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 // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/bug.h> #include <linux/atomic.h> #include <linux/errseq.h> /* * An errseq_t is a way of recording errors in one place, and allowing any * number of "subscribers" to tell whether it has changed since a previous * point where it was sampled. * * It's implemented as an unsigned 32-bit value. The low order bits are * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits * are used as a counter. This is done with atomics instead of locking so that * these functions can be called from any context. * * The general idea is for consumers to sample an errseq_t value. That value * can later be used to tell whether any new errors have occurred since that * sampling was done. * * Note that there is a risk of collisions if new errors are being recorded * frequently, since we have so few bits to use as a counter. * * To mitigate this, one bit is used as a flag to tell whether the value has * been sampled since a new value was recorded. That allows us to avoid bumping * the counter if no one has sampled it since the last time an error was * recorded. * * A new errseq_t should always be zeroed out. A errseq_t value of all zeroes * is the special (but common) case where there has never been an error. An all * zero value thus serves as the "epoch" if one wishes to know whether there * has ever been an error set since it was first initialized. */ /* The low bits are designated for error code (max of MAX_ERRNO) */ #define ERRSEQ_SHIFT ilog2(MAX_ERRNO + 1) /* This bit is used as a flag to indicate whether the value has been seen */ #define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT) /* The lowest bit of the counter */ #define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1)) /** * errseq_set - set a errseq_t for later reporting * @eseq: errseq_t field that should be set * @err: error to set (must be between -1 and -MAX_ERRNO) * * This function sets the error in @eseq, and increments the sequence counter * if the last sequence was sampled at some point in the past. * * Any error set will always overwrite an existing error. * * Return: The previous value, primarily for debugging purposes. The * return value should not be used as a previously sampled value in later * calls as it will not have the SEEN flag set. */ errseq_t errseq_set(errseq_t *eseq, int err) { errseq_t cur, old; /* MAX_ERRNO must be able to serve as a mask */ BUILD_BUG_ON_NOT_POWER_OF_2(MAX_ERRNO + 1); /* * Ensure the error code actually fits where we want it to go. If it * doesn't then just throw a warning and don't record anything. We * also don't accept zero here as that would effectively clear a * previous error. */ old = READ_ONCE(*eseq); if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO), "err = %d\n", err)) return old; for (;;) { errseq_t new; /* Clear out error bits and set new error */ new = (old & ~(MAX_ERRNO|ERRSEQ_SEEN)) | -err; /* Only increment if someone has looked at it */ if (old & ERRSEQ_SEEN) new += ERRSEQ_CTR_INC; /* If there would be no change, then call it done */ if (new == old) { cur = new; break; } /* Try to swap the new value into place */ cur = cmpxchg(eseq, old, new); /* * Call it success if we did the swap or someone else beat us * to it for the same value. */ if (likely(cur == old || cur == new)) break; /* Raced with an update, try again */ old = cur; } return cur; } EXPORT_SYMBOL(errseq_set); /** * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * * This function allows callers to initialise their errseq_t variable. * If the error has been "seen", new callers will not see an old error. * If there is an unseen error in @eseq, the caller of this function will * see it the next time it checks for an error. * * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); /* If nobody has seen this error yet, then we can be the first. */ if (!(old & ERRSEQ_SEEN)) old = 0; return old; } EXPORT_SYMBOL(errseq_sample); /** * errseq_check() - Has an error occurred since a particular sample point? * @eseq: Pointer to errseq_t value to be checked. * @since: Previously-sampled errseq_t from which to check. * * Grab the value that eseq points to, and see if it has changed @since * the given value was sampled. The @since value is not advanced, so there * is no need to mark the value as seen. * * Return: The latest error set in the errseq_t or 0 if it hasn't changed. */ int errseq_check(errseq_t *eseq, errseq_t since) { errseq_t cur = READ_ONCE(*eseq); if (likely(cur == since)) return 0; return -(cur & MAX_ERRNO); } EXPORT_SYMBOL(errseq_check); /** * errseq_check_and_advance() - Check an errseq_t and advance to current value. * @eseq: Pointer to value being checked and reported. * @since: Pointer to previously-sampled errseq_t to check against and advance. * * Grab the eseq value, and see whether it matches the value that @since * points to. If it does, then just return 0. * * If it doesn't, then the value has changed. Set the "seen" flag, and try to * swap it into place as the new eseq value. Then, set that value as the new * "since" value, and return whatever the error portion is set to. * * Note that no locking is provided here for concurrent updates to the "since" * value. The caller must provide that if necessary. Because of this, callers * may want to do a lockless errseq_check before taking the lock and calling * this. * * Return: Negative errno if one has been stored, or 0 if no new error has * occurred. */ int errseq_check_and_advance(errseq_t *eseq, errseq_t *since) { int err = 0; errseq_t old, new; /* * Most callers will want to use the inline wrapper to check this, * so that the common case of no error is handled without needing * to take the lock that protects the "since" value. */ old = READ_ONCE(*eseq); if (old != *since) { /* * Set the flag and try to swap it into place if it has * changed. * * We don't care about the outcome of the swap here. If the * swap doesn't occur, then it has either been updated by a * writer who is altering the value in some way (updating * counter or resetting the error), or another reader who is * just setting the "seen" flag. Either outcome is OK, and we * can advance "since" and return an error based on what we * have. */ new = old | ERRSEQ_SEEN; if (new != old) cmpxchg(eseq, old, new); *since = new; err = -(new & MAX_ERRNO); } return err; } EXPORT_SYMBOL(errseq_check_and_advance);
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 /* SPDX-License-Identifier: GPL-2.0-only */ /* * kref.h - library routines for handling generic reference counted objects * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Corp. * * based on kobject.h which was: * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (C) 2002-2003 Open Source Development Labs */ #ifndef _KREF_H_ #define _KREF_H_ #include <linux/spinlock.h> #include <linux/refcount.h> struct kref { refcount_t refcount; }; #define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { refcount_set(&kref->refcount, 1); } static inline unsigned int kref_read(const struct kref *kref) { return refcount_read(&kref->refcount); } /** * kref_get - increment refcount for object. * @kref: object. */ static inline void kref_get(struct kref *kref) { refcount_inc(&kref->refcount); } /** * kref_put - decrement refcount for object. * @kref: object. * @release: pointer to the function that will clean up the object when the * last reference to the object is released. * This pointer is required, and it is not acceptable to pass kfree * in as this function. * * Decrement the refcount, and if 0, call release(). * Return 1 if the object was removed, otherwise return 0. Beware, if this * function returns 0, you still can not count on the kref from remaining in * memory. Only use the return value if you want to see if the kref is now * gone, not present. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { if (refcount_dec_and_test(&kref->refcount)) { release(kref); return 1; } return 0; } static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) { if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } static inline int kref_put_lock(struct kref *kref, void (*release)(struct kref *kref), spinlock_t *lock) { if (refcount_dec_and_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } /** * kref_get_unless_zero - Increment refcount for object unless it is zero. * @kref: object. * * Return non-zero if the increment succeeded. Otherwise return 0. * * This function is intended to simplify locking around refcounting for * objects that can be looked up from a lookup structure, and which are * removed from that lookup structure in the object destructor. * Operations on such objects require at least a read lock around * lookup + kref_get, and a write lock around kref_put + remove from lookup * structure. Furthermore, RCU implementations become extremely tricky. * With a lookup followed by a kref_get_unless_zero *with return value check* * locking in the kref_put path can be deferred to the actual removal from * the lookup structure and RCU lookups become trivial. */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { return refcount_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/prandom.h * * Include file for the fast pseudo-random 32-bit * generation. */ #ifndef _LINUX_PRANDOM_H #define _LINUX_PRANDOM_H #include <linux/types.h> #include <linux/percpu.h> u32 prandom_u32(void); void prandom_bytes(void *buf, size_t nbytes); void prandom_seed(u32 seed); void prandom_reseed_late(void); DECLARE_PER_CPU(unsigned long, net_rand_noise); #define PRANDOM_ADD_NOISE(a, b, c, d) \ prandom_u32_add_noise((unsigned long)(a), (unsigned long)(b), \ (unsigned long)(c), (unsigned long)(d)) #if BITS_PER_LONG == 64 /* * The core SipHash round function. Each line can be executed in * parallel given enough CPU resources. */ #define PRND_SIPROUND(v0, v1, v2, v3) ( \ v0 += v1, v1 = rol64(v1, 13), v2 += v3, v3 = rol64(v3, 16), \ v1 ^= v0, v0 = rol64(v0, 32), v3 ^= v2, \ v0 += v3, v3 = rol64(v3, 21), v2 += v1, v1 = rol64(v1, 17), \ v3 ^= v0, v1 ^= v2, v2 = rol64(v2, 32) \ ) #define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261) #define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573) #elif BITS_PER_LONG == 32 /* * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash. * This is weaker, but 32-bit machines are not used for high-traffic * applications, so there is less output for an attacker to analyze. */ #define PRND_SIPROUND(v0, v1, v2, v3) ( \ v0 += v1, v1 = rol32(v1, 5), v2 += v3, v3 = rol32(v3, 8), \ v1 ^= v0, v0 = rol32(v0, 16), v3 ^= v2, \ v0 += v3, v3 = rol32(v3, 7), v2 += v1, v1 = rol32(v1, 13), \ v3 ^= v0, v1 ^= v2, v2 = rol32(v2, 16) \ ) #define PRND_K0 0x6c796765 #define PRND_K1 0x74656462 #else #error Unsupported BITS_PER_LONG #endif static inline void prandom_u32_add_noise(unsigned long a, unsigned long b, unsigned long c, unsigned long d) { /* * This is not used cryptographically; it's just * a convenient 4-word hash function. (3 xor, 2 add, 2 rol) */ a ^= raw_cpu_read(net_rand_noise); PRND_SIPROUND(a, b, c, d); raw_cpu_write(net_rand_noise, d); } struct rnd_state { __u32 s1, s2, s3, s4; }; u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); #define prandom_init_once(pcpu_state) \ DO_ONCE(prandom_seed_full_state, (pcpu_state)) /** * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) * @ep_ro: right open interval endpoint * * Returns a pseudo-random number that is in interval [0, ep_ro). Note * that the result depends on PRNG being well distributed in [0, ~0U] * u32 space. Here we use maximally equidistributed combined Tausworthe * generator, that is, prandom_u32(). This is useful when requesting a * random index of an array containing ep_ro elements, for example. * * Returns: pseudo-random number in interval [0, ep_ro) */ static inline u32 prandom_u32_max(u32 ep_ro) { return (u32)(((u64) prandom_u32() * ep_ro) >> 32); } /* * Handle minimum values for seeds */ static inline u32 __seed(u32 x, u32 m) { return (x < m) ? x + m : x; } /** * prandom_seed_state - set seed for prandom_u32_state(). * @state: pointer to state structure to receive the seed. * @seed: arbitrary 64-bit value to use as a seed. */ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) { u32 i = ((seed >> 32) ^ (seed << 10) ^ seed) & 0xffffffffUL; state->s1 = __seed(i, 2U); state->s2 = __seed(i, 8U); state->s3 = __seed(i, 16U); state->s4 = __seed(i, 128U); PRANDOM_ADD_NOISE(state, i, 0, 0); } /* Pseudo random number generator from numerical recipes. */ static inline u32 next_pseudo_random32(u32 seed) { return seed * 1664525 + 1013904223; } #endif
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 // SPDX-License-Identifier: GPL-2.0 /* File: fs/ext4/acl.h (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #include <linux/posix_acl_xattr.h> #define EXT4_ACL_VERSION 0x0001 typedef struct { __le16 e_tag; __le16 e_perm; __le32 e_id; } ext4_acl_entry; typedef struct { __le16 e_tag; __le16 e_perm; } ext4_acl_entry_short; typedef struct { __le32 a_version; } ext4_acl_header; static inline size_t ext4_acl_size(int count) { if (count <= 4) { return sizeof(ext4_acl_header) + count * sizeof(ext4_acl_entry_short); } else { return sizeof(ext4_acl_header) + 4 * sizeof(ext4_acl_entry_short) + (count - 4) * sizeof(ext4_acl_entry); } } static inline int ext4_acl_count(size_t size) { ssize_t s; size -= sizeof(ext4_acl_header); s = size - 4 * sizeof(ext4_acl_entry_short); if (s < 0) { if (size % sizeof(ext4_acl_entry_short)) return -1; return size / sizeof(ext4_acl_entry_short); } else { if (s % sizeof(ext4_acl_entry)) return -1; return s / sizeof(ext4_acl_entry) + 4; } } #ifdef CONFIG_EXT4_FS_POSIX_ACL /* acl.c */ struct posix_acl *ext4_get_acl(struct inode *inode, int type); int ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type); extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); #else /* CONFIG_EXT4_FS_POSIX_ACL */ #include <linux/sched.h> #define ext4_get_acl NULL #define ext4_set_acl NULL static inline int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { return 0; } #endif /* CONFIG_EXT4_FS_POSIX_ACL */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _linux_POSIX_TIMERS_H #define _linux_POSIX_TIMERS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/alarmtimer.h> #include <linux/timerqueue.h> #include <linux/task_work.h> struct kernel_siginfo; struct task_struct; /* * Bit fields within a clockid: * * The most significant 29 bits hold either a pid or a file descriptor. * * Bit 2 indicates whether a cpu clock refers to a thread or a process. * * Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3. * * A clockid is invalid if bits 2, 1, and 0 are all set. */ #define CPUCLOCK_PID(clock) ((pid_t) ~((clock) >> 3)) #define CPUCLOCK_PERTHREAD(clock) \ (((clock) & (clockid_t) CPUCLOCK_PERTHREAD_MASK) != 0) #define CPUCLOCK_PERTHREAD_MASK 4 #define CPUCLOCK_WHICH(clock) ((clock) & (clockid_t) CPUCLOCK_CLOCK_MASK) #define CPUCLOCK_CLOCK_MASK 3 #define CPUCLOCK_PROF 0 #define CPUCLOCK_VIRT 1 #define CPUCLOCK_SCHED 2 #define CPUCLOCK_MAX 3 #define CLOCKFD CPUCLOCK_MAX #define CLOCKFD_MASK (CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK) static inline clockid_t make_process_cpuclock(const unsigned int pid, const clockid_t clock) { return ((~pid) << 3) | clock; } static inline clockid_t make_thread_cpuclock(const unsigned int tid, const clockid_t clock) { return make_process_cpuclock(tid, clock | CPUCLOCK_PERTHREAD_MASK); } static inline clockid_t fd_to_clockid(const int fd) { return make_process_cpuclock((unsigned int) fd, CLOCKFD); } static inline int clockid_to_fd(const clockid_t clk) { return ~(clk >> 3); } #ifdef CONFIG_POSIX_TIMERS /** * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig * @head: timerqueue head on which this timer is queued * @task: Pointer to target task * @elist: List head for the expiry list * @firing: Timer is currently firing */ struct cpu_timer { struct timerqueue_node node; struct timerqueue_head *head; struct pid *pid; struct list_head elist; int firing; }; static inline bool cpu_timer_enqueue(struct timerqueue_head *head, struct cpu_timer *ctmr) { ctmr->head = head; return timerqueue_add(head, &ctmr->node); } static inline void cpu_timer_dequeue(struct cpu_timer *ctmr) { if (ctmr->head) { timerqueue_del(ctmr->head, &ctmr->node); ctmr->head = NULL; } } static inline u64 cpu_timer_getexpires(struct cpu_timer *ctmr) { return ctmr->node.expires; } static inline void cpu_timer_setexpires(struct cpu_timer *ctmr, u64 exp) { ctmr->node.expires = exp; } /** * posix_cputimer_base - Container per posix CPU clock * @nextevt: Earliest-expiration cache * @tqhead: timerqueue head for cpu_timers */ struct posix_cputimer_base { u64 nextevt; struct timerqueue_head tqhead; }; /** * posix_cputimers - Container for posix CPU timer related data * @bases: Base container for posix CPU clocks * @timers_active: Timers are queued. * @expiry_active: Timer expiry is active. Used for * process wide timers to avoid multiple * task trying to handle expiry concurrently * * Used in task_struct and signal_struct */ struct posix_cputimers { struct posix_cputimer_base bases[CPUCLOCK_MAX]; unsigned int timers_active; unsigned int expiry_active; }; /** * posix_cputimers_work - Container for task work based posix CPU timer expiry * @work: The task work to be scheduled * @scheduled: @work has been scheduled already, no further processing */ struct posix_cputimers_work { struct callback_head work; unsigned int scheduled; }; static inline void posix_cputimers_init(struct posix_cputimers *pct) { memset(pct, 0, sizeof(*pct)); pct->bases[0].nextevt = U64_MAX; pct->bases[1].nextevt = U64_MAX; pct->bases[2].nextevt = U64_MAX; } void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit); static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, u64 runtime) { pct->bases[CPUCLOCK_SCHED].nextevt = runtime; } /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ .nextevt = U64_MAX, \ } #define INIT_CPU_TIMERBASES(b) { \ INIT_CPU_TIMERBASE(b[0]), \ INIT_CPU_TIMERBASE(b[1]), \ INIT_CPU_TIMERBASE(b[2]), \ } #define INIT_CPU_TIMERS(s) \ .posix_cputimers = { \ .bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases), \ }, #else struct posix_cputimers { }; struct cpu_timer { }; #define INIT_CPU_TIMERS(s) static inline void posix_cputimers_init(struct posix_cputimers *pct) { } static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK void clear_posix_cputimers_work(struct task_struct *p); void posix_cputimers_init_work(void); #else static inline void clear_posix_cputimers_work(struct task_struct *p) { } static inline void posix_cputimers_init_work(void) { } #endif #define REQUEUE_PENDING 1 /** * struct k_itimer - POSIX.1b interval timer structure. * @list: List head for binding the timer to signals->posix_timers * @t_hash: Entry in the posix timer hash table * @it_lock: Lock protecting the timer * @kclock: Pointer to the k_clock struct handling this timer * @it_clock: The posix timer clock id * @it_id: The posix timer id for identifying the timer * @it_active: Marker that timer is active * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal * @it_requeue_pending: Indicator that timer waits for being requeued on * signal delivery * @it_sigev_notify: The notify word of sigevent struct for signal delivery * @it_interval: The interval for periodic timers * @it_signal: Pointer to the creators signal struct * @it_pid: The pid of the process/task targeted by the signal * @it_process: The task to wakeup on clock_nanosleep (CPU timers) * @sigq: Pointer to preallocated sigqueue * @it: Union representing the various posix timer type * internals. * @rcu: RCU head for freeing the timer. */ struct k_itimer { struct list_head list; struct hlist_node t_hash; spinlock_t it_lock; const struct k_clock *kclock; clockid_t it_clock; timer_t it_id; int it_active; s64 it_overrun; s64 it_overrun_last; int it_requeue_pending; int it_sigev_notify; ktime_t it_interval; struct signal_struct *it_signal; union { struct pid *it_pid; struct task_struct *it_process; }; struct sigqueue *sigq; union { struct { struct hrtimer timer; } real; struct cpu_timer cpu; struct { struct alarm alarmtimer; } alarm; } it; struct rcu_head rcu; }; void run_posix_cpu_timers(void); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, u64 *newval, u64 *oldval); void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); void posixtimer_rearm(struct kernel_siginfo *info); #endif
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMSTAT_H #define _LINUX_VMSTAT_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> #include <linux/static_key.h> #include <linux/mmdebug.h> extern int sysctl_stat_interval; #ifdef CONFIG_NUMA #define ENABLE_NUMA_STAT 1 #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { unsigned nr_dirty; unsigned nr_unqueued_dirty; unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; unsigned nr_pageout; unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; }; enum writeback_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, NR_VM_WRITEBACK_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. * * Counters should only be incremented and no critical kernel component * should rely on the counter values. * * Counters are handled completely inline. On many platforms the code * generated will simply be the increment of a global address. */ struct vm_event_state { unsigned long event[NR_VM_EVENT_ITEMS]; }; DECLARE_PER_CPU(struct vm_event_state, vm_event_states); /* * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the * local_irq_disable overhead. */ static inline void __count_vm_event(enum vm_event_item item) { raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); extern void vm_events_fold_cpu(int cpu); #else /* Disable counters */ static inline void count_vm_event(enum vm_event_item item) { } static inline void count_vm_events(enum vm_event_item item, long delta) { } static inline void __count_vm_event(enum vm_event_item item) { } static inline void __count_vm_events(enum vm_event_item item, long delta) { } static inline void all_vm_events(unsigned long *ret) { } static inline void vm_events_fold_cpu(int cpu) { } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_NUMA_BALANCING #define count_vm_numa_event(x) count_vm_event(x) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_DEBUG_TLBFLUSH #define count_vm_tlb_event(x) count_vm_event(x) #define count_vm_tlb_events(x, y) count_vm_events(x, y) #else #define count_vm_tlb_event(x) do {} while (0) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif #ifdef CONFIG_DEBUG_VM_VMACACHE #define count_vm_vmacache_event(x) count_vm_event(x) #else #define count_vm_vmacache_event(x) do {} while (0) #endif #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA static inline void zone_numa_state_add(long x, struct zone *zone, enum numa_stat_item item) { atomic_long_add(x, &zone->vm_numa_stat[item]); atomic_long_add(x, &vm_numa_stat[item]); } static inline unsigned long global_numa_state(enum numa_stat_item item) { long x = atomic_long_read(&vm_numa_stat[item]); return x; } static inline unsigned long zone_numa_state_snapshot(struct zone *zone, enum numa_stat_item item) { long x = atomic_long_read(&zone->vm_numa_stat[item]); int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]; return x; } #endif /* CONFIG_NUMA */ static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); atomic_long_add(x, &vm_zone_stat[item]); } static inline void node_page_state_add(long x, struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_add(x, &pgdat->vm_stat[item]); atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state_pages(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); return global_node_page_state_pages(item); } static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * More accurate version that also considers the currently pending * deltas. For that we need to loop over all cpus to find the current * deltas. There is no synchronization so the result cannot be * exactly accurate either. */ static inline unsigned long zone_page_state_snapshot(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; #endif return x; } #ifdef CONFIG_NUMA extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item); extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); void __inc_node_page_state(struct page *, enum node_stat_item); void __dec_node_page_state(struct page *, enum node_stat_item); void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)); #else /* CONFIG_SMP */ /* * We do not maintain differentials in a single processor configuration. * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } node_page_state_add(delta, pgdat, item); } static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); atomic_long_inc(&vm_zone_stat[item]); } static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_inc(&pgdat->vm_stat[item]); atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); atomic_long_dec(&vm_zone_stat[item]); } static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_dec(&pgdat->vm_stat[item]); atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } static inline void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } static inline void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. */ #define inc_zone_page_state __inc_zone_page_state #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state #define inc_node_page_state __inc_node_page_state #define dec_node_page_state __dec_node_page_state #define mod_node_page_state __mod_node_page_state #define inc_zone_state __inc_zone_state #define inc_node_state __inc_node_state #define dec_zone_state __dec_zone_state #define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { } #endif /* CONFIG_SMP */ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, int migratetype) { __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); if (is_migrate_cma(migratetype)) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); } extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) { return vmstat_text[item]; } #ifdef CONFIG_NUMA static inline const char *numa_stat_name(enum numa_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + item]; } #endif /* CONFIG_NUMA */ static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_STAT_ITEMS + item]; } static inline const char *lru_list_name(enum lru_list lru) { return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } static inline const char *writeback_stat_name(enum writeback_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_STAT_ITEMS + NR_VM_NODE_STAT_ITEMS + item]; } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_STAT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_WRITEBACK_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ #endif /* _LINUX_VMSTAT_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_LOCAL_H #define _ASM_X86_LOCAL_H #include <linux/percpu.h> #include <linux/atomic.h> #include <asm/asm.h> typedef struct { atomic_long_t a; } local_t; #define LOCAL_INIT(i) { ATOMIC_LONG_INIT(i) } #define local_read(l) atomic_long_read(&(l)->a) #define local_set(l, i) atomic_long_set(&(l)->a, (i)) static inline void local_inc(local_t *l) { asm volatile(_ASM_INC "%0" : "+m" (l->a.counter)); } static inline void local_dec(local_t *l) { asm volatile(_ASM_DEC "%0" : "+m" (l->a.counter)); } static inline void local_add(long i, local_t *l) { asm volatile(_ASM_ADD "%1,%0" : "+m" (l->a.counter) : "ir" (i)); } static inline void local_sub(long i, local_t *l) { asm volatile(_ASM_SUB "%1,%0" : "+m" (l->a.counter) : "ir" (i)); } /** * local_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @l: pointer to type local_t * * Atomically subtracts @i from @l and returns * true if the result is zero, or false for all * other cases. */ static inline bool local_sub_and_test(long i, local_t *l) { return GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, e, "er", i); } /** * local_dec_and_test - decrement and test * @l: pointer to type local_t * * Atomically decrements @l by 1 and * returns true if the result is 0, or false for all other * cases. */ static inline bool local_dec_and_test(local_t *l) { return GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, e); } /** * local_inc_and_test - increment and test * @l: pointer to type local_t * * Atomically increments @l by 1 * and returns true if the result is zero, or false for all * other cases. */ static inline bool local_inc_and_test(local_t *l) { return GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, e); } /** * local_add_negative - add and test if negative * @i: integer value to add * @l: pointer to type local_t * * Atomically adds @i to @l and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static inline bool local_add_negative(long i, local_t *l) { return GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, s, "er", i); } /** * local_add_return - add and return * @i: integer value to add * @l: pointer to type local_t * * Atomically adds @i to @l and returns @i + @l */ static inline long local_add_return(long i, local_t *l) { long __i = i; asm volatile(_ASM_XADD "%0, %1;" : "+r" (i), "+m" (l->a.counter) : : "memory"); return i + __i; } static inline long local_sub_return(long i, local_t *l) { return local_add_return(-i, l); } #define local_inc_return(l) (local_add_return(1, l)) #define local_dec_return(l) (local_sub_return(1, l)) #define local_cmpxchg(l, o, n) \ (cmpxchg_local(&((l)->a.counter), (o), (n))) /* Always has a lock prefix */ #define local_xchg(l, n) (xchg(&((l)->a.counter), (n))) /** * local_add_unless - add unless the number is a given value * @l: pointer of type local_t * @a: the amount to add to l... * @u: ...unless l is equal to u. * * Atomically adds @a to @l, so long as it was not @u. * Returns non-zero if @l was not @u, and zero otherwise. */ #define local_add_unless(l, a, u) \ ({ \ long c, old; \ c = local_read((l)); \ for (;;) { \ if (unlikely(c == (u))) \ break; \ old = local_cmpxchg((l), c, c + (a)); \ if (likely(old == c)) \ break; \ c = old; \ } \ c != (u); \ }) #define local_inc_not_zero(l) local_add_unless((l), 1, 0) /* On x86_32, these are no better than the atomic variants. * On x86-64 these are better than the atomic variants on SMP kernels * because they dont use a lock prefix. */ #define __local_inc(l) local_inc(l) #define __local_dec(l) local_dec(l) #define __local_add(i, l) local_add((i), (l)) #define __local_sub(i, l) local_sub((i), (l)) #endif /* _ASM_X86_LOCAL_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SPINLOCK_H #define __LINUX_SPINLOCK_H /* * include/linux/spinlock.h - generic spinlock/rwlock declarations * * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the * initializers * * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the arch_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the arch_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ #include <linux/typecheck.h> #include <linux/preempt.h> #include <linux/linkage.h> #include <linux/compiler.h> #include <linux/irqflags.h> #include <linux/thread_info.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <asm/barrier.h> #include <asm/mmiowb.h> /* * Must define these before including other files, inline functions need them */ #define LOCK_SECTION_NAME ".text..lock."KBUILD_BASENAME #define LOCK_SECTION_START(extra) \ ".subsection 1\n\t" \ extra \ ".ifndef " LOCK_SECTION_NAME "\n\t" \ LOCK_SECTION_NAME ":\n\t" \ ".endif\n" #define LOCK_SECTION_END \ ".previous\n\t" #define __lockfunc __section(".spinlock.text") /* * Pull the arch_spinlock_t and arch_rwlock_t definitions: */ #include <linux/spinlock_types.h> /* * Pull the arch_spin*() functions/declarations (UP-nondebug doesn't need them): */ #ifdef CONFIG_SMP # include <asm/spinlock.h> #else # include <linux/spinlock_up.h> #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, struct lock_class_key *key, short inner); # define raw_spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init((lock), #lock, &__key, LD_WAIT_SPIN); \ } while (0) #else # define raw_spin_lock_init(lock) \ do { *(lock) = __RAW_SPIN_LOCK_UNLOCKED(lock); } while (0) #endif #define raw_spin_is_locked(lock) arch_spin_is_locked(&(lock)->raw_lock) #ifdef arch_spin_is_contended #define raw_spin_is_contended(lock) arch_spin_is_contended(&(lock)->raw_lock) #else #define raw_spin_is_contended(lock) (((void)(lock), 0)) #endif /*arch_spin_is_contended*/ /* * smp_mb__after_spinlock() provides the equivalent of a full memory barrier * between program-order earlier lock acquisitions and program-order later * memory accesses. * * This guarantees that the following two properties hold: * * 1) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 * * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); * spin_lock(S); smp_mb(); * smp_mb__after_spinlock(); r1 = READ_ONCE(X); * r0 = READ_ONCE(Y); * spin_unlock(S); * * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments * preceding the call to smp_mb__after_spinlock() in __schedule() and in * try_to_wake_up(). * * 2) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 CPU2 * * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); * WRITE_ONCE(Y, 1); * spin_unlock(S); * * it is forbidden that CPU0's critical section executes before CPU1's * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments * preceding the calls to smp_rmb() in try_to_wake_up() for similar * snippets but "projected" onto two CPUs. * * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO * architectures imply an smp_mb() for each atomic instruction and equally don't * need more. * * Architectures that can implement ACQUIRE better need to take care. */ #ifndef smp_mb__after_spinlock #define smp_mb__after_spinlock() do { } while (0) #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); #define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock) extern int do_raw_spin_trylock(raw_spinlock_t *lock); extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock); #else static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) { __acquire(lock); arch_spin_lock(&lock->raw_lock); mmiowb_spin_lock(); } #ifndef arch_spin_lock_flags #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) #endif static inline void do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lock) { __acquire(lock); arch_spin_lock_flags(&lock->raw_lock, *flags); mmiowb_spin_lock(); } static inline int do_raw_spin_trylock(raw_spinlock_t *lock) { int ret = arch_spin_trylock(&(lock)->raw_lock); if (ret) mmiowb_spin_lock(); return ret; } static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) { mmiowb_spin_unlock(); arch_spin_unlock(&lock->raw_lock); __release(lock); } #endif /* * Define the various spin_lock methods. Note we define these * regardless of whether CONFIG_SMP or CONFIG_PREEMPTION are set. The * various methods are defined as nops in the case they are not * required. */ #define raw_spin_trylock(lock) __cond_lock(lock, _raw_spin_trylock(lock)) #define raw_spin_lock(lock) _raw_spin_lock(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock_nested(lock, subclass) # define raw_spin_lock_nest_lock(lock, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\ _raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ } while (0) #else /* * Always evaluate the 'subclass' argument to avoid that the compiler * warns about set-but-not-used variables when building with * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1. */ # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock(((void)(subclass), (lock))) # define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock) #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave_nested(lock, subclass); \ } while (0) #else #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #endif #else #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_lock_irqsave(lock, flags); \ } while (0) #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ raw_spin_lock_irqsave(lock, flags) #endif #define raw_spin_lock_irq(lock) _raw_spin_lock_irq(lock) #define raw_spin_lock_bh(lock) _raw_spin_lock_bh(lock) #define raw_spin_unlock(lock) _raw_spin_unlock(lock) #define raw_spin_unlock_irq(lock) _raw_spin_unlock_irq(lock) #define raw_spin_unlock_irqrestore(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_unlock_irqrestore(lock, flags); \ } while (0) #define raw_spin_unlock_bh(lock) _raw_spin_unlock_bh(lock) #define raw_spin_trylock_bh(lock) \ __cond_lock(lock, _raw_spin_trylock_bh(lock)) #define raw_spin_trylock_irq(lock) \ ({ \ local_irq_disable(); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_enable(); 0; }); \ }) #define raw_spin_trylock_irqsave(lock, flags) \ ({ \ local_irq_save(flags); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_restore(flags); 0; }); \ }) /* Include rwlock functions */ #include <linux/rwlock.h> /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) # include <linux/spinlock_api_smp.h> #else # include <linux/spinlock_api_up.h> #endif /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock) { return &lock->rlock; } #ifdef CONFIG_DEBUG_SPINLOCK # define spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init(spinlock_check(lock), \ #lock, &__key, LD_WAIT_CONFIG); \ } while (0) #else # define spin_lock_init(_lock) \ do { \ spinlock_check(_lock); \ *(_lock) = __SPIN_LOCK_UNLOCKED(_lock); \ } while (0) #endif static __always_inline void spin_lock(spinlock_t *lock) { raw_spin_lock(&lock->rlock); } static __always_inline void spin_lock_bh(spinlock_t *lock) { raw_spin_lock_bh(&lock->rlock); } static __always_inline int spin_trylock(spinlock_t *lock) { return raw_spin_trylock(&lock->rlock); } #define spin_lock_nested(lock, subclass) \ do { \ raw_spin_lock_nested(spinlock_check(lock), subclass); \ } while (0) #define spin_lock_nest_lock(lock, nest_lock) \ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ } while (0) static __always_inline void spin_lock_irq(spinlock_t *lock) { raw_spin_lock_irq(&lock->rlock); } #define spin_lock_irqsave(lock, flags) \ do { \ raw_spin_lock_irqsave(spinlock_check(lock), flags); \ } while (0) #define spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ raw_spin_lock_irqsave_nested(spinlock_check(lock), flags, subclass); \ } while (0) static __always_inline void spin_unlock(spinlock_t *lock) { raw_spin_unlock(&lock->rlock); } static __always_inline void spin_unlock_bh(spinlock_t *lock) { raw_spin_unlock_bh(&lock->rlock); } static __always_inline void spin_unlock_irq(spinlock_t *lock) { raw_spin_unlock_irq(&lock->rlock); } static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) { raw_spin_unlock_irqrestore(&lock->rlock, flags); } static __always_inline int spin_trylock_bh(spinlock_t *lock) { return raw_spin_trylock_bh(&lock->rlock); } static __always_inline int spin_trylock_irq(spinlock_t *lock) { return raw_spin_trylock_irq(&lock->rlock); } #define spin_trylock_irqsave(lock, flags) \ ({ \ raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) /** * spin_is_locked() - Check whether a spinlock is locked. * @lock: Pointer to the spinlock. * * This function is NOT required to provide any memory ordering * guarantees; it could be used for debugging purposes or, when * additional synchronization is needed, accompanied with other * constructs (memory barriers) enforcing the synchronization. * * Returns: 1 if @lock is locked, 0 otherwise. * * Note that the function only tells you that the spinlock is * seen to be locked, not that it is locked on your CPU. * * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n, * the return value is always 0 (see include/linux/spinlock_up.h). * Therefore you should not rely heavily on the return value. */ static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); } static __always_inline int spin_is_contended(spinlock_t *lock) { return raw_spin_is_contended(&lock->rlock); } #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) */ #include <linux/atomic.h> /** * atomic_dec_and_lock - lock on reaching reference count zero * @atomic: the atomic counter * @lock: the spinlock in question * * Decrements @atomic by 1. If the result is 0, returns true and locks * @lock. Returns false for all other cases. */ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags); #define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, struct lock_class_key *key); #define alloc_bucket_spinlocks(locks, lock_mask, max_size, cpu_mult, gfp) \ ({ \ static struct lock_class_key key; \ int ret; \ \ ret = __alloc_bucket_spinlocks(locks, lock_mask, max_size, \ cpu_mult, gfp, #locks, &key); \ ret; \ }) void free_bucket_spinlocks(spinlock_t *locks); #endif /* __LINUX_SPINLOCK_H */
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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/include/linux/jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com> * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved * * Definitions for transaction data structures for the buffer cache * filesystem journaling support. */ #ifndef _LINUX_JBD2_H #define _LINUX_JBD2_H /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ #include "jfs_compat.h" #define JBD2_DEBUG #else #include <linux/types.h> #include <linux/buffer_head.h> #include <linux/journal-head.h> #include <linux/stddef.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> #include <linux/bit_spinlock.h> #include <linux/blkdev.h> #include <crypto/hash.h> #endif #define journal_oom_retry 1 /* * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext4 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on * known-good hardware we may want to trap these errors. */ #undef JBD2_PARANOID_IOFAIL /* * The default maximum commit age, in seconds. */ #define JBD2_DEFAULT_MAX_COMMIT_AGE 5 #ifdef CONFIG_JBD2_DEBUG /* * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING extern ushort jbd2_journal_enable_debug; void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); #define jbd_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else #define jbd_debug(n, fmt, a...) /**/ #endif extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 #define JBD2_MIN_FC_BLOCKS 256 #ifdef __KERNEL__ /** * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. * * All filesystem modifications made by the process go * through this handle. Recursive operations (such as quota operations) * are gathered into a single update. * * The buffer credits field is used to account for journaled buffers * being modified by the running process. To ensure that there is * enough log space for all outstanding operations, we need to limit the * number of outstanding buffers possible at any time. When the * operation completes, any buffer credits not used are credited back to * the transaction, so that at all times we know how many buffers the * outstanding updates on a transaction might possibly touch. * * This is an opaque datatype. **/ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ /** * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. * * journal_t is linked to from the fs superblock structure. * * We use the journal_t to keep track of all outstanding transaction * activity on the filesystem, and to manage the state of the log * writing process. * * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ #endif /* * Internal structures used by the logging mechanism: */ #define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ /* * On-disk structures */ /* * Descriptor block types: */ #define JBD2_DESCRIPTOR_BLOCK 1 #define JBD2_COMMIT_BLOCK 2 #define JBD2_SUPERBLOCK_V1 3 #define JBD2_SUPERBLOCK_V2 4 #define JBD2_REVOKE_BLOCK 5 /* * Standard header for all descriptor blocks: */ typedef struct journal_header_s { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; } journal_header_t; /* * Checksum types. */ #define JBD2_CRC32_CHKSUM 1 #define JBD2_MD5_CHKSUM 2 #define JBD2_SHA1_CHKSUM 3 #define JBD2_CRC32C_CHKSUM 4 #define JBD2_CRC32_CHKSUM_SIZE 4 #define JBD2_CHECKSUM_BYTES (32 / sizeof(u32)) /* * Commit block header for storing transactional checksums: * * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum* * fields are used to store a checksum of the descriptor and data blocks. * * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum * field is used to store crc32c(uuid+commit_block). Each journal metadata * block gets its own checksum, and data block checksums are stored in * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses * journal_block_tag3_t to store a full 32-bit checksum. Everything else * is the same as v2. * * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; unsigned char h_chksum_type; unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; __be64 h_commit_sec; __be32 h_commit_nsec; }; /* * The block tag: used to describe a single buffer in the journal. * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ typedef struct journal_block_tag3_s { __be32 t_blocknr; /* The on-disk block number */ __be32 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ __be32 t_checksum; /* crc32c(uuid+seq+block) */ } journal_block_tag3_t; typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ __be16 t_checksum; /* truncated crc32c(uuid+seq+block) */ __be16 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; /* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; /* * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log */ typedef struct jbd2_journal_revoke_header_s { journal_header_t r_header; __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ #define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ #define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ /* * The journal superblock. All fields are in big-endian byte order. */ typedef struct journal_superblock_s { /* 0x0000 */ journal_header_t s_header; /* 0x000C */ /* Static information describing the journal */ __be32 s_blocksize; /* journal device blocksize */ __be32 s_maxlen; /* total blocks in journal file */ __be32 s_first; /* first block of log information */ /* 0x0018 */ /* Dynamic information describing the current state of the log */ __be32 s_sequence; /* first commit ID expected in log */ __be32 s_start; /* blocknr of start of log */ /* 0x0020 */ /* Error value, as set by jbd2_journal_abort(). */ __be32 s_errno; /* 0x0024 */ /* Remaining fields are only valid in a version-2 superblock */ __be32 s_feature_compat; /* compatible feature set */ __be32 s_feature_incompat; /* incompatible feature set */ __be32 s_feature_ro_compat; /* readonly-compatible feature set */ /* 0x0030 */ __u8 s_uuid[16]; /* 128-bit uuid for journal */ /* 0x0040 */ __be32 s_nr_users; /* Nr of filesystems sharing log */ __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ /* 0x0048 */ __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ __be32 s_max_trans_data; /* Limit of data blocks per trans. */ /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; /* 0x0054 */ __be32 s_num_fc_blks; /* Number of fast commit blocks */ /* 0x0058 */ __u32 s_padding[41]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ /* 0x0400 */ } journal_superblock_t; /* Use the jbd2_{has,set,clear}_feature_* helpers; these will be removed */ #define JBD2_HAS_COMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask)))) #define JBD2_HAS_RO_COMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask)))) #define JBD2_HAS_INCOMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) #define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 #define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 /* See "journal feature predicate functions" below */ /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ #include <linux/fs.h> #include <linux/sched.h> enum jbd_state_bits { BH_JBD /* Has an attached ext3 journal_head */ = BH_PrivateStart, BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ BH_Freed, /* Has been freed (truncated) */ BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ BH_JBDPrivateStart, /* First bit available for private use by FS */ }; BUFFER_FNS(JBD, jbd) BUFFER_FNS(JWrite, jwrite) BUFFER_FNS(JBDDirty, jbddirty) TAS_BUFFER_FNS(JBDDirty, jbddirty) BUFFER_FNS(Revoked, revoked) TAS_BUFFER_FNS(Revoked, revoked) BUFFER_FNS(RevokeValid, revokevalid) TAS_BUFFER_FNS(RevokeValid, revokevalid) BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; } static inline struct journal_head *bh2jh(struct buffer_head *bh) { return bh->b_private; } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { bit_spin_lock(BH_JournalHead, &bh->b_state); } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { bit_spin_unlock(BH_JournalHead, &bh->b_state); } #define J_ASSERT(assert) BUG_ON(!(assert)) #define J_ASSERT_BH(bh, expr) J_ASSERT(expr) #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) #define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) #else #define __journal_expect(expr, why...) \ ({ \ int val = (expr); \ if (!val) { \ printk(KERN_ERR \ "JBD2 unexpected failure: %s: %s;\n", \ __func__, #expr); \ printk(KERN_ERR why "\n"); \ } \ val; \ }) #define J_EXPECT(expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) #endif /* Flags in jbd_inode->i_flags */ #define __JI_COMMIT_RUNNING 0 #define __JI_WRITE_DATA 1 #define __JI_WAIT_DATA 2 /* * Commit of the inode data in progress. We use this flag to protect us from * concurrent deletion of inode. We cannot use reference to inode for this * since we cannot afford doing last iput() on behalf of kjournald */ #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) /* Write allocated dirty buffers in this inode before commit */ #define JI_WRITE_DATA (1 << __JI_WRITE_DATA) /* Wait for outstanding data writes for this inode before commit */ #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { /** * @i_transaction: * * Which transaction does this inode belong to? Either the running * transaction or the committing one. [j_list_lock] */ transaction_t *i_transaction; /** * @i_next_transaction: * * Pointer to the running transaction modifying inode's data in case * there is already a committing transaction touching it. [j_list_lock] */ transaction_t *i_next_transaction; /** * @i_list: List of inodes in the i_transaction [j_list_lock] */ struct list_head i_list; /** * @i_vfs_inode: * * VFS inode this inode belongs to [constant for lifetime of structure] */ struct inode *i_vfs_inode; /** * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; /** * @i_dirty_start: * * Offset in bytes where the dirty range for this inode starts. * [j_list_lock] */ loff_t i_dirty_start; /** * @i_dirty_end: * * Inclusive offset in bytes where the dirty range for this inode * ends. [j_list_lock] */ loff_t i_dirty_end; }; struct jbd2_revoke_table_s; /** * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. * @h_sync: Flag for sync-on-close. * @h_jdata: Flag to force data journaling. * @h_reserved: Flag for handle for reserved credits. * @h_aborted: Flag indicating fatal error on handle. * @h_type: For handle statistics. * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. * @h_requested_credits: Holds @h_total_credits after handle is started. * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation * in so it can be fixed later. */ struct jbd2_journal_handle { union { transaction_t *h_transaction; /* Which journal handle belongs to - used iff h_reserved set */ journal_t *h_journal; }; handle_t *h_rsv_handle; int h_total_credits; int h_revoke_credits; int h_revoke_credits_requested; int h_ref; int h_err; /* Flags [no locking] */ unsigned int h_sync: 1; unsigned int h_jdata: 1; unsigned int h_reserved: 1; unsigned int h_aborted: 1; unsigned int h_type: 8; unsigned int h_line_no: 16; unsigned long h_start_jiffies; unsigned int h_requested_credits; unsigned int saved_alloc_context; }; /* * Some stats for checkpoint phase */ struct transaction_chp_stats_s { unsigned long cs_chp_time; __u32 cs_forced_to_close; __u32 cs_written; __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It * tracks a compound transaction through its various states: * * RUNNING: accepting new updates * LOCKED: Updates still running but we don't accept new ones * RUNDOWN: Updates are tidying up but have finished requesting * new buffers to modify (state not used for now) * FLUSH: All updates complete, but we are still writing to disk * COMMIT: All data on disk, writing commit record * FINISHED: We still have to keep the transaction for checkpointing. * * The transaction keeps track of all of the buffers modified by a * running transaction, and all of the buffers committed but not yet * flushed to home for finished transactions. */ /* * Lock ranking: * * j_list_lock * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock * ->b_state_lock * * b_state_lock * ->j_list_lock * * j_state_lock * ->t_handle_lock * * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ struct transaction_s { /* Pointer to the journal for this transaction. [no locking] */ journal_t *t_journal; /* Sequence number for this transaction [no locking] */ tid_t t_tid; /* * Transaction's current state * [no locking - only kjournald2 alters this] * [j_list_lock] guards transition of a transaction into T_FINISHED * state and subsequent call of __jbd2_journal_drop_transaction() * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ enum { T_RUNNING, T_LOCKED, T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, T_COMMIT_CALLBACK, T_FINISHED } t_state; /* * Where in the log does this transaction's commit start? [no locking] */ unsigned long t_log_start; /* Number of buffers on the t_buffers list [j_list_lock] */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet * modified by this transaction [j_list_lock] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock] */ struct journal_head *t_buffers; /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) * [j_list_lock] */ struct journal_head *t_forget; /* * Doubly-linked circular list of all buffers still to be flushed before * this transaction can be checkpointed. [j_list_lock] */ struct journal_head *t_checkpoint_list; /* * Doubly-linked circular list of all buffers submitted for IO while * checkpointing. [j_list_lock] */ struct journal_head *t_checkpoint_io_list; /* * Doubly-linked circular list of metadata buffers being shadowed by log * IO. The IO buffers on the iobuf list and the shadow buffers on this * list match each other one for one at all times. [j_list_lock] */ struct journal_head *t_shadow_list; /* * List of inodes associated with the transaction; e.g., ext4 uses * this to track inodes in data=ordered and data=journal mode that * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; /* * Protects info related to handles */ spinlock_t t_handle_lock; /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; /* * When transaction started */ unsigned long t_start; /* * When commit was requested */ unsigned long t_requested; /* * Checkpointing stats [j_checkpoint_sem] */ struct transaction_chp_stats_s t_chp_stats; /* * Number of outstanding updates running on this transaction * [none] */ atomic_t t_updates; /* * Number of blocks reserved for this transaction in the journal. * This is including all credits reserved when starting transaction * handles as well as all journal descriptor blocks needed for this * transaction. [none] */ atomic_t t_outstanding_credits; /* * Number of revoke records for this transaction added by already * stopped handles. [none] */ atomic_t t_outstanding_revokes; /* * How many handles used this transaction? [none] */ atomic_t t_handle_count; /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] */ transaction_t *t_cpnext, *t_cpprev; /* * When will the transaction expire (become due for commit), in jiffies? * [no locking] */ unsigned long t_expires; /* * When this transaction started, in nanoseconds [no locking] */ ktime_t t_start_time; /* * This transaction is being forced and some process is * waiting for it to finish. */ unsigned int t_synchronous_commit:1; /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; /* * For use by the filesystem to store fs-specific data * structures associated with the transaction */ struct list_head t_private_list; }; struct transaction_run_stats_s { unsigned long rs_wait; unsigned long rs_request_delay; unsigned long rs_running; unsigned long rs_locked; unsigned long rs_flushing; unsigned long rs_logging; __u32 rs_handle_count; __u32 rs_blocks; __u32 rs_blocks_logged; }; struct transaction_stats_s { unsigned long ts_tid; unsigned long ts_requested; struct transaction_run_stats_s run; }; static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { if (end >= start) return end - start; return end + (MAX_JIFFY_OFFSET - start); } #define JBD2_NR_BATCH 64 enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; #define JBD2_FC_REPLAY_STOP 0 #define JBD2_FC_REPLAY_CONTINUE 1 /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. */ struct journal_s { /** * @j_flags: General journaling state flags [j_state_lock] */ unsigned long j_flags; /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior * abort)? [j_state_lock] */ int j_errno; /** * @j_abort_mutex: Lock the whole aborting procedure. */ struct mutex j_abort_mutex; /** * @j_sb_buffer: The first part of the superblock buffer. */ struct buffer_head *j_sb_buffer; /** * @j_superblock: The second part of the superblock buffer. */ journal_superblock_t *j_superblock; /** * @j_format_version: Version of the superblock format. */ int j_format_version; /** * @j_state_lock: Protect the various scalars in the journal. */ rwlock_t j_state_lock; /** * @j_barrier_count: * * Number of processes waiting to create a barrier lock [j_state_lock] */ int j_barrier_count; /** * @j_barrier: The barrier lock itself. */ struct mutex j_barrier; /** * @j_running_transaction: * * Transactions: The current running transaction... * [j_state_lock] [caller holding open handle] */ transaction_t *j_running_transaction; /** * @j_committing_transaction: * * the transaction we are pushing to disk * [j_state_lock] [caller holding open handle] */ transaction_t *j_committing_transaction; /** * @j_checkpoint_transactions: * * ... and a linked circular list of all transactions waiting for * checkpointing. [j_list_lock] */ transaction_t *j_checkpoint_transactions; /** * @j_wait_transaction_locked: * * Wait queue for waiting for a locked transaction to start committing, * or for a barrier lock to be released. */ wait_queue_head_t j_wait_transaction_locked; /** * @j_wait_done_commit: Wait queue for waiting for commit to complete. */ wait_queue_head_t j_wait_done_commit; /** * @j_wait_commit: Wait queue to trigger commit. */ wait_queue_head_t j_wait_commit; /** * @j_wait_updates: Wait queue to wait for updates to complete. */ wait_queue_head_t j_wait_updates; /** * @j_wait_reserved: * * Wait queue to wait for reserved buffer credits to drop. */ wait_queue_head_t j_wait_reserved; /** * @j_fc_wait: * * Wait queue to wait for completion of async fast commits. */ wait_queue_head_t j_fc_wait; /** * @j_checkpoint_mutex: * * Semaphore for locking against concurrent checkpoints. */ struct mutex j_checkpoint_mutex; /** * @j_chkpt_bhs: * * List of buffer heads used by the checkpoint routine. This * was moved from jbd2_log_do_checkpoint() to reduce stack * usage. Access to this array is controlled by the * @j_checkpoint_mutex. [j_checkpoint_mutex] */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; /** * @j_head: * * Journal head: identifies the first unused block in the journal. * [j_state_lock] */ unsigned long j_head; /** * @j_tail: * * Journal tail: identifies the oldest still-used block in the journal. * [j_state_lock] */ unsigned long j_tail; /** * @j_free: * * Journal free: how many free blocks are there in the journal? * [j_state_lock] */ unsigned long j_free; /** * @j_first: * * The block number of the first usable block in the journal * [j_state_lock]. */ unsigned long j_first; /** * @j_last: * * The block number one beyond the last usable block in the journal * [j_state_lock]. */ unsigned long j_last; /** * @j_fc_first: * * The block number of the first fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_first; /** * @j_fc_off: * * Number of fast commit blocks currently allocated. Accessed only * during fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ unsigned long j_fc_off; /** * @j_fc_last: * * The block number one beyond the last fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_last; /** * @j_dev: Device where we store the journal. */ struct block_device *j_dev; /** * @j_blocksize: Block size for the location where we store the journal. */ int j_blocksize; /** * @j_blk_offset: * * Starting block offset into the device where we store the journal. */ unsigned long long j_blk_offset; /** * @j_devname: Journal device name. */ char j_devname[BDEVNAME_SIZE+24]; /** * @j_fs_dev: * * Device which holds the client fs. For internal journal this will be * equal to j_dev. */ struct block_device *j_fs_dev; /** * @j_total_len: Total maximum capacity of the journal region on disk. */ unsigned int j_total_len; /** * @j_reserved_credits: * * Number of buffers reserved from the running transaction. */ atomic_t j_reserved_credits; /** * @j_list_lock: Protects the buffer lists and internal buffer state. */ spinlock_t j_list_lock; /** * @j_inode: * * Optional inode where we store the journal. If present, all * journal block numbers are mapped into this inode via bmap(). */ struct inode *j_inode; /** * @j_tail_sequence: * * Sequence number of the oldest transaction in the log [j_state_lock] */ tid_t j_tail_sequence; /** * @j_transaction_sequence: * * Sequence number of the next transaction to grant [j_state_lock] */ tid_t j_transaction_sequence; /** * @j_commit_sequence: * * Sequence number of the most recently committed transaction * [j_state_lock]. */ tid_t j_commit_sequence; /** * @j_commit_request: * * Sequence number of the most recent transaction wanting commit * [j_state_lock] */ tid_t j_commit_request; /** * @j_uuid: * * Journal uuid: identifies the object (filesystem, LVM volume etc) * backed by this journal. This will eventually be replaced by an array * of uuids, allowing us to index multiple devices within a single * journal and to perform atomic updates across them. */ __u8 j_uuid[16]; /** * @j_task: Pointer to the current commit thread for this journal. */ struct task_struct *j_task; /** * @j_max_transaction_buffers: * * Maximum number of metadata buffers to allow in a single compound * commit transaction. */ int j_max_transaction_buffers; /** * @j_revoke_records_per_block: * * Number of revoke records that fit in one descriptor block. */ int j_revoke_records_per_block; /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? */ unsigned long j_commit_interval; /** * @j_commit_timer: The timer used to wakeup the commit thread. */ struct timer_list j_commit_timer; /** * @j_revoke_lock: Protect the revoke table. */ spinlock_t j_revoke_lock; /** * @j_revoke: * * The revoke table - maintains the list of revoked blocks in the * current transaction. */ struct jbd2_revoke_table_s *j_revoke; /** * @j_revoke_table: Alternate revoke tables for j_revoke. */ struct jbd2_revoke_table_s *j_revoke_table[2]; /** * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction. */ struct buffer_head **j_wbuf; /** * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only * during a fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; /** * @j_wbufsize: * * Size of @j_wbuf array. */ int j_wbufsize; /** * @j_fc_wbufsize: * * Size of @j_fc_wbuf array. */ int j_fc_wbufsize; /** * @j_last_sync_writer: * * The pid of the last person to run a synchronous operation * through the journal. */ pid_t j_last_sync_writer; /** * @j_average_commit_time: * * The average amount of time in nanoseconds it takes to commit a * transaction to disk. [j_state_lock] */ u64 j_average_commit_time; /** * @j_min_batch_time: * * Minimum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_min_batch_time; /** * @j_max_batch_time: * * Maximum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_max_batch_time; /** * @j_commit_callback: * * This function is called when a transaction is closed. */ void (*j_commit_callback)(journal_t *, transaction_t *); /** * @j_submit_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WRITE_DATA flag * before we start to write out the transaction to the journal. */ int (*j_submit_inode_data_buffers) (struct jbd2_inode *); /** * @j_finish_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WAIT_DATA flag * after we have written the transaction to the journal * but before we write out the commit block. */ int (*j_finish_inode_data_buffers) (struct jbd2_inode *); /* * Journal statistics */ /** * @j_history_lock: Protect the transactions statistics history. */ spinlock_t j_history_lock; /** * @j_proc_entry: procfs entry for the jbd statistics directory. */ struct proc_dir_entry *j_proc_entry; /** * @j_stats: Overall statistics. */ struct transaction_stats_s j_stats; /** * @j_failed_commit: Failed journal commit ID. */ unsigned int j_failed_commit; /** * @j_private: * * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here. */ void *j_private; /** * @j_chksum_driver: * * Reference to checksum algorithm driver via cryptoapi. */ struct crypto_shash *j_chksum_driver; /** * @j_csum_seed: * * Precomputed journal UUID checksum for seeding other checksums. */ __u32 j_csum_seed; #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * @j_trans_commit_map: * * Lockdep entity to track transaction commit dependencies. Handles * hold this "lock" for read, when we wait for commit, we acquire the * "lock" for writing. This matches the properties of jbd2 journalling * where the running transaction has to wait for all handles to be * dropped to commit that transaction and also acquiring a handle may * require transaction commit to finish. */ struct lockdep_map j_trans_commit_map; #endif /** * @j_fc_cleanup_callback: * * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ void (*j_fc_cleanup_callback)(struct journal_s *journal, int); /** * @j_fc_replay_callback: * * File-system specific function that performs replay of a fast * commit. JBD2 calls this function for each fast commit block found in * the journal. This function should return JBD2_FC_REPLAY_CONTINUE * to indicate that the block was processed correctly and more fast * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP * indicates the end of replay (no more blocks remaining). A negative * return value indicates error. */ int (*j_fc_replay_callback)(struct journal_s *journal, struct buffer_head *bh, enum passtype pass, int off, tid_t expected_commit_id); }; #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ } while (0) /* journal feature predicate functions */ #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_compat & \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat |= \ cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_compat &= \ ~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ } #define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_ro_compat & \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat |= \ cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_ro_compat &= \ ~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ } #define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ { \ return ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_incompat & \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \ } \ static inline void jbd2_set_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat |= \ cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } \ static inline void jbd2_clear_feature_##name(journal_t *j) \ { \ (j)->j_superblock->s_feature_incompat &= \ ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ } JBD2_FEATURE_COMPAT_FUNCS(checksum, CHECKSUM) JBD2_FEATURE_INCOMPAT_FUNCS(revoke, REVOKE) JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) /* * Journal flag definitions */ #define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */ #define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */ #define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */ #define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ #define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ #define JBD2_BARRIER 0x020 /* Use IDE barriers */ #define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file * data write error in ordered * mode */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ /* * Function declarations for the journaling transaction and buffer * management */ /* Filing buffers */ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void __journal_free_buffer(struct journal_head *bh); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void __journal_clean_data_list(transaction_t *transaction); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); } static inline void jbd2_unfile_log_bh(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); } /* Log buffer allocation */ struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); int __jbd2_journal_remove_checkpoint(struct journal_head *); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); /* * Triggers */ struct jbd2_buffer_trigger_type { /* * Fired a the moment data to write to the journal are known to be * stable - so either at the moment b_frozen_data is created or just * before a buffer is written to the journal. mapped_data is a mapped * buffer that is the frozen data for commit. */ void (*t_frozen)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh, void *mapped_data, size_t size); /* * Fired during journal abort for dirty buffers that will not be * committed. */ void (*t_abort)(struct jbd2_buffer_trigger_type *type, struct buffer_head *bh); }; extern void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data, struct jbd2_buffer_trigger_type *triggers); extern void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers); /* Buffer IO */ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr); /* Transaction locking */ extern void __wait_on_journal (journal_t *); /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); extern void jbd2_journal_free_transaction(transaction_t *); /* * Journal locking. * * We need to lock the journal during transaction state changes so that nobody * ever tries to take a handle on the running transaction while we are in the * middle of moving it to the commit phase. j_state_lock does this. * * Note that the locking is completely interrupt unsafe. We never touch * journal structures from interrupts. */ static inline handle_t *journal_current_handle(void) { return current->journal_info; } /* The journaling code user interface: * * Create and destroy handles * Register buffer modifications against the current transaction. */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, int revoke_records, gfp_t gfp_mask, unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); extern int jbd2__journal_restart(handle_t *, int nblocks, int revoke_records, gfp_t gfp_mask); extern int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no); extern void jbd2_journal_free_reserved(handle_t *handle); extern int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush (journal_t *); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); extern journal_t * jbd2_journal_init_inode (struct inode *); extern int jbd2_journal_update_format (journal_t *); extern int jbd2_journal_check_used_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_check_available_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, int); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_inode_ranged_write(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *inode, loff_t start_byte, loff_t length); extern int jbd2_journal_submit_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_finish_inode_data_buffers( struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode); /* * journal_head management */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* * handle management */ extern struct kmem_cache *jbd2_handle_cache; static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags) { return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags); } static inline void jbd2_free_handle(handle_t *handle) { kmem_cache_free(jbd2_handle_cache, handle); } /* * jbd2_inode management (optional, for those file systems that want to use * dynamically allocated jbd2_inode structures) */ extern struct kmem_cache *jbd2_inode_cache; static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags) { return kmem_cache_alloc(jbd2_inode_cache, gfp_flags); } static inline void jbd2_free_inode(struct jbd2_inode *jinode) { kmem_cache_free(jbd2_inode_cache, jinode); } /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 extern int jbd2_journal_init_revoke(journal_t *, int); extern void jbd2_journal_destroy_revoke_record_cache(void); extern void jbd2_journal_destroy_revoke_table_cache(void); extern int __init jbd2_journal_init_revoke_record_cache(void); extern int __init jbd2_journal_init_revoke_table_cache(void); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); extern void jbd2_journal_write_revoke_records(transaction_t *transaction, struct list_head *log_bufs); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t); extern void jbd2_journal_clear_revoke(journal_t *); extern void jbd2_journal_switch_revoke_table(journal_t *journal); extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); /* * The log thread user interface: * * Request space in the current transaction, and force transaction commit * transitions on demand. */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); int __jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); int jbd2_transaction_committed(journal_t *journal, tid_t tid); int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); int jbd2_fc_release_bufs(journal_t *journal); static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal) { return (journal->j_total_len - journal->j_fc_wbufsize) / 4; } /* * is_journal_abort * * Simple test wrapper function to test the JBD2_ABORT state flag. This * bit, when set, indicates that we have had a fatal error somewhere, * either inside the journaling layer or indicated to us by the client * (eg. ext3), and that we and should not commit any further * transactions. */ static inline int is_journal_aborted(journal_t *journal) { return journal->j_flags & JBD2_ABORT; } static inline int is_handle_aborted(handle_t *handle) { if (handle->h_aborted || !handle->h_transaction) return 1; return is_journal_aborted(handle->h_transaction->t_journal); } static inline void jbd2_journal_abort_handle(handle_t *handle) { handle->h_aborted = 1; } #endif /* __KERNEL__ */ /* Comparison functions for transaction IDs: perform comparisons using * modulo arithmetic so that they work over sequence number wraps. */ static inline int tid_gt(tid_t x, tid_t y) { int difference = (x - y); return (difference > 0); } static inline int tid_geq(tid_t x, tid_t y) { int difference = (x - y); return (difference >= 0); } extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); static inline bool jbd2_journal_has_csum_v2or3_feature(journal_t *j) { return jbd2_has_feature_csum2(j) || jbd2_has_feature_csum3(j); } static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) { WARN_ON_ONCE(jbd2_journal_has_csum_v2or3_feature(journal) && journal->j_chksum_driver == NULL); return journal->j_chksum_driver != NULL; } /* * Return number of free blocks in the log. Must be called under j_state_lock. */ static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ long free = journal->j_free - 32; if (journal->j_committing_transaction) { free -= atomic_read(&journal-> j_committing_transaction->t_outstanding_credits); } return max_t(long, free, 0); } /* * Definitions which augment the buffer_head layer */ /* journaling buffer types */ #define BJ_None 0 /* Not journaled */ #define BJ_Metadata 1 /* Normal journaled metadata */ #define BJ_Forget 2 /* Buffer superseded by this transaction */ #define BJ_Shadow 3 /* Buffer contents being shadowed to the log */ #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 extern int jbd_blocks_per_page(struct inode *inode); /* JBD uses a CRC32 checksum */ #define JBD_MAX_CHECKSUM_SIZE 4 static inline u32 jbd2_chksum(journal_t *journal, u32 crc, const void *address, unsigned int length) { struct { struct shash_desc shash; char ctx[JBD_MAX_CHECKSUM_SIZE]; } desc; int err; BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) > JBD_MAX_CHECKSUM_SIZE); desc.shash.tfm = journal->j_chksum_driver; *(u32 *)desc.ctx = crc; err = crypto_shash_update(&desc.shash, address, length); BUG_ON(err); return *(u32 *)desc.ctx; } /* Return most recent uncommitted transaction */ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) { tid_t tid; read_lock(&journal->j_state_lock); tid = journal->j_commit_request; if (journal->j_running_transaction) tid = journal->j_running_transaction->t_tid; read_unlock(&journal->j_state_lock); return tid; } static inline int jbd2_handle_buffer_credits(handle_t *handle) { journal_t *journal; if (!handle->h_reserved) journal = handle->h_transaction->t_journal; else journal = handle->h_journal; return handle->h_total_credits - DIV_ROUND_UP(handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); } #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) #define print_buffer_fields(bh) do {} while (0) #define print_buffer_trace(bh) do {} while (0) #define BUFFER_TRACE(bh, info) do {} while (0) #define BUFFER_TRACE2(bh, bh2, info) do {} while (0) #define JBUFFER_TRACE(jh, info) do {} while (0) #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ #endif /* _LINUX_JBD2_H */
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 /* SPDX-License-Identifier: GPL-2.0-only */ /* * Dynamic loading of modules into the kernel. * * Rewritten by Richard Henderson <rth@tamu.edu> Dec 1996 * Rewritten again by Rusty Russell, 2002 */ #ifndef _LINUX_MODULE_H #define _LINUX_MODULE_H #include <linux/list.h> #include <linux/stat.h> #include <linux/compiler.h> #include <linux/cache.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/elf.h> #include <linux/stringify.h> #include <linux/kobject.h> #include <linux/moduleparam.h> #include <linux/jump_label.h> #include <linux/export.h> #include <linux/rbtree_latch.h> #include <linux/error-injection.h> #include <linux/tracepoint-defs.h> #include <linux/srcu.h> #include <linux/static_call_types.h> #include <linux/percpu.h> #include <asm/module.h> /* Not Yet Implemented */ #define MODULE_SUPPORTED_DEVICE(name) #define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN struct modversion_info { unsigned long crc; char name[MODULE_NAME_LEN]; }; struct module; struct exception_table_entry; struct module_kobject { struct kobject kobj; struct module *mod; struct kobject *drivers_dir; struct module_param_attrs *mp; struct completion *kobj_completion; } __randomize_layout; struct module_attribute { struct attribute attr; ssize_t (*show)(struct module_attribute *, struct module_kobject *, char *); ssize_t (*store)(struct module_attribute *, struct module_kobject *, const char *, size_t count); void (*setup)(struct module *, const char *); int (*test)(struct module *); void (*free)(struct module *); }; struct module_version_attribute { struct module_attribute mattr; const char *module_name; const char *version; } __attribute__ ((__aligned__(sizeof(void *)))); extern ssize_t __modver_version_show(struct module_attribute *, struct module_kobject *, char *); extern struct module_attribute module_uevent; /* These are either module local, or the kernel's dummy ones. */ extern int init_module(void); extern void cleanup_module(void); #ifndef MODULE /** * module_init() - driver initialization entry point * @x: function to be run at kernel boot time or module insertion * * module_init() will either be called during do_initcalls() (if * builtin) or at module insertion time (if a module). There can only * be one per module. */ #define module_init(x) __initcall(x); /** * module_exit() - driver exit entry point * @x: function to be run when driver is removed * * module_exit() will wrap the driver clean-up code * with cleanup_module() when used with rmmod when * the driver is a module. If the driver is statically * compiled into the kernel, module_exit() has no effect. * There can only be one per module. */ #define module_exit(x) __exitcall(x); #else /* MODULE */ /* * In most cases loadable modules do not need custom * initcall levels. There are still some valid cases where * a driver may be needed early if built in, and does not * matter when built as a loadable module. Like bus * snooping debug drivers. */ #define early_initcall(fn) module_init(fn) #define core_initcall(fn) module_init(fn) #define core_initcall_sync(fn) module_init(fn) #define postcore_initcall(fn) module_init(fn) #define postcore_initcall_sync(fn) module_init(fn) #define arch_initcall(fn) module_init(fn) #define subsys_initcall(fn) module_init(fn) #define subsys_initcall_sync(fn) module_init(fn) #define fs_initcall(fn) module_init(fn) #define fs_initcall_sync(fn) module_init(fn) #define rootfs_initcall(fn) module_init(fn) #define device_initcall(fn) module_init(fn) #define device_initcall_sync(fn) module_init(fn) #define late_initcall(fn) module_init(fn) #define late_initcall_sync(fn) module_init(fn) #define console_initcall(fn) module_init(fn) /* Each module must use one module_init(). */ #define module_init(initfn) \ static inline initcall_t __maybe_unused __inittest(void) \ { return initfn; } \ int init_module(void) __copy(initfn) __attribute__((alias(#initfn))); /* This is only required if you want to be unloadable. */ #define module_exit(exitfn) \ static inline exitcall_t __maybe_unused __exittest(void) \ { return exitfn; } \ void cleanup_module(void) __copy(exitfn) __attribute__((alias(#exitfn))); #endif /* This means "can be init if no module support, otherwise module load may call it." */ #ifdef CONFIG_MODULES #define __init_or_module #define __initdata_or_module #define __initconst_or_module #define __INIT_OR_MODULE .text #define __INITDATA_OR_MODULE .data #define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits #else #define __init_or_module __init #define __initdata_or_module __initdata #define __initconst_or_module __initconst #define __INIT_OR_MODULE __INIT #define __INITDATA_OR_MODULE __INITDATA #define __INITRODATA_OR_MODULE __INITRODATA #endif /*CONFIG_MODULES*/ /* Generic info of form tag = "info" */ #define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info) /* For userspace: you can also call me... */ #define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias) /* Soft module dependencies. See man modprobe.d for details. * Example: MODULE_SOFTDEP("pre: module-foo module-bar post: module-baz") */ #define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep) /* * MODULE_FILE is used for generating modules.builtin * So, make it no-op when this is being built as a module */ #ifdef MODULE #define MODULE_FILE #else #define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE); #endif /* * The following license idents are currently accepted as indicating free * software modules * * "GPL" [GNU Public License v2] * "GPL v2" [GNU Public License v2] * "GPL and additional rights" [GNU Public License v2 rights and more] * "Dual BSD/GPL" [GNU Public License v2 * or BSD license choice] * "Dual MIT/GPL" [GNU Public License v2 * or MIT license choice] * "Dual MPL/GPL" [GNU Public License v2 * or Mozilla license choice] * * The following other idents are available * * "Proprietary" [Non free products] * * Both "GPL v2" and "GPL" (the latter also in dual licensed strings) are * merely stating that the module is licensed under the GPL v2, but are not * telling whether "GPL v2 only" or "GPL v2 or later". The reason why there * are two variants is a historic and failed attempt to convey more * information in the MODULE_LICENSE string. For module loading the * "only/or later" distinction is completely irrelevant and does neither * replace the proper license identifiers in the corresponding source file * nor amends them in any way. The sole purpose is to make the * 'Proprietary' flagging work and to refuse to bind symbols which are * exported with EXPORT_SYMBOL_GPL when a non free module is loaded. * * In the same way "BSD" is not a clear license information. It merely * states, that the module is licensed under one of the compatible BSD * license variants. The detailed and correct license information is again * to be found in the corresponding source files. * * There are dual licensed components, but when running with Linux it is the * GPL that is relevant so this is a non issue. Similarly LGPL linked with GPL * is a GPL combined work. * * This exists for several reasons * 1. So modinfo can show license info for users wanting to vet their setup * is free * 2. So the community can ignore bug reports including proprietary modules * 3. So vendors can do likewise based on their own policies */ #define MODULE_LICENSE(_license) MODULE_FILE MODULE_INFO(license, _license) /* * Author(s), use "Name <email>" or just "Name", for multiple * authors use multiple MODULE_AUTHOR() statements/lines. */ #define MODULE_AUTHOR(_author) MODULE_INFO(author, _author) /* What your module does. */ #define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description) #ifdef MODULE /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ extern typeof(name) __mod_##type##__##name##_device_table \ __attribute__ ((unused, alias(__stringify(name)))) #else /* !MODULE */ #define MODULE_DEVICE_TABLE(type, name) #endif /* Version of form [<epoch>:]<version>[-<extra-version>]. * Or for CVS/RCS ID version, everything but the number is stripped. * <epoch>: A (small) unsigned integer which allows you to start versions * anew. If not mentioned, it's zero. eg. "2:1.0" is after * "1:2.0". * <version>: The <version> may contain only alphanumerics and the * character `.'. Ordered by numeric sort for numeric parts, * ascii sort for ascii parts (as per RPM or DEB algorithm). * <extraversion>: Like <version>, but inserted for local * customizations, eg "rh3" or "rusty1". * Using this automatically adds a checksum of the .c files and the * local headers in "srcversion". */ #if defined(MODULE) || !defined(CONFIG_SYSFS) #define MODULE_VERSION(_version) MODULE_INFO(version, _version) #else #define MODULE_VERSION(_version) \ MODULE_INFO(version, _version); \ static struct module_version_attribute ___modver_attr = { \ .mattr = { \ .attr = { \ .name = "version", \ .mode = S_IRUGO, \ }, \ .show = __modver_version_show, \ }, \ .module_name = KBUILD_MODNAME, \ .version = _version, \ }; \ static const struct module_version_attribute \ __used __section("__modver") \ * __moduleparam_const __modver_attr = &___modver_attr #endif /* Optional firmware file (or files) needed by the module * format is simply firmware file name. Multiple firmware * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) #define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, #ns) struct notifier_block; #ifdef CONFIG_MODULES extern int modules_disabled; /* for sysctl */ /* Get/put a kernel symbol (calls must be symmetric) */ void *__symbol_get(const char *symbol); void *__symbol_get_gpl(const char *symbol); #define symbol_get(x) ((typeof(&x))(__symbol_get(__stringify(x)))) /* modules using other modules: kdb wants to see this. */ struct module_use { struct list_head source_list; struct list_head target_list; struct module *source, *target; }; enum module_state { MODULE_STATE_LIVE, /* Normal state. */ MODULE_STATE_COMING, /* Full formed, running module_init. */ MODULE_STATE_GOING, /* Going away. */ MODULE_STATE_UNFORMED, /* Still setting it up. */ }; struct mod_tree_node { struct module *mod; struct latch_tree_node node; }; struct module_layout { /* The actual code + data. */ void *base; /* Total size. */ unsigned int size; /* The size of the executable code. */ unsigned int text_size; /* Size of RO section of the module (text+rodata) */ unsigned int ro_size; /* Size of RO after init section */ unsigned int ro_after_init_size; #ifdef CONFIG_MODULES_TREE_LOOKUP struct mod_tree_node mtn; #endif }; #ifdef CONFIG_MODULES_TREE_LOOKUP /* Only touch one cacheline for common rbtree-for-core-layout case. */ #define __module_layout_align ____cacheline_aligned #else #define __module_layout_align #endif struct mod_kallsyms { Elf_Sym *symtab; unsigned int num_symtab; char *strtab; char *typetab; }; #ifdef CONFIG_LIVEPATCH struct klp_modinfo { Elf_Ehdr hdr; Elf_Shdr *sechdrs; char *secstrings; unsigned int symndx; }; #endif struct module { enum module_state state; /* Member of list of modules */ struct list_head list; /* Unique handle for this module */ char name[MODULE_NAME_LEN]; /* Sysfs stuff. */ struct module_kobject mkobj; struct module_attribute *modinfo_attrs; const char *version; const char *srcversion; struct kobject *holders_dir; /* Exported symbols */ const struct kernel_symbol *syms; const s32 *crcs; unsigned int num_syms; /* Kernel parameters. */ #ifdef CONFIG_SYSFS struct mutex param_lock; #endif struct kernel_param *kp; unsigned int num_kp; /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; const s32 *gpl_crcs; bool using_gplonly_symbols; #ifdef CONFIG_UNUSED_SYMBOLS /* unused exported symbols. */ const struct kernel_symbol *unused_syms; const s32 *unused_crcs; unsigned int num_unused_syms; /* GPL-only, unused exported symbols. */ unsigned int num_unused_gpl_syms; const struct kernel_symbol *unused_gpl_syms; const s32 *unused_gpl_crcs; #endif #ifdef CONFIG_MODULE_SIG /* Signature was verified. */ bool sig_ok; #endif bool async_probe_requested; /* symbols that will be GPL-only in the near future. */ const struct kernel_symbol *gpl_future_syms; const s32 *gpl_future_crcs; unsigned int num_gpl_future_syms; /* Exception table */ unsigned int num_exentries; struct exception_table_entry *extable; /* Startup function. */ int (*init)(void); /* Core layout: rbtree is accessed frequently, so keep together. */ struct module_layout core_layout __module_layout_align; struct module_layout init_layout; /* Arch-specific module values */ struct mod_arch_specific arch; unsigned long taints; /* same bits as kernel:taint_flags */ #ifdef CONFIG_GENERIC_BUG /* Support for BUG */ unsigned num_bugs; struct list_head bug_list; struct bug_entry *bug_table; #endif #ifdef CONFIG_KALLSYMS /* Protected by RCU and/or module_mutex: use rcu_dereference() */ struct mod_kallsyms __rcu *kallsyms; struct mod_kallsyms core_kallsyms; /* Section attributes */ struct module_sect_attrs *sect_attrs; /* Notes attributes */ struct module_notes_attrs *notes_attrs; #endif /* The command line arguments (may be mangled). People like keeping pointers to this stuff */ char *args; #ifdef CONFIG_SMP /* Per-cpu data. */ void __percpu *percpu; unsigned int percpu_size; #endif void *noinstr_text_start; unsigned int noinstr_text_size; #ifdef CONFIG_TRACEPOINTS unsigned int num_tracepoints; tracepoint_ptr_t *tracepoints_ptrs; #endif #ifdef CONFIG_TREE_SRCU unsigned int num_srcu_structs; struct srcu_struct **srcu_struct_ptrs; #endif #ifdef CONFIG_BPF_EVENTS unsigned int num_bpf_raw_events; struct bpf_raw_event_map *bpf_raw_events; #endif #ifdef CONFIG_JUMP_LABEL struct jump_entry *jump_entries; unsigned int num_jump_entries; #endif #ifdef CONFIG_TRACING unsigned int num_trace_bprintk_fmt; const char **trace_bprintk_fmt_start; #endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call **trace_events; unsigned int num_trace_events; struct trace_eval_map **trace_evals; unsigned int num_trace_evals; #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD unsigned int num_ftrace_callsites; unsigned long *ftrace_callsites; #endif #ifdef CONFIG_KPROBES void *kprobes_text_start; unsigned int kprobes_text_size; unsigned long *kprobe_blacklist; unsigned int num_kprobe_blacklist; #endif #ifdef CONFIG_HAVE_STATIC_CALL_INLINE int num_static_call_sites; struct static_call_site *static_call_sites; #endif #ifdef CONFIG_LIVEPATCH bool klp; /* Is this a livepatch module? */ bool klp_alive; /* Elf information */ struct klp_modinfo *klp_info; #endif #ifdef CONFIG_MODULE_UNLOAD /* What modules depend on me? */ struct list_head source_list; /* What modules do I depend on? */ struct list_head target_list; /* Destruction function. */ void (*exit)(void); atomic_t refcnt; #endif #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors; unsigned int num_ctors; #endif #ifdef CONFIG_FUNCTION_ERROR_INJECTION struct error_injection_entry *ei_funcs; unsigned int num_ei_funcs; #endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif #ifndef HAVE_ARCH_KALLSYMS_SYMBOL_VALUE static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym) { return sym->st_value; } #endif extern struct mutex module_mutex; /* FIXME: It'd be nice to isolate modules during init, too, so they aren't used before they (may) fail. But presently too much code (IDE & SCSI) require entry into the module during init.*/ static inline bool module_is_live(struct module *mod) { return mod->state != MODULE_STATE_GOING; } struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr); bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); static inline bool within_module_core(unsigned long addr, const struct module *mod) { return (unsigned long)mod->core_layout.base <= addr && addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { return (unsigned long)mod->init_layout.base <= addr && addr < (unsigned long)mod->init_layout.base + mod->init_layout.size; } static inline bool within_module(unsigned long addr, const struct module *mod) { return within_module_init(addr, mod) || within_module_core(addr, mod); } /* Search for module by name: must hold module_mutex. */ struct module *find_module(const char *name); struct symsearch { const struct kernel_symbol *start, *stop; const s32 *crcs; enum mod_license { NOT_GPL_ONLY, GPL_ONLY, WILL_BE_GPL_ONLY, } license; bool unused; }; /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if symnum out of range. */ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported); /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); extern void __noreturn __module_put_and_exit(struct module *mod, long code); #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD int module_refcount(struct module *mod); void __symbol_put(const char *symbol); #define symbol_put(x) __symbol_put(__stringify(x)) void symbol_put_addr(void *addr); /* Sometimes we know we already have a refcount, and it's easier not to handle the error case (which only happens with rmmod --wait). */ extern void __module_get(struct module *module); /* This is the Right Way to get a module: if it fails, it's being removed, * so pretend it's not there. */ extern bool try_module_get(struct module *module); extern void module_put(struct module *module); #else /*!CONFIG_MODULE_UNLOAD*/ static inline bool try_module_get(struct module *module) { return !module || module_is_live(module); } static inline void module_put(struct module *module) { } static inline void __module_get(struct module *module) { } #define symbol_put(x) do { } while (0) #define symbol_put_addr(p) do { } while (0) #endif /* CONFIG_MODULE_UNLOAD */ /* This is a #define so the string doesn't get put in every .o file */ #define module_name(mod) \ ({ \ struct module *__mod = (mod); \ __mod ? __mod->name : "kernel"; \ }) /* Dereference module function descriptor */ void *dereference_module_function_descriptor(struct module *mod, void *ptr); /* For kallsyms to ask for address resolution. namebuf should be at * least KSYM_NAME_LEN long: a pointer to namebuf is returned if * found, otherwise NULL. */ const char *module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, char *namebuf); int lookup_module_symbol_name(unsigned long addr, char *symname); int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); int register_module_notifier(struct notifier_block *nb); int unregister_module_notifier(struct notifier_block *nb); extern void print_modules(void); static inline bool module_requested_async_probing(struct module *module) { return module && module->async_probe_requested; } #ifdef CONFIG_LIVEPATCH static inline bool is_livepatch_module(struct module *mod) { return mod->klp; } #else /* !CONFIG_LIVEPATCH */ static inline bool is_livepatch_module(struct module *mod) { return false; } #endif /* CONFIG_LIVEPATCH */ bool is_module_sig_enforced(void); void set_module_sig_enforced(void); #else /* !CONFIG_MODULES... */ static inline struct module *__module_address(unsigned long addr) { return NULL; } static inline struct module *__module_text_address(unsigned long addr) { return NULL; } static inline bool is_module_address(unsigned long addr) { return false; } static inline bool is_module_percpu_address(unsigned long addr) { return false; } static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) { return false; } static inline bool is_module_text_address(unsigned long addr) { return false; } static inline bool within_module_core(unsigned long addr, const struct module *mod) { return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { return false; } static inline bool within_module(unsigned long addr, const struct module *mod) { return false; } /* Get/put a kernel symbol (calls should be symmetric) */ #define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); }) #define symbol_put(x) do { } while (0) #define symbol_put_addr(x) do { } while (0) static inline void __module_get(struct module *module) { } static inline bool try_module_get(struct module *module) { return true; } static inline void module_put(struct module *module) { } #define module_name(mod) "kernel" /* For kallsyms to ask for address resolution. NULL means not found. */ static inline const char *module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, char *namebuf) { return NULL; } static inline int lookup_module_symbol_name(unsigned long addr, char *symname) { return -ERANGE; } static inline int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name) { return -ERANGE; } static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported) { return -ERANGE; } static inline unsigned long module_kallsyms_lookup_name(const char *name) { return 0; } static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data) { return 0; } static inline int register_module_notifier(struct notifier_block *nb) { /* no events will happen anyway, so this can always succeed */ return 0; } static inline int unregister_module_notifier(struct notifier_block *nb) { return 0; } #define module_put_and_exit(code) do_exit(code) static inline void print_modules(void) { } static inline bool module_requested_async_probing(struct module *module) { return false; } static inline bool is_module_sig_enforced(void) { return false; } static inline void set_module_sig_enforced(void) { } /* Dereference module function descriptor */ static inline void *dereference_module_function_descriptor(struct module *mod, void *ptr) { return ptr; } #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS extern struct kset *module_kset; extern struct kobj_type module_ktype; extern int module_sysfs_initialized; #endif /* CONFIG_SYSFS */ #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) /* BELOW HERE ALL THESE ARE OBSOLETE AND WILL VANISH */ #define __MODULE_STRING(x) __stringify(x) #ifdef CONFIG_GENERIC_BUG void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, struct module *); void module_bug_cleanup(struct module *); #else /* !CONFIG_GENERIC_BUG */ static inline void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { } static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ #ifdef CONFIG_RETPOLINE extern bool retpoline_module_ok(bool has_retpoline); #else static inline bool retpoline_module_ok(bool has_retpoline) { return true; } #endif #ifdef CONFIG_MODULE_SIG static inline bool module_sig_ok(struct module *module) { return module->sig_ok; } #else /* !CONFIG_MODULE_SIG */ static inline bool module_sig_ok(struct module *module) { return true; } #endif /* CONFIG_MODULE_SIG */ #endif /* _LINUX_MODULE_H */
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/ptrace.c * * (C) Copyright 1999 Linus Torvalds * * Common interfaces for "ptrace()" which we do not want * to continually duplicate across every architecture. */ #include <linux/capability.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/signal.h> #include <linux/uio.h> #include <linux/audit.h> #include <linux/pid_namespace.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/regset.h> #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> #include <linux/compat.h> #include <linux/sched/signal.h> #include <asm/syscall.h> /* for syscall_get_* */ /* * Access another process' address space via ptrace. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; if (!tsk->ptrace || (current != tsk->parent) || ((get_dumpable(mm) != SUID_DUMP_USER) && !ptracer_capable(tsk, mm->user_ns))) { mmput(mm); return 0; } ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags); mmput(mm); return ret; } void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred) { BUG_ON(!list_empty(&child->ptrace_entry)); list_add(&child->ptrace_entry, &new_parent->ptraced); child->parent = new_parent; child->ptracer_cred = get_cred(ptracer_cred); } /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */ static void ptrace_link(struct task_struct *child, struct task_struct *new_parent) { __ptrace_link(child, new_parent, current_cred()); } /** * __ptrace_unlink - unlink ptracee and restore its execution state * @child: ptracee to be unlinked * * Remove @child from the ptrace list, move it back to the original parent, * and restore the execution state so that it conforms to the group stop * state. * * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer * exiting. For PTRACE_DETACH, unless the ptracee has been killed between * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED. * If the ptracer is exiting, the ptracee can be in any state. * * After detach, the ptracee should be in a state which conforms to the * group stop. If the group is stopped or in the process of stopping, the * ptracee should be put into TASK_STOPPED; otherwise, it should be woken * up from TASK_TRACED. * * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED, * it goes through TRACED -> RUNNING -> STOPPED transition which is similar * to but in the opposite direction of what happens while attaching to a * stopped task. However, in this direction, the intermediate RUNNING * state is not hidden even from the current ptracer and if it immediately * re-attaches and performs a WNOHANG wait(2), it may fail. * * CONTEXT: * write_lock_irq(tasklist_lock) */ void __ptrace_unlink(struct task_struct *child) { const struct cred *old_cred; BUG_ON(!child->ptrace); clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); #ifdef TIF_SYSCALL_EMU clear_tsk_thread_flag(child, TIF_SYSCALL_EMU); #endif child->parent = child->real_parent; list_del_init(&child->ptrace_entry); old_cred = child->ptracer_cred; child->ptracer_cred = NULL; put_cred(old_cred); spin_lock(&child->sighand->siglock); child->ptrace = 0; /* * Clear all pending traps and TRAPPING. TRAPPING should be * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. */ task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK); task_clear_jobctl_trapping(child); /* * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and * @child isn't dead. */ if (!(child->flags & PF_EXITING) && (child->signal->flags & SIGNAL_STOP_STOPPED || child->signal->group_stop_count)) { child->jobctl |= JOBCTL_STOP_PENDING; /* * This is only possible if this thread was cloned by the * traced task running in the stopped group, set the signal * for the future reports. * FIXME: we should change ptrace_init_task() to handle this * case. */ if (!(child->jobctl & JOBCTL_STOP_SIGMASK)) child->jobctl |= SIGSTOP; } /* * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick * @child in the butt. Note that @resume should be used iff @child * is in TASK_TRACED; otherwise, we might unduly disrupt * TASK_KILLABLE sleeps. */ if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) ptrace_signal_wake_up(child, true); spin_unlock(&child->sighand->siglock); } static bool looks_like_a_spurious_pid(struct task_struct *task) { if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) return false; if (task_pid_vnr(task) == task->ptrace_message) return false; /* * The tracee changed its pid but the PTRACE_EVENT_EXEC event * was not wait()'ed, most probably debugger targets the old * leader which was destroyed in de_thread(). */ return true; } /* Ensure that nothing can wake it up, even SIGKILL */ static bool ptrace_freeze_traced(struct task_struct *task) { bool ret = false; /* Lockless, nobody but us can set this flag */ if (task->jobctl & JOBCTL_LISTENING) return ret; spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { task->state = __TASK_TRACED; ret = true; } spin_unlock_irq(&task->sighand->siglock); return ret; } static void ptrace_unfreeze_traced(struct task_struct *task) { if (task->state != __TASK_TRACED) return; WARN_ON(!task->ptrace || task->parent != current); /* * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely. * Recheck state under the lock to close this race. */ spin_lock_irq(&task->sighand->siglock); if (task->state == __TASK_TRACED) { if (__fatal_signal_pending(task)) wake_up_state(task, __TASK_TRACED); else task->state = TASK_TRACED; } spin_unlock_irq(&task->sighand->siglock); } /** * ptrace_check_attach - check whether ptracee is ready for ptrace operation * @child: ptracee to check for * @ignore_state: don't check whether @child is currently %TASK_TRACED * * Check whether @child is being ptraced by %current and ready for further * ptrace operations. If @ignore_state is %false, @child also should be in * %TASK_TRACED state and on return the child is guaranteed to be traced * and not executing. If @ignore_state is %true, @child can be in any * state. * * CONTEXT: * Grabs and releases tasklist_lock and @child->sighand->siglock. * * RETURNS: * 0 on success, -ESRCH if %child is not ready. */ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) { int ret = -ESRCH; /* * We take the read lock around doing both checks to close a * possible race where someone else was tracing our child and * detached between these two checks. After this locked check, * we are sure that this is our traced child and that can only * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); if (child->ptrace && child->parent == current) { WARN_ON(child->state == __TASK_TRACED); /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ if (ignore_state || ptrace_freeze_traced(child)) ret = 0; } read_unlock(&tasklist_lock); if (!ret && !ignore_state) { if (!wait_task_inactive(child, __TASK_TRACED)) { /* * This can only happen if may_ptrace_stop() fails and * ptrace_stop() changes ->state back to TASK_RUNNING, * so we should not worry about leaking __TASK_TRACED. */ WARN_ON(child->state == __TASK_TRACED); ret = -ESRCH; } } return ret; } static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { if (mode & PTRACE_MODE_NOAUDIT) return ns_capable_noaudit(ns, CAP_SYS_PTRACE); return ns_capable(ns, CAP_SYS_PTRACE); } /* Returns 0 on success, -errno on denial. */ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; struct mm_struct *mm; kuid_t caller_uid; kgid_t caller_gid; if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); return -EPERM; } /* May we inspect the given task? * This check is used both for attaching with ptrace * and for allowing access to sensitive information in /proc. * * ptrace_attach denies several cases that /proc allows * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); if (mode & PTRACE_MODE_FSCREDS) { caller_uid = cred->fsuid; caller_gid = cred->fsgid; } else { /* * Using the euid would make more sense here, but something * in userland might rely on the old behavior, and this * shouldn't be a security problem since * PTRACE_MODE_REALCREDS implies that the caller explicitly * used a syscall that requests access to another process * (and not a filesystem syscall to procfs). */ caller_uid = cred->uid; caller_gid = cred->gid; } tcred = __task_cred(task); if (uid_eq(caller_uid, tcred->euid) && uid_eq(caller_uid, tcred->suid) && uid_eq(caller_uid, tcred->uid) && gid_eq(caller_gid, tcred->egid) && gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; ok: rcu_read_unlock(); /* * If a task drops privileges and becomes nondumpable (through a syscall * like setresuid()) while we are trying to access it, we must ensure * that the dumpability is read after the credentials; otherwise, * we may be able to attach to a task that we shouldn't be able to * attach to (as if the task had dropped privileges without becoming * nondumpable). * Pairs with a write barrier in commit_creds(). */ smp_rmb(); mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); } bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; task_lock(task); err = __ptrace_may_access(task, mode); task_unlock(task); return !err; } static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags) { bool seize = (request == PTRACE_SEIZE); int retval; retval = -EIO; if (seize) { if (addr != 0) goto out; if (flags & ~(unsigned long)PTRACE_O_MASK) goto out; flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); } else { flags = PT_PTRACED; } audit_ptrace(task); retval = -EPERM; if (unlikely(task->flags & PF_KTHREAD)) goto out; if (same_thread_group(task, current)) goto out; /* * Protect exec's credential calculations against our interference; * SUID, SGID and LSM creds get determined differently * under ptrace. */ retval = -ERESTARTNOINTR; if (mutex_lock_interruptible(&task->signal->cred_guard_mutex)) goto out; task_lock(task); retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); task_unlock(task); if (retval) goto unlock_creds; write_lock_irq(&tasklist_lock); retval = -EPERM; if (unlikely(task->exit_state)) goto unlock_tasklist; if (task->ptrace) goto unlock_tasklist; if (seize) flags |= PT_SEIZED; task->ptrace = flags; ptrace_link(task, current); /* SEIZE doesn't trap tracee on attach */ if (!seize) send_sig_info(SIGSTOP, SEND_SIG_PRIV, task); spin_lock(&task->sighand->siglock); /* * If the task is already STOPPED, set JOBCTL_TRAP_STOP and * TRAPPING, and kick it so that it transits to TRACED. TRAPPING * will be cleared if the child completes the transition or any * event which clears the group stop states happens. We'll wait * for the transition to complete before returning from this * function. * * This hides STOPPED -> RUNNING -> TRACED transition from the * attaching thread but a different thread in the same group can * still observe the transient RUNNING state. IOW, if another * thread's WNOHANG wait(2) on the stopped tracee races against * ATTACH, the wait(2) may fail due to the transient RUNNING. * * The following task_is_stopped() test is safe as both transitions * in and out of STOPPED are protected by siglock. */ if (task_is_stopped(task) && task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) signal_wake_up_state(task, __TASK_STOPPED); spin_unlock(&task->sighand->siglock); retval = 0; unlock_tasklist: write_unlock_irq(&tasklist_lock); unlock_creds: mutex_unlock(&task->signal->cred_guard_mutex); out: if (!retval) { /* * We do not bother to change retval or clear JOBCTL_TRAPPING * if wait_on_bit() was interrupted by SIGKILL. The tracer will * not return to user-mode, it will exit and clear this bit in * __ptrace_unlink() if it wasn't already cleared by the tracee; * and until then nobody can ptrace this task. */ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE); proc_ptrace_connector(task, PTRACE_ATTACH); } return retval; } /** * ptrace_traceme -- helper for PTRACE_TRACEME * * Performs checks and sets PT_PTRACED. * Should be used by all ptrace implementations for PTRACE_TRACEME. */ static int ptrace_traceme(void) { int ret = -EPERM; write_lock_irq(&tasklist_lock); /* Are we already being traced? */ if (!current->ptrace) { ret = security_ptrace_traceme(current->parent); /* * Check PF_EXITING to ensure ->real_parent has not passed * exit_ptrace(). Otherwise we don't report the error but * pretend ->real_parent untraces us right after return. */ if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace = PT_PTRACED; ptrace_link(current, current->real_parent); } } write_unlock_irq(&tasklist_lock); return ret; } /* * Called with irqs disabled, returns true if childs should reap themselves. */ static int ignoring_children(struct sighand_struct *sigh) { int ret; spin_lock(&sigh->siglock); ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); spin_unlock(&sigh->siglock); return ret; } /* * Called with tasklist_lock held for writing. * Unlink a traced task, and clean it up if it was a traced zombie. * Return true if it needs to be reaped with release_task(). * (We can't call release_task() here because we already hold tasklist_lock.) * * If it's a zombie, our attachedness prevented normal parent notification * or self-reaping. Do notification now if it would have happened earlier. * If it should reap itself, return true. * * If it's our own child, there is no notification to do. But if our normal * children self-reap, then this child was prevented by ptrace and we must * reap it now, in that case we must also wake up sub-threads sleeping in * do_wait(). */ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) { bool dead; __ptrace_unlink(p); if (p->exit_state != EXIT_ZOMBIE) return false; dead = !thread_group_leader(p); if (!dead && thread_group_empty(p)) { if (!same_thread_group(p->real_parent, tracer)) dead = do_notify_parent(p, p->exit_signal); else if (ignoring_children(tracer->sighand)) { __wake_up_parent(p, tracer); dead = true; } } /* Mark it as in the process of being reaped. */ if (dead) p->exit_state = EXIT_DEAD; return dead; } static int ptrace_detach(struct task_struct *child, unsigned int data) { if (!valid_signal(data)) return -EIO; /* Architecture-specific hardware disable .. */ ptrace_disable(child); write_lock_irq(&tasklist_lock); /* * We rely on ptrace_freeze_traced(). It can't be killed and * untraced by another thread, it can't be a zombie. */ WARN_ON(!child->ptrace || child->exit_state); /* * tasklist_lock avoids the race with wait_task_stopped(), see * the comment in ptrace_resume(). */ child->exit_code = data; __ptrace_detach(current, child); write_unlock_irq(&tasklist_lock); proc_ptrace_connector(child, PTRACE_DETACH); return 0; } /* * Detach all tasks we were using ptrace on. Called with tasklist held * for writing. */ void exit_ptrace(struct task_struct *tracer, struct list_head *dead) { struct task_struct *p, *n; list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { if (unlikely(p->ptrace & PT_EXITKILL)) send_sig_info(SIGKILL, SEND_SIG_PRIV, p); if (__ptrace_detach(tracer, p)) list_add(&p->ptrace_entry, dead); } } int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; retval = ptrace_access_vm(tsk, src, buf, this_len, FOLL_FORCE); if (!retval) { if (copied) break; return -EIO; } if (copy_to_user(dst, buf, retval)) return -EFAULT; copied += retval; src += retval; dst += retval; len -= retval; } return copied; } int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; if (copy_from_user(buf, src, this_len)) return -EFAULT; retval = ptrace_access_vm(tsk, dst, buf, this_len, FOLL_FORCE | FOLL_WRITE); if (!retval) { if (copied) break; return -EIO; } copied += retval; src += retval; dst += retval; len -= retval; } return copied; } static int ptrace_setoptions(struct task_struct *child, unsigned long data) { unsigned flags; if (data & ~(unsigned long)PTRACE_O_MASK) return -EINVAL; if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || !IS_ENABLED(CONFIG_SECCOMP)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (seccomp_mode(&current->seccomp) != SECCOMP_MODE_DISABLED || current->ptrace & PT_SUSPEND_SECCOMP) return -EPERM; } /* Avoid intermediate state when all opts are cleared */ flags = child->ptrace; flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT); flags |= (data << PT_OPT_FLAG_SHIFT); child->ptrace = flags; return 0; } static int ptrace_getsiginfo(struct task_struct *child, kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(info, child->last_siginfo); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_setsiginfo(struct task_struct *child, const kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(child->last_siginfo, info); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_peek_siginfo(struct task_struct *child, unsigned long addr, unsigned long data) { struct ptrace_peeksiginfo_args arg; struct sigpending *pending; struct sigqueue *q; int ret, i; ret = copy_from_user(&arg, (void __user *) addr, sizeof(struct ptrace_peeksiginfo_args)); if (ret) return -EFAULT; if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED) return -EINVAL; /* unknown flags */ if (arg.nr < 0) return -EINVAL; /* Ensure arg.off fits in an unsigned long */ if (arg.off > ULONG_MAX) return 0; if (arg.flags & PTRACE_PEEKSIGINFO_SHARED) pending = &child->signal->shared_pending; else pending = &child->pending; for (i = 0; i < arg.nr; ) { kernel_siginfo_t info; unsigned long off = arg.off + i; bool found = false; spin_lock_irq(&child->sighand->siglock); list_for_each_entry(q, &pending->list, list) { if (!off--) { found = true; copy_siginfo(&info, &q->info); break; } } spin_unlock_irq(&child->sighand->siglock); if (!found) /* beyond the end of the list */ break; #ifdef CONFIG_COMPAT if (unlikely(in_compat_syscall())) { compat_siginfo_t __user *uinfo = compat_ptr(data); if (copy_siginfo_to_user32(uinfo, &info)) { ret = -EFAULT; break; } } else #endif { siginfo_t __user *uinfo = (siginfo_t __user *) data; if (copy_siginfo_to_user(uinfo, &info)) { ret = -EFAULT; break; } } data += sizeof(siginfo_t); i++; if (signal_pending(current)) break; cond_resched(); } if (i > 0) return i; return ret; } #ifdef PTRACE_SINGLESTEP #define is_singlestep(request) ((request) == PTRACE_SINGLESTEP) #else #define is_singlestep(request) 0 #endif #ifdef PTRACE_SINGLEBLOCK #define is_singleblock(request) ((request) == PTRACE_SINGLEBLOCK) #else #define is_singleblock(request) 0 #endif #ifdef PTRACE_SYSEMU #define is_sysemu_singlestep(request) ((request) == PTRACE_SYSEMU_SINGLESTEP) #else #define is_sysemu_singlestep(request) 0 #endif static int ptrace_resume(struct task_struct *child, long request, unsigned long data) { bool need_siglock; if (!valid_signal(data)) return -EIO; if (request == PTRACE_SYSCALL) set_tsk_thread_flag(child, TIF_SYSCALL_TRACE); else clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); #ifdef TIF_SYSCALL_EMU if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP) set_tsk_thread_flag(child, TIF_SYSCALL_EMU); else clear_tsk_thread_flag(child, TIF_SYSCALL_EMU); #endif if (is_singleblock(request)) { if (unlikely(!arch_has_block_step())) return -EIO; user_enable_block_step(child); } else if (is_singlestep(request) || is_sysemu_singlestep(request)) { if (unlikely(!arch_has_single_step())) return -EIO; user_enable_single_step(child); } else { user_disable_single_step(child); } /* * Change ->exit_code and ->state under siglock to avoid the race * with wait_task_stopped() in between; a non-zero ->exit_code will * wrongly look like another report from tracee. * * Note that we need siglock even if ->exit_code == data and/or this * status was not reported yet, the new status must not be cleared by * wait_task_stopped() after resume. * * If data == 0 we do not care if wait_task_stopped() reports the old * status and clears the code too; this can't race with the tracee, it * takes siglock after resume. */ need_siglock = data && !thread_group_empty(current); if (need_siglock) spin_lock_irq(&child->sighand->siglock); child->exit_code = data; wake_up_state(child, __TASK_TRACED); if (need_siglock) spin_unlock_irq(&child->sighand->siglock); return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK static const struct user_regset * find_regset(const struct user_regset_view *view, unsigned int type) { const struct user_regset *regset; int n; for (n = 0; n < view->n; ++n) { regset = view->regsets + n; if (regset->core_note_type == type) return regset; } return NULL; } static int ptrace_regset(struct task_struct *task, int req, unsigned int type, struct iovec *kiov) { const struct user_regset_view *view = task_user_regset_view(task); const struct user_regset *regset = find_regset(view, type); int regset_no; if (!regset || (kiov->iov_len % regset->size) != 0) return -EINVAL; regset_no = regset - view->regsets; kiov->iov_len = min(kiov->iov_len, (__kernel_size_t) (regset->n * regset->size)); if (req == PTRACE_GETREGSET) return copy_regset_to_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); else return copy_regset_from_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); } /* * This is declared in linux/regset.h and defined in machine-dependent * code. We put the export here, near the primary machine-neutral use, * to ensure no machine forgets it. */ EXPORT_SYMBOL_GPL(task_user_regset_view); static unsigned long ptrace_get_syscall_info_entry(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { unsigned long args[ARRAY_SIZE(info->entry.args)]; int i; info->op = PTRACE_SYSCALL_INFO_ENTRY; info->entry.nr = syscall_get_nr(child, regs); syscall_get_arguments(child, regs, args); for (i = 0; i < ARRAY_SIZE(args); i++) info->entry.args[i] = args[i]; /* args is the last field in struct ptrace_syscall_info.entry */ return offsetofend(struct ptrace_syscall_info, entry.args); } static unsigned long ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { /* * As struct ptrace_syscall_info.entry is currently a subset * of struct ptrace_syscall_info.seccomp, it makes sense to * initialize that subset using ptrace_get_syscall_info_entry(). * This can be reconsidered in the future if these structures * diverge significantly enough. */ ptrace_get_syscall_info_entry(child, regs, info); info->op = PTRACE_SYSCALL_INFO_SECCOMP; info->seccomp.ret_data = child->ptrace_message; /* ret_data is the last field in struct ptrace_syscall_info.seccomp */ return offsetofend(struct ptrace_syscall_info, seccomp.ret_data); } static unsigned long ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { info->op = PTRACE_SYSCALL_INFO_EXIT; info->exit.rval = syscall_get_error(child, regs); info->exit.is_error = !!info->exit.rval; if (!info->exit.is_error) info->exit.rval = syscall_get_return_value(child, regs); /* is_error is the last field in struct ptrace_syscall_info.exit */ return offsetofend(struct ptrace_syscall_info, exit.is_error); } static int ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size, void __user *datavp) { struct pt_regs *regs = task_pt_regs(child); struct ptrace_syscall_info info = { .op = PTRACE_SYSCALL_INFO_NONE, .arch = syscall_get_arch(child), .instruction_pointer = instruction_pointer(regs), .stack_pointer = user_stack_pointer(regs), }; unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry); unsigned long write_size; /* * This does not need lock_task_sighand() to access * child->last_siginfo because ptrace_freeze_traced() * called earlier by ptrace_check_attach() ensures that * the tracee cannot go away and clear its last_siginfo. */ switch (child->last_siginfo ? child->last_siginfo->si_code : 0) { case SIGTRAP | 0x80: switch (child->ptrace_message) { case PTRACE_EVENTMSG_SYSCALL_ENTRY: actual_size = ptrace_get_syscall_info_entry(child, regs, &info); break; case PTRACE_EVENTMSG_SYSCALL_EXIT: actual_size = ptrace_get_syscall_info_exit(child, regs, &info); break; } break; case SIGTRAP | (PTRACE_EVENT_SECCOMP << 8): actual_size = ptrace_get_syscall_info_seccomp(child, regs, &info); break; } write_size = min(actual_size, user_size); return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data) { bool seized = child->ptrace & PT_SEIZED; int ret = -EIO; kernel_siginfo_t siginfo, *si; void __user *datavp = (void __user *) data; unsigned long __user *datalp = datavp; unsigned long flags; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: return generic_ptrace_peekdata(child, addr, data); case PTRACE_POKETEXT: case PTRACE_POKEDATA: return generic_ptrace_pokedata(child, addr, data); #ifdef PTRACE_OLDSETOPTIONS case PTRACE_OLDSETOPTIONS: #endif case PTRACE_SETOPTIONS: ret = ptrace_setoptions(child, data); break; case PTRACE_GETEVENTMSG: ret = put_user(child->ptrace_message, datalp); break; case PTRACE_PEEKSIGINFO: ret = ptrace_peek_siginfo(child, addr, data); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user(datavp, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user(&siginfo, datavp); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; case PTRACE_GETSIGMASK: { sigset_t *mask; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (test_tsk_restore_sigmask(child)) mask = &child->saved_sigmask; else mask = &child->blocked; if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; } case PTRACE_SETSIGMASK: { sigset_t new_set; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (copy_from_user(&new_set, datavp, sizeof(sigset_t))) { ret = -EFAULT; break; } sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); /* * Every thread does recalc_sigpending() after resume, so * retarget_shared_pending() and recalc_sigpending() are not * called here. */ spin_lock_irq(&child->sighand->siglock); child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); clear_tsk_restore_sigmask(child); ret = 0; break; } case PTRACE_INTERRUPT: /* * Stop tracee without any side-effect on signal or job * control. At least one trap is guaranteed to happen * after this request. If @child is already trapped, the * current trap is not disturbed and another trap will * happen after the current trap is ended with PTRACE_CONT. * * The actual trap might not be PTRACE_EVENT_STOP trap but * the pending condition is cleared regardless. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; /* * INTERRUPT doesn't disturb existing trap sans one * exception. If ptracer issued LISTEN for the current * STOP, this INTERRUPT should clear LISTEN and re-trap * tracee into STOP. */ if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP))) ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING); unlock_task_sighand(child, &flags); ret = 0; break; case PTRACE_LISTEN: /* * Listen for events. Tracee must be in STOP. It's not * resumed per-se but is not considered to be in TRACED by * wait(2) or ptrace(2). If an async event (e.g. group * stop state change) happens, tracee will enter STOP trap * again. Alternatively, ptracer can issue INTERRUPT to * finish listening and re-trap tracee into STOP. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; si = child->last_siginfo; if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) { child->jobctl |= JOBCTL_LISTENING; /* * If NOTIFY is set, it means event happened between * start of this trap and now. Trigger re-trap. */ if (child->jobctl & JOBCTL_TRAP_NOTIFY) ptrace_signal_wake_up(child, true); ret = 0; } unlock_task_sighand(child, &flags); break; case PTRACE_DETACH: /* detach a process that was attached. */ ret = ptrace_detach(child, data); break; #ifdef CONFIG_BINFMT_ELF_FDPIC case PTRACE_GETFDPIC: { struct mm_struct *mm = get_task_mm(child); unsigned long tmp = 0; ret = -ESRCH; if (!mm) break; switch (addr) { case PTRACE_GETFDPIC_EXEC: tmp = mm->context.exec_fdpic_loadmap; break; case PTRACE_GETFDPIC_INTERP: tmp = mm->context.interp_fdpic_loadmap; break; default: break; } mmput(mm); ret = put_user(tmp, datalp); break; } #endif #ifdef PTRACE_SINGLESTEP case PTRACE_SINGLESTEP: #endif #ifdef PTRACE_SINGLEBLOCK case PTRACE_SINGLEBLOCK: #endif #ifdef PTRACE_SYSEMU case PTRACE_SYSEMU: case PTRACE_SYSEMU_SINGLESTEP: #endif case PTRACE_SYSCALL: case PTRACE_CONT: return ptrace_resume(child, request, data); case PTRACE_KILL: if (child->exit_state) /* already dead */ return 0; return ptrace_resume(child, request, SIGKILL); #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct iovec __user *uiov = datavp; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(kiov.iov_base, &uiov->iov_base) || __get_user(kiov.iov_len, &uiov->iov_len)) return -EFAULT; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } case PTRACE_GET_SYSCALL_INFO: ret = ptrace_get_syscall_info(child, addr, datavp); break; #endif case PTRACE_SECCOMP_GET_FILTER: ret = seccomp_get_filter(child, addr, datavp); break; case PTRACE_SECCOMP_GET_METADATA: ret = seccomp_get_metadata(child, addr, datavp); break; default: break; } return ret; } #ifndef arch_ptrace_attach #define arch_ptrace_attach(child) do { } while (0) #endif SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, unsigned long, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); if (!ret) arch_ptrace_attach(current); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); /* * Some architectures need to do book-keeping after * a ptrace attach. */ if (!ret) arch_ptrace_attach(child); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (ret < 0) goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); out_put_task_struct: put_task_struct(child); out: return ret; } int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, unsigned long data) { unsigned long tmp; int copied; copied = ptrace_access_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE); if (copied != sizeof(tmp)) return -EIO; return put_user(tmp, (unsigned long __user *)data); } int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data) { int copied; copied = ptrace_access_vm(tsk, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); return (copied == sizeof(data)) ? 0 : -EIO; } #if defined CONFIG_COMPAT int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data) { compat_ulong_t __user *datap = compat_ptr(data); compat_ulong_t word; kernel_siginfo_t siginfo; int ret; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: ret = ptrace_access_vm(child, addr, &word, sizeof(word), FOLL_FORCE); if (ret != sizeof(word)) ret = -EIO; else ret = put_user(word, datap); break; case PTRACE_POKETEXT: case PTRACE_POKEDATA: ret = ptrace_access_vm(child, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); ret = (ret != sizeof(data) ? -EIO : 0); break; case PTRACE_GETEVENTMSG: ret = put_user((compat_ulong_t) child->ptrace_message, datap); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user32( (struct compat_siginfo __user *) datap, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user32( &siginfo, (struct compat_siginfo __user *) datap); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct compat_iovec __user *uiov = (struct compat_iovec __user *) datap; compat_uptr_t ptr; compat_size_t len; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(ptr, &uiov->iov_base) || __get_user(len, &uiov->iov_len)) return -EFAULT; kiov.iov_base = compat_ptr(ptr); kiov.iov_len = len; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } #endif default: ret = ptrace_request(child, request, addr, data); } return ret; } COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid, compat_long_t, addr, compat_long_t, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); /* * Some architectures need to do book-keeping after * a ptrace attach. */ if (!ret) arch_ptrace_attach(child); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (!ret) { ret = compat_arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); } out_put_task_struct: put_task_struct(child); out: return ret; } #endif /* CONFIG_COMPAT */
1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * * Copyright (C) 2002, Linus Torvalds. * * Contains all the functions related to writing back and waiting * upon dirty inodes against superblocks, and writing back dirty * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> #include <linux/memcontrol.h> #include "internal.h" /* * 4MB minimal write chunk size */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) /* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct wb_completion *done; /* set if the caller waits */ }; /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its * timestamps updated and when they finally get written out to be two * dirtytime_expire_intervals. We set the default to 12 hours (in * seconds), which means most of the time inodes will have their * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_io_list); } /* * Include the creation of the trace points after defining the * wb_writeback_work structure and inline functions so that the definition * remains local to this file. */ #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static bool wb_io_lists_populated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb)) { return false; } else { set_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(!wb->avg_write_bandwidth); atomic_long_add(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth); return true; } } static void wb_io_lists_depopulated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { clear_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth) < 0); } } /** * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list * @inode: inode to be moved * @wb: target bdi_writeback * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. * Returns %true if @inode is the first occupant of the !dirty_time IO * lists; otherwise, %false. */ static bool inode_io_list_move_locked(struct inode *inode, struct bdi_writeback *wb, struct list_head *head) { assert_spin_locked(&wb->list_lock); list_move(&inode->i_io_list, head); /* dirty_time doesn't count as dirty_io until expiration */ if (head != &wb->b_dirty_time) return wb_io_lists_populated(wb); wb_io_lists_depopulated(wb); return false; } /** * inode_io_list_del_locked - remove an inode from its bdi_writeback IO list * @inode: inode to be removed * @wb: bdi_writeback @inode is being removed from * * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and * clear %WB_has_dirty_io if all are empty afterwards. */ static void inode_io_list_del_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); spin_unlock_bh(&wb->work_lock); } static void finish_writeback_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { struct wb_completion *done = work->done; if (work->auto_free) kfree(work); if (done) { wait_queue_head_t *waitq = done->waitq; /* @done can't be accessed after the following dec */ if (atomic_dec_and_test(&done->cnt)) wake_up_all(waitq); } } static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); if (work->done) atomic_inc(&work->done->cnt); spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else finish_writeback_work(wb, work); spin_unlock_bh(&wb->work_lock); } /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field * set to @done, which should have been initialized with * DEFINE_WB_COMPLETION(). This function returns after all such work items * are completed. Work items which are waited upon aren't freed * automatically on completion. */ void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK /* * Parameters for foreign inode detection, see wbc_detach_inode() to see * how they're used. * * These paramters are inherently heuristical as the detection target * itself is fuzzy. All we want to do is detaching an inode from the * current owner if it's being written to by some other cgroups too much. * * The current cgroup writeback is built on the assumption that multiple * cgroups writing to the same inode concurrently is very rare and a mode * of operation which isn't well supported. As such, the goal is not * taking too long when a different cgroup takes over an inode while * avoiding too aggressive flip-flops from occasional foreign writes. * * We record, very roughly, 2s worth of IO time history and if more than * half of that is foreign, trigger the switch. The recording is quantized * to 16 slots. To avoid tiny writes from swinging the decision too much, * writes smaller than 1/8 of avg size are ignored. */ #define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ #define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ #define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ #define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ #define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ #define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) /* each slot's duration is 2s / 16 */ #define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) /* if foreign slots >= 8, switch */ #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; if (page) { memcg_css = mem_cgroup_css_from_page(page); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); } } if (!wb) wb = &bdi->wb; /* * There may be multiple instances of this function racing to * update the same inode. Use cmpxchg() to tell the winner. */ if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } EXPORT_SYMBOL_GPL(__inode_attach_wb); /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * * Returns @inode's wb with its list_lock held. @inode->i_lock must be * held on entry and is released on return. The returned wb is guaranteed * to stay @inode's associated wb until its list_lock is released. */ static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { while (true) { struct bdi_writeback *wb = inode_to_wb(inode); /* * inode_to_wb() association is protected by both * @inode->i_lock and @wb->list_lock but list_lock nests * outside i_lock. Drop i_lock and verify that the * association hasn't changed after acquiring list_lock. */ wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); /* i_wb may have changed inbetween, can't use inode_to_wb() */ if (likely(wb == inode->i_wb)) { wb_put(wb); /* @inode already has ref */ return wb; } spin_unlock(&wb->list_lock); wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } } /** * inode_to_wb_and_lock_list - determine an inode's wb and lock it * @inode: inode of interest * * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held * on entry. */ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { spin_lock(&inode->i_lock); return locked_inode_to_wb_and_lock_list(inode); } struct inode_switch_wbs_context { struct inode *inode; struct bdi_writeback *new_wb; struct rcu_head rcu_head; struct work_struct work; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { down_write(&bdi->wb_switch_rwsem); } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { up_write(&bdi->wb_switch_rwsem); } static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; struct backing_dev_info *bdi = inode_to_bdi(inode); struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; XA_STATE(xas, &mapping->i_pages, 0); struct page *page; bool switched = false; /* * If @inode switches cgwb membership while sync_inodes_sb() is * being issued, sync_inodes_sb() might miss it. Synchronize. */ down_read(&bdi->wb_switch_rwsem); /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be * synchronizing against the i_pages lock. * * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ if (old_wb < new_wb) { spin_lock(&old_wb->list_lock); spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&new_wb->list_lock); spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING is visible under i_lock, the eviction path owns * the inode and we shouldn't modify ->i_io_list. */ if (unlikely(inode->i_state & I_FREEING)) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to * pages actually under writeback. */ xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_DIRTY) { if (PageDirty(page)) { dec_wb_stat(old_wb, WB_RECLAIMABLE); inc_wb_stat(new_wb, WB_RECLAIMABLE); } } xas_set(&xas, 0); xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { WARN_ON_ONCE(!PageWriteback(page)); dec_wb_stat(old_wb, WB_WRITEBACK); inc_wb_stat(new_wb, WB_WRITEBACK); } wb_get(new_wb); /* * Transfer to @new_wb's IO list if necessary. The specific list * @inode was on is ignored and the inode is put on ->b_dirty which * is always correct including from ->b_dirty_time. The transfer * preserves @inode->dirtied_when ordering. */ if (!list_empty(&inode->i_io_list)) { struct inode *pos; inode_io_list_del_locked(inode, old_wb); inode->i_wb = new_wb; list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) if (time_after_eq(inode->dirtied_when, pos->dirtied_when)) break; inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); } else { inode->i_wb = new_wb; } /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; switched = true; skip_switch: /* * Paired with load_acquire in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); if (switched) { wb_wakeup(new_wb); wb_put(old_wb); } wb_put(new_wb); iput(inode); kfree(isw); atomic_dec(&isw_nr_in_flight); } static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) { struct inode_switch_wbs_context *isw = container_of(rcu_head, struct inode_switch_wbs_context, rcu_head); /* needs to grab bh-unsafe locks, bounce to work item */ INIT_WORK(&isw->work, inode_switch_wbs_work_fn); queue_work(isw_wq, &isw->work); } /** * inode_switch_wbs - change the wb association of an inode * @inode: target inode * @new_wb_id: ID of the new wb * * Switch @inode's wb association to the wb identified by @new_wb_id. The * switching is performed asynchronously and may fail silently. */ static void inode_switch_wbs(struct inode *inode, int new_wb_id) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; /* noop if seems to be already in progress */ if (inode->i_state & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; isw = kzalloc(sizeof(*isw), GFP_ATOMIC); if (!isw) return; atomic_inc(&isw_nr_in_flight); /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) goto out_free; isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!isw->new_wb) goto out_free; /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING) || inode_to_wb(inode) == isw->new_wb) { spin_unlock(&inode->i_lock); goto out_free; } inode->i_state |= I_WB_SWITCH; __iget(inode); spin_unlock(&inode->i_lock); isw->inode = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; out_free: atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode * * @inode is locked and about to be written back under the control of @wbc. * Record @inode's writeback context into @wbc and unlock the i_lock. On * writeback completion, wbc_detach_inode() should be called. This is used * to track the cgroup writeback context. */ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) { if (!inode_cgwb_enabled(inode)) { spin_unlock(&inode->i_lock); return; } wbc->wb = inode_to_wb(inode); wbc->inode = inode; wbc->wb_id = wbc->wb->memcg_css->id; wbc->wb_lcand_id = inode->i_wb_frn_winner; wbc->wb_tcand_id = 0; wbc->wb_bytes = 0; wbc->wb_lcand_bytes = 0; wbc->wb_tcand_bytes = 0; wb_get(wbc->wb); spin_unlock(&inode->i_lock); /* * A dying wb indicates that either the blkcg associated with the * memcg changed or the associated memcg is dying. In the first * case, a replacement wb should already be available and we should * refresh the wb immediately. In the second case, trying to * refresh will keep failing. */ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection * @wbc: writeback_control of the just finished writeback * * To be called after a writeback attempt of an inode finishes and undoes * wbc_attach_and_unlock_inode(). Can be called under any context. * * As concurrent write sharing of an inode is expected to be very rare and * memcg only tracks page ownership on first-use basis severely confining * the usefulness of such sharing, cgroup writeback tracks ownership * per-inode. While the support for concurrent write sharing of an inode * is deemed unnecessary, an inode being written to by different cgroups at * different points in time is a lot more common, and, more importantly, * charging only by first-use can too readily lead to grossly incorrect * behaviors (single foreign page can lead to gigabytes of writeback to be * incorrectly attributed). * * To resolve this issue, cgroup writeback detects the majority dirtier of * an inode and transfers the ownership to it. To avoid unnnecessary * oscillation, the detection mechanism keeps track of history and gives * out the switch verdict only if the foreign usage pattern is stable over * a certain amount of time and/or writeback attempts. * * On each writeback attempt, @wbc tries to detect the majority writer * using Boyer-Moore majority vote algorithm. In addition to the byte * count from the majority voting, it also counts the bytes written for the * current wb and the last round's winner wb (max of last round's current * wb, the winner from two rounds ago, and the last round's majority * candidate). Keeping track of the historical winner helps the algorithm * to semi-reliably detect the most active writer even when it's not the * absolute majority. * * Once the winner of the round is determined, whether the winner is * foreign or not and how much IO time the round consumed is recorded in * inode->i_wb_frn_history. If the amount of recorded foreign IO time is * over a certain threshold, the switch verdict is given. */ void wbc_detach_inode(struct writeback_control *wbc) { struct bdi_writeback *wb = wbc->wb; struct inode *inode = wbc->inode; unsigned long avg_time, max_bytes, max_time; u16 history; int max_id; if (!wb) return; history = inode->i_wb_frn_history; avg_time = inode->i_wb_frn_avg_time; /* pick the winner of this round */ if (wbc->wb_bytes >= wbc->wb_lcand_bytes && wbc->wb_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_id; max_bytes = wbc->wb_bytes; } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_lcand_id; max_bytes = wbc->wb_lcand_bytes; } else { max_id = wbc->wb_tcand_id; max_bytes = wbc->wb_tcand_bytes; } /* * Calculate the amount of IO time the winner consumed and fold it * into the running average kept per inode. If the consumed IO * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for * deciding whether to switch or not. This is to prevent one-off * small dirtiers from skewing the verdict. */ max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, wb->avg_write_bandwidth); if (avg_time) avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - (avg_time >> WB_FRN_TIME_AVG_SHIFT); else avg_time = max_time; /* immediate catch up on first run */ if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { int slots; /* * The switch verdict is reached if foreign wb's consume * more than a certain proportion of IO time in a * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot * history mask where each bit represents one sixteenth of * the period. Determine the number of slots to shift into * history from @max_time. */ slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), (unsigned long)WB_FRN_HIST_MAX_SLOTS); history <<= slots; if (wbc->wb_id != max_id) history |= (1U << slots) - 1; if (history) trace_inode_foreign_history(inode, wbc, history); /* * Switch if the current wb isn't the consistent winner. * If there are multiple closely competing dirtiers, the * inode may switch across them repeatedly over time, which * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ if (hweight32(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } /* * Multiple instances of this function may race to update the * following fields but we don't mind occassional inaccuracies. */ inode->i_wb_frn_winner = max_id; inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); inode->i_wb_frn_history = history; wb_put(wbc->wb); wbc->wb = NULL; } EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @page: page being written out * @bytes: number of bytes being written out * * @bytes from @page are about to written out during the writeback * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes) { struct cgroup_subsys_state *css; int id; /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_page(page); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; return; } if (id == wbc->wb_lcand_id) wbc->wb_lcand_bytes += bytes; /* Boyer-Moore majority vote algorithm */ if (!wbc->wb_tcand_bytes) wbc->wb_tcand_id = id; if (id == wbc->wb_tcand_id) wbc->wb_tcand_bytes += bytes; else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * inode_congested - test whether an inode is congested * @inode: inode to test for congestion (may be NULL) * @cong_bits: mask of WB_[a]sync_congested bits to test * * Tests whether @inode is congested. @cong_bits is the mask of congestion * bits to test and the return value is the mask of set bits. * * If cgroup writeback is enabled for @inode, the congestion state is * determined by whether the cgwb (cgroup bdi_writeback) for the blkcg * associated with @inode is congested; otherwise, the root wb's congestion * state is used. * * @inode is allowed to be NULL as this function is often called on * mapping->host which is NULL for the swapper space. */ int inode_congested(struct inode *inode, int cong_bits) { /* * Once set, ->i_wb never becomes NULL while the inode is alive. * Start transaction iff ->i_wb is visible. */ if (inode && inode_to_wb_is_valid(inode)) { struct bdi_writeback *wb; struct wb_lock_cookie lock_cookie = {}; bool congested; wb = unlocked_inode_to_wb_begin(inode, &lock_cookie); congested = wb_congested(wb, cong_bits); unlocked_inode_to_wb_end(inode, &lock_cookie); return congested; } return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); } EXPORT_SYMBOL_GPL(inode_congested); /** * wb_split_bdi_pages - split nr_pages to write according to bandwidth * @wb: target bdi_writeback to split @nr_pages to * @nr_pages: number of pages to write for the whole bdi * * Split @wb's portion of @nr_pages according to @wb's write bandwidth in * relation to the total write bandwidth of all wb's w/ dirty inodes on * @wb->bdi. */ static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); if (nr_pages == LONG_MAX) return LONG_MAX; /* * This may be called on clean wb's and proportional distribution * may not make sense, just use the original @nr_pages in those * cases. In general, we wanna err on the side of writing more. */ if (!tot_bw || this_bw >= tot_bw) return nr_pages; else return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); } /** * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi * @bdi: target backing_dev_info * @base_work: wb_writeback_work to issue * @skip_if_busy: skip wb's which already have writeback in progress * * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's * distributed to the busy wbs according to each wb's proportion in the * total active write bandwidth of @bdi. */ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { struct bdi_writeback *last_wb = NULL; struct bdi_writeback *wb = list_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; if (last_wb) { wb_put(last_wb); last_wb = NULL; } /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || list_empty(&wb->b_dirty_time))) continue; if (skip_if_busy && writeback_in_progress(wb)) continue; nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 1; wb_queue_work(wb, work); continue; } /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 0; work->done = &fallback_work_done; wb_queue_work(wb, work); /* * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ wb_get(wb); last_wb = wb; rcu_read_unlock(); wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); if (last_wb) wb_put(last_wb); } /** * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id * @nr: number of pages to write, 0 for best-effort dirty flushing * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; int ret; /* lookup bdi and memcg */ bdi = bdi_get_by_id(bdi_id); if (!bdi) return -ENOENT; rcu_read_lock(); memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) { ret = -ENOENT; goto out_bdi_put; } /* * And find the associated wb. If the wb isn't there already * there's nothing to flush, don't create one. */ wb = wb_get_lookup(bdi, memcg_css); if (!wb) { ret = -ENOENT; goto out_css_put; } /* * If @nr is zero, the caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. */ if (!nr) { unsigned long filepages, headroom, dirty, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &dirty, &writeback); nr = dirty * 10 / 8; } /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { work->nr_pages = nr; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; work->done = done; work->auto_free = 1; wb_queue_work(wb, work); ret = 0; } else { ret = -ENOMEM; } wb_put(wb); out_css_put: css_put(memcg_css); out_bdi_put: bdi_put(bdi); return ret; } /** * cgroup_writeback_umount - flush inode wb switches for umount * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through * RCU and then workqueue, so the two need to be flushed in order to ensure * that all previously scheduled switches are finished. As wb switches are * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ void cgroup_writeback_umount(void) { if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to * ensure that all in-flight wb switches are in the workqueue. */ rcu_barrier(); flush_workqueue(isw_wq); } } static int __init cgroup_writeback_init(void) { isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); if (!isw_wq) return -ENOMEM; return 0; } fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); return wb; } static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_lock(&wb->list_lock); return wb; } static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { return nr_pages; } static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { might_sleep(); if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; wb_queue_work(&bdi->wb, base_work); } } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * Add in the number of potentially dirty inodes, because each inode * write can dirty pagecache in the underlying blockdev. */ static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + get_nr_dirty_inodes(); } static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) { if (!wb_has_dirty_io(wb)) return; /* * All callers of this function want to start writeback of all * dirty pages. Places like vmscan can call this at a very * high frequency, causing pointless allocations of tons of * work items and keeping the flusher threads busy retrieving * that work. Ensure that we only allow one of them pending and * inflight at the time. */ if (test_bit(WB_start_all, &wb->state) || test_and_set_bit(WB_start_all, &wb->state)) return; wb->start_all_reason = reason; wb_wakeup(wb); } /** * wb_start_background_writeback - start background writeback * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(wb); wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); inode_io_list_del_locked(inode, wb); spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); /* * mark an inode as under writeback on the sb */ void sb_mark_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (list_empty(&inode->i_wb_list)) { list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); trace_sb_mark_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * clear an inode as under writeback on the sb */ void sb_clear_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (!list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (!list_empty(&inode->i_wb_list)) { list_del_init(&inode->i_wb_list); trace_sb_clear_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * Redirty an inode: set its when-it-was dirtied timestamp and move it to the * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); if (!list_empty(&wb->b_dirty)) { struct inode *tail; tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); inode->i_state &= ~I_SYNC_QUEUED; } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { spin_lock(&inode->i_lock); redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); } /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); /* Waiters must see I_SYNC cleared before being woken up */ smp_mb(); wake_up_bit(&inode->i_state, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) { bool ret = time_after(inode->dirtied_when, t); #ifndef CONFIG_64BIT /* * For inodes being constantly redirtied, dirtied_when can get stuck. * It _appears_ to be in the future, but is actually in distant past. * This test is necessary to prevent such wrapped-around relative times * from permanently stopping the whole bdi writeback. */ ret = ret && time_before_eq(inode->dirtied_when, jiffies); #endif return ret; } #define EXPIRE_DIRTY_ATIME 0x0001 /* * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; int moved = 0; while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (inode_dirtied_after(inode, dirtied_before)) break; list_move(&inode->i_io_list, &tmp); moved++; spin_lock(&inode->i_lock); inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; } /* just one sb in list, splice to dispatch_queue and we're done */ if (!do_sb_sort) { list_splice(&tmp, dispatch_queue); goto out; } /* Move inodes from one superblock together */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) list_move(&inode->i_io_list, dispatch_queue); } } out: return moved; } /* * Queue all expired dirty inodes for io, eldest first. * Before * newly dirtied b_dirty b_io b_more_io * =============> gf edc BA * After * newly dirtied b_dirty b_io b_more_io * =============> g fBAedc * | * +--> dequeue for IO */ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before) { int moved; unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { trace_writeback_write_inode_start(inode, wbc); ret = inode->i_sb->s_op->write_inode(inode, wbc); trace_writeback_write_inode(inode, wbc); return ret; } return 0; } /* * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ static void __inode_wait_for_writeback(struct inode *inode) __releases(inode->i_lock) __acquires(inode->i_lock) { DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); wait_queue_head_t *wqh; wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { spin_unlock(&inode->i_lock); __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); } } /* * Wait for writeback on an inode to complete. Caller must have inode pinned. */ void inode_wait_for_writeback(struct inode *inode) { spin_lock(&inode->i_lock); __inode_wait_for_writeback(inode); spin_unlock(&inode->i_lock); } /* * Sleep until I_SYNC is cleared. This function must be called with i_lock * held and drops it. It is aimed for callers not holding any inode reference * so once i_lock is dropped, inode can go away. */ static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { DEFINE_WAIT(wait); wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC); int sleep; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); sleep = inode->i_state & I_SYNC; spin_unlock(&inode->i_lock); if (sleep) schedule(); finish_wait(wqh, &wait); } /* * Find proper writeback list for the inode depending on its current state and * possibly also change of its state while we were doing writeback. Here we * handle things such as livelock prevention or fairness of writeback among * inodes. This function can be called only by flusher thread - noone else * processes all inodes in writeback lists and requeueing inodes behind flusher * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc) { if (inode->i_state & I_FREEING) return; /* * Sync livelock prevention. Each inode is tagged and synced in one * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ if ((inode->i_state & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* * writeback is not making progress due to locked * buffers. Skip this inode for now. */ redirty_tail_locked(inode, wb); return; } if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ if (wbc->nr_to_write <= 0) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { /* * Writeback blocked by something other than * congestion. Delay the inode for some time to * avoid spinning on the CPU (100% iowait) * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_io_list_del_locked(inode, wb); } } /* * Write out an inode and its dirty pages. Do not update the writeback list * linkage. That is left to the caller. The caller is also responsible for * setting I_SYNC flag and calling inode_sync_complete() to clear it. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; unsigned dirty; int ret; WARN_ON(!(inode->i_state & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); /* * Make sure to wait on the data before writing out the metadata. * This is important for filesystems that modify metadata on data * I/O completion. We don't do it for sync(2) writeback because it has a * separate, external IO completion path and ->sync_fs for guaranteeing * inode metadata is written back correctly. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } /* * If the inode has dirty timestamps and we need to write them, call * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ if ((inode->i_state & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { trace_writeback_lazytime(inode); mark_inode_dirty_sync(inode); } /* * Some filesystems may redirty the inode during the writeback * due to delalloc, clear dirty metadata flags right before * write_inode() */ spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows * __mark_inode_dirty() to test i_state without grabbing i_lock - * either they see the I_DIRTY bits cleared or we see the dirtied * inode. * * I_DIRTY_PAGES is always cleared together above even if @mapping * still has dirty pages. The flag is reinstated after smp_mb() if * necessary. This guarantees that either __mark_inode_dirty() * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. */ smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; spin_unlock(&inode->i_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* * Write out an inode's dirty pages. Either the caller has an active reference * on the inode or the inode has I_WILL_FREE set. * * This function is designed to be called for writing back one inode which * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode() * and does more profound writeback list handling in writeback_sb_inodes(). */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); if (inode->i_state & I_SYNC) { if (wbc->sync_mode != WB_SYNC_ALL) goto out; /* * It's a data-integrity sync. We must wait. Since callers hold * inode reference or inode has I_WILL_FREE set, it cannot go * away under us. */ __inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* * Skip inode if it is clean and we have no outstanding writeback in * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this * function since flusher thread may be doing for example sync in * parallel and if we move the inode, it could get skipped. So here we * make sure inode is on some writeback list and leave it there unless * we have completely cleaned the inode. */ if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If inode is clean, remove it from writeback lists. Otherwise don't * touch it. See comment above for explanation. */ if (!(inode->i_state & I_DIRTY_ALL)) inode_io_list_del_locked(inode, wb); spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: spin_unlock(&inode->i_lock); return ret; } static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; /* * WB_SYNC_ALL mode does livelock avoidance by syncing dirty * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX * here avoids calling into writeback_inodes_wb() more than once. * * The intended call sequence for WB_SYNC_ALL writeback is: * * wb_writeback() * writeback_sb_inodes() <== called only once * write_cache_pages() <== called once for each inode * (quickly) tag currently dirty pages * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { pages = min(wb->avg_write_bandwidth / 2, global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); } return pages; } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. * * NOTE! This is called with wb->list_lock held, and will * unlock and relock that for each inode it ends up doing * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct wb_writeback_work *work) { struct writeback_control wbc = { .sync_mode = work->sync_mode, .tagged_writepages = work->tagged_writepages, .for_kupdate = work->for_kupdate, .for_background = work->for_background, .for_sync = work->for_sync, .range_cyclic = work->range_cyclic, .range_start = 0, .range_end = LLONG_MAX, }; unsigned long start_time = jiffies; long write_chunk; long wrote = 0; /* count both pages and inodes */ while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; if (inode->i_sb != sb) { if (work->sb) { /* * We only want to write back data for this * superblock, move all inodes not belonging * to it back onto the dirty list. */ redirty_tail(inode, wb); continue; } /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and * pin the next superblock. */ break; } /* * Don't bother with new inodes or inodes being freed, first * kind does not need periodic writeout yet, and for the latter * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to * b_more_io so that writeback can proceed with the * other inodes on s_io. * * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ spin_unlock(&inode->i_lock); requeue_io(inode, wb); trace_writeback_sb_inodes_requeue(inode); continue; } spin_unlock(&wb->list_lock); /* * We already requeued the inode if it had I_SYNC set and we * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ if (inode->i_state & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(&wbc, inode); write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; /* * We use I_SYNC to pin the inode in memory. While it is set * evict_inode() will wait so the inode cannot be freed. */ __writeback_single_inode(inode, &wbc); wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote += write_chunk - wbc.nr_to_write; if (need_resched()) { /* * We're trying to balance between building up a nice * long list of IOs to improve our merge rate, and * getting those IOs out quickly for anyone throttling * in balance_dirty_pages(). cond_resched() doesn't * unplug, so get our IOs out the door before we * give up the CPU. */ blk_flush_plug(current); cond_resched(); } /* * Requeue @inode if still dirty. Be careful as @inode may * have been switched to another wb in the meantime. */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) wrote++; requeue_inode(inode, tmp_wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); if (unlikely(tmp_wb != wb)) { spin_unlock(&tmp_wb->list_lock); spin_lock(&wb->list_lock); } /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long start_time = jiffies; long wrote = 0; while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!trylock_super(sb)) { /* * trylock_super() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } /* Leave any unwritten inodes on b_io */ return wrote; } static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, }; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work.nr_pages; } /* * Explicit flushing or periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); for (;;) { /* * Stop writeback when nr_pages has been consumed */ if (work->nr_pages <= 0) break; /* * Background writeout and kupdate-style writeback may * run forever. Stop them if there is other work to do * so that e.g. sync can proceed. They'll be restarted * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ if (work->for_background && !wb_over_bg_thresh(wb)) break; /* * Kupdate and background works are special and we want to * include all inodes that need writing. Livelock avoidance is * handled by these works yielding to any other work so we are * safe. */ if (work->for_kupdate) { dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) dirtied_before = jiffies; trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) queue_io(wb, work, dirtied_before); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); wb_update_bandwidth(wb, wb_start); /* * Did we write something? Try for more * * Dirty inodes are moved to b_io for writeback in batches. * The completion of the current batch does not necessarily * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ if (progress) continue; /* * No more inodes for IO, bail */ if (list_empty(&wb->b_more_io)) break; /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ trace_writeback_wait(wb, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); spin_unlock(&wb->list_lock); /* This function drops i_lock... */ inode_sleep_on_writeback(inode); spin_lock(&wb->list_lock); } spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work->nr_pages; } /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; spin_lock_bh(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } spin_unlock_bh(&wb->work_lock); return work; } static long wb_check_background_flush(struct bdi_writeback *wb) { if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; long nr_pages; /* * When set to zero, disable periodic writeback */ if (!dirty_writeback_interval) return 0; expired = wb->last_old_flush + msecs_to_jiffies(dirty_writeback_interval * 10); if (time_before(jiffies, expired)) return 0; wb->last_old_flush = jiffies; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_start_all(struct bdi_writeback *wb) { long nr_pages; if (!test_bit(WB_start_all, &wb->state)) return 0; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = wb_split_bdi_pages(wb, nr_pages), .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = wb->start_all_reason, }; nr_pages = wb_writeback(wb, &work); } clear_bit(WB_start_all, &wb->state); return nr_pages; } /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { struct wb_writeback_work *work; long wrote = 0; set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); finish_writeback_work(wb, work); } /* * Check for a flush-everything request */ wrote += wb_check_start_all(wb); /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); clear_bit(WB_writeback_running, &wb->state); return wrote; } /* * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); long pages_written; set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } if (!list_empty(&wb->work_list)) wb_wakeup(wb); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) wb_wakeup_delayed(wb); current->flags &= ~PF_SWAPWRITE; } /* * Start writeback of `nr_pages' pages on this bdi. If `nr_pages' is zero, * write back the whole world. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { struct bdi_writeback *wb; if (!bdi_has_dirty_io(bdi)) return; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, reason); } void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { rcu_read_lock(); __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wakeup the flusher threads to start writeback of all currently dirty pages */ void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; /* * If we are expecting writeback progress we must submit plugged IO. */ if (blk_needs_flush_plug(current)) blk_schedule_flush_plug(current); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wake up bdi's periodically to make sure dirtytime inodes gets * written back periodically. We deliberately do *not* check the * b_dirtytime list in wb_has_dirty_io(), since this would cause the * kernel to be constantly waking up once there are any dirtytime * inodes on the system. So instead we define a separate delayed work * function which gets called much more rarely. (By default, only * once every 12 hours.) * * If there is any other write activity going on in the file system, * this function won't be necessary. But if the only thing that has * happened on the file system is a dirtytime inode caused by an atime * update, we need this infrastructure below to make sure that inode * eventually gets pushed out to disk. */ static void wakeup_dirtytime_writeback(struct work_struct *w); static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); static void wakeup_dirtytime_writeback(struct work_struct *w) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) if (!list_empty(&wb->b_dirty_time)) wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int __init start_dirtytime_writeback(void) { schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); return 0; } __initcall(start_dirtytime_writeback); int dirtytime_interval_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) mod_delayed_work(system_wq, &dirtytime_work, 0); return ret; } /** * __mark_inode_dirty - internal function * * @inode: inode to mark * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) * * Mark an inode as dirty. Callers should use mark_inode_dirty or * mark_inode_dirty_sync. * * Put the inode on the super block's dirty list. * * CAREFUL! We mark it dirty unconditionally, but move it onto the * dirty list only if it is hashed or if it refers to a blockdev. * If it was not hashed, it will never be added to the dirty list * even if it is later hashed, as it will have been marked dirty already. * * In short, make sure you hash any inodes _before_ you start marking * them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of * the kernel-internal blockdev inode represents the dirtying time of the * blockdev's pages. This is why for I_DIRTY_PAGES we always use * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; int dirtytime; trace_writeback_mark_inode_dirty(inode, flags); /* * Don't do this for I_DIRTY_PAGES - that doesn't actually * dirty the inode itself */ if (flags & (I_DIRTY_INODE | I_DIRTY_TIME)) { trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags); trace_writeback_dirty_inode(inode, flags); } if (flags & I_DIRTY_INODE) flags &= ~I_DIRTY_TIME; dirtytime = flags & I_DIRTY_TIME; /* * Paired with smp_mb() in __writeback_single_inode() for the * following lockless i_state test. See there for details. */ smp_mb(); if (((inode->i_state & flags) == flags) || (dirtytime && (inode->i_state & I_DIRTY_INODE))) return; spin_lock(&inode->i_lock); if (dirtytime && (inode->i_state & I_DIRTY_INODE)) goto out_unlock_inode; if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; inode_attach_wb(inode, NULL); if (flags & I_DIRTY_INODE) inode->i_state &= ~I_DIRTY_TIME; inode->i_state |= flags; /* * If the inode is queued for writeback by flush worker, just * update its dirty state. Once the flush worker is done with * the inode it will place it on the appropriate superblock * list, based upon its state. */ if (inode->i_state & I_SYNC_QUEUED) goto out_unlock_inode; /* * Only add valid (hashed) inodes to the superblock's * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) goto out_unlock_inode; } if (inode->i_state & I_FREEING) goto out_unlock_inode; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { struct bdi_writeback *wb; struct list_head *dirty_list; bool wakeup_bdi = false; wb = locked_inode_to_wb_and_lock_list(inode); WARN((wb->bdi->capabilities & BDI_CAP_WRITEBACK) && !test_bit(WB_registered, &wb->state), "bdi-%s not registered\n", bdi_dev_name(wb->bdi)); inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; if (inode->i_state & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); spin_unlock(&wb->list_lock); trace_writeback_dirty_inode_enqueue(inode); /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread * to make sure background write-back happens * later. */ if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); return; } } out_unlock_inode: spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); /* * The @s_sync_lock is used to serialise concurrent sync operations * to avoid lock contention problems with concurrent wait_sb_inodes() calls. * Concurrent callers will block on the s_sync_lock rather than doing contending * walks. The queueing maintains sync(2) required behaviour as all the IO that * has been issued up to the time this function is enter is guaranteed to be * completed by the time we have gained the lock and waited for all IO that is * in progress regardless of the order callers are granted the lock. */ static void wait_sb_inodes(struct super_block *sb) { LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); /* * Splice the writeback list onto a temporary list to avoid waiting on * inodes that have started writeback after this point. * * Use rcu_read_lock() to keep the inodes around until we have a * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as * the local list because inodes can be dropped from either by writeback * completion. */ rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); list_splice_init(&sb->s_inodes_wb, &sync_list); /* * Data integrity sync. Must wait for all pages under writeback, because * there may have been pages dirtied before our sync call, but which had * writeout started before we write it out. In which case, the inode * may not be on the dirty list, but we still have to wait for that * writeout. */ while (!list_empty(&sync_list)) { struct inode *inode = list_first_entry(&sync_list, struct inode, i_wb_list); struct address_space *mapping = inode->i_mapping; /* * Move each inode back to the wb list before we drop the lock * to preserve consistency between i_wb_list and the mapping * writeback tag. Writeback completion is responsible to remove * the inode from either list once the writeback tag is cleared. */ list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); /* * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. */ if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(mapping); cond_resched(); iput(inode); rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); } spin_unlock_irq(&sb->s_inode_wblist_lock); rcu_read_unlock(); mutex_unlock(&sb->s_sync_lock); } static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .tagged_writepages = 1, .done = &done, .nr_pages = nr, .reason = reason, }; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); wb_wait_for_completion(&done); } /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock * @nr: the number of pages to write * @reason: reason why some writeback work initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock * @reason: reason why some writeback work was initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock * @reason: reason why some writeback work was initiated * * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { if (!down_read_trylock(&sb->s_umount)) return; __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this * super_block. */ void sync_inodes_sb(struct super_block *sb) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, .for_sync = 1, }; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty * inodes under writeback and I_DIRTY_TIME inodes ignored by * bdi_has_dirty() need to be written out too. */ if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk * @inode: inode to write to disk * @sync: whether the write should be synchronous or not * * This function commits an inode to disk immediately if it is dirty. This is * primarily needed by knfsd. * * The caller must either have a ref on the inode or must have set I_WILL_FREE. */ int write_inode_now(struct inode *inode, int sync) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** * sync_inode - write an inode and its pages to disk. * @inode: the inode to sync * @wbc: controls the writeback mode * * sync_inode() will write an inode and its pages to disk. It will also * correctly update the inode on its superblock's dirty inode lists and will * update inode->i_state. * * The caller must have a ref on the inode. */ int sync_inode(struct inode *inode, struct writeback_control *wbc) { return writeback_single_inode(inode, wbc); } EXPORT_SYMBOL(sync_inode); /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. * * Write an inode to disk and adjust its dirty state after completion. * * Note: only writes the actual inode, no associated data or other metadata. */ int sync_inode_metadata(struct inode *inode, int wait) { struct writeback_control wbc = { .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .nr_to_write = 0, /* metadata-only */ }; return sync_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata);
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * Some corrections by tytso. */ /* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname * lookup logic. */ /* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture. */ #include <linux/init.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/ima.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/device_cgroup.h> #include <linux/fs_struct.h> #include <linux/posix_acl.h> #include <linux/hash.h> #include <linux/bitops.h> #include <linux/init_task.h> #include <linux/uaccess.h> #include "internal.h" #include "mount.h" /* [Feb-1997 T. Schoebel-Theuer] * Fundamental changes in the pathname lookup mechanisms (namei) * were necessary because of omirr. The reason is that omirr needs * to know the _real_ pathname, not the user-supplied one, in case * of symlinks (and also when transname replacements occur). * * The new code replaces the old recursive symlink resolution with * an iterative one (in case of non-nested symlink chains). It does * this with calls to <fs>_follow_link(). * As a side effect, dir_namei(), _namei() and follow_link() are now * replaced with a single function lookup_dentry() that can handle all * the special cases of the former code. * * With the new dcache, the pathname is stored at each inode, at least as * long as the refcount of the inode is positive. As a side effect, the * size of the dcache depends on the inode cache and thus is dynamic. * * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink * resolution to correspond with current state of the code. * * Note that the symlink resolution is not *completely* iterative. * There is still a significant amount of tail- and mid- recursion in * the algorithm. Also, note that <fs>_readlink() is not used in * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink() * may return different results than <fs>_follow_link(). Many virtual * filesystems (including /proc) exhibit this behavior. */ /* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation: * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL * and the name already exists in form of a symlink, try to create the new * name indicated by the symlink. The old code always complained that the * name already exists, due to not following the symlink even if its target * is nonexistent. The new semantics affects also mknod() and link() when * the name is a symlink pointing to a non-existent name. * * I don't know which semantics is the right one, since I have no access * to standards. But I found by trial that HP-UX 9.0 has the full "new" * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the * "old" one. Personally, I think the new semantics is much more logical. * Note that "ln old new" where "new" is a symlink pointing to a non-existing * file does succeed in both HP-UX and SunOs, but not in Solaris * and in the old Linux semantics. */ /* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink * semantics. See the comments in "open_namei" and "do_link" below. * * [10-Sep-98 Alan Modra] Another symlink change. */ /* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks: * inside the path - always follow. * in the last component in creation/removal/renaming - never follow. * if LOOKUP_FOLLOW passed - follow. * if the pathname has trailing slashes - follow. * otherwise - don't follow. * (applied in that order). * * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT * restored for 2.4. This is the last surviving part of old 4.2BSD bug. * During the 2.4 we need to fix the userland stuff depending on it - * hopefully we will be able to get rid of that wart in 2.5. So far only * XEmacs seems to be relying on it... */ /* * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland) * implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives * any extra contention... */ /* In order to reduce some races, while at the same time doing additional * checking and hopefully speeding things up, we copy filenames to the * kernel data space before using them.. * * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ #define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname)) struct filename * getname_flags(const char __user *filename, int flags, int *empty) { struct filename *result; char *kname; int len; result = audit_reusename(filename); if (result) return result; result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); /* * First, try to embed the struct filename inside the names_cache * allocation */ kname = (char *)result->iname; result->name = kname; len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX); if (unlikely(len < 0)) { __putname(result); return ERR_PTR(len); } /* * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a * separate struct filename so we can dedicate the entire * names_cache allocation for the pathname, and re-do the copy from * userland. */ if (unlikely(len == EMBEDDED_NAME_MAX)) { const size_t size = offsetof(struct filename, iname[1]); kname = (char *)result; /* * size is chosen that way we to guarantee that * result->iname[0] is within the same object and that * kname can't be equal to result->iname, no matter what. */ result = kzalloc(size, GFP_KERNEL); if (unlikely(!result)) { __putname(kname); return ERR_PTR(-ENOMEM); } result->name = kname; len = strncpy_from_user(kname, filename, PATH_MAX); if (unlikely(len < 0)) { __putname(kname); kfree(result); return ERR_PTR(len); } if (unlikely(len == PATH_MAX)) { __putname(kname); kfree(result); return ERR_PTR(-ENAMETOOLONG); } } result->refcnt = 1; /* The empty path is special. */ if (unlikely(!len)) { if (empty) *empty = 1; if (!(flags & LOOKUP_EMPTY)) { putname(result); return ERR_PTR(-ENOENT); } } result->uptr = filename; result->aname = NULL; audit_getname(result); return result; } struct filename * getname(const char __user * filename) { return getname_flags(filename, 0, NULL); } struct filename * getname_kernel(const char * filename) { struct filename *result; int len = strlen(filename) + 1; result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); if (len <= EMBEDDED_NAME_MAX) { result->name = (char *)result->iname; } else if (len <= PATH_MAX) { const size_t size = offsetof(struct filename, iname[1]); struct filename *tmp; tmp = kmalloc(size, GFP_KERNEL); if (unlikely(!tmp)) { __putname(result); return ERR_PTR(-ENOMEM); } tmp->name = (char *)result; result = tmp; } else { __putname(result); return ERR_PTR(-ENAMETOOLONG); } memcpy((char *)result->name, filename, len); result->uptr = NULL; result->aname = NULL; result->refcnt = 1; audit_getname(result); return result; } void putname(struct filename *name) { BUG_ON(name->refcnt <= 0); if (--name->refcnt > 0) return; if (name->name != name->iname) { __putname(name->name); kfree(name); } else __putname(name); } static int check_acl(struct inode *inode, int mask) { #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; if (mask & MAY_NOT_BLOCK) { acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS); if (!acl) return -EAGAIN; /* no ->get_acl() calls in RCU mode... */ if (is_uncached_acl(acl)) return -ECHILD; return posix_acl_permission(inode, acl, mask); } acl = get_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { int error = posix_acl_permission(inode, acl, mask); posix_acl_release(acl); return error; } #endif return -EAGAIN; } /* * This does the basic UNIX permission checking. * * Note that the POSIX ACL check cares about the MAY_NOT_BLOCK bit, * for RCU walking. */ static int acl_permission_check(struct inode *inode, int mask) { unsigned int mode = inode->i_mode; /* Are we the owner? If so, ACL's don't matter */ if (likely(uid_eq(current_fsuid(), inode->i_uid))) { mask &= 7; mode >>= 6; return (mask & ~mode) ? -EACCES : 0; } /* Do we have ACL's? */ if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { int error = check_acl(inode, mask); if (error != -EAGAIN) return error; } /* Only RWX matters for group/other mode bits */ mask &= 7; /* * Are the group permissions different from * the other permissions in the bits we care * about? Need to check group ownership if so. */ if (mask & (mode ^ (mode >> 3))) { if (in_group_p(inode->i_gid)) mode >>= 3; } /* Bits in 'mode' clear that we require? */ return (mask & ~mode) ? -EACCES : 0; } /** * generic_permission - check for access rights on a Posix-like filesystem * @inode: inode to check access rights for * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, * %MAY_NOT_BLOCK ...) * * Used to check for read/write/execute permissions on a file. * We use "fsuid" for this, letting us set arbitrary permissions * for filesystem access without changing the "normal" uids which * are used for other things. * * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. */ int generic_permission(struct inode *inode, int mask) { int ret; /* * Do the basic permission checks. */ ret = acl_permission_check(inode, mask); if (ret != -EACCES) return ret; if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) return 0; if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } /* * Searching includes executable on directories, else just read. */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) return 0; /* * Read/write DACs are always overridable. * Executable DACs are overridable when there is * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } EXPORT_SYMBOL(generic_permission); /* * We _really_ want to just do "generic_permission()" without * even looking at the inode->i_op values. So we keep a cache * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ static inline int do_inode_permission(struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) return inode->i_op->permission(inode, mask); /* This gets set once for the inode lifetime */ spin_lock(&inode->i_lock); inode->i_opflags |= IOP_FASTPERM; spin_unlock(&inode->i_lock); } return generic_permission(inode, mask); } /** * sb_permission - Check superblock-level permissions * @sb: Superblock of inode to check permission on * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. */ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) { if (unlikely(mask & MAY_WRITE)) { umode_t mode = inode->i_mode; /* Nobody gets write access to a read-only fs. */ if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) return -EROFS; } return 0; } /** * inode_permission - Check for access rights to a given inode * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Check for read/write/execute permissions on an inode. We use fs[ug]id for * this, letting us set arbitrary permissions for filesystem access without * changing the "normal" UIDs which are used for other things. * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ int inode_permission(struct inode *inode, int mask) { int retval; retval = sb_permission(inode->i_sb, inode, mask); if (retval) return retval; if (unlikely(mask & MAY_WRITE)) { /* * Nobody gets write access to an immutable file. */ if (IS_IMMUTABLE(inode)) return -EPERM; /* * Updating mtime will likely cause i_uid and i_gid to be * written back improperly if their true value is unknown * to the vfs. */ if (HAS_UNMAPPED_ID(inode)) return -EACCES; } retval = do_inode_permission(inode, mask); if (retval) return retval; retval = devcgroup_inode_permission(inode, mask); if (retval) return retval; return security_inode_permission(inode, mask); } EXPORT_SYMBOL(inode_permission); /** * path_get - get a reference to a path * @path: path to get the reference to * * Given a path increment the reference count to the dentry and the vfsmount. */ void path_get(const struct path *path) { mntget(path->mnt); dget(path->dentry); } EXPORT_SYMBOL(path_get); /** * path_put - put a reference to a path * @path: path to put the reference to * * Given a path decrement the reference count to the dentry and the vfsmount. */ void path_put(const struct path *path) { dput(path->dentry); mntput(path->mnt); } EXPORT_SYMBOL(path_put); #define EMBEDDED_LEVELS 2 struct nameidata { struct path path; struct qstr last; struct path root; struct inode *inode; /* path.dentry.d_inode */ unsigned int flags; unsigned seq, m_seq, r_seq; int last_type; unsigned depth; int total_link_count; struct saved { struct path link; struct delayed_call done; const char *name; unsigned seq; } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; struct nameidata *saved; unsigned root_seq; int dfd; kuid_t dir_uid; umode_t dir_mode; } __randomize_layout; static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) { struct nameidata *old = current->nameidata; p->stack = p->internal; p->dfd = dfd; p->name = name; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; } static void restore_nameidata(void) { struct nameidata *now = current->nameidata, *old = now->saved; current->nameidata = old; if (old) old->total_link_count = now->total_link_count; if (now->stack != now->internal) kfree(now->stack); } static bool nd_alloc_stack(struct nameidata *nd) { struct saved *p; p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved), nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL); if (unlikely(!p)) return false; memcpy(p, nd->internal, sizeof(nd->internal)); nd->stack = p; return true; } /** * path_connected - Verify that a dentry is below mnt.mnt_root * * Rename can sometimes move a file or directory outside of a bind * mount, path_connected allows those cases to be detected. */ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry) { struct super_block *sb = mnt->mnt_sb; /* Bind mounts can have disconnected paths */ if (mnt->mnt_root == sb->s_root) return true; return is_subdir(dentry, mnt->mnt_root); } static void drop_links(struct nameidata *nd) { int i = nd->depth; while (i--) { struct saved *last = nd->stack + i; do_delayed_call(&last->done); clear_delayed_call(&last->done); } } static void terminate_walk(struct nameidata *nd) { drop_links(nd); if (!(nd->flags & LOOKUP_RCU)) { int i; path_put(&nd->path); for (i = 0; i < nd->depth; i++) path_put(&nd->stack[i].link); if (nd->flags & LOOKUP_ROOT_GRABBED) { path_put(&nd->root); nd->flags &= ~LOOKUP_ROOT_GRABBED; } } else { nd->flags &= ~LOOKUP_RCU; rcu_read_unlock(); } nd->depth = 0; } /* path_put is needed afterwards regardless of success or failure */ static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq) { int res = __legitimize_mnt(path->mnt, mseq); if (unlikely(res)) { if (res > 0) path->mnt = NULL; path->dentry = NULL; return false; } if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) { path->dentry = NULL; return false; } return !read_seqcount_retry(&path->dentry->d_seq, seq); } static inline bool legitimize_path(struct nameidata *nd, struct path *path, unsigned seq) { return __legitimize_path(path, seq, nd->m_seq); } static bool legitimize_links(struct nameidata *nd) { int i; for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { drop_links(nd); nd->depth = i + 1; return false; } } return true; } static bool legitimize_root(struct nameidata *nd) { /* * For scoped-lookups (where nd->root has been zeroed), we need to * restart the whole lookup from scratch -- because set_root() is wrong * for these lookups (nd->dfd is the root, not the filesystem root). */ if (!nd->root.mnt && (nd->flags & LOOKUP_IS_SCOPED)) return false; /* Nothing to do if nd->root is zero or is managed by the VFS user. */ if (!nd->root.mnt || (nd->flags & LOOKUP_ROOT)) return true; nd->flags |= LOOKUP_ROOT_GRABBED; return legitimize_path(nd, &nd->root, nd->root_seq); } /* * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab * normal reference counts on dentries and vfsmounts to transition to ref-walk * mode. Refcounts are grabbed at the last known good point before rcu-walk * got stuck, so ref-walk may continue from there. If this is not successful * (eg. a seqcount has changed), then failure is returned and it's up to caller * to restart the path walk from the beginning in ref-walk mode. */ /** * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * Returns: true on success, false on failure * * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) goto out; if (unlikely(!legitimize_root(nd))) goto out; rcu_read_unlock(); BUG_ON(nd->inode != parent->d_inode); return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: rcu_read_unlock(); return false; } /** * unlazy_child - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * @dentry: child of nd->path.dentry * @seq: seq number to check dentry against * Returns: 0 on success, -ECHILD on failure * * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry * for ref-walk mode. @dentry must be a path found by a do_lookup call on * @nd. Must be called from rcu-walk context. * Nothing should touch nameidata between unlazy_child() failure and * terminate_walk(). */ static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq) { BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out2; if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq))) goto out2; if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref))) goto out1; /* * We need to move both the parent and the dentry from the RCU domain * to be properly refcounted. And the sequence number in the dentry * validates *both* dentry counters, since we checked the sequence * number of the parent after we got the child sequence number. So we * know the parent must still be valid if the child sequence number is */ if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) goto out; if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) goto out_dput; /* * Sequence counts matched. Now make sure that the root is * still valid and get it if required. */ if (unlikely(!legitimize_root(nd))) goto out_dput; rcu_read_unlock(); return 0; out2: nd->path.mnt = NULL; out1: nd->path.dentry = NULL; out: rcu_read_unlock(); return -ECHILD; out_dput: rcu_read_unlock(); dput(dentry); return -ECHILD; } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) return dentry->d_op->d_revalidate(dentry, flags); else return 1; } /** * complete_walk - successful completion of path walk * @nd: pointer nameidata * * If we had been in RCU mode, drop out of it and legitimize nd->path. * Revalidate the final result, unless we'd already done that during * the path walk or the filesystem doesn't ask for it. Return 0 on * success, -error on failure. In case of failure caller does not * need to drop nd->path. */ static int complete_walk(struct nameidata *nd) { struct dentry *dentry = nd->path.dentry; int status; if (nd->flags & LOOKUP_RCU) { /* * We don't want to zero nd->root for scoped-lookups or * externally-managed nd->root. */ if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; if (!try_to_unlazy(nd)) return -ECHILD; } if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't * ever step outside the root during lookup" and should already * be guaranteed by the rest of namei, we want to avoid a namei * BUG resulting in userspace being given a path that was not * scoped within the root at some point during the lookup. * * So, do a final sanity-check to make sure that in the * worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED) * we won't silently return an fd completely outside of the * requested root to userspace. * * Userspace could move the path outside the root after this * check, but as discussed elsewhere this is not a concern (the * resolved file was inside the root at some point). */ if (!path_is_under(&nd->path, &nd->root)) return -EXDEV; } if (likely(!(nd->flags & LOOKUP_JUMPED))) return 0; if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE))) return 0; status = dentry->d_op->d_weak_revalidate(dentry, nd->flags); if (status > 0) return 0; if (!status) status = -ESTALE; return status; } static int set_root(struct nameidata *nd) { struct fs_struct *fs = current->fs; /* * Jumping to the real root in a scoped-lookup is a BUG in namei, but we * still have to ensure it doesn't happen because it will cause a breakout * from the dirfd. */ if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED)) return -ENOTRECOVERABLE; if (nd->flags & LOOKUP_RCU) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); nd->root = fs->root; nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_root(fs, &nd->root); nd->flags |= LOOKUP_ROOT_GRABBED; } return 0; } static int nd_jump_root(struct nameidata *nd) { if (unlikely(nd->flags & LOOKUP_BENEATH)) return -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { /* Absolute path arguments to path_init() are allowed. */ if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt) return -EXDEV; } if (!nd->root.mnt) { int error = set_root(nd); if (error) return error; } if (nd->flags & LOOKUP_RCU) { struct dentry *d; nd->path = nd->root; d = nd->path.dentry; nd->inode = d->d_inode; nd->seq = nd->root_seq; if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq))) return -ECHILD; } else { path_put(&nd->path); nd->path = nd->root; path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } nd->flags |= LOOKUP_JUMPED; return 0; } /* * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ int nd_jump_link(struct path *path) { int error = -ELOOP; struct nameidata *nd = current->nameidata; if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS)) goto err; error = -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { if (nd->path.mnt != path->mnt) goto err; } /* Not currently safe for scoped-lookups. */ if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) goto err; path_put(&nd->path); nd->path = *path; nd->inode = nd->path.dentry->d_inode; nd->flags |= LOOKUP_JUMPED; return 0; err: path_put(path); return error; } static inline void put_link(struct nameidata *nd) { struct saved *last = nd->stack + --nd->depth; do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link); } int sysctl_protected_symlinks __read_mostly = 0; int sysctl_protected_hardlinks __read_mostly = 0; int sysctl_protected_fifos __read_mostly; int sysctl_protected_regular __read_mostly; /** * may_follow_link - Check symlink following for unsafe situations * @nd: nameidata pathwalk data * * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is * in a sticky world-writable directory. This is to protect privileged * processes from failing races against path names that may change out * from under them by way of other users creating malicious symlinks. * It will permit symlinks to be followed only when outside a sticky * world-writable directory, or when the uid of the symlink and follower * match, or when the directory owner matches the symlink's owner. * * Returns 0 if following the symlink is allowed, -ve on error. */ static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { if (!sysctl_protected_symlinks) return 0; /* Allowed if owner and follower match. */ if (uid_eq(current_cred()->fsuid, inode->i_uid)) return 0; /* Allowed if parent directory not sticky and world-writable. */ if ((nd->dir_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) return 0; /* Allowed if parent directory and link owner match. */ if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, inode->i_uid)) return 0; if (nd->flags & LOOKUP_RCU) return -ECHILD; audit_inode(nd->name, nd->stack[0].link.dentry, 0); audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link"); return -EACCES; } /** * safe_hardlink_source - Check for safe hardlink conditions * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: * - inode is not a regular file * - inode is setuid * - inode is setgid and group-exec * - access failure for read and write * * Otherwise returns true. */ static bool safe_hardlink_source(struct inode *inode) { umode_t mode = inode->i_mode; /* Special files should not get pinned to the filesystem. */ if (!S_ISREG(mode)) return false; /* Setuid files should not get pinned to the filesystem. */ if (mode & S_ISUID) return false; /* Executable setgid files should not get pinned to the filesystem. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ if (inode_permission(inode, MAY_READ | MAY_WRITE)) return false; return true; } /** * may_linkat - Check permissions for creating a hardlink * @link: the source to hardlink from * * Block hardlink when all of: * - sysctl_protected_hardlinks enabled * - fsuid does not match inode * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * * Returns 0 if successful, -ve on error. */ int may_linkat(struct path *link) { struct inode *inode = link->dentry->d_inode; /* Inode writeback is not safe when the uid or gid are invalid. */ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) return -EOVERFLOW; if (!sysctl_protected_hardlinks) return 0; /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ if (safe_hardlink_source(inode) || inode_owner_or_capable(inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); return -EPERM; } /** * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. * @dir_mode: mode bits of directory * @dir_uid: owner of directory * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: * - sysctl_protected_fifos (or sysctl_protected_regular) is enabled * - the file already exists * - we are in a sticky directory * - we don't own the file * - the owner of the directory doesn't own the file * - the directory is world writable * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2 * the directory doesn't have to be world writable: being group writable will * be enough. * * Returns 0 if the open is allowed, -ve on error. */ static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid, struct inode * const inode) { if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || likely(!(dir_mode & S_ISVTX)) || uid_eq(inode->i_uid, dir_uid) || uid_eq(current_fsuid(), inode->i_uid)) return 0; if (likely(dir_mode & 0002) || (dir_mode & 0020 && ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) || (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) { const char *operation = S_ISFIFO(inode->i_mode) ? "sticky_create_fifo" : "sticky_create_regular"; audit_log_path_denied(AUDIT_ANOM_CREAT, operation); return -EACCES; } return 0; } /* * follow_up - Find the mountpoint of path's vfsmount * * Given a path, find the mountpoint of its source file system. * Replace @path with the path of the mountpoint in the parent mount. * Up is towards /. * * Return 1 if we went up a level and 0 if we were already at the * root. */ int follow_up(struct path *path) { struct mount *mnt = real_mount(path->mnt); struct mount *parent; struct dentry *mountpoint; read_seqlock_excl(&mount_lock); parent = mnt->mnt_parent; if (parent == mnt) { read_sequnlock_excl(&mount_lock); return 0; } mntget(&parent->mnt); mountpoint = dget(mnt->mnt_mountpoint); read_sequnlock_excl(&mount_lock); dput(path->dentry); path->dentry = mountpoint; mntput(path->mnt); path->mnt = &parent->mnt; return 1; } EXPORT_SYMBOL(follow_up); static bool choose_mountpoint_rcu(struct mount *m, const struct path *root, struct path *path, unsigned *seqp) { while (mnt_has_parent(m)) { struct dentry *mountpoint = m->mnt_mountpoint; m = m->mnt_parent; if (unlikely(root->dentry == mountpoint && root->mnt == &m->mnt)) break; if (mountpoint != m->mnt.mnt_root) { path->mnt = &m->mnt; path->dentry = mountpoint; *seqp = read_seqcount_begin(&mountpoint->d_seq); return true; } } return false; } static bool choose_mountpoint(struct mount *m, const struct path *root, struct path *path) { bool found; rcu_read_lock(); while (1) { unsigned seq, mseq = read_seqbegin(&mount_lock); found = choose_mountpoint_rcu(m, root, path, &seq); if (unlikely(!found)) { if (!read_seqretry(&mount_lock, mseq)) break; } else { if (likely(__legitimize_path(path, seq, mseq))) break; rcu_read_unlock(); path_put(path); rcu_read_lock(); } } rcu_read_unlock(); return found; } /* * Perform an automount * - return -EISDIR to tell follow_managed() to stop and return the path we * were called with. */ static int follow_automount(struct path *path, int *count, unsigned lookup_flags) { struct dentry *dentry = path->dentry; /* We don't want to mount if someone's just doing a stat - * unless they're stat'ing a directory and appended a '/' to * the name. * * We do, however, want to mount if someone wants to open or * create a file of any type under the mountpoint, wants to * traverse through the mountpoint or wants to open the * mounted directory. Also, autofs may mark negative dentries * as being automount points. These will need the attentions * of the daemon to instantiate them before they can be used. */ if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && dentry->d_inode) return -EISDIR; if (count && (*count)++ >= MAXSYMLINKS) return -ELOOP; return finish_automount(dentry->d_op->d_automount(path), path); } /* * mount traversal - out-of-line part. One note on ->d_flags accesses - * dentries are pinned but not locked here, so negative dentry can go * positive right under us. Use of smp_load_acquire() provides a barrier * sufficient for ->d_inode and ->d_flags consistency. */ static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped, int *count, unsigned lookup_flags) { struct vfsmount *mnt = path->mnt; bool need_mntput = false; int ret = 0; while (flags & DCACHE_MANAGED_DENTRY) { /* Allow the filesystem to manage the transit without i_mutex * being held. */ if (flags & DCACHE_MANAGE_TRANSIT) { ret = path->dentry->d_op->d_manage(path, false); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (flags & DCACHE_MOUNTED) { // something's mounted on it.. struct vfsmount *mounted = lookup_mnt(path); if (mounted) { // ... in our namespace dput(path->dentry); if (need_mntput) mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); // here we know it's positive flags = path->dentry->d_flags; need_mntput = true; continue; } } if (!(flags & DCACHE_NEED_AUTOMOUNT)) break; // uncovered automount point ret = follow_automount(path, count, lookup_flags); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (ret == -EISDIR) ret = 0; // possible if you race with several mount --move if (need_mntput && path->mnt == mnt) mntput(path->mnt); if (!ret && unlikely(d_flags_negative(flags))) ret = -ENOENT; *jumped = need_mntput; return ret; } static inline int traverse_mounts(struct path *path, bool *jumped, int *count, unsigned lookup_flags) { unsigned flags = smp_load_acquire(&path->dentry->d_flags); /* fastpath */ if (likely(!(flags & DCACHE_MANAGED_DENTRY))) { *jumped = false; if (unlikely(d_flags_negative(flags))) return -ENOENT; return 0; } return __traverse_mounts(path, flags, jumped, count, lookup_flags); } int follow_down_one(struct path *path) { struct vfsmount *mounted; mounted = lookup_mnt(path); if (mounted) { dput(path->dentry); mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); return 1; } return 0; } EXPORT_SYMBOL(follow_down_one); /* * Follow down to the covering mount currently visible to userspace. At each * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. */ int follow_down(struct path *path) { struct vfsmount *mnt = path->mnt; bool jumped; int ret = traverse_mounts(path, &jumped, NULL, 0); if (path->mnt != mnt) mntput(mnt); return ret; } EXPORT_SYMBOL(follow_down); /* * Try to skip to top of mountpoint pile in rcuwalk mode. Fail if * we meet a managed dentry that would need blocking. */ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, struct inode **inode, unsigned *seqp) { struct dentry *dentry = path->dentry; unsigned int flags = dentry->d_flags; if (likely(!(flags & DCACHE_MANAGED_DENTRY))) return true; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return false; for (;;) { /* * Don't forget we might have a non-mountpoint managed dentry * that wants to block transit. */ if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) { int res = dentry->d_op->d_manage(path, true); if (res) return res == -EISDIR; flags = dentry->d_flags; } if (flags & DCACHE_MOUNTED) { struct mount *mounted = __lookup_mnt(path->mnt, dentry); if (mounted) { path->mnt = &mounted->mnt; dentry = path->dentry = mounted->mnt.mnt_root; nd->flags |= LOOKUP_JUMPED; *seqp = read_seqcount_begin(&dentry->d_seq); *inode = dentry->d_inode; /* * We don't need to re-check ->d_seq after this * ->d_inode read - there will be an RCU delay * between mount hash removal and ->mnt_root * becoming unpinned. */ flags = dentry->d_flags; continue; } if (read_seqretry(&mount_lock, nd->m_seq)) return false; } return !(flags & DCACHE_NEED_AUTOMOUNT); } } static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, struct path *path, struct inode **inode, unsigned int *seqp) { bool jumped; int ret; path->mnt = nd->path.mnt; path->dentry = dentry; if (nd->flags & LOOKUP_RCU) { unsigned int seq = *seqp; if (unlikely(!*inode)) return -ENOENT; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) return 0; if (unlazy_child(nd, dentry, seq)) return -ECHILD; // *path might've been clobbered by __follow_mount_rcu() path->mnt = nd->path.mnt; path->dentry = dentry; } ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags); if (jumped) { if (unlikely(nd->flags & LOOKUP_NO_XDEV)) ret = -EXDEV; else nd->flags |= LOOKUP_JUMPED; } if (unlikely(ret)) { dput(path->dentry); if (path->mnt != nd->path.mnt) mntput(path->mnt); } else { *inode = d_backing_inode(path->dentry); *seqp = 0; /* out of RCU mode, so the value doesn't matter */ } return ret; } /* * This looks up the name in dcache and possibly revalidates the found dentry. * NULL is returned if the dentry does not exist in the cache. */ static struct dentry *lookup_dcache(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry = d_lookup(dir, name); if (dentry) { int error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (!error) d_invalidate(dentry); dput(dentry); return ERR_PTR(error); } } return dentry; } /* * Parent directory has inode locked exclusive. This is one * and only case when ->lookup() gets called on non in-lookup * dentries - as the matter of fact, this only gets called * when directory is guaranteed to have no in-lookup children * at all. */ static struct dentry *__lookup_hash(const struct qstr *name, struct dentry *base, unsigned int flags) { struct dentry *dentry = lookup_dcache(name, base, flags); struct dentry *old; struct inode *dir = base->d_inode; if (dentry) return dentry; /* Don't create child dentry for a dead directory. */ if (unlikely(IS_DEADDIR(dir))) return ERR_PTR(-ENOENT); dentry = d_alloc(base, name); if (unlikely(!dentry)) return ERR_PTR(-ENOMEM); old = dir->i_op->lookup(dir, dentry, flags); if (unlikely(old)) { dput(dentry); dentry = old; } return dentry; } static struct dentry *lookup_fast(struct nameidata *nd, struct inode **inode, unsigned *seqp) { struct dentry *dentry, *parent = nd->path.dentry; int status = 1; /* * Rename seqlock is not required here because in the off chance * of a false negative due to a concurrent rename, the caller is * going to fall back to non-racy lookup. */ if (nd->flags & LOOKUP_RCU) { unsigned seq; dentry = __d_lookup_rcu(parent, &nd->last, &seq); if (unlikely(!dentry)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); return NULL; } /* * This sequence count validates that the inode matches * the dentry name information from lookup. */ *inode = d_backing_inode(dentry); if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) return ERR_PTR(-ECHILD); /* * This sequence count validates that the parent had no * changes while we did the lookup of the dentry above. * * The memory barrier in read_seqcount_begin of child is * enough, we can use __read_seqcount_retry here. */ if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq))) return ERR_PTR(-ECHILD); *seqp = seq; status = d_revalidate(dentry, nd->flags); if (likely(status > 0)) return dentry; if (unlazy_child(nd, dentry, seq)) return ERR_PTR(-ECHILD); if (unlikely(status == -ECHILD)) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) return NULL; status = d_revalidate(dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) d_invalidate(dentry); dput(dentry); return ERR_PTR(status); } return dentry; } /* Fast lookup failed, do it the slow way */ static struct dentry *__lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry, *old; struct inode *inode = dir->d_inode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); /* Don't go there if it's already dead */ if (unlikely(IS_DEADDIR(inode))) return ERR_PTR(-ENOENT); again: dentry = d_alloc_parallel(dir, name, &wq); if (IS_ERR(dentry)) return dentry; if (unlikely(!d_in_lookup(dentry))) { int error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (!error) { d_invalidate(dentry); dput(dentry); goto again; } dput(dentry); dentry = ERR_PTR(error); } } else { old = inode->i_op->lookup(inode, dentry, flags); d_lookup_done(dentry); if (unlikely(old)) { dput(dentry); dentry = old; } } return dentry; } static struct dentry *lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct inode *inode = dir->d_inode; struct dentry *res; inode_lock_shared(inode); res = __lookup_slow(name, dir, flags); inode_unlock_shared(inode); return res; } static inline int may_lookup(struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); if (err != -ECHILD || !try_to_unlazy(nd)) return err; } return inode_permission(nd->inode, MAY_EXEC); } static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq) { if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) return -ELOOP; if (likely(nd->depth != EMBEDDED_LEVELS)) return 0; if (likely(nd->stack != nd->internal)) return 0; if (likely(nd_alloc_stack(nd))) return 0; if (nd->flags & LOOKUP_RCU) { // we need to grab link before we do unlazy. And we can't skip // unlazy even if we fail to grab the link - cleanup needs it bool grabbed_link = legitimize_path(nd, link, seq); if (!try_to_unlazy(nd) != 0 || !grabbed_link) return -ECHILD; if (nd_alloc_stack(nd)) return 0; } return -ENOMEM; } enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4}; static const char *pick_link(struct nameidata *nd, struct path *link, struct inode *inode, unsigned seq, int flags) { struct saved *last; const char *res; int error = reserve_stack(nd, link, seq); if (unlikely(error)) { if (!(nd->flags & LOOKUP_RCU)) path_put(link); return ERR_PTR(error); } last = nd->stack + nd->depth++; last->link = *link; clear_delayed_call(&last->done); last->seq = seq; if (flags & WALK_TRAILING) { error = may_follow_link(nd, inode); if (unlikely(error)) return ERR_PTR(error); } if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) || unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW)) return ERR_PTR(-ELOOP); if (!(nd->flags & LOOKUP_RCU)) { touch_atime(&last->link); cond_resched(); } else if (atime_needs_update(&last->link, inode)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); touch_atime(&last->link); } error = security_inode_follow_link(link->dentry, inode, nd->flags & LOOKUP_RCU); if (unlikely(error)) return ERR_PTR(error); res = READ_ONCE(inode->i_link); if (!res) { const char * (*get)(struct dentry *, struct inode *, struct delayed_call *); get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) res = get(link->dentry, inode, &last->done); } else { res = get(link->dentry, inode, &last->done); } if (!res) goto all_done; if (IS_ERR(res)) return res; } if (*res == '/') { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); while (unlikely(*++res == '/')) ; } if (*res) return res; all_done: // pure jump put_link(nd); return NULL; } /* * Do we need to follow links? We _really_ want to be able * to do this check without having to look at inode->i_op, * so we keep a cache of "no, this doesn't need follow_link" * for the common case. */ static const char *step_into(struct nameidata *nd, int flags, struct dentry *dentry, struct inode *inode, unsigned seq) { struct path path; int err = handle_mounts(nd, dentry, &path, &inode, &seq); if (err < 0) return ERR_PTR(err); if (likely(!d_is_symlink(path.dentry)) || ((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) || (flags & WALK_NOFOLLOW)) { /* not a symlink or should not follow */ if (!(nd->flags & LOOKUP_RCU)) { dput(nd->path.dentry); if (nd->path.mnt != path.mnt) mntput(nd->path.mnt); } nd->path = path; nd->inode = inode; nd->seq = seq; return NULL; } if (nd->flags & LOOKUP_RCU) { /* make sure that d_is_symlink above matches inode */ if (read_seqcount_retry(&path.dentry->d_seq, seq)) return ERR_PTR(-ECHILD); } else { if (path.mnt == nd->path.mnt) mntget(path.mnt); } return pick_link(nd, &path, inode, seq, flags); } static struct dentry *follow_dotdot_rcu(struct nameidata *nd, struct inode **inodep, unsigned *seqp) { struct dentry *parent, *old; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; unsigned seq; if (!choose_mountpoint_rcu(real_mount(nd->path.mnt), &nd->root, &path, &seq)) goto in_root; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-ECHILD); nd->path = path; nd->inode = path.dentry->d_inode; nd->seq = seq; if (unlikely(read_seqretry(&mount_lock, nd->m_seq))) return ERR_PTR(-ECHILD); /* we know that mountpoint was pinned */ } old = nd->path.dentry; parent = old->d_parent; *inodep = parent->d_inode; *seqp = read_seqcount_begin(&parent->d_seq); if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq))) return ERR_PTR(-ECHILD); if (unlikely(!path_connected(nd->path.mnt, parent))) return ERR_PTR(-ECHILD); return parent; in_root: if (unlikely(read_seqretry(&mount_lock, nd->m_seq))) return ERR_PTR(-ECHILD); if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-ECHILD); return NULL; } static struct dentry *follow_dotdot(struct nameidata *nd, struct inode **inodep, unsigned *seqp) { struct dentry *parent; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; if (!choose_mountpoint(real_mount(nd->path.mnt), &nd->root, &path)) goto in_root; path_put(&nd->path); nd->path = path; nd->inode = path.dentry->d_inode; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-EXDEV); } /* rare case of legitimate dget_parent()... */ parent = dget_parent(nd->path.dentry); if (unlikely(!path_connected(nd->path.mnt, parent))) { dput(parent); return ERR_PTR(-ENOENT); } *seqp = 0; *inodep = parent->d_inode; return parent; in_root: if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-EXDEV); dget(nd->path.dentry); return NULL; } static const char *handle_dots(struct nameidata *nd, int type) { if (type == LAST_DOTDOT) { const char *error = NULL; struct dentry *parent; struct inode *inode; unsigned seq; if (!nd->root.mnt) { error = ERR_PTR(set_root(nd)); if (error) return error; } if (nd->flags & LOOKUP_RCU) parent = follow_dotdot_rcu(nd, &inode, &seq); else parent = follow_dotdot(nd, &inode, &seq); if (IS_ERR(parent)) return ERR_CAST(parent); if (unlikely(!parent)) error = step_into(nd, WALK_NOFOLLOW, nd->path.dentry, nd->inode, nd->seq); else error = step_into(nd, WALK_NOFOLLOW, parent, inode, seq); if (unlikely(error)) return error; if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * If there was a racing rename or mount along our * path, then we can't be sure that ".." hasn't jumped * above nd->root (and so userspace should retry or use * some fallback). */ smp_rmb(); if (unlikely(__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq))) return ERR_PTR(-EAGAIN); if (unlikely(__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq))) return ERR_PTR(-EAGAIN); } } return NULL; } static const char *walk_component(struct nameidata *nd, int flags) { struct dentry *dentry; struct inode *inode; unsigned seq; /* * "." and ".." are special - ".." especially so because it has * to be able to know about the current root directory and * parent relationships. */ if (unlikely(nd->last_type != LAST_NORM)) { if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } dentry = lookup_fast(nd, &inode, &seq); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (unlikely(!dentry)) { dentry = lookup_slow(&nd->last, nd->path.dentry, nd->flags); if (IS_ERR(dentry)) return ERR_CAST(dentry); } if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return step_into(nd, flags, dentry, inode, seq); } /* * We can do the critical dentry name comparison and hashing * operations one word at a time, but we are limited to: * * - Architectures with fast unaligned word accesses. We could * do a "get_unaligned()" if this helps and is sufficiently * fast. * * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we * do not trap on the (extremely unlikely) case of a page * crossing operation. * * - Furthermore, we need an efficient 64-bit compile for the * 64-bit case in order to generate the "number of bytes in * the final mask". Again, that could be replaced with a * efficient population count instruction or similar. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> #ifdef HASH_MIX /* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */ #elif defined(CONFIG_64BIT) /* * Register pressure in the mixing function is an issue, particularly * on 32-bit x86, but almost any function requires one state value and * one temporary. Instead, use a function designed for two state values * and no temporaries. * * This function cannot create a collision in only two iterations, so * we have two iterations to achieve avalanche. In those two iterations, * we have six layers of mixing, which is enough to spread one bit's * influence out to 2^6 = 64 state bits. * * Rotate constants are scored by considering either 64 one-bit input * deltas or 64*63/2 = 2016 two-bit input deltas, and finding the * probability of that delta causing a change to each of the 128 output * bits, using a sample of random initial states. * * The Shannon entropy of the computed probabilities is then summed * to produce a score. Ideally, any input change has a 50% chance of * toggling any given output bit. * * Mixing scores (in bits) for (12,45): * Input delta: 1-bit 2-bit * 1 round: 713.3 42542.6 * 2 rounds: 2753.7 140389.8 * 3 rounds: 5954.1 233458.2 * 4 rounds: 7862.6 256672.2 * Perfect: 8192 258048 * (64*128) (64*63/2 * 128) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol64(x,12),\ x += y, y = rol64(y,45),\ y *= 9 ) /* * Fold two longs into one 32-bit hash value. This must be fast, but * latency isn't quite as critical, as there is a fair bit of additional * work done before the hash value is used. */ static inline unsigned int fold_hash(unsigned long x, unsigned long y) { y ^= x * GOLDEN_RATIO_64; y *= GOLDEN_RATIO_64; return y >> 32; } #else /* 32-bit case */ /* * Mixing scores (in bits) for (7,20): * Input delta: 1-bit 2-bit * 1 round: 330.3 9201.6 * 2 rounds: 1246.4 25475.4 * 3 rounds: 1907.1 31295.1 * 4 rounds: 2042.3 31718.6 * Perfect: 2048 31744 * (32*64) (32*31/2 * 64) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol32(x, 7),\ x += y, y = rol32(y,20),\ y *= 9 ) static inline unsigned int fold_hash(unsigned long x, unsigned long y) { /* Use arch-optimized multiply if one exists */ return __hash_32(y ^ __hash_32(x)); } #endif /* * Return the hash of a string of known length. This is carfully * designed to match hash_name(), which is the more critical function. * In particular, we must end by hashing a final word containing 0..7 * payload bytes, to match the way that hash_name() iterates until it * finds the delimiter after the name. */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long a, x = 0, y = (unsigned long)salt; for (;;) { if (!len) goto done; a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; HASH_MIX(x, y, a); name += sizeof(unsigned long); len -= sizeof(unsigned long); } x ^= a & bytemask_from_count(len); done: return fold_hash(x, y); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long a = 0, x = 0, y = (unsigned long)salt; unsigned long adata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); } while (!has_zero(a, &adata, &constants)); adata = prep_zero_mask(a, adata, &constants); mask = create_zero_mask(adata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } EXPORT_SYMBOL(hashlen_string); /* * Calculate the length and hash of the path component, and * return the "hash_len" as the result. */ static inline u64 hash_name(const void *salt, const char *name) { unsigned long a = 0, b, x = 0, y = (unsigned long)salt; unsigned long adata, bdata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); b = a ^ REPEAT_BYTE('/'); } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants))); adata = prep_zero_mask(a, adata, &constants); bdata = prep_zero_mask(b, bdata, &constants); mask = create_zero_mask(adata | bdata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } #else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */ /* Return the hash of a string of known length */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long hash = init_name_hash(salt); while (len--) hash = partial_name_hash((unsigned char)*name++, hash); return end_name_hash(hash); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; while (c) { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } return hashlen_create(end_name_hash(hash), len); } EXPORT_SYMBOL(hashlen_string); /* * We know there's a real path component here of at least * one character. */ static inline u64 hash_name(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; do { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } while (c && c != '/'); return hashlen_create(end_name_hash(hash), len); } #endif /* * Name resolution. * This is the basic name resolution function, turning a pathname into * the final dentry. We expect 'base' to be positive and a directory. * * Returns 0 and nd will have valid dentry and mnt on success. * Returns error and drops reference to input namei data on failure. */ static int link_path_walk(const char *name, struct nameidata *nd) { int depth = 0; // depth <= nd->depth int err; nd->last_type = LAST_ROOT; nd->flags |= LOOKUP_PARENT; if (IS_ERR(name)) return PTR_ERR(name); while (*name=='/') name++; if (!*name) return 0; /* At this point we know we have a real path component. */ for(;;) { const char *link; u64 hash_len; int type; err = may_lookup(nd); if (err) return err; hash_len = hash_name(nd->path.dentry, name); type = LAST_NORM; if (name[0] == '.') switch (hashlen_len(hash_len)) { case 2: if (name[1] == '.') { type = LAST_DOTDOT; nd->flags |= LOOKUP_JUMPED; } break; case 1: type = LAST_DOT; } if (likely(type == LAST_NORM)) { struct dentry *parent = nd->path.dentry; nd->flags &= ~LOOKUP_JUMPED; if (unlikely(parent->d_flags & DCACHE_OP_HASH)) { struct qstr this = { { .hash_len = hash_len }, .name = name }; err = parent->d_op->d_hash(parent, &this); if (err < 0) return err; hash_len = this.hash_len; name = this.name; } } nd->last.hash_len = hash_len; nd->last.name = name; nd->last_type = type; name += hashlen_len(hash_len); if (!*name) goto OK; /* * If it wasn't NUL, we know it was '/'. Skip that * slash, and continue until no more slashes. */ do { name++; } while (unlikely(*name == '/')); if (unlikely(!*name)) { OK: /* pathname or trailing symlink, done */ if (!depth) { nd->dir_uid = nd->inode->i_uid; nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; return 0; } /* last component of nested symlink */ name = nd->stack[--depth].name; link = walk_component(nd, 0); } else { /* not the last component */ link = walk_component(nd, WALK_MORE); } if (unlikely(link)) { if (IS_ERR(link)) return PTR_ERR(link); /* a symlink to follow */ nd->stack[depth++].name = name; name = link; continue; } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; } } } /* must be paired with terminate_walk() */ static const char *path_init(struct nameidata *nd, unsigned flags) { int error; const char *s = nd->name->name; if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) rcu_read_lock(); nd->flags = flags | LOOKUP_JUMPED; nd->depth = 0; nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount); nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount); smp_rmb(); if (flags & LOOKUP_ROOT) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*s && unlikely(!d_can_lookup(root))) return ERR_PTR(-ENOTDIR); nd->path = nd->root; nd->inode = inode; if (flags & LOOKUP_RCU) { nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); nd->root_seq = nd->seq; } else { path_get(&nd->path); } return s; } nd->root.mnt = NULL; nd->path.mnt = NULL; nd->path.dentry = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); return s; } /* Relative pathname -- get the starting-point it is relative to. */ if (nd->dfd == AT_FDCWD) { if (flags & LOOKUP_RCU) { struct fs_struct *fs = current->fs; unsigned seq; do { seq = read_seqcount_begin(&fs->seq); nd->path = fs->pwd; nd->inode = nd->path.dentry->d_inode; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_pwd(current->fs, &nd->path); nd->inode = nd->path.dentry->d_inode; } } else { /* Caller must check execute permissions on the starting path component */ struct fd f = fdget_raw(nd->dfd); struct dentry *dentry; if (!f.file) return ERR_PTR(-EBADF); dentry = f.file->f_path.dentry; if (*s && unlikely(!d_can_lookup(dentry))) { fdput(f); return ERR_PTR(-ENOTDIR); } nd->path = f.file->f_path; if (flags & LOOKUP_RCU) { nd->inode = nd->path.dentry->d_inode; nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); } else { path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } fdput(f); } /* For scoped-lookups we need to set the root to the dirfd as well. */ if (flags & LOOKUP_IS_SCOPED) { nd->root = nd->path; if (flags & LOOKUP_RCU) { nd->root_seq = nd->seq; } else { path_get(&nd->root); nd->flags |= LOOKUP_ROOT_GRABBED; } } return s; } static inline const char *lookup_last(struct nameidata *nd) { if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; return walk_component(nd, WALK_TRAILING); } static int handle_lookup_down(struct nameidata *nd) { if (!(nd->flags & LOOKUP_RCU)) dget(nd->path.dentry); return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry, nd->inode, nd->seq)); } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path) { const char *s = path_init(nd, flags); int err; if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) { err = handle_lookup_down(nd); if (unlikely(err < 0)) s = ERR_PTR(err); } while (!(err = link_path_walk(s, nd)) && (s = lookup_last(nd)) != NULL) ; if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) { err = handle_lookup_down(nd); nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please... } if (!err) err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) if (!d_can_lookup(nd->path.dentry)) err = -ENOTDIR; if (!err) { *path = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); if (unlikely(root)) { nd.root = *root; flags |= LOOKUP_ROOT; } set_nameidata(&nd, dfd, name); retval = path_lookupat(&nd, flags | LOOKUP_RCU, path); if (unlikely(retval == -ECHILD)) retval = path_lookupat(&nd, flags, path); if (unlikely(retval == -ESTALE)) retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path); if (likely(!retval)) audit_inode(name, path->dentry, flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0); restore_nameidata(); putname(name); return retval; } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int path_parentat(struct nameidata *nd, unsigned flags, struct path *parent) { const char *s = path_init(nd, flags); int err = link_path_walk(s, nd); if (!err) err = complete_walk(nd); if (!err) { *parent = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } static struct filename *filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, int *type) { int retval; struct nameidata nd; if (IS_ERR(name)) return name; set_nameidata(&nd, dfd, name); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); if (unlikely(retval == -ESTALE)) retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent); if (likely(!retval)) { *last = nd.last; *type = nd.last_type; audit_inode(name, parent->dentry, AUDIT_INODE_PARENT); } else { putname(name); name = ERR_PTR(retval); } restore_nameidata(); return name; } /* does lookup, returns the object with parent locked */ struct dentry *kern_path_locked(const char *name, struct path *path) { struct filename *filename; struct dentry *d; struct qstr last; int type; filename = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path, &last, &type); if (IS_ERR(filename)) return ERR_CAST(filename); if (unlikely(type != LAST_NORM)) { path_put(path); putname(filename); return ERR_PTR(-EINVAL); } inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); d = __lookup_hash(&last, path->dentry, 0); if (IS_ERR(d)) { inode_unlock(path->dentry->d_inode); path_put(path); } putname(filename); return d; } int kern_path(const char *name, unsigned int flags, struct path *path) { return filename_lookup(AT_FDCWD, getname_kernel(name), flags, path, NULL); } EXPORT_SYMBOL(kern_path); /** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory * @mnt: pointer to vfs mount of the base directory * @name: pointer to file name * @flags: lookup flags * @path: pointer to struct path to fill */ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { struct path root = {.mnt = mnt, .dentry = dentry}; /* the first argument of filename_lookup() is ignored with root */ return filename_lookup(AT_FDCWD, getname_kernel(name), flags , path, &root); } EXPORT_SYMBOL(vfs_path_lookup); static int lookup_one_len_common(const char *name, struct dentry *base, int len, struct qstr *this) { this->name = name; this->len = len; this->hash = full_name_hash(base, name, len); if (!len) return -EACCES; if (unlikely(name[0] == '.')) { if (len < 2 || (len == 2 && name[1] == '.')) return -EACCES; } while (len--) { unsigned int c = *(const unsigned char *)name++; if (c == '/' || c == '\0') return -EACCES; } /* * See if the low-level filesystem might want * to use its own hash.. */ if (base->d_flags & DCACHE_OP_HASH) { int err = base->d_op->d_hash(base, this); if (err < 0) return err; } return inode_permission(base->d_inode, MAY_EXEC); } /** * try_lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Look up a dentry by name in the dcache, returning NULL if it does not * currently exist. The function does not try to create a dentry. * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len) { struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); return lookup_dcache(&this, base, 0); } EXPORT_SYMBOL(try_lookup_one_len); /** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { struct dentry *dentry; struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); dentry = lookup_dcache(&this, base, 0); return dentry ? dentry : __lookup_slow(&this, base, 0); } EXPORT_SYMBOL(lookup_one_len); /** * lookup_one_len_unlocked - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * Unlike lookup_one_len, it should be called without the parent * i_mutex held, and will take the i_mutex itself if necessary. */ struct dentry *lookup_one_len_unlocked(const char *name, struct dentry *base, int len) { struct qstr this; int err; struct dentry *ret; err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); ret = lookup_dcache(&this, base, 0); if (!ret) ret = lookup_slow(&this, base, 0); return ret; } EXPORT_SYMBOL(lookup_one_len_unlocked); /* * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) * on negatives. Returns known positive or ERR_PTR(); that's what * most of the users want. Note that pinned negative with unlocked parent * _can_ become positive at any time, so callers of lookup_one_len_unlocked() * need to be very careful; pinned positives have ->d_inode stable, so * this one avoids such problems. */ struct dentry *lookup_positive_unlocked(const char *name, struct dentry *base, int len) { struct dentry *ret = lookup_one_len_unlocked(name, base, len); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_positive_unlocked); #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { /* Find something mounted on "pts" in the same directory as * the input path. */ struct dentry *parent = dget_parent(path->dentry); struct dentry *child; struct qstr this = QSTR_INIT("pts", 3); if (unlikely(!path_connected(path->mnt, parent))) { dput(parent); return -ENOENT; } dput(path->dentry); path->dentry = parent; child = d_hash_and_lookup(parent, &this); if (!child) return -ENOENT; path->dentry = child; dput(parent); follow_down(path); return 0; } #endif int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { return filename_lookup(dfd, getname_flags(name, flags, empty), flags, path, NULL); } EXPORT_SYMBOL(user_path_at_empty); int __check_sticky(struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); if (uid_eq(inode->i_uid, fsuid)) return 0; if (uid_eq(dir->i_uid, fsuid)) return 0; return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); /* * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. * 1. We can't do it if dir is read-only (done in permission()) * 2. We should have write and exec permissions on dir * 3. We can't remove anything from append-only dir * 4. We can't do anything with immutable dir (done in permission()) * 5. If the sticky bit on dir is set we should either * a. be owner of dir, or * b. be owner of victim, or * c. have CAP_FOWNER capability * 6. If the victim is append-only or immutable we can't do antyhing with * links pointing to it. * 7. If the victim has an unknown uid or gid we can't change the inode. * 8. If we were asked to remove a directory and victim isn't one - ENOTDIR. * 9. If we were asked to remove a non-directory and victim isn't one - EISDIR. * 10. We can't remove a root or mountpoint. * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; if (d_is_negative(victim)) return -ENOENT; BUG_ON(!inode); BUG_ON(victim->d_parent->d_inode != dir); /* Inode writeback is not safe when the uid or gid are invalid. */ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) return -EOVERFLOW; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; if (check_sticky(dir, inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(inode)) return -EPERM; if (isdir) { if (!d_is_dir(victim)) return -ENOTDIR; if (IS_ROOT(victim)) return -EBUSY; } else if (d_is_dir(victim)) return -EISDIR; if (IS_DEADDIR(dir)) return -ENOENT; if (victim->d_flags & DCACHE_NFSFS_RENAMED) return -EBUSY; return 0; } /* Check whether we can create an object with dentry child in directory * dir. * 1. We can't do it if child already exists (open has special treatment for * this case, but since we are inlined it's OK) * 2. We can't do it if dir is read-only (done in permission()) * 3. We can't do it if the fs can't represent the fsuid or fsgid. * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ static inline int may_create(struct inode *dir, struct dentry *child) { struct user_namespace *s_user_ns; audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); if (child->d_inode) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; s_user_ns = dir->i_sb->s_user_ns; if (!kuid_has_mapping(s_user_ns, current_fsuid()) || !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; return inode_permission(dir, MAY_WRITE | MAY_EXEC); } /* * p1 and p2 should be directories on the same fs. */ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { struct dentry *p; if (p1 == p2) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); return NULL; } mutex_lock(&p1->d_sb->s_vfs_rename_mutex); p = d_ancestor(p2, p1); if (p) { inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); inode_lock_nested(p1->d_inode, I_MUTEX_CHILD); return p; } p = d_ancestor(p1, p2); if (p) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_CHILD); return p; } inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return NULL; } EXPORT_SYMBOL(lock_rename); void unlock_rename(struct dentry *p1, struct dentry *p2) { inode_unlock(p1->d_inode); if (p1 != p2) { inode_unlock(p2->d_inode); mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); } } EXPORT_SYMBOL(unlock_rename); int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool want_excl) { int error = may_create(dir, dentry); if (error) return error; if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ mode &= S_IALLUGO; mode |= S_IFREG; error = security_inode_create(dir, dentry, mode); if (error) return error; error = dir->i_op->create(dir, dentry, mode, want_excl); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_create); int vfs_mkobj(struct dentry *dentry, umode_t mode, int (*f)(struct dentry *, umode_t, void *), void *arg) { struct inode *dir = dentry->d_parent->d_inode; int error = may_create(dir, dentry); if (error) return error; mode &= S_IALLUGO; mode |= S_IFREG; error = security_inode_create(dir, dentry, mode); if (error) return error; error = f(dentry, mode, arg); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkobj); bool may_open_dev(const struct path *path) { return !(path->mnt->mnt_flags & MNT_NODEV) && !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } static int may_open(const struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; struct inode *inode = dentry->d_inode; int error; if (!inode) return -ENOENT; switch (inode->i_mode & S_IFMT) { case S_IFLNK: return -ELOOP; case S_IFDIR: if (acc_mode & MAY_WRITE) return -EISDIR; if (acc_mode & MAY_EXEC) return -EACCES; break; case S_IFBLK: case S_IFCHR: if (!may_open_dev(path)) return -EACCES; fallthrough; case S_IFIFO: case S_IFSOCK: if (acc_mode & MAY_EXEC) return -EACCES; flag &= ~O_TRUNC; break; case S_IFREG: if ((acc_mode & MAY_EXEC) && path_noexec(path)) return -EACCES; break; } error = inode_permission(inode, MAY_OPEN | acc_mode); if (error) return error; /* * An append-only file must be opened in append mode for writing. */ if (IS_APPEND(inode)) { if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND)) return -EPERM; if (flag & O_TRUNC) return -EPERM; } /* O_NOATIME can only be set by the owner or superuser */ if (flag & O_NOATIME && !inode_owner_or_capable(inode)) return -EPERM; return 0; } static int handle_truncate(struct file *filp) { const struct path *path = &filp->f_path; struct inode *inode = path->dentry->d_inode; int error = get_write_access(inode); if (error) return error; /* * Refuse to truncate files with mandatory locks held on them. */ error = locks_verify_locked(filp); if (!error) error = security_path_truncate(path); if (!error) { error = do_truncate(path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } put_write_access(inode); return error; } static inline int open_to_namei_flags(int flag) { if ((flag & O_ACCMODE) == 3) flag--; return flag; } static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode) { struct user_namespace *s_user_ns; int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; s_user_ns = dir->dentry->d_sb->s_user_ns; if (!kuid_has_mapping(s_user_ns, current_fsuid()) || !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; return security_inode_create(dir->dentry->d_inode, dentry, mode); } /* * Attempt to atomically look up, create and open a file from a negative * dentry. * * Returns 0 if successful. The file will have been created and attached to * @file by the filesystem calling finish_open(). * * If the file was looked up only or didn't need creating, FMODE_OPENED won't * be set. The caller will need to perform the open themselves. @path will * have been updated to point to the new dentry. This may be negative. * * Returns an error code otherwise. */ static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry, struct file *file, int open_flag, umode_t mode) { struct dentry *const DENTRY_NOT_SET = (void *) -1UL; struct inode *dir = nd->path.dentry->d_inode; int error; if (nd->flags & LOOKUP_DIRECTORY) open_flag |= O_DIRECTORY; file->f_path.dentry = DENTRY_NOT_SET; file->f_path.mnt = nd->path.mnt; error = dir->i_op->atomic_open(dir, dentry, file, open_to_namei_flags(open_flag), mode); d_lookup_done(dentry); if (!error) { if (file->f_mode & FMODE_OPENED) { if (unlikely(dentry != file->f_path.dentry)) { dput(dentry); dentry = dget(file->f_path.dentry); } } else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { error = -EIO; } else { if (file->f_path.dentry) { dput(dentry); dentry = file->f_path.dentry; } if (unlikely(d_is_negative(dentry))) error = -ENOENT; } } if (error) { dput(dentry); dentry = ERR_PTR(error); } return dentry; } /* * Look up and maybe create and open the last component. * * Must be called with parent locked (exclusive in O_CREAT case). * * Returns 0 on success, that is, if * the file was successfully atomically created (if necessary) and opened, or * the file was not completely opened at this time, though lookups and * creations were performed. * These case are distinguished by presence of FMODE_OPENED on file->f_mode. * In the latter case dentry returned in @path might be negative if O_CREAT * hadn't been specified. * * An error code is returned on failure. */ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op, bool got_write) { struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; int open_flag = op->open_flag; struct dentry *dentry; int error, create_error = 0; umode_t mode = op->mode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); if (unlikely(IS_DEADDIR(dir_inode))) return ERR_PTR(-ENOENT); file->f_mode &= ~FMODE_CREATED; dentry = d_lookup(dir, &nd->last); for (;;) { if (!dentry) { dentry = d_alloc_parallel(dir, &nd->last, &wq); if (IS_ERR(dentry)) return dentry; } if (d_in_lookup(dentry)) break; error = d_revalidate(dentry, nd->flags); if (likely(error > 0)) break; if (error) goto out_dput; d_invalidate(dentry); dput(dentry); dentry = NULL; } if (dentry->d_inode) { /* Cached positive dentry: will open in f_op->open */ return dentry; } /* * Checking write permission is tricky, bacuse we don't know if we are * going to actually need it: O_CREAT opens should work as long as the * file exists. But checking existence breaks atomicity. The trick is * to check access and if not granted clear O_CREAT from the flags. * * Another problem is returing the "right" error value (e.g. for an * O_EXCL open we want to return EEXIST not EROFS). */ if (unlikely(!got_write)) open_flag &= ~O_TRUNC; if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; if (!IS_POSIXACL(dir->d_inode)) mode &= ~current_umask(); if (likely(got_write)) create_error = may_o_create(&nd->path, dentry, mode); else create_error = -EROFS; } if (create_error) open_flag &= ~O_CREAT; if (dir_inode->i_op->atomic_open) { dentry = atomic_open(nd, dentry, file, open_flag, mode); if (unlikely(create_error) && dentry == ERR_PTR(-ENOENT)) dentry = ERR_PTR(create_error); return dentry; } if (d_in_lookup(dentry)) { struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry, nd->flags); d_lookup_done(dentry); if (unlikely(res)) { if (IS_ERR(res)) { error = PTR_ERR(res); goto out_dput; } dput(dentry); dentry = res; } } /* Negative dentry, just create the file */ if (!dentry->d_inode && (open_flag & O_CREAT)) { file->f_mode |= FMODE_CREATED; audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); if (!dir_inode->i_op->create) { error = -EACCES; goto out_dput; } error = dir_inode->i_op->create(dir_inode, dentry, mode, open_flag & O_EXCL); if (error) goto out_dput; } if (unlikely(create_error) && !dentry->d_inode) { error = create_error; goto out_dput; } return dentry; out_dput: dput(dentry); return ERR_PTR(error); } static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct dentry *dir = nd->path.dentry; int open_flag = op->open_flag; bool got_write = false; unsigned seq; struct inode *inode; struct dentry *dentry; const char *res; nd->flags |= op->intent; if (nd->last_type != LAST_NORM) { if (nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } if (!(open_flag & O_CREAT)) { if (nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; /* we _can_ be in RCU mode here */ dentry = lookup_fast(nd, &inode, &seq); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (likely(dentry)) goto finish_lookup; BUG_ON(nd->flags & LOOKUP_RCU); } else { /* create side of things */ if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); } audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* trailing slashes? */ if (unlikely(nd->last.name[nd->last.len])) return ERR_PTR(-EISDIR); } if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; let lookup_open() decide; we'll be * dropping this one anyway. */ } if (open_flag & O_CREAT) inode_lock(dir->d_inode); else inode_lock_shared(dir->d_inode); dentry = lookup_open(nd, file, op, got_write); if (!IS_ERR(dentry) && (file->f_mode & FMODE_CREATED)) fsnotify_create(dir->d_inode, dentry); if (open_flag & O_CREAT) inode_unlock(dir->d_inode); else inode_unlock_shared(dir->d_inode); if (got_write) mnt_drop_write(nd->path.mnt); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) { dput(nd->path.dentry); nd->path.dentry = dentry; return NULL; } finish_lookup: if (nd->depth) put_link(nd); res = step_into(nd, WALK_TRAILING, dentry, inode, seq); if (unlikely(res)) nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); return res; } /* * Handle the last step of open() */ static int do_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { int open_flag = op->open_flag; bool do_truncate; int acc_mode; int error; if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) { error = complete_walk(nd); if (error) return error; } if (!(file->f_mode & FMODE_CREATED)) audit_inode(nd->name, nd->path.dentry, 0); if (open_flag & O_CREAT) { if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED)) return -EEXIST; if (d_is_dir(nd->path.dentry)) return -EISDIR; error = may_create_in_sticky(nd->dir_mode, nd->dir_uid, d_backing_inode(nd->path.dentry)); if (unlikely(error)) return error; } if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) return -ENOTDIR; do_truncate = false; acc_mode = op->acc_mode; if (file->f_mode & FMODE_CREATED) { /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; acc_mode = 0; } else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) { error = mnt_want_write(nd->path.mnt); if (error) return error; do_truncate = true; } error = may_open(&nd->path, acc_mode, open_flag); if (!error && !(file->f_mode & FMODE_OPENED)) error = vfs_open(&nd->path, file); if (!error) error = ima_file_check(file, op->acc_mode); if (!error && do_truncate) error = handle_truncate(file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; } if (do_truncate) mnt_drop_write(nd->path.mnt); return error; } struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) { struct dentry *child = NULL; struct inode *dir = dentry->d_inode; struct inode *inode; int error; /* we want directory to be writable */ error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) goto out_err; error = -EOPNOTSUPP; if (!dir->i_op->tmpfile) goto out_err; error = -ENOMEM; child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; error = dir->i_op->tmpfile(dir, child, mode); if (error) goto out_err; error = -ENOENT; inode = child->d_inode; if (unlikely(!inode)) goto out_err; if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); } ima_post_create_tmpfile(inode); return child; out_err: dput(child); return ERR_PTR(error); } EXPORT_SYMBOL(vfs_tmpfile); static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { struct dentry *child; struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); if (unlikely(error)) return error; error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; child = vfs_tmpfile(path.dentry, op->mode, op->open_flag); error = PTR_ERR(child); if (IS_ERR(child)) goto out2; dput(path.dentry); path.dentry = child; audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ error = may_open(&path, 0, op->open_flag); if (error) goto out2; file->f_path.mnt = path.mnt; error = finish_open(file, child, NULL); out2: mnt_drop_write(path.mnt); out: path_put(&path); return error; } static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file) { struct path path; int error = path_lookupat(nd, flags, &path); if (!error) { audit_inode(nd->name, path.dentry, 0); error = vfs_open(&path, file); path_put(&path); } return error; } static struct file *path_openat(struct nameidata *nd, const struct open_flags *op, unsigned flags) { struct file *file; int error; file = alloc_empty_file(op->open_flag, current_cred()); if (IS_ERR(file)) return file; if (unlikely(file->f_flags & __O_TMPFILE)) { error = do_tmpfile(nd, flags, op, file); } else if (unlikely(file->f_flags & O_PATH)) { error = do_o_path(nd, flags, file); } else { const char *s = path_init(nd, flags); while (!(error = link_path_walk(s, nd)) && (s = open_last_lookups(nd, file, op)) != NULL) ; if (!error) error = do_open(nd, file, op); terminate_walk(nd); } if (likely(!error)) { if (likely(file->f_mode & FMODE_OPENED)) return file; WARN_ON(1); error = -EINVAL; } fput(file); if (error == -EOPENSTALE) { if (flags & LOOKUP_RCU) error = -ECHILD; else error = -ESTALE; } return ERR_PTR(error); } struct file *do_filp_open(int dfd, struct filename *pathname, const struct open_flags *op) { struct nameidata nd; int flags = op->lookup_flags; struct file *filp; set_nameidata(&nd, dfd, pathname); filp = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(filp == ERR_PTR(-ECHILD))) filp = path_openat(&nd, op, flags); if (unlikely(filp == ERR_PTR(-ESTALE))) filp = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); return filp; } struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, const char *name, const struct open_flags *op) { struct nameidata nd; struct file *file; struct filename *filename; int flags = op->lookup_flags | LOOKUP_ROOT; nd.root.mnt = mnt; nd.root.dentry = dentry; if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN) return ERR_PTR(-ELOOP); filename = getname_kernel(name); if (IS_ERR(filename)) return ERR_CAST(filename); set_nameidata(&nd, -1, filename); file = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(file == ERR_PTR(-ECHILD))) file = path_openat(&nd, op, flags); if (unlikely(file == ERR_PTR(-ESTALE))) file = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); putname(filename); return file; } static struct dentry *filename_create(int dfd, struct filename *name, struct path *path, unsigned int lookup_flags) { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; int type; int err2; int error; bool is_dir = (lookup_flags & LOOKUP_DIRECTORY); /* * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any * other flags passed in are ignored! */ lookup_flags &= LOOKUP_REVAL; name = filename_parentat(dfd, name, lookup_flags, path, &last, &type); if (IS_ERR(name)) return ERR_CAST(name); /* * Yucky last component or no last component at all? * (foo/., foo/.., /////) */ if (unlikely(type != LAST_NORM)) goto out; /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* * Do the final lookup. */ lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path->dentry, lookup_flags); if (IS_ERR(dentry)) goto unlock; error = -EEXIST; if (d_is_positive(dentry)) goto fail; /* * Special case - lookup gave negative, but... we had foo/bar/ * From the vfs_mknod() POV we just have a negative dentry - * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ if (unlikely(!is_dir && last.name[last.len])) { error = -ENOENT; goto fail; } if (unlikely(err2)) { error = err2; goto fail; } putname(name); return dentry; fail: dput(dentry); dentry = ERR_PTR(error); unlock: inode_unlock(path->dentry->d_inode); if (!err2) mnt_drop_write(path->mnt); out: path_put(path); putname(name); return dentry; } struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, unsigned int lookup_flags) { return filename_create(dfd, getname_kernel(pathname), path, lookup_flags); } EXPORT_SYMBOL(kern_path_create); void done_path_create(struct path *path, struct dentry *dentry) { dput(dentry); inode_unlock(path->dentry->d_inode); mnt_drop_write(path->mnt); path_put(path); } EXPORT_SYMBOL(done_path_create); inline struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, unsigned int lookup_flags) { return filename_create(dfd, getname(pathname), path, lookup_flags); } EXPORT_SYMBOL(user_path_create); int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; int error = may_create(dir, dentry); if (error) return error; if ((S_ISCHR(mode) || S_ISBLK(mode)) && !is_whiteout && !capable(CAP_MKNOD)) return -EPERM; if (!dir->i_op->mknod) return -EPERM; error = devcgroup_inode_mknod(mode, dev); if (error) return error; error = security_inode_mknod(dir, dentry, mode, dev); if (error) return error; error = dir->i_op->mknod(dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mknod); static int may_mknod(umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK: case 0: /* zero mode translates to S_IFREG */ return 0; case S_IFDIR: return -EPERM; default: return -EINVAL; } } static long do_mknodat(int dfd, const char __user *filename, umode_t mode, unsigned int dev) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = 0; error = may_mknod(mode); if (error) return error; retry: dentry = user_path_create(dfd, filename, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); if (!IS_POSIXACL(path.dentry->d_inode)) mode &= ~current_umask(); error = security_path_mknod(&path, dentry, mode, dev); if (error) goto out; switch (mode & S_IFMT) { case 0: case S_IFREG: error = vfs_create(path.dentry->d_inode,dentry,mode,true); if (!error) ima_post_path_mknod(dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(path.dentry->d_inode,dentry,mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: error = vfs_mknod(path.dentry->d_inode,dentry,mode,0); break; } out: done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, dev) { return do_mknodat(dfd, filename, mode, dev); } SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { return do_mknodat(AT_FDCWD, filename, mode, dev); } int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { int error = may_create(dir, dentry); unsigned max_links = dir->i_sb->s_max_links; if (error) return error; if (!dir->i_op->mkdir) return -EPERM; mode &= (S_IRWXUGO|S_ISVTX); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; if (max_links && dir->i_nlink >= max_links) return -EMLINK; error = dir->i_op->mkdir(dir, dentry, mode); if (!error) fsnotify_mkdir(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkdir); static long do_mkdirat(int dfd, const char __user *pathname, umode_t mode) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = LOOKUP_DIRECTORY; retry: dentry = user_path_create(dfd, pathname, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); if (!IS_POSIXACL(path.dentry->d_inode)) mode &= ~current_umask(); error = security_path_mkdir(&path, dentry, mode); if (!error) error = vfs_mkdir(path.dentry->d_inode, dentry, mode); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) { return do_mkdirat(dfd, pathname, mode); } SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { return do_mkdirat(AT_FDCWD, pathname, mode); } int vfs_rmdir(struct inode *dir, struct dentry *dentry) { int error = may_delete(dir, dentry, 1); if (error) return error; if (!dir->i_op->rmdir) return -EPERM; dget(dentry); inode_lock(dentry->d_inode); error = -EBUSY; if (is_local_mountpoint(dentry)) goto out; error = security_inode_rmdir(dir, dentry); if (error) goto out; error = dir->i_op->rmdir(dir, dentry); if (error) goto out; shrink_dcache_parent(dentry); dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); fsnotify_rmdir(dir, dentry); out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) d_delete(dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); long do_rmdir(int dfd, struct filename *name) { int error = 0; struct dentry *dentry; struct path path; struct qstr last; int type; unsigned int lookup_flags = 0; retry: name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (IS_ERR(name)) return PTR_ERR(name); switch (type) { case LAST_DOTDOT: error = -ENOTEMPTY; goto exit1; case LAST_DOT: error = -EINVAL; goto exit1; case LAST_ROOT: error = -EBUSY; goto exit1; } error = mnt_want_write(path.mnt); if (error) goto exit1; inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit2; if (!dentry->d_inode) { error = -ENOENT; goto exit3; } error = security_path_rmdir(&path, dentry); if (error) goto exit3; error = vfs_rmdir(path.dentry->d_inode, dentry); exit3: dput(dentry); exit2: inode_unlock(path.dentry->d_inode); mnt_drop_write(path.mnt); exit1: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } putname(name); return error; } SYSCALL_DEFINE1(rmdir, const char __user *, pathname) { return do_rmdir(AT_FDCWD, getname(pathname)); } /** * vfs_unlink - unlink a filesystem object * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. * * The caller must hold dir->i_mutex. * * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and * return a reference to the inode in delegated_inode. The caller * should then break the delegation on that inode and retry. Because * breaking a delegation may take a long time, the caller should drop * dir->i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; int error = may_delete(dir, dentry, 0); if (error) return error; if (!dir->i_op->unlink) return -EPERM; inode_lock(target); if (is_local_mountpoint(dentry)) error = -EBUSY; else { error = security_inode_unlink(dir, dentry); if (!error) { error = try_break_deleg(target, delegated_inode); if (error) goto out; error = dir->i_op->unlink(dir, dentry); if (!error) { dont_mount(dentry); detach_mounts(dentry); fsnotify_unlink(dir, dentry); } } } out: inode_unlock(target); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) { fsnotify_link_count(target); d_delete(dentry); } return error; } EXPORT_SYMBOL(vfs_unlink); /* * Make sure that the actual truncation of the file will occur outside its * directory's i_mutex. Truncate can take a long time if there is a lot of * writeout happening, and we don't want to prevent access to the directory * while waiting on the I/O. */ long do_unlinkat(int dfd, struct filename *name) { int error; struct dentry *dentry; struct path path; struct qstr last; int type; struct inode *inode = NULL; struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0; retry: name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (IS_ERR(name)) return PTR_ERR(n