struct sk_buff *to_drop; u16 prio, lp; /* Obtain the priority of @skb. */ prio = min(skb->priority, max_priority); qdisc = &q->qdiscs[prio]; /* sch->limit can change under us from skbprio_change() */ if (sch->q.qlen < READ_ONCE(sch->limit)) { __skb_queue_tail(qdisc, skb); qdisc_qstats_backlog_inc(sch, skb); q->qstats[prio].backlog += qdisc_pkt_len(skb); /* Check to update highest and lowest priorities. */ if (prio > q->highest_prio) q->highest_prio = prio; if (prio < q->lowest_prio) q->lowest_prio = prio; sch->q.qlen++; return NET_XMIT_SUCCESS; } /* If this packet has the lowest priority, drop it. */ lp = q->lowest_prio; if (prio <= lp) { q->qstats[prio].drops++; q->qstats[prio].overlimits++; return qdisc_drop(skb, sch, to_free); } __skb_queue_tail(qdisc, skb); qdisc_qstats_backlog_inc(sch, skb); q->qstats[prio].backlog += qdisc_pkt_len(skb); /* Drop the packet at the tail of the lowest priority qdisc. */ lp_qdisc = &q->qdiscs[lp]; to_drop = __skb_dequeue_tail(lp_qdisc); BUG_ON(!to_drop); qdisc_qstats_backlog_dec(sch, to_drop); qdisc_drop(to_drop, sch, to_free); q->qstats[lp].backlog -= qdisc_pkt_len(to_drop); q->qstats[lp].drops++; q->qstats[lp].overlimits++; /* Check to update highest and lowest priorities. */ if (skb_queue_empty(lp_qdisc)) { if (q->lowest_prio == q->highest_prio) { q->lowest_prio = prio; q->highest_prio = prio; } else { q->lowest_prio = calc_new_low_prio(q); } } if (prio > q->highest_prio) q->highest_prio = prio; return NET_XMIT_CN; } static struct sk_buff *skbprio_dequeue(struct Qdisc *sch) { struct skbprio_sched_data *q = qdisc_priv(sch); struct sk_buff_head *hpq = &q->qdiscs[q->highest_prio]; struct sk_buff *skb = __skb_dequeue(hpq); if (unlikely(!skb)) return NULL; sch->q.qlen--; qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); q->qstats[q->highest_prio].backlog -= qdisc_pkt_len(skb); /* Update highest priority field. */ if (skb_queue_empty(hpq)) { if (q->lowest_prio == q->highest_prio) { q->highest_prio = 0; q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; } else { q->highest_prio = calc_new_high_prio(q); } } return skb; } static int skbprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct tc_skbprio_qopt *ctl = nla_data(opt); if (opt->nla_len != nla_attr_size(sizeof(*ctl))) return -EINVAL; WRITE_ONCE(sch->limit, ctl->limit); return 0; } static int skbprio_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct skbprio_sched_data *q = qdisc_priv(sch); int prio; /* Initialise all queues, one for each possible priority. */ for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) __skb_queue_head_init(&q->qdiscs[prio]); memset(&q->qstats, 0, sizeof(q->qstats)); q->highest_prio = 0; q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; sch->limit = 64; if (!opt) return 0; return skbprio_change(sch, opt, extack); } static int skbprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct tc_skbprio_qopt opt; opt.limit = READ_ONCE(sch->limit); if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) return -1; return skb->len; } static void skbprio_reset(struct Qdisc *sch) { struct skbprio_sched_data *q = qdisc_priv(sch); int prio; for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) __skb_queue_purge(&q->qdiscs[prio]); memset(&q->qstats, 0, sizeof(q->qstats)); q->highest_prio = 0; q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; } static void skbprio_destroy(struct Qdisc *sch) { struct skbprio_sched_data *q = qdisc_priv(sch); int prio; for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) __skb_queue_purge(&q->qdiscs[prio]); } static struct Qdisc *skbprio_leaf(struct Qdisc *sch, unsigned long arg) { return NULL; } static unsigned long skbprio_find(struct Qdisc *sch, u32 classid) { return 0; } static int skbprio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { tcm->tcm_handle |= TC_H_MIN(cl); return 0; } static int skbprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) { struct skbprio_sched_data *q = qdisc_priv(sch); if (gnet_stats_copy_queue(d, NULL, &q->qstats[cl - 1], q->qstats[cl - 1].qlen) < 0) return -1; return 0; } static void skbprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) { unsigned int i; if (arg->stop) return; for (i = 0; i < SKBPRIO_MAX_PRIORITY; i++) { if (!tc_qdisc_stats_dump(sch, i + 1, arg)) break; } } static const struct Qdisc_class_ops skbprio_class_ops = { .leaf = skbprio_leaf, .find = skbprio_find, .dump = skbprio_dump_class, .dump_stats = skbprio_dump_class_stats, .walk = skbprio_walk, }; static struct Qdisc_ops skbprio_qdisc_ops __read_mostly = { .cl_ops = &skbprio_class_ops, .id = "skbprio", .priv_size = sizeof(struct skbprio_sched_data), .enqueue = skbprio_enqueue, .dequeue = skbprio_dequeue, .peek = qdisc_peek_dequeued, .init = skbprio_init, .reset = skbprio_reset, .change = skbprio_change, .dump = skbprio_dump, .destroy = skbprio_destroy, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("skbprio"); static int __init skbprio_module_init(void) { return register_qdisc(&skbprio_qdisc_ops); } static void __exit skbprio_module_exit(void) { unregister_qdisc(&skbprio_qdisc_ops); } module_init(skbprio_module_init) module_exit(skbprio_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SKB priority based scheduling qdisc"); |
| 1144 1150 1149 1145 873 676 1149 1150 1151 3 1146 1151 1147 794 866 197 16 1145 1151 12 1147 15 1663 1151 94 628 15 644 7 6 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs * * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes * 2000-2002 x86-64 support by Andi Kleen */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/smp.h> #include <linux/kernel.h> #include <linux/kstrtox.h> #include <linux/errno.h> #include <linux/wait.h> #include <linux/unistd.h> #include <linux/stddef.h> #include <linux/personality.h> #include <linux/uaccess.h> #include <linux/user-return-notifier.h> #include <linux/uprobes.h> #include <linux/context_tracking.h> #include <linux/entry-common.h> #include <linux/syscalls.h> #include <linux/rseq.h> #include <asm/processor.h> #include <asm/ucontext.h> #include <asm/fpu/signal.h> #include <asm/fpu/xstate.h> #include <asm/vdso.h> #include <asm/mce.h> #include <asm/sighandling.h> #include <asm/vm86.h> #include <asm/syscall.h> #include <asm/sigframe.h> #include <asm/signal.h> #include <asm/shstk.h> static inline int is_ia32_compat_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_IA32_EMULATION) && ksig->ka.sa.sa_flags & SA_IA32_ABI; } static inline int is_ia32_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig); } static inline int is_x32_frame(struct ksignal *ksig) { return IS_ENABLED(CONFIG_X86_X32_ABI) && ksig->ka.sa.sa_flags & SA_X32_ABI; } /* * Enable all pkeys temporarily, so as to ensure that both the current * execution stack as well as the alternate signal stack are writeable. * The application can use any of the available pkeys to protect the * alternate signal stack, and we don't know which one it is, so enable * all. The PKRU register will be reset to init_pkru later in the flow, * in fpu__clear_user_states(), and it is the application's responsibility * to enable the appropriate pkey as the first step in the signal handler * so that the handler does not segfault. */ static inline u32 sig_prepare_pkru(void) { u32 orig_pkru = read_pkru(); write_pkru(0); return orig_pkru; } /* * Set up a signal frame. */ /* x86 ABI requires 16-byte alignment */ #define FRAME_ALIGNMENT 16UL #define MAX_FRAME_PADDING (FRAME_ALIGNMENT - 1) /* * Determine which stack to use.. */ void __user * get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { struct k_sigaction *ka = &ksig->ka; int ia32_frame = is_ia32_frame(ksig); /* Default to using normal stack */ bool nested_altstack = on_sig_stack(regs->sp); bool entering_altstack = false; unsigned long math_size = 0; unsigned long sp = regs->sp; unsigned long buf_fx = 0; u32 pkru; /* redzone */ if (!ia32_frame) sp -= 128; /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { /* * This checks nested_altstack via sas_ss_flags(). Sensible * programs use SS_AUTODISARM, which disables that check, and * programs that don't use SS_AUTODISARM get compatible. */ if (sas_ss_flags(sp) == 0) { sp = current->sas_ss_sp + current->sas_ss_size; entering_altstack = true; } } else if (ia32_frame && !nested_altstack && regs->ss != __USER_DS && !(ka->sa.sa_flags & SA_RESTORER) && ka->sa.sa_restorer) { /* This is the legacy signal stack switching. */ sp = (unsigned long) ka->sa.sa_restorer; entering_altstack = true; } sp = fpu__alloc_mathframe(sp, ia32_frame, &buf_fx, &math_size); *fpstate = (void __user *)sp; sp -= frame_size; if (ia32_frame) /* * Align the stack pointer according to the i386 ABI, * i.e. so that on function entry ((sp + 4) & 15) == 0. */ sp = ((sp + 4) & -FRAME_ALIGNMENT) - 4; else sp = round_down(sp, FRAME_ALIGNMENT) - 8; /* * If we are on the alternate signal stack and would overflow it, don't. * Return an always-bogus address instead so we will die with SIGSEGV. */ if (unlikely((nested_altstack || entering_altstack) && !__on_sig_stack(sp))) { if (show_unhandled_signals && printk_ratelimit()) pr_info("%s[%d] overflowed sigaltstack\n", current->comm, task_pid_nr(current)); return (void __user *)-1L; } /* Update PKRU to enable access to the alternate signal stack. */ pkru = sig_prepare_pkru(); /* save i387 and extended state */ if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size, pkru)) { /* * Restore PKRU to the original, user-defined value; disable * extra pkeys enabled for the alternate signal stack, if any. */ write_pkru(pkru); return (void __user *)-1L; } return (void __user *)sp; } /* * There are four different struct types for signal frame: sigframe_ia32, * rt_sigframe_ia32, rt_sigframe_x32, and rt_sigframe. Use the worst case * -- the largest size. It means the size for 64-bit apps is a bit more * than needed, but this keeps the code simple. */ #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) # define MAX_FRAME_SIGINFO_UCTXT_SIZE sizeof(struct sigframe_ia32) #else # define MAX_FRAME_SIGINFO_UCTXT_SIZE sizeof(struct rt_sigframe) #endif /* * The FP state frame contains an XSAVE buffer which must be 64-byte aligned. * If a signal frame starts at an unaligned address, extra space is required. * This is the max alignment padding, conservatively. */ #define MAX_XSAVE_PADDING 63UL /* * The frame data is composed of the following areas and laid out as: * * ------------------------- * | alignment padding | * ------------------------- * | (f)xsave frame | * ------------------------- * | fsave header | * ------------------------- * | alignment padding | * ------------------------- * | siginfo + ucontext | * ------------------------- */ /* max_frame_size tells userspace the worst case signal stack size. */ static unsigned long __ro_after_init max_frame_size; static unsigned int __ro_after_init fpu_default_state_size; static int __init init_sigframe_size(void) { fpu_default_state_size = fpu__get_fpstate_size(); max_frame_size = MAX_FRAME_SIGINFO_UCTXT_SIZE + MAX_FRAME_PADDING; max_frame_size += fpu_default_state_size + MAX_XSAVE_PADDING; /* Userspace expects an aligned size. */ max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT); pr_info("max sigframe size: %lu\n", max_frame_size); return 0; } early_initcall(init_sigframe_size); unsigned long get_sigframe_size(void) { return max_frame_size; } static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { /* Perform fixup for the pre-signal frame. */ rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ if (is_ia32_frame(ksig)) { if (ksig->ka.sa.sa_flags & SA_SIGINFO) return ia32_setup_rt_frame(ksig, regs); else return ia32_setup_frame(ksig, regs); } else if (is_x32_frame(ksig)) { return x32_setup_rt_frame(ksig, regs); } else { return x64_setup_rt_frame(ksig, regs); } } static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { bool stepping, failed; struct fpu *fpu = x86_task_fpu(current); if (v8086_mode(regs)) save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL); /* Are we from a system call? */ if (syscall_get_nr(current, regs) != -1) { /* If so, check system call restarting.. */ switch (syscall_get_error(current, regs)) { case -ERESTART_RESTARTBLOCK: case -ERESTARTNOHAND: regs->ax = -EINTR; break; case -ERESTARTSYS: if (!(ksig->ka.sa.sa_flags & SA_RESTART)) { regs->ax = -EINTR; break; } fallthrough; case -ERESTARTNOINTR: regs->ax = regs->orig_ax; regs->ip -= 2; break; } } /* * If TF is set due to a debugger (TIF_FORCED_TF), clear TF now * so that register information in the sigcontext is correct and * then notify the tracer before entering the signal handler. */ stepping = test_thread_flag(TIF_SINGLESTEP); if (stepping) user_disable_single_step(current); failed = (setup_rt_frame(ksig, regs) < 0); if (!failed) { /* * Clear the direction flag as per the ABI for function entry. * * Clear RF when entering the signal handler, because * it might disable possible debug exception from the * signal handler. * * Clear TF for the case when it wasn't set by debugger to * avoid the recursive send_sigtrap() in SIGTRAP handler. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); /* * Ensure the signal handler starts with the new fpu state. */ fpu__clear_user_states(fpu); } signal_setup_done(failed, ksig, stepping); } static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) { #ifdef CONFIG_IA32_EMULATION if (current->restart_block.arch_data & TS_COMPAT) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI return __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT); #else return __NR_restart_syscall; #endif } /* * Note that 'init' is a special process: it doesn't get signals it doesn't * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ void arch_do_signal_or_restart(struct pt_regs *regs) { struct ksignal ksig; if (get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); return; } /* Did we come from a system call? */ if (syscall_get_nr(current, regs) != -1) { /* Restart the system call - no handlers present */ switch (syscall_get_error(current, regs)) { case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: regs->ax = regs->orig_ax; regs->ip -= 2; break; case -ERESTART_RESTARTBLOCK: regs->ax = get_nr_restart_syscall(regs); regs->ip -= 2; break; } } /* * If there's no signal to deliver, we just put the saved sigmask * back. */ restore_saved_sigmask(); } void signal_fault(struct pt_regs *regs, void __user *frame, char *where) { struct task_struct *me = current; if (show_unhandled_signals && printk_ratelimit()) { printk("%s" "%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx", task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG, me->comm, me->pid, where, frame, regs->ip, regs->sp, regs->orig_ax); print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } force_sig(SIGSEGV); } #ifdef CONFIG_DYNAMIC_SIGFRAME #ifdef CONFIG_STRICT_SIGALTSTACK_SIZE static bool strict_sigaltstack_size __ro_after_init = true; #else static bool strict_sigaltstack_size __ro_after_init = false; #endif static int __init strict_sas_size(char *arg) { return kstrtobool(arg, &strict_sigaltstack_size) == 0; } __setup("strict_sas_size", strict_sas_size); /* * MINSIGSTKSZ is 2048 and can't be changed despite the fact that AVX512 * exceeds that size already. As such programs might never use the * sigaltstack they just continued to work. While always checking against * the real size would be correct, this might be considered a regression. * * Therefore avoid the sanity check, unless enforced by kernel * configuration or command line option. * * When dynamic FPU features are supported, the check is also enforced when * the task has permissions to use dynamic features. Tasks which have no * permission are checked against the size of the non-dynamic feature set * if strict checking is enabled. This avoids forcing all tasks on the * system to allocate large sigaltstacks even if they are never going * to use a dynamic feature. As this is serialized via sighand::siglock * any permission request for a dynamic feature either happened already * or will see the newly install sigaltstack size in the permission checks. */ bool sigaltstack_size_valid(size_t ss_size) { unsigned long fsize = max_frame_size - fpu_default_state_size; u64 mask; lockdep_assert_held(¤t->sighand->siglock); if (!fpu_state_size_dynamic() && !strict_sigaltstack_size) return true; fsize += x86_task_fpu(current->group_leader)->perm.__user_state_size; if (likely(ss_size > fsize)) return true; if (strict_sigaltstack_size) return ss_size > fsize; mask = x86_task_fpu(current->group_leader)->perm.__state_perm; if (mask & XFEATURE_MASK_USER_DYNAMIC) return ss_size > fsize; return true; } #endif /* CONFIG_DYNAMIC_SIGFRAME */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Public Key Signature Algorithm * * Copyright (c) 2023 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_SIG_H #define _CRYPTO_INTERNAL_SIG_H #include <crypto/algapi.h> #include <crypto/sig.h> struct sig_instance { void (*free)(struct sig_instance *inst); union { struct { char head[offsetof(struct sig_alg, base)]; struct crypto_instance base; }; struct sig_alg alg; }; }; struct crypto_sig_spawn { struct crypto_spawn base; }; static inline void *crypto_sig_ctx(struct crypto_sig *tfm) { return crypto_tfm_ctx(&tfm->base); } /** * crypto_register_sig() -- Register public key signature algorithm * * Function registers an implementation of a public key signature algorithm * * @alg: algorithm definition * * Return: zero on success; error code in case of error */ int crypto_register_sig(struct sig_alg *alg); /** * crypto_unregister_sig() -- Unregister public key signature algorithm * * Function unregisters an implementation of a public key signature algorithm * * @alg: algorithm definition */ void crypto_unregister_sig(struct sig_alg *alg); int sig_register_instance(struct crypto_template *tmpl, struct sig_instance *inst); static inline struct sig_instance *sig_instance(struct crypto_instance *inst) { return container_of(&inst->alg, struct sig_instance, alg.base); } static inline struct sig_instance *sig_alg_instance(struct crypto_sig *tfm) { return sig_instance(crypto_tfm_alg_instance(&tfm->base)); } static inline struct crypto_instance *sig_crypto_instance(struct sig_instance *inst) { return container_of(&inst->alg.base, struct crypto_instance, alg); } static inline void *sig_instance_ctx(struct sig_instance *inst) { return crypto_instance_ctx(sig_crypto_instance(inst)); } int crypto_grab_sig(struct crypto_sig_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline struct crypto_sig *crypto_spawn_sig(struct crypto_sig_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline void crypto_drop_sig(struct crypto_sig_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct sig_alg *crypto_spawn_sig_alg(struct crypto_sig_spawn *spawn) { return container_of(spawn->base.alg, struct sig_alg, base); } #endif |
| 23 113 71 71 72 73 73 73 72 72 101 72 72 72 58 58 58 16 58 58 58 53 6 98 71 72 70 15 15 72 72 52 52 5 49 49 52 8 8 8 8 71 72 72 72 71 70 15 72 72 72 70 71 72 72 72 72 72 72 72 72 71 52 51 52 52 52 52 47 47 39 17 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * zswap.c - zswap driver file * * zswap is a cache that takes pages that are in the process * of being swapped out and attempts to compress and store them in a * RAM-based memory pool. This can result in a significant I/O reduction on * the swap device and, in the case where decompressing from RAM is faster * than reading from the swap device, can also improve workload performance. * * Copyright (C) 2012 Seth Jennings <sjenning@linux.vnet.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/cpu.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/swap.h> #include <linux/crypto.h> #include <linux/scatterlist.h> #include <linux/mempolicy.h> #include <linux/mempool.h> #include <crypto/acompress.h> #include <linux/zswap.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/swapops.h> #include <linux/writeback.h> #include <linux/pagemap.h> #include <linux/workqueue.h> #include <linux/list_lru.h> #include <linux/zsmalloc.h> #include "swap.h" #include "internal.h" /********************************* * statistics **********************************/ /* The number of pages currently stored in zswap */ atomic_long_t zswap_stored_pages = ATOMIC_LONG_INIT(0); /* The number of incompressible pages currently stored in zswap */ static atomic_long_t zswap_stored_incompressible_pages = ATOMIC_LONG_INIT(0); /* * The statistics below are not protected from concurrent access for * performance reasons so they may not be a 100% accurate. However, * they do provide useful information on roughly how many times a * certain event is occurring. */ /* Pool limit was hit (see zswap_max_pool_percent) */ static u64 zswap_pool_limit_hit; /* Pages written back when pool limit was reached */ static u64 zswap_written_back_pages; /* Store failed due to a reclaim failure after pool limit was reached */ static u64 zswap_reject_reclaim_fail; /* Store failed due to compression algorithm failure */ static u64 zswap_reject_compress_fail; /* Compressed page was too big for the allocator to (optimally) store */ static u64 zswap_reject_compress_poor; /* Load or writeback failed due to decompression failure */ static u64 zswap_decompress_fail; /* Store failed because underlying allocator could not get memory */ static u64 zswap_reject_alloc_fail; /* Store failed because the entry metadata could not be allocated (rare) */ static u64 zswap_reject_kmemcache_fail; /* Shrinker work queue */ static struct workqueue_struct *shrink_wq; /* Pool limit was hit, we need to calm down */ static bool zswap_pool_reached_full; /********************************* * tunables **********************************/ #define ZSWAP_PARAM_UNSET "" static int zswap_setup(void); /* Enable/disable zswap */ static DEFINE_STATIC_KEY_MAYBE(CONFIG_ZSWAP_DEFAULT_ON, zswap_ever_enabled); static bool zswap_enabled = IS_ENABLED(CONFIG_ZSWAP_DEFAULT_ON); static int zswap_enabled_param_set(const char *, const struct kernel_param *); static const struct kernel_param_ops zswap_enabled_param_ops = { .set = zswap_enabled_param_set, .get = param_get_bool, }; module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644); /* Crypto compressor to use */ static char *zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT; static int zswap_compressor_param_set(const char *, const struct kernel_param *); static const struct kernel_param_ops zswap_compressor_param_ops = { .set = zswap_compressor_param_set, .get = param_get_charp, .free = param_free_charp, }; module_param_cb(compressor, &zswap_compressor_param_ops, &zswap_compressor, 0644); /* The maximum percentage of memory that the compressed pool can occupy */ static unsigned int zswap_max_pool_percent = 20; module_param_named(max_pool_percent, zswap_max_pool_percent, uint, 0644); /* The threshold for accepting new pages after the max_pool_percent was hit */ static unsigned int zswap_accept_thr_percent = 90; /* of max pool size */ module_param_named(accept_threshold_percent, zswap_accept_thr_percent, uint, 0644); /* Enable/disable memory pressure-based shrinker. */ static bool zswap_shrinker_enabled = IS_ENABLED( CONFIG_ZSWAP_SHRINKER_DEFAULT_ON); module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644); bool zswap_is_enabled(void) { return zswap_enabled; } bool zswap_never_enabled(void) { return !static_branch_maybe(CONFIG_ZSWAP_DEFAULT_ON, &zswap_ever_enabled); } /********************************* * data structures **********************************/ struct crypto_acomp_ctx { struct crypto_acomp *acomp; struct acomp_req *req; struct crypto_wait wait; u8 *buffer; struct mutex mutex; bool is_sleepable; }; /* * The lock ordering is zswap_tree.lock -> zswap_pool.lru_lock. * The only case where lru_lock is not acquired while holding tree.lock is * when a zswap_entry is taken off the lru for writeback, in that case it * needs to be verified that it's still valid in the tree. */ struct zswap_pool { struct zs_pool *zs_pool; struct crypto_acomp_ctx __percpu *acomp_ctx; struct percpu_ref ref; struct list_head list; struct work_struct release_work; struct hlist_node node; char tfm_name[CRYPTO_MAX_ALG_NAME]; }; /* Global LRU lists shared by all zswap pools. */ static struct list_lru zswap_list_lru; /* The lock protects zswap_next_shrink updates. */ static DEFINE_SPINLOCK(zswap_shrink_lock); static struct mem_cgroup *zswap_next_shrink; static struct work_struct zswap_shrink_work; static struct shrinker *zswap_shrinker; /* * struct zswap_entry * * This structure contains the metadata for tracking a single compressed * page within zswap. * * swpentry - associated swap entry, the offset indexes into the red-black tree * length - the length in bytes of the compressed page data. Needed during * decompression. * referenced - true if the entry recently entered the zswap pool. Unset by the * writeback logic. The entry is only reclaimed by the writeback * logic if referenced is unset. See comments in the shrinker * section for context. * pool - the zswap_pool the entry's data is in * handle - zsmalloc allocation handle that stores the compressed page data * objcg - the obj_cgroup that the compressed memory is charged to * lru - handle to the pool's lru used to evict pages. */ struct zswap_entry { swp_entry_t swpentry; unsigned int length; bool referenced; struct zswap_pool *pool; unsigned long handle; struct obj_cgroup *objcg; struct list_head lru; }; static struct xarray *zswap_trees[MAX_SWAPFILES]; static unsigned int nr_zswap_trees[MAX_SWAPFILES]; /* RCU-protected iteration */ static LIST_HEAD(zswap_pools); /* protects zswap_pools list modification */ static DEFINE_SPINLOCK(zswap_pools_lock); /* pool counter to provide unique names to zsmalloc */ static atomic_t zswap_pools_count = ATOMIC_INIT(0); enum zswap_init_type { ZSWAP_UNINIT, ZSWAP_INIT_SUCCEED, ZSWAP_INIT_FAILED }; static enum zswap_init_type zswap_init_state; /* used to ensure the integrity of initialization */ static DEFINE_MUTEX(zswap_init_lock); /* init completed, but couldn't create the initial pool */ static bool zswap_has_pool; /********************************* * helpers and fwd declarations **********************************/ /* One swap address space for each 64M swap space */ #define ZSWAP_ADDRESS_SPACE_SHIFT 14 #define ZSWAP_ADDRESS_SPACE_PAGES (1 << ZSWAP_ADDRESS_SPACE_SHIFT) static inline struct xarray *swap_zswap_tree(swp_entry_t swp) { return &zswap_trees[swp_type(swp)][swp_offset(swp) >> ZSWAP_ADDRESS_SPACE_SHIFT]; } #define zswap_pool_debug(msg, p) \ pr_debug("%s pool %s\n", msg, (p)->tfm_name) /********************************* * pool functions **********************************/ static void __zswap_pool_empty(struct percpu_ref *ref); static struct zswap_pool *zswap_pool_create(char *compressor) { struct zswap_pool *pool; char name[38]; /* 'zswap' + 32 char (max) num + \0 */ int ret, cpu; if (!zswap_has_pool && !strcmp(compressor, ZSWAP_PARAM_UNSET)) return NULL; pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) return NULL; /* unique name for each pool specifically required by zsmalloc */ snprintf(name, 38, "zswap%x", atomic_inc_return(&zswap_pools_count)); pool->zs_pool = zs_create_pool(name); if (!pool->zs_pool) goto error; strscpy(pool->tfm_name, compressor, sizeof(pool->tfm_name)); pool->acomp_ctx = alloc_percpu(*pool->acomp_ctx); if (!pool->acomp_ctx) { pr_err("percpu alloc failed\n"); goto error; } for_each_possible_cpu(cpu) mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex); ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); if (ret) goto error; /* being the current pool takes 1 ref; this func expects the * caller to always add the new pool as the current pool */ ret = percpu_ref_init(&pool->ref, __zswap_pool_empty, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL); if (ret) goto ref_fail; INIT_LIST_HEAD(&pool->list); zswap_pool_debug("created", pool); return pool; ref_fail: cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); error: if (pool->acomp_ctx) free_percpu(pool->acomp_ctx); if (pool->zs_pool) zs_destroy_pool(pool->zs_pool); kfree(pool); return NULL; } static struct zswap_pool *__zswap_pool_create_fallback(void) { if (!crypto_has_acomp(zswap_compressor, 0, 0) && strcmp(zswap_compressor, CONFIG_ZSWAP_COMPRESSOR_DEFAULT)) { pr_err("compressor %s not available, using default %s\n", zswap_compressor, CONFIG_ZSWAP_COMPRESSOR_DEFAULT); param_free_charp(&zswap_compressor); zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT; } /* Default compressor should be available. Kconfig bug? */ if (WARN_ON_ONCE(!crypto_has_acomp(zswap_compressor, 0, 0))) { zswap_compressor = ZSWAP_PARAM_UNSET; return NULL; } return zswap_pool_create(zswap_compressor); } static void zswap_pool_destroy(struct zswap_pool *pool) { zswap_pool_debug("destroying", pool); cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); free_percpu(pool->acomp_ctx); zs_destroy_pool(pool->zs_pool); kfree(pool); } static void __zswap_pool_release(struct work_struct *work) { struct zswap_pool *pool = container_of(work, typeof(*pool), release_work); synchronize_rcu(); /* nobody should have been able to get a ref... */ WARN_ON(!percpu_ref_is_zero(&pool->ref)); percpu_ref_exit(&pool->ref); /* pool is now off zswap_pools list and has no references. */ zswap_pool_destroy(pool); } static struct zswap_pool *zswap_pool_current(void); static void __zswap_pool_empty(struct percpu_ref *ref) { struct zswap_pool *pool; pool = container_of(ref, typeof(*pool), ref); spin_lock_bh(&zswap_pools_lock); WARN_ON(pool == zswap_pool_current()); list_del_rcu(&pool->list); INIT_WORK(&pool->release_work, __zswap_pool_release); schedule_work(&pool->release_work); spin_unlock_bh(&zswap_pools_lock); } static int __must_check zswap_pool_tryget(struct zswap_pool *pool) { if (!pool) return 0; return percpu_ref_tryget(&pool->ref); } /* The caller must already have a reference. */ static void zswap_pool_get(struct zswap_pool *pool) { percpu_ref_get(&pool->ref); } static void zswap_pool_put(struct zswap_pool *pool) { percpu_ref_put(&pool->ref); } static struct zswap_pool *__zswap_pool_current(void) { struct zswap_pool *pool; pool = list_first_or_null_rcu(&zswap_pools, typeof(*pool), list); WARN_ONCE(!pool && zswap_has_pool, "%s: no page storage pool!\n", __func__); return pool; } static struct zswap_pool *zswap_pool_current(void) { assert_spin_locked(&zswap_pools_lock); return __zswap_pool_current(); } static struct zswap_pool *zswap_pool_current_get(void) { struct zswap_pool *pool; rcu_read_lock(); pool = __zswap_pool_current(); if (!zswap_pool_tryget(pool)) pool = NULL; rcu_read_unlock(); return pool; } /* type and compressor must be null-terminated */ static struct zswap_pool *zswap_pool_find_get(char *compressor) { struct zswap_pool *pool; assert_spin_locked(&zswap_pools_lock); list_for_each_entry_rcu(pool, &zswap_pools, list) { if (strcmp(pool->tfm_name, compressor)) continue; /* if we can't get it, it's about to be destroyed */ if (!zswap_pool_tryget(pool)) continue; return pool; } return NULL; } static unsigned long zswap_max_pages(void) { return totalram_pages() * zswap_max_pool_percent / 100; } static unsigned long zswap_accept_thr_pages(void) { return zswap_max_pages() * zswap_accept_thr_percent / 100; } unsigned long zswap_total_pages(void) { struct zswap_pool *pool; unsigned long total = 0; rcu_read_lock(); list_for_each_entry_rcu(pool, &zswap_pools, list) total += zs_get_total_pages(pool->zs_pool); rcu_read_unlock(); return total; } static bool zswap_check_limits(void) { unsigned long cur_pages = zswap_total_pages(); unsigned long max_pages = zswap_max_pages(); if (cur_pages >= max_pages) { zswap_pool_limit_hit++; zswap_pool_reached_full = true; } else if (zswap_pool_reached_full && cur_pages <= zswap_accept_thr_pages()) { zswap_pool_reached_full = false; } return zswap_pool_reached_full; } /********************************* * param callbacks **********************************/ static int zswap_compressor_param_set(const char *val, const struct kernel_param *kp) { struct zswap_pool *pool, *put_pool = NULL; char *s = strstrip((char *)val); bool create_pool = false; int ret = 0; mutex_lock(&zswap_init_lock); switch (zswap_init_state) { case ZSWAP_UNINIT: /* Handled in zswap_setup() */ ret = param_set_charp(s, kp); break; case ZSWAP_INIT_SUCCEED: if (!zswap_has_pool || strcmp(s, *(char **)kp->arg)) create_pool = true; break; case ZSWAP_INIT_FAILED: pr_err("can't set param, initialization failed\n"); ret = -ENODEV; } mutex_unlock(&zswap_init_lock); if (!create_pool) return ret; if (!crypto_has_acomp(s, 0, 0)) { pr_err("compressor %s not available\n", s); return -ENOENT; } spin_lock_bh(&zswap_pools_lock); pool = zswap_pool_find_get(s); if (pool) { zswap_pool_debug("using existing", pool); WARN_ON(pool == zswap_pool_current()); list_del_rcu(&pool->list); } spin_unlock_bh(&zswap_pools_lock); if (!pool) pool = zswap_pool_create(s); else { /* * Restore the initial ref dropped by percpu_ref_kill() * when the pool was decommissioned and switch it again * to percpu mode. */ percpu_ref_resurrect(&pool->ref); /* Drop the ref from zswap_pool_find_get(). */ zswap_pool_put(pool); } if (pool) ret = param_set_charp(s, kp); else ret = -EINVAL; spin_lock_bh(&zswap_pools_lock); if (!ret) { put_pool = zswap_pool_current(); list_add_rcu(&pool->list, &zswap_pools); zswap_has_pool = true; } else if (pool) { /* * Add the possibly pre-existing pool to the end of the pools * list; if it's new (and empty) then it'll be removed and * destroyed by the put after we drop the lock */ list_add_tail_rcu(&pool->list, &zswap_pools); put_pool = pool; } spin_unlock_bh(&zswap_pools_lock); /* * Drop the ref from either the old current pool, * or the new pool we failed to add */ if (put_pool) percpu_ref_kill(&put_pool->ref); return ret; } static int zswap_enabled_param_set(const char *val, const struct kernel_param *kp) { int ret = -ENODEV; /* if this is load-time (pre-init) param setting, only set param. */ if (system_state != SYSTEM_RUNNING) return param_set_bool(val, kp); mutex_lock(&zswap_init_lock); switch (zswap_init_state) { case ZSWAP_UNINIT: if (zswap_setup()) break; fallthrough; case ZSWAP_INIT_SUCCEED: if (!zswap_has_pool) pr_err("can't enable, no pool configured\n"); else ret = param_set_bool(val, kp); break; case ZSWAP_INIT_FAILED: pr_err("can't enable, initialization failed\n"); } mutex_unlock(&zswap_init_lock); return ret; } /********************************* * lru functions **********************************/ /* should be called under RCU */ #ifdef CONFIG_MEMCG static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry) { return entry->objcg ? obj_cgroup_memcg(entry->objcg) : NULL; } #else static inline struct mem_cgroup *mem_cgroup_from_entry(struct zswap_entry *entry) { return NULL; } #endif static inline int entry_to_nid(struct zswap_entry *entry) { return page_to_nid(virt_to_page(entry)); } static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry) { int nid = entry_to_nid(entry); struct mem_cgroup *memcg; /* * Note that it is safe to use rcu_read_lock() here, even in the face of * concurrent memcg offlining: * * 1. list_lru_add() is called before list_lru_one is dead. The * new entry will be reparented to memcg's parent's list_lru. * 2. list_lru_add() is called after list_lru_one is dead. The * new entry will be added directly to memcg's parent's list_lru. * * Similar reasoning holds for list_lru_del(). */ rcu_read_lock(); memcg = mem_cgroup_from_entry(entry); /* will always succeed */ list_lru_add(list_lru, &entry->lru, nid, memcg); rcu_read_unlock(); } static void zswap_lru_del(struct list_lru *list_lru, struct zswap_entry *entry) { int nid = entry_to_nid(entry); struct mem_cgroup *memcg; rcu_read_lock(); memcg = mem_cgroup_from_entry(entry); /* will always succeed */ list_lru_del(list_lru, &entry->lru, nid, memcg); rcu_read_unlock(); } void zswap_lruvec_state_init(struct lruvec *lruvec) { atomic_long_set(&lruvec->zswap_lruvec_state.nr_disk_swapins, 0); } void zswap_folio_swapin(struct folio *folio) { struct lruvec *lruvec; if (folio) { lruvec = folio_lruvec(folio); atomic_long_inc(&lruvec->zswap_lruvec_state.nr_disk_swapins); } } /* * This function should be called when a memcg is being offlined. * * Since the global shrinker shrink_worker() may hold a reference * of the memcg, we must check and release the reference in * zswap_next_shrink. * * shrink_worker() must handle the case where this function releases * the reference of memcg being shrunk. */ void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) { /* lock out zswap shrinker walking memcg tree */ spin_lock(&zswap_shrink_lock); if (zswap_next_shrink == memcg) { do { zswap_next_shrink = mem_cgroup_iter(NULL, zswap_next_shrink, NULL); } while (zswap_next_shrink && !mem_cgroup_online(zswap_next_shrink)); } spin_unlock(&zswap_shrink_lock); } /********************************* * zswap entry functions **********************************/ static struct kmem_cache *zswap_entry_cache; static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid) { struct zswap_entry *entry; entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid); if (!entry) return NULL; return entry; } static void zswap_entry_cache_free(struct zswap_entry *entry) { kmem_cache_free(zswap_entry_cache, entry); } /* * Carries out the common pattern of freeing an entry's zsmalloc allocation, * freeing the entry itself, and decrementing the number of stored pages. */ static void zswap_entry_free(struct zswap_entry *entry) { zswap_lru_del(&zswap_list_lru, entry); zs_free(entry->pool->zs_pool, entry->handle); zswap_pool_put(entry->pool); if (entry->objcg) { obj_cgroup_uncharge_zswap(entry->objcg, entry->length); obj_cgroup_put(entry->objcg); } if (entry->length == PAGE_SIZE) atomic_long_dec(&zswap_stored_incompressible_pages); zswap_entry_cache_free(entry); atomic_long_dec(&zswap_stored_pages); } /********************************* * compressed storage functions **********************************/ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); struct crypto_acomp *acomp = NULL; struct acomp_req *req = NULL; u8 *buffer = NULL; int ret; buffer = kmalloc_node(PAGE_SIZE, GFP_KERNEL, cpu_to_node(cpu)); if (!buffer) { ret = -ENOMEM; goto fail; } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); if (IS_ERR(acomp)) { pr_err("could not alloc crypto acomp %s : %ld\n", pool->tfm_name, PTR_ERR(acomp)); ret = PTR_ERR(acomp); goto fail; } req = acomp_request_alloc(acomp); if (!req) { pr_err("could not alloc crypto acomp_request %s\n", pool->tfm_name); ret = -ENOMEM; goto fail; } /* * Only hold the mutex after completing allocations, otherwise we may * recurse into zswap through reclaim and attempt to hold the mutex * again resulting in a deadlock. */ mutex_lock(&acomp_ctx->mutex); crypto_init_wait(&acomp_ctx->wait); /* * if the backend of acomp is async zip, crypto_req_done() will wakeup * crypto_wait_req(); if the backend of acomp is scomp, the callback * won't be called, crypto_wait_req() will return without blocking. */ acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); acomp_ctx->buffer = buffer; acomp_ctx->acomp = acomp; acomp_ctx->is_sleepable = acomp_is_async(acomp); acomp_ctx->req = req; mutex_unlock(&acomp_ctx->mutex); return 0; fail: if (acomp) crypto_free_acomp(acomp); kfree(buffer); return ret; } static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); struct acomp_req *req; struct crypto_acomp *acomp; u8 *buffer; if (IS_ERR_OR_NULL(acomp_ctx)) return 0; mutex_lock(&acomp_ctx->mutex); req = acomp_ctx->req; acomp = acomp_ctx->acomp; buffer = acomp_ctx->buffer; acomp_ctx->req = NULL; acomp_ctx->acomp = NULL; acomp_ctx->buffer = NULL; mutex_unlock(&acomp_ctx->mutex); /* * Do the actual freeing after releasing the mutex to avoid subtle * locking dependencies causing deadlocks. */ if (!IS_ERR_OR_NULL(req)) acomp_request_free(req); if (!IS_ERR_OR_NULL(acomp)) crypto_free_acomp(acomp); kfree(buffer); return 0; } static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool) { struct crypto_acomp_ctx *acomp_ctx; for (;;) { acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); mutex_lock(&acomp_ctx->mutex); if (likely(acomp_ctx->req)) return acomp_ctx; /* * It is possible that we were migrated to a different CPU after * getting the per-CPU ctx but before the mutex was acquired. If * the old CPU got offlined, zswap_cpu_comp_dead() could have * already freed ctx->req (among other things) and set it to * NULL. Just try again on the new CPU that we ended up on. */ mutex_unlock(&acomp_ctx->mutex); } } static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx) { mutex_unlock(&acomp_ctx->mutex); } static bool zswap_compress(struct page *page, struct zswap_entry *entry, struct zswap_pool *pool) { struct crypto_acomp_ctx *acomp_ctx; struct scatterlist input, output; int comp_ret = 0, alloc_ret = 0; unsigned int dlen = PAGE_SIZE; unsigned long handle; gfp_t gfp; u8 *dst; bool mapped = false; acomp_ctx = acomp_ctx_get_cpu_lock(pool); dst = acomp_ctx->buffer; sg_init_table(&input, 1); sg_set_page(&input, page, PAGE_SIZE, 0); sg_init_one(&output, dst, PAGE_SIZE); acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen); /* * it maybe looks a little bit silly that we send an asynchronous request, * then wait for its completion synchronously. This makes the process look * synchronous in fact. * Theoretically, acomp supports users send multiple acomp requests in one * acomp instance, then get those requests done simultaneously. but in this * case, zswap actually does store and load page by page, there is no * existing method to send the second page before the first page is done * in one thread doing zwap. * but in different threads running on different cpu, we have different * acomp instance, so multiple threads can do (de)compression in parallel. */ comp_ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait); dlen = acomp_ctx->req->dlen; /* * If a page cannot be compressed into a size smaller than PAGE_SIZE, * save the content as is without a compression, to keep the LRU order * of writebacks. If writeback is disabled, reject the page since it * only adds metadata overhead. swap_writeout() will put the page back * to the active LRU list in the case. */ if (comp_ret || !dlen || dlen >= PAGE_SIZE) { dlen = PAGE_SIZE; if (!mem_cgroup_zswap_writeback_enabled( folio_memcg(page_folio(page)))) { comp_ret = comp_ret ? comp_ret : -EINVAL; goto unlock; } comp_ret = 0; dlen = PAGE_SIZE; dst = kmap_local_page(page); mapped = true; } gfp = GFP_NOWAIT | __GFP_NORETRY | __GFP_HIGHMEM | __GFP_MOVABLE; handle = zs_malloc(pool->zs_pool, dlen, gfp, page_to_nid(page)); if (IS_ERR_VALUE(handle)) { alloc_ret = PTR_ERR((void *)handle); goto unlock; } zs_obj_write(pool->zs_pool, handle, dst, dlen); entry->handle = handle; entry->length = dlen; unlock: if (mapped) kunmap_local(dst); if (comp_ret == -ENOSPC || alloc_ret == -ENOSPC) zswap_reject_compress_poor++; else if (comp_ret) zswap_reject_compress_fail++; else if (alloc_ret) zswap_reject_alloc_fail++; acomp_ctx_put_unlock(acomp_ctx); return comp_ret == 0 && alloc_ret == 0; } static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio) { struct zswap_pool *pool = entry->pool; struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; int decomp_ret = 0, dlen = PAGE_SIZE; u8 *src, *obj; acomp_ctx = acomp_ctx_get_cpu_lock(pool); obj = zs_obj_read_begin(pool->zs_pool, entry->handle, acomp_ctx->buffer); /* zswap entries of length PAGE_SIZE are not compressed. */ if (entry->length == PAGE_SIZE) { memcpy_to_folio(folio, 0, obj, entry->length); goto read_done; } /* * zs_obj_read_begin() might return a kmap address of highmem when * acomp_ctx->buffer is not used. However, sg_init_one() does not * handle highmem addresses, so copy the object to acomp_ctx->buffer. */ if (virt_addr_valid(obj)) { src = obj; } else { WARN_ON_ONCE(obj == acomp_ctx->buffer); memcpy(acomp_ctx->buffer, obj, entry->length); src = acomp_ctx->buffer; } sg_init_one(&input, src, entry->length); sg_init_table(&output, 1); sg_set_folio(&output, folio, PAGE_SIZE, 0); acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE); decomp_ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait); dlen = acomp_ctx->req->dlen; read_done: zs_obj_read_end(pool->zs_pool, entry->handle, obj); acomp_ctx_put_unlock(acomp_ctx); if (!decomp_ret && dlen == PAGE_SIZE) return true; zswap_decompress_fail++; pr_alert_ratelimited("Decompression error from zswap (%d:%lu %s %u->%d)\n", swp_type(entry->swpentry), swp_offset(entry->swpentry), entry->pool->tfm_name, entry->length, dlen); return false; } /********************************* * writeback code **********************************/ /* * Attempts to free an entry by adding a folio to the swap cache, * decompressing the entry data into the folio, and issuing a * bio write to write the folio back to the swap device. * * This can be thought of as a "resumed writeback" of the folio * to the swap device. We are basically resuming the same swap * writeback path that was intercepted with the zswap_store() * in the first place. After the folio has been decompressed into * the swap cache, the compressed version stored by zswap can be * freed. */ static int zswap_writeback_entry(struct zswap_entry *entry, swp_entry_t swpentry) { struct xarray *tree; pgoff_t offset = swp_offset(swpentry); struct folio *folio; struct mempolicy *mpol; bool folio_was_allocated; struct swap_info_struct *si; int ret = 0; /* try to allocate swap cache folio */ si = get_swap_device(swpentry); if (!si) return -EEXIST; mpol = get_task_policy(current); folio = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol, NO_INTERLEAVE_INDEX, &folio_was_allocated, true); put_swap_device(si); if (!folio) return -ENOMEM; /* * Found an existing folio, we raced with swapin or concurrent * shrinker. We generally writeback cold folios from zswap, and * swapin means the folio just became hot, so skip this folio. * For unlikely concurrent shrinker case, it will be unlinked * and freed when invalidated by the concurrent shrinker anyway. */ if (!folio_was_allocated) { ret = -EEXIST; goto out; } /* * folio is locked, and the swapcache is now secured against * concurrent swapping to and from the slot, and concurrent * swapoff so we can safely dereference the zswap tree here. * Verify that the swap entry hasn't been invalidated and recycled * behind our backs, to avoid overwriting a new swap folio with * old compressed data. Only when this is successful can the entry * be dereferenced. */ tree = swap_zswap_tree(swpentry); if (entry != xa_load(tree, offset)) { ret = -ENOMEM; goto out; } if (!zswap_decompress(entry, folio)) { ret = -EIO; goto out; } xa_erase(tree, offset); count_vm_event(ZSWPWB); if (entry->objcg) count_objcg_events(entry->objcg, ZSWPWB, 1); zswap_entry_free(entry); /* folio is up to date */ folio_mark_uptodate(folio); /* move it to the tail of the inactive list after end_writeback */ folio_set_reclaim(folio); /* start writeback */ __swap_writepage(folio, NULL); out: if (ret && ret != -EEXIST) { swap_cache_del_folio(folio); folio_unlock(folio); } folio_put(folio); return ret; } /********************************* * shrinker functions **********************************/ /* * The dynamic shrinker is modulated by the following factors: * * 1. Each zswap entry has a referenced bit, which the shrinker unsets (giving * the entry a second chance) before rotating it in the LRU list. If the * entry is considered again by the shrinker, with its referenced bit unset, * it is written back. The writeback rate as a result is dynamically * adjusted by the pool activities - if the pool is dominated by new entries * (i.e lots of recent zswapouts), these entries will be protected and * the writeback rate will slow down. On the other hand, if the pool has a * lot of stagnant entries, these entries will be reclaimed immediately, * effectively increasing the writeback rate. * * 2. Swapins counter: If we observe swapins, it is a sign that we are * overshrinking and should slow down. We maintain a swapins counter, which * is consumed and subtract from the number of eligible objects on the LRU * in zswap_shrinker_count(). * * 3. Compression ratio. The better the workload compresses, the less gains we * can expect from writeback. We scale down the number of objects available * for reclaim by this ratio. */ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l, void *arg) { struct zswap_entry *entry = container_of(item, struct zswap_entry, lru); bool *encountered_page_in_swapcache = (bool *)arg; swp_entry_t swpentry; enum lru_status ret = LRU_REMOVED_RETRY; int writeback_result; /* * Second chance algorithm: if the entry has its referenced bit set, give it * a second chance. Only clear the referenced bit and rotate it in the * zswap's LRU list. */ if (entry->referenced) { entry->referenced = false; return LRU_ROTATE; } /* * As soon as we drop the LRU lock, the entry can be freed by * a concurrent invalidation. This means the following: * * 1. We extract the swp_entry_t to the stack, allowing * zswap_writeback_entry() to pin the swap entry and * then validate the zwap entry against that swap entry's * tree using pointer value comparison. Only when that * is successful can the entry be dereferenced. * * 2. Usually, objects are taken off the LRU for reclaim. In * this case this isn't possible, because if reclaim fails * for whatever reason, we have no means of knowing if the * entry is alive to put it back on the LRU. * * So rotate it before dropping the lock. If the entry is * written back or invalidated, the free path will unlink * it. For failures, rotation is the right thing as well. * * Temporary failures, where the same entry should be tried * again immediately, almost never happen for this shrinker. * We don't do any trylocking; -ENOMEM comes closest, * but that's extremely rare and doesn't happen spuriously * either. Don't bother distinguishing this case. */ list_move_tail(item, &l->list); /* * Once the lru lock is dropped, the entry might get freed. The * swpentry is copied to the stack, and entry isn't deref'd again * until the entry is verified to still be alive in the tree. */ swpentry = entry->swpentry; /* * It's safe to drop the lock here because we return either * LRU_REMOVED_RETRY, LRU_RETRY or LRU_STOP. */ spin_unlock(&l->lock); writeback_result = zswap_writeback_entry(entry, swpentry); if (writeback_result) { zswap_reject_reclaim_fail++; ret = LRU_RETRY; /* * Encountering a page already in swap cache is a sign that we are shrinking * into the warmer region. We should terminate shrinking (if we're in the dynamic * shrinker context). */ if (writeback_result == -EEXIST && encountered_page_in_swapcache) { ret = LRU_STOP; *encountered_page_in_swapcache = true; } } else { zswap_written_back_pages++; } return ret; } static unsigned long zswap_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { unsigned long shrink_ret; bool encountered_page_in_swapcache = false; if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(sc->memcg)) { sc->nr_scanned = 0; return SHRINK_STOP; } shrink_ret = list_lru_shrink_walk(&zswap_list_lru, sc, &shrink_memcg_cb, &encountered_page_in_swapcache); if (encountered_page_in_swapcache) return SHRINK_STOP; return shrink_ret ? shrink_ret : SHRINK_STOP; } static unsigned long zswap_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { struct mem_cgroup *memcg = sc->memcg; struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid)); atomic_long_t *nr_disk_swapins = &lruvec->zswap_lruvec_state.nr_disk_swapins; unsigned long nr_backing, nr_stored, nr_freeable, nr_disk_swapins_cur, nr_remain; if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg)) return 0; /* * The shrinker resumes swap writeback, which will enter block * and may enter fs. XXX: Harmonize with vmscan.c __GFP_FS * rules (may_enter_fs()), which apply on a per-folio basis. */ if (!gfp_has_io_fs(sc->gfp_mask)) return 0; /* * For memcg, use the cgroup-wide ZSWAP stats since we don't * have them per-node and thus per-lruvec. Careful if memcg is * runtime-disabled: we can get sc->memcg == NULL, which is ok * for the lruvec, but not for memcg_page_state(). * * Without memcg, use the zswap pool-wide metrics. */ if (!mem_cgroup_disabled()) { mem_cgroup_flush_stats(memcg); nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); } else { nr_backing = zswap_total_pages(); nr_stored = atomic_long_read(&zswap_stored_pages); } if (!nr_stored) return 0; nr_freeable = list_lru_shrink_count(&zswap_list_lru, sc); if (!nr_freeable) return 0; /* * Subtract from the lru size the number of pages that are recently swapped * in from disk. The idea is that had we protect the zswap's LRU by this * amount of pages, these disk swapins would not have happened. */ nr_disk_swapins_cur = atomic_long_read(nr_disk_swapins); do { if (nr_freeable >= nr_disk_swapins_cur) nr_remain = 0; else nr_remain = nr_disk_swapins_cur - nr_freeable; } while (!atomic_long_try_cmpxchg( nr_disk_swapins, &nr_disk_swapins_cur, nr_remain)); nr_freeable -= nr_disk_swapins_cur - nr_remain; if (!nr_freeable) return 0; /* * Scale the number of freeable pages by the memory saving factor. * This ensures that the better zswap compresses memory, the fewer * pages we will evict to swap (as it will otherwise incur IO for * relatively small memory saving). */ return mult_frac(nr_freeable, nr_backing, nr_stored); } static struct shrinker *zswap_alloc_shrinker(void) { struct shrinker *shrinker; shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "mm-zswap"); if (!shrinker) return NULL; shrinker->scan_objects = zswap_shrinker_scan; shrinker->count_objects = zswap_shrinker_count; shrinker->batch = 0; shrinker->seeks = DEFAULT_SEEKS; return shrinker; } static int shrink_memcg(struct mem_cgroup *memcg) { int nid, shrunk = 0, scanned = 0; if (!mem_cgroup_zswap_writeback_enabled(memcg)) return -ENOENT; /* * Skip zombies because their LRUs are reparented and we would be * reclaiming from the parent instead of the dead memcg. */ if (memcg && !mem_cgroup_online(memcg)) return -ENOENT; for_each_node_state(nid, N_NORMAL_MEMORY) { unsigned long nr_to_walk = 1; shrunk += list_lru_walk_one(&zswap_list_lru, nid, memcg, &shrink_memcg_cb, NULL, &nr_to_walk); scanned += 1 - nr_to_walk; } if (!scanned) return -ENOENT; return shrunk ? 0 : -EAGAIN; } static void shrink_worker(struct work_struct *w) { struct mem_cgroup *memcg; int ret, failures = 0, attempts = 0; unsigned long thr; /* Reclaim down to the accept threshold */ thr = zswap_accept_thr_pages(); /* * Global reclaim will select cgroup in a round-robin fashion from all * online memcgs, but memcgs that have no pages in zswap and * writeback-disabled memcgs (memory.zswap.writeback=0) are not * candidates for shrinking. * * Shrinking will be aborted if we encounter the following * MAX_RECLAIM_RETRIES times: * - No writeback-candidate memcgs found in a memcg tree walk. * - Shrinking a writeback-candidate memcg failed. * * We save iteration cursor memcg into zswap_next_shrink, * which can be modified by the offline memcg cleaner * zswap_memcg_offline_cleanup(). * * Since the offline cleaner is called only once, we cannot leave an * offline memcg reference in zswap_next_shrink. * We can rely on the cleaner only if we get online memcg under lock. * * If we get an offline memcg, we cannot determine if the cleaner has * already been called or will be called later. We must put back the * reference before returning from this function. Otherwise, the * offline memcg left in zswap_next_shrink will hold the reference * until the next run of shrink_worker(). */ do { /* * Start shrinking from the next memcg after zswap_next_shrink. * When the offline cleaner has already advanced the cursor, * advancing the cursor here overlooks one memcg, but this * should be negligibly rare. * * If we get an online memcg, keep the extra reference in case * the original one obtained by mem_cgroup_iter() is dropped by * zswap_memcg_offline_cleanup() while we are shrinking the * memcg. */ spin_lock(&zswap_shrink_lock); do { memcg = mem_cgroup_iter(NULL, zswap_next_shrink, NULL); zswap_next_shrink = memcg; } while (memcg && !mem_cgroup_tryget_online(memcg)); spin_unlock(&zswap_shrink_lock); if (!memcg) { /* * Continue shrinking without incrementing failures if * we found candidate memcgs in the last tree walk. */ if (!attempts && ++failures == MAX_RECLAIM_RETRIES) break; attempts = 0; goto resched; } ret = shrink_memcg(memcg); /* drop the extra reference */ mem_cgroup_put(memcg); /* * There are no writeback-candidate pages in the memcg. * This is not an issue as long as we can find another memcg * with pages in zswap. Skip this without incrementing attempts * and failures. */ if (ret == -ENOENT) continue; ++attempts; if (ret && ++failures == MAX_RECLAIM_RETRIES) break; resched: cond_resched(); } while (zswap_total_pages() > thr); } /********************************* * main API **********************************/ static bool zswap_store_page(struct page *page, struct obj_cgroup *objcg, struct zswap_pool *pool) { swp_entry_t page_swpentry = page_swap_entry(page); struct zswap_entry *entry, *old; /* allocate entry */ entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page)); if (!entry) { zswap_reject_kmemcache_fail++; return false; } if (!zswap_compress(page, entry, pool)) goto compress_failed; old = xa_store(swap_zswap_tree(page_swpentry), swp_offset(page_swpentry), entry, GFP_KERNEL); if (xa_is_err(old)) { int err = xa_err(old); WARN_ONCE(err != -ENOMEM, "unexpected xarray error: %d\n", err); zswap_reject_alloc_fail++; goto store_failed; } /* * We may have had an existing entry that became stale when * the folio was redirtied and now the new version is being * swapped out. Get rid of the old. */ if (old) zswap_entry_free(old); /* * The entry is successfully compressed and stored in the tree, there is * no further possibility of failure. Grab refs to the pool and objcg, * charge zswap memory, and increment zswap_stored_pages. * The opposite actions will be performed by zswap_entry_free() * when the entry is removed from the tree. */ zswap_pool_get(pool); if (objcg) { obj_cgroup_get(objcg); obj_cgroup_charge_zswap(objcg, entry->length); } atomic_long_inc(&zswap_stored_pages); if (entry->length == PAGE_SIZE) atomic_long_inc(&zswap_stored_incompressible_pages); /* * We finish initializing the entry while it's already in xarray. * This is safe because: * * 1. Concurrent stores and invalidations are excluded by folio lock. * * 2. Writeback is excluded by the entry not being on the LRU yet. * The publishing order matters to prevent writeback from seeing * an incoherent entry. */ entry->pool = pool; entry->swpentry = page_swpentry; entry->objcg = objcg; entry->referenced = true; if (entry->length) { INIT_LIST_HEAD(&entry->lru); zswap_lru_add(&zswap_list_lru, entry); } return true; store_failed: zs_free(pool->zs_pool, entry->handle); compress_failed: zswap_entry_cache_free(entry); return false; } bool zswap_store(struct folio *folio) { long nr_pages = folio_nr_pages(folio); swp_entry_t swp = folio->swap; struct obj_cgroup *objcg = NULL; struct mem_cgroup *memcg = NULL; struct zswap_pool *pool; bool ret = false; long index; VM_WARN_ON_ONCE(!folio_test_locked(folio)); VM_WARN_ON_ONCE(!folio_test_swapcache(folio)); if (!zswap_enabled) goto check_old; objcg = get_obj_cgroup_from_folio(folio); if (objcg && !obj_cgroup_may_zswap(objcg)) { memcg = get_mem_cgroup_from_objcg(objcg); if (shrink_memcg(memcg)) { mem_cgroup_put(memcg); goto put_objcg; } mem_cgroup_put(memcg); } if (zswap_check_limits()) goto put_objcg; pool = zswap_pool_current_get(); if (!pool) goto put_objcg; if (objcg) { memcg = get_mem_cgroup_from_objcg(objcg); if (memcg_list_lru_alloc(memcg, &zswap_list_lru, GFP_KERNEL)) { mem_cgroup_put(memcg); goto put_pool; } mem_cgroup_put(memcg); } for (index = 0; index < nr_pages; ++index) { struct page *page = folio_page(folio, index); if (!zswap_store_page(page, objcg, pool)) goto put_pool; } if (objcg) count_objcg_events(objcg, ZSWPOUT, nr_pages); count_vm_events(ZSWPOUT, nr_pages); ret = true; put_pool: zswap_pool_put(pool); put_objcg: obj_cgroup_put(objcg); if (!ret && zswap_pool_reached_full) queue_work(shrink_wq, &zswap_shrink_work); check_old: /* * If the zswap store fails or zswap is disabled, we must invalidate * the possibly stale entries which were previously stored at the * offsets corresponding to each page of the folio. Otherwise, * writeback could overwrite the new data in the swapfile. */ if (!ret) { unsigned type = swp_type(swp); pgoff_t offset = swp_offset(swp); struct zswap_entry *entry; struct xarray *tree; for (index = 0; index < nr_pages; ++index) { tree = swap_zswap_tree(swp_entry(type, offset + index)); entry = xa_erase(tree, offset + index); if (entry) zswap_entry_free(entry); } } return ret; } /** * zswap_load() - load a folio from zswap * @folio: folio to load * * Return: 0 on success, with the folio unlocked and marked up-to-date, or one * of the following error codes: * * -EIO: if the swapped out content was in zswap, but could not be loaded * into the page due to a decompression failure. The folio is unlocked, but * NOT marked up-to-date, so that an IO error is emitted (e.g. do_swap_page() * will SIGBUS). * * -EINVAL: if the swapped out content was in zswap, but the page belongs * to a large folio, which is not supported by zswap. The folio is unlocked, * but NOT marked up-to-date, so that an IO error is emitted (e.g. * do_swap_page() will SIGBUS). * * -ENOENT: if the swapped out content was not in zswap. The folio remains * locked on return. */ int zswap_load(struct folio *folio) { swp_entry_t swp = folio->swap; pgoff_t offset = swp_offset(swp); bool swapcache = folio_test_swapcache(folio); struct xarray *tree = swap_zswap_tree(swp); struct zswap_entry *entry; VM_WARN_ON_ONCE(!folio_test_locked(folio)); if (zswap_never_enabled()) return -ENOENT; /* * Large folios should not be swapped in while zswap is being used, as * they are not properly handled. Zswap does not properly load large * folios, and a large folio may only be partially in zswap. */ if (WARN_ON_ONCE(folio_test_large(folio))) { folio_unlock(folio); return -EINVAL; } entry = xa_load(tree, offset); if (!entry) return -ENOENT; if (!zswap_decompress(entry, folio)) { folio_unlock(folio); return -EIO; } folio_mark_uptodate(folio); count_vm_event(ZSWPIN); if (entry->objcg) count_objcg_events(entry->objcg, ZSWPIN, 1); /* * When reading into the swapcache, invalidate our entry. The * swapcache can be the authoritative owner of the page and * its mappings, and the pressure that results from having two * in-memory copies outweighs any benefits of caching the * compression work. * * (Most swapins go through the swapcache. The notable * exception is the singleton fault on SWP_SYNCHRONOUS_IO * files, which reads into a private page and may free it if * the fault fails. We remain the primary owner of the entry.) */ if (swapcache) { folio_mark_dirty(folio); xa_erase(tree, offset); zswap_entry_free(entry); } folio_unlock(folio); return 0; } void zswap_invalidate(swp_entry_t swp) { pgoff_t offset = swp_offset(swp); struct xarray *tree = swap_zswap_tree(swp); struct zswap_entry *entry; if (xa_empty(tree)) return; entry = xa_erase(tree, offset); if (entry) zswap_entry_free(entry); } int zswap_swapon(int type, unsigned long nr_pages) { struct xarray *trees, *tree; unsigned int nr, i; nr = DIV_ROUND_UP(nr_pages, ZSWAP_ADDRESS_SPACE_PAGES); trees = kvcalloc(nr, sizeof(*tree), GFP_KERNEL); if (!trees) { pr_err("alloc failed, zswap disabled for swap type %d\n", type); return -ENOMEM; } for (i = 0; i < nr; i++) xa_init(trees + i); nr_zswap_trees[type] = nr; zswap_trees[type] = trees; return 0; } void zswap_swapoff(int type) { struct xarray *trees = zswap_trees[type]; unsigned int i; if (!trees) return; /* try_to_unuse() invalidated all the entries already */ for (i = 0; i < nr_zswap_trees[type]; i++) WARN_ON_ONCE(!xa_empty(trees + i)); kvfree(trees); nr_zswap_trees[type] = 0; zswap_trees[type] = NULL; } /********************************* * debugfs functions **********************************/ #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> static struct dentry *zswap_debugfs_root; static int debugfs_get_total_size(void *data, u64 *val) { *val = zswap_total_pages() * PAGE_SIZE; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(total_size_fops, debugfs_get_total_size, NULL, "%llu\n"); static int debugfs_get_stored_pages(void *data, u64 *val) { *val = atomic_long_read(&zswap_stored_pages); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(stored_pages_fops, debugfs_get_stored_pages, NULL, "%llu\n"); static int debugfs_get_stored_incompressible_pages(void *data, u64 *val) { *val = atomic_long_read(&zswap_stored_incompressible_pages); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(stored_incompressible_pages_fops, debugfs_get_stored_incompressible_pages, NULL, "%llu\n"); static int zswap_debugfs_init(void) { if (!debugfs_initialized()) return -ENODEV; zswap_debugfs_root = debugfs_create_dir("zswap", NULL); debugfs_create_u64("pool_limit_hit", 0444, zswap_debugfs_root, &zswap_pool_limit_hit); debugfs_create_u64("reject_reclaim_fail", 0444, zswap_debugfs_root, &zswap_reject_reclaim_fail); debugfs_create_u64("reject_alloc_fail", 0444, zswap_debugfs_root, &zswap_reject_alloc_fail); debugfs_create_u64("reject_kmemcache_fail", 0444, zswap_debugfs_root, &zswap_reject_kmemcache_fail); debugfs_create_u64("reject_compress_fail", 0444, zswap_debugfs_root, &zswap_reject_compress_fail); debugfs_create_u64("reject_compress_poor", 0444, zswap_debugfs_root, &zswap_reject_compress_poor); debugfs_create_u64("decompress_fail", 0444, zswap_debugfs_root, &zswap_decompress_fail); debugfs_create_u64("written_back_pages", 0444, zswap_debugfs_root, &zswap_written_back_pages); debugfs_create_file("pool_total_size", 0444, zswap_debugfs_root, NULL, &total_size_fops); debugfs_create_file("stored_pages", 0444, zswap_debugfs_root, NULL, &stored_pages_fops); debugfs_create_file("stored_incompressible_pages", 0444, zswap_debugfs_root, NULL, &stored_incompressible_pages_fops); return 0; } #else static int zswap_debugfs_init(void) { return 0; } #endif /********************************* * module init and exit **********************************/ static int zswap_setup(void) { struct zswap_pool *pool; int ret; zswap_entry_cache = KMEM_CACHE(zswap_entry, 0); if (!zswap_entry_cache) { pr_err("entry cache creation failed\n"); goto cache_fail; } ret = cpuhp_setup_state_multi(CPUHP_MM_ZSWP_POOL_PREPARE, "mm/zswap_pool:prepare", zswap_cpu_comp_prepare, zswap_cpu_comp_dead); if (ret) goto hp_fail; shrink_wq = alloc_workqueue("zswap-shrink", WQ_UNBOUND|WQ_MEM_RECLAIM, 1); if (!shrink_wq) goto shrink_wq_fail; zswap_shrinker = zswap_alloc_shrinker(); if (!zswap_shrinker) goto shrinker_fail; if (list_lru_init_memcg(&zswap_list_lru, zswap_shrinker)) goto lru_fail; shrinker_register(zswap_shrinker); INIT_WORK(&zswap_shrink_work, shrink_worker); pool = __zswap_pool_create_fallback(); if (pool) { pr_info("loaded using pool %s\n", pool->tfm_name); list_add(&pool->list, &zswap_pools); zswap_has_pool = true; static_branch_enable(&zswap_ever_enabled); } else { pr_err("pool creation failed\n"); zswap_enabled = false; } if (zswap_debugfs_init()) pr_warn("debugfs initialization failed\n"); zswap_init_state = ZSWAP_INIT_SUCCEED; return 0; lru_fail: shrinker_free(zswap_shrinker); shrinker_fail: destroy_workqueue(shrink_wq); shrink_wq_fail: cpuhp_remove_multi_state(CPUHP_MM_ZSWP_POOL_PREPARE); hp_fail: kmem_cache_destroy(zswap_entry_cache); cache_fail: /* if built-in, we aren't unloaded on failure; don't allow use */ zswap_init_state = ZSWAP_INIT_FAILED; zswap_enabled = false; return -ENOMEM; } static int __init zswap_init(void) { if (!zswap_enabled) return 0; return zswap_setup(); } /* must be late so crypto has time to come up */ late_initcall(zswap_init); MODULE_AUTHOR("Seth Jennings <sjennings@variantweb.net>"); MODULE_DESCRIPTION("Compressed cache for swap pages"); |
| 353 326 154 198 140 125 64 116 42 221 152 154 138 198 206 2 1 125 600 4 10 15 598 | 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 #include <net/tcp.h> /* The bandwidth estimator estimates the rate at which the network * can currently deliver outbound data packets for this flow. At a high * level, it operates by taking a delivery rate sample for each ACK. * * A rate sample records the rate at which the network delivered packets * for this flow, calculated over the time interval between the transmission * of a data packet and the acknowledgment of that packet. * * Specifically, over the interval between each transmit and corresponding ACK, * the estimator generates a delivery rate sample. Typically it uses the rate * at which packets were acknowledged. However, the approach of using only the * acknowledgment rate faces a challenge under the prevalent ACK decimation or * compression: packets can temporarily appear to be delivered much quicker * than the bottleneck rate. Since it is physically impossible to do that in a * sustained fashion, when the estimator notices that the ACK rate is faster * than the transmit rate, it uses the latter: * * send_rate = #pkts_delivered/(last_snd_time - first_snd_time) * ack_rate = #pkts_delivered/(last_ack_time - first_ack_time) * bw = min(send_rate, ack_rate) * * Notice the estimator essentially estimates the goodput, not always the * network bottleneck link rate when the sending or receiving is limited by * other factors like applications or receiver window limits. The estimator * deliberately avoids using the inter-packet spacing approach because that * approach requires a large number of samples and sophisticated filtering. * * TCP flows can often be application-limited in request/response workloads. * The estimator marks a bandwidth sample as application-limited if there * was some moment during the sampled window of packets when there was no data * ready to send in the write queue. */ /* Snapshot the current delivery information in the skb, to generate * a rate sample later when the skb is (s)acked in tcp_rate_skb_delivered(). */ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); /* In general we need to start delivery rate samples from the * time we received the most recent ACK, to ensure we include * the full time the network needs to deliver all in-flight * packets. If there are no packets in flight yet, then we * know that any ACKs after now indicate that the network was * able to deliver those packets completely in the sampling * interval between now and the next ACK. * * Note that we use packets_out instead of tcp_packets_in_flight(tp) * because the latter is a guess based on RTO and loss-marking * heuristics. We don't want spurious RTOs or loss markings to cause * a spuriously small time interval, causing a spuriously high * bandwidth estimate. */ if (!tp->packets_out) { u64 tstamp_us = tcp_skb_timestamp_us(skb); tp->first_tx_mstamp = tstamp_us; tp->delivered_mstamp = tstamp_us; } TCP_SKB_CB(skb)->tx.first_tx_mstamp = tp->first_tx_mstamp; TCP_SKB_CB(skb)->tx.delivered_mstamp = tp->delivered_mstamp; TCP_SKB_CB(skb)->tx.delivered = tp->delivered; TCP_SKB_CB(skb)->tx.delivered_ce = tp->delivered_ce; TCP_SKB_CB(skb)->tx.is_app_limited = tp->app_limited ? 1 : 0; } /* When an skb is sacked or acked, we fill in the rate sample with the (prior) * delivery information when the skb was last transmitted. * * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is * called multiple times. We favor the information from the most recently * sent skb, i.e., the skb with the most recently sent time and the highest * sequence. */ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); u64 tx_tstamp; if (!scb->tx.delivered_mstamp) return; tx_tstamp = tcp_skb_timestamp_us(skb); if (!rs->prior_delivered || tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp, scb->end_seq, rs->last_end_seq)) { rs->prior_delivered_ce = scb->tx.delivered_ce; rs->prior_delivered = scb->tx.delivered; rs->prior_mstamp = scb->tx.delivered_mstamp; rs->is_app_limited = scb->tx.is_app_limited; rs->is_retrans = scb->sacked & TCPCB_RETRANS; rs->last_end_seq = scb->end_seq; /* Record send time of most recently ACKed packet: */ tp->first_tx_mstamp = tx_tstamp; /* Find the duration of the "send phase" of this window: */ rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp, scb->tx.first_tx_mstamp); } /* Mark off the skb delivered once it's sacked to avoid being * used again when it's cumulatively acked. For acked packets * we don't need to reset since it'll be freed soon. */ if (scb->sacked & TCPCB_SACKED_ACKED) scb->tx.delivered_mstamp = 0; } /* Update the connection delivery information and generate a rate sample. */ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); u32 snd_us, ack_us; /* Clear app limited if bubble is acked and gone. */ if (tp->app_limited && after(tp->delivered, tp->app_limited)) tp->app_limited = 0; /* TODO: there are multiple places throughout tcp_ack() to get * current time. Refactor the code using a new "tcp_acktag_state" * to carry current time, flags, stats like "tcp_sacktag_state". */ if (delivered) tp->delivered_mstamp = tp->tcp_mstamp; rs->acked_sacked = delivered; /* freshly ACKed or SACKed */ rs->losses = lost; /* freshly marked lost */ /* Return an invalid sample if no timing information is available or * in recovery from loss with SACK reneging. Rate samples taken during * a SACK reneging event may overestimate bw by including packets that * were SACKed before the reneg. */ if (!rs->prior_mstamp || is_sack_reneg) { rs->delivered = -1; rs->interval_us = -1; return; } rs->delivered = tp->delivered - rs->prior_delivered; rs->delivered_ce = tp->delivered_ce - rs->prior_delivered_ce; /* delivered_ce occupies less than 32 bits in the skb control block */ rs->delivered_ce &= TCPCB_DELIVERED_CE_MASK; /* Model sending data and receiving ACKs as separate pipeline phases * for a window. Usually the ACK phase is longer, but with ACK * compression the send phase can be longer. To be safe we use the * longer phase. */ snd_us = rs->interval_us; /* send phase */ ack_us = tcp_stamp_us_delta(tp->tcp_mstamp, rs->prior_mstamp); /* ack phase */ rs->interval_us = max(snd_us, ack_us); /* Record both segment send and ack receive intervals */ rs->snd_interval_us = snd_us; rs->rcv_interval_us = ack_us; /* Normally we expect interval_us >= min-rtt. * Note that rate may still be over-estimated when a spuriously * retransmistted skb was first (s)acked because "interval_us" * is under-estimated (up to an RTT). However continuously * measuring the delivery rate during loss recovery is crucial * for connections suffer heavy or prolonged losses. */ if (unlikely(rs->interval_us < tcp_min_rtt(tp))) { if (!rs->is_retrans) pr_debug("tcp rate: %ld %d %u %u %u\n", rs->interval_us, rs->delivered, inet_csk(sk)->icsk_ca_state, tp->rx_opt.sack_ok, tcp_min_rtt(tp)); rs->interval_us = -1; return; } /* Record the last non-app-limited or the highest app-limited bw */ if (!rs->is_app_limited || ((u64)rs->delivered * tp->rate_interval_us >= (u64)tp->rate_delivered * rs->interval_us)) { tp->rate_delivered = rs->delivered; tp->rate_interval_us = rs->interval_us; tp->rate_app_limited = rs->is_app_limited; } } /* If a gap is detected between sends, mark the socket application-limited. */ void tcp_rate_check_app_limited(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (/* We have less than one packet to send. */ tp->write_seq - tp->snd_nxt < tp->mss_cache && /* Nothing in sending host's qdisc queues or NIC tx queue. */ sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) && /* We are not limited by CWND. */ tcp_packets_in_flight(tp) < tcp_snd_cwnd(tp) && /* All lost packets have been retransmitted. */ tp->lost_out <= tp->retrans_out) tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; } EXPORT_SYMBOL_GPL(tcp_rate_check_app_limited); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file define the new driver API for Wireless Extensions * * Version : 8 16.3.07 * * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 2001-2007 Jean Tourrilhes, All Rights Reserved. */ #ifndef _IW_HANDLER_H #define _IW_HANDLER_H /************************** DOCUMENTATION **************************/ /* * Initial driver API (1996 -> onward) : * ----------------------------------- * The initial API just sends the IOCTL request received from user space * to the driver (via the driver ioctl handler). The driver has to * handle all the rest... * * The initial API also defines a specific handler in struct net_device * to handle wireless statistics. * * The initial APIs served us well and has proven a reasonably good design. * However, there are a few shortcomings : * o No events, everything is a request to the driver. * o Large ioctl function in driver with gigantic switch statement * (i.e. spaghetti code). * o Driver has to mess up with copy_to/from_user, and in many cases * does it unproperly. Common mistakes are : * * buffer overflows (no checks or off by one checks) * * call copy_to/from_user with irq disabled * o The user space interface is tied to ioctl because of the use * copy_to/from_user. * * New driver API (2002 -> onward) : * ------------------------------- * The new driver API is just a bunch of standard functions (handlers), * each handling a specific Wireless Extension. The driver just export * the list of handler it supports, and those will be called appropriately. * * I tried to keep the main advantage of the previous API (simplicity, * efficiency and light weight), and also I provide a good dose of backward * compatibility (most structures are the same, driver can use both API * simultaneously, ...). * Hopefully, I've also addressed the shortcoming of the initial API. * * The advantage of the new API are : * o Handling of Extensions in driver broken in small contained functions * o Tighter checks of ioctl before calling the driver * o Flexible commit strategy (at least, the start of it) * o Backward compatibility (can be mixed with old API) * o Driver doesn't have to worry about memory and user-space issues * The last point is important for the following reasons : * o You are now able to call the new driver API from any API you * want (including from within other parts of the kernel). * o Common mistakes are avoided (buffer overflow, user space copy * with irq disabled and so on). * * The Drawback of the new API are : * o bloat (especially kernel) * o need to migrate existing drivers to new API * My initial testing shows that the new API adds around 3kB to the kernel * and save between 0 and 5kB from a typical driver. * Also, as all structures and data types are unchanged, the migration is * quite straightforward (but tedious). * * --- * * The new driver API is defined below in this file. User space should * not be aware of what's happening down there... * * A new kernel wrapper is in charge of validating the IOCTLs and calling * the appropriate driver handler. This is implemented in : * # net/core/wireless.c * * The driver export the list of handlers in : * # include/linux/netdevice.h (one place) * * The new driver API is available for WIRELESS_EXT >= 13. * Good luck with migration to the new API ;-) */ /* ---------------------- THE IMPLEMENTATION ---------------------- */ /* * Some of the choice I've made are pretty controversial. Defining an * API is very much weighting compromises. This goes into some of the * details and the thinking behind the implementation. * * Implementation goals : * -------------------- * The implementation goals were as follow : * o Obvious : you should not need a PhD to understand what's happening, * the benefit is easier maintenance. * o Flexible : it should accommodate a wide variety of driver * implementations and be as flexible as the old API. * o Lean : it should be efficient memory wise to minimise the impact * on kernel footprint. * o Transparent to user space : the large number of user space * applications that use Wireless Extensions should not need * any modifications. * * Array of functions versus Struct of functions * --------------------------------------------- * 1) Having an array of functions allow the kernel code to access the * handler in a single lookup, which is much more efficient (think hash * table here). * 2) The only drawback is that driver writer may put their handler in * the wrong slot. This is trivial to test (I set the frequency, the * bitrate changes). Once the handler is in the proper slot, it will be * there forever, because the array is only extended at the end. * 3) Backward/forward compatibility : adding new handler just require * extending the array, so you can put newer driver in older kernel * without having to patch the kernel code (and vice versa). * * All handler are of the same generic type * ---------------------------------------- * That's a feature !!! * 1) Having a generic handler allow to have generic code, which is more * efficient. If each of the handler was individually typed I would need * to add a big switch in the kernel (== more bloat). This solution is * more scalable, adding new Wireless Extensions doesn't add new code. * 2) You can use the same handler in different slots of the array. For * hardware, it may be more efficient or logical to handle multiple * Wireless Extensions with a single function, and the API allow you to * do that. (An example would be a single record on the card to control * both bitrate and frequency, the handler would read the old record, * modify it according to info->cmd and rewrite it). * * Functions prototype uses union iwreq_data * ----------------------------------------- * Some would have preferred functions defined this way : * static int mydriver_ioctl_setrate(struct net_device *dev, * long rate, int auto) * 1) The kernel code doesn't "validate" the content of iwreq_data, and * can't do it (different hardware may have different notion of what a * valid frequency is), so we don't pretend that we do it. * 2) The above form is not extendable. If I want to add a flag (for * example to distinguish setting max rate and basic rate), I would * break the prototype. Using iwreq_data is more flexible. * 3) Also, the above form is not generic (see above). * 4) I don't expect driver developer using the wrong field of the * union (Doh !), so static typechecking doesn't add much value. * 5) Lastly, you can skip the union by doing : * static int mydriver_ioctl_setrate(struct net_device *dev, * struct iw_request_info *info, * struct iw_param *rrq, * char *extra) * And then adding the handler in the array like this : * (iw_handler) mydriver_ioctl_setrate, // SIOCSIWRATE * * Using functions and not a registry * ---------------------------------- * Another implementation option would have been for every instance to * define a registry (a struct containing all the Wireless Extensions) * and only have a function to commit the registry to the hardware. * 1) This approach can be emulated by the current code, but not * vice versa. * 2) Some drivers don't keep any configuration in the driver, for them * adding such a registry would be a significant bloat. * 3) The code to translate from Wireless Extension to native format is * needed anyway, so it would not reduce significantely the amount of code. * 4) The current approach only selectively translate Wireless Extensions * to native format and only selectively set, whereas the registry approach * would require to translate all WE and set all parameters for any single * change. * 5) For many Wireless Extensions, the GET operation return the current * dynamic value, not the value that was set. * * This header is <net/iw_handler.h> * --------------------------------- * 1) This header is kernel space only and should not be exported to * user space. Headers in "include/linux/" are exported, headers in * "include/net/" are not. * * Mixed 32/64 bit issues * ---------------------- * The Wireless Extensions are designed to be 64 bit clean, by using only * datatypes with explicit storage size. * There are some issues related to kernel and user space using different * memory model, and in particular 64bit kernel with 32bit user space. * The problem is related to struct iw_point, that contains a pointer * that *may* need to be translated. * This is quite messy. The new API doesn't solve this problem (it can't), * but is a step in the right direction : * 1) Meta data about each ioctl is easily available, so we know what type * of translation is needed. * 2) The move of data between kernel and user space is only done in a single * place in the kernel, so adding specific hooks in there is possible. * 3) In the long term, it allows to move away from using ioctl as the * user space API. * * So many comments and so few code * -------------------------------- * That's a feature. Comments won't bloat the resulting kernel binary. */ /***************************** INCLUDES *****************************/ #include <linux/wireless.h> /* IOCTL user space API */ #include <linux/if_ether.h> /***************************** VERSION *****************************/ /* * This constant is used to know which version of the driver API is * available. Hopefully, this will be pretty stable and no changes * will be needed... * I just plan to increment with each new version. */ #define IW_HANDLER_VERSION 8 /* * Changes : * * V2 to V3 * -------- * - Move event definition in <linux/wireless.h> * - Add Wireless Event support : * o wireless_send_event() prototype * o iwe_stream_add_event/point() inline functions * V3 to V4 * -------- * - Reshuffle IW_HEADER_TYPE_XXX to map IW_PRIV_TYPE_XXX changes * * V4 to V5 * -------- * - Add new spy support : struct iw_spy_data & prototypes * * V5 to V6 * -------- * - Change the way we get to spy_data method for added safety * - Remove spy #ifdef, they are always on -> cleaner code * - Add IW_DESCR_FLAG_NOMAX flag for very large requests * - Start migrating get_wireless_stats to struct iw_handler_def * * V6 to V7 * -------- * - Add struct ieee80211_device pointer in struct iw_public_data * - Remove (struct iw_point *)->pointer from events and streams * - Remove spy_offset from struct iw_handler_def * - Add "check" version of event macros for ieee802.11 stack * * V7 to V8 * ---------- * - Prevent leaking of kernel space in stream on 64 bits. */ /**************************** CONSTANTS ****************************/ /* Enhanced spy support available */ #define IW_WIRELESS_SPY #define IW_WIRELESS_THRSPY /* Special error message for the driver to indicate that we * should do a commit after return from the iw_handler */ #define EIWCOMMIT EINPROGRESS /* Flags available in struct iw_request_info */ #define IW_REQUEST_FLAG_COMPAT 0x0001 /* Compat ioctl call */ /* Type of headers we know about (basically union iwreq_data) */ #define IW_HEADER_TYPE_NULL 0 /* Not available */ #define IW_HEADER_TYPE_CHAR 2 /* char [IFNAMSIZ] */ #define IW_HEADER_TYPE_UINT 4 /* __u32 */ #define IW_HEADER_TYPE_FREQ 5 /* struct iw_freq */ #define IW_HEADER_TYPE_ADDR 6 /* struct sockaddr */ #define IW_HEADER_TYPE_POINT 8 /* struct iw_point */ #define IW_HEADER_TYPE_PARAM 9 /* struct iw_param */ #define IW_HEADER_TYPE_QUAL 10 /* struct iw_quality */ /* Handling flags */ /* Most are not implemented. I just use them as a reminder of some * cool features we might need one day ;-) */ #define IW_DESCR_FLAG_NONE 0x0000 /* Obvious */ /* Wrapper level flags */ #define IW_DESCR_FLAG_DUMP 0x0001 /* Not part of the dump command */ #define IW_DESCR_FLAG_EVENT 0x0002 /* Generate an event on SET */ #define IW_DESCR_FLAG_RESTRICT 0x0004 /* GET : request is ROOT only */ /* SET : Omit payload from generated iwevent */ #define IW_DESCR_FLAG_NOMAX 0x0008 /* GET : no limit on request size */ /****************************** TYPES ******************************/ /* ----------------------- WIRELESS HANDLER ----------------------- */ /* * A wireless handler is just a standard function, that looks like the * ioctl handler. * We also define there how a handler list look like... As the Wireless * Extension space is quite dense, we use a simple array, which is faster * (that's the perfect hash table ;-). */ /* * Meta data about the request passed to the iw_handler. * Most handlers can safely ignore what's in there. * The 'cmd' field might come handy if you want to use the same handler * for multiple command... * This struct is also my long term insurance. I can add new fields here * without breaking the prototype of iw_handler... */ struct iw_request_info { __u16 cmd; /* Wireless Extension command */ __u16 flags; /* More to come ;-) */ }; struct net_device; /* * This is how a function handling a Wireless Extension should look * like (both get and set, standard and private). */ typedef int (*iw_handler)(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra); /* * This define all the handler that the driver export. * As you need only one per driver type, please use a static const * shared by all driver instances... Same for the members... * This will be linked from net_device in <linux/netdevice.h> */ struct iw_handler_def { /* Array of handlers for standard ioctls * We will call dev->wireless_handlers->standard[ioctl - SIOCIWFIRST] */ const iw_handler * standard; /* Number of handlers defined (more precisely, index of the * last defined handler + 1) */ __u16 num_standard; #ifdef CONFIG_WEXT_PRIV __u16 num_private; /* Number of private arg description */ __u16 num_private_args; /* Array of handlers for private ioctls * Will call dev->wireless_handlers->private[ioctl - SIOCIWFIRSTPRIV] */ const iw_handler * private; /* Arguments of private handler. This one is just a list, so you * can put it in any order you want and should not leave holes... * We will automatically export that to user space... */ const struct iw_priv_args * private_args; #endif /* New location of get_wireless_stats, to de-bloat struct net_device. * The old pointer in struct net_device will be gradually phased * out, and drivers are encouraged to use this one... */ struct iw_statistics* (*get_wireless_stats)(struct net_device *dev); }; /* ---------------------- IOCTL DESCRIPTION ---------------------- */ /* * One of the main goal of the new interface is to deal entirely with * user space/kernel space memory move. * For that, we need to know : * o if iwreq is a pointer or contain the full data * o what is the size of the data to copy * * For private IOCTLs, we use the same rules as used by iwpriv and * defined in struct iw_priv_args. * * For standard IOCTLs, things are quite different and we need to * use the structures below. Actually, this struct is also more * efficient, but that's another story... */ /* * Describe how a standard IOCTL looks like. */ struct iw_ioctl_description { __u8 header_type; /* NULL, iw_point or other */ __u8 flags; /* Special handling of the request */ __u16 token_size; /* Granularity of payload */ __u16 min_tokens; /* Min acceptable token number */ __u16 max_tokens; /* Max acceptable token number */ }; /* Need to think of short header translation table. Later. */ /* --------------------- ENHANCED SPY SUPPORT --------------------- */ /* * In the old days, the driver was handling spy support all by itself. * Now, the driver can delegate this task to Wireless Extensions. * It needs to include this struct in its private part and use the * standard spy iw_handler. */ /* * Instance specific spy data, i.e. addresses spied and quality for them. */ struct iw_spy_data { /* --- Standard spy support --- */ int spy_number; u_char spy_address[IW_MAX_SPY][ETH_ALEN]; struct iw_quality spy_stat[IW_MAX_SPY]; /* --- Enhanced spy support (event) */ struct iw_quality spy_thr_low; /* Low threshold */ struct iw_quality spy_thr_high; /* High threshold */ u_char spy_thr_under[IW_MAX_SPY]; }; /**************************** PROTOTYPES ****************************/ /* * Functions part of the Wireless Extensions (defined in net/wireless/wext-core.c). * Those may be called by driver modules. */ /* Send a single event to user space */ void wireless_send_event(struct net_device *dev, unsigned int cmd, union iwreq_data *wrqu, const char *extra); #ifdef CONFIG_WEXT_CORE /* flush all previous wext events - if work is done from netdev notifiers */ void wireless_nlevent_flush(void); #else static inline void wireless_nlevent_flush(void) {} #endif /* We may need a function to send a stream of events to user space. * More on that later... */ /************************* INLINE FUNCTIONS *************************/ /* * Function that are so simple that it's more efficient inlining them */ static inline int iwe_stream_lcp_len(struct iw_request_info *info) { #ifdef CONFIG_COMPAT if (info->flags & IW_REQUEST_FLAG_COMPAT) return IW_EV_COMPAT_LCP_LEN; #endif return IW_EV_LCP_LEN; } static inline int iwe_stream_point_len(struct iw_request_info *info) { #ifdef CONFIG_COMPAT if (info->flags & IW_REQUEST_FLAG_COMPAT) return IW_EV_COMPAT_POINT_LEN; #endif return IW_EV_POINT_LEN; } static inline int iwe_stream_event_len_adjust(struct iw_request_info *info, int event_len) { #ifdef CONFIG_COMPAT if (info->flags & IW_REQUEST_FLAG_COMPAT) { event_len -= IW_EV_LCP_LEN; event_len += IW_EV_COMPAT_LCP_LEN; } #endif return event_len; } /*------------------------------------------------------------------*/ /* * Wrapper to add an Wireless Event to a stream of events. */ char *iwe_stream_add_event(struct iw_request_info *info, char *stream, char *ends, struct iw_event *iwe, int event_len); static inline char * iwe_stream_add_event_check(struct iw_request_info *info, char *stream, char *ends, struct iw_event *iwe, int event_len) { char *res = iwe_stream_add_event(info, stream, ends, iwe, event_len); if (res == stream) return ERR_PTR(-E2BIG); return res; } /*------------------------------------------------------------------*/ /* * Wrapper to add an short Wireless Event containing a pointer to a * stream of events. */ char *iwe_stream_add_point(struct iw_request_info *info, char *stream, char *ends, struct iw_event *iwe, char *extra); static inline char * iwe_stream_add_point_check(struct iw_request_info *info, char *stream, char *ends, struct iw_event *iwe, char *extra) { char *res = iwe_stream_add_point(info, stream, ends, iwe, extra); if (res == stream) return ERR_PTR(-E2BIG); return res; } /*------------------------------------------------------------------*/ /* * Wrapper to add a value to a Wireless Event in a stream of events. * Be careful, this one is tricky to use properly : * At the first run, you need to have (value = event + IW_EV_LCP_LEN). */ char *iwe_stream_add_value(struct iw_request_info *info, char *event, char *value, char *ends, struct iw_event *iwe, int event_len); #endif /* _IW_HANDLER_H */ |
| 1 1 1 1 1 1 1 1 1 1 13 13 9 4 7 7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2019 Mellanox Technologies. All rights reserved. */ #include <rdma/ib_verbs.h> #include <rdma/rdma_counter.h> #include "core_priv.h" #include "restrack.h" #define ALL_AUTO_MODE_MASKS (RDMA_COUNTER_MASK_QP_TYPE | RDMA_COUNTER_MASK_PID) static int __counter_set_mode(struct rdma_port_counter *port_counter, enum rdma_nl_counter_mode new_mode, enum rdma_nl_counter_mask new_mask, bool bind_opcnt) { if (new_mode == RDMA_COUNTER_MODE_AUTO) { if (new_mask & (~ALL_AUTO_MODE_MASKS)) return -EINVAL; if (port_counter->num_counters) return -EBUSY; } port_counter->mode.mode = new_mode; port_counter->mode.mask = new_mask; port_counter->mode.bind_opcnt = bind_opcnt; return 0; } /* * rdma_counter_set_auto_mode() - Turn on/off per-port auto mode * * @dev: Device to operate * @port: Port to use * @mask: Mask to configure * @extack: Message to the user * * Return 0 on success. If counter mode wasn't changed then it is considered * as success as well. * Return -EBUSY when changing to auto mode while there are bounded counters. * */ int rdma_counter_set_auto_mode(struct ib_device *dev, u32 port, enum rdma_nl_counter_mask mask, bool bind_opcnt, struct netlink_ext_ack *extack) { struct rdma_port_counter *port_counter; enum rdma_nl_counter_mode mode; int ret; port_counter = &dev->port_data[port].port_counter; if (!port_counter->hstats) return -EOPNOTSUPP; mutex_lock(&port_counter->lock); if (mask) mode = RDMA_COUNTER_MODE_AUTO; else mode = (port_counter->num_counters) ? RDMA_COUNTER_MODE_MANUAL : RDMA_COUNTER_MODE_NONE; if (port_counter->mode.mode == mode && port_counter->mode.mask == mask && port_counter->mode.bind_opcnt == bind_opcnt) { ret = 0; goto out; } ret = __counter_set_mode(port_counter, mode, mask, bind_opcnt); out: mutex_unlock(&port_counter->lock); if (ret == -EBUSY) NL_SET_ERR_MSG( extack, "Modifying auto mode is not allowed when there is a bound QP"); return ret; } static void auto_mode_init_counter(struct rdma_counter *counter, const struct ib_qp *qp, enum rdma_nl_counter_mask new_mask) { struct auto_mode_param *param = &counter->mode.param; counter->mode.mode = RDMA_COUNTER_MODE_AUTO; counter->mode.mask = new_mask; if (new_mask & RDMA_COUNTER_MASK_QP_TYPE) param->qp_type = qp->qp_type; } static int __rdma_counter_bind_qp(struct rdma_counter *counter, struct ib_qp *qp, u32 port) { int ret; if (qp->counter) return -EINVAL; if (!qp->device->ops.counter_bind_qp) return -EOPNOTSUPP; mutex_lock(&counter->lock); ret = qp->device->ops.counter_bind_qp(counter, qp, port); mutex_unlock(&counter->lock); return ret; } int rdma_counter_modify(struct ib_device *dev, u32 port, unsigned int index, bool enable) { struct rdma_hw_stats *stats; int ret = 0; if (!dev->ops.modify_hw_stat) return -EOPNOTSUPP; stats = ib_get_hw_stats_port(dev, port); if (!stats || index >= stats->num_counters || !(stats->descs[index].flags & IB_STAT_FLAG_OPTIONAL)) return -EINVAL; mutex_lock(&stats->lock); if (enable != test_bit(index, stats->is_disabled)) goto out; ret = dev->ops.modify_hw_stat(dev, port, index, enable); if (ret) goto out; if (enable) clear_bit(index, stats->is_disabled); else set_bit(index, stats->is_disabled); out: mutex_unlock(&stats->lock); return ret; } static struct rdma_counter *alloc_and_bind(struct ib_device *dev, u32 port, struct ib_qp *qp, enum rdma_nl_counter_mode mode, bool bind_opcnt) { struct rdma_port_counter *port_counter; struct rdma_counter *counter; int ret; if (!dev->ops.counter_dealloc || !dev->ops.counter_alloc_stats) return NULL; counter = rdma_zalloc_drv_obj(dev, rdma_counter); if (!counter) return NULL; counter->device = dev; counter->port = port; dev->ops.counter_init(counter); rdma_restrack_new(&counter->res, RDMA_RESTRACK_COUNTER); counter->stats = dev->ops.counter_alloc_stats(counter); if (!counter->stats) goto err_stats; port_counter = &dev->port_data[port].port_counter; mutex_lock(&port_counter->lock); switch (mode) { case RDMA_COUNTER_MODE_MANUAL: ret = __counter_set_mode(port_counter, RDMA_COUNTER_MODE_MANUAL, 0, bind_opcnt); if (ret) { mutex_unlock(&port_counter->lock); goto err_mode; } break; case RDMA_COUNTER_MODE_AUTO: auto_mode_init_counter(counter, qp, port_counter->mode.mask); break; default: ret = -EOPNOTSUPP; mutex_unlock(&port_counter->lock); goto err_mode; } port_counter->num_counters++; mutex_unlock(&port_counter->lock); counter->mode.mode = mode; counter->mode.bind_opcnt = bind_opcnt; kref_init(&counter->kref); mutex_init(&counter->lock); ret = __rdma_counter_bind_qp(counter, qp, port); if (ret) goto err_mode; rdma_restrack_parent_name(&counter->res, &qp->res); rdma_restrack_add(&counter->res); return counter; err_mode: rdma_free_hw_stats_struct(counter->stats); err_stats: rdma_restrack_put(&counter->res); kfree(counter); return NULL; } static void rdma_counter_free(struct rdma_counter *counter) { struct rdma_port_counter *port_counter; port_counter = &counter->device->port_data[counter->port].port_counter; mutex_lock(&port_counter->lock); port_counter->num_counters--; if (!port_counter->num_counters && (port_counter->mode.mode == RDMA_COUNTER_MODE_MANUAL)) __counter_set_mode(port_counter, RDMA_COUNTER_MODE_NONE, 0, false); mutex_unlock(&port_counter->lock); rdma_restrack_del(&counter->res); rdma_free_hw_stats_struct(counter->stats); kfree(counter); } static bool auto_mode_match(struct ib_qp *qp, struct rdma_counter *counter, enum rdma_nl_counter_mask auto_mask) { struct auto_mode_param *param = &counter->mode.param; bool match = true; if (auto_mask & RDMA_COUNTER_MASK_QP_TYPE) match &= (param->qp_type == qp->qp_type); if (auto_mask & RDMA_COUNTER_MASK_PID) match &= (task_pid_nr(counter->res.task) == task_pid_nr(qp->res.task)); return match; } static int __rdma_counter_unbind_qp(struct ib_qp *qp, u32 port) { struct rdma_counter *counter = qp->counter; int ret; if (!qp->device->ops.counter_unbind_qp) return -EOPNOTSUPP; mutex_lock(&counter->lock); ret = qp->device->ops.counter_unbind_qp(qp, port); mutex_unlock(&counter->lock); return ret; } static void counter_history_stat_update(struct rdma_counter *counter) { struct ib_device *dev = counter->device; struct rdma_port_counter *port_counter; int i; port_counter = &dev->port_data[counter->port].port_counter; if (!port_counter->hstats) return; rdma_counter_query_stats(counter); for (i = 0; i < counter->stats->num_counters; i++) port_counter->hstats->value[i] += counter->stats->value[i]; } /* * rdma_get_counter_auto_mode - Find the counter that @qp should be bound * with in auto mode * * Return: The counter (with ref-count increased) if found */ static struct rdma_counter *rdma_get_counter_auto_mode(struct ib_qp *qp, u32 port) { struct rdma_port_counter *port_counter; struct rdma_counter *counter = NULL; struct ib_device *dev = qp->device; struct rdma_restrack_entry *res; struct rdma_restrack_root *rt; unsigned long id = 0; port_counter = &dev->port_data[port].port_counter; rt = &dev->res[RDMA_RESTRACK_COUNTER]; xa_lock(&rt->xa); xa_for_each(&rt->xa, id, res) { counter = container_of(res, struct rdma_counter, res); if ((counter->device != qp->device) || (counter->port != port)) goto next; if (auto_mode_match(qp, counter, port_counter->mode.mask)) break; next: counter = NULL; } if (counter && !kref_get_unless_zero(&counter->kref)) counter = NULL; xa_unlock(&rt->xa); return counter; } static void counter_release(struct kref *kref) { struct rdma_counter *counter; counter = container_of(kref, struct rdma_counter, kref); counter_history_stat_update(counter); counter->device->ops.counter_dealloc(counter); rdma_counter_free(counter); } /* * rdma_counter_bind_qp_auto - Check and bind the QP to a counter base on * the auto-mode rule */ int rdma_counter_bind_qp_auto(struct ib_qp *qp, u32 port) { struct rdma_port_counter *port_counter; struct ib_device *dev = qp->device; struct rdma_counter *counter; int ret; if (!rdma_restrack_is_tracked(&qp->res) || rdma_is_kernel_res(&qp->res)) return 0; if (!rdma_is_port_valid(dev, port)) return -EINVAL; port_counter = &dev->port_data[port].port_counter; if (port_counter->mode.mode != RDMA_COUNTER_MODE_AUTO) return 0; counter = rdma_get_counter_auto_mode(qp, port); if (counter) { ret = __rdma_counter_bind_qp(counter, qp, port); if (ret) { kref_put(&counter->kref, counter_release); return ret; } } else { counter = alloc_and_bind(dev, port, qp, RDMA_COUNTER_MODE_AUTO, port_counter->mode.bind_opcnt); if (!counter) return -ENOMEM; } return 0; } /* * rdma_counter_unbind_qp - Unbind a qp from a counter * @force: * true - Decrease the counter ref-count anyway (e.g., qp destroy) */ int rdma_counter_unbind_qp(struct ib_qp *qp, u32 port, bool force) { struct rdma_counter *counter = qp->counter; int ret; if (!counter) return -EINVAL; ret = __rdma_counter_unbind_qp(qp, port); if (ret && !force) return ret; kref_put(&counter->kref, counter_release); return 0; } int rdma_counter_query_stats(struct rdma_counter *counter) { struct ib_device *dev = counter->device; int ret; if (!dev->ops.counter_update_stats) return -EINVAL; mutex_lock(&counter->lock); ret = dev->ops.counter_update_stats(counter); mutex_unlock(&counter->lock); return ret; } static u64 get_running_counters_hwstat_sum(struct ib_device *dev, u32 port, u32 index) { struct rdma_restrack_entry *res; struct rdma_restrack_root *rt; struct rdma_counter *counter; unsigned long id = 0; u64 sum = 0; rt = &dev->res[RDMA_RESTRACK_COUNTER]; xa_lock(&rt->xa); xa_for_each(&rt->xa, id, res) { if (!rdma_restrack_get(res)) continue; xa_unlock(&rt->xa); counter = container_of(res, struct rdma_counter, res); if ((counter->device != dev) || (counter->port != port) || rdma_counter_query_stats(counter)) goto next; sum += counter->stats->value[index]; next: xa_lock(&rt->xa); rdma_restrack_put(res); } xa_unlock(&rt->xa); return sum; } /* * rdma_counter_get_hwstat_value() - Get the sum value of all counters on a * specific port, including the running ones and history data */ u64 rdma_counter_get_hwstat_value(struct ib_device *dev, u32 port, u32 index) { struct rdma_port_counter *port_counter; u64 sum; port_counter = &dev->port_data[port].port_counter; if (!port_counter->hstats) return 0; sum = get_running_counters_hwstat_sum(dev, port, index); sum += port_counter->hstats->value[index]; return sum; } static struct ib_qp *rdma_counter_get_qp(struct ib_device *dev, u32 qp_num) { struct rdma_restrack_entry *res = NULL; struct ib_qp *qp = NULL; res = rdma_restrack_get_byid(dev, RDMA_RESTRACK_QP, qp_num); if (IS_ERR(res)) return NULL; qp = container_of(res, struct ib_qp, res); if (qp->qp_type == IB_QPT_RAW_PACKET && !rdma_dev_has_raw_cap(dev)) goto err; return qp; err: rdma_restrack_put(res); return NULL; } static struct rdma_counter *rdma_get_counter_by_id(struct ib_device *dev, u32 counter_id) { struct rdma_restrack_entry *res; struct rdma_counter *counter; res = rdma_restrack_get_byid(dev, RDMA_RESTRACK_COUNTER, counter_id); if (IS_ERR(res)) return NULL; counter = container_of(res, struct rdma_counter, res); kref_get(&counter->kref); rdma_restrack_put(res); return counter; } /* * rdma_counter_bind_qpn() - Bind QP @qp_num to counter @counter_id */ int rdma_counter_bind_qpn(struct ib_device *dev, u32 port, u32 qp_num, u32 counter_id) { struct rdma_port_counter *port_counter; struct rdma_counter *counter; struct ib_qp *qp; int ret; port_counter = &dev->port_data[port].port_counter; if (port_counter->mode.mode == RDMA_COUNTER_MODE_AUTO) return -EINVAL; qp = rdma_counter_get_qp(dev, qp_num); if (!qp) return -ENOENT; counter = rdma_get_counter_by_id(dev, counter_id); if (!counter) { ret = -ENOENT; goto err; } if (rdma_is_kernel_res(&counter->res) != rdma_is_kernel_res(&qp->res)) { ret = -EINVAL; goto err_task; } if ((counter->device != qp->device) || (counter->port != qp->port)) { ret = -EINVAL; goto err_task; } ret = __rdma_counter_bind_qp(counter, qp, port); if (ret) goto err_task; rdma_restrack_put(&qp->res); return 0; err_task: kref_put(&counter->kref, counter_release); err: rdma_restrack_put(&qp->res); return ret; } /* * rdma_counter_bind_qpn_alloc() - Alloc a counter and bind QP @qp_num to it * The id of new counter is returned in @counter_id */ int rdma_counter_bind_qpn_alloc(struct ib_device *dev, u32 port, u32 qp_num, u32 *counter_id) { struct rdma_port_counter *port_counter; struct rdma_counter *counter; struct ib_qp *qp; int ret; if (!rdma_is_port_valid(dev, port)) return -EINVAL; port_counter = &dev->port_data[port].port_counter; if (!port_counter->hstats) return -EOPNOTSUPP; if (port_counter->mode.mode == RDMA_COUNTER_MODE_AUTO) return -EINVAL; qp = rdma_counter_get_qp(dev, qp_num); if (!qp) return -ENOENT; if (rdma_is_port_valid(dev, qp->port) && (qp->port != port)) { ret = -EINVAL; goto err; } counter = alloc_and_bind(dev, port, qp, RDMA_COUNTER_MODE_MANUAL, true); if (!counter) { ret = -ENOMEM; goto err; } if (counter_id) *counter_id = counter->id; rdma_restrack_put(&qp->res); return 0; err: rdma_restrack_put(&qp->res); return ret; } /* * rdma_counter_unbind_qpn() - Unbind QP @qp_num from a counter */ int rdma_counter_unbind_qpn(struct ib_device *dev, u32 port, u32 qp_num, u32 counter_id) { struct rdma_port_counter *port_counter; struct ib_qp *qp; int ret; if (!rdma_is_port_valid(dev, port)) return -EINVAL; qp = rdma_counter_get_qp(dev, qp_num); if (!qp) return -ENOENT; if (rdma_is_port_valid(dev, qp->port) && (qp->port != port)) { ret = -EINVAL; goto out; } port_counter = &dev->port_data[port].port_counter; if (!qp->counter || qp->counter->id != counter_id || port_counter->mode.mode != RDMA_COUNTER_MODE_MANUAL) { ret = -EINVAL; goto out; } ret = rdma_counter_unbind_qp(qp, port, false); out: rdma_restrack_put(&qp->res); return ret; } int rdma_counter_get_mode(struct ib_device *dev, u32 port, enum rdma_nl_counter_mode *mode, enum rdma_nl_counter_mask *mask, bool *opcnt) { struct rdma_port_counter *port_counter; port_counter = &dev->port_data[port].port_counter; *mode = port_counter->mode.mode; *mask = port_counter->mode.mask; *opcnt = port_counter->mode.bind_opcnt; return 0; } void rdma_counter_init(struct ib_device *dev) { struct rdma_port_counter *port_counter; u32 port, i; if (!dev->port_data) return; rdma_for_each_port(dev, port) { port_counter = &dev->port_data[port].port_counter; port_counter->mode.mode = RDMA_COUNTER_MODE_NONE; mutex_init(&port_counter->lock); if (!dev->ops.alloc_hw_port_stats) continue; port_counter->hstats = dev->ops.alloc_hw_port_stats(dev, port); if (!port_counter->hstats) goto fail; } return; fail: for (i = port; i >= rdma_start_port(dev); i--) { port_counter = &dev->port_data[port].port_counter; rdma_free_hw_stats_struct(port_counter->hstats); port_counter->hstats = NULL; mutex_destroy(&port_counter->lock); } } void rdma_counter_release(struct ib_device *dev) { struct rdma_port_counter *port_counter; u32 port; rdma_for_each_port(dev, port) { port_counter = &dev->port_data[port].port_counter; rdma_free_hw_stats_struct(port_counter->hstats); mutex_destroy(&port_counter->lock); } } |
| 13 13 42 42 1 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/preempt.h> #include <linux/smp.h> #include <linux/completion.h> #include <asm/msr.h> static void __rdmsr_on_cpu(void *info) { struct msr_info *rv = info; struct msr *reg; if (rv->msrs) reg = this_cpu_ptr(rv->msrs); else reg = &rv->reg; rdmsr(rv->msr_no, reg->l, reg->h); } static void __wrmsr_on_cpu(void *info) { struct msr_info *rv = info; struct msr *reg; if (rv->msrs) reg = this_cpu_ptr(rv->msrs); else reg = &rv->reg; wrmsr(rv->msr_no, reg->l, reg->h); } int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { int err; struct msr_info rv; memset(&rv, 0, sizeof(rv)); rv.msr_no = msr_no; err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1); *l = rv.reg.l; *h = rv.reg.h; return err; } EXPORT_SYMBOL(rdmsr_on_cpu); int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) { int err; struct msr_info rv; memset(&rv, 0, sizeof(rv)); rv.msr_no = msr_no; err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1); *q = rv.reg.q; return err; } EXPORT_SYMBOL(rdmsrq_on_cpu); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { int err; struct msr_info rv; memset(&rv, 0, sizeof(rv)); rv.msr_no = msr_no; rv.reg.l = l; rv.reg.h = h; err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1); return err; } EXPORT_SYMBOL(wrmsr_on_cpu); int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q) { int err; struct msr_info rv; memset(&rv, 0, sizeof(rv)); rv.msr_no = msr_no; rv.reg.q = q; err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1); return err; } EXPORT_SYMBOL(wrmsrq_on_cpu); static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs, void (*msr_func) (void *info)) { struct msr_info rv; int this_cpu; memset(&rv, 0, sizeof(rv)); rv.msrs = msrs; rv.msr_no = msr_no; this_cpu = get_cpu(); if (cpumask_test_cpu(this_cpu, mask)) msr_func(&rv); smp_call_function_many(mask, msr_func, &rv, 1); put_cpu(); } /* rdmsr on a bunch of CPUs * * @mask: which CPUs * @msr_no: which MSR * @msrs: array of MSR values * */ void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs) { __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu); } EXPORT_SYMBOL(rdmsr_on_cpus); /* * wrmsr on a bunch of CPUs * * @mask: which CPUs * @msr_no: which MSR * @msrs: array of MSR values * */ void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs) { __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu); } EXPORT_SYMBOL(wrmsr_on_cpus); struct msr_info_completion { struct msr_info msr; struct completion done; }; /* These "safe" variants are slower and should be used when the target MSR may not actually exist. */ static void __rdmsr_safe_on_cpu(void *info) { struct msr_info_completion *rv = info; rv->msr.err = rdmsr_safe(rv->msr.msr_no, &rv->msr.reg.l, &rv->msr.reg.h); complete(&rv->done); } static void __wrmsr_safe_on_cpu(void *info) { struct msr_info *rv = info; rv->err = wrmsr_safe(rv->msr_no, rv->reg.l, rv->reg.h); } int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { struct msr_info_completion rv; call_single_data_t csd; int err; INIT_CSD(&csd, __rdmsr_safe_on_cpu, &rv); memset(&rv, 0, sizeof(rv)); init_completion(&rv.done); rv.msr.msr_no = msr_no; err = smp_call_function_single_async(cpu, &csd); if (!err) { wait_for_completion(&rv.done); err = rv.msr.err; } *l = rv.msr.reg.l; *h = rv.msr.reg.h; return err; } EXPORT_SYMBOL(rdmsr_safe_on_cpu); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { int err; struct msr_info rv; memset(&rv, 0, sizeof(rv)); rv.msr_no = msr_no; rv.reg.l = l; rv.reg.h = h; err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1); return err ? err : rv.err; } EXPORT_SYMBOL(wrmsr_safe_on_cpu); int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) { int err; struct msr_info rv; memset(&rv, 0, sizeof(rv)); rv.msr_no = msr_no; rv.reg.q = q; err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1); return err ? err : rv.err; } EXPORT_SYMBOL(wrmsrq_safe_on_cpu); int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) { u32 low, high; int err; err = rdmsr_safe_on_cpu(cpu, msr_no, &low, &high); *q = (u64)high << 32 | low; return err; } EXPORT_SYMBOL(rdmsrq_safe_on_cpu); /* * These variants are significantly slower, but allows control over * the entire 32-bit GPR set. */ static void __rdmsr_safe_regs_on_cpu(void *info) { struct msr_regs_info *rv = info; rv->err = rdmsr_safe_regs(rv->regs); } static void __wrmsr_safe_regs_on_cpu(void *info) { struct msr_regs_info *rv = info; rv->err = wrmsr_safe_regs(rv->regs); } int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { int err; struct msr_regs_info rv; rv.regs = regs; rv.err = -EIO; err = smp_call_function_single(cpu, __rdmsr_safe_regs_on_cpu, &rv, 1); return err ? err : rv.err; } EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu); int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { int err; struct msr_regs_info rv; rv.regs = regs; rv.err = -EIO; err = smp_call_function_single(cpu, __wrmsr_safe_regs_on_cpu, &rv, 1); return err ? err : rv.err; } EXPORT_SYMBOL(wrmsr_safe_regs_on_cpu); |
| 12 12 12 12 12 12 11 11 11 2 2 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * vivid-kthread-out.h - video/vbi output thread support functions. * * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/font.h> #include <linux/mutex.h> #include <linux/videodev2.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/random.h> #include <linux/v4l2-dv-timings.h> #include <linux/jiffies.h> #include <asm/div64.h> #include <media/videobuf2-vmalloc.h> #include <media/v4l2-dv-timings.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-fh.h> #include <media/v4l2-event.h> #include "vivid-core.h" #include "vivid-vid-common.h" #include "vivid-vid-cap.h" #include "vivid-vid-out.h" #include "vivid-radio-common.h" #include "vivid-radio-rx.h" #include "vivid-radio-tx.h" #include "vivid-sdr-cap.h" #include "vivid-vbi-cap.h" #include "vivid-vbi-out.h" #include "vivid-osd.h" #include "vivid-ctrls.h" #include "vivid-kthread-out.h" #include "vivid-meta-out.h" static void vivid_thread_vid_out_tick(struct vivid_dev *dev) { struct vivid_buffer *vid_out_buf = NULL; struct vivid_buffer *vbi_out_buf = NULL; struct vivid_buffer *meta_out_buf = NULL; dprintk(dev, 1, "Video Output Thread Tick\n"); /* Drop a certain percentage of buffers. */ if (dev->perc_dropped_buffers && get_random_u32_below(100) < dev->perc_dropped_buffers) return; spin_lock(&dev->slock); /* * Only dequeue buffer if there is at least one more pending. * This makes video loopback possible. */ if (!list_empty(&dev->vid_out_active) && !list_is_singular(&dev->vid_out_active)) { vid_out_buf = list_entry(dev->vid_out_active.next, struct vivid_buffer, list); list_del(&vid_out_buf->list); } if (!list_empty(&dev->vbi_out_active) && (dev->field_out != V4L2_FIELD_ALTERNATE || (dev->vbi_out_seq_count & 1))) { vbi_out_buf = list_entry(dev->vbi_out_active.next, struct vivid_buffer, list); list_del(&vbi_out_buf->list); } if (!list_empty(&dev->meta_out_active)) { meta_out_buf = list_entry(dev->meta_out_active.next, struct vivid_buffer, list); list_del(&meta_out_buf->list); } spin_unlock(&dev->slock); if (!vid_out_buf && !vbi_out_buf && !meta_out_buf) return; if (vid_out_buf) { v4l2_ctrl_request_setup(vid_out_buf->vb.vb2_buf.req_obj.req, &dev->ctrl_hdl_vid_out); v4l2_ctrl_request_complete(vid_out_buf->vb.vb2_buf.req_obj.req, &dev->ctrl_hdl_vid_out); vid_out_buf->vb.sequence = dev->vid_out_seq_count; if (dev->field_out == V4L2_FIELD_ALTERNATE) { /* * The sequence counter counts frames, not fields. * So divide by two. */ vid_out_buf->vb.sequence /= 2; } vid_out_buf->vb.vb2_buf.timestamp = ktime_get_ns() + dev->time_wrap_offset; vb2_buffer_done(&vid_out_buf->vb.vb2_buf, dev->dqbuf_error ? VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE); dprintk(dev, 2, "vid_out buffer %d done\n", vid_out_buf->vb.vb2_buf.index); } if (vbi_out_buf) { v4l2_ctrl_request_setup(vbi_out_buf->vb.vb2_buf.req_obj.req, &dev->ctrl_hdl_vbi_out); v4l2_ctrl_request_complete(vbi_out_buf->vb.vb2_buf.req_obj.req, &dev->ctrl_hdl_vbi_out); if (dev->stream_sliced_vbi_out) vivid_sliced_vbi_out_process(dev, vbi_out_buf); vbi_out_buf->vb.sequence = dev->vbi_out_seq_count; vbi_out_buf->vb.vb2_buf.timestamp = ktime_get_ns() + dev->time_wrap_offset; vb2_buffer_done(&vbi_out_buf->vb.vb2_buf, dev->dqbuf_error ? VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE); dprintk(dev, 2, "vbi_out buffer %d done\n", vbi_out_buf->vb.vb2_buf.index); } if (meta_out_buf) { v4l2_ctrl_request_setup(meta_out_buf->vb.vb2_buf.req_obj.req, &dev->ctrl_hdl_meta_out); v4l2_ctrl_request_complete(meta_out_buf->vb.vb2_buf.req_obj.req, &dev->ctrl_hdl_meta_out); vivid_meta_out_process(dev, meta_out_buf); meta_out_buf->vb.sequence = dev->meta_out_seq_count; meta_out_buf->vb.vb2_buf.timestamp = ktime_get_ns() + dev->time_wrap_offset; vb2_buffer_done(&meta_out_buf->vb.vb2_buf, dev->dqbuf_error ? VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE); dprintk(dev, 2, "meta_out buffer %d done\n", meta_out_buf->vb.vb2_buf.index); } dev->dqbuf_error = false; } static int vivid_thread_vid_out(void *data) { struct vivid_dev *dev = data; u64 numerators_since_start; u64 buffers_since_start; u64 next_jiffies_since_start; unsigned long jiffies_since_start; unsigned long cur_jiffies; unsigned wait_jiffies; unsigned numerator; unsigned denominator; dprintk(dev, 1, "Video Output Thread Start\n"); set_freezable(); /* Resets frame counters */ dev->out_seq_offset = 0; dev->out_seq_count = 0; dev->jiffies_vid_out = jiffies; dev->out_seq_resync = false; if (dev->time_wrap) dev->time_wrap_offset = dev->time_wrap - ktime_get_ns(); else dev->time_wrap_offset = 0; for (;;) { try_to_freeze(); if (kthread_should_stop()) break; if (!mutex_trylock(&dev->mutex)) { schedule(); continue; } cur_jiffies = jiffies; if (dev->out_seq_resync) { dev->jiffies_vid_out = cur_jiffies; dev->out_seq_offset = dev->out_seq_count + 1; dev->out_seq_count = 0; dev->out_seq_resync = false; } numerator = dev->timeperframe_vid_out.numerator; denominator = dev->timeperframe_vid_out.denominator; if (dev->field_out == V4L2_FIELD_ALTERNATE) denominator *= 2; /* Calculate the number of jiffies since we started streaming */ jiffies_since_start = cur_jiffies - dev->jiffies_vid_out; /* Get the number of buffers streamed since the start */ buffers_since_start = (u64)jiffies_since_start * denominator + (HZ * numerator) / 2; do_div(buffers_since_start, HZ * numerator); /* * After more than 0xf0000000 (rounded down to a multiple of * 'jiffies-per-day' to ease jiffies_to_msecs calculation) * jiffies have passed since we started streaming reset the * counters and keep track of the sequence offset. */ if (jiffies_since_start > JIFFIES_RESYNC) { dev->jiffies_vid_out = cur_jiffies; dev->out_seq_offset = buffers_since_start; buffers_since_start = 0; } dev->out_seq_count = buffers_since_start + dev->out_seq_offset; dev->vid_out_seq_count = dev->out_seq_count - dev->vid_out_seq_start; dev->vbi_out_seq_count = dev->out_seq_count - dev->vbi_out_seq_start; dev->meta_out_seq_count = dev->out_seq_count - dev->meta_out_seq_start; vivid_thread_vid_out_tick(dev); mutex_unlock(&dev->mutex); /* * Calculate the number of 'numerators' streamed since we started, * not including the current buffer. */ numerators_since_start = buffers_since_start * numerator; /* And the number of jiffies since we started */ jiffies_since_start = jiffies - dev->jiffies_vid_out; /* Increase by the 'numerator' of one buffer */ numerators_since_start += numerator; /* * Calculate when that next buffer is supposed to start * in jiffies since we started streaming. */ next_jiffies_since_start = numerators_since_start * HZ + denominator / 2; do_div(next_jiffies_since_start, denominator); /* If it is in the past, then just schedule asap */ if (next_jiffies_since_start < jiffies_since_start) next_jiffies_since_start = jiffies_since_start; wait_jiffies = next_jiffies_since_start - jiffies_since_start; if (!time_is_after_jiffies(cur_jiffies + wait_jiffies)) continue; wait_queue_head_t wait; init_waitqueue_head(&wait); wait_event_interruptible_timeout(wait, kthread_should_stop(), cur_jiffies + wait_jiffies - jiffies); } dprintk(dev, 1, "Video Output Thread End\n"); return 0; } static void vivid_grab_controls(struct vivid_dev *dev, bool grab) { v4l2_ctrl_grab(dev->ctrl_has_crop_out, grab); v4l2_ctrl_grab(dev->ctrl_has_compose_out, grab); v4l2_ctrl_grab(dev->ctrl_has_scaler_out, grab); v4l2_ctrl_grab(dev->ctrl_tx_mode, grab); v4l2_ctrl_grab(dev->ctrl_tx_rgb_range, grab); } int vivid_start_generating_vid_out(struct vivid_dev *dev, bool *pstreaming) { dprintk(dev, 1, "%s\n", __func__); if (dev->kthread_vid_out) { u32 seq_count = dev->out_seq_count + dev->seq_wrap * 128; if (pstreaming == &dev->vid_out_streaming) dev->vid_out_seq_start = seq_count; else if (pstreaming == &dev->vbi_out_streaming) dev->vbi_out_seq_start = seq_count; else dev->meta_out_seq_start = seq_count; *pstreaming = true; return 0; } /* Resets frame counters */ dev->jiffies_vid_out = jiffies; dev->vid_out_seq_start = dev->seq_wrap * 128; dev->vbi_out_seq_start = dev->seq_wrap * 128; dev->meta_out_seq_start = dev->seq_wrap * 128; dev->kthread_vid_out = kthread_run(vivid_thread_vid_out, dev, "%s-vid-out", dev->v4l2_dev.name); if (IS_ERR(dev->kthread_vid_out)) { int err = PTR_ERR(dev->kthread_vid_out); dev->kthread_vid_out = NULL; v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n"); return err; } *pstreaming = true; vivid_grab_controls(dev, true); dprintk(dev, 1, "returning from %s\n", __func__); return 0; } void vivid_stop_generating_vid_out(struct vivid_dev *dev, bool *pstreaming) { dprintk(dev, 1, "%s\n", __func__); if (dev->kthread_vid_out == NULL) return; *pstreaming = false; if (pstreaming == &dev->vid_out_streaming) { /* Release all active buffers */ while (!list_empty(&dev->vid_out_active)) { struct vivid_buffer *buf; buf = list_entry(dev->vid_out_active.next, struct vivid_buffer, list); list_del(&buf->list); v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, &dev->ctrl_hdl_vid_out); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); dprintk(dev, 2, "vid_out buffer %d done\n", buf->vb.vb2_buf.index); } } if (pstreaming == &dev->vbi_out_streaming) { while (!list_empty(&dev->vbi_out_active)) { struct vivid_buffer *buf; buf = list_entry(dev->vbi_out_active.next, struct vivid_buffer, list); list_del(&buf->list); v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, &dev->ctrl_hdl_vbi_out); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); dprintk(dev, 2, "vbi_out buffer %d done\n", buf->vb.vb2_buf.index); } } if (pstreaming == &dev->meta_out_streaming) { while (!list_empty(&dev->meta_out_active)) { struct vivid_buffer *buf; buf = list_entry(dev->meta_out_active.next, struct vivid_buffer, list); list_del(&buf->list); v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, &dev->ctrl_hdl_meta_out); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); dprintk(dev, 2, "meta_out buffer %d done\n", buf->vb.vb2_buf.index); } } if (dev->vid_out_streaming || dev->vbi_out_streaming || dev->meta_out_streaming) return; /* shutdown control thread */ vivid_grab_controls(dev, false); kthread_stop(dev->kthread_vid_out); dev->kthread_vid_out = NULL; } |
| 9 9 9 9 9 9 10 10 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005-2006 Micronas USA Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/wait.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/usb.h> #include <linux/i2c.h> #include <asm/byteorder.h> #include <media/i2c/saa7115.h> #include <media/tuner.h> #include <media/i2c/uda1342.h> #include "go7007-priv.h" static unsigned int assume_endura; module_param(assume_endura, int, 0644); MODULE_PARM_DESC(assume_endura, "when probing fails, hardware is a Pelco Endura"); /* #define GO7007_I2C_DEBUG */ /* for debugging the EZ-USB I2C adapter */ #define HPI_STATUS_ADDR 0xFFF4 #define INT_PARAM_ADDR 0xFFF6 #define INT_INDEX_ADDR 0xFFF8 /* * Pipes on EZ-USB interface: * 0 snd - Control * 0 rcv - Control * 2 snd - Download firmware (control) * 4 rcv - Read Interrupt (interrupt) * 6 rcv - Read Video (bulk) * 8 rcv - Read Audio (bulk) */ #define GO7007_USB_EZUSB (1<<0) #define GO7007_USB_EZUSB_I2C (1<<1) struct go7007_usb_board { unsigned int flags; struct go7007_board_info main_info; }; struct go7007_usb { const struct go7007_usb_board *board; struct mutex i2c_lock; struct usb_device *usbdev; struct urb *video_urbs[8]; struct urb *audio_urbs[8]; struct urb *intr_urb; }; /*********************** Product specification data ***********************/ static const struct go7007_usb_board board_matrix_ii = { .flags = GO7007_USB_EZUSB, .main_info = { .flags = GO7007_BOARD_HAS_AUDIO | GO7007_BOARD_USE_ONBOARD_I2C, .audio_flags = GO7007_AUDIO_I2S_MODE_1 | GO7007_AUDIO_WORD_16, .audio_rate = 48000, .audio_bclk_div = 8, .audio_main_div = 2, .hpi_buffer_cap = 7, .sensor_flags = GO7007_SENSOR_656 | GO7007_SENSOR_VALID_ENABLE | GO7007_SENSOR_TV | GO7007_SENSOR_SAA7115 | GO7007_SENSOR_VBI | GO7007_SENSOR_SCALING, .num_i2c_devs = 1, .i2c_devs = { { .type = "saa7115", .addr = 0x20, .is_video = 1, }, }, .num_inputs = 2, .inputs = { { .video_input = 0, .name = "Composite", }, { .video_input = 9, .name = "S-Video", }, }, .video_config = SAA7115_IDQ_IS_DEFAULT, }, }; static const struct go7007_usb_board board_matrix_reload = { .flags = GO7007_USB_EZUSB, .main_info = { .flags = GO7007_BOARD_HAS_AUDIO | GO7007_BOARD_USE_ONBOARD_I2C, .audio_flags = GO7007_AUDIO_I2S_MODE_1 | GO7007_AUDIO_I2S_MASTER | GO7007_AUDIO_WORD_16, .audio_rate = 48000, .audio_bclk_div = 8, .audio_main_div = 2, .hpi_buffer_cap = 7, .sensor_flags = GO7007_SENSOR_656 | GO7007_SENSOR_TV, .num_i2c_devs = 1, .i2c_devs = { { .type = "saa7113", .addr = 0x25, .is_video = 1, }, }, .num_inputs = 2, .inputs = { { .video_input = 0, .name = "Composite", }, { .video_input = 9, .name = "S-Video", }, }, .video_config = SAA7115_IDQ_IS_DEFAULT, }, }; static const struct go7007_usb_board board_star_trek = { .flags = GO7007_USB_EZUSB | GO7007_USB_EZUSB_I2C, .main_info = { .flags = GO7007_BOARD_HAS_AUDIO, /* | GO7007_BOARD_HAS_TUNER, */ .sensor_flags = GO7007_SENSOR_656 | GO7007_SENSOR_VALID_ENABLE | GO7007_SENSOR_TV | GO7007_SENSOR_SAA7115 | GO7007_SENSOR_VBI | GO7007_SENSOR_SCALING, .audio_flags = GO7007_AUDIO_I2S_MODE_1 | GO7007_AUDIO_WORD_16, .audio_bclk_div = 8, .audio_main_div = 2, .hpi_buffer_cap = 7, .num_i2c_devs = 1, .i2c_devs = { { .type = "saa7115", .addr = 0x20, .is_video = 1, }, }, .num_inputs = 2, .inputs = { /* { * .video_input = 3, * .audio_index = AUDIO_TUNER, * .name = "Tuner", * }, */ { .video_input = 1, /* .audio_index = AUDIO_EXTERN, */ .name = "Composite", }, { .video_input = 8, /* .audio_index = AUDIO_EXTERN, */ .name = "S-Video", }, }, .video_config = SAA7115_IDQ_IS_DEFAULT, }, }; static const struct go7007_usb_board board_px_tv402u = { .flags = GO7007_USB_EZUSB | GO7007_USB_EZUSB_I2C, .main_info = { .flags = GO7007_BOARD_HAS_AUDIO | GO7007_BOARD_HAS_TUNER, .sensor_flags = GO7007_SENSOR_656 | GO7007_SENSOR_VALID_ENABLE | GO7007_SENSOR_TV | GO7007_SENSOR_SAA7115 | GO7007_SENSOR_VBI | GO7007_SENSOR_SCALING, .audio_flags = GO7007_AUDIO_I2S_MODE_1 | GO7007_AUDIO_WORD_16, .audio_bclk_div = 8, .audio_main_div = 2, .hpi_buffer_cap = 7, .num_i2c_devs = 5, .i2c_devs = { { .type = "saa7115", .addr = 0x20, .is_video = 1, }, { .type = "uda1342", .addr = 0x1a, .is_audio = 1, }, { .type = "tuner", .addr = 0x60, }, { .type = "tuner", .addr = 0x43, }, { .type = "sony-btf-mpx", .addr = 0x44, }, }, .num_inputs = 3, .inputs = { { .video_input = 3, .audio_index = 0, .name = "Tuner", }, { .video_input = 1, .audio_index = 1, .name = "Composite", }, { .video_input = 8, .audio_index = 1, .name = "S-Video", }, }, .video_config = SAA7115_IDQ_IS_DEFAULT, .num_aud_inputs = 2, .aud_inputs = { { .audio_input = UDA1342_IN2, .name = "Tuner", }, { .audio_input = UDA1342_IN1, .name = "Line In", }, }, }, }; static const struct go7007_usb_board board_xmen = { .flags = 0, .main_info = { .flags = GO7007_BOARD_USE_ONBOARD_I2C, .hpi_buffer_cap = 0, .sensor_flags = GO7007_SENSOR_VREF_POLAR, .sensor_width = 320, .sensor_height = 240, .sensor_framerate = 30030, .audio_flags = GO7007_AUDIO_ONE_CHANNEL | GO7007_AUDIO_I2S_MODE_3 | GO7007_AUDIO_WORD_14 | GO7007_AUDIO_I2S_MASTER | GO7007_AUDIO_BCLK_POLAR | GO7007_AUDIO_OKI_MODE, .audio_rate = 8000, .audio_bclk_div = 48, .audio_main_div = 1, .num_i2c_devs = 1, .i2c_devs = { { .type = "ov7640", .addr = 0x21, }, }, .num_inputs = 1, .inputs = { { .name = "Camera", }, }, }, }; static const struct go7007_usb_board board_matrix_revolution = { .flags = GO7007_USB_EZUSB, .main_info = { .flags = GO7007_BOARD_HAS_AUDIO | GO7007_BOARD_USE_ONBOARD_I2C, .audio_flags = GO7007_AUDIO_I2S_MODE_1 | GO7007_AUDIO_I2S_MASTER | GO7007_AUDIO_WORD_16, .audio_rate = 48000, .audio_bclk_div = 8, .audio_main_div = 2, .hpi_buffer_cap = 7, .sensor_flags = GO7007_SENSOR_656 | GO7007_SENSOR_TV | GO7007_SENSOR_VBI, .num_i2c_devs = 1, .i2c_devs = { { .type = "tw9903", .is_video = 1, .addr = 0x44, }, }, .num_inputs = 2, .inputs = { { .video_input = 2, .name = "Composite", }, { .video_input = 8, .name = "S-Video", }, }, }, }; #if 0 static const struct go7007_usb_board board_lifeview_lr192 = { .flags = GO7007_USB_EZUSB, .main_info = { .flags = GO7007_BOARD_HAS_AUDIO | GO7007_BOARD_USE_ONBOARD_I2C, .audio_flags = GO7007_AUDIO_I2S_MODE_1 | GO7007_AUDIO_WORD_16, .audio_rate = 48000, .audio_bclk_div = 8, .audio_main_div = 2, .hpi_buffer_cap = 7, .sensor_flags = GO7007_SENSOR_656 | GO7007_SENSOR_VALID_ENABLE | GO7007_SENSOR_TV | GO7007_SENSOR_VBI | GO7007_SENSOR_SCALING, .num_i2c_devs = 0, .num_inputs = 1, .inputs = { { .video_input = 0, .name = "Composite", }, }, }, }; #endif static const struct go7007_usb_board board_endura = { .flags = 0, .main_info = { .flags = 0, .audio_flags = GO7007_AUDIO_I2S_MODE_1 | GO7007_AUDIO_I2S_MASTER | GO7007_AUDIO_WORD_16, .audio_rate = 8000, .audio_bclk_div = 48, .audio_main_div = 8, .hpi_buffer_cap = 0, .sensor_flags = GO7007_SENSOR_656 | GO7007_SENSOR_TV, .sensor_h_offset = 8, .num_i2c_devs = 0, .num_inputs = 1, .inputs = { { .name = "Camera", }, }, }, }; static const struct go7007_usb_board board_adlink_mpg24 = { .flags = 0, .main_info = { .flags = GO7007_BOARD_USE_ONBOARD_I2C, .audio_flags = GO7007_AUDIO_I2S_MODE_1 | GO7007_AUDIO_I2S_MASTER | GO7007_AUDIO_WORD_16, .audio_rate = 48000, .audio_bclk_div = 8, .audio_main_div = 2, .hpi_buffer_cap = 0, .sensor_flags = GO7007_SENSOR_656 | GO7007_SENSOR_TV | GO7007_SENSOR_VBI, .num_i2c_devs = 1, .i2c_devs = { { .type = "tw2804", .addr = 0x00, /* yes, really */ .flags = I2C_CLIENT_TEN, .is_video = 1, }, }, .num_inputs = 1, .inputs = { { .name = "Composite", }, }, }, }; static const struct go7007_usb_board board_sensoray_2250 = { .flags = GO7007_USB_EZUSB | GO7007_USB_EZUSB_I2C, .main_info = { .audio_flags = GO7007_AUDIO_I2S_MODE_1 | GO7007_AUDIO_I2S_MASTER | GO7007_AUDIO_WORD_16, .flags = GO7007_BOARD_HAS_AUDIO, .audio_rate = 48000, .audio_bclk_div = 8, .audio_main_div = 2, .hpi_buffer_cap = 7, .sensor_flags = GO7007_SENSOR_656 | GO7007_SENSOR_TV, .num_i2c_devs = 1, .i2c_devs = { { .type = "s2250", .addr = 0x43, .is_video = 1, .is_audio = 1, }, }, .num_inputs = 2, .inputs = { { .video_input = 0, .name = "Composite", }, { .video_input = 1, .name = "S-Video", }, }, .num_aud_inputs = 3, .aud_inputs = { { .audio_input = 0, .name = "Line In", }, { .audio_input = 1, .name = "Mic", }, { .audio_input = 2, .name = "Mic Boost", }, }, }, }; static const struct go7007_usb_board board_ads_usbav_709 = { .flags = GO7007_USB_EZUSB, .main_info = { .flags = GO7007_BOARD_HAS_AUDIO | GO7007_BOARD_USE_ONBOARD_I2C, .audio_flags = GO7007_AUDIO_I2S_MODE_1 | GO7007_AUDIO_I2S_MASTER | GO7007_AUDIO_WORD_16, .audio_rate = 48000, .audio_bclk_div = 8, .audio_main_div = 2, .hpi_buffer_cap = 7, .sensor_flags = GO7007_SENSOR_656 | GO7007_SENSOR_TV | GO7007_SENSOR_VBI, .num_i2c_devs = 1, .i2c_devs = { { .type = "tw9906", .is_video = 1, .addr = 0x44, }, }, .num_inputs = 2, .inputs = { { .video_input = 0, .name = "Composite", }, { .video_input = 10, .name = "S-Video", }, }, }, }; static const struct usb_device_id go7007_usb_id_table[] = { { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION | USB_DEVICE_ID_MATCH_INT_INFO, .idVendor = 0x0eb1, /* Vendor ID of WIS Technologies */ .idProduct = 0x7007, /* Product ID of GO7007SB chip */ .bcdDevice_lo = 0x200, /* Revision number of XMen */ .bcdDevice_hi = 0x200, .bInterfaceClass = 255, .bInterfaceSubClass = 0, .bInterfaceProtocol = 255, .driver_info = (kernel_ulong_t)GO7007_BOARDID_XMEN, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, .idVendor = 0x0eb1, /* Vendor ID of WIS Technologies */ .idProduct = 0x7007, /* Product ID of GO7007SB chip */ .bcdDevice_lo = 0x202, /* Revision number of Matrix II */ .bcdDevice_hi = 0x202, .driver_info = (kernel_ulong_t)GO7007_BOARDID_MATRIX_II, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, .idVendor = 0x0eb1, /* Vendor ID of WIS Technologies */ .idProduct = 0x7007, /* Product ID of GO7007SB chip */ .bcdDevice_lo = 0x204, /* Revision number of Matrix */ .bcdDevice_hi = 0x204, /* Reloaded */ .driver_info = (kernel_ulong_t)GO7007_BOARDID_MATRIX_RELOAD, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION | USB_DEVICE_ID_MATCH_INT_INFO, .idVendor = 0x0eb1, /* Vendor ID of WIS Technologies */ .idProduct = 0x7007, /* Product ID of GO7007SB chip */ .bcdDevice_lo = 0x205, /* Revision number of XMen-II */ .bcdDevice_hi = 0x205, .bInterfaceClass = 255, .bInterfaceSubClass = 0, .bInterfaceProtocol = 255, .driver_info = (kernel_ulong_t)GO7007_BOARDID_XMEN_II, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, .idVendor = 0x0eb1, /* Vendor ID of WIS Technologies */ .idProduct = 0x7007, /* Product ID of GO7007SB chip */ .bcdDevice_lo = 0x208, /* Revision number of Star Trek */ .bcdDevice_hi = 0x208, .driver_info = (kernel_ulong_t)GO7007_BOARDID_STAR_TREK, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION | USB_DEVICE_ID_MATCH_INT_INFO, .idVendor = 0x0eb1, /* Vendor ID of WIS Technologies */ .idProduct = 0x7007, /* Product ID of GO7007SB chip */ .bcdDevice_lo = 0x209, /* Revision number of XMen-III */ .bcdDevice_hi = 0x209, .bInterfaceClass = 255, .bInterfaceSubClass = 0, .bInterfaceProtocol = 255, .driver_info = (kernel_ulong_t)GO7007_BOARDID_XMEN_III, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, .idVendor = 0x0eb1, /* Vendor ID of WIS Technologies */ .idProduct = 0x7007, /* Product ID of GO7007SB chip */ .bcdDevice_lo = 0x210, /* Revision number of Matrix */ .bcdDevice_hi = 0x210, /* Revolution */ .driver_info = (kernel_ulong_t)GO7007_BOARDID_MATRIX_REV, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, .idVendor = 0x093b, /* Vendor ID of Plextor */ .idProduct = 0xa102, /* Product ID of M402U */ .bcdDevice_lo = 0x1, /* revision number of Blueberry */ .bcdDevice_hi = 0x1, .driver_info = (kernel_ulong_t)GO7007_BOARDID_PX_M402U, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, .idVendor = 0x093b, /* Vendor ID of Plextor */ .idProduct = 0xa104, /* Product ID of TV402U */ .bcdDevice_lo = 0x1, .bcdDevice_hi = 0x1, .driver_info = (kernel_ulong_t)GO7007_BOARDID_PX_TV402U, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, .idVendor = 0x10fd, /* Vendor ID of Anubis Electronics */ .idProduct = 0xde00, /* Product ID of Lifeview LR192 */ .bcdDevice_lo = 0x1, .bcdDevice_hi = 0x1, .driver_info = (kernel_ulong_t)GO7007_BOARDID_LIFEVIEW_LR192, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, .idVendor = 0x1943, /* Vendor ID Sensoray */ .idProduct = 0x2250, /* Product ID of 2250/2251 */ .bcdDevice_lo = 0x1, .bcdDevice_hi = 0x1, .driver_info = (kernel_ulong_t)GO7007_BOARDID_SENSORAY_2250, }, { .match_flags = USB_DEVICE_ID_MATCH_DEVICE_AND_VERSION, .idVendor = 0x06e1, /* Vendor ID of ADS Technologies */ .idProduct = 0x0709, /* Product ID of DVD Xpress DX2 */ .bcdDevice_lo = 0x204, .bcdDevice_hi = 0x204, .driver_info = (kernel_ulong_t)GO7007_BOARDID_ADS_USBAV_709, }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, go7007_usb_id_table); /********************* Driver for EZ-USB HPI interface *********************/ static int go7007_usb_vendor_request(struct go7007 *go, int request, int value, int index, void *transfer_buffer, int length, int in) { struct go7007_usb *usb = go->hpi_context; int timeout = 5000; if (in) { return usb_control_msg(usb->usbdev, usb_rcvctrlpipe(usb->usbdev, 0), request, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN, value, index, transfer_buffer, length, timeout); } else { return usb_control_msg(usb->usbdev, usb_sndctrlpipe(usb->usbdev, 0), request, USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, transfer_buffer, length, timeout); } } static int go7007_usb_interface_reset(struct go7007 *go) { struct go7007_usb *usb = go->hpi_context; u16 intr_val, intr_data; if (go->status == STATUS_SHUTDOWN) return -1; /* Reset encoder */ if (go7007_write_interrupt(go, 0x0001, 0x0001) < 0) return -1; msleep(100); if (usb->board->flags & GO7007_USB_EZUSB) { /* Reset buffer in EZ-USB */ pr_debug("resetting EZ-USB buffers\n"); if (go7007_usb_vendor_request(go, 0x10, 0, 0, NULL, 0, 0) < 0 || go7007_usb_vendor_request(go, 0x10, 0, 0, NULL, 0, 0) < 0) return -1; /* Reset encoder again */ if (go7007_write_interrupt(go, 0x0001, 0x0001) < 0) return -1; msleep(100); } /* Wait for an interrupt to indicate successful hardware reset */ if (go7007_read_interrupt(go, &intr_val, &intr_data) < 0 || (intr_val & ~0x1) != 0x55aa) { dev_err(go->dev, "unable to reset the USB interface\n"); return -1; } return 0; } static int go7007_usb_ezusb_write_interrupt(struct go7007 *go, int addr, int data) { struct go7007_usb *usb = go->hpi_context; int i, r; u16 status_reg = 0; int timeout = 500; pr_debug("WriteInterrupt: %04x %04x\n", addr, data); for (i = 0; i < 100; ++i) { r = usb_control_msg(usb->usbdev, usb_rcvctrlpipe(usb->usbdev, 0), 0x14, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN, 0, HPI_STATUS_ADDR, go->usb_buf, sizeof(status_reg), timeout); if (r < 0) break; status_reg = le16_to_cpu(*((__le16 *)go->usb_buf)); if (!(status_reg & 0x0010)) break; msleep(10); } if (r < 0) goto write_int_error; if (i == 100) { dev_err(go->dev, "device is hung, status reg = 0x%04x\n", status_reg); return -1; } r = usb_control_msg(usb->usbdev, usb_sndctrlpipe(usb->usbdev, 0), 0x12, USB_TYPE_VENDOR | USB_RECIP_DEVICE, data, INT_PARAM_ADDR, NULL, 0, timeout); if (r < 0) goto write_int_error; r = usb_control_msg(usb->usbdev, usb_sndctrlpipe(usb->usbdev, 0), 0x12, USB_TYPE_VENDOR | USB_RECIP_DEVICE, addr, INT_INDEX_ADDR, NULL, 0, timeout); if (r < 0) goto write_int_error; return 0; write_int_error: dev_err(go->dev, "error in WriteInterrupt: %d\n", r); return r; } static int go7007_usb_onboard_write_interrupt(struct go7007 *go, int addr, int data) { struct go7007_usb *usb = go->hpi_context; int r; int timeout = 500; pr_debug("WriteInterrupt: %04x %04x\n", addr, data); go->usb_buf[0] = data & 0xff; go->usb_buf[1] = data >> 8; go->usb_buf[2] = addr & 0xff; go->usb_buf[3] = addr >> 8; go->usb_buf[4] = go->usb_buf[5] = go->usb_buf[6] = go->usb_buf[7] = 0; r = usb_control_msg(usb->usbdev, usb_sndctrlpipe(usb->usbdev, 2), 0x00, USB_TYPE_VENDOR | USB_RECIP_ENDPOINT, 0x55aa, 0xf0f0, go->usb_buf, 8, timeout); if (r < 0) { dev_err(go->dev, "error in WriteInterrupt: %d\n", r); return r; } return 0; } static void go7007_usb_readinterrupt_complete(struct urb *urb) { struct go7007 *go = (struct go7007 *)urb->context; __le16 *regs = (__le16 *)urb->transfer_buffer; int status = urb->status; if (status) { if (status != -ESHUTDOWN && go->status != STATUS_SHUTDOWN) { dev_err(go->dev, "error in read interrupt: %d\n", urb->status); } else { wake_up(&go->interrupt_waitq); return; } } else if (urb->actual_length != urb->transfer_buffer_length) { dev_err(go->dev, "short read in interrupt pipe!\n"); } else { go->interrupt_available = 1; go->interrupt_data = __le16_to_cpu(regs[0]); go->interrupt_value = __le16_to_cpu(regs[1]); pr_debug("ReadInterrupt: %04x %04x\n", go->interrupt_value, go->interrupt_data); } wake_up(&go->interrupt_waitq); } static int go7007_usb_read_interrupt(struct go7007 *go) { struct go7007_usb *usb = go->hpi_context; int r; r = usb_submit_urb(usb->intr_urb, GFP_KERNEL); if (r < 0) { dev_err(go->dev, "unable to submit interrupt urb: %d\n", r); return r; } return 0; } static void go7007_usb_read_video_pipe_complete(struct urb *urb) { struct go7007 *go = (struct go7007 *)urb->context; int r, status = urb->status; if (!vb2_is_streaming(&go->vidq)) { wake_up_interruptible(&go->frame_waitq); return; } if (status) { dev_err(go->dev, "error in video pipe: %d\n", status); return; } if (urb->actual_length != urb->transfer_buffer_length) { dev_err(go->dev, "short read in video pipe!\n"); return; } go7007_parse_video_stream(go, urb->transfer_buffer, urb->actual_length); r = usb_submit_urb(urb, GFP_ATOMIC); if (r < 0) dev_err(go->dev, "error in video pipe: %d\n", r); } static void go7007_usb_read_audio_pipe_complete(struct urb *urb) { struct go7007 *go = (struct go7007 *)urb->context; int r, status = urb->status; if (!vb2_is_streaming(&go->vidq)) return; if (status) { dev_err(go->dev, "error in audio pipe: %d\n", status); return; } if (urb->actual_length != urb->transfer_buffer_length) { dev_err(go->dev, "short read in audio pipe!\n"); return; } if (go->audio_deliver != NULL) go->audio_deliver(go, urb->transfer_buffer, urb->actual_length); r = usb_submit_urb(urb, GFP_ATOMIC); if (r < 0) dev_err(go->dev, "error in audio pipe: %d\n", r); } static int go7007_usb_stream_start(struct go7007 *go) { struct go7007_usb *usb = go->hpi_context; int i, r; for (i = 0; i < 8; ++i) { r = usb_submit_urb(usb->video_urbs[i], GFP_KERNEL); if (r < 0) { dev_err(go->dev, "error submitting video urb %d: %d\n", i, r); goto video_submit_failed; } } if (!go->audio_enabled) return 0; for (i = 0; i < 8; ++i) { r = usb_submit_urb(usb->audio_urbs[i], GFP_KERNEL); if (r < 0) { dev_err(go->dev, "error submitting audio urb %d: %d\n", i, r); goto audio_submit_failed; } } return 0; audio_submit_failed: for (i = 0; i < 7; ++i) usb_kill_urb(usb->audio_urbs[i]); video_submit_failed: for (i = 0; i < 8; ++i) usb_kill_urb(usb->video_urbs[i]); return -1; } static int go7007_usb_stream_stop(struct go7007 *go) { struct go7007_usb *usb = go->hpi_context; int i; if (go->status == STATUS_SHUTDOWN) return 0; for (i = 0; i < 8; ++i) usb_kill_urb(usb->video_urbs[i]); if (go->audio_enabled) for (i = 0; i < 8; ++i) usb_kill_urb(usb->audio_urbs[i]); return 0; } static int go7007_usb_send_firmware(struct go7007 *go, u8 *data, int len) { struct go7007_usb *usb = go->hpi_context; int transferred, pipe; int timeout = 500; pr_debug("DownloadBuffer sending %d bytes\n", len); if (usb->board->flags & GO7007_USB_EZUSB) pipe = usb_sndbulkpipe(usb->usbdev, 2); else pipe = usb_sndbulkpipe(usb->usbdev, 3); return usb_bulk_msg(usb->usbdev, pipe, data, len, &transferred, timeout); } static void go7007_usb_release(struct go7007 *go) { struct go7007_usb *usb = go->hpi_context; struct urb *vurb, *aurb; int i; if (usb->intr_urb) { usb_kill_urb(usb->intr_urb); kfree(usb->intr_urb->transfer_buffer); usb_free_urb(usb->intr_urb); } /* Free USB-related structs */ for (i = 0; i < 8; ++i) { vurb = usb->video_urbs[i]; if (vurb) { usb_kill_urb(vurb); kfree(vurb->transfer_buffer); usb_free_urb(vurb); } aurb = usb->audio_urbs[i]; if (aurb) { usb_kill_urb(aurb); kfree(aurb->transfer_buffer); usb_free_urb(aurb); } } kfree(go->hpi_context); } static const struct go7007_hpi_ops go7007_usb_ezusb_hpi_ops = { .interface_reset = go7007_usb_interface_reset, .write_interrupt = go7007_usb_ezusb_write_interrupt, .read_interrupt = go7007_usb_read_interrupt, .stream_start = go7007_usb_stream_start, .stream_stop = go7007_usb_stream_stop, .send_firmware = go7007_usb_send_firmware, .release = go7007_usb_release, }; static const struct go7007_hpi_ops go7007_usb_onboard_hpi_ops = { .interface_reset = go7007_usb_interface_reset, .write_interrupt = go7007_usb_onboard_write_interrupt, .read_interrupt = go7007_usb_read_interrupt, .stream_start = go7007_usb_stream_start, .stream_stop = go7007_usb_stream_stop, .send_firmware = go7007_usb_send_firmware, .release = go7007_usb_release, }; /********************* Driver for EZ-USB I2C adapter *********************/ static int go7007_usb_i2c_master_xfer(struct i2c_adapter *adapter, struct i2c_msg msgs[], int num) { struct go7007 *go = i2c_get_adapdata(adapter); struct go7007_usb *usb = go->hpi_context; u8 *buf = go->usb_buf; int buf_len, i; int ret = -EIO; if (go->status == STATUS_SHUTDOWN) return -ENODEV; mutex_lock(&usb->i2c_lock); for (i = 0; i < num; ++i) { /* The hardware command is "write some bytes then read some * bytes", so we try to coalesce a write followed by a read * into a single USB transaction */ if (i + 1 < num && msgs[i].addr == msgs[i + 1].addr && !(msgs[i].flags & I2C_M_RD) && (msgs[i + 1].flags & I2C_M_RD)) { #ifdef GO7007_I2C_DEBUG pr_debug("i2c write/read %d/%d bytes on %02x\n", msgs[i].len, msgs[i + 1].len, msgs[i].addr); #endif buf[0] = 0x01; buf[1] = msgs[i].len + 1; buf[2] = msgs[i].addr << 1; memcpy(&buf[3], msgs[i].buf, msgs[i].len); buf_len = msgs[i].len + 3; buf[buf_len++] = msgs[++i].len; } else if (msgs[i].flags & I2C_M_RD) { #ifdef GO7007_I2C_DEBUG pr_debug("i2c read %d bytes on %02x\n", msgs[i].len, msgs[i].addr); #endif buf[0] = 0x01; buf[1] = 1; buf[2] = msgs[i].addr << 1; buf[3] = msgs[i].len; buf_len = 4; } else { #ifdef GO7007_I2C_DEBUG pr_debug("i2c write %d bytes on %02x\n", msgs[i].len, msgs[i].addr); #endif buf[0] = 0x00; buf[1] = msgs[i].len + 1; buf[2] = msgs[i].addr << 1; memcpy(&buf[3], msgs[i].buf, msgs[i].len); buf_len = msgs[i].len + 3; buf[buf_len++] = 0; } if (go7007_usb_vendor_request(go, 0x24, 0, 0, buf, buf_len, 0) < 0) goto i2c_done; if (msgs[i].flags & I2C_M_RD) { memset(buf, 0, msgs[i].len + 1); if (go7007_usb_vendor_request(go, 0x25, 0, 0, buf, msgs[i].len + 1, 1) < 0) goto i2c_done; memcpy(msgs[i].buf, buf + 1, msgs[i].len); } } ret = num; i2c_done: mutex_unlock(&usb->i2c_lock); return ret; } static u32 go7007_usb_functionality(struct i2c_adapter *adapter) { /* No errors are reported by the hardware, so we don't bother * supporting quick writes to avoid confusing probing */ return (I2C_FUNC_SMBUS_EMUL) & ~I2C_FUNC_SMBUS_QUICK; } static const struct i2c_algorithm go7007_usb_algo = { .master_xfer = go7007_usb_i2c_master_xfer, .functionality = go7007_usb_functionality, }; static struct i2c_adapter go7007_usb_adap_templ = { .owner = THIS_MODULE, .name = "WIS GO7007SB EZ-USB", .algo = &go7007_usb_algo, }; /********************* USB add/remove functions *********************/ static int go7007_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct go7007 *go; struct go7007_usb *usb; const struct go7007_usb_board *board; struct usb_device *usbdev = interface_to_usbdev(intf); struct usb_host_endpoint *ep; unsigned num_i2c_devs; char *name; int video_pipe, i, v_urb_len; pr_debug("probing new GO7007 USB board\n"); switch (id->driver_info) { case GO7007_BOARDID_MATRIX_II: name = "WIS Matrix II or compatible"; board = &board_matrix_ii; break; case GO7007_BOARDID_MATRIX_RELOAD: name = "WIS Matrix Reloaded or compatible"; board = &board_matrix_reload; break; case GO7007_BOARDID_MATRIX_REV: name = "WIS Matrix Revolution or compatible"; board = &board_matrix_revolution; break; case GO7007_BOARDID_STAR_TREK: name = "WIS Star Trek or compatible"; board = &board_star_trek; break; case GO7007_BOARDID_XMEN: name = "WIS XMen or compatible"; board = &board_xmen; break; case GO7007_BOARDID_XMEN_II: name = "WIS XMen II or compatible"; board = &board_xmen; break; case GO7007_BOARDID_XMEN_III: name = "WIS XMen III or compatible"; board = &board_xmen; break; case GO7007_BOARDID_PX_M402U: name = "Plextor PX-M402U"; board = &board_matrix_ii; break; case GO7007_BOARDID_PX_TV402U: name = "Plextor PX-TV402U (unknown tuner)"; board = &board_px_tv402u; break; case GO7007_BOARDID_LIFEVIEW_LR192: dev_err(&intf->dev, "The Lifeview TV Walker Ultra is not supported. Sorry!\n"); return -ENODEV; #if 0 name = "Lifeview TV Walker Ultra"; board = &board_lifeview_lr192; #endif break; case GO7007_BOARDID_SENSORAY_2250: dev_info(&intf->dev, "Sensoray 2250 found\n"); name = "Sensoray 2250/2251"; board = &board_sensoray_2250; break; case GO7007_BOARDID_ADS_USBAV_709: name = "ADS Tech DVD Xpress DX2"; board = &board_ads_usbav_709; break; default: dev_err(&intf->dev, "unknown board ID %d!\n", (unsigned int)id->driver_info); return -ENODEV; } go = go7007_alloc(&board->main_info, &intf->dev); if (go == NULL) return -ENOMEM; usb = kzalloc(sizeof(struct go7007_usb), GFP_KERNEL); if (usb == NULL) { kfree(go); return -ENOMEM; } usb->board = board; usb->usbdev = usbdev; usb_make_path(usbdev, go->bus_info, sizeof(go->bus_info)); go->board_id = id->driver_info; strscpy(go->name, name, sizeof(go->name)); if (board->flags & GO7007_USB_EZUSB) go->hpi_ops = &go7007_usb_ezusb_hpi_ops; else go->hpi_ops = &go7007_usb_onboard_hpi_ops; go->hpi_context = usb; ep = usb->usbdev->ep_in[4]; if (!ep) goto allocfail; /* Allocate the URB and buffer for receiving incoming interrupts */ usb->intr_urb = usb_alloc_urb(0, GFP_KERNEL); if (usb->intr_urb == NULL) goto allocfail; usb->intr_urb->transfer_buffer = kmalloc_array(2, sizeof(u16), GFP_KERNEL); if (usb->intr_urb->transfer_buffer == NULL) goto allocfail; if (usb_endpoint_type(&ep->desc) == USB_ENDPOINT_XFER_BULK) usb_fill_bulk_urb(usb->intr_urb, usb->usbdev, usb_rcvbulkpipe(usb->usbdev, 4), usb->intr_urb->transfer_buffer, 2*sizeof(u16), go7007_usb_readinterrupt_complete, go); else usb_fill_int_urb(usb->intr_urb, usb->usbdev, usb_rcvintpipe(usb->usbdev, 4), usb->intr_urb->transfer_buffer, 2*sizeof(u16), go7007_usb_readinterrupt_complete, go, 8); usb_set_intfdata(intf, &go->v4l2_dev); /* Boot the GO7007 */ if (go7007_boot_encoder(go, go->board_info->flags & GO7007_BOARD_USE_ONBOARD_I2C) < 0) goto allocfail; /* Register the EZ-USB I2C adapter, if we're using it */ if (board->flags & GO7007_USB_EZUSB_I2C) { memcpy(&go->i2c_adapter, &go7007_usb_adap_templ, sizeof(go7007_usb_adap_templ)); mutex_init(&usb->i2c_lock); go->i2c_adapter.dev.parent = go->dev; i2c_set_adapdata(&go->i2c_adapter, go); if (i2c_add_adapter(&go->i2c_adapter) < 0) { dev_err(go->dev, "error: i2c_add_adapter failed\n"); goto allocfail; } go->i2c_adapter_online = 1; } /* Pelco and Adlink reused the XMen and XMen-III vendor and product * IDs for their own incompatible designs. We can detect XMen boards * by probing the sensor, but there is no way to probe the sensors on * the Pelco and Adlink designs so we default to the Adlink. If it * is actually a Pelco, the user must set the assume_endura module * parameter. */ if ((go->board_id == GO7007_BOARDID_XMEN || go->board_id == GO7007_BOARDID_XMEN_III) && go->i2c_adapter_online) { union i2c_smbus_data data; /* Check to see if register 0x0A is 0x76 */ i2c_smbus_xfer(&go->i2c_adapter, 0x21, I2C_CLIENT_SCCB, I2C_SMBUS_READ, 0x0A, I2C_SMBUS_BYTE_DATA, &data); if (data.byte != 0x76) { if (assume_endura) { go->board_id = GO7007_BOARDID_ENDURA; usb->board = board = &board_endura; go->board_info = &board->main_info; strscpy(go->name, "Pelco Endura", sizeof(go->name)); } else { u16 channel; /* read channel number from GPIO[1:0] */ if (go7007_read_addr(go, 0x3c81, &channel)) goto allocfail; channel &= 0x3; go->board_id = GO7007_BOARDID_ADLINK_MPG24; usb->board = board = &board_adlink_mpg24; go->board_info = &board->main_info; go->channel_number = channel; snprintf(go->name, sizeof(go->name), "Adlink PCI-MPG24, channel #%d", channel); } go7007_update_board(go); } } num_i2c_devs = go->board_info->num_i2c_devs; /* Probe the tuner model on the TV402U */ if (go->board_id == GO7007_BOARDID_PX_TV402U) { /* Board strapping indicates tuner model */ if (go7007_usb_vendor_request(go, 0x41, 0, 0, go->usb_buf, 3, 1) < 0) { dev_err(go->dev, "GPIO read failed!\n"); goto allocfail; } switch (go->usb_buf[0] >> 6) { case 1: go->tuner_type = TUNER_SONY_BTF_PG472Z; go->std = V4L2_STD_PAL; strscpy(go->name, "Plextor PX-TV402U-EU", sizeof(go->name)); break; case 2: go->tuner_type = TUNER_SONY_BTF_PK467Z; go->std = V4L2_STD_NTSC_M_JP; num_i2c_devs -= 2; strscpy(go->name, "Plextor PX-TV402U-JP", sizeof(go->name)); break; case 3: go->tuner_type = TUNER_SONY_BTF_PB463Z; num_i2c_devs -= 2; strscpy(go->name, "Plextor PX-TV402U-NA", sizeof(go->name)); break; default: pr_debug("unable to detect tuner type!\n"); break; } /* Configure tuner mode selection inputs connected * to the EZ-USB GPIO output pins */ if (go7007_usb_vendor_request(go, 0x40, 0x7f02, 0, NULL, 0, 0) < 0) { dev_err(go->dev, "GPIO write failed!\n"); goto allocfail; } } /* Print a nasty message if the user attempts to use a USB2.0 device in * a USB1.1 port. There will be silent corruption of the stream. */ if ((board->flags & GO7007_USB_EZUSB) && usbdev->speed != USB_SPEED_HIGH) dev_err(go->dev, "*** WARNING *** This device must be connected to a USB 2.0 port! Attempting to capture video through a USB 1.1 port will result in stream corruption, even at low bitrates!\n"); /* Allocate the URBs and buffers for receiving the video stream */ if (board->flags & GO7007_USB_EZUSB) { if (!usb->usbdev->ep_in[6]) goto allocfail; v_urb_len = 1024; video_pipe = usb_rcvbulkpipe(usb->usbdev, 6); } else { if (!usb->usbdev->ep_in[1]) goto allocfail; v_urb_len = 512; video_pipe = usb_rcvbulkpipe(usb->usbdev, 1); } for (i = 0; i < 8; ++i) { usb->video_urbs[i] = usb_alloc_urb(0, GFP_KERNEL); if (usb->video_urbs[i] == NULL) goto allocfail; usb->video_urbs[i]->transfer_buffer = kmalloc(v_urb_len, GFP_KERNEL); if (usb->video_urbs[i]->transfer_buffer == NULL) goto allocfail; usb_fill_bulk_urb(usb->video_urbs[i], usb->usbdev, video_pipe, usb->video_urbs[i]->transfer_buffer, v_urb_len, go7007_usb_read_video_pipe_complete, go); } /* Allocate the URBs and buffers for receiving the audio stream */ if ((board->flags & GO7007_USB_EZUSB) && (board->main_info.flags & GO7007_BOARD_HAS_AUDIO)) { if (!usb->usbdev->ep_in[8]) goto allocfail; for (i = 0; i < 8; ++i) { usb->audio_urbs[i] = usb_alloc_urb(0, GFP_KERNEL); if (usb->audio_urbs[i] == NULL) goto allocfail; usb->audio_urbs[i]->transfer_buffer = kmalloc(4096, GFP_KERNEL); if (usb->audio_urbs[i]->transfer_buffer == NULL) goto allocfail; usb_fill_bulk_urb(usb->audio_urbs[i], usb->usbdev, usb_rcvbulkpipe(usb->usbdev, 8), usb->audio_urbs[i]->transfer_buffer, 4096, go7007_usb_read_audio_pipe_complete, go); } } /* Do any final GO7007 initialization, then register the * V4L2 and ALSA interfaces */ if (go7007_register_encoder(go, num_i2c_devs) < 0) goto allocfail; go->status = STATUS_ONLINE; return 0; allocfail: go7007_usb_release(go); kfree(go); return -ENOMEM; } static void go7007_usb_disconnect(struct usb_interface *intf) { struct go7007 *go = to_go7007(usb_get_intfdata(intf)); mutex_lock(&go->queue_lock); mutex_lock(&go->serialize_lock); if (go->audio_enabled) go7007_snd_remove(go); go->status = STATUS_SHUTDOWN; v4l2_device_disconnect(&go->v4l2_dev); video_unregister_device(&go->vdev); mutex_unlock(&go->serialize_lock); mutex_unlock(&go->queue_lock); v4l2_device_put(&go->v4l2_dev); } static struct usb_driver go7007_usb_driver = { .name = "go7007", .probe = go7007_usb_probe, .disconnect = go7007_usb_disconnect, .id_table = go7007_usb_id_table, }; module_usb_driver(go7007_usb_driver); MODULE_DESCRIPTION("WIS GO7007 USB support"); MODULE_LICENSE("GPL v2"); |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Memory-to-memory device framework for Video for Linux 2. * * Helper functions for devices that use memory buffers for both source * and destination. * * Copyright (c) 2009 Samsung Electronics Co., Ltd. * Pawel Osciak, <pawel@osciak.com> * Marek Szyprowski, <m.szyprowski@samsung.com> */ #ifndef _MEDIA_V4L2_MEM2MEM_H #define _MEDIA_V4L2_MEM2MEM_H #include <media/videobuf2-v4l2.h> /** * struct v4l2_m2m_ops - mem-to-mem device driver callbacks * @device_run: required. Begin the actual job (transaction) inside this * callback. * The job does NOT have to end before this callback returns * (and it will be the usual case). When the job finishes, * v4l2_m2m_job_finish() or v4l2_m2m_buf_done_and_job_finish() * has to be called. * @job_ready: optional. Should return 0 if the driver does not have a job * fully prepared to run yet (i.e. it will not be able to finish a * transaction without sleeping). If not provided, it will be * assumed that one source and one destination buffer are all * that is required for the driver to perform one full transaction. * This method may not sleep. * @job_abort: optional. Informs the driver that it has to abort the currently * running transaction as soon as possible (i.e. as soon as it can * stop the device safely; e.g. in the next interrupt handler), * even if the transaction would not have been finished by then. * After the driver performs the necessary steps, it has to call * v4l2_m2m_job_finish() or v4l2_m2m_buf_done_and_job_finish() as * if the transaction ended normally. * This function does not have to (and will usually not) wait * until the device enters a state when it can be stopped. */ struct v4l2_m2m_ops { void (*device_run)(void *priv); int (*job_ready)(void *priv); void (*job_abort)(void *priv); }; struct video_device; struct v4l2_m2m_dev; /** * struct v4l2_m2m_queue_ctx - represents a queue for buffers ready to be * processed * * @q: pointer to struct &vb2_queue * @rdy_queue: List of V4L2 mem-to-mem queues * @rdy_spinlock: spin lock to protect the struct usage * @num_rdy: number of buffers ready to be processed * @buffered: is the queue buffered? * * Queue for buffers ready to be processed as soon as this * instance receives access to the device. */ struct v4l2_m2m_queue_ctx { struct vb2_queue q; struct list_head rdy_queue; spinlock_t rdy_spinlock; u8 num_rdy; bool buffered; }; /** * struct v4l2_m2m_ctx - Memory to memory context structure * * @q_lock: struct &mutex lock * @new_frame: valid in the device_run callback: if true, then this * starts a new frame; if false, then this is a new slice * for an existing frame. This is always true unless * V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF is set, which * indicates slicing support. * @is_draining: indicates device is in draining phase * @last_src_buf: indicate the last source buffer for draining * @next_buf_last: next capture queud buffer will be tagged as last * @has_stopped: indicate the device has been stopped * @ignore_cap_streaming: If true, job_ready can be called even if the CAPTURE * queue is not streaming. This allows firmware to * analyze the bitstream header which arrives on the * OUTPUT queue. The driver must implement the job_ready * callback correctly to make sure that the requirements * for actual decoding are met. * @m2m_dev: opaque pointer to the internal data to handle M2M context * @cap_q_ctx: Capture (output to memory) queue context * @out_q_ctx: Output (input from memory) queue context * @queue: List of memory to memory contexts * @job_flags: Job queue flags, used internally by v4l2-mem2mem.c: * %TRANS_QUEUED, %TRANS_RUNNING and %TRANS_ABORT. * @finished: Wait queue used to signalize when a job queue finished. * @priv: Instance private data * * The memory to memory context is specific to a file handle, NOT to e.g. * a device. */ struct v4l2_m2m_ctx { /* optional cap/out vb2 queues lock */ struct mutex *q_lock; bool new_frame; bool is_draining; struct vb2_v4l2_buffer *last_src_buf; bool next_buf_last; bool has_stopped; bool ignore_cap_streaming; /* internal use only */ struct v4l2_m2m_dev *m2m_dev; struct v4l2_m2m_queue_ctx cap_q_ctx; struct v4l2_m2m_queue_ctx out_q_ctx; /* For device job queue */ struct list_head queue; unsigned long job_flags; wait_queue_head_t finished; void *priv; }; /** * struct v4l2_m2m_buffer - Memory to memory buffer * * @vb: pointer to struct &vb2_v4l2_buffer * @list: list of m2m buffers */ struct v4l2_m2m_buffer { struct vb2_v4l2_buffer vb; struct list_head list; }; /** * v4l2_m2m_get_curr_priv() - return driver private data for the currently * running instance or NULL if no instance is running * * @m2m_dev: opaque pointer to the internal data to handle M2M context */ void *v4l2_m2m_get_curr_priv(struct v4l2_m2m_dev *m2m_dev); /** * v4l2_m2m_get_vq() - return vb2_queue for the given type * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @type: type of the V4L2 buffer, as defined by enum &v4l2_buf_type */ struct vb2_queue *v4l2_m2m_get_vq(struct v4l2_m2m_ctx *m2m_ctx, enum v4l2_buf_type type); /** * v4l2_m2m_try_schedule() - check whether an instance is ready to be added to * the pending job queue and add it if so. * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * * There are three basic requirements an instance has to meet to be able to run: * 1) at least one source buffer has to be queued, * 2) at least one destination buffer has to be queued, * 3) streaming has to be on. * * If a queue is buffered (for example a decoder hardware ringbuffer that has * to be drained before doing streamoff), allow scheduling without v4l2 buffers * on that queue. * * There may also be additional, custom requirements. In such case the driver * should supply a custom callback (job_ready in v4l2_m2m_ops) that should * return 1 if the instance is ready. * An example of the above could be an instance that requires more than one * src/dst buffer per transaction. */ void v4l2_m2m_try_schedule(struct v4l2_m2m_ctx *m2m_ctx); /** * v4l2_m2m_job_finish() - inform the framework that a job has been finished * and have it clean up * * @m2m_dev: opaque pointer to the internal data to handle M2M context * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * * Called by a driver to yield back the device after it has finished with it. * Should be called as soon as possible after reaching a state which allows * other instances to take control of the device. * * This function has to be called only after &v4l2_m2m_ops->device_run * callback has been called on the driver. To prevent recursion, it should * not be called directly from the &v4l2_m2m_ops->device_run callback though. */ void v4l2_m2m_job_finish(struct v4l2_m2m_dev *m2m_dev, struct v4l2_m2m_ctx *m2m_ctx); /** * v4l2_m2m_buf_done_and_job_finish() - return source/destination buffers with * state and inform the framework that a job has been finished and have it * clean up * * @m2m_dev: opaque pointer to the internal data to handle M2M context * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @state: vb2 buffer state passed to v4l2_m2m_buf_done(). * * Drivers that set V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF must use this * function instead of job_finish() to take held buffers into account. It is * optional for other drivers. * * This function removes the source buffer from the ready list and returns * it with the given state. The same is done for the destination buffer, unless * it is marked 'held'. In that case the buffer is kept on the ready list. * * After that the job is finished (see job_finish()). * * This allows for multiple output buffers to be used to fill in a single * capture buffer. This is typically used by stateless decoders where * multiple e.g. H.264 slices contribute to a single decoded frame. */ void v4l2_m2m_buf_done_and_job_finish(struct v4l2_m2m_dev *m2m_dev, struct v4l2_m2m_ctx *m2m_ctx, enum vb2_buffer_state state); static inline void v4l2_m2m_buf_done(struct vb2_v4l2_buffer *buf, enum vb2_buffer_state state) { vb2_buffer_done(&buf->vb2_buf, state); } /** * v4l2_m2m_clear_state() - clear encoding/decoding state * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline void v4l2_m2m_clear_state(struct v4l2_m2m_ctx *m2m_ctx) { m2m_ctx->next_buf_last = false; m2m_ctx->is_draining = false; m2m_ctx->has_stopped = false; } /** * v4l2_m2m_mark_stopped() - set current encoding/decoding state as stopped * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline void v4l2_m2m_mark_stopped(struct v4l2_m2m_ctx *m2m_ctx) { m2m_ctx->next_buf_last = false; m2m_ctx->is_draining = false; m2m_ctx->has_stopped = true; } /** * v4l2_m2m_dst_buf_is_last() - return the current encoding/decoding session * draining management state of next queued capture buffer * * This last capture buffer should be tagged with V4L2_BUF_FLAG_LAST to notify * the end of the capture session. * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline bool v4l2_m2m_dst_buf_is_last(struct v4l2_m2m_ctx *m2m_ctx) { return m2m_ctx->is_draining && m2m_ctx->next_buf_last; } /** * v4l2_m2m_has_stopped() - return the current encoding/decoding session * stopped state * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline bool v4l2_m2m_has_stopped(struct v4l2_m2m_ctx *m2m_ctx) { return m2m_ctx->has_stopped; } /** * v4l2_m2m_is_last_draining_src_buf() - return the output buffer draining * state in the current encoding/decoding session * * This will identify the last output buffer queued before a session stop * was required, leading to an actual encoding/decoding session stop state * in the encoding/decoding process after being processed. * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @vbuf: pointer to struct &v4l2_buffer */ static inline bool v4l2_m2m_is_last_draining_src_buf(struct v4l2_m2m_ctx *m2m_ctx, struct vb2_v4l2_buffer *vbuf) { return m2m_ctx->is_draining && vbuf == m2m_ctx->last_src_buf; } /** * v4l2_m2m_last_buffer_done() - marks the buffer with LAST flag and DONE * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @vbuf: pointer to struct &v4l2_buffer */ void v4l2_m2m_last_buffer_done(struct v4l2_m2m_ctx *m2m_ctx, struct vb2_v4l2_buffer *vbuf); /** * v4l2_m2m_suspend() - stop new jobs from being run and wait for current job * to finish * * @m2m_dev: opaque pointer to the internal data to handle M2M context * * Called by a driver in the suspend hook. Stop new jobs from being run, and * wait for current running job to finish. */ void v4l2_m2m_suspend(struct v4l2_m2m_dev *m2m_dev); /** * v4l2_m2m_resume() - resume job running and try to run a queued job * * @m2m_dev: opaque pointer to the internal data to handle M2M context * * Called by a driver in the resume hook. This reverts the operation of * v4l2_m2m_suspend() and allows job to be run. Also try to run a queued job if * there is any. */ void v4l2_m2m_resume(struct v4l2_m2m_dev *m2m_dev); /** * v4l2_m2m_reqbufs() - multi-queue-aware REQBUFS multiplexer * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @reqbufs: pointer to struct &v4l2_requestbuffers */ int v4l2_m2m_reqbufs(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_requestbuffers *reqbufs); /** * v4l2_m2m_querybuf() - multi-queue-aware QUERYBUF multiplexer * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @buf: pointer to struct &v4l2_buffer * * See v4l2_m2m_mmap() documentation for details. */ int v4l2_m2m_querybuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_buffer *buf); /** * v4l2_m2m_qbuf() - enqueue a source or destination buffer, depending on * the type * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @buf: pointer to struct &v4l2_buffer */ int v4l2_m2m_qbuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_buffer *buf); /** * v4l2_m2m_dqbuf() - dequeue a source or destination buffer, depending on * the type * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @buf: pointer to struct &v4l2_buffer */ int v4l2_m2m_dqbuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_buffer *buf); /** * v4l2_m2m_prepare_buf() - prepare a source or destination buffer, depending on * the type * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @buf: pointer to struct &v4l2_buffer */ int v4l2_m2m_prepare_buf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_buffer *buf); /** * v4l2_m2m_create_bufs() - create a source or destination buffer, depending * on the type * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @create: pointer to struct &v4l2_create_buffers */ int v4l2_m2m_create_bufs(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_create_buffers *create); /** * v4l2_m2m_expbuf() - export a source or destination buffer, depending on * the type * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @eb: pointer to struct &v4l2_exportbuffer */ int v4l2_m2m_expbuf(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_exportbuffer *eb); /** * v4l2_m2m_streamon() - turn on streaming for a video queue * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @type: type of the V4L2 buffer, as defined by enum &v4l2_buf_type */ int v4l2_m2m_streamon(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, enum v4l2_buf_type type); /** * v4l2_m2m_streamoff() - turn off streaming for a video queue * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @type: type of the V4L2 buffer, as defined by enum &v4l2_buf_type */ int v4l2_m2m_streamoff(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, enum v4l2_buf_type type); /** * v4l2_m2m_update_start_streaming_state() - update the encoding/decoding * session state when a start of streaming of a video queue is requested * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @q: queue */ void v4l2_m2m_update_start_streaming_state(struct v4l2_m2m_ctx *m2m_ctx, struct vb2_queue *q); /** * v4l2_m2m_update_stop_streaming_state() - update the encoding/decoding * session state when a stop of streaming of a video queue is requested * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @q: queue */ void v4l2_m2m_update_stop_streaming_state(struct v4l2_m2m_ctx *m2m_ctx, struct vb2_queue *q); /** * v4l2_m2m_encoder_cmd() - execute an encoder command * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @ec: pointer to the encoder command */ int v4l2_m2m_encoder_cmd(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_encoder_cmd *ec); /** * v4l2_m2m_decoder_cmd() - execute a decoder command * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @dc: pointer to the decoder command */ int v4l2_m2m_decoder_cmd(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_decoder_cmd *dc); /** * v4l2_m2m_poll() - poll replacement, for destination buffers only * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @wait: pointer to struct &poll_table_struct * * Call from the driver's poll() function. Will poll both queues. If a buffer * is available to dequeue (with dqbuf) from the source queue, this will * indicate that a non-blocking write can be performed, while read will be * returned in case of the destination queue. */ __poll_t v4l2_m2m_poll(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct poll_table_struct *wait); /** * v4l2_m2m_mmap() - source and destination queues-aware mmap multiplexer * * @file: pointer to struct &file * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @vma: pointer to struct &vm_area_struct * * Call from driver's mmap() function. Will handle mmap() for both queues * seamlessly for the video buffer, which will receive normal per-queue offsets * and proper vb2 queue pointers. The differentiation is made outside * vb2 by adding a predefined offset to buffers from one of the queues * and subtracting it before passing it back to vb2. Only drivers (and * thus applications) receive modified offsets. */ int v4l2_m2m_mmap(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct vm_area_struct *vma); #ifndef CONFIG_MMU unsigned long v4l2_m2m_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif /** * v4l2_m2m_init() - initialize per-driver m2m data * * @m2m_ops: pointer to struct v4l2_m2m_ops * * Usually called from driver's ``probe()`` function. * * Return: returns an opaque pointer to the internal data to handle M2M context */ struct v4l2_m2m_dev *v4l2_m2m_init(const struct v4l2_m2m_ops *m2m_ops); #if defined(CONFIG_MEDIA_CONTROLLER) void v4l2_m2m_unregister_media_controller(struct v4l2_m2m_dev *m2m_dev); int v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev, struct video_device *vdev, int function); #else static inline void v4l2_m2m_unregister_media_controller(struct v4l2_m2m_dev *m2m_dev) { } static inline int v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev, struct video_device *vdev, int function) { return 0; } #endif /** * v4l2_m2m_release() - cleans up and frees a m2m_dev structure * * @m2m_dev: opaque pointer to the internal data to handle M2M context * * Usually called from driver's ``remove()`` function. */ void v4l2_m2m_release(struct v4l2_m2m_dev *m2m_dev); /** * v4l2_m2m_ctx_init() - allocate and initialize a m2m context * * @m2m_dev: opaque pointer to the internal data to handle M2M context * @drv_priv: driver's instance private data * @queue_init: a callback for queue type-specific initialization function * to be used for initializing vb2_queues * * Usually called from driver's ``open()`` function. */ struct v4l2_m2m_ctx *v4l2_m2m_ctx_init(struct v4l2_m2m_dev *m2m_dev, void *drv_priv, int (*queue_init)(void *priv, struct vb2_queue *src_vq, struct vb2_queue *dst_vq)); static inline void v4l2_m2m_set_src_buffered(struct v4l2_m2m_ctx *m2m_ctx, bool buffered) { m2m_ctx->out_q_ctx.buffered = buffered; } static inline void v4l2_m2m_set_dst_buffered(struct v4l2_m2m_ctx *m2m_ctx, bool buffered) { m2m_ctx->cap_q_ctx.buffered = buffered; } /** * v4l2_m2m_ctx_release() - release m2m context * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * * Usually called from driver's release() function. */ void v4l2_m2m_ctx_release(struct v4l2_m2m_ctx *m2m_ctx); /** * v4l2_m2m_buf_queue() - add a buffer to the proper ready buffers list. * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @vbuf: pointer to struct &vb2_v4l2_buffer * * Call from vb2_queue_ops->ops->buf_queue, vb2_queue_ops callback. */ void v4l2_m2m_buf_queue(struct v4l2_m2m_ctx *m2m_ctx, struct vb2_v4l2_buffer *vbuf); /** * v4l2_m2m_num_src_bufs_ready() - return the number of source buffers ready for * use * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline unsigned int v4l2_m2m_num_src_bufs_ready(struct v4l2_m2m_ctx *m2m_ctx) { unsigned int num_buf_rdy; unsigned long flags; spin_lock_irqsave(&m2m_ctx->out_q_ctx.rdy_spinlock, flags); num_buf_rdy = m2m_ctx->out_q_ctx.num_rdy; spin_unlock_irqrestore(&m2m_ctx->out_q_ctx.rdy_spinlock, flags); return num_buf_rdy; } /** * v4l2_m2m_num_dst_bufs_ready() - return the number of destination buffers * ready for use * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline unsigned int v4l2_m2m_num_dst_bufs_ready(struct v4l2_m2m_ctx *m2m_ctx) { unsigned int num_buf_rdy; unsigned long flags; spin_lock_irqsave(&m2m_ctx->cap_q_ctx.rdy_spinlock, flags); num_buf_rdy = m2m_ctx->cap_q_ctx.num_rdy; spin_unlock_irqrestore(&m2m_ctx->cap_q_ctx.rdy_spinlock, flags); return num_buf_rdy; } /** * v4l2_m2m_next_buf() - return next buffer from the list of ready buffers * * @q_ctx: pointer to struct @v4l2_m2m_queue_ctx */ struct vb2_v4l2_buffer *v4l2_m2m_next_buf(struct v4l2_m2m_queue_ctx *q_ctx); /** * v4l2_m2m_next_src_buf() - return next source buffer from the list of ready * buffers * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline struct vb2_v4l2_buffer * v4l2_m2m_next_src_buf(struct v4l2_m2m_ctx *m2m_ctx) { return v4l2_m2m_next_buf(&m2m_ctx->out_q_ctx); } /** * v4l2_m2m_next_dst_buf() - return next destination buffer from the list of * ready buffers * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline struct vb2_v4l2_buffer * v4l2_m2m_next_dst_buf(struct v4l2_m2m_ctx *m2m_ctx) { return v4l2_m2m_next_buf(&m2m_ctx->cap_q_ctx); } /** * v4l2_m2m_last_buf() - return last buffer from the list of ready buffers * * @q_ctx: pointer to struct @v4l2_m2m_queue_ctx */ struct vb2_v4l2_buffer *v4l2_m2m_last_buf(struct v4l2_m2m_queue_ctx *q_ctx); /** * v4l2_m2m_last_src_buf() - return last source buffer from the list of * ready buffers * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline struct vb2_v4l2_buffer * v4l2_m2m_last_src_buf(struct v4l2_m2m_ctx *m2m_ctx) { return v4l2_m2m_last_buf(&m2m_ctx->out_q_ctx); } /** * v4l2_m2m_last_dst_buf() - return last destination buffer from the list of * ready buffers * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline struct vb2_v4l2_buffer * v4l2_m2m_last_dst_buf(struct v4l2_m2m_ctx *m2m_ctx) { return v4l2_m2m_last_buf(&m2m_ctx->cap_q_ctx); } /** * v4l2_m2m_for_each_dst_buf() - iterate over a list of destination ready * buffers * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @b: current buffer of type struct v4l2_m2m_buffer */ #define v4l2_m2m_for_each_dst_buf(m2m_ctx, b) \ list_for_each_entry(b, &m2m_ctx->cap_q_ctx.rdy_queue, list) /** * v4l2_m2m_for_each_src_buf() - iterate over a list of source ready buffers * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @b: current buffer of type struct v4l2_m2m_buffer */ #define v4l2_m2m_for_each_src_buf(m2m_ctx, b) \ list_for_each_entry(b, &m2m_ctx->out_q_ctx.rdy_queue, list) /** * v4l2_m2m_for_each_dst_buf_safe() - iterate over a list of destination ready * buffers safely * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @b: current buffer of type struct v4l2_m2m_buffer * @n: used as temporary storage */ #define v4l2_m2m_for_each_dst_buf_safe(m2m_ctx, b, n) \ list_for_each_entry_safe(b, n, &m2m_ctx->cap_q_ctx.rdy_queue, list) /** * v4l2_m2m_for_each_src_buf_safe() - iterate over a list of source ready * buffers safely * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @b: current buffer of type struct v4l2_m2m_buffer * @n: used as temporary storage */ #define v4l2_m2m_for_each_src_buf_safe(m2m_ctx, b, n) \ list_for_each_entry_safe(b, n, &m2m_ctx->out_q_ctx.rdy_queue, list) /** * v4l2_m2m_get_src_vq() - return vb2_queue for source buffers * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline struct vb2_queue *v4l2_m2m_get_src_vq(struct v4l2_m2m_ctx *m2m_ctx) { return &m2m_ctx->out_q_ctx.q; } /** * v4l2_m2m_get_dst_vq() - return vb2_queue for destination buffers * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline struct vb2_queue *v4l2_m2m_get_dst_vq(struct v4l2_m2m_ctx *m2m_ctx) { return &m2m_ctx->cap_q_ctx.q; } /** * v4l2_m2m_buf_remove() - take off a buffer from the list of ready buffers and * return it * * @q_ctx: pointer to struct @v4l2_m2m_queue_ctx */ struct vb2_v4l2_buffer *v4l2_m2m_buf_remove(struct v4l2_m2m_queue_ctx *q_ctx); /** * v4l2_m2m_src_buf_remove() - take off a source buffer from the list of ready * buffers and return it * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline struct vb2_v4l2_buffer * v4l2_m2m_src_buf_remove(struct v4l2_m2m_ctx *m2m_ctx) { return v4l2_m2m_buf_remove(&m2m_ctx->out_q_ctx); } /** * v4l2_m2m_dst_buf_remove() - take off a destination buffer from the list of * ready buffers and return it * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx */ static inline struct vb2_v4l2_buffer * v4l2_m2m_dst_buf_remove(struct v4l2_m2m_ctx *m2m_ctx) { return v4l2_m2m_buf_remove(&m2m_ctx->cap_q_ctx); } /** * v4l2_m2m_buf_remove_by_buf() - take off exact buffer from the list of ready * buffers * * @q_ctx: pointer to struct @v4l2_m2m_queue_ctx * @vbuf: the buffer to be removed */ void v4l2_m2m_buf_remove_by_buf(struct v4l2_m2m_queue_ctx *q_ctx, struct vb2_v4l2_buffer *vbuf); /** * v4l2_m2m_src_buf_remove_by_buf() - take off exact source buffer from the list * of ready buffers * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @vbuf: the buffer to be removed */ static inline void v4l2_m2m_src_buf_remove_by_buf(struct v4l2_m2m_ctx *m2m_ctx, struct vb2_v4l2_buffer *vbuf) { v4l2_m2m_buf_remove_by_buf(&m2m_ctx->out_q_ctx, vbuf); } /** * v4l2_m2m_dst_buf_remove_by_buf() - take off exact destination buffer from the * list of ready buffers * * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx * @vbuf: the buffer to be removed */ static inline void v4l2_m2m_dst_buf_remove_by_buf(struct v4l2_m2m_ctx *m2m_ctx, struct vb2_v4l2_buffer *vbuf) { v4l2_m2m_buf_remove_by_buf(&m2m_ctx->cap_q_ctx, vbuf); } struct vb2_v4l2_buffer * v4l2_m2m_buf_remove_by_idx(struct v4l2_m2m_queue_ctx *q_ctx, unsigned int idx); static inline struct vb2_v4l2_buffer * v4l2_m2m_src_buf_remove_by_idx(struct v4l2_m2m_ctx *m2m_ctx, unsigned int idx) { return v4l2_m2m_buf_remove_by_idx(&m2m_ctx->out_q_ctx, idx); } static inline struct vb2_v4l2_buffer * v4l2_m2m_dst_buf_remove_by_idx(struct v4l2_m2m_ctx *m2m_ctx, unsigned int idx) { return v4l2_m2m_buf_remove_by_idx(&m2m_ctx->cap_q_ctx, idx); } /** * v4l2_m2m_buf_copy_metadata() - copy buffer metadata from * the output buffer to the capture buffer * * @out_vb: the output buffer that is the source of the metadata. * @cap_vb: the capture buffer that will receive the metadata. * @copy_frame_flags: copy the KEY/B/PFRAME flags as well. * * This helper function copies the timestamp, timecode (if the TIMECODE * buffer flag was set), field and the TIMECODE, KEYFRAME, BFRAME, PFRAME * and TSTAMP_SRC_MASK flags from @out_vb to @cap_vb. * * If @copy_frame_flags is false, then the KEYFRAME, BFRAME and PFRAME * flags are not copied. This is typically needed for encoders that * set this bits explicitly. */ void v4l2_m2m_buf_copy_metadata(const struct vb2_v4l2_buffer *out_vb, struct vb2_v4l2_buffer *cap_vb, bool copy_frame_flags); /* v4l2 request helper */ void v4l2_m2m_request_queue(struct media_request *req); /* v4l2 ioctl helpers */ int v4l2_m2m_ioctl_reqbufs(struct file *file, void *priv, struct v4l2_requestbuffers *rb); int v4l2_m2m_ioctl_create_bufs(struct file *file, void *priv, struct v4l2_create_buffers *create); int v4l2_m2m_ioctl_remove_bufs(struct file *file, void *priv, struct v4l2_remove_buffers *d); int v4l2_m2m_ioctl_querybuf(struct file *file, void *priv, struct v4l2_buffer *buf); int v4l2_m2m_ioctl_expbuf(struct file *file, void *priv, struct v4l2_exportbuffer *eb); int v4l2_m2m_ioctl_qbuf(struct file *file, void *priv, struct v4l2_buffer *buf); int v4l2_m2m_ioctl_dqbuf(struct file *file, void *priv, struct v4l2_buffer *buf); int v4l2_m2m_ioctl_prepare_buf(struct file *file, void *priv, struct v4l2_buffer *buf); int v4l2_m2m_ioctl_streamon(struct file *file, void *priv, enum v4l2_buf_type type); int v4l2_m2m_ioctl_streamoff(struct file *file, void *priv, enum v4l2_buf_type type); int v4l2_m2m_ioctl_encoder_cmd(struct file *file, void *priv, struct v4l2_encoder_cmd *ec); int v4l2_m2m_ioctl_decoder_cmd(struct file *file, void *priv, struct v4l2_decoder_cmd *dc); int v4l2_m2m_ioctl_try_encoder_cmd(struct file *file, void *priv, struct v4l2_encoder_cmd *ec); int v4l2_m2m_ioctl_try_decoder_cmd(struct file *file, void *priv, struct v4l2_decoder_cmd *dc); int v4l2_m2m_ioctl_stateless_try_decoder_cmd(struct file *file, void *priv, struct v4l2_decoder_cmd *dc); int v4l2_m2m_ioctl_stateless_decoder_cmd(struct file *file, void *priv, struct v4l2_decoder_cmd *dc); int v4l2_m2m_fop_mmap(struct file *file, struct vm_area_struct *vma); __poll_t v4l2_m2m_fop_poll(struct file *file, poll_table *wait); #endif /* _MEDIA_V4L2_MEM2MEM_H */ |
| 5 5 5 5 5 5 5 5 5 5 1 4 1 4 3 1 3 3 4 2 2 15 2 2 2 2 16 1 15 1 5 2 5 3 7 1 1 1 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> #include <linux/filter.h> #include <linux/kmod.h> #include <linux/module.h> #include <linux/netfilter.h> #include <net/netfilter/nf_bpf_link.h> #include <uapi/linux/netfilter_ipv4.h> static unsigned int nf_hook_run_bpf(void *bpf_prog, struct sk_buff *skb, const struct nf_hook_state *s) { const struct bpf_prog *prog = bpf_prog; struct bpf_nf_ctx ctx = { .state = s, .skb = skb, }; return bpf_prog_run_pin_on_cpu(prog, &ctx); } struct bpf_nf_link { struct bpf_link link; struct nf_hook_ops hook_ops; netns_tracker ns_tracker; struct net *net; u32 dead; const struct nf_defrag_hook *defrag_hook; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) static const struct nf_defrag_hook * get_proto_defrag_hook(struct bpf_nf_link *link, const struct nf_defrag_hook __rcu **ptr_global_hook, const char *mod) { const struct nf_defrag_hook *hook; int err; /* RCU protects us from races against module unloading */ rcu_read_lock(); hook = rcu_dereference(*ptr_global_hook); if (!hook) { rcu_read_unlock(); err = request_module("%s", mod); if (err) return ERR_PTR(err < 0 ? err : -EINVAL); rcu_read_lock(); hook = rcu_dereference(*ptr_global_hook); } if (hook && try_module_get(hook->owner)) { /* Once we have a refcnt on the module, we no longer need RCU */ hook = rcu_pointer_handoff(hook); } else { WARN_ONCE(!hook, "%s has bad registration", mod); hook = ERR_PTR(-ENOENT); } rcu_read_unlock(); if (!IS_ERR(hook)) { err = hook->enable(link->net); if (err) { module_put(hook->owner); hook = ERR_PTR(err); } } return hook; } #endif static int bpf_nf_enable_defrag(struct bpf_nf_link *link) { const struct nf_defrag_hook __maybe_unused *hook; switch (link->hook_ops.pf) { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) case NFPROTO_IPV4: hook = get_proto_defrag_hook(link, &nf_defrag_v4_hook, "nf_defrag_ipv4"); if (IS_ERR(hook)) return PTR_ERR(hook); link->defrag_hook = hook; return 0; #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) case NFPROTO_IPV6: hook = get_proto_defrag_hook(link, &nf_defrag_v6_hook, "nf_defrag_ipv6"); if (IS_ERR(hook)) return PTR_ERR(hook); link->defrag_hook = hook; return 0; #endif default: return -EAFNOSUPPORT; } } static void bpf_nf_disable_defrag(struct bpf_nf_link *link) { const struct nf_defrag_hook *hook = link->defrag_hook; if (!hook) return; hook->disable(link->net); module_put(hook->owner); } static void bpf_nf_link_release(struct bpf_link *link) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); if (nf_link->dead) return; /* do not double release in case .detach was already called */ if (!cmpxchg(&nf_link->dead, 0, 1)) { nf_unregister_net_hook(nf_link->net, &nf_link->hook_ops); bpf_nf_disable_defrag(nf_link); put_net_track(nf_link->net, &nf_link->ns_tracker); } } static void bpf_nf_link_dealloc(struct bpf_link *link) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); kfree(nf_link); } static int bpf_nf_link_detach(struct bpf_link *link) { bpf_nf_link_release(link); return 0; } static void bpf_nf_link_show_info(const struct bpf_link *link, struct seq_file *seq) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); seq_printf(seq, "pf:\t%u\thooknum:\t%u\tprio:\t%d\n", nf_link->hook_ops.pf, nf_link->hook_ops.hooknum, nf_link->hook_ops.priority); } static int bpf_nf_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); const struct nf_defrag_hook *hook = nf_link->defrag_hook; info->netfilter.pf = nf_link->hook_ops.pf; info->netfilter.hooknum = nf_link->hook_ops.hooknum; info->netfilter.priority = nf_link->hook_ops.priority; info->netfilter.flags = hook ? BPF_F_NETFILTER_IP_DEFRAG : 0; return 0; } static int bpf_nf_link_update(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { return -EOPNOTSUPP; } static const struct bpf_link_ops bpf_nf_link_lops = { .release = bpf_nf_link_release, .dealloc = bpf_nf_link_dealloc, .detach = bpf_nf_link_detach, .show_fdinfo = bpf_nf_link_show_info, .fill_link_info = bpf_nf_link_fill_link_info, .update_prog = bpf_nf_link_update, }; static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr) { int prio; switch (attr->link_create.netfilter.pf) { case NFPROTO_IPV4: case NFPROTO_IPV6: if (attr->link_create.netfilter.hooknum >= NF_INET_NUMHOOKS) return -EPROTO; break; default: return -EAFNOSUPPORT; } if (attr->link_create.netfilter.flags & ~BPF_F_NETFILTER_IP_DEFRAG) return -EOPNOTSUPP; /* make sure conntrack confirm is always last */ prio = attr->link_create.netfilter.priority; if (prio == NF_IP_PRI_FIRST) return -ERANGE; /* sabotage_in and other warts */ else if (prio == NF_IP_PRI_LAST) return -ERANGE; /* e.g. conntrack confirm */ else if ((attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) && prio <= NF_IP_PRI_CONNTRACK_DEFRAG) return -ERANGE; /* cannot use defrag if prog runs before nf_defrag */ return 0; } int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct net *net = current->nsproxy->net_ns; struct bpf_link_primer link_primer; struct bpf_nf_link *link; int err; if (attr->link_create.flags) return -EINVAL; err = bpf_nf_check_pf_and_hooks(attr); if (err) return err; link = kzalloc(sizeof(*link), GFP_USER); if (!link) return -ENOMEM; bpf_link_init(&link->link, BPF_LINK_TYPE_NETFILTER, &bpf_nf_link_lops, prog, attr->link_create.attach_type); link->hook_ops.hook = nf_hook_run_bpf; link->hook_ops.hook_ops_type = NF_HOOK_OP_BPF; link->hook_ops.priv = prog; link->hook_ops.pf = attr->link_create.netfilter.pf; link->hook_ops.priority = attr->link_create.netfilter.priority; link->hook_ops.hooknum = attr->link_create.netfilter.hooknum; link->net = net; link->dead = false; link->defrag_hook = NULL; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); return err; } if (attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) { err = bpf_nf_enable_defrag(link); if (err) { bpf_link_cleanup(&link_primer); return err; } } err = nf_register_net_hook(net, &link->hook_ops); if (err) { bpf_nf_disable_defrag(link); bpf_link_cleanup(&link_primer); return err; } get_net_track(net, &link->ns_tracker, GFP_KERNEL); return bpf_link_settle(&link_primer); } const struct bpf_prog_ops netfilter_prog_ops = { .test_run = bpf_prog_test_run_nf, }; static bool nf_ptr_to_btf_id(struct bpf_insn_access_aux *info, const char *name) { struct btf *btf; s32 type_id; btf = bpf_get_btf_vmlinux(); if (IS_ERR_OR_NULL(btf)) return false; type_id = btf_find_by_name_kind(btf, name, BTF_KIND_STRUCT); if (WARN_ON_ONCE(type_id < 0)) return false; info->btf = btf; info->btf_id = type_id; info->reg_type = PTR_TO_BTF_ID | PTR_TRUSTED; return true; } static bool nf_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct bpf_nf_ctx)) return false; if (off % size != 0) return false; if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct bpf_nf_ctx, skb): if (size != sizeof_field(struct bpf_nf_ctx, skb)) return false; return nf_ptr_to_btf_id(info, "sk_buff"); case bpf_ctx_range(struct bpf_nf_ctx, state): if (size != sizeof_field(struct bpf_nf_ctx, state)) return false; return nf_ptr_to_btf_id(info, "nf_hook_state"); default: return false; } return false; } static const struct bpf_func_proto * bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return bpf_base_func_proto(func_id, prog); } const struct bpf_verifier_ops netfilter_verifier_ops = { .is_valid_access = nf_is_valid_access, .get_func_proto = bpf_nf_func_proto, }; |
| 5 5 2 6 6 10 10 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Line 6 Linux USB driver * * Copyright (C) 2004-2010 Markus Grabner (line6@grabner-graz.at) */ #include <linux/slab.h> #include <linux/wait.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/usb.h> #include <sound/core.h> #include <sound/control.h> #include "capture.h" #include "driver.h" #include "playback.h" /* Locate name in binary program dump */ #define POD_NAME_OFFSET 0 #define POD_NAME_LENGTH 16 /* Other constants */ #define POD_CONTROL_SIZE 0x80 #define POD_BUFSIZE_DUMPREQ 7 #define POD_STARTUP_DELAY 1000 /* Stages of POD startup procedure */ enum { POD_STARTUP_VERSIONREQ, POD_STARTUP_SETUP, POD_STARTUP_DONE, }; enum { LINE6_BASSPODXT, LINE6_BASSPODXTLIVE, LINE6_BASSPODXTPRO, LINE6_POCKETPOD, LINE6_PODXT, LINE6_PODXTLIVE_POD, LINE6_PODXTPRO, }; struct usb_line6_pod { /* Generic Line 6 USB data */ struct usb_line6 line6; /* Instrument monitor level */ int monitor_level; /* Current progress in startup procedure */ int startup_progress; /* Serial number of device */ u32 serial_number; /* Firmware version (x 100) */ int firmware_version; /* Device ID */ int device_id; }; #define line6_to_pod(x) container_of(x, struct usb_line6_pod, line6) #define POD_SYSEX_CODE 3 /* *INDENT-OFF* */ enum { POD_SYSEX_SAVE = 0x24, POD_SYSEX_SYSTEM = 0x56, POD_SYSEX_SYSTEMREQ = 0x57, /* POD_SYSEX_UPDATE = 0x6c, */ /* software update! */ POD_SYSEX_STORE = 0x71, POD_SYSEX_FINISH = 0x72, POD_SYSEX_DUMPMEM = 0x73, POD_SYSEX_DUMP = 0x74, POD_SYSEX_DUMPREQ = 0x75 /* dumps entire internal memory of PODxt Pro */ /* POD_SYSEX_DUMPMEM2 = 0x76 */ }; enum { POD_MONITOR_LEVEL = 0x04, POD_SYSTEM_INVALID = 0x10000 }; /* *INDENT-ON* */ enum { POD_DUMP_MEMORY = 2 }; enum { POD_BUSY_READ, POD_BUSY_WRITE, POD_CHANNEL_DIRTY, POD_SAVE_PRESSED, POD_BUSY_MIDISEND }; static const struct snd_ratden pod_ratden = { .num_min = 78125, .num_max = 78125, .num_step = 1, .den = 2 }; static struct line6_pcm_properties pod_pcm_properties = { .playback_hw = { .info = (SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_BLOCK_TRANSFER | SNDRV_PCM_INFO_MMAP_VALID | SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_SYNC_START), .formats = SNDRV_PCM_FMTBIT_S24_3LE, .rates = SNDRV_PCM_RATE_KNOT, .rate_min = 39062, .rate_max = 39063, .channels_min = 2, .channels_max = 2, .buffer_bytes_max = 60000, .period_bytes_min = 64, .period_bytes_max = 8192, .periods_min = 1, .periods_max = 1024}, .capture_hw = { .info = (SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_BLOCK_TRANSFER | SNDRV_PCM_INFO_MMAP_VALID | SNDRV_PCM_INFO_SYNC_START), .formats = SNDRV_PCM_FMTBIT_S24_3LE, .rates = SNDRV_PCM_RATE_KNOT, .rate_min = 39062, .rate_max = 39063, .channels_min = 2, .channels_max = 2, .buffer_bytes_max = 60000, .period_bytes_min = 64, .period_bytes_max = 8192, .periods_min = 1, .periods_max = 1024}, .rates = { .nrats = 1, .rats = &pod_ratden}, .bytes_per_channel = 3 /* SNDRV_PCM_FMTBIT_S24_3LE */ }; static const char pod_version_header[] = { 0xf0, 0x7e, 0x7f, 0x06, 0x02 }; static char *pod_alloc_sysex_buffer(struct usb_line6_pod *pod, int code, int size) { return line6_alloc_sysex_buffer(&pod->line6, POD_SYSEX_CODE, code, size); } /* Process a completely received message. */ static void line6_pod_process_message(struct usb_line6 *line6) { struct usb_line6_pod *pod = line6_to_pod(line6); const unsigned char *buf = pod->line6.buffer_message; if (memcmp(buf, pod_version_header, sizeof(pod_version_header)) == 0) { pod->firmware_version = buf[13] * 100 + buf[14] * 10 + buf[15]; pod->device_id = ((int)buf[8] << 16) | ((int)buf[9] << 8) | (int) buf[10]; if (pod->startup_progress == POD_STARTUP_VERSIONREQ) { pod->startup_progress = POD_STARTUP_SETUP; schedule_delayed_work(&line6->startup_work, 0); } return; } /* Only look for sysex messages from this device */ if (buf[0] != (LINE6_SYSEX_BEGIN | LINE6_CHANNEL_DEVICE) && buf[0] != (LINE6_SYSEX_BEGIN | LINE6_CHANNEL_UNKNOWN)) { return; } if (memcmp(buf + 1, line6_midi_id, sizeof(line6_midi_id)) != 0) return; if (buf[5] == POD_SYSEX_SYSTEM && buf[6] == POD_MONITOR_LEVEL) { short value = ((int)buf[7] << 12) | ((int)buf[8] << 8) | ((int)buf[9] << 4) | (int)buf[10]; pod->monitor_level = value; } } /* Send system parameter (from integer). */ static int pod_set_system_param_int(struct usb_line6_pod *pod, int value, int code) { char *sysex; static const int size = 5; sysex = pod_alloc_sysex_buffer(pod, POD_SYSEX_SYSTEM, size); if (!sysex) return -ENOMEM; sysex[SYSEX_DATA_OFS] = code; sysex[SYSEX_DATA_OFS + 1] = (value >> 12) & 0x0f; sysex[SYSEX_DATA_OFS + 2] = (value >> 8) & 0x0f; sysex[SYSEX_DATA_OFS + 3] = (value >> 4) & 0x0f; sysex[SYSEX_DATA_OFS + 4] = (value) & 0x0f; line6_send_sysex_message(&pod->line6, sysex, size); kfree(sysex); return 0; } /* "read" request on "serial_number" special file. */ static ssize_t serial_number_show(struct device *dev, struct device_attribute *attr, char *buf) { struct snd_card *card = dev_to_snd_card(dev); struct usb_line6_pod *pod = card->private_data; return sysfs_emit(buf, "%u\n", pod->serial_number); } /* "read" request on "firmware_version" special file. */ static ssize_t firmware_version_show(struct device *dev, struct device_attribute *attr, char *buf) { struct snd_card *card = dev_to_snd_card(dev); struct usb_line6_pod *pod = card->private_data; return sysfs_emit(buf, "%d.%02d\n", pod->firmware_version / 100, pod->firmware_version % 100); } /* "read" request on "device_id" special file. */ static ssize_t device_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct snd_card *card = dev_to_snd_card(dev); struct usb_line6_pod *pod = card->private_data; return sysfs_emit(buf, "%d\n", pod->device_id); } /* POD startup procedure. This is a sequence of functions with special requirements (e.g., must not run immediately after initialization, must not run in interrupt context). After the last one has finished, the device is ready to use. */ static void pod_startup(struct usb_line6 *line6) { struct usb_line6_pod *pod = line6_to_pod(line6); switch (pod->startup_progress) { case POD_STARTUP_VERSIONREQ: /* request firmware version: */ line6_version_request_async(line6); break; case POD_STARTUP_SETUP: /* serial number: */ line6_read_serial_number(&pod->line6, &pod->serial_number); /* ALSA audio interface: */ if (snd_card_register(line6->card)) dev_err(line6->ifcdev, "Failed to register POD card.\n"); pod->startup_progress = POD_STARTUP_DONE; break; default: break; } } /* POD special files: */ static DEVICE_ATTR_RO(device_id); static DEVICE_ATTR_RO(firmware_version); static DEVICE_ATTR_RO(serial_number); static struct attribute *pod_dev_attrs[] = { &dev_attr_device_id.attr, &dev_attr_firmware_version.attr, &dev_attr_serial_number.attr, NULL }; static const struct attribute_group pod_dev_attr_group = { .name = "pod", .attrs = pod_dev_attrs, }; /* control info callback */ static int snd_pod_control_monitor_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER; uinfo->count = 1; uinfo->value.integer.min = 0; uinfo->value.integer.max = 65535; return 0; } /* control get callback */ static int snd_pod_control_monitor_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_line6_pcm *line6pcm = snd_kcontrol_chip(kcontrol); struct usb_line6_pod *pod = line6_to_pod(line6pcm->line6); ucontrol->value.integer.value[0] = pod->monitor_level; return 0; } /* control put callback */ static int snd_pod_control_monitor_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct snd_line6_pcm *line6pcm = snd_kcontrol_chip(kcontrol); struct usb_line6_pod *pod = line6_to_pod(line6pcm->line6); if (ucontrol->value.integer.value[0] == pod->monitor_level) return 0; pod->monitor_level = ucontrol->value.integer.value[0]; pod_set_system_param_int(pod, ucontrol->value.integer.value[0], POD_MONITOR_LEVEL); return 1; } /* control definition */ static const struct snd_kcontrol_new pod_control_monitor = { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = "Monitor Playback Volume", .index = 0, .access = SNDRV_CTL_ELEM_ACCESS_READWRITE, .info = snd_pod_control_monitor_info, .get = snd_pod_control_monitor_get, .put = snd_pod_control_monitor_put }; /* Try to init POD device. */ static int pod_init(struct usb_line6 *line6, const struct usb_device_id *id) { int err; struct usb_line6_pod *pod = line6_to_pod(line6); line6->process_message = line6_pod_process_message; line6->startup = pod_startup; /* create sysfs entries: */ err = snd_card_add_dev_attr(line6->card, &pod_dev_attr_group); if (err < 0) return err; /* initialize PCM subsystem: */ err = line6_init_pcm(line6, &pod_pcm_properties); if (err < 0) return err; /* register monitor control: */ err = snd_ctl_add(line6->card, snd_ctl_new1(&pod_control_monitor, line6->line6pcm)); if (err < 0) return err; /* When the sound card is registered at this point, the PODxt Live displays "Invalid Code Error 07", so we do it later in the event handler. */ if (pod->line6.properties->capabilities & LINE6_CAP_CONTROL) { pod->monitor_level = POD_SYSTEM_INVALID; /* initiate startup procedure: */ schedule_delayed_work(&line6->startup_work, msecs_to_jiffies(POD_STARTUP_DELAY)); } return 0; } #define LINE6_DEVICE(prod) USB_DEVICE(0x0e41, prod) #define LINE6_IF_NUM(prod, n) USB_DEVICE_INTERFACE_NUMBER(0x0e41, prod, n) /* table of devices that work with this driver */ static const struct usb_device_id pod_id_table[] = { { LINE6_DEVICE(0x4250), .driver_info = LINE6_BASSPODXT }, { LINE6_DEVICE(0x4642), .driver_info = LINE6_BASSPODXTLIVE }, { LINE6_DEVICE(0x4252), .driver_info = LINE6_BASSPODXTPRO }, { LINE6_IF_NUM(0x5051, 1), .driver_info = LINE6_POCKETPOD }, { LINE6_DEVICE(0x5044), .driver_info = LINE6_PODXT }, { LINE6_IF_NUM(0x4650, 0), .driver_info = LINE6_PODXTLIVE_POD }, { LINE6_DEVICE(0x5050), .driver_info = LINE6_PODXTPRO }, {} }; MODULE_DEVICE_TABLE(usb, pod_id_table); static const struct line6_properties pod_properties_table[] = { [LINE6_BASSPODXT] = { .id = "BassPODxt", .name = "BassPODxt", .capabilities = LINE6_CAP_CONTROL | LINE6_CAP_CONTROL_MIDI | LINE6_CAP_PCM | LINE6_CAP_HWMON, .altsetting = 5, .ep_ctrl_r = 0x84, .ep_ctrl_w = 0x03, .ep_audio_r = 0x82, .ep_audio_w = 0x01, }, [LINE6_BASSPODXTLIVE] = { .id = "BassPODxtLive", .name = "BassPODxt Live", .capabilities = LINE6_CAP_CONTROL | LINE6_CAP_CONTROL_MIDI | LINE6_CAP_PCM | LINE6_CAP_HWMON, .altsetting = 1, .ep_ctrl_r = 0x84, .ep_ctrl_w = 0x03, .ep_audio_r = 0x82, .ep_audio_w = 0x01, }, [LINE6_BASSPODXTPRO] = { .id = "BassPODxtPro", .name = "BassPODxt Pro", .capabilities = LINE6_CAP_CONTROL | LINE6_CAP_CONTROL_MIDI | LINE6_CAP_PCM | LINE6_CAP_HWMON, .altsetting = 5, .ep_ctrl_r = 0x84, .ep_ctrl_w = 0x03, .ep_audio_r = 0x82, .ep_audio_w = 0x01, }, [LINE6_POCKETPOD] = { .id = "PocketPOD", .name = "Pocket POD", .capabilities = LINE6_CAP_CONTROL | LINE6_CAP_CONTROL_MIDI, .altsetting = 0, .ep_ctrl_r = 0x82, .ep_ctrl_w = 0x02, /* no audio channel */ }, [LINE6_PODXT] = { .id = "PODxt", .name = "PODxt", .capabilities = LINE6_CAP_CONTROL | LINE6_CAP_CONTROL_MIDI | LINE6_CAP_PCM | LINE6_CAP_HWMON, .altsetting = 5, .ep_ctrl_r = 0x84, .ep_ctrl_w = 0x03, .ep_audio_r = 0x82, .ep_audio_w = 0x01, }, [LINE6_PODXTLIVE_POD] = { .id = "PODxtLive", .name = "PODxt Live", .capabilities = LINE6_CAP_CONTROL | LINE6_CAP_CONTROL_MIDI | LINE6_CAP_PCM | LINE6_CAP_HWMON, .altsetting = 1, .ep_ctrl_r = 0x84, .ep_ctrl_w = 0x03, .ep_audio_r = 0x82, .ep_audio_w = 0x01, }, [LINE6_PODXTPRO] = { .id = "PODxtPro", .name = "PODxt Pro", .capabilities = LINE6_CAP_CONTROL | LINE6_CAP_CONTROL_MIDI | LINE6_CAP_PCM | LINE6_CAP_HWMON, .altsetting = 5, .ep_ctrl_r = 0x84, .ep_ctrl_w = 0x03, .ep_audio_r = 0x82, .ep_audio_w = 0x01, }, }; /* Probe USB device. */ static int pod_probe(struct usb_interface *interface, const struct usb_device_id *id) { return line6_probe(interface, id, "Line6-POD", &pod_properties_table[id->driver_info], pod_init, sizeof(struct usb_line6_pod)); } static struct usb_driver pod_driver = { .name = KBUILD_MODNAME, .probe = pod_probe, .disconnect = line6_disconnect, #ifdef CONFIG_PM .suspend = line6_suspend, .resume = line6_resume, .reset_resume = line6_resume, #endif .id_table = pod_id_table, }; module_usb_driver(pod_driver); MODULE_DESCRIPTION("Line 6 POD USB driver"); MODULE_LICENSE("GPL"); |
| 1 12 11 14 8 18 1 2 3 36 37 17 5 1 15 21 3 30 17 48 44 13 75 55 5 17 2 1 40 2 23 20 6 13 14 49 27 287 1 194 104 54 138 40 1 109 21 15 15 15 14 1 13 15 15 10 10 10 10 59 3 3 1 1 1 2 568 10 535 548 57 4 62 47 15 379 375 36 191 172 18 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 | // 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 <uapi/linux/pidfd.h> #include <linux/pidfs.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); static inline int scm_replace_pid(struct scm_cookie *scm, struct pid *pid) { int err; /* drop all previous references */ scm_destroy_cred(scm); err = pidfs_register_pid(pid); if (unlikely(err)) return err; scm->pid = pid; scm->creds.pid = pid_vnr(pid); return 0; } 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; if (!p->pid || pid_vnr(p->pid) != creds.pid) { struct pid *pid; err = -ESRCH; pid = find_get_pid(creds.pid); if (!pid) goto error; /* pass a struct pid reference from * find_get_pid() to scm_replace_pid(). */ err = scm_replace_pid(p, pid); if (err) { put_pid(pid); goto error; } } 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 (can_do_masked_user_access()) cm = masked_user_access_begin(cm); else 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); int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len, void *data) { /* Don't produce truncated CMSGs */ if (!msg->msg_control || msg->msg_controllen < CMSG_LEN(len)) return -ETOOSMALL; return put_cmsg(msg, level, type, len, data); } 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); #ifdef CONFIG_SECURITY_NETWORK static void scm_passec(struct sock *sk, struct msghdr *msg, struct scm_cookie *scm) { struct lsm_context ctx; int err; if (sk->sk_scm_security) { err = security_secid_to_secctx(scm->secid, &ctx); if (err >= 0) { put_cmsg(msg, SOL_SOCKET, SCM_SECURITY, ctx.len, ctx.context); security_release_secctx(&ctx); } } } static bool scm_has_secdata(struct sock *sk) { return sk->sk_scm_security; } #else static void scm_passec(struct sock *sk, struct msghdr *msg, struct scm_cookie *scm) { } static bool scm_has_secdata(struct sock *sk) { return false; } #endif static void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm) { struct file *pidfd_file = NULL; int len, pidfd; /* put_cmsg() doesn't return an error if CMSG is truncated, * that's why we need to opencode these checks here. */ if (msg->msg_flags & MSG_CMSG_COMPAT) len = sizeof(struct compat_cmsghdr) + sizeof(int); else len = sizeof(struct cmsghdr) + sizeof(int); if (msg->msg_controllen < len) { msg->msg_flags |= MSG_CTRUNC; return; } if (!scm->pid) return; pidfd = pidfd_prepare(scm->pid, PIDFD_STALE, &pidfd_file); if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) { if (pidfd_file) { put_unused_fd(pidfd); fput(pidfd_file); } return; } if (pidfd_file) fd_install(pidfd, pidfd_file); } static bool __scm_recv_common(struct sock *sk, struct msghdr *msg, struct scm_cookie *scm, int flags) { if (!msg->msg_control) { if (sk->sk_scm_credentials || sk->sk_scm_pidfd || scm->fp || scm_has_secdata(sk)) msg->msg_flags |= MSG_CTRUNC; scm_destroy(scm); return false; } if (sk->sk_scm_credentials) { struct user_namespace *current_ns = current_user_ns(); struct ucred ucreds = { .pid = scm->creds.pid, .uid = from_kuid_munged(current_ns, scm->creds.uid), .gid = from_kgid_munged(current_ns, scm->creds.gid), }; put_cmsg(msg, SOL_SOCKET, SCM_CREDENTIALS, sizeof(ucreds), &ucreds); } scm_passec(sk, msg, scm); if (scm->fp) scm_detach_fds(msg, scm); return true; } void scm_recv(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm, int flags) { if (!__scm_recv_common(sock->sk, msg, scm, flags)) return; scm_destroy_cred(scm); } EXPORT_SYMBOL(scm_recv); void scm_recv_unix(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm, int flags) { if (!__scm_recv_common(sock->sk, msg, scm, flags)) return; if (sock->sk->sk_scm_pidfd) scm_pidfd_recv(msg, scm); scm_destroy_cred(scm); } |
| 1 7267 7221 7234 1 128 | 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 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-long.sh // DO NOT MODIFY THIS FILE DIRECTLY #ifndef _LINUX_ATOMIC_LONG_H #define _LINUX_ATOMIC_LONG_H #include <linux/compiler.h> #include <asm/types.h> #ifdef CONFIG_64BIT typedef atomic64_t atomic_long_t; #define ATOMIC_LONG_INIT(i) ATOMIC64_INIT(i) #define atomic_long_cond_read_acquire atomic64_cond_read_acquire #define atomic_long_cond_read_relaxed atomic64_cond_read_relaxed #else typedef atomic_t atomic_long_t; #define ATOMIC_LONG_INIT(i) ATOMIC_INIT(i) #define atomic_long_cond_read_acquire atomic_cond_read_acquire #define atomic_long_cond_read_relaxed atomic_cond_read_relaxed #endif /** * raw_atomic_long_read() - atomic load with relaxed ordering * @v: pointer to atomic_long_t * * Atomically loads the value of @v with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_read() elsewhere. * * Return: The value loaded from @v. */ static __always_inline long raw_atomic_long_read(const atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_read(v); #else return raw_atomic_read(v); #endif } /** * raw_atomic_long_read_acquire() - atomic load with acquire ordering * @v: pointer to atomic_long_t * * Atomically loads the value of @v with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_read_acquire() elsewhere. * * Return: The value loaded from @v. */ static __always_inline long raw_atomic_long_read_acquire(const atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_read_acquire(v); #else return raw_atomic_read_acquire(v); #endif } /** * raw_atomic_long_set() - atomic set with relaxed ordering * @v: pointer to atomic_long_t * @i: long value to assign * * Atomically sets @v to @i with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_set() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_set(atomic_long_t *v, long i) { #ifdef CONFIG_64BIT raw_atomic64_set(v, i); #else raw_atomic_set(v, i); #endif } /** * raw_atomic_long_set_release() - atomic set with release ordering * @v: pointer to atomic_long_t * @i: long value to assign * * Atomically sets @v to @i with release ordering. * * Safe to use in noinstr code; prefer atomic_long_set_release() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_set_release(atomic_long_t *v, long i) { #ifdef CONFIG_64BIT raw_atomic64_set_release(v, i); #else raw_atomic_set_release(v, i); #endif } /** * raw_atomic_long_add() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_add() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_add(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_add(i, v); #else raw_atomic_add(i, v); #endif } /** * raw_atomic_long_add_return() - atomic add with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_add_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_add_return(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_return(i, v); #else return raw_atomic_add_return(i, v); #endif } /** * raw_atomic_long_add_return_acquire() - atomic add with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_add_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_add_return_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_return_acquire(i, v); #else return raw_atomic_add_return_acquire(i, v); #endif } /** * raw_atomic_long_add_return_release() - atomic add with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_add_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_add_return_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_return_release(i, v); #else return raw_atomic_add_return_release(i, v); #endif } /** * raw_atomic_long_add_return_relaxed() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_add_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_add_return_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_return_relaxed(i, v); #else return raw_atomic_add_return_relaxed(i, v); #endif } /** * raw_atomic_long_fetch_add() - atomic add with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_add() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_add(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_add(i, v); #else return raw_atomic_fetch_add(i, v); #endif } /** * raw_atomic_long_fetch_add_acquire() - atomic add with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_add_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_add_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_add_acquire(i, v); #else return raw_atomic_fetch_add_acquire(i, v); #endif } /** * raw_atomic_long_fetch_add_release() - atomic add with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_add_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_add_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_add_release(i, v); #else return raw_atomic_fetch_add_release(i, v); #endif } /** * raw_atomic_long_fetch_add_relaxed() - atomic add with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_add_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_add_relaxed(i, v); #else return raw_atomic_fetch_add_relaxed(i, v); #endif } /** * raw_atomic_long_sub() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_sub() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_sub(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_sub(i, v); #else raw_atomic_sub(i, v); #endif } /** * raw_atomic_long_sub_return() - atomic subtract with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_sub_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_sub_return(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_sub_return(i, v); #else return raw_atomic_sub_return(i, v); #endif } /** * raw_atomic_long_sub_return_acquire() - atomic subtract with acquire ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_sub_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_sub_return_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_sub_return_acquire(i, v); #else return raw_atomic_sub_return_acquire(i, v); #endif } /** * raw_atomic_long_sub_return_release() - atomic subtract with release ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_sub_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_sub_return_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_sub_return_release(i, v); #else return raw_atomic_sub_return_release(i, v); #endif } /** * raw_atomic_long_sub_return_relaxed() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_sub_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_sub_return_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_sub_return_relaxed(i, v); #else return raw_atomic_sub_return_relaxed(i, v); #endif } /** * raw_atomic_long_fetch_sub() - atomic subtract with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_sub() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_sub(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_sub(i, v); #else return raw_atomic_fetch_sub(i, v); #endif } /** * raw_atomic_long_fetch_sub_acquire() - atomic subtract with acquire ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_sub_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_sub_acquire(i, v); #else return raw_atomic_fetch_sub_acquire(i, v); #endif } /** * raw_atomic_long_fetch_sub_release() - atomic subtract with release ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_sub_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_sub_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_sub_release(i, v); #else return raw_atomic_fetch_sub_release(i, v); #endif } /** * raw_atomic_long_fetch_sub_relaxed() - atomic subtract with relaxed ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_sub_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_sub_relaxed(i, v); #else return raw_atomic_fetch_sub_relaxed(i, v); #endif } /** * raw_atomic_long_inc() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_inc() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_inc(atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_inc(v); #else raw_atomic_inc(v); #endif } /** * raw_atomic_long_inc_return() - atomic increment with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_inc_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_inc_return(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_return(v); #else return raw_atomic_inc_return(v); #endif } /** * raw_atomic_long_inc_return_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_inc_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_inc_return_acquire(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_return_acquire(v); #else return raw_atomic_inc_return_acquire(v); #endif } /** * raw_atomic_long_inc_return_release() - atomic increment with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_inc_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_inc_return_release(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_return_release(v); #else return raw_atomic_inc_return_release(v); #endif } /** * raw_atomic_long_inc_return_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_inc_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_inc_return_relaxed(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_return_relaxed(v); #else return raw_atomic_inc_return_relaxed(v); #endif } /** * raw_atomic_long_fetch_inc() - atomic increment with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_inc() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_inc(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_inc(v); #else return raw_atomic_fetch_inc(v); #endif } /** * raw_atomic_long_fetch_inc_acquire() - atomic increment with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_inc_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_inc_acquire(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_inc_acquire(v); #else return raw_atomic_fetch_inc_acquire(v); #endif } /** * raw_atomic_long_fetch_inc_release() - atomic increment with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_inc_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_inc_release(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_inc_release(v); #else return raw_atomic_fetch_inc_release(v); #endif } /** * raw_atomic_long_fetch_inc_relaxed() - atomic increment with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_inc_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_inc_relaxed(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_inc_relaxed(v); #else return raw_atomic_fetch_inc_relaxed(v); #endif } /** * raw_atomic_long_dec() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_dec() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_dec(atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_dec(v); #else raw_atomic_dec(v); #endif } /** * raw_atomic_long_dec_return() - atomic decrement with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_dec_return() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_dec_return(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_return(v); #else return raw_atomic_dec_return(v); #endif } /** * raw_atomic_long_dec_return_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_dec_return_acquire() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_dec_return_acquire(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_return_acquire(v); #else return raw_atomic_dec_return_acquire(v); #endif } /** * raw_atomic_long_dec_return_release() - atomic decrement with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_dec_return_release() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_dec_return_release(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_return_release(v); #else return raw_atomic_dec_return_release(v); #endif } /** * raw_atomic_long_dec_return_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_dec_return_relaxed() elsewhere. * * Return: The updated value of @v. */ static __always_inline long raw_atomic_long_dec_return_relaxed(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_return_relaxed(v); #else return raw_atomic_dec_return_relaxed(v); #endif } /** * raw_atomic_long_fetch_dec() - atomic decrement with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_dec() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_dec(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_dec(v); #else return raw_atomic_fetch_dec(v); #endif } /** * raw_atomic_long_fetch_dec_acquire() - atomic decrement with acquire ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_dec_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_dec_acquire(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_dec_acquire(v); #else return raw_atomic_fetch_dec_acquire(v); #endif } /** * raw_atomic_long_fetch_dec_release() - atomic decrement with release ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_dec_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_dec_release(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_dec_release(v); #else return raw_atomic_fetch_dec_release(v); #endif } /** * raw_atomic_long_fetch_dec_relaxed() - atomic decrement with relaxed ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_dec_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_dec_relaxed(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_dec_relaxed(v); #else return raw_atomic_fetch_dec_relaxed(v); #endif } /** * raw_atomic_long_and() - atomic bitwise AND with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_and() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_and(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_and(i, v); #else raw_atomic_and(i, v); #endif } /** * raw_atomic_long_fetch_and() - atomic bitwise AND with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_and() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_and(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_and(i, v); #else return raw_atomic_fetch_and(i, v); #endif } /** * raw_atomic_long_fetch_and_acquire() - atomic bitwise AND with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_and_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_and_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_and_acquire(i, v); #else return raw_atomic_fetch_and_acquire(i, v); #endif } /** * raw_atomic_long_fetch_and_release() - atomic bitwise AND with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_and_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_and_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_and_release(i, v); #else return raw_atomic_fetch_and_release(i, v); #endif } /** * raw_atomic_long_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_and_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_and_relaxed(i, v); #else return raw_atomic_fetch_and_relaxed(i, v); #endif } /** * raw_atomic_long_andnot() - atomic bitwise AND NOT with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_andnot() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_andnot(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_andnot(i, v); #else raw_atomic_andnot(i, v); #endif } /** * raw_atomic_long_fetch_andnot() - atomic bitwise AND NOT with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_andnot() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_andnot(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_andnot(i, v); #else return raw_atomic_fetch_andnot(i, v); #endif } /** * raw_atomic_long_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_andnot_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_andnot_acquire(i, v); #else return raw_atomic_fetch_andnot_acquire(i, v); #endif } /** * raw_atomic_long_fetch_andnot_release() - atomic bitwise AND NOT with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_andnot_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_andnot_release(i, v); #else return raw_atomic_fetch_andnot_release(i, v); #endif } /** * raw_atomic_long_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v & ~@i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_andnot_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_andnot_relaxed(i, v); #else return raw_atomic_fetch_andnot_relaxed(i, v); #endif } /** * raw_atomic_long_or() - atomic bitwise OR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_or() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_or(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_or(i, v); #else raw_atomic_or(i, v); #endif } /** * raw_atomic_long_fetch_or() - atomic bitwise OR with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_or() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_or(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_or(i, v); #else return raw_atomic_fetch_or(i, v); #endif } /** * raw_atomic_long_fetch_or_acquire() - atomic bitwise OR with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_or_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_or_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_or_acquire(i, v); #else return raw_atomic_fetch_or_acquire(i, v); #endif } /** * raw_atomic_long_fetch_or_release() - atomic bitwise OR with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_or_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_or_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_or_release(i, v); #else return raw_atomic_fetch_or_release(i, v); #endif } /** * raw_atomic_long_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v | @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_or_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_or_relaxed(i, v); #else return raw_atomic_fetch_or_relaxed(i, v); #endif } /** * raw_atomic_long_xor() - atomic bitwise XOR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_xor() elsewhere. * * Return: Nothing. */ static __always_inline void raw_atomic_long_xor(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT raw_atomic64_xor(i, v); #else raw_atomic_xor(i, v); #endif } /** * raw_atomic_long_fetch_xor() - atomic bitwise XOR with full ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_xor() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_xor(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_xor(i, v); #else return raw_atomic_fetch_xor(i, v); #endif } /** * raw_atomic_long_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_xor_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_xor_acquire(i, v); #else return raw_atomic_fetch_xor_acquire(i, v); #endif } /** * raw_atomic_long_fetch_xor_release() - atomic bitwise XOR with release ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_xor_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_xor_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_xor_release(i, v); #else return raw_atomic_fetch_xor_release(i, v); #endif } /** * raw_atomic_long_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering * @i: long value * @v: pointer to atomic_long_t * * Atomically updates @v to (@v ^ @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_fetch_xor_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_xor_relaxed(i, v); #else return raw_atomic_fetch_xor_relaxed(i, v); #endif } /** * raw_atomic_long_xchg() - atomic exchange with full ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with full ordering. * * Safe to use in noinstr code; prefer atomic_long_xchg() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_xchg(atomic_long_t *v, long new) { #ifdef CONFIG_64BIT return raw_atomic64_xchg(v, new); #else return raw_atomic_xchg(v, new); #endif } /** * raw_atomic_long_xchg_acquire() - atomic exchange with acquire ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_xchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_xchg_acquire(atomic_long_t *v, long new) { #ifdef CONFIG_64BIT return raw_atomic64_xchg_acquire(v, new); #else return raw_atomic_xchg_acquire(v, new); #endif } /** * raw_atomic_long_xchg_release() - atomic exchange with release ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with release ordering. * * Safe to use in noinstr code; prefer atomic_long_xchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_xchg_release(atomic_long_t *v, long new) { #ifdef CONFIG_64BIT return raw_atomic64_xchg_release(v, new); #else return raw_atomic_xchg_release(v, new); #endif } /** * raw_atomic_long_xchg_relaxed() - atomic exchange with relaxed ordering * @v: pointer to atomic_long_t * @new: long value to assign * * Atomically updates @v to @new with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_xchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_xchg_relaxed(atomic_long_t *v, long new) { #ifdef CONFIG_64BIT return raw_atomic64_xchg_relaxed(v, new); #else return raw_atomic_xchg_relaxed(v, new); #endif } /** * raw_atomic_long_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_cmpxchg(v, old, new); #else return raw_atomic_cmpxchg(v, old, new); #endif } /** * raw_atomic_long_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_acquire() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_cmpxchg_acquire(v, old, new); #else return raw_atomic_cmpxchg_acquire(v, old, new); #endif } /** * raw_atomic_long_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_release() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_cmpxchg_release(v, old, new); #else return raw_atomic_cmpxchg_release(v, old, new); #endif } /** * raw_atomic_long_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_long_t * @old: long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_relaxed() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_cmpxchg_relaxed(v, old, new); #else return raw_atomic_cmpxchg_relaxed(v, old, new); #endif } /** * raw_atomic_long_try_cmpxchg() - atomic compare and exchange with full ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_try_cmpxchg(v, (s64 *)old, new); #else return raw_atomic_try_cmpxchg(v, (int *)old, new); #endif } /** * raw_atomic_long_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_acquire() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_try_cmpxchg_acquire(v, (s64 *)old, new); #else return raw_atomic_try_cmpxchg_acquire(v, (int *)old, new); #endif } /** * raw_atomic_long_try_cmpxchg_release() - atomic compare and exchange with release ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_release() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_try_cmpxchg_release(v, (s64 *)old, new); #else return raw_atomic_try_cmpxchg_release(v, (int *)old, new); #endif } /** * raw_atomic_long_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering * @v: pointer to atomic_long_t * @old: pointer to long value to compare with * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. * Otherwise, @v is not modified, @old is updated to the current value of @v, * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_relaxed() elsewhere. * * Return: @true if the exchange occured, @false otherwise. */ static __always_inline bool raw_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { #ifdef CONFIG_64BIT return raw_atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new); #else return raw_atomic_try_cmpxchg_relaxed(v, (int *)old, new); #endif } /** * raw_atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_sub_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_long_sub_and_test(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_sub_and_test(i, v); #else return raw_atomic_sub_and_test(i, v); #endif } /** * raw_atomic_long_dec_and_test() - atomic decrement and test if zero with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_dec_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_long_dec_and_test(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_and_test(v); #else return raw_atomic_dec_and_test(v); #endif } /** * raw_atomic_long_inc_and_test() - atomic increment and test if zero with full ordering * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + 1) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_inc_and_test() elsewhere. * * Return: @true if the resulting value of @v is zero, @false otherwise. */ static __always_inline bool raw_atomic_long_inc_and_test(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_and_test(v); #else return raw_atomic_inc_and_test(v); #endif } /** * raw_atomic_long_add_negative() - atomic add and test if negative with full ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with full ordering. * * Safe to use in noinstr code; prefer atomic_long_add_negative() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_long_add_negative(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_negative(i, v); #else return raw_atomic_add_negative(i, v); #endif } /** * raw_atomic_long_add_negative_acquire() - atomic add and test if negative with acquire ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with acquire ordering. * * Safe to use in noinstr code; prefer atomic_long_add_negative_acquire() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_long_add_negative_acquire(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_negative_acquire(i, v); #else return raw_atomic_add_negative_acquire(i, v); #endif } /** * raw_atomic_long_add_negative_release() - atomic add and test if negative with release ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with release ordering. * * Safe to use in noinstr code; prefer atomic_long_add_negative_release() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_long_add_negative_release(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_negative_release(i, v); #else return raw_atomic_add_negative_release(i, v); #endif } /** * raw_atomic_long_add_negative_relaxed() - atomic add and test if negative with relaxed ordering * @i: long value to add * @v: pointer to atomic_long_t * * Atomically updates @v to (@v + @i) with relaxed ordering. * * Safe to use in noinstr code; prefer atomic_long_add_negative_relaxed() elsewhere. * * Return: @true if the resulting value of @v is negative, @false otherwise. */ static __always_inline bool raw_atomic_long_add_negative_relaxed(long i, atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_add_negative_relaxed(i, v); #else return raw_atomic_add_negative_relaxed(i, v); #endif } /** * raw_atomic_long_fetch_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_long_t * @a: long value to add * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_fetch_add_unless() elsewhere. * * Return: The original value of @v. */ static __always_inline long raw_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { #ifdef CONFIG_64BIT return raw_atomic64_fetch_add_unless(v, a, u); #else return raw_atomic_fetch_add_unless(v, a, u); #endif } /** * raw_atomic_long_add_unless() - atomic add unless value with full ordering * @v: pointer to atomic_long_t * @a: long value to add * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_add_unless() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_long_add_unless(atomic_long_t *v, long a, long u) { #ifdef CONFIG_64BIT return raw_atomic64_add_unless(v, a, u); #else return raw_atomic_add_unless(v, a, u); #endif } /** * raw_atomic_long_inc_not_zero() - atomic increment unless zero with full ordering * @v: pointer to atomic_long_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_inc_not_zero() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_long_inc_not_zero(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_not_zero(v); #else return raw_atomic_inc_not_zero(v); #endif } /** * raw_atomic_long_inc_unless_negative() - atomic increment unless negative with full ordering * @v: pointer to atomic_long_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_inc_unless_negative() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_long_inc_unless_negative(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_inc_unless_negative(v); #else return raw_atomic_inc_unless_negative(v); #endif } /** * raw_atomic_long_dec_unless_positive() - atomic decrement unless positive with full ordering * @v: pointer to atomic_long_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_dec_unless_positive() elsewhere. * * Return: @true if @v was updated, @false otherwise. */ static __always_inline bool raw_atomic_long_dec_unless_positive(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_unless_positive(v); #else return raw_atomic_dec_unless_positive(v); #endif } /** * raw_atomic_long_dec_if_positive() - atomic decrement if positive with full ordering * @v: pointer to atomic_long_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_dec_if_positive() elsewhere. * * Return: The old value of (@v - 1), regardless of whether @v was updated. */ static __always_inline long raw_atomic_long_dec_if_positive(atomic_long_t *v) { #ifdef CONFIG_64BIT return raw_atomic64_dec_if_positive(v); #else return raw_atomic_dec_if_positive(v); #endif } #endif /* _LINUX_ATOMIC_LONG_H */ // eadf183c3600b8b92b91839dd3be6bcc560c752d |
| 10 10 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Antonio Quartulli */ #include "bat_v_ogm.h" #include "main.h" #include <linux/atomic.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_ether.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/minmax.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> #include <linux/workqueue.h> #include <uapi/linux/batadv_packet.h> #include "hard-interface.h" #include "hash.h" #include "log.h" #include "originator.h" #include "routing.h" #include "send.h" #include "translation-table.h" #include "tvlv.h" /** * batadv_v_ogm_orig_get() - retrieve and possibly create an originator node * @bat_priv: the bat priv with all the mesh interface information * @addr: the address of the originator * * Return: the orig_node corresponding to the specified address. If such an * object does not exist, it is allocated here. In case of allocation failure * returns NULL. */ struct batadv_orig_node *batadv_v_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; int hash_added; orig_node = batadv_orig_hash_find(bat_priv, addr); if (orig_node) return orig_node; orig_node = batadv_orig_node_new(bat_priv, addr); if (!orig_node) return NULL; kref_get(&orig_node->refcount); hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, batadv_choose_orig, orig_node, &orig_node->hash_entry); if (hash_added != 0) { /* remove refcnt for newly created orig_node and hash entry */ batadv_orig_node_put(orig_node); batadv_orig_node_put(orig_node); orig_node = NULL; } return orig_node; } /** * batadv_v_ogm_start_queue_timer() - restart the OGM aggregation timer * @hard_iface: the interface to use to send the OGM */ static void batadv_v_ogm_start_queue_timer(struct batadv_hard_iface *hard_iface) { unsigned int msecs = BATADV_MAX_AGGREGATION_MS * 1000; /* msecs * [0.9, 1.1] */ msecs += get_random_u32_below(msecs / 5) - (msecs / 10); queue_delayed_work(batadv_event_workqueue, &hard_iface->bat_v.aggr_wq, msecs_to_jiffies(msecs / 1000)); } /** * batadv_v_ogm_start_timer() - restart the OGM sending timer * @bat_priv: the bat priv with all the mesh interface information */ static void batadv_v_ogm_start_timer(struct batadv_priv *bat_priv) { unsigned long msecs; /* this function may be invoked in different contexts (ogm rescheduling * or hard_iface activation), but the work timer should not be reset */ if (delayed_work_pending(&bat_priv->bat_v.ogm_wq)) return; msecs = atomic_read(&bat_priv->orig_interval) - BATADV_JITTER; msecs += get_random_u32_below(2 * BATADV_JITTER); queue_delayed_work(batadv_event_workqueue, &bat_priv->bat_v.ogm_wq, msecs_to_jiffies(msecs)); } /** * batadv_v_ogm_send_to_if() - send a batman ogm using a given interface * @skb: the OGM to send * @hard_iface: the interface to use to send the OGM */ static void batadv_v_ogm_send_to_if(struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); if (hard_iface->if_status != BATADV_IF_ACTIVE) { kfree_skb(skb); return; } batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_TX); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_TX_BYTES, skb->len + ETH_HLEN); batadv_send_broadcast_skb(skb, hard_iface); } /** * batadv_v_ogm_len() - OGMv2 packet length * @skb: the OGM to check * * Return: Length of the given OGMv2 packet, including tvlv length, excluding * ethernet header length. */ static unsigned int batadv_v_ogm_len(struct sk_buff *skb) { struct batadv_ogm2_packet *ogm_packet; ogm_packet = (struct batadv_ogm2_packet *)skb->data; return BATADV_OGM2_HLEN + ntohs(ogm_packet->tvlv_len); } /** * batadv_v_ogm_queue_left() - check if given OGM still fits aggregation queue * @skb: the OGM to check * @hard_iface: the interface to use to send the OGM * * Caller needs to hold the hard_iface->bat_v.aggr_list.lock. * * Return: True, if the given OGMv2 packet still fits, false otherwise. */ static bool batadv_v_ogm_queue_left(struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { unsigned int max = min_t(unsigned int, hard_iface->net_dev->mtu, BATADV_MAX_AGGREGATION_BYTES); unsigned int ogm_len = batadv_v_ogm_len(skb); lockdep_assert_held(&hard_iface->bat_v.aggr_list.lock); return hard_iface->bat_v.aggr_len + ogm_len <= max; } /** * batadv_v_ogm_aggr_list_free - free all elements in an aggregation queue * @hard_iface: the interface holding the aggregation queue * * Empties the OGMv2 aggregation queue and frees all the skbs it contains. * * Caller needs to hold the hard_iface->bat_v.aggr_list.lock. */ static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface) { lockdep_assert_held(&hard_iface->bat_v.aggr_list.lock); __skb_queue_purge(&hard_iface->bat_v.aggr_list); hard_iface->bat_v.aggr_len = 0; } /** * batadv_v_ogm_aggr_send() - flush & send aggregation queue * @hard_iface: the interface with the aggregation queue to flush * * Aggregates all OGMv2 packets currently in the aggregation queue into a * single OGMv2 packet and transmits this aggregate. * * The aggregation queue is empty after this call. * * Caller needs to hold the hard_iface->bat_v.aggr_list.lock. */ static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface) { unsigned int aggr_len = hard_iface->bat_v.aggr_len; struct sk_buff *skb_aggr; unsigned int ogm_len; struct sk_buff *skb; lockdep_assert_held(&hard_iface->bat_v.aggr_list.lock); if (!aggr_len) return; skb_aggr = dev_alloc_skb(aggr_len + ETH_HLEN + NET_IP_ALIGN); if (!skb_aggr) { batadv_v_ogm_aggr_list_free(hard_iface); return; } skb_reserve(skb_aggr, ETH_HLEN + NET_IP_ALIGN); skb_reset_network_header(skb_aggr); while ((skb = __skb_dequeue(&hard_iface->bat_v.aggr_list))) { hard_iface->bat_v.aggr_len -= batadv_v_ogm_len(skb); ogm_len = batadv_v_ogm_len(skb); skb_put_data(skb_aggr, skb->data, ogm_len); consume_skb(skb); } batadv_v_ogm_send_to_if(skb_aggr, hard_iface); } /** * batadv_v_ogm_queue_on_if() - queue a batman ogm on a given interface * @skb: the OGM to queue * @hard_iface: the interface to queue the OGM on */ static void batadv_v_ogm_queue_on_if(struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); if (!atomic_read(&bat_priv->aggregated_ogms)) { batadv_v_ogm_send_to_if(skb, hard_iface); return; } spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); if (!batadv_v_ogm_queue_left(skb, hard_iface)) batadv_v_ogm_aggr_send(hard_iface); hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb); __skb_queue_tail(&hard_iface->bat_v.aggr_list, skb); spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock); } /** * batadv_v_ogm_send_meshif() - periodic worker broadcasting the own OGM * @bat_priv: the bat priv with all the mesh interface information */ static void batadv_v_ogm_send_meshif(struct batadv_priv *bat_priv) { struct batadv_hard_iface *hard_iface; struct batadv_ogm2_packet *ogm_packet; struct sk_buff *skb, *skb_tmp; unsigned char *ogm_buff; struct list_head *iter; int ogm_buff_len; u16 tvlv_len = 0; int ret; lockdep_assert_held(&bat_priv->bat_v.ogm_buff_mutex); if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) goto out; ogm_buff = bat_priv->bat_v.ogm_buff; ogm_buff_len = bat_priv->bat_v.ogm_buff_len; /* tt changes have to be committed before the tvlv data is * appended as it may alter the tt tvlv container */ batadv_tt_local_commit_changes(bat_priv); tvlv_len = batadv_tvlv_container_ogm_append(bat_priv, &ogm_buff, &ogm_buff_len, BATADV_OGM2_HLEN); bat_priv->bat_v.ogm_buff = ogm_buff; bat_priv->bat_v.ogm_buff_len = ogm_buff_len; skb = netdev_alloc_skb_ip_align(NULL, ETH_HLEN + ogm_buff_len); if (!skb) goto reschedule; skb_reserve(skb, ETH_HLEN); skb_put_data(skb, ogm_buff, ogm_buff_len); ogm_packet = (struct batadv_ogm2_packet *)skb->data; ogm_packet->seqno = htonl(atomic_read(&bat_priv->bat_v.ogm_seqno)); atomic_inc(&bat_priv->bat_v.ogm_seqno); ogm_packet->tvlv_len = htons(tvlv_len); /* broadcast on every interface */ rcu_read_lock(); netdev_for_each_lower_private_rcu(bat_priv->mesh_iface, hard_iface, iter) { if (!kref_get_unless_zero(&hard_iface->refcount)) continue; ret = batadv_hardif_no_broadcast(hard_iface, NULL, NULL); if (ret) { char *type; 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, "OGM2 from ourselves on %s suppressed: %s\n", hard_iface->net_dev->name, type); batadv_hardif_put(hard_iface); continue; } batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Sending own OGM2 packet (originator %pM, seqno %u, throughput %u, TTL %d) on interface %s [%pM]\n", ogm_packet->orig, ntohl(ogm_packet->seqno), ntohl(ogm_packet->throughput), ogm_packet->ttl, hard_iface->net_dev->name, hard_iface->net_dev->dev_addr); /* this skb gets consumed by batadv_v_ogm_send_to_if() */ skb_tmp = skb_clone(skb, GFP_ATOMIC); if (!skb_tmp) { batadv_hardif_put(hard_iface); break; } batadv_v_ogm_queue_on_if(skb_tmp, hard_iface); batadv_hardif_put(hard_iface); } rcu_read_unlock(); consume_skb(skb); reschedule: batadv_v_ogm_start_timer(bat_priv); out: return; } /** * batadv_v_ogm_send() - periodic worker broadcasting the own OGM * @work: work queue item */ static void batadv_v_ogm_send(struct work_struct *work) { struct batadv_priv_bat_v *bat_v; struct batadv_priv *bat_priv; bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work); bat_priv = container_of(bat_v, struct batadv_priv, bat_v); mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); batadv_v_ogm_send_meshif(bat_priv); mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); } /** * batadv_v_ogm_aggr_work() - OGM queue periodic task per interface * @work: work queue item * * Emits aggregated OGM messages in regular intervals. */ void batadv_v_ogm_aggr_work(struct work_struct *work) { struct batadv_hard_iface_bat_v *batv; struct batadv_hard_iface *hard_iface; batv = container_of(work, struct batadv_hard_iface_bat_v, aggr_wq.work); hard_iface = container_of(batv, struct batadv_hard_iface, bat_v); spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); batadv_v_ogm_aggr_send(hard_iface); spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock); batadv_v_ogm_start_queue_timer(hard_iface); } /** * batadv_v_ogm_iface_enable() - prepare an interface for B.A.T.M.A.N. V * @hard_iface: the interface to prepare * * Takes care of scheduling its own OGM sending routine for this interface. * * Return: 0 on success or a negative error code otherwise */ int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); batadv_v_ogm_start_queue_timer(hard_iface); batadv_v_ogm_start_timer(bat_priv); return 0; } /** * batadv_v_ogm_iface_disable() - release OGM interface private resources * @hard_iface: interface for which the resources have to be released */ void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface) { cancel_delayed_work_sync(&hard_iface->bat_v.aggr_wq); spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); batadv_v_ogm_aggr_list_free(hard_iface); spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock); } /** * batadv_v_ogm_primary_iface_set() - set a new primary interface * @primary_iface: the new primary interface */ void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface) { struct batadv_priv *bat_priv = netdev_priv(primary_iface->mesh_iface); struct batadv_ogm2_packet *ogm_packet; mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); if (!bat_priv->bat_v.ogm_buff) goto unlock; ogm_packet = (struct batadv_ogm2_packet *)bat_priv->bat_v.ogm_buff; ether_addr_copy(ogm_packet->orig, primary_iface->net_dev->dev_addr); unlock: mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); } /** * batadv_v_forward_penalty() - apply a penalty to the throughput metric * forwarded with B.A.T.M.A.N. V OGMs * @bat_priv: the bat priv with all the mesh interface information * @if_incoming: the interface where the OGM has been received * @if_outgoing: the interface where the OGM has to be forwarded to * @throughput: the current throughput * * Apply a penalty on the current throughput metric value based on the * characteristic of the interface where the OGM has been received. * * Initially the per hardif hop penalty is applied to the throughput. After * that the return value is then computed as follows: * - throughput * 50% if the incoming and outgoing interface are the * same WiFi interface and the throughput is above * 1MBit/s * - throughput if the outgoing interface is the default * interface (i.e. this OGM is processed for the * internal table and not forwarded) * - throughput * node hop penalty otherwise * * Return: the penalised throughput metric. */ static u32 batadv_v_forward_penalty(struct batadv_priv *bat_priv, struct batadv_hard_iface *if_incoming, struct batadv_hard_iface *if_outgoing, u32 throughput) { int if_hop_penalty = atomic_read(&if_incoming->hop_penalty); int hop_penalty = atomic_read(&bat_priv->hop_penalty); int hop_penalty_max = BATADV_TQ_MAX_VALUE; /* Apply per hardif hop penalty */ throughput = throughput * (hop_penalty_max - if_hop_penalty) / hop_penalty_max; /* Don't apply hop penalty in default originator table. */ if (if_outgoing == BATADV_IF_DEFAULT) return throughput; /* Forwarding on the same WiFi interface cuts the throughput in half * due to the store & forward characteristics of WIFI. * Very low throughput values are the exception. */ if (throughput > 10 && if_incoming == if_outgoing && !(if_incoming->bat_v.flags & BATADV_FULL_DUPLEX)) return throughput / 2; /* hop penalty of 255 equals 100% */ return throughput * (hop_penalty_max - hop_penalty) / hop_penalty_max; } /** * batadv_v_ogm_forward() - check conditions and forward an OGM to the given * outgoing interface * @bat_priv: the bat priv with all the mesh interface information * @ogm_received: previously received OGM to be forwarded * @orig_node: the originator which has been updated * @neigh_node: the neigh_node through with the OGM has been received * @if_incoming: the interface on which this OGM was received on * @if_outgoing: the interface to which the OGM has to be forwarded to * * Forward an OGM to an interface after having altered the throughput metric and * the TTL value contained in it. The original OGM isn't modified. */ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv, const struct batadv_ogm2_packet *ogm_received, struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node, struct batadv_hard_iface *if_incoming, struct batadv_hard_iface *if_outgoing) { struct batadv_neigh_ifinfo *neigh_ifinfo = NULL; struct batadv_orig_ifinfo *orig_ifinfo = NULL; struct batadv_neigh_node *router = NULL; struct batadv_ogm2_packet *ogm_forward; unsigned char *skb_buff; struct sk_buff *skb; size_t packet_len; u16 tvlv_len; /* only forward for specific interfaces, not for the default one. */ if (if_outgoing == BATADV_IF_DEFAULT) goto out; orig_ifinfo = batadv_orig_ifinfo_new(orig_node, if_outgoing); if (!orig_ifinfo) goto out; /* acquire possibly updated router */ router = batadv_orig_router_get(orig_node, if_outgoing); /* strict rule: forward packets coming from the best next hop only */ if (neigh_node != router) goto out; /* don't forward the same seqno twice on one interface */ if (orig_ifinfo->last_seqno_forwarded == ntohl(ogm_received->seqno)) goto out; orig_ifinfo->last_seqno_forwarded = ntohl(ogm_received->seqno); if (ogm_received->ttl <= 1) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "ttl exceeded\n"); goto out; } neigh_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing); if (!neigh_ifinfo) goto out; tvlv_len = ntohs(ogm_received->tvlv_len); packet_len = BATADV_OGM2_HLEN + tvlv_len; skb = netdev_alloc_skb_ip_align(if_outgoing->net_dev, ETH_HLEN + packet_len); if (!skb) goto out; skb_reserve(skb, ETH_HLEN); skb_buff = skb_put_data(skb, ogm_received, packet_len); /* apply forward penalty */ ogm_forward = (struct batadv_ogm2_packet *)skb_buff; ogm_forward->throughput = htonl(neigh_ifinfo->bat_v.throughput); ogm_forward->ttl--; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Forwarding OGM2 packet on %s: throughput %u, ttl %u, received via %s\n", if_outgoing->net_dev->name, ntohl(ogm_forward->throughput), ogm_forward->ttl, if_incoming->net_dev->name); batadv_v_ogm_queue_on_if(skb, if_outgoing); out: batadv_orig_ifinfo_put(orig_ifinfo); batadv_neigh_node_put(router); batadv_neigh_ifinfo_put(neigh_ifinfo); } /** * batadv_v_ogm_metric_update() - update route metric based on OGM * @bat_priv: the bat priv with all the mesh interface information * @ogm2: OGM2 structure * @orig_node: Originator structure for which the OGM has been received * @neigh_node: the neigh_node through with the OGM has been received * @if_incoming: the interface where this packet was received * @if_outgoing: the interface for which the packet should be considered * * Return: * 1 if the OGM is new, * 0 if it is not new but valid, * <0 on error (e.g. old OGM) */ static int batadv_v_ogm_metric_update(struct batadv_priv *bat_priv, const struct batadv_ogm2_packet *ogm2, struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node, struct batadv_hard_iface *if_incoming, struct batadv_hard_iface *if_outgoing) { struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_ifinfo *neigh_ifinfo = NULL; bool protection_started = false; int ret = -EINVAL; u32 path_throughput; s32 seq_diff; orig_ifinfo = batadv_orig_ifinfo_new(orig_node, if_outgoing); if (!orig_ifinfo) goto out; seq_diff = ntohl(ogm2->seqno) - orig_ifinfo->last_real_seqno; if (!hlist_empty(&orig_node->neigh_list) && batadv_window_protected(bat_priv, seq_diff, BATADV_OGM_MAX_AGE, &orig_ifinfo->batman_seqno_reset, &protection_started)) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: packet within window protection time from %pM\n", ogm2->orig); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Last reset: %ld, %ld\n", orig_ifinfo->batman_seqno_reset, jiffies); goto out; } /* drop packets with old seqnos, however accept the first packet after * a host has been rebooted. */ if (seq_diff < 0 && !protection_started) goto out; neigh_node->last_seen = jiffies; orig_node->last_seen = jiffies; orig_ifinfo->last_real_seqno = ntohl(ogm2->seqno); orig_ifinfo->last_ttl = ogm2->ttl; neigh_ifinfo = batadv_neigh_ifinfo_new(neigh_node, if_outgoing); if (!neigh_ifinfo) goto out; path_throughput = batadv_v_forward_penalty(bat_priv, if_incoming, if_outgoing, ntohl(ogm2->throughput)); neigh_ifinfo->bat_v.throughput = path_throughput; neigh_ifinfo->bat_v.last_seqno = ntohl(ogm2->seqno); neigh_ifinfo->last_ttl = ogm2->ttl; if (seq_diff > 0 || protection_started) ret = 1; else ret = 0; out: batadv_orig_ifinfo_put(orig_ifinfo); batadv_neigh_ifinfo_put(neigh_ifinfo); return ret; } /** * batadv_v_ogm_route_update() - update routes based on OGM * @bat_priv: the bat priv with all the mesh interface information * @ethhdr: the Ethernet header of the OGM2 * @ogm2: OGM2 structure * @orig_node: Originator structure for which the OGM has been received * @neigh_node: the neigh_node through with the OGM has been received * @if_incoming: the interface where this packet was received * @if_outgoing: the interface for which the packet should be considered * * Return: true if the packet should be forwarded, false otherwise */ static bool batadv_v_ogm_route_update(struct batadv_priv *bat_priv, const struct ethhdr *ethhdr, const struct batadv_ogm2_packet *ogm2, struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node, struct batadv_hard_iface *if_incoming, struct batadv_hard_iface *if_outgoing) { struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_neigh_node; struct batadv_neigh_node *orig_neigh_router = NULL; struct batadv_neigh_ifinfo *router_ifinfo = NULL, *neigh_ifinfo = NULL; u32 router_throughput, neigh_throughput; u32 router_last_seqno; u32 neigh_last_seqno; s32 neigh_seq_diff; bool forward = false; orig_neigh_node = batadv_v_ogm_orig_get(bat_priv, ethhdr->h_source); if (!orig_neigh_node) goto out; orig_neigh_router = batadv_orig_router_get(orig_neigh_node, if_outgoing); /* drop packet if sender is not a direct neighbor and if we * don't route towards it */ router = batadv_orig_router_get(orig_node, if_outgoing); if (router && router->orig_node != orig_node && !orig_neigh_router) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: OGM via unknown neighbor!\n"); goto out; } /* Mark the OGM to be considered for forwarding, and update routes * if needed. */ forward = true; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Searching and updating originator entry of received packet\n"); /* if this neighbor already is our next hop there is nothing * to change */ if (router == neigh_node) goto out; /* don't consider neighbours with worse throughput. * also switch route if this seqno is BATADV_V_MAX_ORIGDIFF newer than * the last received seqno from our best next hop. */ if (router) { router_ifinfo = batadv_neigh_ifinfo_get(router, if_outgoing); neigh_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing); /* if these are not allocated, something is wrong. */ if (!router_ifinfo || !neigh_ifinfo) goto out; neigh_last_seqno = neigh_ifinfo->bat_v.last_seqno; router_last_seqno = router_ifinfo->bat_v.last_seqno; neigh_seq_diff = neigh_last_seqno - router_last_seqno; router_throughput = router_ifinfo->bat_v.throughput; neigh_throughput = neigh_ifinfo->bat_v.throughput; if (neigh_seq_diff < BATADV_OGM_MAX_ORIGDIFF && router_throughput >= neigh_throughput) goto out; } batadv_update_route(bat_priv, orig_node, if_outgoing, neigh_node); out: batadv_neigh_node_put(router); batadv_neigh_node_put(orig_neigh_router); batadv_orig_node_put(orig_neigh_node); batadv_neigh_ifinfo_put(router_ifinfo); batadv_neigh_ifinfo_put(neigh_ifinfo); return forward; } /** * batadv_v_ogm_process_per_outif() - process a batman v OGM for an outgoing if * @bat_priv: the bat priv with all the mesh interface information * @ethhdr: the Ethernet header of the OGM2 * @ogm2: OGM2 structure * @orig_node: Originator structure for which the OGM has been received * @neigh_node: the neigh_node through with the OGM has been received * @if_incoming: the interface where this packet was received * @if_outgoing: the interface for which the packet should be considered */ static void batadv_v_ogm_process_per_outif(struct batadv_priv *bat_priv, const struct ethhdr *ethhdr, const struct batadv_ogm2_packet *ogm2, struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node, struct batadv_hard_iface *if_incoming, struct batadv_hard_iface *if_outgoing) { int seqno_age; bool forward; /* first, update the metric with according sanity checks */ seqno_age = batadv_v_ogm_metric_update(bat_priv, ogm2, orig_node, neigh_node, if_incoming, if_outgoing); /* outdated sequence numbers are to be discarded */ if (seqno_age < 0) return; /* only unknown & newer OGMs contain TVLVs we are interested in */ if (seqno_age > 0 && if_outgoing == BATADV_IF_DEFAULT) batadv_tvlv_containers_process(bat_priv, BATADV_OGM2, orig_node, NULL, (unsigned char *)(ogm2 + 1), ntohs(ogm2->tvlv_len)); /* if the metric update went through, update routes if needed */ forward = batadv_v_ogm_route_update(bat_priv, ethhdr, ogm2, orig_node, neigh_node, if_incoming, if_outgoing); /* if the routes have been processed correctly, check and forward */ if (forward) batadv_v_ogm_forward(bat_priv, ogm2, orig_node, neigh_node, if_incoming, if_outgoing); } /** * batadv_v_ogm_aggr_packet() - checks if there is another OGM aggregated * @buff_pos: current position in the skb * @packet_len: total length of the skb * @ogm2_packet: potential OGM2 in buffer * * Return: true if there is enough space for another OGM, false otherwise. */ static bool batadv_v_ogm_aggr_packet(int buff_pos, int packet_len, const struct batadv_ogm2_packet *ogm2_packet) { int next_buff_pos = 0; /* check if there is enough space for the header */ next_buff_pos += buff_pos + sizeof(*ogm2_packet); if (next_buff_pos > packet_len) return false; /* check if there is enough space for the optional TVLV */ next_buff_pos += ntohs(ogm2_packet->tvlv_len); return next_buff_pos <= packet_len; } /** * batadv_v_ogm_process() - process an incoming batman v OGM * @skb: the skb containing the OGM * @ogm_offset: offset to the OGM which should be processed (for aggregates) * @if_incoming: the interface where this packet was received */ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, struct batadv_hard_iface *if_incoming) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface); struct ethhdr *ethhdr; struct batadv_orig_node *orig_node = NULL; struct batadv_hardif_neigh_node *hardif_neigh = NULL; struct batadv_neigh_node *neigh_node = NULL; struct batadv_hard_iface *hard_iface; struct batadv_ogm2_packet *ogm_packet; u32 ogm_throughput, link_throughput, path_throughput; struct list_head *iter; int ret; ethhdr = eth_hdr(skb); ogm_packet = (struct batadv_ogm2_packet *)(skb->data + ogm_offset); ogm_throughput = ntohl(ogm_packet->throughput); batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Received OGM2 packet via NB: %pM, IF: %s [%pM] (from OG: %pM, seqno %u, throughput %u, TTL %u, V %u, tvlv_len %u)\n", ethhdr->h_source, if_incoming->net_dev->name, if_incoming->net_dev->dev_addr, ogm_packet->orig, ntohl(ogm_packet->seqno), ogm_throughput, ogm_packet->ttl, ogm_packet->version, ntohs(ogm_packet->tvlv_len)); if (batadv_is_my_mac(bat_priv, ogm_packet->orig)) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: originator packet from ourself\n"); return; } /* If the throughput metric is 0, immediately drop the packet. No need * to create orig_node / neigh_node for an unusable route. */ if (ogm_throughput == 0) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: originator packet with throughput metric of 0\n"); return; } /* require ELP packets be to received from this neighbor first */ hardif_neigh = batadv_hardif_neigh_get(if_incoming, ethhdr->h_source); if (!hardif_neigh) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Drop packet: OGM via unknown neighbor!\n"); goto out; } orig_node = batadv_v_ogm_orig_get(bat_priv, ogm_packet->orig); if (!orig_node) goto out; neigh_node = batadv_neigh_node_get_or_create(orig_node, if_incoming, ethhdr->h_source); if (!neigh_node) goto out; /* Update the received throughput metric to match the link * characteristic: * - If this OGM traveled one hop so far (emitted by single hop * neighbor) the path throughput metric equals the link throughput. * - For OGMs traversing more than hop the path throughput metric is * the smaller of the path throughput and the link throughput. */ link_throughput = ewma_throughput_read(&hardif_neigh->bat_v.throughput); path_throughput = min_t(u32, link_throughput, ogm_throughput); ogm_packet->throughput = htonl(path_throughput); batadv_v_ogm_process_per_outif(bat_priv, ethhdr, ogm_packet, orig_node, neigh_node, if_incoming, BATADV_IF_DEFAULT); rcu_read_lock(); netdev_for_each_lower_private_rcu(bat_priv->mesh_iface, hard_iface, iter) { if (hard_iface->if_status != BATADV_IF_ACTIVE) continue; if (!kref_get_unless_zero(&hard_iface->refcount)) continue; ret = batadv_hardif_no_broadcast(hard_iface, ogm_packet->orig, hardif_neigh->orig); if (ret) { char *type; 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, "OGM2 packet from %pM on %s suppressed: %s\n", ogm_packet->orig, hard_iface->net_dev->name, type); batadv_hardif_put(hard_iface); continue; } batadv_v_ogm_process_per_outif(bat_priv, ethhdr, ogm_packet, orig_node, neigh_node, if_incoming, hard_iface); batadv_hardif_put(hard_iface); } rcu_read_unlock(); out: batadv_orig_node_put(orig_node); batadv_neigh_node_put(neigh_node); batadv_hardif_neigh_put(hardif_neigh); } /** * batadv_v_ogm_packet_recv() - OGM2 receiving handler * @skb: the received OGM * @if_incoming: the interface where this OGM has been received * * Return: NET_RX_SUCCESS and consume the skb on success or returns NET_RX_DROP * (without freeing the skb) on failure */ int batadv_v_ogm_packet_recv(struct sk_buff *skb, struct batadv_hard_iface *if_incoming) { struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface); struct batadv_ogm2_packet *ogm_packet; struct ethhdr *ethhdr; int ogm_offset; u8 *packet_pos; int ret = NET_RX_DROP; /* did we receive a OGM2 packet on an interface that does not have * B.A.T.M.A.N. V enabled ? */ if (strcmp(bat_priv->algo_ops->name, "BATMAN_V") != 0) goto free_skb; if (!batadv_check_management_packet(skb, if_incoming, BATADV_OGM2_HLEN)) goto free_skb; ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_RX); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_RX_BYTES, skb->len + ETH_HLEN); ogm_offset = 0; ogm_packet = (struct batadv_ogm2_packet *)skb->data; while (batadv_v_ogm_aggr_packet(ogm_offset, skb_headlen(skb), ogm_packet)) { batadv_v_ogm_process(skb, ogm_offset, if_incoming); ogm_offset += BATADV_OGM2_HLEN; ogm_offset += ntohs(ogm_packet->tvlv_len); packet_pos = skb->data + ogm_offset; ogm_packet = (struct batadv_ogm2_packet *)packet_pos; } ret = NET_RX_SUCCESS; free_skb: if (ret == NET_RX_SUCCESS) consume_skb(skb); else kfree_skb(skb); return ret; } /** * batadv_v_ogm_init() - initialise the OGM2 engine * @bat_priv: the bat priv with all the mesh interface information * * Return: 0 on success or a negative error code in case of failure */ int batadv_v_ogm_init(struct batadv_priv *bat_priv) { struct batadv_ogm2_packet *ogm_packet; unsigned char *ogm_buff; u32 random_seqno; bat_priv->bat_v.ogm_buff_len = BATADV_OGM2_HLEN; ogm_buff = kzalloc(bat_priv->bat_v.ogm_buff_len, GFP_ATOMIC); if (!ogm_buff) return -ENOMEM; bat_priv->bat_v.ogm_buff = ogm_buff; ogm_packet = (struct batadv_ogm2_packet *)ogm_buff; ogm_packet->packet_type = BATADV_OGM2; ogm_packet->version = BATADV_COMPAT_VERSION; ogm_packet->ttl = BATADV_TTL; ogm_packet->flags = BATADV_NO_FLAGS; ogm_packet->throughput = htonl(BATADV_THROUGHPUT_MAX_VALUE); /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); atomic_set(&bat_priv->bat_v.ogm_seqno, random_seqno); INIT_DELAYED_WORK(&bat_priv->bat_v.ogm_wq, batadv_v_ogm_send); mutex_init(&bat_priv->bat_v.ogm_buff_mutex); return 0; } /** * batadv_v_ogm_free() - free OGM private resources * @bat_priv: the bat priv with all the mesh interface information */ void batadv_v_ogm_free(struct batadv_priv *bat_priv) { cancel_delayed_work_sync(&bat_priv->bat_v.ogm_wq); mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); kfree(bat_priv->bat_v.ogm_buff); bat_priv->bat_v.ogm_buff = NULL; bat_priv->bat_v.ogm_buff_len = 0; mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); } |
| 24 1 1 5 15 21 14 29 1 4 24 3 34 5 9 14 11 3 3 3 40 28 11 25 1 1 1 1 6 1 1 48 28 28 16 39 34 4 38 2 43 56 57 32 1 10 4 6 56 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/exportfs.h> #include <linux/fs_struct.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <linux/nsfs.h> #include "internal.h" #include "mount.h" static long do_sys_name_to_handle(const struct path *path, struct file_handle __user *ufh, void __user *mnt_id, bool unique_mntid, int fh_flags) { long retval; struct file_handle f_handle; int handle_dwords, handle_bytes; struct file_handle *handle = NULL; /* * We need to make sure whether the file system support decoding of * the file handle if decodeable file handle was requested. */ if (!exportfs_can_encode_fh(path->dentry->d_sb->s_export_op, fh_flags)) return -EOPNOTSUPP; /* * A request to encode a connectable handle for a disconnected dentry * is unexpected since AT_EMPTY_PATH is not allowed. */ if (fh_flags & EXPORT_FH_CONNECTABLE && WARN_ON(path->dentry->d_flags & DCACHE_DISCONNECTED)) return -EINVAL; if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) return -EFAULT; if (f_handle.handle_bytes > MAX_HANDLE_SZ) return -EINVAL; handle = kzalloc(struct_size(handle, f_handle, f_handle.handle_bytes), GFP_KERNEL); if (!handle) return -ENOMEM; /* convert handle size to multiple of sizeof(u32) */ handle_dwords = f_handle.handle_bytes >> 2; /* Encode a possibly decodeable/connectable file handle */ retval = exportfs_encode_fh(path->dentry, (struct fid *)handle->f_handle, &handle_dwords, fh_flags); handle->handle_type = retval; /* convert handle size to bytes */ handle_bytes = handle_dwords * sizeof(u32); handle->handle_bytes = handle_bytes; if ((handle->handle_bytes > f_handle.handle_bytes) || (retval == FILEID_INVALID) || (retval < 0)) { /* As per old exportfs_encode_fh documentation * we could return ENOSPC to indicate overflow * But file system returned 255 always. So handle * both the values */ if (retval == FILEID_INVALID || retval == -ENOSPC) retval = -EOVERFLOW; /* * set the handle size to zero so we copy only * non variable part of the file_handle */ handle_bytes = 0; } else { /* * When asked to encode a connectable file handle, encode this * property in the file handle itself, so that we later know * how to decode it. * For sanity, also encode in the file handle if the encoded * object is a directory and verify this during decode, because * decoding directory file handles is quite different than * decoding connectable non-directory file handles. */ if (fh_flags & EXPORT_FH_CONNECTABLE) { handle->handle_type |= FILEID_IS_CONNECTABLE; if (d_is_dir(path->dentry)) handle->handle_type |= FILEID_IS_DIR; } retval = 0; } /* copy the mount id */ if (unique_mntid) { if (put_user(real_mount(path->mnt)->mnt_id_unique, (u64 __user *) mnt_id)) retval = -EFAULT; } else { if (put_user(real_mount(path->mnt)->mnt_id, (int __user *) mnt_id)) retval = -EFAULT; } /* copy the handle */ if (retval != -EFAULT && copy_to_user(ufh, handle, struct_size(handle, f_handle, handle_bytes))) retval = -EFAULT; kfree(handle); return retval; } /** * sys_name_to_handle_at: convert name to handle * @dfd: directory relative to which name is interpreted if not absolute * @name: name that should be converted to handle. * @handle: resulting file handle * @mnt_id: mount id of the file system containing the file * (u64 if AT_HANDLE_MNT_ID_UNIQUE, otherwise int) * @flag: flag value to indicate whether to follow symlink or not * and whether a decodable file handle is required. * * @handle->handle_size indicate the space available to store the * variable part of the file handle in bytes. If there is not * enough space, the field is updated to return the minimum * value required. */ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name, struct file_handle __user *, handle, void __user *, mnt_id, int, flag) { struct path path; int lookup_flags; int fh_flags = 0; int err; if (flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH | AT_HANDLE_FID | AT_HANDLE_MNT_ID_UNIQUE | AT_HANDLE_CONNECTABLE)) return -EINVAL; /* * AT_HANDLE_FID means there is no intention to decode file handle * AT_HANDLE_CONNECTABLE means there is an intention to decode a * connected fd (with known path), so these flags are conflicting. * AT_EMPTY_PATH could be used along with a dfd that refers to a * disconnected non-directory, which cannot be used to encode a * connectable file handle, because its parent is unknown. */ if (flag & AT_HANDLE_CONNECTABLE && flag & (AT_HANDLE_FID | AT_EMPTY_PATH)) return -EINVAL; else if (flag & AT_HANDLE_FID) fh_flags |= EXPORT_FH_FID; else if (flag & AT_HANDLE_CONNECTABLE) fh_flags |= EXPORT_FH_CONNECTABLE; lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0; if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; err = user_path_at(dfd, name, lookup_flags, &path); if (!err) { err = do_sys_name_to_handle(&path, handle, mnt_id, flag & AT_HANDLE_MNT_ID_UNIQUE, fh_flags); path_put(&path); } return err; } static int get_path_anchor(int fd, struct path *root) { if (fd >= 0) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; *root = fd_file(f)->f_path; path_get(root); return 0; } if (fd == AT_FDCWD) { get_fs_pwd(current->fs, root); return 0; } if (fd == FD_PIDFS_ROOT) { pidfs_get_root(root); return 0; } if (fd == FD_NSFS_ROOT) { nsfs_get_root(root); return 0; } return -EBADF; } static int vfs_dentry_acceptable(void *context, struct dentry *dentry) { struct handle_to_path_ctx *ctx = context; struct user_namespace *user_ns = current_user_ns(); struct dentry *d, *root = ctx->root.dentry; struct mnt_idmap *idmap = mnt_idmap(ctx->root.mnt); int retval = 0; if (!root) return 1; /* Old permission model with global CAP_DAC_READ_SEARCH. */ if (!ctx->flags) return 1; /* * Verify that the decoded dentry itself has a valid id mapping. * In case the decoded dentry is the mountfd root itself, this * verifies that the mountfd inode itself has a valid id mapping. */ if (!privileged_wrt_inode_uidgid(user_ns, idmap, d_inode(dentry))) return 0; /* * It's racy as we're not taking rename_lock but we're able to ignore * permissions and we just need an approximation whether we were able * to follow a path to the file. * * It's also potentially expensive on some filesystems especially if * there is a deep path. */ d = dget(dentry); while (d != root && !IS_ROOT(d)) { struct dentry *parent = dget_parent(d); /* * We know that we have the ability to override DAC permissions * as we've verified this earlier via CAP_DAC_READ_SEARCH. But * we also need to make sure that there aren't any unmapped * inodes in the path that would prevent us from reaching the * file. */ if (!privileged_wrt_inode_uidgid(user_ns, idmap, d_inode(parent))) { dput(d); dput(parent); return retval; } dput(d); d = parent; } if (!(ctx->flags & HANDLE_CHECK_SUBTREE) || d == root) retval = 1; /* * exportfs_decode_fh_raw() does not call acceptable() callback with * a disconnected directory dentry, so we should have reached either * mount fd directory or sb root. */ if (ctx->fh_flags & EXPORT_FH_DIR_ONLY) WARN_ON_ONCE(d != root && d != root->d_sb->s_root); dput(d); return retval; } static int do_handle_to_path(struct file_handle *handle, struct path *path, struct handle_to_path_ctx *ctx) { int handle_dwords; struct vfsmount *mnt = ctx->root.mnt; struct dentry *dentry; /* change the handle size to multiple of sizeof(u32) */ handle_dwords = handle->handle_bytes >> 2; dentry = exportfs_decode_fh_raw(mnt, (struct fid *)handle->f_handle, handle_dwords, handle->handle_type, ctx->fh_flags, vfs_dentry_acceptable, ctx); if (IS_ERR_OR_NULL(dentry)) { if (dentry == ERR_PTR(-ENOMEM)) return -ENOMEM; return -ESTALE; } path->dentry = dentry; path->mnt = mntget(mnt); return 0; } static inline int may_decode_fh(struct handle_to_path_ctx *ctx, unsigned int o_flags) { struct path *root = &ctx->root; if (capable(CAP_DAC_READ_SEARCH)) return 0; /* * Allow relaxed permissions of file handles if the caller has * the ability to mount the filesystem or create a bind-mount of * the provided @mountdirfd. * * In both cases the caller may be able to get an unobstructed * way to the encoded file handle. If the caller is only able to * create a bind-mount we need to verify that there are no * locked mounts on top of it that could prevent us from getting * to the encoded file. * * In principle, locked mounts can prevent the caller from * mounting the filesystem but that only applies to procfs and * sysfs neither of which support decoding file handles. * * Restrict to O_DIRECTORY to provide a deterministic API that * avoids a confusing api in the face of disconnected non-dir * dentries. * * There's only one dentry for each directory inode (VFS rule)... */ if (!(o_flags & O_DIRECTORY)) return -EPERM; if (ns_capable(root->mnt->mnt_sb->s_user_ns, CAP_SYS_ADMIN)) ctx->flags = HANDLE_CHECK_PERMS; else if (is_mounted(root->mnt) && ns_capable(real_mount(root->mnt)->mnt_ns->user_ns, CAP_SYS_ADMIN) && !has_locked_children(real_mount(root->mnt), root->dentry)) ctx->flags = HANDLE_CHECK_PERMS | HANDLE_CHECK_SUBTREE; else return -EPERM; /* Are we able to override DAC permissions? */ if (!ns_capable(current_user_ns(), CAP_DAC_READ_SEARCH)) return -EPERM; ctx->fh_flags = EXPORT_FH_DIR_ONLY; return 0; } static int handle_to_path(int mountdirfd, struct file_handle __user *ufh, struct path *path, unsigned int o_flags) { int retval = 0; struct file_handle f_handle; struct file_handle *handle __free(kfree) = NULL; struct handle_to_path_ctx ctx = {}; const struct export_operations *eops; if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) return -EFAULT; if ((f_handle.handle_bytes > MAX_HANDLE_SZ) || (f_handle.handle_bytes == 0)) return -EINVAL; if (f_handle.handle_type < 0 || FILEID_USER_FLAGS(f_handle.handle_type) & ~FILEID_VALID_USER_FLAGS) return -EINVAL; retval = get_path_anchor(mountdirfd, &ctx.root); if (retval) return retval; eops = ctx.root.mnt->mnt_sb->s_export_op; if (eops && eops->permission) retval = eops->permission(&ctx, o_flags); else retval = may_decode_fh(&ctx, o_flags); if (retval) goto out_path; handle = kmalloc(struct_size(handle, f_handle, f_handle.handle_bytes), GFP_KERNEL); if (!handle) { retval = -ENOMEM; goto out_path; } /* copy the full handle */ *handle = f_handle; if (copy_from_user(&handle->f_handle, &ufh->f_handle, f_handle.handle_bytes)) { retval = -EFAULT; goto out_path; } /* * If handle was encoded with AT_HANDLE_CONNECTABLE, verify that we * are decoding an fd with connected path, which is accessible from * the mount fd path. */ if (f_handle.handle_type & FILEID_IS_CONNECTABLE) { ctx.fh_flags |= EXPORT_FH_CONNECTABLE; ctx.flags |= HANDLE_CHECK_SUBTREE; } if (f_handle.handle_type & FILEID_IS_DIR) ctx.fh_flags |= EXPORT_FH_DIR_ONLY; /* Filesystem code should not be exposed to user flags */ handle->handle_type &= ~FILEID_USER_FLAGS_MASK; retval = do_handle_to_path(handle, path, &ctx); out_path: path_put(&ctx.root); return retval; } static long do_handle_open(int mountdirfd, struct file_handle __user *ufh, int open_flag) { long retval = 0; struct path path __free(path_put) = {}; struct file *file; const struct export_operations *eops; retval = handle_to_path(mountdirfd, ufh, &path, open_flag); if (retval) return retval; CLASS(get_unused_fd, fd)(open_flag); if (fd < 0) return fd; eops = path.mnt->mnt_sb->s_export_op; if (eops->open) file = eops->open(&path, open_flag); else file = file_open_root(&path, "", open_flag, 0); if (IS_ERR(file)) return PTR_ERR(file); fd_install(fd, file); return take_fd(fd); } /** * sys_open_by_handle_at: Open the file handle * @mountdirfd: directory file descriptor * @handle: file handle to be opened * @flags: open flags. * * @mountdirfd indicate the directory file descriptor * of the mount point. file handle is decoded relative * to the vfsmount pointed by the @mountdirfd. @flags * value is same as the open(2) flags. */ SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd, struct file_handle __user *, handle, int, flags) { long ret; if (force_o_largefile()) flags |= O_LARGEFILE; ret = do_handle_open(mountdirfd, handle, flags); return ret; } #ifdef CONFIG_COMPAT /* * Exactly like fs/open.c:sys_open_by_handle_at(), except that it * doesn't set the O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd, struct file_handle __user *, handle, int, flags) { return do_handle_open(mountdirfd, handle, flags); } #endif |
| 20 20 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/async.h> #include <linux/export.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 <linux/overflow.h> #include "do_mounts.h" #include "initramfs_internal.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 __initdata bool hardlink_seen; 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; strscpy(q->name, name); q->next = NULL; *p = q; hardlink_seen = true; return NULL; } static void __init free_hash(void) { struct hash **p, *q; for (p = head; hardlink_seen && p < head + 32; p++) { while (*p) { q = *p; *p = q->next; kfree(q); } } hardlink_seen = false; } #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, size_t nlen, time64_t mtime) { struct dir_entry *de; de = kmalloc(struct_size(de, name, 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, size_t nlen, 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]; int i; for (i = 0, s += 6; i < 13; i++, s += 8) parsed[i] = simple_strntoul(s, NULL, 16, 8); 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, CPIO_HDRLEN, 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; /* name_len > 0 && name_len <= PATH_MAX checked in do_header */ if (collected[name_len - 1] != '\0') { pr_err("initramfs name without nulterm: %.*s\n", (int)name_len, collected); error("malformed archive"); return 1; } 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, name_len, 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) { if (collected[name_len - 1] != '\0') { pr_err("initramfs symlink without nulterm: %.*s\n", (int)name_len, collected); error("malformed archive"); return 1; } 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> /** * unpack_to_rootfs - decompress and extract an initramfs archive * @buf: input initramfs archive to extract * @len: length of initramfs data to process * * Returns: NULL for success or an error message string * * This symbol shouldn't be used externally. It's available for unit tests. */ char * __init unpack_to_rootfs(char *buf, unsigned long len) { long written; decompress_fn decompress; const char *compress_name; struct { char header[CPIO_HDRLEN]; char symlink[PATH_MAX + N_ALIGN(PATH_MAX) + 1]; char name[N_ALIGN(PATH_MAX)]; } *bufs = kmalloc(sizeof(*bufs), GFP_KERNEL); if (!bufs) panic_show_mem("can't allocate buffers"); header_buf = bufs->header; symlink_buf = bufs->symlink; name_buf = bufs->name; 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) { pr_err("compression method %s not configured\n", compress_name); error("decompressor failed"); } 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(); /* free any hardlink state collected without optional TRAILER!!! */ free_hash(); kfree(bufs); 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); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file contains common definitions for working with Enlightened VMCS which * are used both by Hyper-V on KVM and KVM on Hyper-V. */ #ifndef __KVM_X86_VMX_HYPERV_EVMCS_H #define __KVM_X86_VMX_HYPERV_EVMCS_H #include <hyperv/hvhdk.h> #include "capabilities.h" #include "vmcs12.h" #define KVM_EVMCS_VERSION 1 /* * Enlightened VMCSv1 doesn't support these: * * POSTED_INTR_NV = 0x00000002, * GUEST_INTR_STATUS = 0x00000810, * APIC_ACCESS_ADDR = 0x00002014, * POSTED_INTR_DESC_ADDR = 0x00002016, * EOI_EXIT_BITMAP0 = 0x0000201c, * EOI_EXIT_BITMAP1 = 0x0000201e, * EOI_EXIT_BITMAP2 = 0x00002020, * EOI_EXIT_BITMAP3 = 0x00002022, * GUEST_PML_INDEX = 0x00000812, * PML_ADDRESS = 0x0000200e, * VM_FUNCTION_CONTROL = 0x00002018, * EPTP_LIST_ADDRESS = 0x00002024, * VMREAD_BITMAP = 0x00002026, * VMWRITE_BITMAP = 0x00002028, * * TSC_MULTIPLIER = 0x00002032, * PLE_GAP = 0x00004020, * PLE_WINDOW = 0x00004022, * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, * * Currently unsupported in KVM: * GUEST_IA32_RTIT_CTL = 0x00002814, */ #define EVMCS1_SUPPORTED_PINCTRL \ (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ PIN_BASED_EXT_INTR_MASK | \ PIN_BASED_NMI_EXITING | \ PIN_BASED_VIRTUAL_NMIS) #define EVMCS1_SUPPORTED_EXEC_CTRL \ (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ CPU_BASED_HLT_EXITING | \ CPU_BASED_CR3_LOAD_EXITING | \ CPU_BASED_CR3_STORE_EXITING | \ CPU_BASED_UNCOND_IO_EXITING | \ CPU_BASED_MOV_DR_EXITING | \ CPU_BASED_USE_TSC_OFFSETTING | \ CPU_BASED_MWAIT_EXITING | \ CPU_BASED_MONITOR_EXITING | \ CPU_BASED_INVLPG_EXITING | \ CPU_BASED_RDPMC_EXITING | \ CPU_BASED_INTR_WINDOW_EXITING | \ CPU_BASED_CR8_LOAD_EXITING | \ CPU_BASED_CR8_STORE_EXITING | \ CPU_BASED_RDTSC_EXITING | \ CPU_BASED_TPR_SHADOW | \ CPU_BASED_USE_IO_BITMAPS | \ CPU_BASED_MONITOR_TRAP_FLAG | \ CPU_BASED_USE_MSR_BITMAPS | \ CPU_BASED_NMI_WINDOW_EXITING | \ CPU_BASED_PAUSE_EXITING | \ CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) #define EVMCS1_SUPPORTED_2NDEXEC \ (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ SECONDARY_EXEC_WBINVD_EXITING | \ SECONDARY_EXEC_ENABLE_VPID | \ SECONDARY_EXEC_ENABLE_EPT | \ SECONDARY_EXEC_UNRESTRICTED_GUEST | \ SECONDARY_EXEC_DESC | \ SECONDARY_EXEC_ENABLE_RDTSCP | \ SECONDARY_EXEC_ENABLE_INVPCID | \ SECONDARY_EXEC_ENABLE_XSAVES | \ SECONDARY_EXEC_RDSEED_EXITING | \ SECONDARY_EXEC_RDRAND_EXITING | \ SECONDARY_EXEC_TSC_SCALING | \ SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ SECONDARY_EXEC_PT_USE_GPA | \ SECONDARY_EXEC_PT_CONCEAL_VMX | \ SECONDARY_EXEC_BUS_LOCK_DETECTION | \ SECONDARY_EXEC_NOTIFY_VM_EXITING | \ SECONDARY_EXEC_ENCLS_EXITING) #define EVMCS1_SUPPORTED_3RDEXEC (0ULL) #define EVMCS1_SUPPORTED_VMEXIT_CTRL \ (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ VM_EXIT_SAVE_DEBUG_CONTROLS | \ VM_EXIT_ACK_INTR_ON_EXIT | \ VM_EXIT_HOST_ADDR_SPACE_SIZE | \ VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ VM_EXIT_SAVE_IA32_PAT | \ VM_EXIT_LOAD_IA32_PAT | \ VM_EXIT_SAVE_IA32_EFER | \ VM_EXIT_LOAD_IA32_EFER | \ VM_EXIT_CLEAR_BNDCFGS | \ VM_EXIT_PT_CONCEAL_PIP | \ VM_EXIT_CLEAR_IA32_RTIT_CTL) #define EVMCS1_SUPPORTED_VMENTRY_CTRL \ (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ VM_ENTRY_LOAD_DEBUG_CONTROLS | \ VM_ENTRY_IA32E_MODE | \ VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ VM_ENTRY_LOAD_IA32_PAT | \ VM_ENTRY_LOAD_IA32_EFER | \ VM_ENTRY_LOAD_BNDCFGS | \ VM_ENTRY_PT_CONCEAL_PIP | \ VM_ENTRY_LOAD_IA32_RTIT_CTL) #define EVMCS1_SUPPORTED_VMFUNC (0) struct evmcs_field { u16 offset; u16 clean_field; }; extern const struct evmcs_field vmcs_field_to_evmcs_1[]; extern const unsigned int nr_evmcs_1_fields; static __always_inline int evmcs_field_offset(unsigned long field, u16 *clean_field) { const struct evmcs_field *evmcs_field; unsigned int index = ROL16(field, 6); if (unlikely(index >= nr_evmcs_1_fields)) return -ENOENT; evmcs_field = &vmcs_field_to_evmcs_1[index]; /* * Use offset=0 to detect holes in eVMCS. This offset belongs to * 'revision_id' but this field has no encoding and is supposed to * be accessed directly. */ if (unlikely(!evmcs_field->offset)) return -ENOENT; if (clean_field) *clean_field = evmcs_field->clean_field; return evmcs_field->offset; } static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, unsigned long field, u16 offset) { /* * vmcs12_read_any() doesn't care whether the supplied structure * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes * the exact offset of the required field, use it for convenience * here. */ return vmcs12_read_any((void *)evmcs, field, offset); } #endif /* __KVM_X86_VMX_HYPERV_H */ |
| 9 9 9 9 9 9 9 7 5 7 4 3 3 2 1 5 5 5 5 5 2 5 9 5 1 1 1 2 1 7 2 5 5 9 9 9 1 1 7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2015 Microchip Technology */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/phylink.h> #include <linux/usb.h> #include <linux/crc32.h> #include <linux/signal.h> #include <linux/slab.h> #include <linux/if_vlan.h> #include <linux/uaccess.h> #include <linux/linkmode.h> #include <linux/list.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/mdio.h> #include <linux/phy.h> #include <net/ip6_checksum.h> #include <net/selftests.h> #include <net/vxlan.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> #include <linux/irq.h> #include <linux/irqchip/chained_irq.h> #include <linux/microchipphy.h> #include <linux/of_mdio.h> #include <linux/of_net.h> #include "lan78xx.h" #define DRIVER_AUTHOR "WOOJUNG HUH <woojung.huh@microchip.com>" #define DRIVER_DESC "LAN78XX USB 3.0 Gigabit Ethernet Devices" #define DRIVER_NAME "lan78xx" #define TX_TIMEOUT_JIFFIES (5 * HZ) #define THROTTLE_JIFFIES (HZ / 8) #define UNLINK_TIMEOUT_MS 3 #define RX_MAX_QUEUE_MEMORY (60 * 1518) #define SS_USB_PKT_SIZE (1024) #define HS_USB_PKT_SIZE (512) #define FS_USB_PKT_SIZE (64) #define MAX_RX_FIFO_SIZE (12 * 1024) #define MAX_TX_FIFO_SIZE (12 * 1024) #define FLOW_THRESHOLD(n) ((((n) + 511) / 512) & 0x7F) #define FLOW_CTRL_THRESHOLD(on, off) ((FLOW_THRESHOLD(on) << 0) | \ (FLOW_THRESHOLD(off) << 8)) /* Flow control turned on when Rx FIFO level rises above this level (bytes) */ #define FLOW_ON_SS 9216 #define FLOW_ON_HS 8704 /* Flow control turned off when Rx FIFO level falls below this level (bytes) */ #define FLOW_OFF_SS 4096 #define FLOW_OFF_HS 1024 #define DEFAULT_BURST_CAP_SIZE (MAX_TX_FIFO_SIZE) #define DEFAULT_BULK_IN_DELAY (0x0800) #define MAX_SINGLE_PACKET_SIZE (9000) #define DEFAULT_TX_CSUM_ENABLE (true) #define DEFAULT_RX_CSUM_ENABLE (true) #define DEFAULT_TSO_CSUM_ENABLE (true) #define DEFAULT_VLAN_FILTER_ENABLE (true) #define DEFAULT_VLAN_RX_OFFLOAD (true) #define TX_ALIGNMENT (4) #define RXW_PADDING 2 #define LAN78XX_USB_VENDOR_ID (0x0424) #define LAN7800_USB_PRODUCT_ID (0x7800) #define LAN7850_USB_PRODUCT_ID (0x7850) #define LAN7801_USB_PRODUCT_ID (0x7801) #define LAN78XX_EEPROM_MAGIC (0x78A5) #define LAN78XX_OTP_MAGIC (0x78F3) #define AT29M2AF_USB_VENDOR_ID (0x07C9) #define AT29M2AF_USB_PRODUCT_ID (0x0012) #define MII_READ 1 #define MII_WRITE 0 #define EEPROM_INDICATOR (0xA5) #define EEPROM_MAC_OFFSET (0x01) #define MAX_EEPROM_SIZE 512 #define OTP_INDICATOR_1 (0xF3) #define OTP_INDICATOR_2 (0xF7) #define WAKE_ALL (WAKE_PHY | WAKE_UCAST | \ WAKE_MCAST | WAKE_BCAST | \ WAKE_ARP | WAKE_MAGIC) #define TX_URB_NUM 10 #define TX_SS_URB_NUM TX_URB_NUM #define TX_HS_URB_NUM TX_URB_NUM #define TX_FS_URB_NUM TX_URB_NUM /* A single URB buffer must be large enough to hold a complete jumbo packet */ #define TX_SS_URB_SIZE (32 * 1024) #define TX_HS_URB_SIZE (16 * 1024) #define TX_FS_URB_SIZE (10 * 1024) #define RX_SS_URB_NUM 30 #define RX_HS_URB_NUM 10 #define RX_FS_URB_NUM 10 #define RX_SS_URB_SIZE TX_SS_URB_SIZE #define RX_HS_URB_SIZE TX_HS_URB_SIZE #define RX_FS_URB_SIZE TX_FS_URB_SIZE #define SS_BURST_CAP_SIZE RX_SS_URB_SIZE #define SS_BULK_IN_DELAY 0x2000 #define HS_BURST_CAP_SIZE RX_HS_URB_SIZE #define HS_BULK_IN_DELAY 0x2000 #define FS_BURST_CAP_SIZE RX_FS_URB_SIZE #define FS_BULK_IN_DELAY 0x2000 #define TX_CMD_LEN 8 #define TX_SKB_MIN_LEN (TX_CMD_LEN + ETH_HLEN) #define LAN78XX_TSO_SIZE(dev) ((dev)->tx_urb_size - TX_SKB_MIN_LEN) #define RX_CMD_LEN 10 #define RX_SKB_MIN_LEN (RX_CMD_LEN + ETH_HLEN) #define RX_MAX_FRAME_LEN(mtu) ((mtu) + ETH_HLEN + VLAN_HLEN) /* USB related defines */ #define BULK_IN_PIPE 1 #define BULK_OUT_PIPE 2 /* default autosuspend delay (mSec)*/ #define DEFAULT_AUTOSUSPEND_DELAY (10 * 1000) /* statistic update interval (mSec) */ #define STAT_UPDATE_TIMER (1 * 1000) /* time to wait for MAC or FCT to stop (jiffies) */ #define HW_DISABLE_TIMEOUT (HZ / 10) /* time to wait between polling MAC or FCT state (ms) */ #define HW_DISABLE_DELAY_MS 1 /* defines interrupts from interrupt EP */ #define MAX_INT_EP (32) #define INT_EP_INTEP (31) #define INT_EP_OTP_WR_DONE (28) #define INT_EP_EEE_TX_LPI_START (26) #define INT_EP_EEE_TX_LPI_STOP (25) #define INT_EP_EEE_RX_LPI (24) #define INT_EP_MAC_RESET_TIMEOUT (23) #define INT_EP_RDFO (22) #define INT_EP_TXE (21) #define INT_EP_USB_STATUS (20) #define INT_EP_TX_DIS (19) #define INT_EP_RX_DIS (18) #define INT_EP_PHY (17) #define INT_EP_DP (16) #define INT_EP_MAC_ERR (15) #define INT_EP_TDFU (14) #define INT_EP_TDFO (13) #define INT_EP_UTX (12) #define INT_EP_GPIO_11 (11) #define INT_EP_GPIO_10 (10) #define INT_EP_GPIO_9 (9) #define INT_EP_GPIO_8 (8) #define INT_EP_GPIO_7 (7) #define INT_EP_GPIO_6 (6) #define INT_EP_GPIO_5 (5) #define INT_EP_GPIO_4 (4) #define INT_EP_GPIO_3 (3) #define INT_EP_GPIO_2 (2) #define INT_EP_GPIO_1 (1) #define INT_EP_GPIO_0 (0) static const char lan78xx_gstrings[][ETH_GSTRING_LEN] = { "RX FCS Errors", "RX Alignment Errors", "Rx Fragment Errors", "RX Jabber Errors", "RX Undersize Frame Errors", "RX Oversize Frame Errors", "RX Dropped Frames", "RX Unicast Byte Count", "RX Broadcast Byte Count", "RX Multicast Byte Count", "RX Unicast Frames", "RX Broadcast Frames", "RX Multicast Frames", "RX Pause Frames", "RX 64 Byte Frames", "RX 65 - 127 Byte Frames", "RX 128 - 255 Byte Frames", "RX 256 - 511 Bytes Frames", "RX 512 - 1023 Byte Frames", "RX 1024 - 1518 Byte Frames", "RX Greater 1518 Byte Frames", "EEE RX LPI Transitions", "EEE RX LPI Time", "TX FCS Errors", "TX Excess Deferral Errors", "TX Carrier Errors", "TX Bad Byte Count", "TX Single Collisions", "TX Multiple Collisions", "TX Excessive Collision", "TX Late Collisions", "TX Unicast Byte Count", "TX Broadcast Byte Count", "TX Multicast Byte Count", "TX Unicast Frames", "TX Broadcast Frames", "TX Multicast Frames", "TX Pause Frames", "TX 64 Byte Frames", "TX 65 - 127 Byte Frames", "TX 128 - 255 Byte Frames", "TX 256 - 511 Bytes Frames", "TX 512 - 1023 Byte Frames", "TX 1024 - 1518 Byte Frames", "TX Greater 1518 Byte Frames", "EEE TX LPI Transitions", "EEE TX LPI Time", }; struct lan78xx_statstage { u32 rx_fcs_errors; u32 rx_alignment_errors; u32 rx_fragment_errors; u32 rx_jabber_errors; u32 rx_undersize_frame_errors; u32 rx_oversize_frame_errors; u32 rx_dropped_frames; u32 rx_unicast_byte_count; u32 rx_broadcast_byte_count; u32 rx_multicast_byte_count; u32 rx_unicast_frames; u32 rx_broadcast_frames; u32 rx_multicast_frames; u32 rx_pause_frames; u32 rx_64_byte_frames; u32 rx_65_127_byte_frames; u32 rx_128_255_byte_frames; u32 rx_256_511_bytes_frames; u32 rx_512_1023_byte_frames; u32 rx_1024_1518_byte_frames; u32 rx_greater_1518_byte_frames; u32 eee_rx_lpi_transitions; u32 eee_rx_lpi_time; u32 tx_fcs_errors; u32 tx_excess_deferral_errors; u32 tx_carrier_errors; u32 tx_bad_byte_count; u32 tx_single_collisions; u32 tx_multiple_collisions; u32 tx_excessive_collision; u32 tx_late_collisions; u32 tx_unicast_byte_count; u32 tx_broadcast_byte_count; u32 tx_multicast_byte_count; u32 tx_unicast_frames; u32 tx_broadcast_frames; u32 tx_multicast_frames; u32 tx_pause_frames; u32 tx_64_byte_frames; u32 tx_65_127_byte_frames; u32 tx_128_255_byte_frames; u32 tx_256_511_bytes_frames; u32 tx_512_1023_byte_frames; u32 tx_1024_1518_byte_frames; u32 tx_greater_1518_byte_frames; u32 eee_tx_lpi_transitions; u32 eee_tx_lpi_time; }; struct lan78xx_statstage64 { u64 rx_fcs_errors; u64 rx_alignment_errors; u64 rx_fragment_errors; u64 rx_jabber_errors; u64 rx_undersize_frame_errors; u64 rx_oversize_frame_errors; u64 rx_dropped_frames; u64 rx_unicast_byte_count; u64 rx_broadcast_byte_count; u64 rx_multicast_byte_count; u64 rx_unicast_frames; u64 rx_broadcast_frames; u64 rx_multicast_frames; u64 rx_pause_frames; u64 rx_64_byte_frames; u64 rx_65_127_byte_frames; u64 rx_128_255_byte_frames; u64 rx_256_511_bytes_frames; u64 rx_512_1023_byte_frames; u64 rx_1024_1518_byte_frames; u64 rx_greater_1518_byte_frames; u64 eee_rx_lpi_transitions; u64 eee_rx_lpi_time; u64 tx_fcs_errors; u64 tx_excess_deferral_errors; u64 tx_carrier_errors; u64 tx_bad_byte_count; u64 tx_single_collisions; u64 tx_multiple_collisions; u64 tx_excessive_collision; u64 tx_late_collisions; u64 tx_unicast_byte_count; u64 tx_broadcast_byte_count; u64 tx_multicast_byte_count; u64 tx_unicast_frames; u64 tx_broadcast_frames; u64 tx_multicast_frames; u64 tx_pause_frames; u64 tx_64_byte_frames; u64 tx_65_127_byte_frames; u64 tx_128_255_byte_frames; u64 tx_256_511_bytes_frames; u64 tx_512_1023_byte_frames; u64 tx_1024_1518_byte_frames; u64 tx_greater_1518_byte_frames; u64 eee_tx_lpi_transitions; u64 eee_tx_lpi_time; }; static u32 lan78xx_regs[] = { ID_REV, INT_STS, HW_CFG, PMT_CTL, E2P_CMD, E2P_DATA, USB_STATUS, VLAN_TYPE, MAC_CR, MAC_RX, MAC_TX, FLOW, ERR_STS, MII_ACC, MII_DATA, EEE_TX_LPI_REQ_DLY, EEE_TW_TX_SYS, EEE_TX_LPI_REM_DLY, WUCSR }; #define PHY_REG_SIZE (32 * sizeof(u32)) struct lan78xx_net; struct lan78xx_priv { struct lan78xx_net *dev; u32 rfe_ctl; u32 mchash_table[DP_SEL_VHF_HASH_LEN]; /* multicast hash table */ u32 pfilter_table[NUM_OF_MAF][2]; /* perfect filter table */ u32 vlan_table[DP_SEL_VHF_VLAN_LEN]; struct mutex dataport_mutex; /* for dataport access */ spinlock_t rfe_ctl_lock; /* for rfe register access */ struct work_struct set_multicast; struct work_struct set_vlan; u32 wol; }; enum skb_state { illegal = 0, tx_start, tx_done, rx_start, rx_done, rx_cleanup, unlink_start }; struct skb_data { /* skb->cb is one of these */ struct urb *urb; struct lan78xx_net *dev; enum skb_state state; size_t length; int num_of_packet; }; #define EVENT_TX_HALT 0 #define EVENT_RX_HALT 1 #define EVENT_RX_MEMORY 2 #define EVENT_STS_SPLIT 3 #define EVENT_PHY_INT_ACK 4 #define EVENT_RX_PAUSED 5 #define EVENT_DEV_WAKING 6 #define EVENT_DEV_ASLEEP 7 #define EVENT_DEV_OPEN 8 #define EVENT_STAT_UPDATE 9 #define EVENT_DEV_DISCONNECT 10 struct statstage { struct mutex access_lock; /* for stats access */ struct lan78xx_statstage saved; struct lan78xx_statstage rollover_count; struct lan78xx_statstage rollover_max; struct lan78xx_statstage64 curr_stat; }; struct irq_domain_data { struct irq_domain *irqdomain; unsigned int phyirq; struct irq_chip *irqchip; irq_flow_handler_t irq_handler; u32 irqenable; struct mutex irq_lock; /* for irq bus access */ }; struct lan78xx_net { struct net_device *net; struct usb_device *udev; struct usb_interface *intf; unsigned int tx_pend_data_len; size_t n_tx_urbs; size_t n_rx_urbs; size_t tx_urb_size; size_t rx_urb_size; struct sk_buff_head rxq_free; struct sk_buff_head rxq; struct sk_buff_head rxq_done; struct sk_buff_head rxq_overflow; struct sk_buff_head txq_free; struct sk_buff_head txq; struct sk_buff_head txq_pend; struct napi_struct napi; struct delayed_work wq; int msg_enable; struct urb *urb_intr; struct usb_anchor deferred; struct mutex dev_mutex; /* serialise open/stop wrt suspend/resume */ struct mutex mdiobus_mutex; /* for MDIO bus access */ unsigned int pipe_in, pipe_out, pipe_intr; unsigned int bulk_in_delay; unsigned int burst_cap; unsigned long flags; wait_queue_head_t *wait; unsigned int maxpacket; struct timer_list stat_monitor; unsigned long data[5]; u32 chipid; u32 chiprev; struct mii_bus *mdiobus; phy_interface_t interface; int delta; struct statstage stats; struct irq_domain_data domain_data; struct phylink *phylink; struct phylink_config phylink_config; }; /* use ethtool to change the level for any given device */ static int msg_level = -1; module_param(msg_level, int, 0); MODULE_PARM_DESC(msg_level, "Override default message level"); static struct sk_buff *lan78xx_get_buf(struct sk_buff_head *buf_pool) { if (skb_queue_empty(buf_pool)) return NULL; return skb_dequeue(buf_pool); } static void lan78xx_release_buf(struct sk_buff_head *buf_pool, struct sk_buff *buf) { buf->data = buf->head; skb_reset_tail_pointer(buf); buf->len = 0; buf->data_len = 0; skb_queue_tail(buf_pool, buf); } static void lan78xx_free_buf_pool(struct sk_buff_head *buf_pool) { struct skb_data *entry; struct sk_buff *buf; while (!skb_queue_empty(buf_pool)) { buf = skb_dequeue(buf_pool); if (buf) { entry = (struct skb_data *)buf->cb; usb_free_urb(entry->urb); dev_kfree_skb_any(buf); } } } static int lan78xx_alloc_buf_pool(struct sk_buff_head *buf_pool, size_t n_urbs, size_t urb_size, struct lan78xx_net *dev) { struct skb_data *entry; struct sk_buff *buf; struct urb *urb; int i; skb_queue_head_init(buf_pool); for (i = 0; i < n_urbs; i++) { buf = alloc_skb(urb_size, GFP_ATOMIC); if (!buf) goto error; if (skb_linearize(buf) != 0) { dev_kfree_skb_any(buf); goto error; } urb = usb_alloc_urb(0, GFP_ATOMIC); if (!urb) { dev_kfree_skb_any(buf); goto error; } entry = (struct skb_data *)buf->cb; entry->urb = urb; entry->dev = dev; entry->length = 0; entry->num_of_packet = 0; skb_queue_tail(buf_pool, buf); } return 0; error: lan78xx_free_buf_pool(buf_pool); return -ENOMEM; } static struct sk_buff *lan78xx_get_rx_buf(struct lan78xx_net *dev) { return lan78xx_get_buf(&dev->rxq_free); } static void lan78xx_release_rx_buf(struct lan78xx_net *dev, struct sk_buff *rx_buf) { lan78xx_release_buf(&dev->rxq_free, rx_buf); } static void lan78xx_free_rx_resources(struct lan78xx_net *dev) { lan78xx_free_buf_pool(&dev->rxq_free); } static int lan78xx_alloc_rx_resources(struct lan78xx_net *dev) { return lan78xx_alloc_buf_pool(&dev->rxq_free, dev->n_rx_urbs, dev->rx_urb_size, dev); } static struct sk_buff *lan78xx_get_tx_buf(struct lan78xx_net *dev) { return lan78xx_get_buf(&dev->txq_free); } static void lan78xx_release_tx_buf(struct lan78xx_net *dev, struct sk_buff *tx_buf) { lan78xx_release_buf(&dev->txq_free, tx_buf); } static void lan78xx_free_tx_resources(struct lan78xx_net *dev) { lan78xx_free_buf_pool(&dev->txq_free); } static int lan78xx_alloc_tx_resources(struct lan78xx_net *dev) { return lan78xx_alloc_buf_pool(&dev->txq_free, dev->n_tx_urbs, dev->tx_urb_size, dev); } static int lan78xx_read_reg(struct lan78xx_net *dev, u32 index, u32 *data) { u32 *buf; int ret; if (test_bit(EVENT_DEV_DISCONNECT, &dev->flags)) return -ENODEV; buf = kmalloc(sizeof(u32), GFP_KERNEL); if (!buf) return -ENOMEM; ret = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), USB_VENDOR_REQUEST_READ_REGISTER, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, index, buf, 4, USB_CTRL_GET_TIMEOUT); if (likely(ret >= 0)) { le32_to_cpus(buf); *data = *buf; } else if (net_ratelimit()) { netdev_warn(dev->net, "Failed to read register index 0x%08x. ret = %pe", index, ERR_PTR(ret)); } kfree(buf); return ret < 0 ? ret : 0; } static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data) { u32 *buf; int ret; if (test_bit(EVENT_DEV_DISCONNECT, &dev->flags)) return -ENODEV; buf = kmalloc(sizeof(u32), GFP_KERNEL); if (!buf) return -ENOMEM; *buf = data; cpu_to_le32s(buf); ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), USB_VENDOR_REQUEST_WRITE_REGISTER, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, index, buf, 4, USB_CTRL_SET_TIMEOUT); if (unlikely(ret < 0) && net_ratelimit()) { netdev_warn(dev->net, "Failed to write register index 0x%08x. ret = %pe", index, ERR_PTR(ret)); } kfree(buf); return ret < 0 ? ret : 0; } static int lan78xx_update_reg(struct lan78xx_net *dev, u32 reg, u32 mask, u32 data) { int ret; u32 buf; ret = lan78xx_read_reg(dev, reg, &buf); if (ret < 0) return ret; buf &= ~mask; buf |= (mask & data); return lan78xx_write_reg(dev, reg, buf); } static int lan78xx_read_stats(struct lan78xx_net *dev, struct lan78xx_statstage *data) { int ret = 0; int i; struct lan78xx_statstage *stats; u32 *src; u32 *dst; stats = kmalloc(sizeof(*stats), GFP_KERNEL); if (!stats) return -ENOMEM; ret = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), USB_VENDOR_REQUEST_GET_STATS, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, 0, (void *)stats, sizeof(*stats), USB_CTRL_SET_TIMEOUT); if (likely(ret >= 0)) { src = (u32 *)stats; dst = (u32 *)data; for (i = 0; i < sizeof(*stats) / sizeof(u32); i++) { le32_to_cpus(&src[i]); dst[i] = src[i]; } } else { netdev_warn(dev->net, "Failed to read stat ret = %d", ret); } kfree(stats); return ret; } #define check_counter_rollover(struct1, dev_stats, member) \ do { \ if ((struct1)->member < (dev_stats).saved.member) \ (dev_stats).rollover_count.member++; \ } while (0) static void lan78xx_check_stat_rollover(struct lan78xx_net *dev, struct lan78xx_statstage *stats) { check_counter_rollover(stats, dev->stats, rx_fcs_errors); check_counter_rollover(stats, dev->stats, rx_alignment_errors); check_counter_rollover(stats, dev->stats, rx_fragment_errors); check_counter_rollover(stats, dev->stats, rx_jabber_errors); check_counter_rollover(stats, dev->stats, rx_undersize_frame_errors); check_counter_rollover(stats, dev->stats, rx_oversize_frame_errors); check_counter_rollover(stats, dev->stats, rx_dropped_frames); check_counter_rollover(stats, dev->stats, rx_unicast_byte_count); check_counter_rollover(stats, dev->stats, rx_broadcast_byte_count); check_counter_rollover(stats, dev->stats, rx_multicast_byte_count); check_counter_rollover(stats, dev->stats, rx_unicast_frames); check_counter_rollover(stats, dev->stats, rx_broadcast_frames); check_counter_rollover(stats, dev->stats, rx_multicast_frames); check_counter_rollover(stats, dev->stats, rx_pause_frames); check_counter_rollover(stats, dev->stats, rx_64_byte_frames); check_counter_rollover(stats, dev->stats, rx_65_127_byte_frames); check_counter_rollover(stats, dev->stats, rx_128_255_byte_frames); check_counter_rollover(stats, dev->stats, rx_256_511_bytes_frames); check_counter_rollover(stats, dev->stats, rx_512_1023_byte_frames); check_counter_rollover(stats, dev->stats, rx_1024_1518_byte_frames); check_counter_rollover(stats, dev->stats, rx_greater_1518_byte_frames); check_counter_rollover(stats, dev->stats, eee_rx_lpi_transitions); check_counter_rollover(stats, dev->stats, eee_rx_lpi_time); check_counter_rollover(stats, dev->stats, tx_fcs_errors); check_counter_rollover(stats, dev->stats, tx_excess_deferral_errors); check_counter_rollover(stats, dev->stats, tx_carrier_errors); check_counter_rollover(stats, dev->stats, tx_bad_byte_count); check_counter_rollover(stats, dev->stats, tx_single_collisions); check_counter_rollover(stats, dev->stats, tx_multiple_collisions); check_counter_rollover(stats, dev->stats, tx_excessive_collision); check_counter_rollover(stats, dev->stats, tx_late_collisions); check_counter_rollover(stats, dev->stats, tx_unicast_byte_count); check_counter_rollover(stats, dev->stats, tx_broadcast_byte_count); check_counter_rollover(stats, dev->stats, tx_multicast_byte_count); check_counter_rollover(stats, dev->stats, tx_unicast_frames); check_counter_rollover(stats, dev->stats, tx_broadcast_frames); check_counter_rollover(stats, dev->stats, tx_multicast_frames); check_counter_rollover(stats, dev->stats, tx_pause_frames); check_counter_rollover(stats, dev->stats, tx_64_byte_frames); check_counter_rollover(stats, dev->stats, tx_65_127_byte_frames); check_counter_rollover(stats, dev->stats, tx_128_255_byte_frames); check_counter_rollover(stats, dev->stats, tx_256_511_bytes_frames); check_counter_rollover(stats, dev->stats, tx_512_1023_byte_frames); check_counter_rollover(stats, dev->stats, tx_1024_1518_byte_frames); check_counter_rollover(stats, dev->stats, tx_greater_1518_byte_frames); check_counter_rollover(stats, dev->stats, eee_tx_lpi_transitions); check_counter_rollover(stats, dev->stats, eee_tx_lpi_time); memcpy(&dev->stats.saved, stats, sizeof(struct lan78xx_statstage)); } static void lan78xx_update_stats(struct lan78xx_net *dev) { u32 *p, *count, *max; u64 *data; int i; struct lan78xx_statstage lan78xx_stats; if (usb_autopm_get_interface(dev->intf) < 0) return; p = (u32 *)&lan78xx_stats; count = (u32 *)&dev->stats.rollover_count; max = (u32 *)&dev->stats.rollover_max; data = (u64 *)&dev->stats.curr_stat; mutex_lock(&dev->stats.access_lock); if (lan78xx_read_stats(dev, &lan78xx_stats) > 0) lan78xx_check_stat_rollover(dev, &lan78xx_stats); for (i = 0; i < (sizeof(lan78xx_stats) / (sizeof(u32))); i++) data[i] = (u64)p[i] + ((u64)count[i] * ((u64)max[i] + 1)); mutex_unlock(&dev->stats.access_lock); usb_autopm_put_interface(dev->intf); } static int lan78xx_start_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enable) { return lan78xx_update_reg(dev, reg, hw_enable, hw_enable); } static int lan78xx_stop_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enabled, u32 hw_disabled) { unsigned long timeout; bool stopped = true; int ret; u32 buf; /* Stop the h/w block (if not already stopped) */ ret = lan78xx_read_reg(dev, reg, &buf); if (ret < 0) return ret; if (buf & hw_enabled) { buf &= ~hw_enabled; ret = lan78xx_write_reg(dev, reg, buf); if (ret < 0) return ret; stopped = false; timeout = jiffies + HW_DISABLE_TIMEOUT; do { ret = lan78xx_read_reg(dev, reg, &buf); if (ret < 0) return ret; if (buf & hw_disabled) stopped = true; else msleep(HW_DISABLE_DELAY_MS); } while (!stopped && !time_after(jiffies, timeout)); } return stopped ? 0 : -ETIMEDOUT; } static int lan78xx_flush_fifo(struct lan78xx_net *dev, u32 reg, u32 fifo_flush) { return lan78xx_update_reg(dev, reg, fifo_flush, fifo_flush); } static int lan78xx_start_tx_path(struct lan78xx_net *dev) { int ret; netif_dbg(dev, drv, dev->net, "start tx path"); /* Start the MAC transmitter */ ret = lan78xx_start_hw(dev, MAC_TX, MAC_TX_TXEN_); if (ret < 0) return ret; /* Start the Tx FIFO */ ret = lan78xx_start_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_); if (ret < 0) return ret; return 0; } static int lan78xx_stop_tx_path(struct lan78xx_net *dev) { int ret; netif_dbg(dev, drv, dev->net, "stop tx path"); /* Stop the Tx FIFO */ ret = lan78xx_stop_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_, FCT_TX_CTL_DIS_); if (ret < 0) return ret; /* Stop the MAC transmitter */ ret = lan78xx_stop_hw(dev, MAC_TX, MAC_TX_TXEN_, MAC_TX_TXD_); if (ret < 0) return ret; return 0; } /* The caller must ensure the Tx path is stopped before calling * lan78xx_flush_tx_fifo(). */ static int lan78xx_flush_tx_fifo(struct lan78xx_net *dev) { return lan78xx_flush_fifo(dev, FCT_TX_CTL, FCT_TX_CTL_RST_); } static int lan78xx_start_rx_path(struct lan78xx_net *dev) { int ret; netif_dbg(dev, drv, dev->net, "start rx path"); /* Start the Rx FIFO */ ret = lan78xx_start_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_); if (ret < 0) return ret; /* Start the MAC receiver*/ ret = lan78xx_start_hw(dev, MAC_RX, MAC_RX_RXEN_); if (ret < 0) return ret; return 0; } static int lan78xx_stop_rx_path(struct lan78xx_net *dev) { int ret; netif_dbg(dev, drv, dev->net, "stop rx path"); /* Stop the MAC receiver */ ret = lan78xx_stop_hw(dev, MAC_RX, MAC_RX_RXEN_, MAC_RX_RXD_); if (ret < 0) return ret; /* Stop the Rx FIFO */ ret = lan78xx_stop_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_, FCT_RX_CTL_DIS_); if (ret < 0) return ret; return 0; } /* The caller must ensure the Rx path is stopped before calling * lan78xx_flush_rx_fifo(). */ static int lan78xx_flush_rx_fifo(struct lan78xx_net *dev) { return lan78xx_flush_fifo(dev, FCT_RX_CTL, FCT_RX_CTL_RST_); } /* Loop until the read is completed with timeout called with mdiobus_mutex held */ static int lan78xx_mdiobus_wait_not_busy(struct lan78xx_net *dev) { unsigned long start_time = jiffies; u32 val; int ret; do { ret = lan78xx_read_reg(dev, MII_ACC, &val); if (ret < 0) return ret; if (!(val & MII_ACC_MII_BUSY_)) return 0; } while (!time_after(jiffies, start_time + HZ)); return -ETIMEDOUT; } static inline u32 mii_access(int id, int index, int read) { u32 ret; ret = ((u32)id << MII_ACC_PHY_ADDR_SHIFT_) & MII_ACC_PHY_ADDR_MASK_; ret |= ((u32)index << MII_ACC_MIIRINDA_SHIFT_) & MII_ACC_MIIRINDA_MASK_; if (read) ret |= MII_ACC_MII_READ_; else ret |= MII_ACC_MII_WRITE_; ret |= MII_ACC_MII_BUSY_; return ret; } static int lan78xx_wait_eeprom(struct lan78xx_net *dev) { unsigned long start_time = jiffies; u32 val; int ret; do { ret = lan78xx_read_reg(dev, E2P_CMD, &val); if (ret < 0) return ret; if (!(val & E2P_CMD_EPC_BUSY_) || (val & E2P_CMD_EPC_TIMEOUT_)) break; usleep_range(40, 100); } while (!time_after(jiffies, start_time + HZ)); if (val & (E2P_CMD_EPC_TIMEOUT_ | E2P_CMD_EPC_BUSY_)) { netdev_warn(dev->net, "EEPROM read operation timeout"); return -ETIMEDOUT; } return 0; } static int lan78xx_eeprom_confirm_not_busy(struct lan78xx_net *dev) { unsigned long start_time = jiffies; u32 val; int ret; do { ret = lan78xx_read_reg(dev, E2P_CMD, &val); if (ret < 0) return ret; if (!(val & E2P_CMD_EPC_BUSY_)) return 0; usleep_range(40, 100); } while (!time_after(jiffies, start_time + HZ)); netdev_warn(dev->net, "EEPROM is busy"); return -ETIMEDOUT; } static int lan78xx_read_raw_eeprom(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { u32 val, saved; int i, ret; /* depends on chip, some EEPROM pins are muxed with LED function. * disable & restore LED function to access EEPROM. */ ret = lan78xx_read_reg(dev, HW_CFG, &val); if (ret < 0) return ret; saved = val; if (dev->chipid == ID_REV_CHIP_ID_7800_) { val &= ~(HW_CFG_LED1_EN_ | HW_CFG_LED0_EN_); ret = lan78xx_write_reg(dev, HW_CFG, val); if (ret < 0) return ret; } ret = lan78xx_eeprom_confirm_not_busy(dev); if (ret == -ETIMEDOUT) goto read_raw_eeprom_done; /* If USB fails, there is nothing to do */ if (ret < 0) return ret; for (i = 0; i < length; i++) { val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_READ_; val |= (offset & E2P_CMD_EPC_ADDR_MASK_); ret = lan78xx_write_reg(dev, E2P_CMD, val); if (ret < 0) return ret; ret = lan78xx_wait_eeprom(dev); /* Looks like not USB specific error, try to recover */ if (ret == -ETIMEDOUT) goto read_raw_eeprom_done; /* If USB fails, there is nothing to do */ if (ret < 0) return ret; ret = lan78xx_read_reg(dev, E2P_DATA, &val); if (ret < 0) return ret; data[i] = val & 0xFF; offset++; } read_raw_eeprom_done: if (dev->chipid == ID_REV_CHIP_ID_7800_) { int rc = lan78xx_write_reg(dev, HW_CFG, saved); /* If USB fails, there is nothing to do */ if (rc < 0) return rc; } return ret; } static int lan78xx_read_eeprom(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { int ret; u8 sig; ret = lan78xx_read_raw_eeprom(dev, 0, 1, &sig); if (ret < 0) return ret; if (sig != EEPROM_INDICATOR) return -ENODATA; return lan78xx_read_raw_eeprom(dev, offset, length, data); } static int lan78xx_write_raw_eeprom(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { u32 val; u32 saved; int i, ret; /* depends on chip, some EEPROM pins are muxed with LED function. * disable & restore LED function to access EEPROM. */ ret = lan78xx_read_reg(dev, HW_CFG, &val); if (ret < 0) return ret; saved = val; if (dev->chipid == ID_REV_CHIP_ID_7800_) { val &= ~(HW_CFG_LED1_EN_ | HW_CFG_LED0_EN_); ret = lan78xx_write_reg(dev, HW_CFG, val); if (ret < 0) return ret; } ret = lan78xx_eeprom_confirm_not_busy(dev); /* Looks like not USB specific error, try to recover */ if (ret == -ETIMEDOUT) goto write_raw_eeprom_done; /* If USB fails, there is nothing to do */ if (ret < 0) return ret; /* Issue write/erase enable command */ val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_EWEN_; ret = lan78xx_write_reg(dev, E2P_CMD, val); if (ret < 0) return ret; ret = lan78xx_wait_eeprom(dev); /* Looks like not USB specific error, try to recover */ if (ret == -ETIMEDOUT) goto write_raw_eeprom_done; /* If USB fails, there is nothing to do */ if (ret < 0) return ret; for (i = 0; i < length; i++) { /* Fill data register */ val = data[i]; ret = lan78xx_write_reg(dev, E2P_DATA, val); if (ret < 0) return ret; /* Send "write" command */ val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_WRITE_; val |= (offset & E2P_CMD_EPC_ADDR_MASK_); ret = lan78xx_write_reg(dev, E2P_CMD, val); if (ret < 0) return ret; ret = lan78xx_wait_eeprom(dev); /* Looks like not USB specific error, try to recover */ if (ret == -ETIMEDOUT) goto write_raw_eeprom_done; /* If USB fails, there is nothing to do */ if (ret < 0) return ret; offset++; } write_raw_eeprom_done: if (dev->chipid == ID_REV_CHIP_ID_7800_) { int rc = lan78xx_write_reg(dev, HW_CFG, saved); /* If USB fails, there is nothing to do */ if (rc < 0) return rc; } return ret; } static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { unsigned long timeout; int ret, i; u32 buf; ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (ret < 0) return ret; if (buf & OTP_PWR_DN_PWRDN_N_) { /* clear it and wait to be cleared */ ret = lan78xx_write_reg(dev, OTP_PWR_DN, 0); if (ret < 0) return ret; timeout = jiffies + HZ; do { usleep_range(1, 10); ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (ret < 0) return ret; if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_PWR_DN"); return -ETIMEDOUT; } } while (buf & OTP_PWR_DN_PWRDN_N_); } for (i = 0; i < length; i++) { ret = lan78xx_write_reg(dev, OTP_ADDR1, ((offset + i) >> 8) & OTP_ADDR1_15_11); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, OTP_ADDR2, ((offset + i) & OTP_ADDR2_10_3)); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); if (ret < 0) return ret; timeout = jiffies + HZ; do { udelay(1); ret = lan78xx_read_reg(dev, OTP_STATUS, &buf); if (ret < 0) return ret; if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_STATUS"); return -ETIMEDOUT; } } while (buf & OTP_STATUS_BUSY_); ret = lan78xx_read_reg(dev, OTP_RD_DATA, &buf); if (ret < 0) return ret; data[i] = (u8)(buf & 0xFF); } return 0; } static int lan78xx_write_raw_otp(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { int i; u32 buf; unsigned long timeout; int ret; ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (ret < 0) return ret; if (buf & OTP_PWR_DN_PWRDN_N_) { /* clear it and wait to be cleared */ ret = lan78xx_write_reg(dev, OTP_PWR_DN, 0); if (ret < 0) return ret; timeout = jiffies + HZ; do { udelay(1); ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (ret < 0) return ret; if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_PWR_DN completion"); return -ETIMEDOUT; } } while (buf & OTP_PWR_DN_PWRDN_N_); } /* set to BYTE program mode */ ret = lan78xx_write_reg(dev, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_); if (ret < 0) return ret; for (i = 0; i < length; i++) { ret = lan78xx_write_reg(dev, OTP_ADDR1, ((offset + i) >> 8) & OTP_ADDR1_15_11); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, OTP_ADDR2, ((offset + i) & OTP_ADDR2_10_3)); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); if (ret < 0) return ret; timeout = jiffies + HZ; do { udelay(1); ret = lan78xx_read_reg(dev, OTP_STATUS, &buf); if (ret < 0) return ret; if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "Timeout on OTP_STATUS completion"); return -ETIMEDOUT; } } while (buf & OTP_STATUS_BUSY_); } return 0; } static int lan78xx_read_otp(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { u8 sig; int ret; ret = lan78xx_read_raw_otp(dev, 0, 1, &sig); if (ret == 0) { if (sig == OTP_INDICATOR_2) offset += 0x100; else if (sig != OTP_INDICATOR_1) ret = -EINVAL; if (!ret) ret = lan78xx_read_raw_otp(dev, offset, length, data); } return ret; } static int lan78xx_dataport_wait_not_busy(struct lan78xx_net *dev) { int i, ret; for (i = 0; i < 100; i++) { u32 dp_sel; ret = lan78xx_read_reg(dev, DP_SEL, &dp_sel); if (unlikely(ret < 0)) return ret; if (dp_sel & DP_SEL_DPRDY_) return 0; usleep_range(40, 100); } netdev_warn(dev->net, "%s timed out", __func__); return -ETIMEDOUT; } static int lan78xx_dataport_write(struct lan78xx_net *dev, u32 ram_select, u32 addr, u32 length, u32 *buf) { struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); int i, ret; ret = usb_autopm_get_interface(dev->intf); if (ret < 0) return ret; mutex_lock(&pdata->dataport_mutex); ret = lan78xx_dataport_wait_not_busy(dev); if (ret < 0) goto dataport_write; ret = lan78xx_update_reg(dev, DP_SEL, DP_SEL_RSEL_MASK_, ram_select); if (ret < 0) goto dataport_write; for (i = 0; i < length; i++) { ret = lan78xx_write_reg(dev, DP_ADDR, addr + i); if (ret < 0) goto dataport_write; ret = lan78xx_write_reg(dev, DP_DATA, buf[i]); if (ret < 0) goto dataport_write; ret = lan78xx_write_reg(dev, DP_CMD, DP_CMD_WRITE_); if (ret < 0) goto dataport_write; ret = lan78xx_dataport_wait_not_busy(dev); if (ret < 0) goto dataport_write; } dataport_write: if (ret < 0) netdev_warn(dev->net, "dataport write failed %pe", ERR_PTR(ret)); mutex_unlock(&pdata->dataport_mutex); usb_autopm_put_interface(dev->intf); return ret; } static void lan78xx_set_addr_filter(struct lan78xx_priv *pdata, int index, u8 addr[ETH_ALEN]) { u32 temp; if ((pdata) && (index > 0) && (index < NUM_OF_MAF)) { temp = addr[3]; temp = addr[2] | (temp << 8); temp = addr[1] | (temp << 8); temp = addr[0] | (temp << 8); pdata->pfilter_table[index][1] = temp; temp = addr[5]; temp = addr[4] | (temp << 8); temp |= MAF_HI_VALID_ | MAF_HI_TYPE_DST_; pdata->pfilter_table[index][0] = temp; } } /* returns hash bit number for given MAC address */ static inline u32 lan78xx_hash(char addr[ETH_ALEN]) { return (ether_crc(ETH_ALEN, addr) >> 23) & 0x1ff; } static void lan78xx_deferred_multicast_write(struct work_struct *param) { struct lan78xx_priv *pdata = container_of(param, struct lan78xx_priv, set_multicast); struct lan78xx_net *dev = pdata->dev; int i, ret; netif_dbg(dev, drv, dev->net, "deferred multicast write 0x%08x\n", pdata->rfe_ctl); ret = lan78xx_dataport_write(dev, DP_SEL_RSEL_VLAN_DA_, DP_SEL_VHF_VLAN_LEN, DP_SEL_VHF_HASH_LEN, pdata->mchash_table); if (ret < 0) goto multicast_write_done; for (i = 1; i < NUM_OF_MAF; i++) { ret = lan78xx_write_reg(dev, MAF_HI(i), 0); if (ret < 0) goto multicast_write_done; ret = lan78xx_write_reg(dev, MAF_LO(i), pdata->pfilter_table[i][1]); if (ret < 0) goto multicast_write_done; ret = lan78xx_write_reg(dev, MAF_HI(i), pdata->pfilter_table[i][0]); if (ret < 0) goto multicast_write_done; } ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); multicast_write_done: if (ret < 0) netdev_warn(dev->net, "multicast write failed %pe", ERR_PTR(ret)); return; } static void lan78xx_set_multicast(struct net_device *netdev) { struct lan78xx_net *dev = netdev_priv(netdev); struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); unsigned long flags; int i; spin_lock_irqsave(&pdata->rfe_ctl_lock, flags); pdata->rfe_ctl &= ~(RFE_CTL_UCAST_EN_ | RFE_CTL_MCAST_EN_ | RFE_CTL_DA_PERFECT_ | RFE_CTL_MCAST_HASH_); for (i = 0; i < DP_SEL_VHF_HASH_LEN; i++) pdata->mchash_table[i] = 0; /* pfilter_table[0] has own HW address */ for (i = 1; i < NUM_OF_MAF; i++) { pdata->pfilter_table[i][0] = 0; pdata->pfilter_table[i][1] = 0; } pdata->rfe_ctl |= RFE_CTL_BCAST_EN_; if (dev->net->flags & IFF_PROMISC) { netif_dbg(dev, drv, dev->net, "promiscuous mode enabled"); pdata->rfe_ctl |= RFE_CTL_MCAST_EN_ | RFE_CTL_UCAST_EN_; } else { if (dev->net->flags & IFF_ALLMULTI) { netif_dbg(dev, drv, dev->net, "receive all multicast enabled"); pdata->rfe_ctl |= RFE_CTL_MCAST_EN_; } } if (netdev_mc_count(dev->net)) { struct netdev_hw_addr *ha; int i; netif_dbg(dev, drv, dev->net, "receive multicast hash filter"); pdata->rfe_ctl |= RFE_CTL_DA_PERFECT_; i = 1; netdev_for_each_mc_addr(ha, netdev) { /* set first 32 into Perfect Filter */ if (i < 33) { lan78xx_set_addr_filter(pdata, i, ha->addr); } else { u32 bitnum = lan78xx_hash(ha->addr); pdata->mchash_table[bitnum / 32] |= (1 << (bitnum % 32)); pdata->rfe_ctl |= RFE_CTL_MCAST_HASH_; } i++; } } spin_unlock_irqrestore(&pdata->rfe_ctl_lock, flags); /* defer register writes to a sleepable context */ schedule_work(&pdata->set_multicast); } static void lan78xx_rx_urb_submit_all(struct lan78xx_net *dev); static int lan78xx_mac_reset(struct lan78xx_net *dev) { unsigned long start_time = jiffies; u32 val; int ret; mutex_lock(&dev->mdiobus_mutex); /* Resetting the device while there is activity on the MDIO * bus can result in the MAC interface locking up and not * completing register access transactions. */ ret = lan78xx_mdiobus_wait_not_busy(dev); if (ret < 0) goto exit_unlock; ret = lan78xx_read_reg(dev, MAC_CR, &val); if (ret < 0) goto exit_unlock; val |= MAC_CR_RST_; ret = lan78xx_write_reg(dev, MAC_CR, val); if (ret < 0) goto exit_unlock; /* Wait for the reset to complete before allowing any further * MAC register accesses otherwise the MAC may lock up. */ do { ret = lan78xx_read_reg(dev, MAC_CR, &val); if (ret < 0) goto exit_unlock; if (!(val & MAC_CR_RST_)) { ret = 0; goto exit_unlock; } } while (!time_after(jiffies, start_time + HZ)); ret = -ETIMEDOUT; exit_unlock: mutex_unlock(&dev->mdiobus_mutex); return ret; } /** * lan78xx_phy_int_ack - Acknowledge PHY interrupt * @dev: pointer to the LAN78xx device structure * * This function acknowledges the PHY interrupt by setting the * INT_STS_PHY_INT_ bit in the interrupt status register (INT_STS). * * Return: 0 on success or a negative error code on failure. */ static int lan78xx_phy_int_ack(struct lan78xx_net *dev) { return lan78xx_write_reg(dev, INT_STS, INT_STS_PHY_INT_); } /* some work can't be done in tasklets, so we use keventd * * NOTE: annoying asymmetry: if it's active, schedule_work() fails, * but tasklet_schedule() doesn't. hope the failure is rare. */ static void lan78xx_defer_kevent(struct lan78xx_net *dev, int work) { set_bit(work, &dev->flags); if (!schedule_delayed_work(&dev->wq, 0)) netdev_err(dev->net, "kevent %d may have been dropped\n", work); } static void lan78xx_status(struct lan78xx_net *dev, struct urb *urb) { u32 intdata; if (urb->actual_length != 4) { netdev_warn(dev->net, "unexpected urb length %d", urb->actual_length); return; } intdata = get_unaligned_le32(urb->transfer_buffer); if (intdata & INT_ENP_PHY_INT) { netif_dbg(dev, link, dev->net, "PHY INTR: 0x%08x\n", intdata); lan78xx_defer_kevent(dev, EVENT_PHY_INT_ACK); if (dev->domain_data.phyirq > 0) generic_handle_irq_safe(dev->domain_data.phyirq); } else { netdev_warn(dev->net, "unexpected interrupt: 0x%08x\n", intdata); } } static int lan78xx_ethtool_get_eeprom_len(struct net_device *netdev) { return MAX_EEPROM_SIZE; } static int lan78xx_ethtool_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *ee, u8 *data) { struct lan78xx_net *dev = netdev_priv(netdev); int ret; ret = usb_autopm_get_interface(dev->intf); if (ret) return ret; ee->magic = LAN78XX_EEPROM_MAGIC; ret = lan78xx_read_raw_eeprom(dev, ee->offset, ee->len, data); usb_autopm_put_interface(dev->intf); return ret; } static int lan78xx_ethtool_set_eeprom(struct net_device *netdev, struct ethtool_eeprom *ee, u8 *data) { struct lan78xx_net *dev = netdev_priv(netdev); int ret; ret = usb_autopm_get_interface(dev->intf); if (ret) return ret; /* Invalid EEPROM_INDICATOR at offset zero will result in a failure * to load data from EEPROM */ if (ee->magic == LAN78XX_EEPROM_MAGIC) ret = lan78xx_write_raw_eeprom(dev, ee->offset, ee->len, data); else if ((ee->magic == LAN78XX_OTP_MAGIC) && (ee->offset == 0) && (ee->len == 512) && (data[0] == OTP_INDICATOR_1)) ret = lan78xx_write_raw_otp(dev, ee->offset, ee->len, data); usb_autopm_put_interface(dev->intf); return ret; } static void lan78xx_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { if (stringset == ETH_SS_STATS) memcpy(data, lan78xx_gstrings, sizeof(lan78xx_gstrings)); else if (stringset == ETH_SS_TEST) net_selftest_get_strings(data); } static int lan78xx_get_sset_count(struct net_device *netdev, int sset) { if (sset == ETH_SS_STATS) return ARRAY_SIZE(lan78xx_gstrings); else if (sset == ETH_SS_TEST) return net_selftest_get_count(); else return -EOPNOTSUPP; } static void lan78xx_get_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { struct lan78xx_net *dev = netdev_priv(netdev); lan78xx_update_stats(dev); mutex_lock(&dev->stats.access_lock); memcpy(data, &dev->stats.curr_stat, sizeof(dev->stats.curr_stat)); mutex_unlock(&dev->stats.access_lock); } static void lan78xx_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct lan78xx_net *dev = netdev_priv(netdev); int ret; u32 buf; struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); if (usb_autopm_get_interface(dev->intf) < 0) return; ret = lan78xx_read_reg(dev, USB_CFG0, &buf); if (unlikely(ret < 0)) { netdev_warn(dev->net, "failed to get WoL %pe", ERR_PTR(ret)); wol->supported = 0; wol->wolopts = 0; } else { if (buf & USB_CFG_RMT_WKP_) { wol->supported = WAKE_ALL; wol->wolopts = pdata->wol; } else { wol->supported = 0; wol->wolopts = 0; } } usb_autopm_put_interface(dev->intf); } static int lan78xx_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct lan78xx_net *dev = netdev_priv(netdev); struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); int ret; if (wol->wolopts & ~WAKE_ALL) return -EINVAL; ret = usb_autopm_get_interface(dev->intf); if (ret < 0) return ret; pdata->wol = wol->wolopts; ret = device_set_wakeup_enable(&dev->udev->dev, (bool)wol->wolopts); if (ret < 0) goto exit_pm_put; ret = phy_ethtool_set_wol(netdev->phydev, wol); exit_pm_put: usb_autopm_put_interface(dev->intf); return ret; } static int lan78xx_get_eee(struct net_device *net, struct ethtool_keee *edata) { struct lan78xx_net *dev = netdev_priv(net); return phylink_ethtool_get_eee(dev->phylink, edata); } static int lan78xx_set_eee(struct net_device *net, struct ethtool_keee *edata) { struct lan78xx_net *dev = netdev_priv(net); return phylink_ethtool_set_eee(dev->phylink, edata); } static void lan78xx_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info) { struct lan78xx_net *dev = netdev_priv(net); strscpy(info->driver, DRIVER_NAME, sizeof(info->driver)); usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info)); } static u32 lan78xx_get_msglevel(struct net_device *net) { struct lan78xx_net *dev = netdev_priv(net); return dev->msg_enable; } static void lan78xx_set_msglevel(struct net_device *net, u32 level) { struct lan78xx_net *dev = netdev_priv(net); dev->msg_enable = level; } static int lan78xx_get_link_ksettings(struct net_device *net, struct ethtool_link_ksettings *cmd) { struct lan78xx_net *dev = netdev_priv(net); return phylink_ethtool_ksettings_get(dev->phylink, cmd); } static int lan78xx_set_link_ksettings(struct net_device *net, const struct ethtool_link_ksettings *cmd) { struct lan78xx_net *dev = netdev_priv(net); return phylink_ethtool_ksettings_set(dev->phylink, cmd); } static void lan78xx_get_pause(struct net_device *net, struct ethtool_pauseparam *pause) { struct lan78xx_net *dev = netdev_priv(net); phylink_ethtool_get_pauseparam(dev->phylink, pause); } static int lan78xx_set_pause(struct net_device *net, struct ethtool_pauseparam *pause) { struct lan78xx_net *dev = netdev_priv(net); return phylink_ethtool_set_pauseparam(dev->phylink, pause); } static int lan78xx_get_regs_len(struct net_device *netdev) { return sizeof(lan78xx_regs); } static void lan78xx_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *buf) { struct lan78xx_net *dev = netdev_priv(netdev); unsigned int data_count = 0; u32 *data = buf; int i, ret; /* Read Device/MAC registers */ for (i = 0; i < ARRAY_SIZE(lan78xx_regs); i++) { ret = lan78xx_read_reg(dev, lan78xx_regs[i], &data[i]); if (ret < 0) { netdev_warn(dev->net, "failed to read register 0x%08x\n", lan78xx_regs[i]); goto clean_data; } data_count++; } return; clean_data: memset(data, 0, data_count * sizeof(u32)); } static const struct ethtool_ops lan78xx_ethtool_ops = { .get_link = ethtool_op_get_link, .nway_reset = phy_ethtool_nway_reset, .get_drvinfo = lan78xx_get_drvinfo, .get_msglevel = lan78xx_get_msglevel, .set_msglevel = lan78xx_set_msglevel, .get_eeprom_len = lan78xx_ethtool_get_eeprom_len, .get_eeprom = lan78xx_ethtool_get_eeprom, .set_eeprom = lan78xx_ethtool_set_eeprom, .get_ethtool_stats = lan78xx_get_stats, .get_sset_count = lan78xx_get_sset_count, .self_test = net_selftest, .get_strings = lan78xx_get_strings, .get_wol = lan78xx_get_wol, .set_wol = lan78xx_set_wol, .get_ts_info = ethtool_op_get_ts_info, .get_eee = lan78xx_get_eee, .set_eee = lan78xx_set_eee, .get_pauseparam = lan78xx_get_pause, .set_pauseparam = lan78xx_set_pause, .get_link_ksettings = lan78xx_get_link_ksettings, .set_link_ksettings = lan78xx_set_link_ksettings, .get_regs_len = lan78xx_get_regs_len, .get_regs = lan78xx_get_regs, }; static int lan78xx_init_mac_address(struct lan78xx_net *dev) { u32 addr_lo, addr_hi; u8 addr[6]; int ret; ret = lan78xx_read_reg(dev, RX_ADDRL, &addr_lo); if (ret < 0) return ret; ret = lan78xx_read_reg(dev, RX_ADDRH, &addr_hi); if (ret < 0) return ret; addr[0] = addr_lo & 0xFF; addr[1] = (addr_lo >> 8) & 0xFF; addr[2] = (addr_lo >> 16) & 0xFF; addr[3] = (addr_lo >> 24) & 0xFF; addr[4] = addr_hi & 0xFF; addr[5] = (addr_hi >> 8) & 0xFF; if (!is_valid_ether_addr(addr)) { if (!eth_platform_get_mac_address(&dev->udev->dev, addr)) { /* valid address present in Device Tree */ netif_dbg(dev, ifup, dev->net, "MAC address read from Device Tree"); } else if (((lan78xx_read_eeprom(dev, EEPROM_MAC_OFFSET, ETH_ALEN, addr) == 0) || (lan78xx_read_otp(dev, EEPROM_MAC_OFFSET, ETH_ALEN, addr) == 0)) && is_valid_ether_addr(addr)) { /* eeprom values are valid so use them */ netif_dbg(dev, ifup, dev->net, "MAC address read from EEPROM"); } else { /* generate random MAC */ eth_random_addr(addr); netif_dbg(dev, ifup, dev->net, "MAC address set to random addr"); } addr_lo = addr[0] | (addr[1] << 8) | (addr[2] << 16) | (addr[3] << 24); addr_hi = addr[4] | (addr[5] << 8); ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); if (ret < 0) return ret; } ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); if (ret < 0) return ret; eth_hw_addr_set(dev->net, addr); return 0; } /* MDIO read and write wrappers for phylib */ static int lan78xx_mdiobus_read(struct mii_bus *bus, int phy_id, int idx) { struct lan78xx_net *dev = bus->priv; u32 val, addr; int ret; ret = usb_autopm_get_interface(dev->intf); if (ret < 0) return ret; mutex_lock(&dev->mdiobus_mutex); /* confirm MII not busy */ ret = lan78xx_mdiobus_wait_not_busy(dev); if (ret < 0) goto done; /* set the address, index & direction (read from PHY) */ addr = mii_access(phy_id, idx, MII_READ); ret = lan78xx_write_reg(dev, MII_ACC, addr); if (ret < 0) goto done; ret = lan78xx_mdiobus_wait_not_busy(dev); if (ret < 0) goto done; ret = lan78xx_read_reg(dev, MII_DATA, &val); if (ret < 0) goto done; ret = (int)(val & 0xFFFF); done: mutex_unlock(&dev->mdiobus_mutex); usb_autopm_put_interface(dev->intf); return ret; } static int lan78xx_mdiobus_write(struct mii_bus *bus, int phy_id, int idx, u16 regval) { struct lan78xx_net *dev = bus->priv; u32 val, addr; int ret; ret = usb_autopm_get_interface(dev->intf); if (ret < 0) return ret; mutex_lock(&dev->mdiobus_mutex); /* confirm MII not busy */ ret = lan78xx_mdiobus_wait_not_busy(dev); if (ret < 0) goto done; val = (u32)regval; ret = lan78xx_write_reg(dev, MII_DATA, val); if (ret < 0) goto done; /* set the address, index & direction (write to PHY) */ addr = mii_access(phy_id, idx, MII_WRITE); ret = lan78xx_write_reg(dev, MII_ACC, addr); if (ret < 0) goto done; ret = lan78xx_mdiobus_wait_not_busy(dev); if (ret < 0) goto done; done: mutex_unlock(&dev->mdiobus_mutex); usb_autopm_put_interface(dev->intf); return ret; } static int lan78xx_mdio_init(struct lan78xx_net *dev) { struct device_node *node; int ret; dev->mdiobus = mdiobus_alloc(); if (!dev->mdiobus) { netdev_err(dev->net, "can't allocate MDIO bus\n"); return -ENOMEM; } dev->mdiobus->priv = (void *)dev; dev->mdiobus->read = lan78xx_mdiobus_read; dev->mdiobus->write = lan78xx_mdiobus_write; dev->mdiobus->name = "lan78xx-mdiobus"; dev->mdiobus->parent = &dev->udev->dev; snprintf(dev->mdiobus->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); switch (dev->chipid) { case ID_REV_CHIP_ID_7800_: case ID_REV_CHIP_ID_7850_: /* set to internal PHY id */ dev->mdiobus->phy_mask = ~(1 << 1); break; case ID_REV_CHIP_ID_7801_: /* scan thru PHYAD[2..0] */ dev->mdiobus->phy_mask = ~(0xFF); break; } node = of_get_child_by_name(dev->udev->dev.of_node, "mdio"); ret = of_mdiobus_register(dev->mdiobus, node); of_node_put(node); if (ret) { netdev_err(dev->net, "can't register MDIO bus\n"); goto exit1; } netdev_dbg(dev->net, "registered mdiobus bus %s\n", dev->mdiobus->id); return 0; exit1: mdiobus_free(dev->mdiobus); return ret; } static void lan78xx_remove_mdio(struct lan78xx_net *dev) { mdiobus_unregister(dev->mdiobus); mdiobus_free(dev->mdiobus); } static int irq_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hwirq) { struct irq_domain_data *data = d->host_data; irq_set_chip_data(irq, data); irq_set_chip_and_handler(irq, data->irqchip, data->irq_handler); irq_set_noprobe(irq); return 0; } static void irq_unmap(struct irq_domain *d, unsigned int irq) { irq_set_chip_and_handler(irq, NULL, NULL); irq_set_chip_data(irq, NULL); } static const struct irq_domain_ops chip_domain_ops = { .map = irq_map, .unmap = irq_unmap, }; static void lan78xx_irq_mask(struct irq_data *irqd) { struct irq_domain_data *data = irq_data_get_irq_chip_data(irqd); data->irqenable &= ~BIT(irqd_to_hwirq(irqd)); } static void lan78xx_irq_unmask(struct irq_data *irqd) { struct irq_domain_data *data = irq_data_get_irq_chip_data(irqd); data->irqenable |= BIT(irqd_to_hwirq(irqd)); } static void lan78xx_irq_bus_lock(struct irq_data *irqd) { struct irq_domain_data *data = irq_data_get_irq_chip_data(irqd); mutex_lock(&data->irq_lock); } static void lan78xx_irq_bus_sync_unlock(struct irq_data *irqd) { struct irq_domain_data *data = irq_data_get_irq_chip_data(irqd); struct lan78xx_net *dev = container_of(data, struct lan78xx_net, domain_data); u32 buf; int ret; /* call register access here because irq_bus_lock & irq_bus_sync_unlock * are only two callbacks executed in non-atomic contex. */ ret = lan78xx_read_reg(dev, INT_EP_CTL, &buf); if (ret < 0) goto irq_bus_sync_unlock; if (buf != data->irqenable) ret = lan78xx_write_reg(dev, INT_EP_CTL, data->irqenable); irq_bus_sync_unlock: if (ret < 0) netdev_err(dev->net, "Failed to sync IRQ enable register: %pe\n", ERR_PTR(ret)); mutex_unlock(&data->irq_lock); } static struct irq_chip lan78xx_irqchip = { .name = "lan78xx-irqs", .irq_mask = lan78xx_irq_mask, .irq_unmask = lan78xx_irq_unmask, .irq_bus_lock = lan78xx_irq_bus_lock, .irq_bus_sync_unlock = lan78xx_irq_bus_sync_unlock, }; static int lan78xx_setup_irq_domain(struct lan78xx_net *dev) { struct irq_domain *irqdomain; unsigned int irqmap = 0; u32 buf; int ret = 0; mutex_init(&dev->domain_data.irq_lock); ret = lan78xx_read_reg(dev, INT_EP_CTL, &buf); if (ret < 0) return ret; dev->domain_data.irqenable = buf; dev->domain_data.irqchip = &lan78xx_irqchip; dev->domain_data.irq_handler = handle_simple_irq; irqdomain = irq_domain_create_simple(dev_fwnode(dev->udev->dev.parent), MAX_INT_EP, 0, &chip_domain_ops, &dev->domain_data); if (irqdomain) { /* create mapping for PHY interrupt */ irqmap = irq_create_mapping(irqdomain, INT_EP_PHY); if (!irqmap) { irq_domain_remove(irqdomain); irqdomain = NULL; ret = -EINVAL; } } else { ret = -EINVAL; } dev->domain_data.irqdomain = irqdomain; dev->domain_data.phyirq = irqmap; return ret; } static void lan78xx_remove_irq_domain(struct lan78xx_net *dev) { if (dev->domain_data.phyirq > 0) { irq_dispose_mapping(dev->domain_data.phyirq); if (dev->domain_data.irqdomain) irq_domain_remove(dev->domain_data.irqdomain); } dev->domain_data.phyirq = 0; dev->domain_data.irqdomain = NULL; } static void lan78xx_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { struct net_device *net = to_net_dev(config->dev); struct lan78xx_net *dev = netdev_priv(net); u32 mac_cr = 0; int ret; /* Check if the mode is supported */ if (mode != MLO_AN_FIXED && mode != MLO_AN_PHY) { netdev_err(net, "Unsupported negotiation mode: %u\n", mode); return; } switch (state->interface) { case PHY_INTERFACE_MODE_GMII: mac_cr |= MAC_CR_GMII_EN_; break; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_TXID: case PHY_INTERFACE_MODE_RGMII_RXID: break; default: netdev_warn(net, "Unsupported interface mode: %d\n", state->interface); return; } ret = lan78xx_update_reg(dev, MAC_CR, MAC_CR_GMII_EN_, mac_cr); if (ret < 0) netdev_err(net, "Failed to config MAC with error %pe\n", ERR_PTR(ret)); } static void lan78xx_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { struct net_device *net = to_net_dev(config->dev); struct lan78xx_net *dev = netdev_priv(net); int ret; netif_stop_queue(net); /* MAC reset will not de-assert TXEN/RXEN, we need to stop them * manually before reset. TX and RX should be disabled before running * link_up sequence. */ ret = lan78xx_stop_tx_path(dev); if (ret < 0) goto link_down_fail; ret = lan78xx_stop_rx_path(dev); if (ret < 0) goto link_down_fail; /* MAC reset seems to not affect MAC configuration, no idea if it is * really needed, but it was done in previous driver version. So, leave * it here. */ ret = lan78xx_mac_reset(dev); if (ret < 0) goto link_down_fail; return; link_down_fail: netdev_err(dev->net, "Failed to set MAC down with error %pe\n", ERR_PTR(ret)); } /** * lan78xx_configure_usb - Configure USB link power settings * @dev: pointer to the LAN78xx device structure * @speed: negotiated Ethernet link speed (in Mbps) * * This function configures U1/U2 link power management for SuperSpeed * USB devices based on the current Ethernet link speed. It uses the * USB_CFG1 register to enable or disable U1 and U2 low-power states. * * Note: Only LAN7800 and LAN7801 support SuperSpeed (USB 3.x). * LAN7850 is a High-Speed-only (USB 2.0) device and is skipped. * * Return: 0 on success or a negative error code on failure. */ static int lan78xx_configure_usb(struct lan78xx_net *dev, int speed) { u32 mask, val; int ret; /* Only configure USB settings for SuperSpeed devices */ if (dev->udev->speed != USB_SPEED_SUPER) return 0; /* LAN7850 does not support USB 3.x */ if (dev->chipid == ID_REV_CHIP_ID_7850_) { netdev_warn_once(dev->net, "Unexpected SuperSpeed for LAN7850 (USB 2.0 only)\n"); return 0; } switch (speed) { case SPEED_1000: /* Disable U2, enable U1 */ ret = lan78xx_update_reg(dev, USB_CFG1, USB_CFG1_DEV_U2_INIT_EN_, 0); if (ret < 0) return ret; return lan78xx_update_reg(dev, USB_CFG1, USB_CFG1_DEV_U1_INIT_EN_, USB_CFG1_DEV_U1_INIT_EN_); case SPEED_100: case SPEED_10: /* Enable both U1 and U2 */ mask = USB_CFG1_DEV_U1_INIT_EN_ | USB_CFG1_DEV_U2_INIT_EN_; val = mask; return lan78xx_update_reg(dev, USB_CFG1, mask, val); default: netdev_warn(dev->net, "Unsupported link speed: %d\n", speed); return -EINVAL; } } /** * lan78xx_configure_flowcontrol - Set MAC and FIFO flow control configuration * @dev: pointer to the LAN78xx device structure * @tx_pause: enable transmission of pause frames * @rx_pause: enable reception of pause frames * * This function configures the LAN78xx flow control settings by writing * to the FLOW and FCT_FLOW registers. The pause time is set to the * maximum allowed value (65535 quanta). FIFO thresholds are selected * based on USB speed. * * The Pause Time field is measured in units of 512-bit times (quanta): * - At 1 Gbps: 1 quanta = 512 ns → max ~33.6 ms pause * - At 100 Mbps: 1 quanta = 5.12 µs → max ~335 ms pause * - At 10 Mbps: 1 quanta = 51.2 µs → max ~3.3 s pause * * Flow control thresholds (FCT_FLOW) are used to trigger pause/resume: * - RXUSED is the number of bytes used in the RX FIFO * - Flow is turned ON when RXUSED ≥ FLOW_ON threshold * - Flow is turned OFF when RXUSED ≤ FLOW_OFF threshold * - Both thresholds are encoded in units of 512 bytes (rounded up) * * Thresholds differ by USB speed because available USB bandwidth * affects how fast packets can be drained from the RX FIFO: * - USB 3.x (SuperSpeed): * FLOW_ON = 9216 bytes → 18 units * FLOW_OFF = 4096 bytes → 8 units * - USB 2.0 (High-Speed): * FLOW_ON = 8704 bytes → 17 units * FLOW_OFF = 1024 bytes → 2 units * * Note: The FCT_FLOW register must be configured before enabling TX pause * (i.e., before setting FLOW_CR_TX_FCEN_), as required by the hardware. * * Return: 0 on success or a negative error code on failure. */ static int lan78xx_configure_flowcontrol(struct lan78xx_net *dev, bool tx_pause, bool rx_pause) { /* Use maximum pause time: 65535 quanta (512-bit times) */ const u32 pause_time_quanta = 65535; u32 fct_flow = 0; u32 flow = 0; int ret; /* Prepare MAC flow control bits */ if (tx_pause) flow |= FLOW_CR_TX_FCEN_ | pause_time_quanta; if (rx_pause) flow |= FLOW_CR_RX_FCEN_; /* Select RX FIFO thresholds based on USB speed * * FCT_FLOW layout: * bits [6:0] FLOW_ON threshold (RXUSED ≥ ON → assert pause) * bits [14:8] FLOW_OFF threshold (RXUSED ≤ OFF → deassert pause) * thresholds are expressed in units of 512 bytes */ switch (dev->udev->speed) { case USB_SPEED_SUPER: fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_SS, FLOW_OFF_SS); break; case USB_SPEED_HIGH: fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_HS, FLOW_OFF_HS); break; default: netdev_warn(dev->net, "Unsupported USB speed: %d\n", dev->udev->speed); return -EINVAL; } /* Step 1: Write FIFO thresholds before enabling pause frames */ ret = lan78xx_write_reg(dev, FCT_FLOW, fct_flow); if (ret < 0) return ret; /* Step 2: Enable MAC pause functionality */ return lan78xx_write_reg(dev, FLOW, flow); } static void lan78xx_mac_link_up(struct phylink_config *config, struct phy_device *phy, unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause) { struct net_device *net = to_net_dev(config->dev); struct lan78xx_net *dev = netdev_priv(net); u32 mac_cr = 0; int ret; switch (speed) { case SPEED_1000: mac_cr |= MAC_CR_SPEED_1000_; break; case SPEED_100: mac_cr |= MAC_CR_SPEED_100_; break; case SPEED_10: mac_cr |= MAC_CR_SPEED_10_; break; default: netdev_err(dev->net, "Unsupported speed %d\n", speed); return; } if (duplex == DUPLEX_FULL) mac_cr |= MAC_CR_FULL_DUPLEX_; /* make sure TXEN and RXEN are disabled before reconfiguring MAC */ ret = lan78xx_update_reg(dev, MAC_CR, MAC_CR_SPEED_MASK_ | MAC_CR_FULL_DUPLEX_ | MAC_CR_EEE_EN_, mac_cr); if (ret < 0) goto link_up_fail; ret = lan78xx_configure_flowcontrol(dev, tx_pause, rx_pause); if (ret < 0) goto link_up_fail; ret = lan78xx_configure_usb(dev, speed); if (ret < 0) goto link_up_fail; lan78xx_rx_urb_submit_all(dev); ret = lan78xx_flush_rx_fifo(dev); if (ret < 0) goto link_up_fail; ret = lan78xx_flush_tx_fifo(dev); if (ret < 0) goto link_up_fail; ret = lan78xx_start_tx_path(dev); if (ret < 0) goto link_up_fail; ret = lan78xx_start_rx_path(dev); if (ret < 0) goto link_up_fail; netif_start_queue(net); return; link_up_fail: netdev_err(dev->net, "Failed to set MAC up with error %pe\n", ERR_PTR(ret)); } /** * lan78xx_mac_eee_enable - Enable or disable MAC-side EEE support * @dev: LAN78xx device * @enable: true to enable EEE, false to disable * * This function sets or clears the MAC_CR_EEE_EN_ bit to control Energy * Efficient Ethernet (EEE) operation. According to current understanding * of the LAN7800 documentation, this bit can be modified while TX and RX * are enabled. No explicit requirement was found to disable data paths * before changing this bit. * * Return: 0 on success or a negative error code */ static int lan78xx_mac_eee_enable(struct lan78xx_net *dev, bool enable) { u32 mac_cr = 0; if (enable) mac_cr |= MAC_CR_EEE_EN_; return lan78xx_update_reg(dev, MAC_CR, MAC_CR_EEE_EN_, mac_cr); } static void lan78xx_mac_disable_tx_lpi(struct phylink_config *config) { struct net_device *net = to_net_dev(config->dev); struct lan78xx_net *dev = netdev_priv(net); lan78xx_mac_eee_enable(dev, false); } static int lan78xx_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, bool tx_clk_stop) { struct net_device *net = to_net_dev(config->dev); struct lan78xx_net *dev = netdev_priv(net); int ret; /* Software should only change this field when Energy Efficient * Ethernet Enable (EEEEN) is cleared. We ensure that by clearing * EEEEN during probe, and phylink itself guarantees that * mac_disable_tx_lpi() will have been previously called. */ ret = lan78xx_write_reg(dev, EEE_TX_LPI_REQ_DLY, timer); if (ret < 0) return ret; return lan78xx_mac_eee_enable(dev, true); } static const struct phylink_mac_ops lan78xx_phylink_mac_ops = { .mac_config = lan78xx_mac_config, .mac_link_down = lan78xx_mac_link_down, .mac_link_up = lan78xx_mac_link_up, .mac_disable_tx_lpi = lan78xx_mac_disable_tx_lpi, .mac_enable_tx_lpi = lan78xx_mac_enable_tx_lpi, }; /** * lan78xx_set_fixed_link() - Set fixed link configuration for LAN7801 * @dev: LAN78xx device * * Use fixed link configuration with 1 Gbps full duplex. This is used in special * cases like EVB-KSZ9897-1, where LAN7801 acts as a USB-to-Ethernet interface * to a switch without a visible PHY. * * Return: pointer to the registered fixed PHY, or ERR_PTR() on error. */ static int lan78xx_set_fixed_link(struct lan78xx_net *dev) { static const struct phylink_link_state state = { .speed = SPEED_1000, .duplex = DUPLEX_FULL, }; netdev_info(dev->net, "No PHY found on LAN7801 – using fixed link instead (e.g. EVB-KSZ9897-1)\n"); return phylink_set_fixed_link(dev->phylink, &state); } /** * lan78xx_get_phy() - Probe or register PHY device and set interface mode * @dev: LAN78xx device structure * * This function attempts to find a PHY on the MDIO bus. If no PHY is found * and the chip is LAN7801, it registers a fixed PHY as fallback. It also * sets dev->interface based on chip ID and detected PHY type. * * Return: a valid PHY device pointer, or ERR_PTR() on failure. */ static struct phy_device *lan78xx_get_phy(struct lan78xx_net *dev) { struct phy_device *phydev; /* Attempt to locate a PHY on the MDIO bus */ phydev = phy_find_first(dev->mdiobus); switch (dev->chipid) { case ID_REV_CHIP_ID_7801_: if (phydev) { /* External RGMII PHY detected */ dev->interface = PHY_INTERFACE_MODE_RGMII_ID; phydev->is_internal = false; if (!phydev->drv) netdev_warn(dev->net, "PHY driver not found – assuming RGMII delays are on PCB or strapped for the PHY\n"); return phydev; } dev->interface = PHY_INTERFACE_MODE_RGMII; /* No PHY found – fallback to fixed PHY (e.g. KSZ switch board) */ return NULL; case ID_REV_CHIP_ID_7800_: case ID_REV_CHIP_ID_7850_: if (!phydev) return ERR_PTR(-ENODEV); /* These use internal GMII-connected PHY */ dev->interface = PHY_INTERFACE_MODE_GMII; phydev->is_internal = true; return phydev; default: netdev_err(dev->net, "Unknown CHIP ID: 0x%08x\n", dev->chipid); return ERR_PTR(-ENODEV); } } /** * lan78xx_mac_prepare_for_phy() - Preconfigure MAC-side interface settings * @dev: LAN78xx device * * Configure MAC-side registers according to dev->interface, which should be * set by lan78xx_get_phy(). * * - For PHY_INTERFACE_MODE_RGMII: * Enable MAC-side TXC delay. This mode seems to be used in a special setup * without a real PHY, likely on EVB-KSZ9897-1. In that design, LAN7801 is * connected to the KSZ9897 switch, and the link timing is expected to be * hardwired (e.g. via strapping or board layout). No devicetree support is * assumed here. * * - For PHY_INTERFACE_MODE_RGMII_ID: * Disable MAC-side delay and rely on the PHY driver to provide delay. * * - For GMII, no MAC-specific config is needed. * * Return: 0 on success or a negative error code. */ static int lan78xx_mac_prepare_for_phy(struct lan78xx_net *dev) { int ret; switch (dev->interface) { case PHY_INTERFACE_MODE_RGMII: /* Enable MAC-side TX clock delay */ ret = lan78xx_write_reg(dev, MAC_RGMII_ID, MAC_RGMII_ID_TXC_DELAY_EN_); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00); if (ret < 0) return ret; ret = lan78xx_update_reg(dev, HW_CFG, HW_CFG_CLK125_EN_ | HW_CFG_REFCLK25_EN_, HW_CFG_CLK125_EN_ | HW_CFG_REFCLK25_EN_); if (ret < 0) return ret; break; case PHY_INTERFACE_MODE_RGMII_ID: /* Disable MAC-side TXC delay, PHY provides it */ ret = lan78xx_write_reg(dev, MAC_RGMII_ID, 0); if (ret < 0) return ret; break; case PHY_INTERFACE_MODE_GMII: /* No MAC-specific configuration required */ break; default: netdev_warn(dev->net, "Unsupported interface mode: %d\n", dev->interface); break; } return 0; } /** * lan78xx_configure_leds_from_dt() - Configure LED enables based on DT * @dev: LAN78xx device * @phydev: PHY device (must be valid) * * Reads "microchip,led-modes" property from the PHY's DT node and enables * the corresponding number of LEDs by writing to HW_CFG. * * This helper preserves the original logic, enabling up to 4 LEDs. * If the property is not present, this function does nothing. * * Return: 0 on success or a negative error code. */ static int lan78xx_configure_leds_from_dt(struct lan78xx_net *dev, struct phy_device *phydev) { struct device_node *np = phydev->mdio.dev.of_node; u32 reg; int len, ret; if (!np) return 0; len = of_property_count_elems_of_size(np, "microchip,led-modes", sizeof(u32)); if (len < 0) return 0; ret = lan78xx_read_reg(dev, HW_CFG, ®); if (ret < 0) return ret; reg &= ~(HW_CFG_LED0_EN_ | HW_CFG_LED1_EN_ | HW_CFG_LED2_EN_ | HW_CFG_LED3_EN_); reg |= (len > 0) * HW_CFG_LED0_EN_ | (len > 1) * HW_CFG_LED1_EN_ | (len > 2) * HW_CFG_LED2_EN_ | (len > 3) * HW_CFG_LED3_EN_; return lan78xx_write_reg(dev, HW_CFG, reg); } static int lan78xx_phylink_setup(struct lan78xx_net *dev) { struct phylink_config *pc = &dev->phylink_config; struct phylink *phylink; pc->dev = &dev->net->dev; pc->type = PHYLINK_NETDEV; pc->mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD; pc->mac_managed_pm = true; pc->lpi_capabilities = MAC_100FD | MAC_1000FD; /* * Default TX LPI (Low Power Idle) request delay count is set to 50us. * * Source: LAN7800 Documentation, DS00001992H, Section 15.1.57, Page 204. * * Reasoning: * According to the application note in the LAN7800 documentation, a * zero delay may negatively impact the TX data path’s ability to * support Gigabit operation. A value of 50us is recommended as a * reasonable default when the part operates at Gigabit speeds, * balancing stability and power efficiency in EEE mode. This delay can * be increased based on performance testing, as EEE is designed for * scenarios with mostly idle links and occasional bursts of full * bandwidth transmission. The goal is to ensure reliable Gigabit * performance without overly aggressive power optimization during * inactive periods. */ pc->lpi_timer_default = 50; pc->eee_enabled_default = true; if (dev->chipid == ID_REV_CHIP_ID_7801_) phy_interface_set_rgmii(pc->supported_interfaces); else __set_bit(PHY_INTERFACE_MODE_GMII, pc->supported_interfaces); memcpy(dev->phylink_config.lpi_interfaces, dev->phylink_config.supported_interfaces, sizeof(dev->phylink_config.lpi_interfaces)); phylink = phylink_create(pc, dev->net->dev.fwnode, dev->interface, &lan78xx_phylink_mac_ops); if (IS_ERR(phylink)) return PTR_ERR(phylink); dev->phylink = phylink; return 0; } static void lan78xx_phy_uninit(struct lan78xx_net *dev) { if (dev->phylink) { phylink_disconnect_phy(dev->phylink); phylink_destroy(dev->phylink); dev->phylink = NULL; } } static int lan78xx_phy_init(struct lan78xx_net *dev) { struct phy_device *phydev; int ret; phydev = lan78xx_get_phy(dev); /* phydev can be NULL if no PHY is found and the chip is LAN7801, * which will use a fixed link later. * If an error occurs, return the error code immediately. */ if (IS_ERR(phydev)) return PTR_ERR(phydev); ret = lan78xx_phylink_setup(dev); if (ret < 0) return ret; ret = lan78xx_mac_prepare_for_phy(dev); if (ret < 0) goto phylink_uninit; /* If no PHY is found, set up a fixed link. It is very specific to * the LAN7801 and is used in special cases like EVB-KSZ9897-1 where * LAN7801 acts as a USB-to-Ethernet interface to a switch without * a visible PHY. */ if (!phydev) { ret = lan78xx_set_fixed_link(dev); if (ret < 0) goto phylink_uninit; /* No PHY found, so set up a fixed link and return early. * No need to configure PHY IRQ or attach to phylink. */ return 0; } /* if phyirq is not set, use polling mode in phylib */ if (dev->domain_data.phyirq > 0) phydev->irq = dev->domain_data.phyirq; else phydev->irq = PHY_POLL; netdev_dbg(dev->net, "phydev->irq = %d\n", phydev->irq); ret = phylink_connect_phy(dev->phylink, phydev); if (ret) { netdev_err(dev->net, "can't attach PHY to %s, error %pe\n", dev->mdiobus->id, ERR_PTR(ret)); goto phylink_uninit; } ret = lan78xx_configure_leds_from_dt(dev, phydev); if (ret < 0) goto phylink_uninit; return 0; phylink_uninit: lan78xx_phy_uninit(dev); return ret; } static int lan78xx_set_rx_max_frame_length(struct lan78xx_net *dev, int size) { bool rxenabled; u32 buf; int ret; ret = lan78xx_read_reg(dev, MAC_RX, &buf); if (ret < 0) return ret; rxenabled = ((buf & MAC_RX_RXEN_) != 0); if (rxenabled) { buf &= ~MAC_RX_RXEN_; ret = lan78xx_write_reg(dev, MAC_RX, buf); if (ret < 0) return ret; } /* add 4 to size for FCS */ buf &= ~MAC_RX_MAX_SIZE_MASK_; buf |= (((size + 4) << MAC_RX_MAX_SIZE_SHIFT_) & MAC_RX_MAX_SIZE_MASK_); ret = lan78xx_write_reg(dev, MAC_RX, buf); if (ret < 0) return ret; if (rxenabled) { buf |= MAC_RX_RXEN_; ret = lan78xx_write_reg(dev, MAC_RX, buf); if (ret < 0) return ret; } return 0; } static int unlink_urbs(struct lan78xx_net *dev, struct sk_buff_head *q) { struct sk_buff *skb; unsigned long flags; int count = 0; spin_lock_irqsave(&q->lock, flags); while (!skb_queue_empty(q)) { struct skb_data *entry; struct urb *urb; int ret; skb_queue_walk(q, skb) { entry = (struct skb_data *)skb->cb; if (entry->state != unlink_start) goto found; } break; found: entry->state = unlink_start; urb = entry->urb; /* Get reference count of the URB to avoid it to be * freed during usb_unlink_urb, which may trigger * use-after-free problem inside usb_unlink_urb since * usb_unlink_urb is always racing with .complete * handler(include defer_bh). */ usb_get_urb(urb); spin_unlock_irqrestore(&q->lock, flags); /* during some PM-driven resume scenarios, * these (async) unlinks complete immediately */ ret = usb_unlink_urb(urb); if (ret != -EINPROGRESS && ret != 0) netdev_dbg(dev->net, "unlink urb err, %d\n", ret); else count++; usb_put_urb(urb); spin_lock_irqsave(&q->lock, flags); } spin_unlock_irqrestore(&q->lock, flags); return count; } static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu) { struct lan78xx_net *dev = netdev_priv(netdev); int max_frame_len = RX_MAX_FRAME_LEN(new_mtu); int ret; /* no second zero-length packet read wanted after mtu-sized packets */ if ((max_frame_len % dev->maxpacket) == 0) return -EDOM; ret = usb_autopm_get_interface(dev->intf); if (ret < 0) return ret; ret = lan78xx_set_rx_max_frame_length(dev, max_frame_len); if (ret < 0) netdev_err(dev->net, "MTU changed to %d from %d failed with %pe\n", new_mtu, netdev->mtu, ERR_PTR(ret)); else WRITE_ONCE(netdev->mtu, new_mtu); usb_autopm_put_interface(dev->intf); return ret; } static int lan78xx_set_mac_addr(struct net_device *netdev, void *p) { struct lan78xx_net *dev = netdev_priv(netdev); struct sockaddr *addr = p; u32 addr_lo, addr_hi; int ret; if (netif_running(netdev)) return -EBUSY; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; eth_hw_addr_set(netdev, addr->sa_data); addr_lo = netdev->dev_addr[0] | netdev->dev_addr[1] << 8 | netdev->dev_addr[2] << 16 | netdev->dev_addr[3] << 24; addr_hi = netdev->dev_addr[4] | netdev->dev_addr[5] << 8; ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); if (ret < 0) return ret; /* Added to support MAC address changes */ ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); if (ret < 0) return ret; return lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); } /* Enable or disable Rx checksum offload engine */ static int lan78xx_set_features(struct net_device *netdev, netdev_features_t features) { struct lan78xx_net *dev = netdev_priv(netdev); struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); unsigned long flags; spin_lock_irqsave(&pdata->rfe_ctl_lock, flags); if (features & NETIF_F_RXCSUM) { pdata->rfe_ctl |= RFE_CTL_TCPUDP_COE_ | RFE_CTL_IP_COE_; pdata->rfe_ctl |= RFE_CTL_ICMP_COE_ | RFE_CTL_IGMP_COE_; } else { pdata->rfe_ctl &= ~(RFE_CTL_TCPUDP_COE_ | RFE_CTL_IP_COE_); pdata->rfe_ctl &= ~(RFE_CTL_ICMP_COE_ | RFE_CTL_IGMP_COE_); } if (features & NETIF_F_HW_VLAN_CTAG_RX) pdata->rfe_ctl |= RFE_CTL_VLAN_STRIP_; else pdata->rfe_ctl &= ~RFE_CTL_VLAN_STRIP_; if (features & NETIF_F_HW_VLAN_CTAG_FILTER) pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_; else pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_; spin_unlock_irqrestore(&pdata->rfe_ctl_lock, flags); return lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); } static void lan78xx_deferred_vlan_write(struct work_struct *param) { struct lan78xx_priv *pdata = container_of(param, struct lan78xx_priv, set_vlan); struct lan78xx_net *dev = pdata->dev; lan78xx_dataport_write(dev, DP_SEL_RSEL_VLAN_DA_, 0, DP_SEL_VHF_VLAN_LEN, pdata->vlan_table); } static int lan78xx_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct lan78xx_net *dev = netdev_priv(netdev); struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); u16 vid_bit_index; u16 vid_dword_index; vid_dword_index = (vid >> 5) & 0x7F; vid_bit_index = vid & 0x1F; pdata->vlan_table[vid_dword_index] |= (1 << vid_bit_index); /* defer register writes to a sleepable context */ schedule_work(&pdata->set_vlan); return 0; } static int lan78xx_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct lan78xx_net *dev = netdev_priv(netdev); struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); u16 vid_bit_index; u16 vid_dword_index; vid_dword_index = (vid >> 5) & 0x7F; vid_bit_index = vid & 0x1F; pdata->vlan_table[vid_dword_index] &= ~(1 << vid_bit_index); /* defer register writes to a sleepable context */ schedule_work(&pdata->set_vlan); return 0; } static int lan78xx_init_ltm(struct lan78xx_net *dev) { u32 regs[6] = { 0 }; int ret; u32 buf; ret = lan78xx_read_reg(dev, USB_CFG1, &buf); if (ret < 0) goto init_ltm_failed; if (buf & USB_CFG1_LTM_ENABLE_) { u8 temp[2]; /* Get values from EEPROM first */ if (lan78xx_read_eeprom(dev, 0x3F, 2, temp) == 0) { if (temp[0] == 24) { ret = lan78xx_read_raw_eeprom(dev, temp[1] * 2, 24, (u8 *)regs); if (ret < 0) return ret; } } else if (lan78xx_read_otp(dev, 0x3F, 2, temp) == 0) { if (temp[0] == 24) { ret = lan78xx_read_raw_otp(dev, temp[1] * 2, 24, (u8 *)regs); if (ret < 0) return ret; } } } ret = lan78xx_write_reg(dev, LTM_BELT_IDLE0, regs[0]); if (ret < 0) goto init_ltm_failed; ret = lan78xx_write_reg(dev, LTM_BELT_IDLE1, regs[1]); if (ret < 0) goto init_ltm_failed; ret = lan78xx_write_reg(dev, LTM_BELT_ACT0, regs[2]); if (ret < 0) goto init_ltm_failed; ret = lan78xx_write_reg(dev, LTM_BELT_ACT1, regs[3]); if (ret < 0) goto init_ltm_failed; ret = lan78xx_write_reg(dev, LTM_INACTIVE0, regs[4]); if (ret < 0) goto init_ltm_failed; ret = lan78xx_write_reg(dev, LTM_INACTIVE1, regs[5]); if (ret < 0) goto init_ltm_failed; return 0; init_ltm_failed: netdev_err(dev->net, "Failed to init LTM with error %pe\n", ERR_PTR(ret)); return ret; } static int lan78xx_urb_config_init(struct lan78xx_net *dev) { int result = 0; switch (dev->udev->speed) { case USB_SPEED_SUPER: dev->rx_urb_size = RX_SS_URB_SIZE; dev->tx_urb_size = TX_SS_URB_SIZE; dev->n_rx_urbs = RX_SS_URB_NUM; dev->n_tx_urbs = TX_SS_URB_NUM; dev->bulk_in_delay = SS_BULK_IN_DELAY; dev->burst_cap = SS_BURST_CAP_SIZE / SS_USB_PKT_SIZE; break; case USB_SPEED_HIGH: dev->rx_urb_size = RX_HS_URB_SIZE; dev->tx_urb_size = TX_HS_URB_SIZE; dev->n_rx_urbs = RX_HS_URB_NUM; dev->n_tx_urbs = TX_HS_URB_NUM; dev->bulk_in_delay = HS_BULK_IN_DELAY; dev->burst_cap = HS_BURST_CAP_SIZE / HS_USB_PKT_SIZE; break; case USB_SPEED_FULL: dev->rx_urb_size = RX_FS_URB_SIZE; dev->tx_urb_size = TX_FS_URB_SIZE; dev->n_rx_urbs = RX_FS_URB_NUM; dev->n_tx_urbs = TX_FS_URB_NUM; dev->bulk_in_delay = FS_BULK_IN_DELAY; dev->burst_cap = FS_BURST_CAP_SIZE / FS_USB_PKT_SIZE; break; default: netdev_warn(dev->net, "USB bus speed not supported\n"); result = -EIO; break; } return result; } static int lan78xx_reset(struct lan78xx_net *dev) { struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); unsigned long timeout; int ret; u32 buf; ret = lan78xx_read_reg(dev, HW_CFG, &buf); if (ret < 0) return ret; buf |= HW_CFG_LRST_; ret = lan78xx_write_reg(dev, HW_CFG, buf); if (ret < 0) return ret; timeout = jiffies + HZ; do { mdelay(1); ret = lan78xx_read_reg(dev, HW_CFG, &buf); if (ret < 0) return ret; if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on completion of LiteReset"); ret = -ETIMEDOUT; return ret; } } while (buf & HW_CFG_LRST_); /* save DEVID for later usage */ ret = lan78xx_read_reg(dev, ID_REV, &buf); if (ret < 0) return ret; dev->chipid = (buf & ID_REV_CHIP_ID_MASK_) >> 16; dev->chiprev = buf & ID_REV_CHIP_REV_MASK_; ret = lan78xx_init_mac_address(dev); if (ret < 0) return ret; /* Respond to the IN token with a NAK */ ret = lan78xx_read_reg(dev, USB_CFG0, &buf); if (ret < 0) return ret; buf |= USB_CFG_BIR_; ret = lan78xx_write_reg(dev, USB_CFG0, buf); if (ret < 0) return ret; /* Init LTM */ ret = lan78xx_init_ltm(dev); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, BURST_CAP, dev->burst_cap); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, BULK_IN_DLY, dev->bulk_in_delay); if (ret < 0) return ret; ret = lan78xx_read_reg(dev, HW_CFG, &buf); if (ret < 0) return ret; buf |= HW_CFG_MEF_; buf |= HW_CFG_CLK125_EN_; buf |= HW_CFG_REFCLK25_EN_; ret = lan78xx_write_reg(dev, HW_CFG, buf); if (ret < 0) return ret; ret = lan78xx_read_reg(dev, USB_CFG0, &buf); if (ret < 0) return ret; buf |= USB_CFG_BCE_; ret = lan78xx_write_reg(dev, USB_CFG0, buf); if (ret < 0) return ret; /* set FIFO sizes */ buf = (MAX_RX_FIFO_SIZE - 512) / 512; ret = lan78xx_write_reg(dev, FCT_RX_FIFO_END, buf); if (ret < 0) return ret; buf = (MAX_TX_FIFO_SIZE - 512) / 512; ret = lan78xx_write_reg(dev, FCT_TX_FIFO_END, buf); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, INT_STS, INT_STS_CLEAR_ALL_); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, FLOW, 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, FCT_FLOW, 0); if (ret < 0) return ret; /* Don't need rfe_ctl_lock during initialisation */ ret = lan78xx_read_reg(dev, RFE_CTL, &pdata->rfe_ctl); if (ret < 0) return ret; pdata->rfe_ctl |= RFE_CTL_BCAST_EN_ | RFE_CTL_DA_PERFECT_; ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); if (ret < 0) return ret; /* Enable or disable checksum offload engines */ ret = lan78xx_set_features(dev->net, dev->net->features); if (ret < 0) return ret; lan78xx_set_multicast(dev->net); /* reset PHY */ ret = lan78xx_read_reg(dev, PMT_CTL, &buf); if (ret < 0) return ret; buf |= PMT_CTL_PHY_RST_; ret = lan78xx_write_reg(dev, PMT_CTL, buf); if (ret < 0) return ret; timeout = jiffies + HZ; do { mdelay(1); ret = lan78xx_read_reg(dev, PMT_CTL, &buf); if (ret < 0) return ret; if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout waiting for PHY Reset"); ret = -ETIMEDOUT; return ret; } } while ((buf & PMT_CTL_PHY_RST_) || !(buf & PMT_CTL_READY_)); ret = lan78xx_read_reg(dev, MAC_CR, &buf); if (ret < 0) return ret; buf &= ~(MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_ | MAC_CR_EEE_EN_); /* LAN7801 only has RGMII mode */ if (dev->chipid == ID_REV_CHIP_ID_7801_) buf &= ~MAC_CR_GMII_EN_; ret = lan78xx_write_reg(dev, MAC_CR, buf); if (ret < 0) return ret; ret = lan78xx_set_rx_max_frame_length(dev, RX_MAX_FRAME_LEN(dev->net->mtu)); return ret; } static void lan78xx_init_stats(struct lan78xx_net *dev) { u32 *p; int i; /* initialize for stats update * some counters are 20bits and some are 32bits */ p = (u32 *)&dev->stats.rollover_max; for (i = 0; i < (sizeof(dev->stats.rollover_max) / (sizeof(u32))); i++) p[i] = 0xFFFFF; dev->stats.rollover_max.rx_unicast_byte_count = 0xFFFFFFFF; dev->stats.rollover_max.rx_broadcast_byte_count = 0xFFFFFFFF; dev->stats.rollover_max.rx_multicast_byte_count = 0xFFFFFFFF; dev->stats.rollover_max.eee_rx_lpi_transitions = 0xFFFFFFFF; dev->stats.rollover_max.eee_rx_lpi_time = 0xFFFFFFFF; dev->stats.rollover_max.tx_unicast_byte_count = 0xFFFFFFFF; dev->stats.rollover_max.tx_broadcast_byte_count = 0xFFFFFFFF; dev->stats.rollover_max.tx_multicast_byte_count = 0xFFFFFFFF; dev->stats.rollover_max.eee_tx_lpi_transitions = 0xFFFFFFFF; dev->stats.rollover_max.eee_tx_lpi_time = 0xFFFFFFFF; set_bit(EVENT_STAT_UPDATE, &dev->flags); } static int lan78xx_open(struct net_device *net) { struct lan78xx_net *dev = netdev_priv(net); int ret; netif_dbg(dev, ifup, dev->net, "open device"); ret = usb_autopm_get_interface(dev->intf); if (ret < 0) return ret; mutex_lock(&dev->dev_mutex); lan78xx_init_stats(dev); napi_enable(&dev->napi); set_bit(EVENT_DEV_OPEN, &dev->flags); /* for Link Check */ if (dev->urb_intr) { ret = usb_submit_urb(dev->urb_intr, GFP_KERNEL); if (ret < 0) { netif_err(dev, ifup, dev->net, "intr submit %d\n", ret); goto done; } } phylink_start(dev->phylink); done: mutex_unlock(&dev->dev_mutex); if (ret < 0) usb_autopm_put_interface(dev->intf); return ret; } static void lan78xx_terminate_urbs(struct lan78xx_net *dev) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(unlink_wakeup); DECLARE_WAITQUEUE(wait, current); int temp; /* ensure there are no more active urbs */ add_wait_queue(&unlink_wakeup, &wait); set_current_state(TASK_UNINTERRUPTIBLE); dev->wait = &unlink_wakeup; temp = unlink_urbs(dev, &dev->txq) + unlink_urbs(dev, &dev->rxq); /* maybe wait for deletions to finish. */ while (!skb_queue_empty(&dev->rxq) || !skb_queue_empty(&dev->txq)) { schedule_timeout(msecs_to_jiffies(UNLINK_TIMEOUT_MS)); set_current_state(TASK_UNINTERRUPTIBLE); netif_dbg(dev, ifdown, dev->net, "waited for %d urb completions", temp); } set_current_state(TASK_RUNNING); dev->wait = NULL; remove_wait_queue(&unlink_wakeup, &wait); /* empty Rx done, Rx overflow and Tx pend queues */ while (!skb_queue_empty(&dev->rxq_done)) { struct sk_buff *skb = skb_dequeue(&dev->rxq_done); lan78xx_release_rx_buf(dev, skb); } skb_queue_purge(&dev->rxq_overflow); skb_queue_purge(&dev->txq_pend); } static int lan78xx_stop(struct net_device *net) { struct lan78xx_net *dev = netdev_priv(net); netif_dbg(dev, ifup, dev->net, "stop device"); mutex_lock(&dev->dev_mutex); if (timer_pending(&dev->stat_monitor)) timer_delete_sync(&dev->stat_monitor); clear_bit(EVENT_DEV_OPEN, &dev->flags); napi_disable(&dev->napi); lan78xx_terminate_urbs(dev); netif_info(dev, ifdown, dev->net, "stop stats: rx/tx %lu/%lu, errs %lu/%lu\n", net->stats.rx_packets, net->stats.tx_packets, net->stats.rx_errors, net->stats.tx_errors); phylink_stop(dev->phylink); usb_kill_urb(dev->urb_intr); /* deferred work (task, timer, softirq) must also stop. * can't flush_scheduled_work() until we drop rtnl (later), * else workers could deadlock; so make workers a NOP. */ clear_bit(EVENT_TX_HALT, &dev->flags); clear_bit(EVENT_RX_HALT, &dev->flags); clear_bit(EVENT_PHY_INT_ACK, &dev->flags); clear_bit(EVENT_STAT_UPDATE, &dev->flags); cancel_delayed_work_sync(&dev->wq); usb_autopm_put_interface(dev->intf); mutex_unlock(&dev->dev_mutex); return 0; } static enum skb_state defer_bh(struct lan78xx_net *dev, struct sk_buff *skb, struct sk_buff_head *list, enum skb_state state) { unsigned long flags; enum skb_state old_state; struct skb_data *entry = (struct skb_data *)skb->cb; spin_lock_irqsave(&list->lock, flags); old_state = entry->state; entry->state = state; __skb_unlink(skb, list); spin_unlock(&list->lock); spin_lock(&dev->rxq_done.lock); __skb_queue_tail(&dev->rxq_done, skb); if (skb_queue_len(&dev->rxq_done) == 1) napi_schedule(&dev->napi); spin_unlock_irqrestore(&dev->rxq_done.lock, flags); return old_state; } static void tx_complete(struct urb *urb) { struct sk_buff *skb = (struct sk_buff *)urb->context; struct skb_data *entry = (struct skb_data *)skb->cb; struct lan78xx_net *dev = entry->dev; if (urb->status == 0) { dev->net->stats.tx_packets += entry->num_of_packet; dev->net->stats.tx_bytes += entry->length; } else { dev->net->stats.tx_errors += entry->num_of_packet; switch (urb->status) { case -EPIPE: lan78xx_defer_kevent(dev, EVENT_TX_HALT); break; /* software-driven interface shutdown */ case -ECONNRESET: case -ESHUTDOWN: netif_dbg(dev, tx_err, dev->net, "tx err interface gone %d\n", entry->urb->status); break; case -EPROTO: case -ETIME: case -EILSEQ: netif_stop_queue(dev->net); netif_dbg(dev, tx_err, dev->net, "tx err queue stopped %d\n", entry->urb->status); break; default: netif_dbg(dev, tx_err, dev->net, "unknown tx err %d\n", entry->urb->status); break; } } usb_autopm_put_interface_async(dev->intf); skb_unlink(skb, &dev->txq); lan78xx_release_tx_buf(dev, skb); /* Re-schedule NAPI if Tx data pending but no URBs in progress. */ if (skb_queue_empty(&dev->txq) && !skb_queue_empty(&dev->txq_pend)) napi_schedule(&dev->napi); } static void lan78xx_queue_skb(struct sk_buff_head *list, struct sk_buff *newsk, enum skb_state state) { struct skb_data *entry = (struct skb_data *)newsk->cb; __skb_queue_tail(list, newsk); entry->state = state; } static unsigned int lan78xx_tx_urb_space(struct lan78xx_net *dev) { return skb_queue_len(&dev->txq_free) * dev->tx_urb_size; } static unsigned int lan78xx_tx_pend_data_len(struct lan78xx_net *dev) { return dev->tx_pend_data_len; } static void lan78xx_tx_pend_skb_add(struct lan78xx_net *dev, struct sk_buff *skb, unsigned int *tx_pend_data_len) { unsigned long flags; spin_lock_irqsave(&dev->txq_pend.lock, flags); __skb_queue_tail(&dev->txq_pend, skb); dev->tx_pend_data_len += skb->len; *tx_pend_data_len = dev->tx_pend_data_len; spin_unlock_irqrestore(&dev->txq_pend.lock, flags); } static void lan78xx_tx_pend_skb_head_add(struct lan78xx_net *dev, struct sk_buff *skb, unsigned int *tx_pend_data_len) { unsigned long flags; spin_lock_irqsave(&dev->txq_pend.lock, flags); __skb_queue_head(&dev->txq_pend, skb); dev->tx_pend_data_len += skb->len; *tx_pend_data_len = dev->tx_pend_data_len; spin_unlock_irqrestore(&dev->txq_pend.lock, flags); } static void lan78xx_tx_pend_skb_get(struct lan78xx_net *dev, struct sk_buff **skb, unsigned int *tx_pend_data_len) { unsigned long flags; spin_lock_irqsave(&dev->txq_pend.lock, flags); *skb = __skb_dequeue(&dev->txq_pend); if (*skb) dev->tx_pend_data_len -= (*skb)->len; *tx_pend_data_len = dev->tx_pend_data_len; spin_unlock_irqrestore(&dev->txq_pend.lock, flags); } static netdev_tx_t lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net) { struct lan78xx_net *dev = netdev_priv(net); unsigned int tx_pend_data_len; if (test_bit(EVENT_DEV_ASLEEP, &dev->flags)) schedule_delayed_work(&dev->wq, 0); skb_tx_timestamp(skb); lan78xx_tx_pend_skb_add(dev, skb, &tx_pend_data_len); /* Set up a Tx URB if none is in progress */ if (skb_queue_empty(&dev->txq)) napi_schedule(&dev->napi); /* Stop stack Tx queue if we have enough data to fill * all the free Tx URBs. */ if (tx_pend_data_len > lan78xx_tx_urb_space(dev)) { netif_stop_queue(net); netif_dbg(dev, hw, dev->net, "tx data len: %u, urb space %u", tx_pend_data_len, lan78xx_tx_urb_space(dev)); /* Kick off transmission of pending data */ if (!skb_queue_empty(&dev->txq_free)) napi_schedule(&dev->napi); } return NETDEV_TX_OK; } static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) { struct lan78xx_priv *pdata = NULL; int ret; int i; dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL); pdata = (struct lan78xx_priv *)(dev->data[0]); if (!pdata) { netdev_warn(dev->net, "Unable to allocate lan78xx_priv"); return -ENOMEM; } pdata->dev = dev; spin_lock_init(&pdata->rfe_ctl_lock); mutex_init(&pdata->dataport_mutex); INIT_WORK(&pdata->set_multicast, lan78xx_deferred_multicast_write); for (i = 0; i < DP_SEL_VHF_VLAN_LEN; i++) pdata->vlan_table[i] = 0; INIT_WORK(&pdata->set_vlan, lan78xx_deferred_vlan_write); dev->net->features = 0; if (DEFAULT_TX_CSUM_ENABLE) dev->net->features |= NETIF_F_HW_CSUM; if (DEFAULT_RX_CSUM_ENABLE) dev->net->features |= NETIF_F_RXCSUM; if (DEFAULT_TSO_CSUM_ENABLE) dev->net->features |= NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_SG; if (DEFAULT_VLAN_RX_OFFLOAD) dev->net->features |= NETIF_F_HW_VLAN_CTAG_RX; if (DEFAULT_VLAN_FILTER_ENABLE) dev->net->features |= NETIF_F_HW_VLAN_CTAG_FILTER; dev->net->hw_features = dev->net->features; ret = lan78xx_setup_irq_domain(dev); if (ret < 0) { netdev_warn(dev->net, "lan78xx_setup_irq_domain() failed : %d", ret); goto out1; } /* Init all registers */ ret = lan78xx_reset(dev); if (ret) { netdev_warn(dev->net, "Registers INIT FAILED...."); goto out2; } ret = lan78xx_mdio_init(dev); if (ret) { netdev_warn(dev->net, "MDIO INIT FAILED....."); goto out2; } dev->net->flags |= IFF_MULTICAST; pdata->wol = WAKE_MAGIC; return ret; out2: lan78xx_remove_irq_domain(dev); out1: netdev_warn(dev->net, "Bind routine FAILED"); cancel_work_sync(&pdata->set_multicast); cancel_work_sync(&pdata->set_vlan); kfree(pdata); return ret; } static void lan78xx_unbind(struct lan78xx_net *dev, struct usb_interface *intf) { struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); lan78xx_remove_irq_domain(dev); lan78xx_remove_mdio(dev); if (pdata) { cancel_work_sync(&pdata->set_multicast); cancel_work_sync(&pdata->set_vlan); netif_dbg(dev, ifdown, dev->net, "free pdata"); kfree(pdata); pdata = NULL; dev->data[0] = 0; } } static void lan78xx_rx_csum_offload(struct lan78xx_net *dev, struct sk_buff *skb, u32 rx_cmd_a, u32 rx_cmd_b) { /* HW Checksum offload appears to be flawed if used when not stripping * VLAN headers. Drop back to S/W checksums under these conditions. */ if (!(dev->net->features & NETIF_F_RXCSUM) || unlikely(rx_cmd_a & RX_CMD_A_ICSM_) || ((rx_cmd_a & RX_CMD_A_FVTG_) && !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) { skb->ip_summed = CHECKSUM_NONE; } else { skb->csum = ntohs((u16)(rx_cmd_b >> RX_CMD_B_CSUM_SHIFT_)); skb->ip_summed = CHECKSUM_COMPLETE; } } static void lan78xx_rx_vlan_offload(struct lan78xx_net *dev, struct sk_buff *skb, u32 rx_cmd_a, u32 rx_cmd_b) { if ((dev->net->features & NETIF_F_HW_VLAN_CTAG_RX) && (rx_cmd_a & RX_CMD_A_FVTG_)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), (rx_cmd_b & 0xffff)); } static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb) { dev->net->stats.rx_packets++; dev->net->stats.rx_bytes += skb->len; skb->protocol = eth_type_trans(skb, dev->net); netif_dbg(dev, rx_status, dev->net, "< rx, len %zu, type 0x%x\n", skb->len + sizeof(struct ethhdr), skb->protocol); memset(skb->cb, 0, sizeof(struct skb_data)); if (skb_defer_rx_timestamp(skb)) return; napi_gro_receive(&dev->napi, skb); } static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb, int budget, int *work_done) { if (skb->len < RX_SKB_MIN_LEN) return 0; /* Extract frames from the URB buffer and pass each one to * the stack in a new NAPI SKB. */ while (skb->len > 0) { u32 rx_cmd_a, rx_cmd_b, align_count, size; u16 rx_cmd_c; unsigned char *packet; rx_cmd_a = get_unaligned_le32(skb->data); skb_pull(skb, sizeof(rx_cmd_a)); rx_cmd_b = get_unaligned_le32(skb->data); skb_pull(skb, sizeof(rx_cmd_b)); rx_cmd_c = get_unaligned_le16(skb->data); skb_pull(skb, sizeof(rx_cmd_c)); packet = skb->data; /* get the packet length */ size = (rx_cmd_a & RX_CMD_A_LEN_MASK_); align_count = (4 - ((size + RXW_PADDING) % 4)) % 4; if (unlikely(size > skb->len)) { netif_dbg(dev, rx_err, dev->net, "size err rx_cmd_a=0x%08x\n", rx_cmd_a); return 0; } if (unlikely(rx_cmd_a & RX_CMD_A_RED_)) { netif_dbg(dev, rx_err, dev->net, "Error rx_cmd_a=0x%08x", rx_cmd_a); } else { u32 frame_len; struct sk_buff *skb2; if (unlikely(size < ETH_FCS_LEN)) { netif_dbg(dev, rx_err, dev->net, "size err rx_cmd_a=0x%08x\n", rx_cmd_a); return 0; } frame_len = size - ETH_FCS_LEN; skb2 = napi_alloc_skb(&dev->napi, frame_len); if (!skb2) return 0; memcpy(skb2->data, packet, frame_len); skb_put(skb2, frame_len); lan78xx_rx_csum_offload(dev, skb2, rx_cmd_a, rx_cmd_b); lan78xx_rx_vlan_offload(dev, skb2, rx_cmd_a, rx_cmd_b); /* Processing of the URB buffer must complete once * it has started. If the NAPI work budget is exhausted * while frames remain they are added to the overflow * queue for delivery in the next NAPI polling cycle. */ if (*work_done < budget) { lan78xx_skb_return(dev, skb2); ++(*work_done); } else { skb_queue_tail(&dev->rxq_overflow, skb2); } } skb_pull(skb, size); /* skip padding bytes before the next frame starts */ if (skb->len) skb_pull(skb, align_count); } return 1; } static inline void rx_process(struct lan78xx_net *dev, struct sk_buff *skb, int budget, int *work_done) { if (!lan78xx_rx(dev, skb, budget, work_done)) { netif_dbg(dev, rx_err, dev->net, "drop\n"); dev->net->stats.rx_errors++; } } static void rx_complete(struct urb *urb) { struct sk_buff *skb = (struct sk_buff *)urb->context; struct skb_data *entry = (struct skb_data *)skb->cb; struct lan78xx_net *dev = entry->dev; int urb_status = urb->status; enum skb_state state; netif_dbg(dev, rx_status, dev->net, "rx done: status %d", urb->status); skb_put(skb, urb->actual_length); state = rx_done; if (urb != entry->urb) netif_warn(dev, rx_err, dev->net, "URB pointer mismatch"); switch (urb_status) { case 0: if (skb->len < RX_SKB_MIN_LEN) { state = rx_cleanup; dev->net->stats.rx_errors++; dev->net->stats.rx_length_errors++; netif_dbg(dev, rx_err, dev->net, "rx length %d\n", skb->len); } usb_mark_last_busy(dev->udev); break; case -EPIPE: dev->net->stats.rx_errors++; lan78xx_defer_kevent(dev, EVENT_RX_HALT); fallthrough; case -ECONNRESET: /* async unlink */ case -ESHUTDOWN: /* hardware gone */ netif_dbg(dev, ifdown, dev->net, "rx shutdown, code %d\n", urb_status); state = rx_cleanup; break; case -EPROTO: case -ETIME: case -EILSEQ: dev->net->stats.rx_errors++; state = rx_cleanup; break; /* data overrun ... flush fifo? */ case -EOVERFLOW: dev->net->stats.rx_over_errors++; fallthrough; default: state = rx_cleanup; dev->net->stats.rx_errors++; netif_dbg(dev, rx_err, dev->net, "rx status %d\n", urb_status); break; } state = defer_bh(dev, skb, &dev->rxq, state); } static int rx_submit(struct lan78xx_net *dev, struct sk_buff *skb, gfp_t flags) { struct skb_data *entry = (struct skb_data *)skb->cb; size_t size = dev->rx_urb_size; struct urb *urb = entry->urb; unsigned long lockflags; int ret = 0; usb_fill_bulk_urb(urb, dev->udev, dev->pipe_in, skb->data, size, rx_complete, skb); spin_lock_irqsave(&dev->rxq.lock, lockflags); if (netif_device_present(dev->net) && netif_running(dev->net) && !test_bit(EVENT_RX_HALT, &dev->flags) && !test_bit(EVENT_DEV_ASLEEP, &dev->flags)) { ret = usb_submit_urb(urb, flags); switch (ret) { case 0: lan78xx_queue_skb(&dev->rxq, skb, rx_start); break; case -EPIPE: lan78xx_defer_kevent(dev, EVENT_RX_HALT); break; case -ENODEV: case -ENOENT: netif_dbg(dev, ifdown, dev->net, "device gone\n"); netif_device_detach(dev->net); break; case -EHOSTUNREACH: ret = -ENOLINK; napi_schedule(&dev->napi); break; default: netif_dbg(dev, rx_err, dev->net, "rx submit, %d\n", ret); napi_schedule(&dev->napi); break; } } else { netif_dbg(dev, ifdown, dev->net, "rx: stopped\n"); ret = -ENOLINK; } spin_unlock_irqrestore(&dev->rxq.lock, lockflags); if (ret) lan78xx_release_rx_buf(dev, skb); return ret; } static void lan78xx_rx_urb_submit_all(struct lan78xx_net *dev) { struct sk_buff *rx_buf; /* Ensure the maximum number of Rx URBs is submitted */ while ((rx_buf = lan78xx_get_rx_buf(dev)) != NULL) { if (rx_submit(dev, rx_buf, GFP_ATOMIC) != 0) break; } } static void lan78xx_rx_urb_resubmit(struct lan78xx_net *dev, struct sk_buff *rx_buf) { /* reset SKB data pointers */ rx_buf->data = rx_buf->head; skb_reset_tail_pointer(rx_buf); rx_buf->len = 0; rx_buf->data_len = 0; rx_submit(dev, rx_buf, GFP_ATOMIC); } static void lan78xx_fill_tx_cmd_words(struct sk_buff *skb, u8 *buffer) { u32 tx_cmd_a; u32 tx_cmd_b; tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN_MASK_) | TX_CMD_A_FCS_; if (skb->ip_summed == CHECKSUM_PARTIAL) tx_cmd_a |= TX_CMD_A_IPE_ | TX_CMD_A_TPE_; tx_cmd_b = 0; if (skb_is_gso(skb)) { u16 mss = max(skb_shinfo(skb)->gso_size, TX_CMD_B_MSS_MIN_); tx_cmd_b = (mss << TX_CMD_B_MSS_SHIFT_) & TX_CMD_B_MSS_MASK_; tx_cmd_a |= TX_CMD_A_LSO_; } if (skb_vlan_tag_present(skb)) { tx_cmd_a |= TX_CMD_A_IVTG_; tx_cmd_b |= skb_vlan_tag_get(skb) & TX_CMD_B_VTAG_MASK_; } put_unaligned_le32(tx_cmd_a, buffer); put_unaligned_le32(tx_cmd_b, buffer + 4); } static struct skb_data *lan78xx_tx_buf_fill(struct lan78xx_net *dev, struct sk_buff *tx_buf) { struct skb_data *entry = (struct skb_data *)tx_buf->cb; int remain = dev->tx_urb_size; u8 *tx_data = tx_buf->data; u32 urb_len = 0; entry->num_of_packet = 0; entry->length = 0; /* Work through the pending SKBs and copy the data of each SKB into * the URB buffer if there room for all the SKB data. * * There must be at least DST+SRC+TYPE in the SKB (with padding enabled) */ while (remain >= TX_SKB_MIN_LEN) { unsigned int pending_bytes; unsigned int align_bytes; struct sk_buff *skb; unsigned int len; lan78xx_tx_pend_skb_get(dev, &skb, &pending_bytes); if (!skb) break; align_bytes = (TX_ALIGNMENT - (urb_len % TX_ALIGNMENT)) % TX_ALIGNMENT; len = align_bytes + TX_CMD_LEN + skb->len; if (len > remain) { lan78xx_tx_pend_skb_head_add(dev, skb, &pending_bytes); break; } tx_data += align_bytes; lan78xx_fill_tx_cmd_words(skb, tx_data); tx_data += TX_CMD_LEN; len = skb->len; if (skb_copy_bits(skb, 0, tx_data, len) < 0) { struct net_device_stats *stats = &dev->net->stats; stats->tx_dropped++; dev_kfree_skb_any(skb); tx_data -= TX_CMD_LEN; continue; } tx_data += len; entry->length += len; entry->num_of_packet += skb_shinfo(skb)->gso_segs ?: 1; dev_kfree_skb_any(skb); urb_len = (u32)(tx_data - (u8 *)tx_buf->data); remain = dev->tx_urb_size - urb_len; } skb_put(tx_buf, urb_len); return entry; } static void lan78xx_tx_bh(struct lan78xx_net *dev) { int ret; /* Start the stack Tx queue if it was stopped */ netif_tx_lock(dev->net); if (netif_queue_stopped(dev->net)) { if (lan78xx_tx_pend_data_len(dev) < lan78xx_tx_urb_space(dev)) netif_wake_queue(dev->net); } netif_tx_unlock(dev->net); /* Go through the Tx pending queue and set up URBs to transfer * the data to the device. Stop if no more pending data or URBs, * or if an error occurs when a URB is submitted. */ do { struct skb_data *entry; struct sk_buff *tx_buf; unsigned long flags; if (skb_queue_empty(&dev->txq_pend)) break; tx_buf = lan78xx_get_tx_buf(dev); if (!tx_buf) break; entry = lan78xx_tx_buf_fill(dev, tx_buf); spin_lock_irqsave(&dev->txq.lock, flags); ret = usb_autopm_get_interface_async(dev->intf); if (ret < 0) { spin_unlock_irqrestore(&dev->txq.lock, flags); goto out; } usb_fill_bulk_urb(entry->urb, dev->udev, dev->pipe_out, tx_buf->data, tx_buf->len, tx_complete, tx_buf); if (tx_buf->len % dev->maxpacket == 0) { /* send USB_ZERO_PACKET */ entry->urb->transfer_flags |= URB_ZERO_PACKET; } #ifdef CONFIG_PM /* if device is asleep stop outgoing packet processing */ if (test_bit(EVENT_DEV_ASLEEP, &dev->flags)) { usb_anchor_urb(entry->urb, &dev->deferred); netif_stop_queue(dev->net); spin_unlock_irqrestore(&dev->txq.lock, flags); netdev_dbg(dev->net, "Delaying transmission for resumption\n"); return; } #endif ret = usb_submit_urb(entry->urb, GFP_ATOMIC); switch (ret) { case 0: netif_trans_update(dev->net); lan78xx_queue_skb(&dev->txq, tx_buf, tx_start); break; case -EPIPE: netif_stop_queue(dev->net); lan78xx_defer_kevent(dev, EVENT_TX_HALT); usb_autopm_put_interface_async(dev->intf); break; case -ENODEV: case -ENOENT: netif_dbg(dev, tx_err, dev->net, "tx submit urb err %d (disconnected?)", ret); netif_device_detach(dev->net); break; default: usb_autopm_put_interface_async(dev->intf); netif_dbg(dev, tx_err, dev->net, "tx submit urb err %d\n", ret); break; } spin_unlock_irqrestore(&dev->txq.lock, flags); if (ret) { netdev_warn(dev->net, "failed to tx urb %d\n", ret); out: dev->net->stats.tx_dropped += entry->num_of_packet; lan78xx_release_tx_buf(dev, tx_buf); } } while (ret == 0); } static int lan78xx_bh(struct lan78xx_net *dev, int budget) { struct sk_buff_head done; struct sk_buff *rx_buf; struct skb_data *entry; unsigned long flags; int work_done = 0; /* Pass frames received in the last NAPI cycle before * working on newly completed URBs. */ while (!skb_queue_empty(&dev->rxq_overflow)) { lan78xx_skb_return(dev, skb_dequeue(&dev->rxq_overflow)); ++work_done; } /* Take a snapshot of the done queue and move items to a * temporary queue. Rx URB completions will continue to add * to the done queue. */ __skb_queue_head_init(&done); spin_lock_irqsave(&dev->rxq_done.lock, flags); skb_queue_splice_init(&dev->rxq_done, &done); spin_unlock_irqrestore(&dev->rxq_done.lock, flags); /* Extract receive frames from completed URBs and * pass them to the stack. Re-submit each completed URB. */ while ((work_done < budget) && (rx_buf = __skb_dequeue(&done))) { entry = (struct skb_data *)(rx_buf->cb); switch (entry->state) { case rx_done: rx_process(dev, rx_buf, budget, &work_done); break; case rx_cleanup: break; default: netdev_dbg(dev->net, "rx buf state %d\n", entry->state); break; } lan78xx_rx_urb_resubmit(dev, rx_buf); } /* If budget was consumed before processing all the URBs put them * back on the front of the done queue. They will be first to be * processed in the next NAPI cycle. */ spin_lock_irqsave(&dev->rxq_done.lock, flags); skb_queue_splice(&done, &dev->rxq_done); spin_unlock_irqrestore(&dev->rxq_done.lock, flags); if (netif_device_present(dev->net) && netif_running(dev->net)) { /* reset update timer delta */ if (timer_pending(&dev->stat_monitor) && (dev->delta != 1)) { dev->delta = 1; mod_timer(&dev->stat_monitor, jiffies + STAT_UPDATE_TIMER); } /* Submit all free Rx URBs */ if (!test_bit(EVENT_RX_HALT, &dev->flags)) lan78xx_rx_urb_submit_all(dev); /* Submit new Tx URBs */ lan78xx_tx_bh(dev); } return work_done; } static int lan78xx_poll(struct napi_struct *napi, int budget) { struct lan78xx_net *dev = container_of(napi, struct lan78xx_net, napi); int result = budget; int work_done; /* Don't do any work if the device is suspended */ if (test_bit(EVENT_DEV_ASLEEP, &dev->flags)) { napi_complete_done(napi, 0); return 0; } /* Process completed URBs and submit new URBs */ work_done = lan78xx_bh(dev, budget); if (work_done < budget) { napi_complete_done(napi, work_done); /* Start a new polling cycle if data was received or * data is waiting to be transmitted. */ if (!skb_queue_empty(&dev->rxq_done)) { napi_schedule(napi); } else if (netif_carrier_ok(dev->net)) { if (skb_queue_empty(&dev->txq) && !skb_queue_empty(&dev->txq_pend)) { napi_schedule(napi); } else { netif_tx_lock(dev->net); if (netif_queue_stopped(dev->net)) { netif_wake_queue(dev->net); napi_schedule(napi); } netif_tx_unlock(dev->net); } } result = work_done; } return result; } static void lan78xx_delayedwork(struct work_struct *work) { int status; struct lan78xx_net *dev; dev = container_of(work, struct lan78xx_net, wq.work); if (test_bit(EVENT_DEV_DISCONNECT, &dev->flags)) return; if (usb_autopm_get_interface(dev->intf) < 0) return; if (test_bit(EVENT_TX_HALT, &dev->flags)) { unlink_urbs(dev, &dev->txq); status = usb_clear_halt(dev->udev, dev->pipe_out); if (status < 0 && status != -EPIPE && status != -ESHUTDOWN) { if (netif_msg_tx_err(dev)) netdev_err(dev->net, "can't clear tx halt, status %d\n", status); } else { clear_bit(EVENT_TX_HALT, &dev->flags); if (status != -ESHUTDOWN) netif_wake_queue(dev->net); } } if (test_bit(EVENT_RX_HALT, &dev->flags)) { unlink_urbs(dev, &dev->rxq); status = usb_clear_halt(dev->udev, dev->pipe_in); if (status < 0 && status != -EPIPE && status != -ESHUTDOWN) { if (netif_msg_rx_err(dev)) netdev_err(dev->net, "can't clear rx halt, status %d\n", status); } else { clear_bit(EVENT_RX_HALT, &dev->flags); napi_schedule(&dev->napi); } } if (test_bit(EVENT_PHY_INT_ACK, &dev->flags)) { int ret = 0; clear_bit(EVENT_PHY_INT_ACK, &dev->flags); ret = lan78xx_phy_int_ack(dev); if (ret) netdev_info(dev->net, "PHY INT ack failed (%pe)\n", ERR_PTR(ret)); } if (test_bit(EVENT_STAT_UPDATE, &dev->flags)) { lan78xx_update_stats(dev); clear_bit(EVENT_STAT_UPDATE, &dev->flags); mod_timer(&dev->stat_monitor, jiffies + (STAT_UPDATE_TIMER * dev->delta)); dev->delta = min((dev->delta * 2), 50); } usb_autopm_put_interface(dev->intf); } static void intr_complete(struct urb *urb) { struct lan78xx_net *dev = urb->context; int status = urb->status; switch (status) { /* success */ case 0: lan78xx_status(dev, urb); break; /* software-driven interface shutdown */ case -ENOENT: /* urb killed */ case -ENODEV: /* hardware gone */ case -ESHUTDOWN: /* hardware gone */ netif_dbg(dev, ifdown, dev->net, "intr shutdown, code %d\n", status); return; /* NOTE: not throttling like RX/TX, since this endpoint * already polls infrequently */ default: netdev_dbg(dev->net, "intr status %d\n", status); break; } if (!netif_device_present(dev->net) || !netif_running(dev->net)) { netdev_warn(dev->net, "not submitting new status URB"); return; } memset(urb->transfer_buffer, 0, urb->transfer_buffer_length); status = usb_submit_urb(urb, GFP_ATOMIC); switch (status) { case 0: break; case -ENODEV: case -ENOENT: netif_dbg(dev, timer, dev->net, "intr resubmit %d (disconnect?)", status); netif_device_detach(dev->net); break; default: netif_err(dev, timer, dev->net, "intr resubmit --> %d\n", status); break; } } static void lan78xx_disconnect(struct usb_interface *intf) { struct lan78xx_net *dev; struct usb_device *udev; struct net_device *net; dev = usb_get_intfdata(intf); usb_set_intfdata(intf, NULL); if (!dev) return; udev = interface_to_usbdev(intf); net = dev->net; rtnl_lock(); phylink_stop(dev->phylink); phylink_disconnect_phy(dev->phylink); rtnl_unlock(); netif_napi_del(&dev->napi); unregister_netdev(net); timer_shutdown_sync(&dev->stat_monitor); set_bit(EVENT_DEV_DISCONNECT, &dev->flags); cancel_delayed_work_sync(&dev->wq); phylink_destroy(dev->phylink); usb_scuttle_anchored_urbs(&dev->deferred); lan78xx_unbind(dev, intf); lan78xx_free_tx_resources(dev); lan78xx_free_rx_resources(dev); usb_kill_urb(dev->urb_intr); usb_free_urb(dev->urb_intr); free_netdev(net); usb_put_dev(udev); } static void lan78xx_tx_timeout(struct net_device *net, unsigned int txqueue) { struct lan78xx_net *dev = netdev_priv(net); unlink_urbs(dev, &dev->txq); napi_schedule(&dev->napi); } static netdev_features_t lan78xx_features_check(struct sk_buff *skb, struct net_device *netdev, netdev_features_t features) { struct lan78xx_net *dev = netdev_priv(netdev); if (skb->len > LAN78XX_TSO_SIZE(dev)) features &= ~NETIF_F_GSO_MASK; features = vlan_features_check(skb, features); features = vxlan_features_check(skb, features); return features; } static const struct net_device_ops lan78xx_netdev_ops = { .ndo_open = lan78xx_open, .ndo_stop = lan78xx_stop, .ndo_start_xmit = lan78xx_start_xmit, .ndo_tx_timeout = lan78xx_tx_timeout, .ndo_change_mtu = lan78xx_change_mtu, .ndo_set_mac_address = lan78xx_set_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_rx_mode = lan78xx_set_multicast, .ndo_set_features = lan78xx_set_features, .ndo_vlan_rx_add_vid = lan78xx_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = lan78xx_vlan_rx_kill_vid, .ndo_features_check = lan78xx_features_check, }; static void lan78xx_stat_monitor(struct timer_list *t) { struct lan78xx_net *dev = timer_container_of(dev, t, stat_monitor); lan78xx_defer_kevent(dev, EVENT_STAT_UPDATE); } static int lan78xx_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_host_endpoint *ep_blkin, *ep_blkout, *ep_intr; struct lan78xx_net *dev; struct net_device *netdev; struct usb_device *udev; int ret; unsigned int maxp; unsigned int period; u8 *buf = NULL; udev = interface_to_usbdev(intf); udev = usb_get_dev(udev); netdev = alloc_etherdev(sizeof(struct lan78xx_net)); if (!netdev) { dev_err(&intf->dev, "Error: OOM\n"); ret = -ENOMEM; goto out1; } SET_NETDEV_DEV(netdev, &intf->dev); dev = netdev_priv(netdev); dev->udev = udev; dev->intf = intf; dev->net = netdev; dev->msg_enable = netif_msg_init(msg_level, NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK); skb_queue_head_init(&dev->rxq); skb_queue_head_init(&dev->txq); skb_queue_head_init(&dev->rxq_done); skb_queue_head_init(&dev->txq_pend); skb_queue_head_init(&dev->rxq_overflow); mutex_init(&dev->mdiobus_mutex); mutex_init(&dev->dev_mutex); ret = lan78xx_urb_config_init(dev); if (ret < 0) goto out2; ret = lan78xx_alloc_tx_resources(dev); if (ret < 0) goto out2; ret = lan78xx_alloc_rx_resources(dev); if (ret < 0) goto out3; /* MTU range: 68 - 9000 */ netdev->max_mtu = MAX_SINGLE_PACKET_SIZE; netif_set_tso_max_size(netdev, LAN78XX_TSO_SIZE(dev)); netif_napi_add(netdev, &dev->napi, lan78xx_poll); INIT_DELAYED_WORK(&dev->wq, lan78xx_delayedwork); init_usb_anchor(&dev->deferred); netdev->netdev_ops = &lan78xx_netdev_ops; netdev->watchdog_timeo = TX_TIMEOUT_JIFFIES; netdev->ethtool_ops = &lan78xx_ethtool_ops; dev->delta = 1; timer_setup(&dev->stat_monitor, lan78xx_stat_monitor, 0); mutex_init(&dev->stats.access_lock); if (intf->cur_altsetting->desc.bNumEndpoints < 3) { ret = -ENODEV; goto out4; } dev->pipe_in = usb_rcvbulkpipe(udev, BULK_IN_PIPE); ep_blkin = usb_pipe_endpoint(udev, dev->pipe_in); if (!ep_blkin || !usb_endpoint_is_bulk_in(&ep_blkin->desc)) { ret = -ENODEV; goto out4; } dev->pipe_out = usb_sndbulkpipe(udev, BULK_OUT_PIPE); ep_blkout = usb_pipe_endpoint(udev, dev->pipe_out); if (!ep_blkout || !usb_endpoint_is_bulk_out(&ep_blkout->desc)) { ret = -ENODEV; goto out4; } ep_intr = &intf->cur_altsetting->endpoint[2]; if (!usb_endpoint_is_int_in(&ep_intr->desc)) { ret = -ENODEV; goto out4; } dev->pipe_intr = usb_rcvintpipe(dev->udev, usb_endpoint_num(&ep_intr->desc)); ret = lan78xx_bind(dev, intf); if (ret < 0) goto out4; period = ep_intr->desc.bInterval; maxp = usb_maxpacket(dev->udev, dev->pipe_intr); dev->urb_intr = usb_alloc_urb(0, GFP_KERNEL); if (!dev->urb_intr) { ret = -ENOMEM; goto out5; } buf = kmalloc(maxp, GFP_KERNEL); if (!buf) { ret = -ENOMEM; goto free_urbs; } usb_fill_int_urb(dev->urb_intr, dev->udev, dev->pipe_intr, buf, maxp, intr_complete, dev, period); dev->urb_intr->transfer_flags |= URB_FREE_BUFFER; dev->maxpacket = usb_maxpacket(dev->udev, dev->pipe_out); /* Reject broken descriptors. */ if (dev->maxpacket == 0) { ret = -ENODEV; goto free_urbs; } /* driver requires remote-wakeup capability during autosuspend. */ intf->needs_remote_wakeup = 1; ret = lan78xx_phy_init(dev); if (ret < 0) goto free_urbs; ret = register_netdev(netdev); if (ret != 0) { netif_err(dev, probe, netdev, "couldn't register the device\n"); goto phy_uninit; } usb_set_intfdata(intf, dev); ret = device_set_wakeup_enable(&udev->dev, true); /* Default delay of 2sec has more overhead than advantage. * Set to 10sec as default. */ pm_runtime_set_autosuspend_delay(&udev->dev, DEFAULT_AUTOSUSPEND_DELAY); return 0; phy_uninit: lan78xx_phy_uninit(dev); free_urbs: usb_free_urb(dev->urb_intr); out5: lan78xx_unbind(dev, intf); out4: netif_napi_del(&dev->napi); lan78xx_free_rx_resources(dev); out3: lan78xx_free_tx_resources(dev); out2: free_netdev(netdev); out1: usb_put_dev(udev); return ret; } static u16 lan78xx_wakeframe_crc16(const u8 *buf, int len) { const u16 crc16poly = 0x8005; int i; u16 bit, crc, msb; u8 data; crc = 0xFFFF; for (i = 0; i < len; i++) { data = *buf++; for (bit = 0; bit < 8; bit++) { msb = crc >> 15; crc <<= 1; if (msb ^ (u16)(data & 1)) { crc ^= crc16poly; crc |= (u16)0x0001U; } data >>= 1; } } return crc; } static int lan78xx_set_auto_suspend(struct lan78xx_net *dev) { u32 buf; int ret; ret = lan78xx_stop_tx_path(dev); if (ret < 0) return ret; ret = lan78xx_stop_rx_path(dev); if (ret < 0) return ret; /* auto suspend (selective suspend) */ ret = lan78xx_write_reg(dev, WUCSR, 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUCSR2, 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); if (ret < 0) return ret; /* set goodframe wakeup */ ret = lan78xx_read_reg(dev, WUCSR, &buf); if (ret < 0) return ret; buf |= WUCSR_RFE_WAKE_EN_; buf |= WUCSR_STORE_WAKE_; ret = lan78xx_write_reg(dev, WUCSR, buf); if (ret < 0) return ret; ret = lan78xx_read_reg(dev, PMT_CTL, &buf); if (ret < 0) return ret; buf &= ~PMT_CTL_RES_CLR_WKP_EN_; buf |= PMT_CTL_RES_CLR_WKP_STS_; buf |= PMT_CTL_PHY_WAKE_EN_; buf |= PMT_CTL_WOL_EN_; buf &= ~PMT_CTL_SUS_MODE_MASK_; buf |= PMT_CTL_SUS_MODE_3_; ret = lan78xx_write_reg(dev, PMT_CTL, buf); if (ret < 0) return ret; ret = lan78xx_read_reg(dev, PMT_CTL, &buf); if (ret < 0) return ret; buf |= PMT_CTL_WUPS_MASK_; ret = lan78xx_write_reg(dev, PMT_CTL, buf); if (ret < 0) return ret; ret = lan78xx_start_rx_path(dev); return ret; } static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) { const u8 ipv4_multicast[3] = { 0x01, 0x00, 0x5E }; const u8 ipv6_multicast[3] = { 0x33, 0x33 }; const u8 arp_type[2] = { 0x08, 0x06 }; u32 temp_pmt_ctl; int mask_index; u32 temp_wucsr; u32 buf; u16 crc; int ret; ret = lan78xx_stop_tx_path(dev); if (ret < 0) return ret; ret = lan78xx_stop_rx_path(dev); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUCSR, 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUCSR2, 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); if (ret < 0) return ret; temp_wucsr = 0; temp_pmt_ctl = 0; ret = lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl); if (ret < 0) return ret; temp_pmt_ctl &= ~PMT_CTL_RES_CLR_WKP_EN_; temp_pmt_ctl |= PMT_CTL_RES_CLR_WKP_STS_; for (mask_index = 0; mask_index < NUM_OF_WUF_CFG; mask_index++) { ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), 0); if (ret < 0) return ret; } mask_index = 0; if (wol & WAKE_PHY) { temp_pmt_ctl |= PMT_CTL_PHY_WAKE_EN_; temp_pmt_ctl |= PMT_CTL_WOL_EN_; temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } if (wol & WAKE_MAGIC) { temp_wucsr |= WUCSR_MPEN_; temp_pmt_ctl |= PMT_CTL_WOL_EN_; temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_3_; } if (wol & WAKE_BCAST) { temp_wucsr |= WUCSR_BCST_EN_; temp_pmt_ctl |= PMT_CTL_WOL_EN_; temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } if (wol & WAKE_MCAST) { temp_wucsr |= WUCSR_WAKE_EN_; /* set WUF_CFG & WUF_MASK for IPv4 Multicast */ crc = lan78xx_wakeframe_crc16(ipv4_multicast, 3); ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_MCAST_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); if (ret < 0) return ret; mask_index++; /* for IPv6 Multicast */ crc = lan78xx_wakeframe_crc16(ipv6_multicast, 2); ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_MCAST_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); if (ret < 0) return ret; mask_index++; temp_pmt_ctl |= PMT_CTL_WOL_EN_; temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } if (wol & WAKE_UCAST) { temp_wucsr |= WUCSR_PFDA_EN_; temp_pmt_ctl |= PMT_CTL_WOL_EN_; temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } if (wol & WAKE_ARP) { temp_wucsr |= WUCSR_WAKE_EN_; /* set WUF_CFG & WUF_MASK * for packettype (offset 12,13) = ARP (0x0806) */ crc = lan78xx_wakeframe_crc16(arp_type, 2); ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_ALL_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); if (ret < 0) return ret; ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); if (ret < 0) return ret; mask_index++; temp_pmt_ctl |= PMT_CTL_WOL_EN_; temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } ret = lan78xx_write_reg(dev, WUCSR, temp_wucsr); if (ret < 0) return ret; /* when multiple WOL bits are set */ if (hweight_long((unsigned long)wol) > 1) { temp_pmt_ctl |= PMT_CTL_WOL_EN_; temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } ret = lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl); if (ret < 0) return ret; /* clear WUPS */ ret = lan78xx_read_reg(dev, PMT_CTL, &buf); if (ret < 0) return ret; buf |= PMT_CTL_WUPS_MASK_; ret = lan78xx_write_reg(dev, PMT_CTL, buf); if (ret < 0) return ret; ret = lan78xx_start_rx_path(dev); return ret; } static int lan78xx_suspend(struct usb_interface *intf, pm_message_t message) { struct lan78xx_net *dev = usb_get_intfdata(intf); bool dev_open; int ret; mutex_lock(&dev->dev_mutex); netif_dbg(dev, ifdown, dev->net, "suspending: pm event %#x", message.event); dev_open = test_bit(EVENT_DEV_OPEN, &dev->flags); if (dev_open) { spin_lock_irq(&dev->txq.lock); /* don't autosuspend while transmitting */ if ((skb_queue_len(&dev->txq) || skb_queue_len(&dev->txq_pend)) && PMSG_IS_AUTO(message)) { spin_unlock_irq(&dev->txq.lock); ret = -EBUSY; goto out; } else { set_bit(EVENT_DEV_ASLEEP, &dev->flags); spin_unlock_irq(&dev->txq.lock); } rtnl_lock(); phylink_suspend(dev->phylink, false); rtnl_unlock(); /* stop RX */ ret = lan78xx_stop_rx_path(dev); if (ret < 0) goto out; ret = lan78xx_flush_rx_fifo(dev); if (ret < 0) goto out; /* stop Tx */ ret = lan78xx_stop_tx_path(dev); if (ret < 0) goto out; /* empty out the Rx and Tx queues */ netif_device_detach(dev->net); lan78xx_terminate_urbs(dev); usb_kill_urb(dev->urb_intr); /* reattach */ netif_device_attach(dev->net); timer_delete(&dev->stat_monitor); if (PMSG_IS_AUTO(message)) { ret = lan78xx_set_auto_suspend(dev); if (ret < 0) goto out; } else { struct lan78xx_priv *pdata; pdata = (struct lan78xx_priv *)(dev->data[0]); netif_carrier_off(dev->net); ret = lan78xx_set_suspend(dev, pdata->wol); if (ret < 0) goto out; } } else { /* Interface is down; don't allow WOL and PHY * events to wake up the host */ u32 buf; set_bit(EVENT_DEV_ASLEEP, &dev->flags); ret = lan78xx_write_reg(dev, WUCSR, 0); if (ret < 0) goto out; ret = lan78xx_write_reg(dev, WUCSR2, 0); if (ret < 0) goto out; ret = lan78xx_read_reg(dev, PMT_CTL, &buf); if (ret < 0) goto out; buf &= ~PMT_CTL_RES_CLR_WKP_EN_; buf |= PMT_CTL_RES_CLR_WKP_STS_; buf &= ~PMT_CTL_SUS_MODE_MASK_; buf |= PMT_CTL_SUS_MODE_3_; ret = lan78xx_write_reg(dev, PMT_CTL, buf); if (ret < 0) goto out; ret = lan78xx_read_reg(dev, PMT_CTL, &buf); if (ret < 0) goto out; buf |= PMT_CTL_WUPS_MASK_; ret = lan78xx_write_reg(dev, PMT_CTL, buf); if (ret < 0) goto out; } ret = 0; out: mutex_unlock(&dev->dev_mutex); return ret; } static bool lan78xx_submit_deferred_urbs(struct lan78xx_net *dev) { bool pipe_halted = false; struct urb *urb; while ((urb = usb_get_from_anchor(&dev->deferred))) { struct sk_buff *skb = urb->context; int ret; if (!netif_device_present(dev->net) || !netif_carrier_ok(dev->net) || pipe_halted) { lan78xx_release_tx_buf(dev, skb); continue; } ret = usb_submit_urb(urb, GFP_ATOMIC); if (ret == 0) { netif_trans_update(dev->net); lan78xx_queue_skb(&dev->txq, skb, tx_start); } else { if (ret == -EPIPE) { netif_stop_queue(dev->net); pipe_halted = true; } else if (ret == -ENODEV) { netif_device_detach(dev->net); } lan78xx_release_tx_buf(dev, skb); } } return pipe_halted; } static int lan78xx_resume(struct usb_interface *intf) { struct lan78xx_net *dev = usb_get_intfdata(intf); bool dev_open; int ret; mutex_lock(&dev->dev_mutex); netif_dbg(dev, ifup, dev->net, "resuming device"); dev_open = test_bit(EVENT_DEV_OPEN, &dev->flags); if (dev_open) { bool pipe_halted = false; ret = lan78xx_flush_tx_fifo(dev); if (ret < 0) goto out; if (dev->urb_intr) { int ret = usb_submit_urb(dev->urb_intr, GFP_KERNEL); if (ret < 0) { if (ret == -ENODEV) netif_device_detach(dev->net); netdev_warn(dev->net, "Failed to submit intr URB"); } } spin_lock_irq(&dev->txq.lock); if (netif_device_present(dev->net)) { pipe_halted = lan78xx_submit_deferred_urbs(dev); if (pipe_halted) lan78xx_defer_kevent(dev, EVENT_TX_HALT); } clear_bit(EVENT_DEV_ASLEEP, &dev->flags); spin_unlock_irq(&dev->txq.lock); if (!pipe_halted && netif_device_present(dev->net) && (lan78xx_tx_pend_data_len(dev) < lan78xx_tx_urb_space(dev))) netif_start_queue(dev->net); ret = lan78xx_start_tx_path(dev); if (ret < 0) goto out; napi_schedule(&dev->napi); if (!timer_pending(&dev->stat_monitor)) { dev->delta = 1; mod_timer(&dev->stat_monitor, jiffies + STAT_UPDATE_TIMER); } } else { clear_bit(EVENT_DEV_ASLEEP, &dev->flags); } ret = lan78xx_write_reg(dev, WUCSR2, 0); if (ret < 0) goto out; ret = lan78xx_write_reg(dev, WUCSR, 0); if (ret < 0) goto out; ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); if (ret < 0) goto out; ret = lan78xx_write_reg(dev, WUCSR2, WUCSR2_NS_RCD_ | WUCSR2_ARP_RCD_ | WUCSR2_IPV6_TCPSYN_RCD_ | WUCSR2_IPV4_TCPSYN_RCD_); if (ret < 0) goto out; ret = lan78xx_write_reg(dev, WUCSR, WUCSR_EEE_TX_WAKE_ | WUCSR_EEE_RX_WAKE_ | WUCSR_PFDA_FR_ | WUCSR_RFE_WAKE_FR_ | WUCSR_WUFR_ | WUCSR_MPR_ | WUCSR_BCST_FR_); if (ret < 0) goto out; ret = 0; out: mutex_unlock(&dev->dev_mutex); return ret; } static int lan78xx_reset_resume(struct usb_interface *intf) { struct lan78xx_net *dev = usb_get_intfdata(intf); int ret; netif_dbg(dev, ifup, dev->net, "(reset) resuming device"); ret = lan78xx_reset(dev); if (ret < 0) return ret; ret = lan78xx_resume(intf); if (ret < 0) return ret; rtnl_lock(); phylink_resume(dev->phylink); rtnl_unlock(); return 0; } static const struct usb_device_id products[] = { { /* LAN7800 USB Gigabit Ethernet Device */ USB_DEVICE(LAN78XX_USB_VENDOR_ID, LAN7800_USB_PRODUCT_ID), }, { /* LAN7850 USB Gigabit Ethernet Device */ USB_DEVICE(LAN78XX_USB_VENDOR_ID, LAN7850_USB_PRODUCT_ID), }, { /* LAN7801 USB Gigabit Ethernet Device */ USB_DEVICE(LAN78XX_USB_VENDOR_ID, LAN7801_USB_PRODUCT_ID), }, { /* ATM2-AF USB Gigabit Ethernet Device */ USB_DEVICE(AT29M2AF_USB_VENDOR_ID, AT29M2AF_USB_PRODUCT_ID), }, {}, }; MODULE_DEVICE_TABLE(usb, products); static struct usb_driver lan78xx_driver = { .name = DRIVER_NAME, .id_table = products, .probe = lan78xx_probe, .disconnect = lan78xx_disconnect, .suspend = lan78xx_suspend, .resume = lan78xx_resume, .reset_resume = lan78xx_reset_resume, .supports_autosuspend = 1, .disable_hub_initiated_lpm = 1, }; module_usb_driver(lan78xx_driver); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); |
| 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 | /* * Copyright (C) 2009 Thomas Gleixner <tglx@linutronix.de> * * For licencing details see kernel-base/COPYING */ #include <linux/dmi.h> #include <linux/init.h> #include <linux/ioport.h> #include <linux/export.h> #include <linux/pci.h> #include <linux/acpi.h> #include <asm/acpi.h> #include <asm/bios_ebda.h> #include <asm/paravirt.h> #include <asm/pci_x86.h> #include <asm/mpspec.h> #include <asm/setup.h> #include <asm/apic.h> #include <asm/e820/api.h> #include <asm/time.h> #include <asm/irq.h> #include <asm/io_apic.h> #include <asm/hpet.h> #include <asm/memtype.h> #include <asm/tsc.h> #include <asm/iommu.h> #include <asm/mach_traps.h> #include <asm/irqdomain.h> #include <asm/realmode.h> void x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } static int __init iommu_init_noop(void) { return 0; } static void iommu_shutdown_noop(void) { } bool __init bool_x86_init_noop(void) { return false; } void x86_op_int_noop(int cpu) { } int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } void get_rtc_noop(struct timespec64 *now) { } static __initconst const struct of_device_id of_cmos_match[] = { { .compatible = "motorola,mc146818" }, {} }; /* * Allow devicetree configured systems to disable the RTC by setting the * corresponding DT node's status property to disabled. Code is optimized * out for CONFIG_OF=n builds. */ static __init void x86_wallclock_init(void) { struct device_node *node = of_find_matching_node(NULL, of_cmos_match); if (node && !of_device_is_available(node)) { x86_platform.get_wallclock = get_rtc_noop; x86_platform.set_wallclock = set_rtc_noop; } } /* * The platform setup functions are preset with the default functions * for standard PC hardware. */ struct x86_init_ops x86_init __initdata = { .resources = { .probe_roms = probe_roms, .reserve_resources = reserve_standard_io_resources, .memory_setup = e820__memory_setup_default, .dmi_setup = dmi_setup, }, .mpparse = { .setup_ioapic_ids = x86_init_noop, .find_mptable = mpparse_find_mptable, .early_parse_smp_cfg = mpparse_parse_early_smp_config, .parse_smp_cfg = mpparse_parse_smp_config, }, .irqs = { .pre_vector_init = init_ISA_irqs, .intr_init = native_init_IRQ, .intr_mode_select = apic_intr_mode_select, .intr_mode_init = apic_intr_mode_init, .create_pci_msi_domain = native_create_pci_msi_domain, }, .oem = { .arch_setup = x86_init_noop, .banner = default_banner, }, .paging = { .pagetable_init = native_pagetable_init, }, .timers = { .setup_percpu_clockev = setup_boot_APIC_clock, .timer_init = hpet_time_init, .wallclock_init = x86_wallclock_init, }, .iommu = { .iommu_init = iommu_init_noop, }, .pci = { .init = x86_default_pci_init, .init_irq = x86_default_pci_init_irq, .fixup_irqs = x86_default_pci_fixup_irqs, }, .hyper = { .init_platform = x86_init_noop, .guest_late_init = x86_init_noop, .x2apic_available = bool_x86_init_noop, .msi_ext_dest_id = bool_x86_init_noop, .init_mem_mapping = x86_init_noop, .init_after_bootmem = x86_init_noop, }, .acpi = { .set_root_pointer = x86_default_set_root_pointer, .get_root_pointer = x86_default_get_root_pointer, .reduced_hw_early_init = acpi_generic_reduced_hw_init, }, }; struct x86_cpuinit_ops x86_cpuinit = { .early_percpu_clock_init = x86_init_noop, .setup_percpu_clockev = setup_secondary_APIC_clock, .parallel_bringup = true, }; static void default_nmi_init(void) { }; static int enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return 0; } static int enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return 0; } static bool enc_tlb_flush_required_noop(bool enc) { return false; } static bool enc_cache_flush_required_noop(void) { return false; } static void enc_kexec_begin_noop(void) {} static void enc_kexec_finish_noop(void) {} static bool is_private_mmio_noop(u64 addr) {return false; } struct x86_platform_ops x86_platform __ro_after_init = { .calibrate_cpu = native_calibrate_cpu_early, .calibrate_tsc = native_calibrate_tsc, .get_wallclock = mach_get_cmos_time, .set_wallclock = mach_set_cmos_time, .iommu_shutdown = iommu_shutdown_noop, .is_untracked_pat_range = is_ISA_range, .nmi_init = default_nmi_init, .get_nmi_reason = default_get_nmi_reason, .save_sched_clock_state = tsc_save_sched_clock_state, .restore_sched_clock_state = tsc_restore_sched_clock_state, .realmode_reserve = reserve_real_mode, .realmode_init = init_real_mode, .hyper.pin_vcpu = x86_op_int_noop, .hyper.is_private_mmio = is_private_mmio_noop, .guest = { .enc_status_change_prepare = enc_status_change_prepare_noop, .enc_status_change_finish = enc_status_change_finish_noop, .enc_tlb_flush_required = enc_tlb_flush_required_noop, .enc_cache_flush_required = enc_cache_flush_required_noop, .enc_kexec_begin = enc_kexec_begin_noop, .enc_kexec_finish = enc_kexec_finish_noop, }, }; EXPORT_SYMBOL_GPL(x86_platform); struct x86_apic_ops x86_apic_ops __ro_after_init = { .io_apic_read = native_io_apic_read, .restore = native_restore_boot_irq_mode, }; |
| 1418 1403 55 1085 1403 23 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Copyright Amazon.com Inc. or its affiliates. */ #include <linux/init.h> #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/rtnetlink.h> #include <net/net_namespace.h> #include <net/netdev_lock.h> #include <net/netns/generic.h> int netdev_debug_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); enum netdev_cmd cmd = event; /* Keep enum and don't add default to trigger -Werror=switch */ switch (cmd) { case NETDEV_XDP_FEAT_CHANGE: netdev_assert_locked(dev); fallthrough; case NETDEV_CHANGE: case NETDEV_REGISTER: case NETDEV_UP: netdev_ops_assert_locked(dev); fallthrough; case NETDEV_DOWN: case NETDEV_REBOOT: case NETDEV_UNREGISTER: case NETDEV_CHANGEMTU: case NETDEV_CHANGEADDR: case NETDEV_PRE_CHANGEADDR: case NETDEV_GOING_DOWN: case NETDEV_FEAT_CHANGE: case NETDEV_BONDING_FAILOVER: case NETDEV_PRE_UP: case NETDEV_PRE_TYPE_CHANGE: case NETDEV_POST_TYPE_CHANGE: case NETDEV_POST_INIT: case NETDEV_PRE_UNINIT: case NETDEV_RELEASE: case NETDEV_NOTIFY_PEERS: case NETDEV_JOIN: case NETDEV_CHANGEUPPER: case NETDEV_RESEND_IGMP: case NETDEV_PRECHANGEMTU: case NETDEV_CHANGEINFODATA: case NETDEV_BONDING_INFO: case NETDEV_PRECHANGEUPPER: case NETDEV_CHANGELOWERSTATE: case NETDEV_UDP_TUNNEL_PUSH_INFO: case NETDEV_UDP_TUNNEL_DROP_INFO: case NETDEV_CHANGE_TX_QUEUE_LEN: case NETDEV_CVLAN_FILTER_PUSH_INFO: case NETDEV_CVLAN_FILTER_DROP_INFO: case NETDEV_SVLAN_FILTER_PUSH_INFO: case NETDEV_SVLAN_FILTER_DROP_INFO: case NETDEV_OFFLOAD_XSTATS_ENABLE: case NETDEV_OFFLOAD_XSTATS_DISABLE: case NETDEV_OFFLOAD_XSTATS_REPORT_USED: case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA: ASSERT_RTNL(); break; case NETDEV_CHANGENAME: ASSERT_RTNL_NET(net); break; } return NOTIFY_DONE; } EXPORT_SYMBOL_NS_GPL(netdev_debug_event, "NETDEV_INTERNAL"); static int rtnl_net_debug_net_id; static int __net_init rtnl_net_debug_net_init(struct net *net) { struct notifier_block *nb; nb = net_generic(net, rtnl_net_debug_net_id); nb->notifier_call = netdev_debug_event; return register_netdevice_notifier_net(net, nb); } static void __net_exit rtnl_net_debug_net_exit(struct net *net) { struct notifier_block *nb; nb = net_generic(net, rtnl_net_debug_net_id); unregister_netdevice_notifier_net(net, nb); } static struct pernet_operations rtnl_net_debug_net_ops __net_initdata = { .init = rtnl_net_debug_net_init, .exit = rtnl_net_debug_net_exit, .id = &rtnl_net_debug_net_id, .size = sizeof(struct notifier_block), }; static struct notifier_block rtnl_net_debug_block = { .notifier_call = netdev_debug_event, }; static int __init rtnl_net_debug_init(void) { int ret; ret = register_pernet_subsys(&rtnl_net_debug_net_ops); if (ret) return ret; ret = register_netdevice_notifier(&rtnl_net_debug_block); if (ret) unregister_pernet_subsys(&rtnl_net_debug_net_ops); return ret; } subsys_initcall(rtnl_net_debug_init); |
| 296 296 248 49 55 11 45 45 30 27 70 101 1 5 94 7 7 88 108 108 192 191 54 8 54 54 8 8 5 66 65 3 61 9 61 9 66 3 62 9 4 38 6 6 22 2 2 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Symmetric key cipher operations. * * Generic encrypt/decrypt wrapper for ciphers, handles operations across * multiple page boundaries by using temporary blocks. In user context, * the kernel is given a chance to schedule us once per page. * * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/internal/aead.h> #include <crypto/internal/cipher.h> #include <crypto/internal/skcipher.h> #include <crypto/scatterwalk.h> #include <linux/bug.h> #include <linux/cryptouser.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/string_choices.h> #include <net/netlink.h> #include "skcipher.h" #define CRYPTO_ALG_TYPE_SKCIPHER_MASK 0x0000000e static const struct crypto_type crypto_skcipher_type; static inline struct skcipher_alg *__crypto_skcipher_alg( struct crypto_alg *alg) { return container_of(alg, struct skcipher_alg, base); } int skcipher_walk_virt(struct skcipher_walk *__restrict walk, struct skcipher_request *__restrict req, bool atomic) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct skcipher_alg *alg; might_sleep_if(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP); alg = crypto_skcipher_alg(tfm); walk->total = req->cryptlen; walk->nbytes = 0; walk->iv = req->iv; walk->oiv = req->iv; if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP)) atomic = true; if (unlikely(!walk->total)) return 0; scatterwalk_start(&walk->in, req->src); scatterwalk_start(&walk->out, req->dst); walk->blocksize = crypto_skcipher_blocksize(tfm); walk->ivsize = crypto_skcipher_ivsize(tfm); walk->alignmask = crypto_skcipher_alignmask(tfm); if (alg->co.base.cra_type != &crypto_skcipher_type) walk->stride = alg->co.chunksize; else walk->stride = alg->walksize; return skcipher_walk_first(walk, atomic); } EXPORT_SYMBOL_GPL(skcipher_walk_virt); static int skcipher_walk_aead_common(struct skcipher_walk *__restrict walk, struct aead_request *__restrict req, bool atomic) { struct crypto_aead *tfm = crypto_aead_reqtfm(req); walk->nbytes = 0; walk->iv = req->iv; walk->oiv = req->iv; if (!(req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP)) atomic = true; if (unlikely(!walk->total)) return 0; scatterwalk_start_at_pos(&walk->in, req->src, req->assoclen); scatterwalk_start_at_pos(&walk->out, req->dst, req->assoclen); walk->blocksize = crypto_aead_blocksize(tfm); walk->stride = crypto_aead_chunksize(tfm); walk->ivsize = crypto_aead_ivsize(tfm); walk->alignmask = crypto_aead_alignmask(tfm); return skcipher_walk_first(walk, atomic); } int skcipher_walk_aead_encrypt(struct skcipher_walk *__restrict walk, struct aead_request *__restrict req, bool atomic) { walk->total = req->cryptlen; return skcipher_walk_aead_common(walk, req, atomic); } EXPORT_SYMBOL_GPL(skcipher_walk_aead_encrypt); int skcipher_walk_aead_decrypt(struct skcipher_walk *__restrict walk, struct aead_request *__restrict req, bool atomic) { struct crypto_aead *tfm = crypto_aead_reqtfm(req); walk->total = req->cryptlen - crypto_aead_authsize(tfm); return skcipher_walk_aead_common(walk, req, atomic); } EXPORT_SYMBOL_GPL(skcipher_walk_aead_decrypt); static void skcipher_set_needkey(struct crypto_skcipher *tfm) { if (crypto_skcipher_max_keysize(tfm) != 0) crypto_skcipher_set_flags(tfm, CRYPTO_TFM_NEED_KEY); } static int skcipher_setkey_unaligned(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { unsigned long alignmask = crypto_skcipher_alignmask(tfm); struct skcipher_alg *cipher = crypto_skcipher_alg(tfm); u8 *buffer, *alignbuffer; unsigned long absize; int ret; absize = keylen + alignmask; buffer = kmalloc(absize, GFP_ATOMIC); if (!buffer) return -ENOMEM; alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1); memcpy(alignbuffer, key, keylen); ret = cipher->setkey(tfm, alignbuffer, keylen); kfree_sensitive(buffer); return ret; } int crypto_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { struct skcipher_alg *cipher = crypto_skcipher_alg(tfm); unsigned long alignmask = crypto_skcipher_alignmask(tfm); int err; if (cipher->co.base.cra_type != &crypto_skcipher_type) { struct crypto_lskcipher **ctx = crypto_skcipher_ctx(tfm); crypto_lskcipher_clear_flags(*ctx, CRYPTO_TFM_REQ_MASK); crypto_lskcipher_set_flags(*ctx, crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_REQ_MASK); err = crypto_lskcipher_setkey(*ctx, key, keylen); goto out; } if (keylen < cipher->min_keysize || keylen > cipher->max_keysize) return -EINVAL; if ((unsigned long)key & alignmask) err = skcipher_setkey_unaligned(tfm, key, keylen); else err = cipher->setkey(tfm, key, keylen); out: if (unlikely(err)) { skcipher_set_needkey(tfm); return err; } crypto_skcipher_clear_flags(tfm, CRYPTO_TFM_NEED_KEY); return 0; } EXPORT_SYMBOL_GPL(crypto_skcipher_setkey); int crypto_skcipher_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct skcipher_alg *alg = crypto_skcipher_alg(tfm); if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; if (alg->co.base.cra_type != &crypto_skcipher_type) return crypto_lskcipher_encrypt_sg(req); return alg->encrypt(req); } EXPORT_SYMBOL_GPL(crypto_skcipher_encrypt); int crypto_skcipher_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct skcipher_alg *alg = crypto_skcipher_alg(tfm); if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; if (alg->co.base.cra_type != &crypto_skcipher_type) return crypto_lskcipher_decrypt_sg(req); return alg->decrypt(req); } EXPORT_SYMBOL_GPL(crypto_skcipher_decrypt); static int crypto_lskcipher_export(struct skcipher_request *req, void *out) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); u8 *ivs = skcipher_request_ctx(req); ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(tfm) + 1); memcpy(out, ivs + crypto_skcipher_ivsize(tfm), crypto_skcipher_statesize(tfm)); return 0; } static int crypto_lskcipher_import(struct skcipher_request *req, const void *in) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); u8 *ivs = skcipher_request_ctx(req); ivs = PTR_ALIGN(ivs, crypto_skcipher_alignmask(tfm) + 1); memcpy(ivs + crypto_skcipher_ivsize(tfm), in, crypto_skcipher_statesize(tfm)); return 0; } static int skcipher_noexport(struct skcipher_request *req, void *out) { return 0; } static int skcipher_noimport(struct skcipher_request *req, const void *in) { return 0; } int crypto_skcipher_export(struct skcipher_request *req, void *out) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct skcipher_alg *alg = crypto_skcipher_alg(tfm); if (alg->co.base.cra_type != &crypto_skcipher_type) return crypto_lskcipher_export(req, out); return alg->export(req, out); } EXPORT_SYMBOL_GPL(crypto_skcipher_export); int crypto_skcipher_import(struct skcipher_request *req, const void *in) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct skcipher_alg *alg = crypto_skcipher_alg(tfm); if (alg->co.base.cra_type != &crypto_skcipher_type) return crypto_lskcipher_import(req, in); return alg->import(req, in); } EXPORT_SYMBOL_GPL(crypto_skcipher_import); static void crypto_skcipher_exit_tfm(struct crypto_tfm *tfm) { struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm); struct skcipher_alg *alg = crypto_skcipher_alg(skcipher); alg->exit(skcipher); } static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm) { struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm); struct skcipher_alg *alg = crypto_skcipher_alg(skcipher); skcipher_set_needkey(skcipher); if (tfm->__crt_alg->cra_type != &crypto_skcipher_type) { unsigned am = crypto_skcipher_alignmask(skcipher); unsigned reqsize; reqsize = am & ~(crypto_tfm_ctx_alignment() - 1); reqsize += crypto_skcipher_ivsize(skcipher); reqsize += crypto_skcipher_statesize(skcipher); crypto_skcipher_set_reqsize(skcipher, reqsize); return crypto_init_lskcipher_ops_sg(tfm); } crypto_skcipher_set_reqsize(skcipher, crypto_tfm_alg_reqsize(tfm)); if (alg->exit) skcipher->base.exit = crypto_skcipher_exit_tfm; if (alg->init) return alg->init(skcipher); return 0; } static unsigned int crypto_skcipher_extsize(struct crypto_alg *alg) { if (alg->cra_type != &crypto_skcipher_type) return sizeof(struct crypto_lskcipher *); return crypto_alg_extsize(alg); } static void crypto_skcipher_free_instance(struct crypto_instance *inst) { struct skcipher_instance *skcipher = container_of(inst, struct skcipher_instance, s.base); skcipher->free(skcipher); } static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg) __maybe_unused; static void crypto_skcipher_show(struct seq_file *m, struct crypto_alg *alg) { struct skcipher_alg *skcipher = __crypto_skcipher_alg(alg); seq_printf(m, "type : skcipher\n"); seq_printf(m, "async : %s\n", str_yes_no(alg->cra_flags & CRYPTO_ALG_ASYNC)); seq_printf(m, "blocksize : %u\n", alg->cra_blocksize); seq_printf(m, "min keysize : %u\n", skcipher->min_keysize); seq_printf(m, "max keysize : %u\n", skcipher->max_keysize); seq_printf(m, "ivsize : %u\n", skcipher->ivsize); seq_printf(m, "chunksize : %u\n", skcipher->chunksize); seq_printf(m, "walksize : %u\n", skcipher->walksize); seq_printf(m, "statesize : %u\n", skcipher->statesize); } static int __maybe_unused crypto_skcipher_report( struct sk_buff *skb, struct crypto_alg *alg) { struct skcipher_alg *skcipher = __crypto_skcipher_alg(alg); struct crypto_report_blkcipher rblkcipher; memset(&rblkcipher, 0, sizeof(rblkcipher)); strscpy(rblkcipher.type, "skcipher", sizeof(rblkcipher.type)); strscpy(rblkcipher.geniv, "<none>", sizeof(rblkcipher.geniv)); rblkcipher.blocksize = alg->cra_blocksize; rblkcipher.min_keysize = skcipher->min_keysize; rblkcipher.max_keysize = skcipher->max_keysize; rblkcipher.ivsize = skcipher->ivsize; return nla_put(skb, CRYPTOCFGA_REPORT_BLKCIPHER, sizeof(rblkcipher), &rblkcipher); } static const struct crypto_type crypto_skcipher_type = { .extsize = crypto_skcipher_extsize, .init_tfm = crypto_skcipher_init_tfm, .free = crypto_skcipher_free_instance, #ifdef CONFIG_PROC_FS .show = crypto_skcipher_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_skcipher_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_SKCIPHER_MASK, .type = CRYPTO_ALG_TYPE_SKCIPHER, .tfmsize = offsetof(struct crypto_skcipher, base), .algsize = offsetof(struct skcipher_alg, base), }; int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { spawn->base.frontend = &crypto_skcipher_type; return crypto_grab_spawn(&spawn->base, inst, name, type, mask); } EXPORT_SYMBOL_GPL(crypto_grab_skcipher); struct crypto_skcipher *crypto_alloc_skcipher(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_skcipher_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_skcipher); struct crypto_sync_skcipher *crypto_alloc_sync_skcipher( const char *alg_name, u32 type, u32 mask) { struct crypto_skcipher *tfm; /* Only sync algorithms allowed. */ mask |= CRYPTO_ALG_ASYNC | CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE; type &= ~(CRYPTO_ALG_ASYNC | CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE); tfm = crypto_alloc_tfm(alg_name, &crypto_skcipher_type, type, mask); /* * Make sure we do not allocate something that might get used with * an on-stack request: check the request size. */ if (!IS_ERR(tfm) && WARN_ON(crypto_skcipher_reqsize(tfm) > MAX_SYNC_SKCIPHER_REQSIZE)) { crypto_free_skcipher(tfm); return ERR_PTR(-EINVAL); } return (struct crypto_sync_skcipher *)tfm; } EXPORT_SYMBOL_GPL(crypto_alloc_sync_skcipher); int crypto_has_skcipher(const char *alg_name, u32 type, u32 mask) { return crypto_type_has_alg(alg_name, &crypto_skcipher_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_has_skcipher); int skcipher_prepare_alg_common(struct skcipher_alg_common *alg) { struct crypto_alg *base = &alg->base; if (alg->ivsize > PAGE_SIZE / 8 || alg->chunksize > PAGE_SIZE / 8 || alg->statesize > PAGE_SIZE / 2 || (alg->ivsize + alg->statesize) > PAGE_SIZE / 2) return -EINVAL; if (!alg->chunksize) alg->chunksize = base->cra_blocksize; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; return 0; } static int skcipher_prepare_alg(struct skcipher_alg *alg) { struct crypto_alg *base = &alg->base; int err; err = skcipher_prepare_alg_common(&alg->co); if (err) return err; if (alg->walksize > PAGE_SIZE / 8) return -EINVAL; if (!alg->walksize) alg->walksize = alg->chunksize; if (!alg->statesize) { alg->import = skcipher_noimport; alg->export = skcipher_noexport; } else if (!(alg->import && alg->export)) return -EINVAL; base->cra_type = &crypto_skcipher_type; base->cra_flags |= CRYPTO_ALG_TYPE_SKCIPHER; return 0; } int crypto_register_skcipher(struct skcipher_alg *alg) { struct crypto_alg *base = &alg->base; int err; err = skcipher_prepare_alg(alg); if (err) return err; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_skcipher); void crypto_unregister_skcipher(struct skcipher_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_skcipher); int crypto_register_skciphers(struct skcipher_alg *algs, int count) { int i, ret; for (i = 0; i < count; i++) { ret = crypto_register_skcipher(&algs[i]); if (ret) goto err; } return 0; err: for (--i; i >= 0; --i) crypto_unregister_skcipher(&algs[i]); return ret; } EXPORT_SYMBOL_GPL(crypto_register_skciphers); void crypto_unregister_skciphers(struct skcipher_alg *algs, int count) { int i; for (i = count - 1; i >= 0; --i) crypto_unregister_skcipher(&algs[i]); } EXPORT_SYMBOL_GPL(crypto_unregister_skciphers); int skcipher_register_instance(struct crypto_template *tmpl, struct skcipher_instance *inst) { int err; if (WARN_ON(!inst->free)) return -EINVAL; err = skcipher_prepare_alg(&inst->alg); if (err) return err; return crypto_register_instance(tmpl, skcipher_crypto_instance(inst)); } EXPORT_SYMBOL_GPL(skcipher_register_instance); static int skcipher_setkey_simple(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { struct crypto_cipher *cipher = skcipher_cipher_simple(tfm); crypto_cipher_clear_flags(cipher, CRYPTO_TFM_REQ_MASK); crypto_cipher_set_flags(cipher, crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_REQ_MASK); return crypto_cipher_setkey(cipher, key, keylen); } static int skcipher_init_tfm_simple(struct crypto_skcipher *tfm) { struct skcipher_instance *inst = skcipher_alg_instance(tfm); struct crypto_cipher_spawn *spawn = skcipher_instance_ctx(inst); struct skcipher_ctx_simple *ctx = crypto_skcipher_ctx(tfm); struct crypto_cipher *cipher; cipher = crypto_spawn_cipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->cipher = cipher; return 0; } static void skcipher_exit_tfm_simple(struct crypto_skcipher *tfm) { struct skcipher_ctx_simple *ctx = crypto_skcipher_ctx(tfm); crypto_free_cipher(ctx->cipher); } static void skcipher_free_instance_simple(struct skcipher_instance *inst) { crypto_drop_cipher(skcipher_instance_ctx(inst)); kfree(inst); } /** * skcipher_alloc_instance_simple - allocate instance of simple block cipher mode * * Allocate an skcipher_instance for a simple block cipher mode of operation, * e.g. cbc or ecb. The instance context will have just a single crypto_spawn, * that for the underlying cipher. The {min,max}_keysize, ivsize, blocksize, * alignmask, and priority are set from the underlying cipher but can be * overridden if needed. The tfm context defaults to skcipher_ctx_simple, and * default ->setkey(), ->init(), and ->exit() methods are installed. * * @tmpl: the template being instantiated * @tb: the template parameters * * Return: a pointer to the new instance, or an ERR_PTR(). The caller still * needs to register the instance. */ struct skcipher_instance *skcipher_alloc_instance_simple( struct crypto_template *tmpl, struct rtattr **tb) { u32 mask; struct skcipher_instance *inst; struct crypto_cipher_spawn *spawn; struct crypto_alg *cipher_alg; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SKCIPHER, &mask); if (err) return ERR_PTR(err); inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return ERR_PTR(-ENOMEM); spawn = skcipher_instance_ctx(inst); err = crypto_grab_cipher(spawn, skcipher_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; cipher_alg = crypto_spawn_cipher_alg(spawn); err = crypto_inst_setname(skcipher_crypto_instance(inst), tmpl->name, cipher_alg); if (err) goto err_free_inst; inst->free = skcipher_free_instance_simple; /* Default algorithm properties, can be overridden */ inst->alg.base.cra_blocksize = cipher_alg->cra_blocksize; inst->alg.base.cra_alignmask = cipher_alg->cra_alignmask; inst->alg.base.cra_priority = cipher_alg->cra_priority; inst->alg.min_keysize = cipher_alg->cra_cipher.cia_min_keysize; inst->alg.max_keysize = cipher_alg->cra_cipher.cia_max_keysize; inst->alg.ivsize = cipher_alg->cra_blocksize; /* Use skcipher_ctx_simple by default, can be overridden */ inst->alg.base.cra_ctxsize = sizeof(struct skcipher_ctx_simple); inst->alg.setkey = skcipher_setkey_simple; inst->alg.init = skcipher_init_tfm_simple; inst->alg.exit = skcipher_exit_tfm_simple; return inst; err_free_inst: skcipher_free_instance_simple(inst); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(skcipher_alloc_instance_simple); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Symmetric key cipher type"); MODULE_IMPORT_NS("CRYPTO_INTERNAL"); |
| 844 2 842 844 13 837 825 648 748 133 18 18 3 831 837 831 649 2 23 114 1 2 2 2 112 4 139 140 4 4 4 3 3 3 65 1 64 36 58 340 10 346 18 1 14 12 3 103 1 102 104 104 99 99 99 93 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Filesystem parameter parser. * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/namei.h> #include "internal.h" const struct constant_table bool_names[] = { { "0", false }, { "1", true }, { "false", false }, { "no", false }, { "true", true }, { "yes", true }, { }, }; EXPORT_SYMBOL(bool_names); static const struct constant_table * __lookup_constant(const struct constant_table *tbl, const char *name) { for ( ; tbl->name; tbl++) if (strcmp(name, tbl->name) == 0) return tbl; return NULL; } /** * lookup_constant - Look up a constant by name in an ordered table * @tbl: The table of constants to search. * @name: The name to look up. * @not_found: The value to return if the name is not found. */ int lookup_constant(const struct constant_table *tbl, const char *name, int not_found) { const struct constant_table *p = __lookup_constant(tbl, name); return p ? p->value : not_found; } EXPORT_SYMBOL(lookup_constant); static inline bool is_flag(const struct fs_parameter_spec *p) { return p->type == NULL; } static const struct fs_parameter_spec *fs_lookup_key( const struct fs_parameter_spec *desc, struct fs_parameter *param, bool *negated) { const struct fs_parameter_spec *p, *other = NULL; const char *name = param->key; bool want_flag = param->type == fs_value_is_flag; *negated = false; for (p = desc; p->name; p++) { if (strcmp(p->name, name) != 0) continue; if (likely(is_flag(p) == want_flag)) return p; other = p; } if (want_flag) { if (name[0] == 'n' && name[1] == 'o' && name[2]) { for (p = desc; p->name; p++) { if (strcmp(p->name, name + 2) != 0) continue; if (!(p->flags & fs_param_neg_with_no)) continue; *negated = true; return p; } } } return other; } /* * __fs_parse - Parse a filesystem configuration parameter * @log: The filesystem context to log errors through. * @desc: The parameter description to use. * @param: The parameter. * @result: Where to place the result of the parse * * Parse a filesystem configuration parameter and attempt a conversion for a * simple parameter for which this is requested. If successful, the determined * parameter ID is placed into @result->key, the desired type is indicated in * @result->t and any converted value is placed into an appropriate member of * the union in @result. * * The function returns the parameter number if the parameter was matched, * -ENOPARAM if it wasn't matched and @desc->ignore_unknown indicated that * unknown parameters are okay and -EINVAL if there was a conversion issue or * the parameter wasn't recognised and unknowns aren't okay. */ int __fs_parse(struct p_log *log, const struct fs_parameter_spec *desc, struct fs_parameter *param, struct fs_parse_result *result) { const struct fs_parameter_spec *p; result->uint_64 = 0; p = fs_lookup_key(desc, param, &result->negated); if (!p) return -ENOPARAM; if (p->flags & fs_param_deprecated) warn_plog(log, "Deprecated parameter '%s'", param->key); /* Try to turn the type we were given into the type desired by the * parameter and give an error if we can't. */ if (is_flag(p)) { if (param->type != fs_value_is_flag) return inval_plog(log, "Unexpected value for '%s'", param->key); result->boolean = !result->negated; } else { int ret = p->type(log, p, param, result); if (ret) return ret; } return p->opt; } EXPORT_SYMBOL(__fs_parse); /** * fs_lookup_param - Look up a path referred to by a parameter * @fc: The filesystem context to log errors through. * @param: The parameter. * @want_bdev: T if want a blockdev * @flags: Pathwalk flags passed to filename_lookup() * @_path: The result of the lookup */ int fs_lookup_param(struct fs_context *fc, struct fs_parameter *param, bool want_bdev, unsigned int flags, struct path *_path) { struct filename *f; bool put_f; int ret; switch (param->type) { case fs_value_is_string: f = getname_kernel(param->string); if (IS_ERR(f)) return PTR_ERR(f); param->dirfd = AT_FDCWD; put_f = true; break; case fs_value_is_filename: f = param->name; put_f = false; break; default: return invalf(fc, "%s: not usable as path", param->key); } ret = filename_lookup(param->dirfd, f, flags, _path, NULL); if (ret < 0) { errorf(fc, "%s: Lookup failure for '%s'", param->key, f->name); goto out; } if (want_bdev && !S_ISBLK(d_backing_inode(_path->dentry)->i_mode)) { path_put(_path); _path->dentry = NULL; _path->mnt = NULL; errorf(fc, "%s: Non-blockdev passed as '%s'", param->key, f->name); ret = -ENOTBLK; } out: if (put_f) putname(f); return ret; } EXPORT_SYMBOL(fs_lookup_param); static int fs_param_bad_value(struct p_log *log, struct fs_parameter *param) { return inval_plog(log, "Bad value for '%s'", param->key); } int fs_param_is_bool(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { int b; if (param->type != fs_value_is_string) return fs_param_bad_value(log, param); if (!*param->string && (p->flags & fs_param_can_be_empty)) return 0; b = lookup_constant(bool_names, param->string, -1); if (b == -1) return fs_param_bad_value(log, param); result->boolean = b; return 0; } EXPORT_SYMBOL(fs_param_is_bool); int fs_param_is_u32(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { int base = (unsigned long)p->data; if (param->type != fs_value_is_string) return fs_param_bad_value(log, param); if (!*param->string && (p->flags & fs_param_can_be_empty)) return 0; if (kstrtouint(param->string, base, &result->uint_32) < 0) return fs_param_bad_value(log, param); return 0; } EXPORT_SYMBOL(fs_param_is_u32); int fs_param_is_s32(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { if (param->type != fs_value_is_string) return fs_param_bad_value(log, param); if (!*param->string && (p->flags & fs_param_can_be_empty)) return 0; if (kstrtoint(param->string, 0, &result->int_32) < 0) return fs_param_bad_value(log, param); return 0; } EXPORT_SYMBOL(fs_param_is_s32); int fs_param_is_u64(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { if (param->type != fs_value_is_string) return fs_param_bad_value(log, param); if (!*param->string && (p->flags & fs_param_can_be_empty)) return 0; if (kstrtoull(param->string, 0, &result->uint_64) < 0) return fs_param_bad_value(log, param); return 0; } EXPORT_SYMBOL(fs_param_is_u64); int fs_param_is_enum(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { const struct constant_table *c; if (param->type != fs_value_is_string) return fs_param_bad_value(log, param); if (!*param->string && (p->flags & fs_param_can_be_empty)) return 0; c = __lookup_constant(p->data, param->string); if (!c) return fs_param_bad_value(log, param); result->uint_32 = c->value; return 0; } EXPORT_SYMBOL(fs_param_is_enum); int fs_param_is_string(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { if (param->type != fs_value_is_string || (!*param->string && !(p->flags & fs_param_can_be_empty))) return fs_param_bad_value(log, param); return 0; } EXPORT_SYMBOL(fs_param_is_string); int fs_param_is_blob(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { if (param->type != fs_value_is_blob) return fs_param_bad_value(log, param); return 0; } EXPORT_SYMBOL(fs_param_is_blob); int fs_param_is_fd(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { switch (param->type) { case fs_value_is_string: if ((!*param->string && !(p->flags & fs_param_can_be_empty)) || kstrtouint(param->string, 0, &result->uint_32) < 0) break; if (result->uint_32 <= INT_MAX) return 0; break; case fs_value_is_file: result->uint_32 = param->dirfd; if (result->uint_32 <= INT_MAX) return 0; break; default: break; } return fs_param_bad_value(log, param); } EXPORT_SYMBOL(fs_param_is_fd); int fs_param_is_file_or_string(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { switch (param->type) { case fs_value_is_string: return fs_param_is_string(log, p, param, result); case fs_value_is_file: result->uint_32 = param->dirfd; if (result->uint_32 <= INT_MAX) return 0; break; default: break; } return fs_param_bad_value(log, param); } EXPORT_SYMBOL(fs_param_is_file_or_string); int fs_param_is_uid(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { kuid_t uid; if (fs_param_is_u32(log, p, param, result) != 0) return fs_param_bad_value(log, param); uid = make_kuid(current_user_ns(), result->uint_32); if (!uid_valid(uid)) return inval_plog(log, "Invalid uid '%s'", param->string); result->uid = uid; return 0; } EXPORT_SYMBOL(fs_param_is_uid); int fs_param_is_gid(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { kgid_t gid; if (fs_param_is_u32(log, p, param, result) != 0) return fs_param_bad_value(log, param); gid = make_kgid(current_user_ns(), result->uint_32); if (!gid_valid(gid)) return inval_plog(log, "Invalid gid '%s'", param->string); result->gid = gid; return 0; } EXPORT_SYMBOL(fs_param_is_gid); int fs_param_is_blockdev(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { return 0; } EXPORT_SYMBOL(fs_param_is_blockdev); int fs_param_is_path(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { return 0; } EXPORT_SYMBOL(fs_param_is_path); #ifdef CONFIG_VALIDATE_FS_PARSER /** * fs_validate_description - Validate a parameter specification array * @name: Owner name of the parameter specification array * @desc: The parameter specification array to validate. */ bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc) { const struct fs_parameter_spec *param, *p2; bool good = true; for (param = desc; param->name; param++) { /* Check for duplicate parameter names */ for (p2 = desc; p2 < param; p2++) { if (strcmp(param->name, p2->name) == 0) { if (is_flag(param) != is_flag(p2)) continue; pr_err("VALIDATE %s: PARAM[%s]: Duplicate\n", name, param->name); good = false; } } } return good; } #endif /* CONFIG_VALIDATE_FS_PARSER */ |
| 143 141 141 133 31 142 143 10 10 10 10 10 10 3 3 3 3 3 26 25 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Block stat tracking code * * Copyright (C) 2016 Jens Axboe */ #include <linux/kernel.h> #include <linux/rculist.h> #include "blk-stat.h" #include "blk-mq.h" #include "blk.h" struct blk_queue_stats { struct list_head callbacks; spinlock_t lock; int accounting; }; void blk_rq_stat_init(struct blk_rq_stat *stat) { stat->min = -1ULL; stat->max = stat->nr_samples = stat->mean = 0; stat->batch = 0; } /* src is a per-cpu stat, mean isn't initialized */ void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) { if (dst->nr_samples + src->nr_samples <= dst->nr_samples) return; dst->min = min(dst->min, src->min); dst->max = max(dst->max, src->max); dst->mean = div_u64(src->batch + dst->mean * dst->nr_samples, dst->nr_samples + src->nr_samples); dst->nr_samples += src->nr_samples; } void blk_rq_stat_add(struct blk_rq_stat *stat, u64 value) { stat->min = min(stat->min, value); stat->max = max(stat->max, value); stat->batch += value; stat->nr_samples++; } void blk_stat_add(struct request *rq, u64 now) { struct request_queue *q = rq->q; struct blk_stat_callback *cb; struct blk_rq_stat *stat; int bucket, cpu; u64 value; value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0; rcu_read_lock(); cpu = get_cpu(); list_for_each_entry_rcu(cb, &q->stats->callbacks, list) { if (!blk_stat_is_active(cb)) continue; bucket = cb->bucket_fn(rq); if (bucket < 0) continue; stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket]; blk_rq_stat_add(stat, value); } put_cpu(); rcu_read_unlock(); } static void blk_stat_timer_fn(struct timer_list *t) { struct blk_stat_callback *cb = timer_container_of(cb, t, timer); unsigned int bucket; int cpu; for (bucket = 0; bucket < cb->buckets; bucket++) blk_rq_stat_init(&cb->stat[bucket]); for_each_online_cpu(cpu) { struct blk_rq_stat *cpu_stat; cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu); for (bucket = 0; bucket < cb->buckets; bucket++) { blk_rq_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]); blk_rq_stat_init(&cpu_stat[bucket]); } } cb->timer_fn(cb); } struct blk_stat_callback * blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *), int (*bucket_fn)(const struct request *), unsigned int buckets, void *data) { struct blk_stat_callback *cb; cb = kmalloc(sizeof(*cb), GFP_KERNEL); if (!cb) return NULL; cb->stat = kmalloc_array(buckets, sizeof(struct blk_rq_stat), GFP_KERNEL); if (!cb->stat) { kfree(cb); return NULL; } cb->cpu_stat = __alloc_percpu(buckets * sizeof(struct blk_rq_stat), __alignof__(struct blk_rq_stat)); if (!cb->cpu_stat) { kfree(cb->stat); kfree(cb); return NULL; } cb->timer_fn = timer_fn; cb->bucket_fn = bucket_fn; cb->data = data; cb->buckets = buckets; timer_setup(&cb->timer, blk_stat_timer_fn, 0); return cb; } void blk_stat_add_callback(struct request_queue *q, struct blk_stat_callback *cb) { unsigned int bucket; unsigned long flags; int cpu; for_each_possible_cpu(cpu) { struct blk_rq_stat *cpu_stat; cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu); for (bucket = 0; bucket < cb->buckets; bucket++) blk_rq_stat_init(&cpu_stat[bucket]); } spin_lock_irqsave(&q->stats->lock, flags); list_add_tail_rcu(&cb->list, &q->stats->callbacks); blk_queue_flag_set(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } void blk_stat_remove_callback(struct request_queue *q, struct blk_stat_callback *cb) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); list_del_rcu(&cb->list); if (list_empty(&q->stats->callbacks) && !q->stats->accounting) blk_queue_flag_clear(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); timer_delete_sync(&cb->timer); } static void blk_stat_free_callback_rcu(struct rcu_head *head) { struct blk_stat_callback *cb; cb = container_of(head, struct blk_stat_callback, rcu); free_percpu(cb->cpu_stat); kfree(cb->stat); kfree(cb); } void blk_stat_free_callback(struct blk_stat_callback *cb) { if (cb) call_rcu(&cb->rcu, blk_stat_free_callback_rcu); } void blk_stat_disable_accounting(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); if (!--q->stats->accounting && list_empty(&q->stats->callbacks)) blk_queue_flag_clear(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } EXPORT_SYMBOL_GPL(blk_stat_disable_accounting); void blk_stat_enable_accounting(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); if (!q->stats->accounting++ && list_empty(&q->stats->callbacks)) blk_queue_flag_set(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } EXPORT_SYMBOL_GPL(blk_stat_enable_accounting); struct blk_queue_stats *blk_alloc_queue_stats(void) { struct blk_queue_stats *stats; stats = kmalloc(sizeof(*stats), GFP_KERNEL); if (!stats) return NULL; INIT_LIST_HEAD(&stats->callbacks); spin_lock_init(&stats->lock); stats->accounting = 0; return stats; } void blk_free_queue_stats(struct blk_queue_stats *stats) { if (!stats) return; WARN_ON(!list_empty(&stats->callbacks)); kfree(stats); } |
| 15 15 8 7 7 4 4 13 25 5 2 8 20 6 13 13 13 13 13 13 13 16 4 1 26 25 5 13 11 8 2 15 8 5 3 8 3 5 6 7 4 3 2 1 2 1 3 1 3 6 1 16 8 4 4 1 13 13 43 43 4 5 3 8 10 8 6 3 3 24 2 2 19 1 4 8 1 7 7 3 13 13 10 20 13 9 5 29 5 4 6 13 10 5 6 2 11 2 15 11 6 1 1 4 27 1 1 2 2 22 24 5 5 4 21 2 6 6 15 15 15 10 6 6 3 18 8 11 27 66 66 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/msg.c * Copyright (C) 1992 Krishna Balasubramanian * * Removed all the remaining kerneld mess * Catch the -EFAULT stuff properly * Use GFP_KERNEL for messages as in 1.2 * Fixed up the unchecked user space derefs * Copyright (C) 1998 Alan Cox & Andi Kleen * * /proc/sysvipc/msg support (c) 1999 Dragos Acostachioaie <dragos@iname.com> * * mostly rewritten, threaded and wake-one semantics added * MSGMAX limit removed, sysctl's added * (c) 1999 Manfred Spraul <manfred@colorfullife.com> * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> * * namespaces support * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> */ #include <linux/capability.h> #include <linux/msg.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/proc_fs.h> #include <linux/list.h> #include <linux/security.h> #include <linux/sched/wake_q.h> #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/seq_file.h> #include <linux/rwsem.h> #include <linux/nsproxy.h> #include <linux/ipc_namespace.h> #include <linux/rhashtable.h> #include <linux/percpu_counter.h> #include <asm/current.h> #include <linux/uaccess.h> #include "util.h" /* one msq_queue structure for each present queue on the system */ struct msg_queue { struct kern_ipc_perm q_perm; time64_t q_stime; /* last msgsnd time */ time64_t q_rtime; /* last msgrcv time */ time64_t q_ctime; /* last change time */ unsigned long q_cbytes; /* current number of bytes on queue */ unsigned long q_qnum; /* number of messages in queue */ unsigned long q_qbytes; /* max number of bytes on queue */ struct pid *q_lspid; /* pid of last msgsnd */ struct pid *q_lrpid; /* last receive pid */ struct list_head q_messages; struct list_head q_receivers; struct list_head q_senders; } __randomize_layout; /* * MSG_BARRIER Locking: * * Similar to the optimization used in ipc/mqueue.c, one syscall return path * does not acquire any locks when it sees that a message exists in * msg_receiver.r_msg. Therefore r_msg is set using smp_store_release() * and accessed using READ_ONCE()+smp_acquire__after_ctrl_dep(). In addition, * wake_q_add_safe() is used. See ipc/mqueue.c for more details */ /* one msg_receiver structure for each sleeping receiver */ struct msg_receiver { struct list_head r_list; struct task_struct *r_tsk; int r_mode; long r_msgtype; long r_maxsize; struct msg_msg *r_msg; }; /* one msg_sender for each sleeping sender */ struct msg_sender { struct list_head list; struct task_struct *tsk; size_t msgsz; }; #define SEARCH_ANY 1 #define SEARCH_EQUAL 2 #define SEARCH_NOTEQUAL 3 #define SEARCH_LESSEQUAL 4 #define SEARCH_NUMBER 5 #define msg_ids(ns) ((ns)->ids[IPC_MSG_IDS]) static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&msg_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct msg_queue, q_perm); } static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct msg_queue, q_perm); } static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) { ipc_rmid(&msg_ids(ns), &s->q_perm); } static void msg_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); struct msg_queue *msq = container_of(p, struct msg_queue, q_perm); security_msg_queue_free(&msq->q_perm); kfree(msq); } /** * newque - Create a new msg queue * @ns: namespace * @params: ptr to the structure that contains the key and msgflg * * Called with msg_ids.rwsem held (writer) */ static int newque(struct ipc_namespace *ns, struct ipc_params *params) { struct msg_queue *msq; int retval; key_t key = params->key; int msgflg = params->flg; msq = kmalloc(sizeof(*msq), GFP_KERNEL_ACCOUNT); if (unlikely(!msq)) return -ENOMEM; msq->q_perm.mode = msgflg & S_IRWXUGO; msq->q_perm.key = key; msq->q_perm.security = NULL; retval = security_msg_queue_alloc(&msq->q_perm); if (retval) { kfree(msq); return retval; } msq->q_stime = msq->q_rtime = 0; msq->q_ctime = ktime_get_real_seconds(); msq->q_cbytes = msq->q_qnum = 0; msq->q_qbytes = ns->msg_ctlmnb; msq->q_lspid = msq->q_lrpid = NULL; INIT_LIST_HEAD(&msq->q_messages); INIT_LIST_HEAD(&msq->q_receivers); INIT_LIST_HEAD(&msq->q_senders); /* ipc_addid() locks msq upon success. */ retval = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); if (retval < 0) { ipc_rcu_putref(&msq->q_perm, msg_rcu_free); return retval; } ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); return msq->q_perm.id; } static inline bool msg_fits_inqueue(struct msg_queue *msq, size_t msgsz) { return msgsz + msq->q_cbytes <= msq->q_qbytes && 1 + msq->q_qnum <= msq->q_qbytes; } static inline void ss_add(struct msg_queue *msq, struct msg_sender *mss, size_t msgsz) { mss->tsk = current; mss->msgsz = msgsz; /* * No memory barrier required: we did ipc_lock_object(), * and the waker obtains that lock before calling wake_q_add(). */ __set_current_state(TASK_INTERRUPTIBLE); list_add_tail(&mss->list, &msq->q_senders); } static inline void ss_del(struct msg_sender *mss) { if (mss->list.next) list_del(&mss->list); } static void ss_wakeup(struct msg_queue *msq, struct wake_q_head *wake_q, bool kill) { struct msg_sender *mss, *t; struct task_struct *stop_tsk = NULL; struct list_head *h = &msq->q_senders; list_for_each_entry_safe(mss, t, h, list) { if (kill) mss->list.next = NULL; /* * Stop at the first task we don't wakeup, * we've already iterated the original * sender queue. */ else if (stop_tsk == mss->tsk) break; /* * We are not in an EIDRM scenario here, therefore * verify that we really need to wakeup the task. * To maintain current semantics and wakeup order, * move the sender to the tail on behalf of the * blocked task. */ else if (!msg_fits_inqueue(msq, mss->msgsz)) { if (!stop_tsk) stop_tsk = mss->tsk; list_move_tail(&mss->list, &msq->q_senders); continue; } wake_q_add(wake_q, mss->tsk); } } static void expunge_all(struct msg_queue *msq, int res, struct wake_q_head *wake_q) { struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { struct task_struct *r_tsk; r_tsk = get_task_struct(msr->r_tsk); /* see MSG_BARRIER for purpose/pairing */ smp_store_release(&msr->r_msg, ERR_PTR(res)); wake_q_add_safe(wake_q, r_tsk); } } /* * freeque() wakes up waiters on the sender and receiver waiting queue, * removes the message queue from message queue ID IDR, and cleans up all the * messages associated with this queue. * * msg_ids.rwsem (writer) and the spinlock for this message queue are held * before freeque() is called. msg_ids.rwsem remains locked on exit. */ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) __releases(RCU) __releases(&msq->q_perm) { struct msg_msg *msg, *t; struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); DEFINE_WAKE_Q(wake_q); expunge_all(msq, -EIDRM, &wake_q); ss_wakeup(msq, &wake_q, true); msg_rmid(ns, msq); ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); rcu_read_unlock(); list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) { percpu_counter_sub_local(&ns->percpu_msg_hdrs, 1); free_msg(msg); } percpu_counter_sub_local(&ns->percpu_msg_bytes, msq->q_cbytes); ipc_update_pid(&msq->q_lspid, NULL); ipc_update_pid(&msq->q_lrpid, NULL); ipc_rcu_putref(&msq->q_perm, msg_rcu_free); } long ksys_msgget(key_t key, int msgflg) { struct ipc_namespace *ns; static const struct ipc_ops msg_ops = { .getnew = newque, .associate = security_msg_queue_associate, }; struct ipc_params msg_params; ns = current->nsproxy->ipc_ns; msg_params.key = key; msg_params.flg = msgflg; return ipcget(ns, &msg_ids(ns), &msg_ops, &msg_params); } SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg) { return ksys_msgget(key, msgflg); } static inline unsigned long copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct msqid_ds out; memset(&out, 0, sizeof(out)); ipc64_perm_to_ipc_perm(&in->msg_perm, &out.msg_perm); out.msg_stime = in->msg_stime; out.msg_rtime = in->msg_rtime; out.msg_ctime = in->msg_ctime; if (in->msg_cbytes > USHRT_MAX) out.msg_cbytes = USHRT_MAX; else out.msg_cbytes = in->msg_cbytes; out.msg_lcbytes = in->msg_cbytes; if (in->msg_qnum > USHRT_MAX) out.msg_qnum = USHRT_MAX; else out.msg_qnum = in->msg_qnum; if (in->msg_qbytes > USHRT_MAX) out.msg_qbytes = USHRT_MAX; else out.msg_qbytes = in->msg_qbytes; out.msg_lqbytes = in->msg_qbytes; out.msg_lspid = in->msg_lspid; out.msg_lrpid = in->msg_lrpid; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } static inline unsigned long copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version) { switch (version) { case IPC_64: if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; return 0; case IPC_OLD: { struct msqid_ds tbuf_old; if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; out->msg_perm.uid = tbuf_old.msg_perm.uid; out->msg_perm.gid = tbuf_old.msg_perm.gid; out->msg_perm.mode = tbuf_old.msg_perm.mode; if (tbuf_old.msg_qbytes == 0) out->msg_qbytes = tbuf_old.msg_lqbytes; else out->msg_qbytes = tbuf_old.msg_qbytes; return 0; } default: return -EINVAL; } } /* * This function handles some msgctl commands which require the rwsem * to be held in write mode. * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, struct ipc64_perm *perm, int msg_qbytes) { struct kern_ipc_perm *ipcp; struct msg_queue *msq; int err; down_write(&msg_ids(ns).rwsem); rcu_read_lock(); ipcp = ipcctl_obtain_check(ns, &msg_ids(ns), msqid, cmd, perm, msg_qbytes); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; } msq = container_of(ipcp, struct msg_queue, q_perm); err = security_msg_queue_msgctl(&msq->q_perm, cmd); if (err) goto out_unlock1; switch (cmd) { case IPC_RMID: ipc_lock_object(&msq->q_perm); /* freeque unlocks the ipc object and rcu */ freeque(ns, ipcp); goto out_up; case IPC_SET: { DEFINE_WAKE_Q(wake_q); if (msg_qbytes > ns->msg_ctlmnb && !capable(CAP_SYS_RESOURCE)) { err = -EPERM; goto out_unlock1; } ipc_lock_object(&msq->q_perm); err = ipc_update_perm(perm, ipcp); if (err) goto out_unlock0; msq->q_qbytes = msg_qbytes; msq->q_ctime = ktime_get_real_seconds(); /* * Sleeping receivers might be excluded by * stricter permissions. */ expunge_all(msq, -EAGAIN, &wake_q); /* * Sleeping senders might be able to send * due to a larger queue size. */ ss_wakeup(msq, &wake_q, false); ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); goto out_unlock1; } default: err = -EINVAL; goto out_unlock1; } out_unlock0: ipc_unlock_object(&msq->q_perm); out_unlock1: rcu_read_unlock(); out_up: up_write(&msg_ids(ns).rwsem); return err; } static int msgctl_info(struct ipc_namespace *ns, int msqid, int cmd, struct msginfo *msginfo) { int err; int max_idx; /* * We must not return kernel stack data. * due to padding, it's not enough * to set all member fields. */ err = security_msg_queue_msgctl(NULL, cmd); if (err) return err; memset(msginfo, 0, sizeof(*msginfo)); msginfo->msgmni = ns->msg_ctlmni; msginfo->msgmax = ns->msg_ctlmax; msginfo->msgmnb = ns->msg_ctlmnb; msginfo->msgssz = MSGSSZ; msginfo->msgseg = MSGSEG; down_read(&msg_ids(ns).rwsem); if (cmd == MSG_INFO) msginfo->msgpool = msg_ids(ns).in_use; max_idx = ipc_get_maxidx(&msg_ids(ns)); up_read(&msg_ids(ns).rwsem); if (cmd == MSG_INFO) { msginfo->msgmap = min_t(int, percpu_counter_sum(&ns->percpu_msg_hdrs), INT_MAX); msginfo->msgtql = min_t(int, percpu_counter_sum(&ns->percpu_msg_bytes), INT_MAX); } else { msginfo->msgmap = MSGMAP; msginfo->msgpool = MSGPOOL; msginfo->msgtql = MSGTQL; } return (max_idx < 0) ? 0 : max_idx; } static int msgctl_stat(struct ipc_namespace *ns, int msqid, int cmd, struct msqid64_ds *p) { struct msg_queue *msq; int err; memset(p, 0, sizeof(*p)); rcu_read_lock(); if (cmd == MSG_STAT || cmd == MSG_STAT_ANY) { msq = msq_obtain_object(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock; } } else { /* IPC_STAT */ msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock; } } /* see comment for SHM_STAT_ANY */ if (cmd == MSG_STAT_ANY) audit_ipc_obj(&msq->q_perm); else { err = -EACCES; if (ipcperms(ns, &msq->q_perm, S_IRUGO)) goto out_unlock; } err = security_msg_queue_msgctl(&msq->q_perm, cmd); if (err) goto out_unlock; ipc_lock_object(&msq->q_perm); if (!ipc_valid_object(&msq->q_perm)) { ipc_unlock_object(&msq->q_perm); err = -EIDRM; goto out_unlock; } kernel_to_ipc64_perm(&msq->q_perm, &p->msg_perm); p->msg_stime = msq->q_stime; p->msg_rtime = msq->q_rtime; p->msg_ctime = msq->q_ctime; #ifndef CONFIG_64BIT p->msg_stime_high = msq->q_stime >> 32; p->msg_rtime_high = msq->q_rtime >> 32; p->msg_ctime_high = msq->q_ctime >> 32; #endif p->msg_cbytes = msq->q_cbytes; p->msg_qnum = msq->q_qnum; p->msg_qbytes = msq->q_qbytes; p->msg_lspid = pid_vnr(msq->q_lspid); p->msg_lrpid = pid_vnr(msq->q_lrpid); if (cmd == IPC_STAT) { /* * As defined in SUS: * Return 0 on success */ err = 0; } else { /* * MSG_STAT and MSG_STAT_ANY (both Linux specific) * Return the full id, including the sequence number */ err = msq->q_perm.id; } ipc_unlock_object(&msq->q_perm); out_unlock: rcu_read_unlock(); return err; } static long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf, int version) { struct ipc_namespace *ns; struct msqid64_ds msqid64; int err; if (msqid < 0 || cmd < 0) return -EINVAL; ns = current->nsproxy->ipc_ns; switch (cmd) { case IPC_INFO: case MSG_INFO: { struct msginfo msginfo; err = msgctl_info(ns, msqid, cmd, &msginfo); if (err < 0) return err; if (copy_to_user(buf, &msginfo, sizeof(struct msginfo))) err = -EFAULT; return err; } case MSG_STAT: /* msqid is an index rather than a msg queue id */ case MSG_STAT_ANY: case IPC_STAT: err = msgctl_stat(ns, msqid, cmd, &msqid64); if (err < 0) return err; if (copy_msqid_to_user(buf, &msqid64, version)) err = -EFAULT; return err; case IPC_SET: if (copy_msqid_from_user(&msqid64, buf, version)) return -EFAULT; return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes); case IPC_RMID: return msgctl_down(ns, msqid, cmd, NULL, 0); default: return -EINVAL; } } SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) { return ksys_msgctl(msqid, cmd, buf, IPC_64); } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION long ksys_old_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) { int version = ipc_parse_version(&cmd); return ksys_msgctl(msqid, cmd, buf, version); } SYSCALL_DEFINE3(old_msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) { return ksys_old_msgctl(msqid, cmd, buf); } #endif #ifdef CONFIG_COMPAT struct compat_msqid_ds { struct compat_ipc_perm msg_perm; compat_uptr_t msg_first; compat_uptr_t msg_last; old_time32_t msg_stime; old_time32_t msg_rtime; old_time32_t msg_ctime; compat_ulong_t msg_lcbytes; compat_ulong_t msg_lqbytes; unsigned short msg_cbytes; unsigned short msg_qnum; unsigned short msg_qbytes; compat_ipc_pid_t msg_lspid; compat_ipc_pid_t msg_lrpid; }; static int copy_compat_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version) { memset(out, 0, sizeof(*out)); if (version == IPC_64) { struct compat_msqid64_ds __user *p = buf; if (get_compat_ipc64_perm(&out->msg_perm, &p->msg_perm)) return -EFAULT; if (get_user(out->msg_qbytes, &p->msg_qbytes)) return -EFAULT; } else { struct compat_msqid_ds __user *p = buf; if (get_compat_ipc_perm(&out->msg_perm, &p->msg_perm)) return -EFAULT; if (get_user(out->msg_qbytes, &p->msg_qbytes)) return -EFAULT; } return 0; } static int copy_compat_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version) { if (version == IPC_64) { struct compat_msqid64_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc64_perm(&v.msg_perm, &in->msg_perm); v.msg_stime = lower_32_bits(in->msg_stime); v.msg_stime_high = upper_32_bits(in->msg_stime); v.msg_rtime = lower_32_bits(in->msg_rtime); v.msg_rtime_high = upper_32_bits(in->msg_rtime); v.msg_ctime = lower_32_bits(in->msg_ctime); v.msg_ctime_high = upper_32_bits(in->msg_ctime); v.msg_cbytes = in->msg_cbytes; v.msg_qnum = in->msg_qnum; v.msg_qbytes = in->msg_qbytes; v.msg_lspid = in->msg_lspid; v.msg_lrpid = in->msg_lrpid; return copy_to_user(buf, &v, sizeof(v)); } else { struct compat_msqid_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc_perm(&v.msg_perm, &in->msg_perm); v.msg_stime = in->msg_stime; v.msg_rtime = in->msg_rtime; v.msg_ctime = in->msg_ctime; v.msg_cbytes = in->msg_cbytes; v.msg_qnum = in->msg_qnum; v.msg_qbytes = in->msg_qbytes; v.msg_lspid = in->msg_lspid; v.msg_lrpid = in->msg_lrpid; return copy_to_user(buf, &v, sizeof(v)); } } static long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr, int version) { struct ipc_namespace *ns; int err; struct msqid64_ds msqid64; ns = current->nsproxy->ipc_ns; if (msqid < 0 || cmd < 0) return -EINVAL; switch (cmd & (~IPC_64)) { case IPC_INFO: case MSG_INFO: { struct msginfo msginfo; err = msgctl_info(ns, msqid, cmd, &msginfo); if (err < 0) return err; if (copy_to_user(uptr, &msginfo, sizeof(struct msginfo))) err = -EFAULT; return err; } case IPC_STAT: case MSG_STAT: case MSG_STAT_ANY: err = msgctl_stat(ns, msqid, cmd, &msqid64); if (err < 0) return err; if (copy_compat_msqid_to_user(uptr, &msqid64, version)) err = -EFAULT; return err; case IPC_SET: if (copy_compat_msqid_from_user(&msqid64, uptr, version)) return -EFAULT; return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes); case IPC_RMID: return msgctl_down(ns, msqid, cmd, NULL, 0); default: return -EINVAL; } } COMPAT_SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, void __user *, uptr) { return compat_ksys_msgctl(msqid, cmd, uptr, IPC_64); } #ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION long compat_ksys_old_msgctl(int msqid, int cmd, void __user *uptr) { int version = compat_ipc_parse_version(&cmd); return compat_ksys_msgctl(msqid, cmd, uptr, version); } COMPAT_SYSCALL_DEFINE3(old_msgctl, int, msqid, int, cmd, void __user *, uptr) { return compat_ksys_old_msgctl(msqid, cmd, uptr); } #endif #endif static int testmsg(struct msg_msg *msg, long type, int mode) { switch (mode) { case SEARCH_ANY: case SEARCH_NUMBER: return 1; case SEARCH_LESSEQUAL: if (msg->m_type <= type) return 1; break; case SEARCH_EQUAL: if (msg->m_type == type) return 1; break; case SEARCH_NOTEQUAL: if (msg->m_type != type) return 1; break; } return 0; } static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg, struct wake_q_head *wake_q) { struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { if (testmsg(msg, msr->r_msgtype, msr->r_mode) && !security_msg_queue_msgrcv(&msq->q_perm, msg, msr->r_tsk, msr->r_msgtype, msr->r_mode)) { list_del(&msr->r_list); if (msr->r_maxsize < msg->m_ts) { wake_q_add(wake_q, msr->r_tsk); /* See expunge_all regarding memory barrier */ smp_store_release(&msr->r_msg, ERR_PTR(-E2BIG)); } else { ipc_update_pid(&msq->q_lrpid, task_pid(msr->r_tsk)); msq->q_rtime = ktime_get_real_seconds(); wake_q_add(wake_q, msr->r_tsk); /* See expunge_all regarding memory barrier */ smp_store_release(&msr->r_msg, msg); return 1; } } } return 0; } static long do_msgsnd(int msqid, long mtype, void __user *mtext, size_t msgsz, int msgflg) { struct msg_queue *msq; struct msg_msg *msg; int err; struct ipc_namespace *ns; DEFINE_WAKE_Q(wake_q); ns = current->nsproxy->ipc_ns; if (msgsz > ns->msg_ctlmax || (long) msgsz < 0 || msqid < 0) return -EINVAL; if (mtype < 1) return -EINVAL; msg = load_msg(mtext, msgsz); if (IS_ERR(msg)) return PTR_ERR(msg); msg->m_type = mtype; msg->m_ts = msgsz; rcu_read_lock(); msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock1; } ipc_lock_object(&msq->q_perm); for (;;) { struct msg_sender s; err = -EACCES; if (ipcperms(ns, &msq->q_perm, S_IWUGO)) goto out_unlock0; /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } err = security_msg_queue_msgsnd(&msq->q_perm, msg, msgflg); if (err) goto out_unlock0; if (msg_fits_inqueue(msq, msgsz)) break; /* queue full, wait: */ if (msgflg & IPC_NOWAIT) { err = -EAGAIN; goto out_unlock0; } /* enqueue the sender and prepare to block */ ss_add(msq, &s, msgsz); if (!ipc_rcu_getref(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); schedule(); rcu_read_lock(); ipc_lock_object(&msq->q_perm); ipc_rcu_putref(&msq->q_perm, msg_rcu_free); /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { err = -EIDRM; goto out_unlock0; } ss_del(&s); if (signal_pending(current)) { err = -ERESTARTNOHAND; goto out_unlock0; } } ipc_update_pid(&msq->q_lspid, task_tgid(current)); msq->q_stime = ktime_get_real_seconds(); if (!pipelined_send(msq, msg, &wake_q)) { /* no one is waiting for this message, enqueue it */ list_add_tail(&msg->m_list, &msq->q_messages); msq->q_cbytes += msgsz; msq->q_qnum++; percpu_counter_add_local(&ns->percpu_msg_bytes, msgsz); percpu_counter_add_local(&ns->percpu_msg_hdrs, 1); } err = 0; msg = NULL; out_unlock0: ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); out_unlock1: rcu_read_unlock(); if (msg != NULL) free_msg(msg); return err; } long ksys_msgsnd(int msqid, struct msgbuf __user *msgp, size_t msgsz, int msgflg) { long mtype; if (get_user(mtype, &msgp->mtype)) return -EFAULT; return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg); } SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, int, msgflg) { return ksys_msgsnd(msqid, msgp, msgsz, msgflg); } #ifdef CONFIG_COMPAT struct compat_msgbuf { compat_long_t mtype; char mtext[]; }; long compat_ksys_msgsnd(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, int msgflg) { struct compat_msgbuf __user *up = compat_ptr(msgp); compat_long_t mtype; if (get_user(mtype, &up->mtype)) return -EFAULT; return do_msgsnd(msqid, mtype, up->mtext, (ssize_t)msgsz, msgflg); } COMPAT_SYSCALL_DEFINE4(msgsnd, int, msqid, compat_uptr_t, msgp, compat_ssize_t, msgsz, int, msgflg) { return compat_ksys_msgsnd(msqid, msgp, msgsz, msgflg); } #endif static inline int convert_mode(long *msgtyp, int msgflg) { if (msgflg & MSG_COPY) return SEARCH_NUMBER; /* * find message of correct type. * msgtyp = 0 => get first. * msgtyp > 0 => get first message of matching type. * msgtyp < 0 => get message with least type must be < abs(msgtype). */ if (*msgtyp == 0) return SEARCH_ANY; if (*msgtyp < 0) { if (*msgtyp == LONG_MIN) /* -LONG_MIN is undefined */ *msgtyp = LONG_MAX; else *msgtyp = -*msgtyp; return SEARCH_LESSEQUAL; } if (msgflg & MSG_EXCEPT) return SEARCH_NOTEQUAL; return SEARCH_EQUAL; } static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz) { struct msgbuf __user *msgp = dest; size_t msgsz; if (put_user(msg->m_type, &msgp->mtype)) return -EFAULT; msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz; if (store_msg(msgp->mtext, msg, msgsz)) return -EFAULT; return msgsz; } #ifdef CONFIG_CHECKPOINT_RESTORE /* * This function creates new kernel message structure, large enough to store * bufsz message bytes. */ static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz) { struct msg_msg *copy; /* * Create dummy message to copy real message to. */ copy = load_msg(buf, bufsz); if (!IS_ERR(copy)) copy->m_ts = bufsz; return copy; } static inline void free_copy(struct msg_msg *copy) { if (copy) free_msg(copy); } #else static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz) { return ERR_PTR(-ENOSYS); } static inline void free_copy(struct msg_msg *copy) { } #endif static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode) { struct msg_msg *msg, *found = NULL; long count = 0; list_for_each_entry(msg, &msq->q_messages, m_list) { if (testmsg(msg, *msgtyp, mode) && !security_msg_queue_msgrcv(&msq->q_perm, msg, current, *msgtyp, mode)) { if (mode == SEARCH_LESSEQUAL && msg->m_type != 1) { *msgtyp = msg->m_type - 1; found = msg; } else if (mode == SEARCH_NUMBER) { if (*msgtyp == count) return msg; } else return msg; count++; } } return found ?: ERR_PTR(-EAGAIN); } static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg, long (*msg_handler)(void __user *, struct msg_msg *, size_t)) { int mode; struct msg_queue *msq; struct ipc_namespace *ns; struct msg_msg *msg, *copy = NULL; DEFINE_WAKE_Q(wake_q); ns = current->nsproxy->ipc_ns; if (msqid < 0 || (long) bufsz < 0) return -EINVAL; if (msgflg & MSG_COPY) { if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT)) return -EINVAL; copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax)); if (IS_ERR(copy)) return PTR_ERR(copy); } mode = convert_mode(&msgtyp, msgflg); rcu_read_lock(); msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { rcu_read_unlock(); free_copy(copy); return PTR_ERR(msq); } for (;;) { struct msg_receiver msr_d; msg = ERR_PTR(-EACCES); if (ipcperms(ns, &msq->q_perm, S_IRUGO)) goto out_unlock1; ipc_lock_object(&msq->q_perm); /* raced with RMID? */ if (!ipc_valid_object(&msq->q_perm)) { msg = ERR_PTR(-EIDRM); goto out_unlock0; } msg = find_msg(msq, &msgtyp, mode); if (!IS_ERR(msg)) { /* * Found a suitable message. * Unlink it from the queue. */ if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) { msg = ERR_PTR(-E2BIG); goto out_unlock0; } /* * If we are copying, then do not unlink message and do * not update queue parameters. */ if (msgflg & MSG_COPY) { msg = copy_msg(msg, copy); goto out_unlock0; } list_del(&msg->m_list); msq->q_qnum--; msq->q_rtime = ktime_get_real_seconds(); ipc_update_pid(&msq->q_lrpid, task_tgid(current)); msq->q_cbytes -= msg->m_ts; percpu_counter_sub_local(&ns->percpu_msg_bytes, msg->m_ts); percpu_counter_sub_local(&ns->percpu_msg_hdrs, 1); ss_wakeup(msq, &wake_q, false); goto out_unlock0; } /* No message waiting. Wait for a message */ if (msgflg & IPC_NOWAIT) { msg = ERR_PTR(-ENOMSG); goto out_unlock0; } list_add_tail(&msr_d.r_list, &msq->q_receivers); msr_d.r_tsk = current; msr_d.r_msgtype = msgtyp; msr_d.r_mode = mode; if (msgflg & MSG_NOERROR) msr_d.r_maxsize = INT_MAX; else msr_d.r_maxsize = bufsz; /* memory barrier not require due to ipc_lock_object() */ WRITE_ONCE(msr_d.r_msg, ERR_PTR(-EAGAIN)); /* memory barrier not required, we own ipc_lock_object() */ __set_current_state(TASK_INTERRUPTIBLE); ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); schedule(); /* * Lockless receive, part 1: * We don't hold a reference to the queue and getting a * reference would defeat the idea of a lockless operation, * thus the code relies on rcu to guarantee the existence of * msq: * Prior to destruction, expunge_all(-EIRDM) changes r_msg. * Thus if r_msg is -EAGAIN, then the queue not yet destroyed. */ rcu_read_lock(); /* * Lockless receive, part 2: * The work in pipelined_send() and expunge_all(): * - Set pointer to message * - Queue the receiver task for later wakeup * - Wake up the process after the lock is dropped. * * Should the process wake up before this wakeup (due to a * signal) it will either see the message and continue ... */ msg = READ_ONCE(msr_d.r_msg); if (msg != ERR_PTR(-EAGAIN)) { /* see MSG_BARRIER for purpose/pairing */ smp_acquire__after_ctrl_dep(); goto out_unlock1; } /* * ... or see -EAGAIN, acquire the lock to check the message * again. */ ipc_lock_object(&msq->q_perm); msg = READ_ONCE(msr_d.r_msg); if (msg != ERR_PTR(-EAGAIN)) goto out_unlock0; list_del(&msr_d.r_list); if (signal_pending(current)) { msg = ERR_PTR(-ERESTARTNOHAND); goto out_unlock0; } ipc_unlock_object(&msq->q_perm); } out_unlock0: ipc_unlock_object(&msq->q_perm); wake_up_q(&wake_q); out_unlock1: rcu_read_unlock(); if (IS_ERR(msg)) { free_copy(copy); return PTR_ERR(msg); } bufsz = msg_handler(buf, msg, bufsz); free_msg(msg); return bufsz; } long ksys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, long msgtyp, int msgflg) { return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill); } SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, long, msgtyp, int, msgflg) { return ksys_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg); } #ifdef CONFIG_COMPAT static long compat_do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz) { struct compat_msgbuf __user *msgp = dest; size_t msgsz; if (put_user(msg->m_type, &msgp->mtype)) return -EFAULT; msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz; if (store_msg(msgp->mtext, msg, msgsz)) return -EFAULT; return msgsz; } long compat_ksys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg) { return do_msgrcv(msqid, compat_ptr(msgp), (ssize_t)msgsz, (long)msgtyp, msgflg, compat_do_msg_fill); } COMPAT_SYSCALL_DEFINE5(msgrcv, int, msqid, compat_uptr_t, msgp, compat_ssize_t, msgsz, compat_long_t, msgtyp, int, msgflg) { return compat_ksys_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg); } #endif int msg_init_ns(struct ipc_namespace *ns) { int ret; ns->msg_ctlmax = MSGMAX; ns->msg_ctlmnb = MSGMNB; ns->msg_ctlmni = MSGMNI; ret = percpu_counter_init(&ns->percpu_msg_bytes, 0, GFP_KERNEL); if (ret) goto fail_msg_bytes; ret = percpu_counter_init(&ns->percpu_msg_hdrs, 0, GFP_KERNEL); if (ret) goto fail_msg_hdrs; ipc_init_ids(&ns->ids[IPC_MSG_IDS]); return 0; fail_msg_hdrs: percpu_counter_destroy(&ns->percpu_msg_bytes); fail_msg_bytes: return ret; } #ifdef CONFIG_IPC_NS void msg_exit_ns(struct ipc_namespace *ns) { free_ipcs(ns, &msg_ids(ns), freeque); idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr); rhashtable_destroy(&ns->ids[IPC_MSG_IDS].key_ht); percpu_counter_destroy(&ns->percpu_msg_bytes); percpu_counter_destroy(&ns->percpu_msg_hdrs); } #endif #ifdef CONFIG_PROC_FS static int sysvipc_msg_proc_show(struct seq_file *s, void *it) { struct pid_namespace *pid_ns = ipc_seq_pid_ns(s); struct user_namespace *user_ns = seq_user_ns(s); struct kern_ipc_perm *ipcp = it; struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); seq_printf(s, "%10d %10d %4o %10lu %10lu %5u %5u %5u %5u %5u %5u %10llu %10llu %10llu\n", msq->q_perm.key, msq->q_perm.id, msq->q_perm.mode, msq->q_cbytes, msq->q_qnum, pid_nr_ns(msq->q_lspid, pid_ns), pid_nr_ns(msq->q_lrpid, pid_ns), from_kuid_munged(user_ns, msq->q_perm.uid), from_kgid_munged(user_ns, msq->q_perm.gid), from_kuid_munged(user_ns, msq->q_perm.cuid), from_kgid_munged(user_ns, msq->q_perm.cgid), msq->q_stime, msq->q_rtime, msq->q_ctime); return 0; } #endif void __init msg_init(void) { msg_init_ns(&init_ipc_ns); ipc_init_proc_interface("sysvipc/msg", " key msqid perms cbytes qnum lspid lrpid uid gid cuid cgid stime rtime ctime\n", IPC_MSG_IDS, sysvipc_msg_proc_show); } |
| 1 2 4 1 3 6 1 1 4 2 1 1 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved. */ #include <linux/fs.h> #include <linux/filelock.h> #include <linux/miscdevice.h> #include <linux/poll.h> #include <linux/dlm.h> #include <linux/dlm_plock.h> #include <linux/slab.h> #include <trace/events/dlm.h> #include "dlm_internal.h" #include "lockspace.h" static DEFINE_SPINLOCK(ops_lock); static LIST_HEAD(send_list); static LIST_HEAD(recv_list); static DECLARE_WAIT_QUEUE_HEAD(send_wq); static DECLARE_WAIT_QUEUE_HEAD(recv_wq); struct plock_async_data { void *fl; void *file; struct file_lock flc; int (*callback)(struct file_lock *fl, int result); }; struct plock_op { struct list_head list; int done; struct dlm_plock_info info; /* if set indicates async handling */ struct plock_async_data *data; }; static inline void set_version(struct dlm_plock_info *info) { info->version[0] = DLM_PLOCK_VERSION_MAJOR; info->version[1] = DLM_PLOCK_VERSION_MINOR; info->version[2] = DLM_PLOCK_VERSION_PATCH; } static struct plock_op *plock_lookup_waiter(const struct dlm_plock_info *info) { struct plock_op *op = NULL, *iter; list_for_each_entry(iter, &recv_list, list) { if (iter->info.fsid == info->fsid && iter->info.number == info->number && iter->info.owner == info->owner && iter->info.pid == info->pid && iter->info.start == info->start && iter->info.end == info->end && iter->info.ex == info->ex && iter->info.wait) { op = iter; break; } } return op; } static int check_version(struct dlm_plock_info *info) { if ((DLM_PLOCK_VERSION_MAJOR != info->version[0]) || (DLM_PLOCK_VERSION_MINOR < info->version[1])) { log_print("plock device version mismatch: " "kernel (%u.%u.%u), user (%u.%u.%u)", DLM_PLOCK_VERSION_MAJOR, DLM_PLOCK_VERSION_MINOR, DLM_PLOCK_VERSION_PATCH, info->version[0], info->version[1], info->version[2]); return -EINVAL; } return 0; } static void dlm_release_plock_op(struct plock_op *op) { kfree(op->data); kfree(op); } static void send_op(struct plock_op *op) { set_version(&op->info); spin_lock(&ops_lock); list_add_tail(&op->list, &send_list); spin_unlock(&ops_lock); wake_up(&send_wq); } static int do_lock_cancel(const struct dlm_plock_info *orig_info) { struct plock_op *op; int rv; op = kzalloc(sizeof(*op), GFP_NOFS); if (!op) return -ENOMEM; op->info = *orig_info; op->info.optype = DLM_PLOCK_OP_CANCEL; op->info.wait = 0; send_op(op); wait_event(recv_wq, (op->done != 0)); rv = op->info.rv; dlm_release_plock_op(op); return rv; } int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, int cmd, struct file_lock *fl) { struct plock_async_data *op_data; struct dlm_ls *ls; struct plock_op *op; int rv; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; op = kzalloc(sizeof(*op), GFP_NOFS); if (!op) { rv = -ENOMEM; goto out; } op->info.optype = DLM_PLOCK_OP_LOCK; op->info.pid = fl->c.flc_pid; op->info.ex = lock_is_write(fl); op->info.wait = !!(fl->c.flc_flags & FL_SLEEP); op->info.fsid = ls->ls_global_id; op->info.number = number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; op->info.owner = (__u64)(long) fl->c.flc_owner; /* async handling */ if (fl->fl_lmops && fl->fl_lmops->lm_grant) { op_data = kzalloc(sizeof(*op_data), GFP_NOFS); if (!op_data) { dlm_release_plock_op(op); rv = -ENOMEM; goto out; } op_data->callback = fl->fl_lmops->lm_grant; locks_init_lock(&op_data->flc); locks_copy_lock(&op_data->flc, fl); op_data->fl = fl; op_data->file = file; op->data = op_data; send_op(op); rv = FILE_LOCK_DEFERRED; goto out; } send_op(op); if (op->info.wait) { rv = wait_event_interruptible(recv_wq, (op->done != 0)); if (rv == -ERESTARTSYS) { spin_lock(&ops_lock); /* recheck under ops_lock if we got a done != 0, * if so this interrupt case should be ignored */ if (op->done != 0) { spin_unlock(&ops_lock); goto do_lock_wait; } spin_unlock(&ops_lock); rv = do_lock_cancel(&op->info); switch (rv) { case 0: /* waiter was deleted in user space, answer will never come * remove original request. The original request must be * on recv_list because the answer of do_lock_cancel() * synchronized it. */ spin_lock(&ops_lock); list_del(&op->list); spin_unlock(&ops_lock); rv = -EINTR; break; case -ENOENT: /* cancellation wasn't successful but op should be done */ fallthrough; default: /* internal error doing cancel we need to wait */ goto wait; } log_debug(ls, "%s: wait interrupted %x %llx pid %d", __func__, ls->ls_global_id, (unsigned long long)number, op->info.pid); dlm_release_plock_op(op); goto out; } } else { wait: wait_event(recv_wq, (op->done != 0)); } do_lock_wait: WARN_ON(!list_empty(&op->list)); rv = op->info.rv; if (!rv) { if (locks_lock_file_wait(file, fl) < 0) log_error(ls, "dlm_posix_lock: vfs lock error %llx", (unsigned long long)number); } dlm_release_plock_op(op); out: dlm_put_lockspace(ls); return rv; } EXPORT_SYMBOL_GPL(dlm_posix_lock); /* Returns failure iff a successful lock operation should be canceled */ static int dlm_plock_callback(struct plock_op *op) { struct plock_async_data *op_data = op->data; struct file *file; struct file_lock *fl; struct file_lock *flc; int (*notify)(struct file_lock *fl, int result) = NULL; int rv = 0; WARN_ON(!list_empty(&op->list)); /* check if the following 2 are still valid or make a copy */ file = op_data->file; flc = &op_data->flc; fl = op_data->fl; notify = op_data->callback; if (op->info.rv) { notify(fl, op->info.rv); goto out; } /* got fs lock; bookkeep locally as well: */ flc->c.flc_flags &= ~FL_SLEEP; if (posix_lock_file(file, flc, NULL)) { /* * This can only happen in the case of kmalloc() failure. * The filesystem's own lock is the authoritative lock, * so a failure to get the lock locally is not a disaster. * As long as the fs cannot reliably cancel locks (especially * in a low-memory situation), we're better off ignoring * this failure than trying to recover. */ log_print("dlm_plock_callback: vfs lock error %llx file %p fl %p", (unsigned long long)op->info.number, file, fl); } rv = notify(fl, 0); if (rv) { /* XXX: We need to cancel the fs lock here: */ log_print("%s: lock granted after lock request failed; dangling lock!", __func__); goto out; } out: dlm_release_plock_op(op); return rv; } int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, struct file_lock *fl) { struct dlm_ls *ls; struct plock_op *op; int rv; unsigned char saved_flags = fl->c.flc_flags; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; op = kzalloc(sizeof(*op), GFP_NOFS); if (!op) { rv = -ENOMEM; goto out; } /* cause the vfs unlock to return ENOENT if lock is not found */ fl->c.flc_flags |= FL_EXISTS; rv = locks_lock_file_wait(file, fl); if (rv == -ENOENT) { rv = 0; goto out_free; } if (rv < 0) { log_error(ls, "dlm_posix_unlock: vfs unlock error %d %llx", rv, (unsigned long long)number); } op->info.optype = DLM_PLOCK_OP_UNLOCK; op->info.pid = fl->c.flc_pid; op->info.fsid = ls->ls_global_id; op->info.number = number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; op->info.owner = (__u64)(long) fl->c.flc_owner; if (fl->c.flc_flags & FL_CLOSE) { op->info.flags |= DLM_PLOCK_FL_CLOSE; send_op(op); rv = 0; goto out; } send_op(op); wait_event(recv_wq, (op->done != 0)); WARN_ON(!list_empty(&op->list)); rv = op->info.rv; if (rv == -ENOENT) rv = 0; out_free: dlm_release_plock_op(op); out: dlm_put_lockspace(ls); fl->c.flc_flags = saved_flags; return rv; } EXPORT_SYMBOL_GPL(dlm_posix_unlock); /* * NOTE: This implementation can only handle async lock requests as nfs * do it. It cannot handle cancellation of a pending lock request sitting * in wait_event(), but for now only nfs is the only user local kernel * user. */ int dlm_posix_cancel(dlm_lockspace_t *lockspace, u64 number, struct file *file, struct file_lock *fl) { struct dlm_plock_info info; struct plock_op *op; struct dlm_ls *ls; int rv; /* this only works for async request for now and nfs is the only * kernel user right now. */ if (WARN_ON_ONCE(!fl->fl_lmops || !fl->fl_lmops->lm_grant)) return -EOPNOTSUPP; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; memset(&info, 0, sizeof(info)); info.pid = fl->c.flc_pid; info.ex = lock_is_write(fl); info.fsid = ls->ls_global_id; dlm_put_lockspace(ls); info.number = number; info.start = fl->fl_start; info.end = fl->fl_end; info.owner = (__u64)(long) fl->c.flc_owner; rv = do_lock_cancel(&info); switch (rv) { case 0: spin_lock(&ops_lock); /* lock request to cancel must be on recv_list because * do_lock_cancel() synchronizes it. */ op = plock_lookup_waiter(&info); if (WARN_ON_ONCE(!op)) { spin_unlock(&ops_lock); rv = -ENOLCK; break; } list_del(&op->list); spin_unlock(&ops_lock); WARN_ON(op->info.optype != DLM_PLOCK_OP_LOCK); op->data->callback(op->data->fl, -EINTR); dlm_release_plock_op(op); rv = -EINTR; break; case -ENOENT: /* if cancel wasn't successful we probably were to late * or it was a non-blocking lock request, so just unlock it. */ rv = dlm_posix_unlock(lockspace, number, file, fl); break; default: break; } return rv; } EXPORT_SYMBOL_GPL(dlm_posix_cancel); int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file, struct file_lock *fl) { struct dlm_ls *ls; struct plock_op *op; int rv; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; op = kzalloc(sizeof(*op), GFP_NOFS); if (!op) { rv = -ENOMEM; goto out; } op->info.optype = DLM_PLOCK_OP_GET; op->info.pid = fl->c.flc_pid; op->info.ex = lock_is_write(fl); op->info.fsid = ls->ls_global_id; op->info.number = number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; op->info.owner = (__u64)(long) fl->c.flc_owner; send_op(op); wait_event(recv_wq, (op->done != 0)); WARN_ON(!list_empty(&op->list)); /* info.rv from userspace is 1 for conflict, 0 for no-conflict, -ENOENT if there are no locks on the file */ rv = op->info.rv; fl->c.flc_type = F_UNLCK; if (rv == -ENOENT) rv = 0; else if (rv > 0) { locks_init_lock(fl); fl->c.flc_type = (op->info.ex) ? F_WRLCK : F_RDLCK; fl->c.flc_flags = FL_POSIX; fl->c.flc_pid = op->info.pid; if (op->info.nodeid != dlm_our_nodeid()) fl->c.flc_pid = -fl->c.flc_pid; fl->fl_start = op->info.start; fl->fl_end = op->info.end; rv = 0; } dlm_release_plock_op(op); out: dlm_put_lockspace(ls); return rv; } EXPORT_SYMBOL_GPL(dlm_posix_get); /* a read copies out one plock request from the send list */ static ssize_t dev_read(struct file *file, char __user *u, size_t count, loff_t *ppos) { struct dlm_plock_info info; struct plock_op *op = NULL; if (count < sizeof(info)) return -EINVAL; spin_lock(&ops_lock); if (!list_empty(&send_list)) { op = list_first_entry(&send_list, struct plock_op, list); if (op->info.flags & DLM_PLOCK_FL_CLOSE) list_del(&op->list); else list_move_tail(&op->list, &recv_list); memcpy(&info, &op->info, sizeof(info)); } spin_unlock(&ops_lock); if (!op) return -EAGAIN; trace_dlm_plock_read(&info); /* there is no need to get a reply from userspace for unlocks that were generated by the vfs cleaning up for a close (the process did not make an unlock call). */ if (op->info.flags & DLM_PLOCK_FL_CLOSE) dlm_release_plock_op(op); if (copy_to_user(u, &info, sizeof(info))) return -EFAULT; return sizeof(info); } /* a write copies in one plock result that should match a plock_op on the recv list */ static ssize_t dev_write(struct file *file, const char __user *u, size_t count, loff_t *ppos) { struct plock_op *op = NULL, *iter; struct dlm_plock_info info; int do_callback = 0; if (count != sizeof(info)) return -EINVAL; if (copy_from_user(&info, u, sizeof(info))) return -EFAULT; trace_dlm_plock_write(&info); if (check_version(&info)) return -EINVAL; /* * The results for waiting ops (SETLKW) can be returned in any * order, so match all fields to find the op. The results for * non-waiting ops are returned in the order that they were sent * to userspace, so match the result with the first non-waiting op. */ spin_lock(&ops_lock); if (info.wait) { op = plock_lookup_waiter(&info); } else { list_for_each_entry(iter, &recv_list, list) { if (!iter->info.wait && iter->info.fsid == info.fsid) { op = iter; break; } } } if (op) { /* Sanity check that op and info match. */ if (info.wait) WARN_ON(op->info.optype != DLM_PLOCK_OP_LOCK); else WARN_ON(op->info.number != info.number || op->info.owner != info.owner || op->info.optype != info.optype); list_del_init(&op->list); memcpy(&op->info, &info, sizeof(info)); if (op->data) do_callback = 1; else op->done = 1; } spin_unlock(&ops_lock); if (op) { if (do_callback) dlm_plock_callback(op); else wake_up(&recv_wq); } else pr_debug("%s: no op %x %llx", __func__, info.fsid, (unsigned long long)info.number); return count; } static __poll_t dev_poll(struct file *file, poll_table *wait) { __poll_t mask = 0; poll_wait(file, &send_wq, wait); spin_lock(&ops_lock); if (!list_empty(&send_list)) mask = EPOLLIN | EPOLLRDNORM; spin_unlock(&ops_lock); return mask; } static const struct file_operations dev_fops = { .read = dev_read, .write = dev_write, .poll = dev_poll, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice plock_dev_misc = { .minor = MISC_DYNAMIC_MINOR, .name = DLM_PLOCK_MISC_NAME, .fops = &dev_fops }; int dlm_plock_init(void) { int rv; rv = misc_register(&plock_dev_misc); if (rv) log_print("dlm_plock_init: misc_register failed %d", rv); return rv; } void dlm_plock_exit(void) { misc_deregister(&plock_dev_misc); WARN_ON(!list_empty(&send_list)); WARN_ON(!list_empty(&recv_list)); } |
| 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. */ /* * Quota change tags are associated with each transaction that allocates or * deallocates space. Those changes are accumulated locally to each node (in a * per-node file) and then are periodically synced to the quota file. This * avoids the bottleneck of constantly touching the quota file, but introduces * fuzziness in the current usage value of IDs that are being used on different * nodes in the cluster simultaneously. So, it is possible for a user on * multiple nodes to overrun their quota, but that overrun is controlable. * Since quota tags are part of transactions, there is no need for a quota check * program to be run on node crashes or anything like that. * * There are couple of knobs that let the administrator manage the quota * fuzziness. "quota_quantum" sets the maximum time a quota change can be * sitting on one node before being synced to the quota file. (The default is * 60 seconds.) Another knob, "quota_scale" controls how quickly the frequency * of quota file syncs increases as the user moves closer to their limit. The * more frequent the syncs, the more accurate the quota enforcement, but that * means that there is more contention between the nodes for the quota file. * The default value is one. This sets the maximum theoretical quota overrun * (with infinite node with infinite bandwidth) to twice the user's limit. (In * practice, the maximum overrun you see should be much less.) A "quota_scale" * number greater than one makes quota syncs more frequent and reduces the * maximum overrun. Numbers less than one (but greater than zero) make quota * syncs less frequent. * * GFS quotas also use per-ID Lock Value Blocks (LVBs) to cache the contents of * the quota file, so it is not being constantly read. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/sched.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/sort.h> #include <linux/fs.h> #include <linux/bio.h> #include <linux/gfs2_ondisk.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/quota.h> #include <linux/dqblk_xfs.h> #include <linux/lockref.h> #include <linux/list_lru.h> #include <linux/rcupdate.h> #include <linux/rculist_bl.h> #include <linux/bit_spinlock.h> #include <linux/jhash.h> #include <linux/vmalloc.h> #include "gfs2.h" #include "incore.h" #include "bmap.h" #include "glock.h" #include "glops.h" #include "log.h" #include "meta_io.h" #include "quota.h" #include "rgrp.h" #include "super.h" #include "trans.h" #include "inode.h" #include "util.h" #define GFS2_QD_HASH_SHIFT 12 #define GFS2_QD_HASH_SIZE BIT(GFS2_QD_HASH_SHIFT) #define GFS2_QD_HASH_MASK (GFS2_QD_HASH_SIZE - 1) /* Lock order: qd_lock -> bucket lock -> qd->lockref.lock -> lru lock */ /* -> sd_bitmap_lock */ static DEFINE_SPINLOCK(qd_lock); struct list_lru gfs2_qd_lru; static struct hlist_bl_head qd_hash_table[GFS2_QD_HASH_SIZE]; static unsigned int gfs2_qd_hash(const struct gfs2_sbd *sdp, const struct kqid qid) { unsigned int h; h = jhash(&sdp, sizeof(struct gfs2_sbd *), 0); h = jhash(&qid, sizeof(struct kqid), h); return h & GFS2_QD_HASH_MASK; } static inline void spin_lock_bucket(unsigned int hash) { hlist_bl_lock(&qd_hash_table[hash]); } static inline void spin_unlock_bucket(unsigned int hash) { hlist_bl_unlock(&qd_hash_table[hash]); } static void gfs2_qd_dealloc(struct rcu_head *rcu) { struct gfs2_quota_data *qd = container_of(rcu, struct gfs2_quota_data, qd_rcu); struct gfs2_sbd *sdp = qd->qd_sbd; kmem_cache_free(gfs2_quotad_cachep, qd); if (atomic_dec_and_test(&sdp->sd_quota_count)) wake_up(&sdp->sd_kill_wait); } static void gfs2_qd_dispose(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; spin_lock(&qd_lock); list_del(&qd->qd_list); spin_unlock(&qd_lock); spin_lock_bucket(qd->qd_hash); hlist_bl_del_rcu(&qd->qd_hlist); spin_unlock_bucket(qd->qd_hash); if (!gfs2_withdrawing_or_withdrawn(sdp)) { gfs2_assert_warn(sdp, !qd->qd_change); gfs2_assert_warn(sdp, !qd->qd_slot_ref); gfs2_assert_warn(sdp, !qd->qd_bh_count); } gfs2_glock_put(qd->qd_gl); call_rcu(&qd->qd_rcu, gfs2_qd_dealloc); } static void gfs2_qd_list_dispose(struct list_head *list) { struct gfs2_quota_data *qd; while (!list_empty(list)) { qd = list_first_entry(list, struct gfs2_quota_data, qd_lru); list_del(&qd->qd_lru); gfs2_qd_dispose(qd); } } static enum lru_status gfs2_qd_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *dispose = arg; struct gfs2_quota_data *qd = list_entry(item, struct gfs2_quota_data, qd_lru); enum lru_status status; if (!spin_trylock(&qd->qd_lockref.lock)) return LRU_SKIP; status = LRU_SKIP; if (qd->qd_lockref.count == 0) { lockref_mark_dead(&qd->qd_lockref); list_lru_isolate_move(lru, &qd->qd_lru, dispose); status = LRU_REMOVED; } spin_unlock(&qd->qd_lockref.lock); return status; } static unsigned long gfs2_qd_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(dispose); unsigned long freed; if (!(sc->gfp_mask & __GFP_FS)) return SHRINK_STOP; freed = list_lru_shrink_walk(&gfs2_qd_lru, sc, gfs2_qd_isolate, &dispose); gfs2_qd_list_dispose(&dispose); return freed; } static unsigned long gfs2_qd_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { return vfs_pressure_ratio(list_lru_shrink_count(&gfs2_qd_lru, sc)); } static struct shrinker *gfs2_qd_shrinker; int __init gfs2_qd_shrinker_init(void) { gfs2_qd_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE, "gfs2-qd"); if (!gfs2_qd_shrinker) return -ENOMEM; gfs2_qd_shrinker->count_objects = gfs2_qd_shrink_count; gfs2_qd_shrinker->scan_objects = gfs2_qd_shrink_scan; shrinker_register(gfs2_qd_shrinker); return 0; } void gfs2_qd_shrinker_exit(void) { shrinker_free(gfs2_qd_shrinker); } static u64 qd2index(struct gfs2_quota_data *qd) { struct kqid qid = qd->qd_id; return (2 * (u64)from_kqid(&init_user_ns, qid)) + ((qid.type == USRQUOTA) ? 0 : 1); } static u64 qd2offset(struct gfs2_quota_data *qd) { return qd2index(qd) * sizeof(struct gfs2_quota); } static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, struct kqid qid) { struct gfs2_quota_data *qd; int error; qd = kmem_cache_zalloc(gfs2_quotad_cachep, GFP_NOFS); if (!qd) return NULL; qd->qd_sbd = sdp; lockref_init(&qd->qd_lockref); qd->qd_id = qid; qd->qd_slot = -1; INIT_LIST_HEAD(&qd->qd_lru); qd->qd_hash = hash; error = gfs2_glock_get(sdp, qd2index(qd), &gfs2_quota_glops, CREATE, &qd->qd_gl); if (error) goto fail; return qd; fail: kmem_cache_free(gfs2_quotad_cachep, qd); return NULL; } static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash, const struct gfs2_sbd *sdp, struct kqid qid) { struct gfs2_quota_data *qd; struct hlist_bl_node *h; hlist_bl_for_each_entry_rcu(qd, h, &qd_hash_table[hash], qd_hlist) { if (!qid_eq(qd->qd_id, qid)) continue; if (qd->qd_sbd != sdp) continue; if (lockref_get_not_dead(&qd->qd_lockref)) { list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru); return qd; } } return NULL; } static int qd_get(struct gfs2_sbd *sdp, struct kqid qid, struct gfs2_quota_data **qdp) { struct gfs2_quota_data *qd, *new_qd; unsigned int hash = gfs2_qd_hash(sdp, qid); rcu_read_lock(); *qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid); rcu_read_unlock(); if (qd) return 0; new_qd = qd_alloc(hash, sdp, qid); if (!new_qd) return -ENOMEM; spin_lock(&qd_lock); spin_lock_bucket(hash); *qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid); if (qd == NULL) { *qdp = new_qd; list_add(&new_qd->qd_list, &sdp->sd_quota_list); hlist_bl_add_head_rcu(&new_qd->qd_hlist, &qd_hash_table[hash]); atomic_inc(&sdp->sd_quota_count); } spin_unlock_bucket(hash); spin_unlock(&qd_lock); if (qd) { gfs2_glock_put(new_qd->qd_gl); kmem_cache_free(gfs2_quotad_cachep, new_qd); } return 0; } static void __qd_hold(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; gfs2_assert(sdp, qd->qd_lockref.count > 0); qd->qd_lockref.count++; } static void qd_put(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp; if (lockref_put_or_lock(&qd->qd_lockref)) return; BUG_ON(__lockref_is_dead(&qd->qd_lockref)); sdp = qd->qd_sbd; if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) { lockref_mark_dead(&qd->qd_lockref); spin_unlock(&qd->qd_lockref.lock); gfs2_qd_dispose(qd); return; } qd->qd_lockref.count = 0; list_lru_add_obj(&gfs2_qd_lru, &qd->qd_lru); spin_unlock(&qd->qd_lockref.lock); } static int slot_get(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; unsigned int bit; int error = 0; spin_lock(&sdp->sd_bitmap_lock); if (qd->qd_slot_ref == 0) { bit = find_first_zero_bit(sdp->sd_quota_bitmap, sdp->sd_quota_slots); if (bit >= sdp->sd_quota_slots) { error = -ENOSPC; goto out; } set_bit(bit, sdp->sd_quota_bitmap); qd->qd_slot = bit; } qd->qd_slot_ref++; out: spin_unlock(&sdp->sd_bitmap_lock); return error; } static void slot_hold(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; spin_lock(&sdp->sd_bitmap_lock); gfs2_assert(sdp, qd->qd_slot_ref); qd->qd_slot_ref++; spin_unlock(&sdp->sd_bitmap_lock); } static void slot_put(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; spin_lock(&sdp->sd_bitmap_lock); gfs2_assert(sdp, qd->qd_slot_ref); if (!--qd->qd_slot_ref) { BUG_ON(!test_and_clear_bit(qd->qd_slot, sdp->sd_quota_bitmap)); qd->qd_slot = -1; } spin_unlock(&sdp->sd_bitmap_lock); } static int bh_get(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; struct inode *inode = sdp->sd_qc_inode; struct gfs2_inode *ip = GFS2_I(inode); unsigned int block, offset; struct buffer_head *bh = NULL; struct iomap iomap = { }; int error; spin_lock(&qd->qd_lockref.lock); if (qd->qd_bh_count) { qd->qd_bh_count++; spin_unlock(&qd->qd_lockref.lock); return 0; } spin_unlock(&qd->qd_lockref.lock); block = qd->qd_slot / sdp->sd_qc_per_block; offset = qd->qd_slot % sdp->sd_qc_per_block; error = gfs2_iomap_get(inode, (loff_t)block << inode->i_blkbits, i_blocksize(inode), &iomap); if (error) return error; error = -ENOENT; if (iomap.type != IOMAP_MAPPED) return error; error = gfs2_meta_read(ip->i_gl, iomap.addr >> inode->i_blkbits, DIO_WAIT, 0, &bh); if (error) return error; error = -EIO; if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_QC)) goto out; spin_lock(&qd->qd_lockref.lock); if (qd->qd_bh == NULL) { qd->qd_bh = bh; qd->qd_bh_qc = (struct gfs2_quota_change *) (bh->b_data + sizeof(struct gfs2_meta_header) + offset * sizeof(struct gfs2_quota_change)); bh = NULL; } qd->qd_bh_count++; spin_unlock(&qd->qd_lockref.lock); error = 0; out: brelse(bh); return error; } static void bh_put(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; struct buffer_head *bh = NULL; spin_lock(&qd->qd_lockref.lock); gfs2_assert(sdp, qd->qd_bh_count); if (!--qd->qd_bh_count) { bh = qd->qd_bh; qd->qd_bh = NULL; qd->qd_bh_qc = NULL; } spin_unlock(&qd->qd_lockref.lock); brelse(bh); } static bool qd_grab_sync(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd, u64 sync_gen) { bool ret = false; spin_lock(&qd->qd_lockref.lock); if (test_bit(QDF_LOCKED, &qd->qd_flags) || !test_bit(QDF_CHANGE, &qd->qd_flags) || qd->qd_sync_gen >= sync_gen) goto out; if (__lockref_is_dead(&qd->qd_lockref)) goto out; qd->qd_lockref.count++; list_move_tail(&qd->qd_list, &sdp->sd_quota_list); set_bit(QDF_LOCKED, &qd->qd_flags); qd->qd_change_sync = qd->qd_change; slot_hold(qd); ret = true; out: spin_unlock(&qd->qd_lockref.lock); return ret; } static void qd_ungrab_sync(struct gfs2_quota_data *qd) { clear_bit(QDF_LOCKED, &qd->qd_flags); slot_put(qd); qd_put(qd); } static void qdsb_put(struct gfs2_quota_data *qd) { bh_put(qd); slot_put(qd); qd_put(qd); } static void qd_unlock(struct gfs2_quota_data *qd) { spin_lock(&qd->qd_lockref.lock); gfs2_assert_warn(qd->qd_sbd, test_bit(QDF_LOCKED, &qd->qd_flags)); clear_bit(QDF_LOCKED, &qd->qd_flags); spin_unlock(&qd->qd_lockref.lock); qdsb_put(qd); } static int qdsb_get(struct gfs2_sbd *sdp, struct kqid qid, struct gfs2_quota_data **qdp) { int error; error = qd_get(sdp, qid, qdp); if (error) return error; error = slot_get(*qdp); if (error) goto fail; error = bh_get(*qdp); if (error) goto fail_slot; return 0; fail_slot: slot_put(*qdp); fail: qd_put(*qdp); return error; } /** * gfs2_qa_get - make sure we have a quota allocations data structure, * if necessary * @ip: the inode for this reservation */ int gfs2_qa_get(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct inode *inode = &ip->i_inode; if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; spin_lock(&inode->i_lock); if (ip->i_qadata == NULL) { struct gfs2_qadata *tmp; spin_unlock(&inode->i_lock); tmp = kmem_cache_zalloc(gfs2_qadata_cachep, GFP_NOFS); if (!tmp) return -ENOMEM; spin_lock(&inode->i_lock); if (ip->i_qadata == NULL) ip->i_qadata = tmp; else kmem_cache_free(gfs2_qadata_cachep, tmp); } ip->i_qadata->qa_ref++; spin_unlock(&inode->i_lock); return 0; } void gfs2_qa_put(struct gfs2_inode *ip) { struct inode *inode = &ip->i_inode; spin_lock(&inode->i_lock); if (ip->i_qadata && --ip->i_qadata->qa_ref == 0) { kmem_cache_free(gfs2_qadata_cachep, ip->i_qadata); ip->i_qadata = NULL; } spin_unlock(&inode->i_lock); } int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data **qd; int error; if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; error = gfs2_qa_get(ip); if (error) return error; qd = ip->i_qadata->qa_qd; if (gfs2_assert_warn(sdp, !ip->i_qadata->qa_qd_num) || gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags))) { error = -EIO; gfs2_qa_put(ip); goto out; } error = qdsb_get(sdp, make_kqid_uid(ip->i_inode.i_uid), qd); if (error) goto out_unhold; ip->i_qadata->qa_qd_num++; qd++; error = qdsb_get(sdp, make_kqid_gid(ip->i_inode.i_gid), qd); if (error) goto out_unhold; ip->i_qadata->qa_qd_num++; qd++; if (!uid_eq(uid, NO_UID_QUOTA_CHANGE) && !uid_eq(uid, ip->i_inode.i_uid)) { error = qdsb_get(sdp, make_kqid_uid(uid), qd); if (error) goto out_unhold; ip->i_qadata->qa_qd_num++; qd++; } if (!gid_eq(gid, NO_GID_QUOTA_CHANGE) && !gid_eq(gid, ip->i_inode.i_gid)) { error = qdsb_get(sdp, make_kqid_gid(gid), qd); if (error) goto out_unhold; ip->i_qadata->qa_qd_num++; qd++; } out_unhold: if (error) gfs2_quota_unhold(ip); out: return error; } void gfs2_quota_unhold(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); u32 x; if (ip->i_qadata == NULL) return; gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)); for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qdsb_put(ip->i_qadata->qa_qd[x]); ip->i_qadata->qa_qd[x] = NULL; } ip->i_qadata->qa_qd_num = 0; gfs2_qa_put(ip); } static int sort_qd(const void *a, const void *b) { const struct gfs2_quota_data *qd_a = *(const struct gfs2_quota_data **)a; const struct gfs2_quota_data *qd_b = *(const struct gfs2_quota_data **)b; if (qid_lt(qd_a->qd_id, qd_b->qd_id)) return -1; if (qid_lt(qd_b->qd_id, qd_a->qd_id)) return 1; return 0; } static void do_qc(struct gfs2_quota_data *qd, s64 change) { struct gfs2_sbd *sdp = qd->qd_sbd; struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode); struct gfs2_quota_change *qc = qd->qd_bh_qc; bool needs_put = false; s64 x; gfs2_trans_add_meta(ip->i_gl, qd->qd_bh); /* * The QDF_CHANGE flag indicates that the slot in the quota change file * is used. Here, we use the value of qc->qc_change when the slot is * used, and we assume a value of 0 otherwise. */ spin_lock(&qd->qd_lockref.lock); x = 0; if (test_bit(QDF_CHANGE, &qd->qd_flags)) x = be64_to_cpu(qc->qc_change); x += change; qd->qd_change += change; if (!x && test_bit(QDF_CHANGE, &qd->qd_flags)) { /* The slot in the quota change file becomes unused. */ clear_bit(QDF_CHANGE, &qd->qd_flags); qc->qc_flags = 0; qc->qc_id = 0; needs_put = true; } else if (x && !test_bit(QDF_CHANGE, &qd->qd_flags)) { /* The slot in the quota change file becomes used. */ set_bit(QDF_CHANGE, &qd->qd_flags); __qd_hold(qd); slot_hold(qd); qc->qc_flags = 0; if (qd->qd_id.type == USRQUOTA) qc->qc_flags = cpu_to_be32(GFS2_QCF_USER); qc->qc_id = cpu_to_be32(from_kqid(&init_user_ns, qd->qd_id)); } qc->qc_change = cpu_to_be64(x); spin_unlock(&qd->qd_lockref.lock); if (needs_put) { slot_put(qd); qd_put(qd); } if (change < 0) /* Reset quiet flag if we freed some blocks */ clear_bit(QDF_QMSG_QUIET, &qd->qd_flags); } static int gfs2_write_buf_to_page(struct gfs2_sbd *sdp, unsigned long index, unsigned off, void *buf, unsigned bytes) { struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct inode *inode = &ip->i_inode; struct address_space *mapping = inode->i_mapping; struct folio *folio; struct buffer_head *bh; u64 blk; unsigned bsize = sdp->sd_sb.sb_bsize, bnum = 0, boff = 0; unsigned to_write = bytes, pg_off = off; blk = index << (PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift); boff = off % bsize; folio = filemap_grab_folio(mapping, index); if (IS_ERR(folio)) return PTR_ERR(folio); bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, bsize, 0); for (;;) { /* Find the beginning block within the folio */ if (pg_off >= ((bnum * bsize) + bsize)) { bh = bh->b_this_page; bnum++; blk++; continue; } if (!buffer_mapped(bh)) { gfs2_block_map(inode, blk, bh, 1); if (!buffer_mapped(bh)) goto unlock_out; /* If it's a newly allocated disk block, zero it */ if (buffer_new(bh)) folio_zero_range(folio, bnum * bsize, bh->b_size); } if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); if (bh_read(bh, REQ_META | REQ_PRIO) < 0) goto unlock_out; gfs2_trans_add_data(ip->i_gl, bh); /* If we need to write to the next block as well */ if (to_write > (bsize - boff)) { pg_off += (bsize - boff); to_write -= (bsize - boff); boff = pg_off % bsize; continue; } break; } /* Write to the folio, now that we have setup the buffer(s) */ memcpy_to_folio(folio, off, buf, bytes); flush_dcache_folio(folio); folio_unlock(folio); folio_put(folio); return 0; unlock_out: folio_unlock(folio); folio_put(folio); return -EIO; } static int gfs2_write_disk_quota(struct gfs2_sbd *sdp, struct gfs2_quota *qp, loff_t loc) { unsigned long pg_beg; unsigned pg_off, nbytes, overflow = 0; int error; void *ptr; nbytes = sizeof(struct gfs2_quota); pg_beg = loc >> PAGE_SHIFT; pg_off = offset_in_page(loc); /* If the quota straddles a page boundary, split the write in two */ if ((pg_off + nbytes) > PAGE_SIZE) overflow = (pg_off + nbytes) - PAGE_SIZE; ptr = qp; error = gfs2_write_buf_to_page(sdp, pg_beg, pg_off, ptr, nbytes - overflow); /* If there's an overflow, write the remaining bytes to the next page */ if (!error && overflow) error = gfs2_write_buf_to_page(sdp, pg_beg + 1, 0, ptr + nbytes - overflow, overflow); return error; } /** * gfs2_adjust_quota - adjust record of current block usage * @sdp: The superblock * @loc: Offset of the entry in the quota file * @change: The amount of usage change to record * @qd: The quota data * @fdq: The updated limits to record * * This function was mostly borrowed from gfs2_block_truncate_page which was * in turn mostly borrowed from ext3 * * Returns: 0 or -ve on error */ static int gfs2_adjust_quota(struct gfs2_sbd *sdp, loff_t loc, s64 change, struct gfs2_quota_data *qd, struct qc_dqblk *fdq) { struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct inode *inode = &ip->i_inode; struct gfs2_quota q; int err; u64 size; if (gfs2_is_stuffed(ip)) { err = gfs2_unstuff_dinode(ip); if (err) return err; } memset(&q, 0, sizeof(struct gfs2_quota)); err = gfs2_internal_read(ip, (char *)&q, &loc, sizeof(q)); if (err < 0) return err; loc -= sizeof(q); /* gfs2_internal_read would've advanced the loc ptr */ be64_add_cpu(&q.qu_value, change); if (((s64)be64_to_cpu(q.qu_value)) < 0) q.qu_value = 0; /* Never go negative on quota usage */ spin_lock(&qd->qd_lockref.lock); qd->qd_qb.qb_value = q.qu_value; if (fdq) { if (fdq->d_fieldmask & QC_SPC_SOFT) { q.qu_warn = cpu_to_be64(fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_warn = q.qu_warn; } if (fdq->d_fieldmask & QC_SPC_HARD) { q.qu_limit = cpu_to_be64(fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_limit = q.qu_limit; } if (fdq->d_fieldmask & QC_SPACE) { q.qu_value = cpu_to_be64(fdq->d_space >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_value = q.qu_value; } } spin_unlock(&qd->qd_lockref.lock); err = gfs2_write_disk_quota(sdp, &q, loc); if (!err) { size = loc + sizeof(struct gfs2_quota); if (size > inode->i_size) i_size_write(inode, size); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); mark_inode_dirty(inode); set_bit(QDF_REFRESH, &qd->qd_flags); } return err; } static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda, u64 sync_gen) { struct gfs2_sbd *sdp = (*qda)->qd_sbd; struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct gfs2_alloc_parms ap = {}; unsigned int data_blocks, ind_blocks; struct gfs2_holder *ghs, i_gh; unsigned int qx, x; struct gfs2_quota_data *qd; unsigned reserved; loff_t offset; unsigned int nalloc = 0, blocks; int error; gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota), &data_blocks, &ind_blocks); ghs = kmalloc_array(num_qd, sizeof(struct gfs2_holder), GFP_NOFS); if (!ghs) return -ENOMEM; sort(qda, num_qd, sizeof(struct gfs2_quota_data *), sort_qd, NULL); inode_lock(&ip->i_inode); for (qx = 0; qx < num_qd; qx++) { error = gfs2_glock_nq_init(qda[qx]->qd_gl, LM_ST_EXCLUSIVE, GL_NOCACHE, &ghs[qx]); if (error) goto out_dq; } error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh); if (error) goto out_dq; for (x = 0; x < num_qd; x++) { offset = qd2offset(qda[x]); if (gfs2_write_alloc_required(ip, offset, sizeof(struct gfs2_quota))) nalloc++; } /* * 1 blk for unstuffing inode if stuffed. We add this extra * block to the reservation unconditionally. If the inode * doesn't need unstuffing, the block will be released to the * rgrp since it won't be allocated during the transaction */ /* +3 in the end for unstuffing block, inode size update block * and another block in case quota straddles page boundary and * two blocks need to be updated instead of 1 */ blocks = num_qd * data_blocks + RES_DINODE + num_qd + 3; reserved = 1 + (nalloc * (data_blocks + ind_blocks)); ap.target = reserved; error = gfs2_inplace_reserve(ip, &ap); if (error) goto out_alloc; if (nalloc) blocks += gfs2_rg_blocks(ip, reserved) + nalloc * ind_blocks + RES_STATFS; error = gfs2_trans_begin(sdp, blocks, 0); if (error) goto out_ipres; for (x = 0; x < num_qd; x++) { qd = qda[x]; offset = qd2offset(qd); error = gfs2_adjust_quota(sdp, offset, qd->qd_change_sync, qd, NULL); if (error) goto out_end_trans; do_qc(qd, -qd->qd_change_sync); set_bit(QDF_REFRESH, &qd->qd_flags); } out_end_trans: gfs2_trans_end(sdp); out_ipres: gfs2_inplace_release(ip); out_alloc: gfs2_glock_dq_uninit(&i_gh); out_dq: while (qx--) gfs2_glock_dq_uninit(&ghs[qx]); inode_unlock(&ip->i_inode); kfree(ghs); gfs2_log_flush(ip->i_gl->gl_name.ln_sbd, ip->i_gl, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_DO_SYNC); if (!error) { for (x = 0; x < num_qd; x++) { qd = qda[x]; spin_lock(&qd->qd_lockref.lock); if (qd->qd_sync_gen < sync_gen) qd->qd_sync_gen = sync_gen; spin_unlock(&qd->qd_lockref.lock); } } return error; } static int update_qd(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd) { struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct gfs2_quota q; struct gfs2_quota_lvb *qlvb; loff_t pos; int error; memset(&q, 0, sizeof(struct gfs2_quota)); pos = qd2offset(qd); error = gfs2_internal_read(ip, (char *)&q, &pos, sizeof(q)); if (error < 0) return error; qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; qlvb->qb_magic = cpu_to_be32(GFS2_MAGIC); qlvb->__pad = 0; qlvb->qb_limit = q.qu_limit; qlvb->qb_warn = q.qu_warn; qlvb->qb_value = q.qu_value; spin_lock(&qd->qd_lockref.lock); qd->qd_qb = *qlvb; spin_unlock(&qd->qd_lockref.lock); return 0; } static int do_glock(struct gfs2_quota_data *qd, int force_refresh, struct gfs2_holder *q_gh) { struct gfs2_sbd *sdp = qd->qd_sbd; struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct gfs2_holder i_gh; int error; gfs2_assert_warn(sdp, sdp == qd->qd_gl->gl_name.ln_sbd); restart: error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_SHARED, 0, q_gh); if (error) return error; if (test_and_clear_bit(QDF_REFRESH, &qd->qd_flags)) force_refresh = FORCE; spin_lock(&qd->qd_lockref.lock); qd->qd_qb = *(struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; spin_unlock(&qd->qd_lockref.lock); if (force_refresh || qd->qd_qb.qb_magic != cpu_to_be32(GFS2_MAGIC)) { gfs2_glock_dq_uninit(q_gh); error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE, GL_NOCACHE, q_gh); if (error) return error; error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); if (error) goto fail; error = update_qd(sdp, qd); if (error) goto fail_gunlock; gfs2_glock_dq_uninit(&i_gh); gfs2_glock_dq_uninit(q_gh); force_refresh = 0; goto restart; } return 0; fail_gunlock: gfs2_glock_dq_uninit(&i_gh); fail: gfs2_glock_dq_uninit(q_gh); return error; } int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qd; u32 x; int error; if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; error = gfs2_quota_hold(ip, uid, gid); if (error) return error; sort(ip->i_qadata->qa_qd, ip->i_qadata->qa_qd_num, sizeof(struct gfs2_quota_data *), sort_qd, NULL); for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; error = do_glock(qd, NO_FORCE, &ip->i_qadata->qa_qd_ghs[x]); if (error) break; } if (!error) set_bit(GIF_QD_LOCKED, &ip->i_flags); else { while (x--) gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]); gfs2_quota_unhold(ip); } return error; } static bool need_sync(struct gfs2_quota_data *qd) { struct gfs2_sbd *sdp = qd->qd_sbd; struct gfs2_tune *gt = &sdp->sd_tune; s64 value, change, limit; unsigned int num, den; int ret = false; spin_lock(&qd->qd_lockref.lock); if (!qd->qd_qb.qb_limit) goto out; change = qd->qd_change; if (change <= 0) goto out; value = (s64)be64_to_cpu(qd->qd_qb.qb_value); limit = (s64)be64_to_cpu(qd->qd_qb.qb_limit); if (value >= limit) goto out; spin_lock(>->gt_spin); num = gt->gt_quota_scale_num; den = gt->gt_quota_scale_den; spin_unlock(>->gt_spin); change *= gfs2_jindex_size(sdp) * num; change = div_s64(change, den); if (value + change < limit) goto out; ret = true; out: spin_unlock(&qd->qd_lockref.lock); return ret; } void gfs2_quota_unlock(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qda[2 * GFS2_MAXQUOTAS]; unsigned int count = 0; u32 x; if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags)) return; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { struct gfs2_quota_data *qd; bool sync; int error; qd = ip->i_qadata->qa_qd[x]; sync = need_sync(qd); gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]); if (!sync) continue; spin_lock(&qd_lock); sync = qd_grab_sync(sdp, qd, U64_MAX); spin_unlock(&qd_lock); if (!sync) continue; gfs2_assert_warn(sdp, qd->qd_change_sync); error = bh_get(qd); if (error) { qd_ungrab_sync(qd); continue; } qda[count++] = qd; } if (count) { u64 sync_gen = READ_ONCE(sdp->sd_quota_sync_gen); do_sync(count, qda, sync_gen); for (x = 0; x < count; x++) qd_unlock(qda[x]); } gfs2_quota_unhold(ip); } #define MAX_LINE 256 static void print_message(struct gfs2_quota_data *qd, char *type) { struct gfs2_sbd *sdp = qd->qd_sbd; if (sdp->sd_args.ar_quota != GFS2_QUOTA_QUIET) { fs_info(sdp, "quota %s for %s %u\n", type, (qd->qd_id.type == USRQUOTA) ? "user" : "group", from_kqid(&init_user_ns, qd->qd_id)); } } /** * gfs2_quota_check - check if allocating new blocks will exceed quota * @ip: The inode for which this check is being performed * @uid: The uid to check against * @gid: The gid to check against * @ap: The allocation parameters. ap->target contains the requested * blocks. ap->min_target, if set, contains the minimum blks * requested. * * Returns: 0 on success. * min_req = ap->min_target ? ap->min_target : ap->target; * quota must allow at least min_req blks for success and * ap->allowed is set to the number of blocks allowed * * -EDQUOT otherwise, quota violation. ap->allowed is set to number * of blocks available. */ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, struct gfs2_alloc_parms *ap) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_quota_data *qd; s64 value, warn, limit; u32 x; int error = 0; ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ if (!test_bit(GIF_QD_LOCKED, &ip->i_flags)) return 0; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; if (!(qid_eq(qd->qd_id, make_kqid_uid(uid)) || qid_eq(qd->qd_id, make_kqid_gid(gid)))) continue; spin_lock(&qd->qd_lockref.lock); warn = (s64)be64_to_cpu(qd->qd_qb.qb_warn); limit = (s64)be64_to_cpu(qd->qd_qb.qb_limit); value = (s64)be64_to_cpu(qd->qd_qb.qb_value); value += qd->qd_change; spin_unlock(&qd->qd_lockref.lock); if (limit > 0 && (limit - value) < ap->allowed) ap->allowed = limit - value; /* If we can't meet the target */ if (limit && limit < (value + (s64)ap->target)) { /* If no min_target specified or we don't meet * min_target, return -EDQUOT */ if (!ap->min_target || ap->min_target > ap->allowed) { if (!test_and_set_bit(QDF_QMSG_QUIET, &qd->qd_flags)) { print_message(qd, "exceeded"); quota_send_warning(qd->qd_id, sdp->sd_vfs->s_dev, QUOTA_NL_BHARDWARN); } error = -EDQUOT; break; } } else if (warn && warn < value && time_after_eq(jiffies, qd->qd_last_warn + gfs2_tune_get(sdp, gt_quota_warn_period) * HZ)) { quota_send_warning(qd->qd_id, sdp->sd_vfs->s_dev, QUOTA_NL_BSOFTWARN); print_message(qd, "warning"); error = 0; qd->qd_last_warn = jiffies; } } return error; } void gfs2_quota_change(struct gfs2_inode *ip, s64 change, kuid_t uid, kgid_t gid) { struct gfs2_quota_data *qd; u32 x; struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF || gfs2_assert_warn(sdp, change)) return; if (ip->i_diskflags & GFS2_DIF_SYSTEM) return; if (gfs2_assert_withdraw(sdp, ip->i_qadata && ip->i_qadata->qa_ref > 0)) return; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; if (qid_eq(qd->qd_id, make_kqid_uid(uid)) || qid_eq(qd->qd_id, make_kqid_gid(gid))) { do_qc(qd, change); } } } int gfs2_quota_sync(struct super_block *sb, int type) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_quota_data **qda; unsigned int max_qd = PAGE_SIZE / sizeof(struct gfs2_holder); u64 sync_gen; int error = 0; if (sb_rdonly(sdp->sd_vfs)) return 0; qda = kcalloc(max_qd, sizeof(struct gfs2_quota_data *), GFP_KERNEL); if (!qda) return -ENOMEM; mutex_lock(&sdp->sd_quota_sync_mutex); sync_gen = sdp->sd_quota_sync_gen + 1; do { struct gfs2_quota_data *iter; unsigned int num_qd = 0; unsigned int x; spin_lock(&qd_lock); list_for_each_entry(iter, &sdp->sd_quota_list, qd_list) { if (qd_grab_sync(sdp, iter, sync_gen)) { qda[num_qd++] = iter; if (num_qd == max_qd) break; } } spin_unlock(&qd_lock); if (!num_qd) break; for (x = 0; x < num_qd; x++) { error = bh_get(qda[x]); if (!error) continue; while (x < num_qd) qd_ungrab_sync(qda[--num_qd]); break; } if (!error) { WRITE_ONCE(sdp->sd_quota_sync_gen, sync_gen); error = do_sync(num_qd, qda, sync_gen); } for (x = 0; x < num_qd; x++) qd_unlock(qda[x]); } while (!error); mutex_unlock(&sdp->sd_quota_sync_mutex); kfree(qda); return error; } int gfs2_quota_refresh(struct gfs2_sbd *sdp, struct kqid qid) { struct gfs2_quota_data *qd; struct gfs2_holder q_gh; int error; error = qd_get(sdp, qid, &qd); if (error) return error; error = do_glock(qd, FORCE, &q_gh); if (!error) gfs2_glock_dq_uninit(&q_gh); qd_put(qd); return error; } int gfs2_quota_init(struct gfs2_sbd *sdp) { struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode); u64 size = i_size_read(sdp->sd_qc_inode); unsigned int blocks = size >> sdp->sd_sb.sb_bsize_shift; unsigned int x, slot = 0; unsigned int found = 0; unsigned int hash; unsigned int bm_size; struct buffer_head *bh; u64 dblock; u32 extlen = 0; int error; if (gfs2_check_internal_file_size(sdp->sd_qc_inode, 1, 64 << 20)) return -EIO; sdp->sd_quota_slots = blocks * sdp->sd_qc_per_block; bm_size = DIV_ROUND_UP(sdp->sd_quota_slots, 8 * sizeof(unsigned long)); bm_size *= sizeof(unsigned long); error = -ENOMEM; sdp->sd_quota_bitmap = kzalloc(bm_size, GFP_NOFS | __GFP_NOWARN); if (sdp->sd_quota_bitmap == NULL) sdp->sd_quota_bitmap = __vmalloc(bm_size, GFP_NOFS | __GFP_ZERO); if (!sdp->sd_quota_bitmap) return error; for (x = 0; x < blocks; x++) { struct gfs2_quota_change *qc; unsigned int y; if (!extlen) { extlen = 32; error = gfs2_get_extent(&ip->i_inode, x, &dblock, &extlen); if (error) goto fail; } error = -EIO; bh = gfs2_meta_ra(ip->i_gl, dblock, extlen); if (!bh) goto fail; if (gfs2_metatype_check(sdp, bh, GFS2_METATYPE_QC)) goto fail_brelse; qc = (struct gfs2_quota_change *)(bh->b_data + sizeof(struct gfs2_meta_header)); for (y = 0; y < sdp->sd_qc_per_block && slot < sdp->sd_quota_slots; y++, slot++) { struct gfs2_quota_data *old_qd, *qd; s64 qc_change = be64_to_cpu(qc->qc_change); u32 qc_flags = be32_to_cpu(qc->qc_flags); enum quota_type qtype = (qc_flags & GFS2_QCF_USER) ? USRQUOTA : GRPQUOTA; struct kqid qc_id = make_kqid(&init_user_ns, qtype, be32_to_cpu(qc->qc_id)); qc++; if (!qc_change) continue; hash = gfs2_qd_hash(sdp, qc_id); qd = qd_alloc(hash, sdp, qc_id); if (qd == NULL) goto fail_brelse; qd->qd_lockref.count = 0; set_bit(QDF_CHANGE, &qd->qd_flags); qd->qd_change = qc_change; qd->qd_slot = slot; qd->qd_slot_ref = 1; spin_lock(&qd_lock); spin_lock_bucket(hash); old_qd = gfs2_qd_search_bucket(hash, sdp, qc_id); if (old_qd) { fs_err(sdp, "Corruption found in quota_change%u" "file: duplicate identifier in " "slot %u\n", sdp->sd_jdesc->jd_jid, slot); spin_unlock_bucket(hash); spin_unlock(&qd_lock); qd_put(old_qd); gfs2_glock_put(qd->qd_gl); kmem_cache_free(gfs2_quotad_cachep, qd); /* zero out the duplicate slot */ lock_buffer(bh); memset(qc, 0, sizeof(*qc)); mark_buffer_dirty(bh); unlock_buffer(bh); continue; } BUG_ON(test_and_set_bit(slot, sdp->sd_quota_bitmap)); list_add(&qd->qd_list, &sdp->sd_quota_list); atomic_inc(&sdp->sd_quota_count); hlist_bl_add_head_rcu(&qd->qd_hlist, &qd_hash_table[hash]); spin_unlock_bucket(hash); spin_unlock(&qd_lock); found++; } if (buffer_dirty(bh)) sync_dirty_buffer(bh); brelse(bh); dblock++; extlen--; } if (found) fs_info(sdp, "found %u quota changes\n", found); return 0; fail_brelse: if (buffer_dirty(bh)) sync_dirty_buffer(bh); brelse(bh); fail: gfs2_quota_cleanup(sdp); return error; } void gfs2_quota_cleanup(struct gfs2_sbd *sdp) { struct gfs2_quota_data *qd; LIST_HEAD(dispose); int count; BUG_ON(!test_bit(SDF_NORECOVERY, &sdp->sd_flags) && test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)); spin_lock(&qd_lock); list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) { spin_lock(&qd->qd_lockref.lock); if (qd->qd_lockref.count != 0) { spin_unlock(&qd->qd_lockref.lock); continue; } lockref_mark_dead(&qd->qd_lockref); spin_unlock(&qd->qd_lockref.lock); list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru); list_add(&qd->qd_lru, &dispose); } spin_unlock(&qd_lock); gfs2_qd_list_dispose(&dispose); wait_event_timeout(sdp->sd_kill_wait, (count = atomic_read(&sdp->sd_quota_count)) == 0, HZ * 60); if (count != 0) fs_err(sdp, "%d left-over quota data objects\n", count); kvfree(sdp->sd_quota_bitmap); sdp->sd_quota_bitmap = NULL; } static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error) { if (error == 0 || error == -EROFS) return; if (!gfs2_withdrawing_or_withdrawn(sdp)) { if (!cmpxchg(&sdp->sd_log_error, 0, error)) fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error); wake_up(&sdp->sd_logd_waitq); } } static void quotad_check_timeo(struct gfs2_sbd *sdp, const char *msg, int (*fxn)(struct super_block *sb, int type), unsigned long t, unsigned long *timeo, unsigned int *new_timeo) { if (t >= *timeo) { int error = fxn(sdp->sd_vfs, 0); quotad_error(sdp, msg, error); *timeo = gfs2_tune_get_i(&sdp->sd_tune, new_timeo) * HZ; } else { *timeo -= t; } } void gfs2_wake_up_statfs(struct gfs2_sbd *sdp) { if (!sdp->sd_statfs_force_sync) { sdp->sd_statfs_force_sync = 1; wake_up(&sdp->sd_quota_wait); } } /** * gfs2_quotad - Write cached quota changes into the quota file * @data: Pointer to GFS2 superblock * */ int gfs2_quotad(void *data) { struct gfs2_sbd *sdp = data; struct gfs2_tune *tune = &sdp->sd_tune; unsigned long statfs_timeo = 0; unsigned long quotad_timeo = 0; unsigned long t = 0; set_freezable(); while (!kthread_should_stop()) { if (gfs2_withdrawing_or_withdrawn(sdp)) break; /* Update the master statfs file */ if (sdp->sd_statfs_force_sync) { int error = gfs2_statfs_sync(sdp->sd_vfs, 0); quotad_error(sdp, "statfs", error); statfs_timeo = gfs2_tune_get(sdp, gt_statfs_quantum) * HZ; } else quotad_check_timeo(sdp, "statfs", gfs2_statfs_sync, t, &statfs_timeo, &tune->gt_statfs_quantum); /* Update quota file */ quotad_check_timeo(sdp, "sync", gfs2_quota_sync, t, "ad_timeo, &tune->gt_quota_quantum); t = min(quotad_timeo, statfs_timeo); t = wait_event_freezable_timeout(sdp->sd_quota_wait, sdp->sd_statfs_force_sync || gfs2_withdrawing_or_withdrawn(sdp) || kthread_should_stop(), t); if (sdp->sd_statfs_force_sync) t = 0; } return 0; } static int gfs2_quota_get_state(struct super_block *sb, struct qc_state *state) { struct gfs2_sbd *sdp = sb->s_fs_info; memset(state, 0, sizeof(*state)); switch (sdp->sd_args.ar_quota) { case GFS2_QUOTA_QUIET: fallthrough; case GFS2_QUOTA_ON: state->s_state[USRQUOTA].flags |= QCI_LIMITS_ENFORCED; state->s_state[GRPQUOTA].flags |= QCI_LIMITS_ENFORCED; fallthrough; case GFS2_QUOTA_ACCOUNT: state->s_state[USRQUOTA].flags |= QCI_ACCT_ENABLED | QCI_SYSFILE; state->s_state[GRPQUOTA].flags |= QCI_ACCT_ENABLED | QCI_SYSFILE; break; case GFS2_QUOTA_OFF: break; } if (sdp->sd_quota_inode) { state->s_state[USRQUOTA].ino = GFS2_I(sdp->sd_quota_inode)->i_no_addr; state->s_state[USRQUOTA].blocks = sdp->sd_quota_inode->i_blocks; } state->s_state[USRQUOTA].nextents = 1; /* unsupported */ state->s_state[GRPQUOTA] = state->s_state[USRQUOTA]; state->s_incoredqs = list_lru_count(&gfs2_qd_lru); return 0; } static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, struct qc_dqblk *fdq) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_quota_lvb *qlvb; struct gfs2_quota_data *qd; struct gfs2_holder q_gh; int error; memset(fdq, 0, sizeof(*fdq)); if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return -ESRCH; /* Crazy XFS error code */ if ((qid.type != USRQUOTA) && (qid.type != GRPQUOTA)) return -EINVAL; error = qd_get(sdp, qid, &qd); if (error) return error; error = do_glock(qd, FORCE, &q_gh); if (error) goto out; qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; fdq->d_spc_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_sb.sb_bsize_shift; fdq->d_spc_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_sb.sb_bsize_shift; fdq->d_space = be64_to_cpu(qlvb->qb_value) << sdp->sd_sb.sb_bsize_shift; gfs2_glock_dq_uninit(&q_gh); out: qd_put(qd); return error; } /* GFS2 only supports a subset of the XFS fields */ #define GFS2_FIELDMASK (QC_SPC_SOFT|QC_SPC_HARD|QC_SPACE) static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid, struct qc_dqblk *fdq) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); struct gfs2_quota_data *qd; struct gfs2_holder q_gh, i_gh; unsigned int data_blocks, ind_blocks; unsigned int blocks = 0; int alloc_required; loff_t offset; int error; if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return -ESRCH; /* Crazy XFS error code */ if ((qid.type != USRQUOTA) && (qid.type != GRPQUOTA)) return -EINVAL; if (fdq->d_fieldmask & ~GFS2_FIELDMASK) return -EINVAL; error = qd_get(sdp, qid, &qd); if (error) return error; error = gfs2_qa_get(ip); if (error) goto out_put; inode_lock(&ip->i_inode); error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_EXCLUSIVE, 0, &q_gh); if (error) goto out_unlockput; error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh); if (error) goto out_q; /* Check for existing entry, if none then alloc new blocks */ error = update_qd(sdp, qd); if (error) goto out_i; /* If nothing has changed, this is a no-op */ if ((fdq->d_fieldmask & QC_SPC_SOFT) && ((fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_warn))) fdq->d_fieldmask ^= QC_SPC_SOFT; if ((fdq->d_fieldmask & QC_SPC_HARD) && ((fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_limit))) fdq->d_fieldmask ^= QC_SPC_HARD; if ((fdq->d_fieldmask & QC_SPACE) && ((fdq->d_space >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_value))) fdq->d_fieldmask ^= QC_SPACE; if (fdq->d_fieldmask == 0) goto out_i; offset = qd2offset(qd); alloc_required = gfs2_write_alloc_required(ip, offset, sizeof(struct gfs2_quota)); if (gfs2_is_stuffed(ip)) alloc_required = 1; if (alloc_required) { struct gfs2_alloc_parms ap = {}; gfs2_write_calc_reserv(ip, sizeof(struct gfs2_quota), &data_blocks, &ind_blocks); blocks = 1 + data_blocks + ind_blocks; ap.target = blocks; error = gfs2_inplace_reserve(ip, &ap); if (error) goto out_i; blocks += gfs2_rg_blocks(ip, blocks); } /* Some quotas span block boundaries and can update two blocks, adding an extra block to the transaction to handle such quotas */ error = gfs2_trans_begin(sdp, blocks + RES_DINODE + 2, 0); if (error) goto out_release; /* Apply changes */ error = gfs2_adjust_quota(sdp, offset, 0, qd, fdq); if (!error) clear_bit(QDF_QMSG_QUIET, &qd->qd_flags); gfs2_trans_end(sdp); out_release: if (alloc_required) gfs2_inplace_release(ip); out_i: gfs2_glock_dq_uninit(&i_gh); out_q: gfs2_glock_dq_uninit(&q_gh); out_unlockput: gfs2_qa_put(ip); inode_unlock(&ip->i_inode); out_put: qd_put(qd); return error; } const struct quotactl_ops gfs2_quotactl_ops = { .quota_sync = gfs2_quota_sync, .get_state = gfs2_quota_get_state, .get_dqblk = gfs2_get_dqblk, .set_dqblk = gfs2_set_dqblk, }; void __init gfs2_quota_hash_init(void) { unsigned i; for(i = 0; i < GFS2_QD_HASH_SIZE; i++) INIT_HLIST_BL_HEAD(&qd_hash_table[i]); } |
| 1 1 1 1 1 6 1 1 1 2 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/capability.h> #include <linux/if.h> #include <linux/inetdevice.h> #include <linux/ip.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/tcp.h> #include <net/ip.h> #include <net/tcp.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_log.h> #include <linux/netfilter/nfnetlink_osf.h> /* * Indexed by dont-fragment bit. * It is the only constant value in the fingerprint. */ struct list_head nf_osf_fingers[2]; EXPORT_SYMBOL_GPL(nf_osf_fingers); static inline int nf_osf_ttl(const struct sk_buff *skb, int ttl_check, unsigned char f_ttl) { struct in_device *in_dev = __in_dev_get_rcu(skb->dev); const struct iphdr *ip = ip_hdr(skb); const struct in_ifaddr *ifa; int ret = 0; if (ttl_check == NF_OSF_TTL_TRUE) return ip->ttl == f_ttl; if (ttl_check == NF_OSF_TTL_NOCHECK) return 1; else if (ip->ttl <= f_ttl) return 1; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (inet_ifa_match(ip->saddr, ifa)) { ret = (ip->ttl == f_ttl); break; } } return ret; } struct nf_osf_hdr_ctx { bool df; u16 window; u16 totlen; const unsigned char *optp; unsigned int optsize; }; static bool nf_osf_match_one(const struct sk_buff *skb, const struct nf_osf_user_finger *f, int ttl_check, struct nf_osf_hdr_ctx *ctx) { const __u8 *optpinit = ctx->optp; unsigned int check_WSS = 0; int fmatch = FMATCH_WRONG; int foptsize, optnum; u16 mss = 0; if (ctx->totlen != f->ss || !nf_osf_ttl(skb, ttl_check, f->ttl)) return false; /* * Should not happen if userspace parser was written correctly. */ if (f->wss.wc >= OSF_WSS_MAX) return false; /* Check options */ foptsize = 0; for (optnum = 0; optnum < f->opt_num; ++optnum) foptsize += f->opt[optnum].length; if (foptsize > MAX_IPOPTLEN || ctx->optsize > MAX_IPOPTLEN || ctx->optsize != foptsize) return false; check_WSS = f->wss.wc; for (optnum = 0; optnum < f->opt_num; ++optnum) { if (f->opt[optnum].kind == *ctx->optp) { __u32 len = f->opt[optnum].length; const __u8 *optend = ctx->optp + len; fmatch = FMATCH_OK; switch (*ctx->optp) { case OSFOPT_MSS: mss = ctx->optp[3]; mss <<= 8; mss |= ctx->optp[2]; mss = ntohs((__force __be16)mss); break; case OSFOPT_TS: break; } ctx->optp = optend; } else fmatch = FMATCH_OPT_WRONG; if (fmatch != FMATCH_OK) break; } if (fmatch != FMATCH_OPT_WRONG) { fmatch = FMATCH_WRONG; switch (check_WSS) { case OSF_WSS_PLAIN: if (f->wss.val == 0 || ctx->window == f->wss.val) fmatch = FMATCH_OK; break; case OSF_WSS_MSS: /* * Some smart modems decrease mangle MSS to * SMART_MSS_2, so we check standard, decreased * and the one provided in the fingerprint MSS * values. */ #define SMART_MSS_1 1460 #define SMART_MSS_2 1448 if (ctx->window == f->wss.val * mss || ctx->window == f->wss.val * SMART_MSS_1 || ctx->window == f->wss.val * SMART_MSS_2) fmatch = FMATCH_OK; break; case OSF_WSS_MTU: if (ctx->window == f->wss.val * (mss + 40) || ctx->window == f->wss.val * (SMART_MSS_1 + 40) || ctx->window == f->wss.val * (SMART_MSS_2 + 40)) fmatch = FMATCH_OK; break; case OSF_WSS_MODULO: if ((ctx->window % f->wss.val) == 0) fmatch = FMATCH_OK; break; } } if (fmatch != FMATCH_OK) ctx->optp = optpinit; return fmatch == FMATCH_OK; } static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx, const struct sk_buff *skb, const struct iphdr *ip, unsigned char *opts, struct tcphdr *_tcph) { const struct tcphdr *tcp; tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), _tcph); if (!tcp) return NULL; if (!tcp->syn) return NULL; ctx->totlen = ntohs(ip->tot_len); ctx->df = ntohs(ip->frag_off) & IP_DF; ctx->window = ntohs(tcp->window); if (tcp->doff * 4 > sizeof(struct tcphdr)) { ctx->optsize = tcp->doff * 4 - sizeof(struct tcphdr); ctx->optp = skb_header_pointer(skb, ip_hdrlen(skb) + sizeof(struct tcphdr), ctx->optsize, opts); if (!ctx->optp) return NULL; } return tcp; } bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, int hooknum, struct net_device *in, struct net_device *out, const struct nf_osf_info *info, struct net *net, const struct list_head *nf_osf_fingers) { const struct iphdr *ip = ip_hdr(skb); const struct nf_osf_user_finger *f; unsigned char opts[MAX_IPOPTLEN]; const struct nf_osf_finger *kf; int fcount = 0, ttl_check; int fmatch = FMATCH_WRONG; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; ttl_check = (info->flags & NF_OSF_TTL) ? info->ttl : 0; list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) { f = &kf->finger; if (!(info->flags & NF_OSF_LOG) && strcmp(info->genre, f->genre)) continue; if (!nf_osf_match_one(skb, f, ttl_check, &ctx)) continue; fmatch = FMATCH_OK; fcount++; if (info->flags & NF_OSF_LOG) nf_log_packet(net, family, hooknum, skb, in, out, NULL, "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n", f->genre, f->version, f->subtype, &ip->saddr, ntohs(tcp->source), &ip->daddr, ntohs(tcp->dest), f->ttl - ip->ttl); if ((info->flags & NF_OSF_LOG) && info->loglevel == NF_OSF_LOGLEVEL_FIRST) break; } if (!fcount && (info->flags & NF_OSF_LOG)) nf_log_packet(net, family, hooknum, skb, in, out, NULL, "Remote OS is not known: %pI4:%u -> %pI4:%u\n", &ip->saddr, ntohs(tcp->source), &ip->daddr, ntohs(tcp->dest)); if (fcount) fmatch = FMATCH_OK; return fmatch == FMATCH_OK; } EXPORT_SYMBOL_GPL(nf_osf_match); bool nf_osf_find(const struct sk_buff *skb, const struct list_head *nf_osf_fingers, const int ttl_check, struct nf_osf_data *data) { const struct iphdr *ip = ip_hdr(skb); const struct nf_osf_user_finger *f; unsigned char opts[MAX_IPOPTLEN]; const struct nf_osf_finger *kf; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; struct tcphdr _tcph; bool found = false; memset(&ctx, 0, sizeof(ctx)); tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) { f = &kf->finger; if (!nf_osf_match_one(skb, f, ttl_check, &ctx)) continue; data->genre = f->genre; data->version = f->version; found = true; break; } return found; } EXPORT_SYMBOL_GPL(nf_osf_find); static const struct nla_policy nfnl_osf_policy[OSF_ATTR_MAX + 1] = { [OSF_ATTR_FINGER] = { .len = sizeof(struct nf_osf_user_finger) }, }; static int nfnl_osf_add_callback(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const osf_attrs[]) { struct nf_osf_user_finger *f; struct nf_osf_finger *kf = NULL, *sf; int err = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL; if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) return -EINVAL; f = nla_data(osf_attrs[OSF_ATTR_FINGER]); if (f->opt_num > ARRAY_SIZE(f->opt)) return -EINVAL; if (!memchr(f->genre, 0, MAXGENRELEN) || !memchr(f->subtype, 0, MAXGENRELEN) || !memchr(f->version, 0, MAXGENRELEN)) return -EINVAL; kf = kmalloc(sizeof(struct nf_osf_finger), GFP_KERNEL); if (!kf) return -ENOMEM; memcpy(&kf->finger, f, sizeof(struct nf_osf_user_finger)); list_for_each_entry(sf, &nf_osf_fingers[!!f->df], finger_entry) { if (memcmp(&sf->finger, f, sizeof(struct nf_osf_user_finger))) continue; kfree(kf); kf = NULL; if (info->nlh->nlmsg_flags & NLM_F_EXCL) err = -EEXIST; break; } /* * We are protected by nfnl mutex. */ if (kf) list_add_tail_rcu(&kf->finger_entry, &nf_osf_fingers[!!f->df]); return err; } static int nfnl_osf_remove_callback(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const osf_attrs[]) { struct nf_osf_user_finger *f; struct nf_osf_finger *sf; int err = -ENOENT; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL; f = nla_data(osf_attrs[OSF_ATTR_FINGER]); list_for_each_entry(sf, &nf_osf_fingers[!!f->df], finger_entry) { if (memcmp(&sf->finger, f, sizeof(struct nf_osf_user_finger))) continue; /* * We are protected by nfnl mutex. */ list_del_rcu(&sf->finger_entry); kfree_rcu(sf, rcu_head); err = 0; break; } return err; } static const struct nfnl_callback nfnl_osf_callbacks[OSF_MSG_MAX] = { [OSF_MSG_ADD] = { .call = nfnl_osf_add_callback, .type = NFNL_CB_MUTEX, .attr_count = OSF_ATTR_MAX, .policy = nfnl_osf_policy, }, [OSF_MSG_REMOVE] = { .call = nfnl_osf_remove_callback, .type = NFNL_CB_MUTEX, .attr_count = OSF_ATTR_MAX, .policy = nfnl_osf_policy, }, }; static const struct nfnetlink_subsystem nfnl_osf_subsys = { .name = "osf", .subsys_id = NFNL_SUBSYS_OSF, .cb_count = OSF_MSG_MAX, .cb = nfnl_osf_callbacks, }; static int __init nfnl_osf_init(void) { int err = -EINVAL; int i; for (i = 0; i < ARRAY_SIZE(nf_osf_fingers); ++i) INIT_LIST_HEAD(&nf_osf_fingers[i]); err = nfnetlink_subsys_register(&nfnl_osf_subsys); if (err < 0) { pr_err("Failed to register OSF nsfnetlink helper (%d)\n", err); goto err_out_exit; } return 0; err_out_exit: return err; } static void __exit nfnl_osf_fini(void) { struct nf_osf_finger *f; int i; nfnetlink_subsys_unregister(&nfnl_osf_subsys); rcu_read_lock(); for (i = 0; i < ARRAY_SIZE(nf_osf_fingers); ++i) { list_for_each_entry_rcu(f, &nf_osf_fingers[i], finger_entry) { list_del_rcu(&f->finger_entry); kfree_rcu(f, rcu_head); } } rcu_read_unlock(); rcu_barrier(); } module_init(nfnl_osf_init); module_exit(nfnl_osf_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Passive OS fingerprint matching"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF); |
| 4 5 9 9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Public Key Encryption * * Copyright (c) 2015, Intel Corporation * Authors: Tadeusz Struk <tadeusz.struk@intel.com> */ #include <crypto/internal/akcipher.h> #include <linux/cryptouser.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/scatterlist.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/string.h> #include <net/netlink.h> #include "internal.h" #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000e struct crypto_akcipher_sync_data { struct crypto_akcipher *tfm; const void *src; void *dst; unsigned int slen; unsigned int dlen; struct akcipher_request *req; struct crypto_wait cwait; struct scatterlist sg; u8 *buf; }; static int __maybe_unused crypto_akcipher_report( struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_akcipher rakcipher; memset(&rakcipher, 0, sizeof(rakcipher)); strscpy(rakcipher.type, "akcipher", sizeof(rakcipher.type)); return nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER, sizeof(rakcipher), &rakcipher); } static void crypto_akcipher_show(struct seq_file *m, struct crypto_alg *alg) __maybe_unused; static void crypto_akcipher_show(struct seq_file *m, struct crypto_alg *alg) { seq_puts(m, "type : akcipher\n"); } static void crypto_akcipher_exit_tfm(struct crypto_tfm *tfm) { struct crypto_akcipher *akcipher = __crypto_akcipher_tfm(tfm); struct akcipher_alg *alg = crypto_akcipher_alg(akcipher); alg->exit(akcipher); } static int crypto_akcipher_init_tfm(struct crypto_tfm *tfm) { struct crypto_akcipher *akcipher = __crypto_akcipher_tfm(tfm); struct akcipher_alg *alg = crypto_akcipher_alg(akcipher); if (alg->exit) akcipher->base.exit = crypto_akcipher_exit_tfm; if (alg->init) return alg->init(akcipher); return 0; } static void crypto_akcipher_free_instance(struct crypto_instance *inst) { struct akcipher_instance *akcipher = akcipher_instance(inst); akcipher->free(akcipher); } static const struct crypto_type crypto_akcipher_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_akcipher_init_tfm, .free = crypto_akcipher_free_instance, #ifdef CONFIG_PROC_FS .show = crypto_akcipher_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_akcipher_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_AHASH_MASK, .type = CRYPTO_ALG_TYPE_AKCIPHER, .tfmsize = offsetof(struct crypto_akcipher, base), .algsize = offsetof(struct akcipher_alg, base), }; int crypto_grab_akcipher(struct crypto_akcipher_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { spawn->base.frontend = &crypto_akcipher_type; return crypto_grab_spawn(&spawn->base, inst, name, type, mask); } EXPORT_SYMBOL_GPL(crypto_grab_akcipher); struct crypto_akcipher *crypto_alloc_akcipher(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_akcipher_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_akcipher); static void akcipher_prepare_alg(struct akcipher_alg *alg) { struct crypto_alg *base = &alg->base; base->cra_type = &crypto_akcipher_type; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; base->cra_flags |= CRYPTO_ALG_TYPE_AKCIPHER; } static int akcipher_default_op(struct akcipher_request *req) { return -ENOSYS; } static int akcipher_default_set_key(struct crypto_akcipher *tfm, const void *key, unsigned int keylen) { return -ENOSYS; } int crypto_register_akcipher(struct akcipher_alg *alg) { struct crypto_alg *base = &alg->base; if (!alg->encrypt) alg->encrypt = akcipher_default_op; if (!alg->decrypt) alg->decrypt = akcipher_default_op; if (!alg->set_priv_key) alg->set_priv_key = akcipher_default_set_key; akcipher_prepare_alg(alg); return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_akcipher); void crypto_unregister_akcipher(struct akcipher_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_akcipher); int akcipher_register_instance(struct crypto_template *tmpl, struct akcipher_instance *inst) { if (WARN_ON(!inst->free)) return -EINVAL; akcipher_prepare_alg(&inst->alg); return crypto_register_instance(tmpl, akcipher_crypto_instance(inst)); } EXPORT_SYMBOL_GPL(akcipher_register_instance); static int crypto_akcipher_sync_prep(struct crypto_akcipher_sync_data *data) { unsigned int reqsize = crypto_akcipher_reqsize(data->tfm); struct akcipher_request *req; struct scatterlist *sg; unsigned int mlen; unsigned int len; u8 *buf; mlen = max(data->slen, data->dlen); len = sizeof(*req) + reqsize + mlen; if (len < mlen) return -EOVERFLOW; req = kzalloc(len, GFP_KERNEL); if (!req) return -ENOMEM; data->req = req; akcipher_request_set_tfm(req, data->tfm); buf = (u8 *)(req + 1) + reqsize; data->buf = buf; memcpy(buf, data->src, data->slen); sg = &data->sg; sg_init_one(sg, buf, mlen); akcipher_request_set_crypt(req, sg, sg, data->slen, data->dlen); crypto_init_wait(&data->cwait); akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &data->cwait); return 0; } static int crypto_akcipher_sync_post(struct crypto_akcipher_sync_data *data, int err) { err = crypto_wait_req(err, &data->cwait); memcpy(data->dst, data->buf, data->dlen); data->dlen = data->req->dst_len; kfree_sensitive(data->req); return err; } int crypto_akcipher_sync_encrypt(struct crypto_akcipher *tfm, const void *src, unsigned int slen, void *dst, unsigned int dlen) { struct crypto_akcipher_sync_data data = { .tfm = tfm, .src = src, .dst = dst, .slen = slen, .dlen = dlen, }; return crypto_akcipher_sync_prep(&data) ?: crypto_akcipher_sync_post(&data, crypto_akcipher_encrypt(data.req)); } EXPORT_SYMBOL_GPL(crypto_akcipher_sync_encrypt); int crypto_akcipher_sync_decrypt(struct crypto_akcipher *tfm, const void *src, unsigned int slen, void *dst, unsigned int dlen) { struct crypto_akcipher_sync_data data = { .tfm = tfm, .src = src, .dst = dst, .slen = slen, .dlen = dlen, }; return crypto_akcipher_sync_prep(&data) ?: crypto_akcipher_sync_post(&data, crypto_akcipher_decrypt(data.req)) ?: data.dlen; } EXPORT_SYMBOL_GPL(crypto_akcipher_sync_decrypt); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Generic public key cipher type"); |
| 13 12 7 7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 | /* * Copyright (c) 2016 Mellanox Technologies Ltd. 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/security.h> #include <linux/completion.h> #include <linux/list.h> #include <rdma/ib_verbs.h> #include <rdma/ib_cache.h> #include "core_priv.h" #include "mad_priv.h" static LIST_HEAD(mad_agent_list); /* Lock to protect mad_agent_list */ static DEFINE_SPINLOCK(mad_agent_list_lock); static struct pkey_index_qp_list *get_pkey_idx_qp_list(struct ib_port_pkey *pp) { struct pkey_index_qp_list *pkey = NULL; struct pkey_index_qp_list *tmp_pkey; struct ib_device *dev = pp->sec->dev; spin_lock(&dev->port_data[pp->port_num].pkey_list_lock); list_for_each_entry (tmp_pkey, &dev->port_data[pp->port_num].pkey_list, pkey_index_list) { if (tmp_pkey->pkey_index == pp->pkey_index) { pkey = tmp_pkey; break; } } spin_unlock(&dev->port_data[pp->port_num].pkey_list_lock); return pkey; } static int get_pkey_and_subnet_prefix(struct ib_port_pkey *pp, u16 *pkey, u64 *subnet_prefix) { struct ib_device *dev = pp->sec->dev; int ret; ret = ib_get_cached_pkey(dev, pp->port_num, pp->pkey_index, pkey); if (ret) return ret; ib_get_cached_subnet_prefix(dev, pp->port_num, subnet_prefix); return ret; } static int enforce_qp_pkey_security(u16 pkey, u64 subnet_prefix, struct ib_qp_security *qp_sec) { struct ib_qp_security *shared_qp_sec; int ret; ret = security_ib_pkey_access(qp_sec->security, subnet_prefix, pkey); if (ret) return ret; list_for_each_entry(shared_qp_sec, &qp_sec->shared_qp_list, shared_qp_list) { ret = security_ib_pkey_access(shared_qp_sec->security, subnet_prefix, pkey); if (ret) return ret; } return 0; } /* The caller of this function must hold the QP security * mutex of the QP of the security structure in *pps. * * It takes separate ports_pkeys and security structure * because in some cases the pps will be for a new settings * or the pps will be for the real QP and security structure * will be for a shared QP. */ static int check_qp_port_pkey_settings(struct ib_ports_pkeys *pps, struct ib_qp_security *sec) { u64 subnet_prefix; u16 pkey; int ret = 0; if (!pps) return 0; if (pps->main.state != IB_PORT_PKEY_NOT_VALID) { ret = get_pkey_and_subnet_prefix(&pps->main, &pkey, &subnet_prefix); if (ret) return ret; ret = enforce_qp_pkey_security(pkey, subnet_prefix, sec); if (ret) return ret; } if (pps->alt.state != IB_PORT_PKEY_NOT_VALID) { ret = get_pkey_and_subnet_prefix(&pps->alt, &pkey, &subnet_prefix); if (ret) return ret; ret = enforce_qp_pkey_security(pkey, subnet_prefix, sec); } return ret; } /* The caller of this function must hold the QP security * mutex. */ static void qp_to_error(struct ib_qp_security *sec) { struct ib_qp_security *shared_qp_sec; struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR }; struct ib_event event = { .event = IB_EVENT_QP_FATAL }; /* If the QP is in the process of being destroyed * the qp pointer in the security structure is * undefined. It cannot be modified now. */ if (sec->destroying) return; ib_modify_qp(sec->qp, &attr, IB_QP_STATE); if (sec->qp->event_handler && sec->qp->qp_context) { event.element.qp = sec->qp; sec->qp->event_handler(&event, sec->qp->qp_context); } list_for_each_entry(shared_qp_sec, &sec->shared_qp_list, shared_qp_list) { struct ib_qp *qp = shared_qp_sec->qp; if (qp->event_handler && qp->qp_context) { event.element.qp = qp; event.device = qp->device; qp->event_handler(&event, qp->qp_context); } } } static inline void check_pkey_qps(struct pkey_index_qp_list *pkey, struct ib_device *device, u32 port_num, u64 subnet_prefix) { struct ib_port_pkey *pp, *tmp_pp; bool comp; LIST_HEAD(to_error_list); u16 pkey_val; if (!ib_get_cached_pkey(device, port_num, pkey->pkey_index, &pkey_val)) { spin_lock(&pkey->qp_list_lock); list_for_each_entry(pp, &pkey->qp_list, qp_list) { if (atomic_read(&pp->sec->error_list_count)) continue; if (enforce_qp_pkey_security(pkey_val, subnet_prefix, pp->sec)) { atomic_inc(&pp->sec->error_list_count); list_add(&pp->to_error_list, &to_error_list); } } spin_unlock(&pkey->qp_list_lock); } list_for_each_entry_safe(pp, tmp_pp, &to_error_list, to_error_list) { mutex_lock(&pp->sec->mutex); qp_to_error(pp->sec); list_del(&pp->to_error_list); atomic_dec(&pp->sec->error_list_count); comp = pp->sec->destroying; mutex_unlock(&pp->sec->mutex); if (comp) complete(&pp->sec->error_complete); } } /* The caller of this function must hold the QP security * mutex. */ static int port_pkey_list_insert(struct ib_port_pkey *pp) { struct pkey_index_qp_list *tmp_pkey; struct pkey_index_qp_list *pkey; struct ib_device *dev; u32 port_num = pp->port_num; int ret = 0; if (pp->state != IB_PORT_PKEY_VALID) return 0; dev = pp->sec->dev; pkey = get_pkey_idx_qp_list(pp); if (!pkey) { bool found = false; pkey = kzalloc(sizeof(*pkey), GFP_KERNEL); if (!pkey) return -ENOMEM; spin_lock(&dev->port_data[port_num].pkey_list_lock); /* Check for the PKey again. A racing process may * have created it. */ list_for_each_entry(tmp_pkey, &dev->port_data[port_num].pkey_list, pkey_index_list) { if (tmp_pkey->pkey_index == pp->pkey_index) { kfree(pkey); pkey = tmp_pkey; found = true; break; } } if (!found) { pkey->pkey_index = pp->pkey_index; spin_lock_init(&pkey->qp_list_lock); INIT_LIST_HEAD(&pkey->qp_list); list_add(&pkey->pkey_index_list, &dev->port_data[port_num].pkey_list); } spin_unlock(&dev->port_data[port_num].pkey_list_lock); } spin_lock(&pkey->qp_list_lock); list_add(&pp->qp_list, &pkey->qp_list); spin_unlock(&pkey->qp_list_lock); pp->state = IB_PORT_PKEY_LISTED; return ret; } /* The caller of this function must hold the QP security * mutex. */ static void port_pkey_list_remove(struct ib_port_pkey *pp) { struct pkey_index_qp_list *pkey; if (pp->state != IB_PORT_PKEY_LISTED) return; pkey = get_pkey_idx_qp_list(pp); spin_lock(&pkey->qp_list_lock); list_del(&pp->qp_list); spin_unlock(&pkey->qp_list_lock); /* The setting may still be valid, i.e. after * a destroy has failed for example. */ pp->state = IB_PORT_PKEY_VALID; } static void destroy_qp_security(struct ib_qp_security *sec) { security_ib_free_security(sec->security); kfree(sec->ports_pkeys); kfree(sec); } /* The caller of this function must hold the QP security * mutex. */ static struct ib_ports_pkeys *get_new_pps(const struct ib_qp *qp, const struct ib_qp_attr *qp_attr, int qp_attr_mask) { struct ib_ports_pkeys *new_pps; struct ib_ports_pkeys *qp_pps = qp->qp_sec->ports_pkeys; new_pps = kzalloc(sizeof(*new_pps), GFP_KERNEL); if (!new_pps) return NULL; if (qp_attr_mask & IB_QP_PORT) new_pps->main.port_num = qp_attr->port_num; else if (qp_pps) new_pps->main.port_num = qp_pps->main.port_num; if (qp_attr_mask & IB_QP_PKEY_INDEX) new_pps->main.pkey_index = qp_attr->pkey_index; else if (qp_pps) new_pps->main.pkey_index = qp_pps->main.pkey_index; if (((qp_attr_mask & IB_QP_PKEY_INDEX) && (qp_attr_mask & IB_QP_PORT)) || (qp_pps && qp_pps->main.state != IB_PORT_PKEY_NOT_VALID)) new_pps->main.state = IB_PORT_PKEY_VALID; if (qp_attr_mask & IB_QP_ALT_PATH) { new_pps->alt.port_num = qp_attr->alt_port_num; new_pps->alt.pkey_index = qp_attr->alt_pkey_index; new_pps->alt.state = IB_PORT_PKEY_VALID; } else if (qp_pps) { new_pps->alt.port_num = qp_pps->alt.port_num; new_pps->alt.pkey_index = qp_pps->alt.pkey_index; if (qp_pps->alt.state != IB_PORT_PKEY_NOT_VALID) new_pps->alt.state = IB_PORT_PKEY_VALID; } new_pps->main.sec = qp->qp_sec; new_pps->alt.sec = qp->qp_sec; return new_pps; } int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev) { struct ib_qp *real_qp = qp->real_qp; int ret; ret = ib_create_qp_security(qp, dev); if (ret) return ret; if (!qp->qp_sec) return 0; mutex_lock(&real_qp->qp_sec->mutex); ret = check_qp_port_pkey_settings(real_qp->qp_sec->ports_pkeys, qp->qp_sec); if (ret) goto ret; if (qp != real_qp) list_add(&qp->qp_sec->shared_qp_list, &real_qp->qp_sec->shared_qp_list); ret: mutex_unlock(&real_qp->qp_sec->mutex); if (ret) destroy_qp_security(qp->qp_sec); return ret; } void ib_close_shared_qp_security(struct ib_qp_security *sec) { struct ib_qp *real_qp = sec->qp->real_qp; mutex_lock(&real_qp->qp_sec->mutex); list_del(&sec->shared_qp_list); mutex_unlock(&real_qp->qp_sec->mutex); destroy_qp_security(sec); } int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev) { unsigned int i; bool is_ib = false; int ret; rdma_for_each_port (dev, i) { is_ib = rdma_protocol_ib(dev, i); if (is_ib) break; } /* If this isn't an IB device don't create the security context */ if (!is_ib) return 0; qp->qp_sec = kzalloc(sizeof(*qp->qp_sec), GFP_KERNEL); if (!qp->qp_sec) return -ENOMEM; qp->qp_sec->qp = qp; qp->qp_sec->dev = dev; mutex_init(&qp->qp_sec->mutex); INIT_LIST_HEAD(&qp->qp_sec->shared_qp_list); atomic_set(&qp->qp_sec->error_list_count, 0); init_completion(&qp->qp_sec->error_complete); ret = security_ib_alloc_security(&qp->qp_sec->security); if (ret) { kfree(qp->qp_sec); qp->qp_sec = NULL; } return ret; } EXPORT_SYMBOL(ib_create_qp_security); void ib_destroy_qp_security_begin(struct ib_qp_security *sec) { /* Return if not IB */ if (!sec) return; mutex_lock(&sec->mutex); /* Remove the QP from the lists so it won't get added to * a to_error_list during the destroy process. */ if (sec->ports_pkeys) { port_pkey_list_remove(&sec->ports_pkeys->main); port_pkey_list_remove(&sec->ports_pkeys->alt); } /* If the QP is already in one or more of those lists * the destroying flag will ensure the to error flow * doesn't operate on an undefined QP. */ sec->destroying = true; /* Record the error list count to know how many completions * to wait for. */ sec->error_comps_pending = atomic_read(&sec->error_list_count); mutex_unlock(&sec->mutex); } void ib_destroy_qp_security_abort(struct ib_qp_security *sec) { int ret; int i; /* Return if not IB */ if (!sec) return; /* If a concurrent cache update is in progress this * QP security could be marked for an error state * transition. Wait for this to complete. */ for (i = 0; i < sec->error_comps_pending; i++) wait_for_completion(&sec->error_complete); mutex_lock(&sec->mutex); sec->destroying = false; /* Restore the position in the lists and verify * access is still allowed in case a cache update * occurred while attempting to destroy. * * Because these setting were listed already * and removed during ib_destroy_qp_security_begin * we know the pkey_index_qp_list for the PKey * already exists so port_pkey_list_insert won't fail. */ if (sec->ports_pkeys) { port_pkey_list_insert(&sec->ports_pkeys->main); port_pkey_list_insert(&sec->ports_pkeys->alt); } ret = check_qp_port_pkey_settings(sec->ports_pkeys, sec); if (ret) qp_to_error(sec); mutex_unlock(&sec->mutex); } void ib_destroy_qp_security_end(struct ib_qp_security *sec) { int i; /* Return if not IB */ if (!sec) return; /* If a concurrent cache update is occurring we must * wait until this QP security structure is processed * in the QP to error flow before destroying it because * the to_error_list is in use. */ for (i = 0; i < sec->error_comps_pending; i++) wait_for_completion(&sec->error_complete); destroy_qp_security(sec); } void ib_security_cache_change(struct ib_device *device, u32 port_num, u64 subnet_prefix) { struct pkey_index_qp_list *pkey; list_for_each_entry (pkey, &device->port_data[port_num].pkey_list, pkey_index_list) { check_pkey_qps(pkey, device, port_num, subnet_prefix); } } void ib_security_release_port_pkey_list(struct ib_device *device) { struct pkey_index_qp_list *pkey, *tmp_pkey; unsigned int i; rdma_for_each_port (device, i) { list_for_each_entry_safe(pkey, tmp_pkey, &device->port_data[i].pkey_list, pkey_index_list) { list_del(&pkey->pkey_index_list); kfree(pkey); } } } int ib_security_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata) { int ret = 0; struct ib_ports_pkeys *tmp_pps; struct ib_ports_pkeys *new_pps = NULL; struct ib_qp *real_qp = qp->real_qp; bool special_qp = (real_qp->qp_type == IB_QPT_SMI || real_qp->qp_type == IB_QPT_GSI || real_qp->qp_type >= IB_QPT_RESERVED1); bool pps_change = ((qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) || (qp_attr_mask & IB_QP_ALT_PATH)); WARN_ONCE((qp_attr_mask & IB_QP_PORT && rdma_protocol_ib(real_qp->device, qp_attr->port_num) && !real_qp->qp_sec), "%s: QP security is not initialized for IB QP: %u\n", __func__, real_qp->qp_num); /* The port/pkey settings are maintained only for the real QP. Open * handles on the real QP will be in the shared_qp_list. When * enforcing security on the real QP all the shared QPs will be * checked as well. */ if (pps_change && !special_qp && real_qp->qp_sec) { mutex_lock(&real_qp->qp_sec->mutex); new_pps = get_new_pps(real_qp, qp_attr, qp_attr_mask); if (!new_pps) { mutex_unlock(&real_qp->qp_sec->mutex); return -ENOMEM; } /* Add this QP to the lists for the new port * and pkey settings before checking for permission * in case there is a concurrent cache update * occurring. Walking the list for a cache change * doesn't acquire the security mutex unless it's * sending the QP to error. */ ret = port_pkey_list_insert(&new_pps->main); if (!ret) ret = port_pkey_list_insert(&new_pps->alt); if (!ret) ret = check_qp_port_pkey_settings(new_pps, real_qp->qp_sec); } if (!ret) ret = real_qp->device->ops.modify_qp(real_qp, qp_attr, qp_attr_mask, udata); if (new_pps) { /* Clean up the lists and free the appropriate * ports_pkeys structure. */ if (ret) { tmp_pps = new_pps; } else { tmp_pps = real_qp->qp_sec->ports_pkeys; real_qp->qp_sec->ports_pkeys = new_pps; } if (tmp_pps) { port_pkey_list_remove(&tmp_pps->main); port_pkey_list_remove(&tmp_pps->alt); } kfree(tmp_pps); mutex_unlock(&real_qp->qp_sec->mutex); } return ret; } static int ib_security_pkey_access(struct ib_device *dev, u32 port_num, u16 pkey_index, void *sec) { u64 subnet_prefix; u16 pkey; int ret; if (!rdma_protocol_ib(dev, port_num)) return 0; ret = ib_get_cached_pkey(dev, port_num, pkey_index, &pkey); if (ret) return ret; ib_get_cached_subnet_prefix(dev, port_num, &subnet_prefix); return security_ib_pkey_access(sec, subnet_prefix, pkey); } void ib_mad_agent_security_change(void) { struct ib_mad_agent *ag; spin_lock(&mad_agent_list_lock); list_for_each_entry(ag, &mad_agent_list, mad_agent_sec_list) WRITE_ONCE(ag->smp_allowed, !security_ib_endport_manage_subnet(ag->security, dev_name(&ag->device->dev), ag->port_num)); spin_unlock(&mad_agent_list_lock); } int ib_mad_agent_security_setup(struct ib_mad_agent *agent, enum ib_qp_type qp_type) { int ret; if (!rdma_protocol_ib(agent->device, agent->port_num)) return 0; INIT_LIST_HEAD(&agent->mad_agent_sec_list); ret = security_ib_alloc_security(&agent->security); if (ret) return ret; if (qp_type != IB_QPT_SMI) return 0; spin_lock(&mad_agent_list_lock); ret = security_ib_endport_manage_subnet(agent->security, dev_name(&agent->device->dev), agent->port_num); if (ret) goto free_security; WRITE_ONCE(agent->smp_allowed, true); list_add(&agent->mad_agent_sec_list, &mad_agent_list); spin_unlock(&mad_agent_list_lock); return 0; free_security: spin_unlock(&mad_agent_list_lock); security_ib_free_security(agent->security); return ret; } void ib_mad_agent_security_cleanup(struct ib_mad_agent *agent) { if (!rdma_protocol_ib(agent->device, agent->port_num)) return; if (agent->qp->qp_type == IB_QPT_SMI) { spin_lock(&mad_agent_list_lock); list_del(&agent->mad_agent_sec_list); spin_unlock(&mad_agent_list_lock); } security_ib_free_security(agent->security); } int ib_mad_enforce_security(struct ib_mad_agent_private *map, u16 pkey_index) { if (!rdma_protocol_ib(map->agent.device, map->agent.port_num)) return 0; if (map->agent.qp->qp_type == IB_QPT_SMI) { if (!READ_ONCE(map->agent.smp_allowed)) return -EACCES; return 0; } return ib_security_pkey_access(map->agent.device, map->agent.port_num, pkey_index, map->agent.security); } |
| 1 7 7 7 7 7 7 6 7 7 3 3 7 3 7 7 7 16 15 16 8 8 8 8 16 16 16 16 5 5 17 17 17 | 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 | // SPDX-License-Identifier: GPL-2.0 // rc-ir-raw.c - handle IR pulse/space events // // Copyright (C) 2010 by Mauro Carvalho Chehab #include <linux/export.h> #include <linux/kthread.h> #include <linux/mutex.h> #include <linux/kmod.h> #include <linux/sched.h> #include "rc-core-priv.h" /* Used to keep track of IR raw clients, protected by ir_raw_handler_lock */ static LIST_HEAD(ir_raw_client_list); /* Used to handle IR raw handler extensions */ DEFINE_MUTEX(ir_raw_handler_lock); static LIST_HEAD(ir_raw_handler_list); static atomic64_t available_protocols = ATOMIC64_INIT(0); static int ir_raw_event_thread(void *data) { struct ir_raw_event ev; struct ir_raw_handler *handler; struct ir_raw_event_ctrl *raw = data; struct rc_dev *dev = raw->dev; while (1) { mutex_lock(&ir_raw_handler_lock); while (kfifo_out(&raw->kfifo, &ev, 1)) { if (is_timing_event(ev)) { if (ev.duration == 0) dev_warn_once(&dev->dev, "nonsensical timing event of duration 0"); if (is_timing_event(raw->prev_ev) && !is_transition(&ev, &raw->prev_ev)) dev_warn_once(&dev->dev, "two consecutive events of type %s", TO_STR(ev.pulse)); } list_for_each_entry(handler, &ir_raw_handler_list, list) if (dev->enabled_protocols & handler->protocols || !handler->protocols) handler->decode(dev, ev); lirc_raw_event(dev, ev); raw->prev_ev = ev; } mutex_unlock(&ir_raw_handler_lock); set_current_state(TASK_INTERRUPTIBLE); if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); break; } else if (!kfifo_is_empty(&raw->kfifo)) set_current_state(TASK_RUNNING); schedule(); } return 0; } /** * ir_raw_event_store() - pass a pulse/space duration to the raw ir decoders * @dev: the struct rc_dev device descriptor * @ev: the struct ir_raw_event descriptor of the pulse/space * * This routine (which may be called from an interrupt context) stores a * pulse/space duration for the raw ir decoding state machines. Pulses are * signalled as positive values and spaces as negative values. A zero value * will reset the decoding state machines. */ int ir_raw_event_store(struct rc_dev *dev, struct ir_raw_event *ev) { if (!dev->raw) return -EINVAL; dev_dbg(&dev->dev, "sample: (%05dus %s)\n", ev->duration, TO_STR(ev->pulse)); if (!kfifo_put(&dev->raw->kfifo, *ev)) { dev_err(&dev->dev, "IR event FIFO is full!\n"); return -ENOSPC; } return 0; } EXPORT_SYMBOL_GPL(ir_raw_event_store); /** * ir_raw_event_store_edge() - notify raw ir decoders of the start of a pulse/space * @dev: the struct rc_dev device descriptor * @pulse: true for pulse, false for space * * This routine (which may be called from an interrupt context) is used to * store the beginning of an ir pulse or space (or the start/end of ir * reception) for the raw ir decoding state machines. This is used by * hardware which does not provide durations directly but only interrupts * (or similar events) on state change. */ int ir_raw_event_store_edge(struct rc_dev *dev, bool pulse) { ktime_t now; struct ir_raw_event ev = {}; if (!dev->raw) return -EINVAL; now = ktime_get(); ev.duration = ktime_to_us(ktime_sub(now, dev->raw->last_event)); ev.pulse = !pulse; return ir_raw_event_store_with_timeout(dev, &ev); } EXPORT_SYMBOL_GPL(ir_raw_event_store_edge); /* * ir_raw_event_store_with_timeout() - pass a pulse/space duration to the raw * ir decoders, schedule decoding and * timeout * @dev: the struct rc_dev device descriptor * @ev: the struct ir_raw_event descriptor of the pulse/space * * This routine (which may be called from an interrupt context) stores a * pulse/space duration for the raw ir decoding state machines, schedules * decoding and generates a timeout. */ int ir_raw_event_store_with_timeout(struct rc_dev *dev, struct ir_raw_event *ev) { ktime_t now; int rc = 0; if (!dev->raw) return -EINVAL; now = ktime_get(); spin_lock(&dev->raw->edge_spinlock); rc = ir_raw_event_store(dev, ev); dev->raw->last_event = now; /* timer could be set to timeout (125ms by default) */ if (!timer_pending(&dev->raw->edge_handle) || time_after(dev->raw->edge_handle.expires, jiffies + msecs_to_jiffies(15))) { mod_timer(&dev->raw->edge_handle, jiffies + msecs_to_jiffies(15)); } spin_unlock(&dev->raw->edge_spinlock); return rc; } EXPORT_SYMBOL_GPL(ir_raw_event_store_with_timeout); /** * ir_raw_event_store_with_filter() - pass next pulse/space to decoders with some processing * @dev: the struct rc_dev device descriptor * @ev: the event that has occurred * * This routine (which may be called from an interrupt context) works * in similar manner to ir_raw_event_store_edge. * This routine is intended for devices with limited internal buffer * It automerges samples of same type, and handles timeouts. Returns non-zero * if the event was added, and zero if the event was ignored due to idle * processing. */ int ir_raw_event_store_with_filter(struct rc_dev *dev, struct ir_raw_event *ev) { if (!dev->raw) return -EINVAL; /* Ignore spaces in idle mode */ if (dev->idle && !ev->pulse) return 0; else if (dev->idle) ir_raw_event_set_idle(dev, false); if (!dev->raw->this_ev.duration) dev->raw->this_ev = *ev; else if (ev->pulse == dev->raw->this_ev.pulse) dev->raw->this_ev.duration += ev->duration; else { ir_raw_event_store(dev, &dev->raw->this_ev); dev->raw->this_ev = *ev; } /* Enter idle mode if necessary */ if (!ev->pulse && dev->timeout && dev->raw->this_ev.duration >= dev->timeout) ir_raw_event_set_idle(dev, true); return 1; } EXPORT_SYMBOL_GPL(ir_raw_event_store_with_filter); /** * ir_raw_event_set_idle() - provide hint to rc-core when the device is idle or not * @dev: the struct rc_dev device descriptor * @idle: whether the device is idle or not */ void ir_raw_event_set_idle(struct rc_dev *dev, bool idle) { if (!dev->raw) return; dev_dbg(&dev->dev, "%s idle mode\n", idle ? "enter" : "leave"); if (idle) { dev->raw->this_ev.timeout = true; ir_raw_event_store(dev, &dev->raw->this_ev); dev->raw->this_ev = (struct ir_raw_event) {}; } if (dev->s_idle) dev->s_idle(dev, idle); dev->idle = idle; } EXPORT_SYMBOL_GPL(ir_raw_event_set_idle); /** * ir_raw_event_handle() - schedules the decoding of stored ir data * @dev: the struct rc_dev device descriptor * * This routine will tell rc-core to start decoding stored ir data. */ void ir_raw_event_handle(struct rc_dev *dev) { if (!dev->raw || !dev->raw->thread) return; wake_up_process(dev->raw->thread); } EXPORT_SYMBOL_GPL(ir_raw_event_handle); /* used internally by the sysfs interface */ u64 ir_raw_get_allowed_protocols(void) { return atomic64_read(&available_protocols); } static int change_protocol(struct rc_dev *dev, u64 *rc_proto) { struct ir_raw_handler *handler; u32 timeout = 0; mutex_lock(&ir_raw_handler_lock); list_for_each_entry(handler, &ir_raw_handler_list, list) { if (!(dev->enabled_protocols & handler->protocols) && (*rc_proto & handler->protocols) && handler->raw_register) handler->raw_register(dev); if ((dev->enabled_protocols & handler->protocols) && !(*rc_proto & handler->protocols) && handler->raw_unregister) handler->raw_unregister(dev); } mutex_unlock(&ir_raw_handler_lock); if (!dev->max_timeout) return 0; mutex_lock(&ir_raw_handler_lock); list_for_each_entry(handler, &ir_raw_handler_list, list) { if (handler->protocols & *rc_proto) { if (timeout < handler->min_timeout) timeout = handler->min_timeout; } } mutex_unlock(&ir_raw_handler_lock); if (timeout == 0) timeout = IR_DEFAULT_TIMEOUT; else timeout += MS_TO_US(10); if (timeout < dev->min_timeout) timeout = dev->min_timeout; else if (timeout > dev->max_timeout) timeout = dev->max_timeout; if (dev->s_timeout) dev->s_timeout(dev, timeout); else dev->timeout = timeout; return 0; } static void ir_raw_disable_protocols(struct rc_dev *dev, u64 protocols) { mutex_lock(&dev->lock); dev->enabled_protocols &= ~protocols; mutex_unlock(&dev->lock); } /** * ir_raw_gen_manchester() - Encode data with Manchester (bi-phase) modulation. * @ev: Pointer to pointer to next free event. *@ev is incremented for * each raw event filled. * @max: Maximum number of raw events to fill. * @timings: Manchester modulation timings. * @n: Number of bits of data. * @data: Data bits to encode. * * Encodes the @n least significant bits of @data using Manchester (bi-phase) * modulation with the timing characteristics described by @timings, writing up * to @max raw IR events using the *@ev pointer. * * Returns: 0 on success. * -ENOBUFS if there isn't enough space in the array to fit the * full encoded data. In this case all @max events will have been * written. */ int ir_raw_gen_manchester(struct ir_raw_event **ev, unsigned int max, const struct ir_raw_timings_manchester *timings, unsigned int n, u64 data) { bool need_pulse; u64 i; int ret = -ENOBUFS; i = BIT_ULL(n - 1); if (timings->leader_pulse) { if (!max--) return ret; init_ir_raw_event_duration((*ev), 1, timings->leader_pulse); if (timings->leader_space) { if (!max--) return ret; init_ir_raw_event_duration(++(*ev), 0, timings->leader_space); } } else { /* continue existing signal */ --(*ev); } /* from here on *ev will point to the last event rather than the next */ while (n && i > 0) { need_pulse = !(data & i); if (timings->invert) need_pulse = !need_pulse; if (need_pulse == !!(*ev)->pulse) { (*ev)->duration += timings->clock; } else { if (!max--) goto nobufs; init_ir_raw_event_duration(++(*ev), need_pulse, timings->clock); } if (!max--) goto nobufs; init_ir_raw_event_duration(++(*ev), !need_pulse, timings->clock); i >>= 1; } if (timings->trailer_space) { if (!(*ev)->pulse) (*ev)->duration += timings->trailer_space; else if (!max--) goto nobufs; else init_ir_raw_event_duration(++(*ev), 0, timings->trailer_space); } ret = 0; nobufs: /* point to the next event rather than last event before returning */ ++(*ev); return ret; } EXPORT_SYMBOL(ir_raw_gen_manchester); /** * ir_raw_gen_pd() - Encode data to raw events with pulse-distance modulation. * @ev: Pointer to pointer to next free event. *@ev is incremented for * each raw event filled. * @max: Maximum number of raw events to fill. * @timings: Pulse distance modulation timings. * @n: Number of bits of data. * @data: Data bits to encode. * * Encodes the @n least significant bits of @data using pulse-distance * modulation with the timing characteristics described by @timings, writing up * to @max raw IR events using the *@ev pointer. * * Returns: 0 on success. * -ENOBUFS if there isn't enough space in the array to fit the * full encoded data. In this case all @max events will have been * written. */ int ir_raw_gen_pd(struct ir_raw_event **ev, unsigned int max, const struct ir_raw_timings_pd *timings, unsigned int n, u64 data) { int i; int ret; unsigned int space; if (timings->header_pulse) { ret = ir_raw_gen_pulse_space(ev, &max, timings->header_pulse, timings->header_space); if (ret) return ret; } if (timings->msb_first) { for (i = n - 1; i >= 0; --i) { space = timings->bit_space[(data >> i) & 1]; ret = ir_raw_gen_pulse_space(ev, &max, timings->bit_pulse, space); if (ret) return ret; } } else { for (i = 0; i < n; ++i, data >>= 1) { space = timings->bit_space[data & 1]; ret = ir_raw_gen_pulse_space(ev, &max, timings->bit_pulse, space); if (ret) return ret; } } ret = ir_raw_gen_pulse_space(ev, &max, timings->trailer_pulse, timings->trailer_space); return ret; } EXPORT_SYMBOL(ir_raw_gen_pd); /** * ir_raw_gen_pl() - Encode data to raw events with pulse-length modulation. * @ev: Pointer to pointer to next free event. *@ev is incremented for * each raw event filled. * @max: Maximum number of raw events to fill. * @timings: Pulse distance modulation timings. * @n: Number of bits of data. * @data: Data bits to encode. * * Encodes the @n least significant bits of @data using space-distance * modulation with the timing characteristics described by @timings, writing up * to @max raw IR events using the *@ev pointer. * * Returns: 0 on success. * -ENOBUFS if there isn't enough space in the array to fit the * full encoded data. In this case all @max events will have been * written. */ int ir_raw_gen_pl(struct ir_raw_event **ev, unsigned int max, const struct ir_raw_timings_pl *timings, unsigned int n, u64 data) { int i; int ret = -ENOBUFS; unsigned int pulse; if (!max--) return ret; init_ir_raw_event_duration((*ev)++, 1, timings->header_pulse); if (timings->msb_first) { for (i = n - 1; i >= 0; --i) { if (!max--) return ret; init_ir_raw_event_duration((*ev)++, 0, timings->bit_space); if (!max--) return ret; pulse = timings->bit_pulse[(data >> i) & 1]; init_ir_raw_event_duration((*ev)++, 1, pulse); } } else { for (i = 0; i < n; ++i, data >>= 1) { if (!max--) return ret; init_ir_raw_event_duration((*ev)++, 0, timings->bit_space); if (!max--) return ret; pulse = timings->bit_pulse[data & 1]; init_ir_raw_event_duration((*ev)++, 1, pulse); } } if (!max--) return ret; init_ir_raw_event_duration((*ev)++, 0, timings->trailer_space); return 0; } EXPORT_SYMBOL(ir_raw_gen_pl); /** * ir_raw_encode_scancode() - Encode a scancode as raw events * * @protocol: protocol * @scancode: scancode filter describing a single scancode * @events: array of raw events to write into * @max: max number of raw events * * Attempts to encode the scancode as raw events. * * Returns: The number of events written. * -ENOBUFS if there isn't enough space in the array to fit the * encoding. In this case all @max events will have been written. * -EINVAL if the scancode is ambiguous or invalid, or if no * compatible encoder was found. */ int ir_raw_encode_scancode(enum rc_proto protocol, u32 scancode, struct ir_raw_event *events, unsigned int max) { struct ir_raw_handler *handler; int ret = -EINVAL; u64 mask = 1ULL << protocol; ir_raw_load_modules(&mask); mutex_lock(&ir_raw_handler_lock); list_for_each_entry(handler, &ir_raw_handler_list, list) { if (handler->protocols & mask && handler->encode) { ret = handler->encode(protocol, scancode, events, max); if (ret >= 0 || ret == -ENOBUFS) break; } } mutex_unlock(&ir_raw_handler_lock); return ret; } EXPORT_SYMBOL(ir_raw_encode_scancode); /** * ir_raw_edge_handle() - Handle ir_raw_event_store_edge() processing * * @t: timer_list * * This callback is armed by ir_raw_event_store_edge(). It does two things: * first of all, rather than calling ir_raw_event_handle() for each * edge and waking up the rc thread, 15 ms after the first edge * ir_raw_event_handle() is called. Secondly, generate a timeout event * no more IR is received after the rc_dev timeout. */ static void ir_raw_edge_handle(struct timer_list *t) { struct ir_raw_event_ctrl *raw = timer_container_of(raw, t, edge_handle); struct rc_dev *dev = raw->dev; unsigned long flags; ktime_t interval; spin_lock_irqsave(&dev->raw->edge_spinlock, flags); interval = ktime_sub(ktime_get(), dev->raw->last_event); if (ktime_to_us(interval) >= dev->timeout) { struct ir_raw_event ev = { .timeout = true, .duration = ktime_to_us(interval) }; ir_raw_event_store(dev, &ev); } else { mod_timer(&dev->raw->edge_handle, jiffies + usecs_to_jiffies(dev->timeout - ktime_to_us(interval))); } spin_unlock_irqrestore(&dev->raw->edge_spinlock, flags); ir_raw_event_handle(dev); } /** * ir_raw_encode_carrier() - Get carrier used for protocol * * @protocol: protocol * * Attempts to find the carrier for the specified protocol * * Returns: The carrier in Hz * -EINVAL if the protocol is invalid, or if no * compatible encoder was found. */ int ir_raw_encode_carrier(enum rc_proto protocol) { struct ir_raw_handler *handler; int ret = -EINVAL; u64 mask = BIT_ULL(protocol); mutex_lock(&ir_raw_handler_lock); list_for_each_entry(handler, &ir_raw_handler_list, list) { if (handler->protocols & mask && handler->encode) { ret = handler->carrier; break; } } mutex_unlock(&ir_raw_handler_lock); return ret; } EXPORT_SYMBOL(ir_raw_encode_carrier); /* * Used to (un)register raw event clients */ int ir_raw_event_prepare(struct rc_d |