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 /* SPDX-License-Identifier: GPL-2.0 */ /* * memory buffer pool support */ #ifndef _LINUX_MEMPOOL_H #define _LINUX_MEMPOOL_H #include <linux/wait.h> #include <linux/compiler.h> struct kmem_cache; typedef void * (mempool_alloc_t)(gfp_t gfp_mask, void *pool_data); typedef void (mempool_free_t)(void *element, void *pool_data); typedef struct mempool_s { spinlock_t lock; int min_nr; /* nr of elements at *elements */ int curr_nr; /* Current nr of elements at *elements */ void **elements; void *pool_data; mempool_alloc_t *alloc; mempool_free_t *free; wait_queue_head_t wait; } mempool_t; static inline bool mempool_initialized(mempool_t *pool) { return pool->elements != NULL; } void mempool_exit(mempool_t *pool); int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int node_id); int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int nid); extern int mempool_resize(mempool_t *pool, int new_min_nr); extern void mempool_destroy(mempool_t *pool); extern void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) __malloc; extern void mempool_free(void *element, mempool_t *pool); /* * A mempool_alloc_t and mempool_free_t that get the memory from * a slab cache that is passed in through pool_data. * Note: the slab cache may not have a ctor function. */ void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data); void mempool_free_slab(void *element, void *pool_data); static inline int mempool_init_slab_pool(mempool_t *pool, int min_nr, struct kmem_cache *kc) { return mempool_init(pool, min_nr, mempool_alloc_slab, mempool_free_slab, (void *) kc); } static inline mempool_t * mempool_create_slab_pool(int min_nr, struct kmem_cache *kc) { return mempool_create(min_nr, mempool_alloc_slab, mempool_free_slab, (void *) kc); } /* * a mempool_alloc_t and a mempool_free_t to kmalloc and kfree the * amount of memory specified by pool_data */ void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data); void mempool_kfree(void *element, void *pool_data); static inline int mempool_init_kmalloc_pool(mempool_t *pool, int min_nr, size_t size) { return mempool_init(pool, min_nr, mempool_kmalloc, mempool_kfree, (void *) size); } static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size) { return mempool_create(min_nr, mempool_kmalloc, mempool_kfree, (void *) size); } /* * A mempool_alloc_t and mempool_free_t for a simple page allocator that * allocates pages of the order specified by pool_data */ void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data); void mempool_free_pages(void *element, void *pool_data); static inline int mempool_init_page_pool(mempool_t *pool, int min_nr, int order) { return mempool_init(pool, min_nr, mempool_alloc_pages, mempool_free_pages, (void *)(long)order); } static inline mempool_t *mempool_create_page_pool(int min_nr, int order) { return mempool_create(min_nr, mempool_alloc_pages, mempool_free_pages, (void *)(long)order); } #endif /* _LINUX_MEMPOOL_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 /* SPDX-License-Identifier: GPL-2.0 */ /* * RT Mutexes: blocking mutual exclusion locks with PI support * * started by Ingo Molnar and Thomas Gleixner: * * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * This file contains the private data structure and API definitions. */ #ifndef __KERNEL_RTMUTEX_COMMON_H #define __KERNEL_RTMUTEX_COMMON_H #include <linux/rtmutex.h> #include <linux/sched/wake_q.h> /* * This is the control structure for tasks blocked on a rt_mutex, * which is allocated on the kernel stack on of the blocked task. * * @tree_entry: pi node to enqueue into the mutex waiters tree * @pi_tree_entry: pi node to enqueue into the mutex owner waiters tree * @task: task reference to the blocked task */ struct rt_mutex_waiter { struct rb_node tree_entry; struct rb_node pi_tree_entry; struct task_struct *task; struct rt_mutex *lock; #ifdef CONFIG_DEBUG_RT_MUTEXES unsigned long ip; struct pid *deadlock_task_pid; struct rt_mutex *deadlock_lock; #endif int prio; u64 deadline; }; /* * Various helpers to access the waiters-tree: */ #ifdef CONFIG_RT_MUTEXES static inline int rt_mutex_has_waiters(struct rt_mutex *lock) { return !RB_EMPTY_ROOT(&lock->waiters.rb_root); } static inline struct rt_mutex_waiter * rt_mutex_top_waiter(struct rt_mutex *lock) { struct rb_node *leftmost = rb_first_cached(&lock->waiters); struct rt_mutex_waiter *w = NULL; if (leftmost) { w = rb_entry(leftmost, struct rt_mutex_waiter, tree_entry); BUG_ON(w->lock != lock); } return w; } static inline int task_has_pi_waiters(struct task_struct *p) { return !RB_EMPTY_ROOT(&p->pi_waiters.rb_root); } static inline struct rt_mutex_waiter * task_top_pi_waiter(struct task_struct *p) { return rb_entry(p->pi_waiters.rb_leftmost, struct rt_mutex_waiter, pi_tree_entry); } #else static inline int rt_mutex_has_waiters(struct rt_mutex *lock) { return false; } static inline struct rt_mutex_waiter * rt_mutex_top_waiter(struct rt_mutex *lock) { return NULL; } static inline int task_has_pi_waiters(struct task_struct *p) { return false; } static inline struct rt_mutex_waiter * task_top_pi_waiter(struct task_struct *p) { return NULL; } #endif /* * lock->owner state tracking: */ #define RT_MUTEX_HAS_WAITERS 1UL static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) { unsigned long owner = (unsigned long) READ_ONCE(lock->owner); return (struct task_struct *) (owner & ~RT_MUTEX_HAS_WAITERS); } /* * Constants for rt mutex functions which have a selectable deadlock * detection. * * RT_MUTEX_MIN_CHAINWALK: Stops the lock chain walk when there are * no further PI adjustments to be made. * * RT_MUTEX_FULL_CHAINWALK: Invoke deadlock detection with a full * walk of the lock chain. */ enum rtmutex_chainwalk { RT_MUTEX_MIN_CHAINWALK, RT_MUTEX_FULL_CHAINWALK, }; /* * PI-futex support (proxy locking functions, etc.): */ extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner); extern void rt_mutex_proxy_unlock(struct rt_mutex *lock); extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task); extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task); extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, struct hrtimer_sleeper *to, struct rt_mutex_waiter *waiter); extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter); extern int rt_mutex_futex_trylock(struct rt_mutex *l); extern int __rt_mutex_futex_trylock(struct rt_mutex *l); extern void rt_mutex_futex_unlock(struct rt_mutex *lock); extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, struct wake_q_head *wqh); extern void rt_mutex_postunlock(struct wake_q_head *wake_q); #ifdef CONFIG_DEBUG_RT_MUTEXES # include "rtmutex-debug.h" #else # include "rtmutex.h" #endif #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 /* SPDX-License-Identifier: GPL-2.0 */ /* * bvec iterator * * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com> */ #ifndef __LINUX_BVEC_ITER_H #define __LINUX_BVEC_ITER_H #include <linux/bug.h> #include <linux/errno.h> #include <linux/limits.h> #include <linux/minmax.h> #include <linux/mm.h> #include <linux/types.h> struct page; /** * struct bio_vec - a contiguous range of physical memory addresses * @bv_page: First page associated with the address range. * @bv_len: Number of bytes in the address range. * @bv_offset: Start of the address range relative to the start of @bv_page. * * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len: * * nth_page(@bv_page, n) == @bv_page + n * * This holds because page_is_mergeable() checks the above property. */ struct bio_vec { struct page *bv_page; unsigned int bv_len; unsigned int bv_offset; }; struct bvec_iter { sector_t bi_sector; /* device address in 512 byte sectors */ unsigned int bi_size; /* residual I/O count */ unsigned int bi_idx; /* current index into bvl_vec */ unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ }; struct bvec_iter_all { struct bio_vec bv; int idx; unsigned done; }; /* * various member access, note that bio_data should of course not be used * on highmem page vectors */ #define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) /* multi-page (mp_bvec) helpers */ #define mp_bvec_iter_page(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_page) #define mp_bvec_iter_len(bvec, iter) \ min((iter).bi_size, \ __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done) #define mp_bvec_iter_offset(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done) #define mp_bvec_iter_page_idx(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) / PAGE_SIZE) #define mp_bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = mp_bvec_iter_page((bvec), (iter)), \ .bv_len = mp_bvec_iter_len((bvec), (iter)), \ .bv_offset = mp_bvec_iter_offset((bvec), (iter)), \ }) /* For building single-page bvec in flight */ #define bvec_iter_offset(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) % PAGE_SIZE) #define bvec_iter_len(bvec, iter) \ min_t(unsigned, mp_bvec_iter_len((bvec), (iter)), \ PAGE_SIZE - bvec_iter_offset((bvec), (iter))) #define bvec_iter_page(bvec, iter) \ (mp_bvec_iter_page((bvec), (iter)) + \ mp_bvec_iter_page_idx((bvec), (iter))) #define bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = bvec_iter_page((bvec), (iter)), \ .bv_len = bvec_iter_len((bvec), (iter)), \ .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) static inline bool bvec_iter_advance(const struct bio_vec *bv, struct bvec_iter *iter, unsigned bytes) { unsigned int idx = iter->bi_idx; if (WARN_ONCE(bytes > iter->bi_size, "Attempted to advance past end of bvec iter\n")) { iter->bi_size = 0; return false; } iter->bi_size -= bytes; bytes += iter->bi_bvec_done; while (bytes && bytes >= bv[idx].bv_len) { bytes -= bv[idx].bv_len; idx++; } iter->bi_idx = idx; iter->bi_bvec_done = bytes; return true; } static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter) { iter->bi_bvec_done = 0; iter->bi_idx++; } #define for_each_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter), \ (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter))) /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ { \ .bi_sector = 0, \ .bi_size = UINT_MAX, \ .bi_idx = 0, \ .bi_bvec_done = 0, \ } static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) { iter_all->done = 0; iter_all->idx = 0; return &iter_all->bv; } static inline void bvec_advance(const struct bio_vec *bvec, struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; if (iter_all->done) { bv->bv_page++; bv->bv_offset = 0; } else { bv->bv_page = bvec->bv_page + (bvec->bv_offset >> PAGE_SHIFT); bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); iter_all->done += bv->bv_len; if (iter_all->done == bvec->bv_len) { iter_all->idx++; iter_all->done = 0; } } #endif /* __LINUX_BVEC_ITER_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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Common values and helper functions for the ChaCha and XChaCha stream ciphers. * * XChaCha extends ChaCha's nonce to 192 bits, while provably retaining ChaCha's * security. Here they share the same key size, tfm context, and setkey * function; only their IV size and encrypt/decrypt function differ. * * The ChaCha paper specifies 20, 12, and 8-round variants. In general, it is * recommended to use the 20-round variant ChaCha20. However, the other * variants can be needed in some performance-sensitive scenarios. The generic * ChaCha code currently allows only the 20 and 12-round variants. */ #ifndef _CRYPTO_CHACHA_H #define _CRYPTO_CHACHA_H #include <asm/unaligned.h> #include <linux/types.h> /* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */ #define CHACHA_IV_SIZE 16 #define CHACHA_KEY_SIZE 32 #define CHACHA_BLOCK_SIZE 64 #define CHACHAPOLY_IV_SIZE 12 #define CHACHA_STATE_WORDS (CHACHA_BLOCK_SIZE / sizeof(u32)) /* 192-bit nonce, then 64-bit stream position */ #define XCHACHA_IV_SIZE 32 void chacha_block_generic(u32 *state, u8 *stream, int nrounds); static inline void chacha20_block(u32 *state, u8 *stream) { chacha_block_generic(state, stream, 20); } void hchacha_block_arch(const u32 *state, u32 *out, int nrounds); void hchacha_block_generic(const u32 *state, u32 *out, int nrounds); static inline void hchacha_block(const u32 *state, u32 *out, int nrounds) { if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA)) hchacha_block_arch(state, out, nrounds); else hchacha_block_generic(state, out, nrounds); } enum chacha_constants { /* expand 32-byte k */ CHACHA_CONSTANT_EXPA = 0x61707865U, CHACHA_CONSTANT_ND_3 = 0x3320646eU, CHACHA_CONSTANT_2_BY = 0x79622d32U, CHACHA_CONSTANT_TE_K = 0x6b206574U }; static inline void chacha_init_consts(u32 *state) { state[0] = CHACHA_CONSTANT_EXPA; state[1] = CHACHA_CONSTANT_ND_3; state[2] = CHACHA_CONSTANT_2_BY; state[3] = CHACHA_CONSTANT_TE_K; } void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv); static inline void chacha_init_generic(u32 *state, const u32 *key, const u8 *iv) { chacha_init_consts(state); state[4] = key[0]; state[5] = key[1]; state[6] = key[2]; state[7] = key[3]; state[8] = key[4]; state[9] = key[5]; state[10] = key[6]; state[11] = key[7]; state[12] = get_unaligned_le32(iv + 0); state[13] = get_unaligned_le32(iv + 4); state[14] = get_unaligned_le32(iv + 8); state[15] = get_unaligned_le32(iv + 12); } static inline void chacha_init(u32 *state, const u32 *key, const u8 *iv) { if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA)) chacha_init_arch(state, key, iv); else chacha_init_generic(state, key, iv); } void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, int nrounds); void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, int nrounds); static inline void chacha_crypt(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, int nrounds) { if (IS_ENABLED(CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA)) chacha_crypt_arch(state, dst, src, bytes, nrounds); else chacha_crypt_generic(state, dst, src, bytes, nrounds); } static inline void chacha20_crypt(u32 *state, u8 *dst, const u8 *src, unsigned int bytes) { chacha_crypt(state, dst, src, bytes, 20); } #endif /* _CRYPTO_CHACHA_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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM libata #if !defined(_TRACE_LIBATA_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_LIBATA_H #include <linux/ata.h> #include <linux/libata.h> #include <linux/tracepoint.h> #include <linux/trace_seq.h> #define ata_opcode_name(opcode) { opcode, #opcode } #define show_opcode_name(val) \ __print_symbolic(val, \ ata_opcode_name(ATA_CMD_DEV_RESET), \ ata_opcode_name(ATA_CMD_CHK_POWER), \ ata_opcode_name(ATA_CMD_STANDBY), \ ata_opcode_name(ATA_CMD_IDLE), \ ata_opcode_name(ATA_CMD_EDD), \ ata_opcode_name(ATA_CMD_DOWNLOAD_MICRO), \ ata_opcode_name(ATA_CMD_DOWNLOAD_MICRO_DMA), \ ata_opcode_name(ATA_CMD_NOP), \ ata_opcode_name(ATA_CMD_FLUSH), \ ata_opcode_name(ATA_CMD_FLUSH_EXT), \ ata_opcode_name(ATA_CMD_ID_ATA), \ ata_opcode_name(ATA_CMD_ID_ATAPI), \ ata_opcode_name(ATA_CMD_SERVICE), \ ata_opcode_name(ATA_CMD_READ), \ ata_opcode_name(ATA_CMD_READ_EXT), \ ata_opcode_name(ATA_CMD_READ_QUEUED), \ ata_opcode_name(ATA_CMD_READ_STREAM_EXT), \ ata_opcode_name(ATA_CMD_READ_STREAM_DMA_EXT), \ ata_opcode_name(ATA_CMD_WRITE), \ ata_opcode_name(ATA_CMD_WRITE_EXT), \ ata_opcode_name(ATA_CMD_WRITE_QUEUED), \ ata_opcode_name(ATA_CMD_WRITE_STREAM_EXT), \ ata_opcode_name(ATA_CMD_WRITE_STREAM_DMA_EXT), \ ata_opcode_name(ATA_CMD_WRITE_FUA_EXT), \ ata_opcode_name(ATA_CMD_WRITE_QUEUED_FUA_EXT), \ ata_opcode_name(ATA_CMD_FPDMA_READ), \ ata_opcode_name(ATA_CMD_FPDMA_WRITE), \ ata_opcode_name(ATA_CMD_NCQ_NON_DATA), \ ata_opcode_name(ATA_CMD_FPDMA_SEND), \ ata_opcode_name(ATA_CMD_FPDMA_RECV), \ ata_opcode_name(ATA_CMD_PIO_READ), \ ata_opcode_name(ATA_CMD_PIO_READ_EXT), \ ata_opcode_name(ATA_CMD_PIO_WRITE), \ ata_opcode_name(ATA_CMD_PIO_WRITE_EXT), \ ata_opcode_name(ATA_CMD_READ_MULTI), \ ata_opcode_name(ATA_CMD_READ_MULTI_EXT), \ ata_opcode_name(ATA_CMD_WRITE_MULTI), \ ata_opcode_name(ATA_CMD_WRITE_MULTI_EXT), \ ata_opcode_name(ATA_CMD_WRITE_MULTI_FUA_EXT), \ ata_opcode_name(ATA_CMD_SET_FEATURES), \ ata_opcode_name(ATA_CMD_SET_MULTI), \ ata_opcode_name(ATA_CMD_PACKET), \ ata_opcode_name(ATA_CMD_VERIFY), \ ata_opcode_name(ATA_CMD_VERIFY_EXT), \ ata_opcode_name(ATA_CMD_WRITE_UNCORR_EXT), \ ata_opcode_name(ATA_CMD_STANDBYNOW1), \ ata_opcode_name(ATA_CMD_IDLEIMMEDIATE), \ ata_opcode_name(ATA_CMD_SLEEP), \ ata_opcode_name(ATA_CMD_INIT_DEV_PARAMS), \ ata_opcode_name(ATA_CMD_READ_NATIVE_MAX), \ ata_opcode_name(ATA_CMD_READ_NATIVE_MAX_EXT), \ ata_opcode_name(ATA_CMD_SET_MAX), \ ata_opcode_name(ATA_CMD_SET_MAX_EXT), \ ata_opcode_name(ATA_CMD_READ_LOG_EXT), \ ata_opcode_name(ATA_CMD_WRITE_LOG_EXT), \ ata_opcode_name(ATA_CMD_READ_LOG_DMA_EXT), \ ata_opcode_name(ATA_CMD_WRITE_LOG_DMA_EXT), \ ata_opcode_name(ATA_CMD_TRUSTED_NONDATA), \ ata_opcode_name(ATA_CMD_TRUSTED_RCV), \ ata_opcode_name(ATA_CMD_TRUSTED_RCV_DMA), \ ata_opcode_name(ATA_CMD_TRUSTED_SND), \ ata_opcode_name(ATA_CMD_TRUSTED_SND_DMA), \ ata_opcode_name(ATA_CMD_PMP_READ), \ ata_opcode_name(ATA_CMD_PMP_READ_DMA), \ ata_opcode_name(ATA_CMD_PMP_WRITE), \ ata_opcode_name(ATA_CMD_PMP_WRITE_DMA), \ ata_opcode_name(ATA_CMD_CONF_OVERLAY), \ ata_opcode_name(ATA_CMD_SEC_SET_PASS), \ ata_opcode_name(ATA_CMD_SEC_UNLOCK), \ ata_opcode_name(ATA_CMD_SEC_ERASE_PREP), \ ata_opcode_name(ATA_CMD_SEC_ERASE_UNIT), \ ata_opcode_name(ATA_CMD_SEC_FREEZE_LOCK), \ ata_opcode_name(ATA_CMD_SEC_DISABLE_PASS), \ ata_opcode_name(ATA_CMD_CONFIG_STREAM), \ ata_opcode_name(ATA_CMD_SMART), \ ata_opcode_name(ATA_CMD_MEDIA_LOCK), \ ata_opcode_name(ATA_CMD_MEDIA_UNLOCK), \ ata_opcode_name(ATA_CMD_DSM), \ ata_opcode_name(ATA_CMD_CHK_MED_CRD_TYP), \ ata_opcode_name(ATA_CMD_CFA_REQ_EXT_ERR), \ ata_opcode_name(ATA_CMD_CFA_WRITE_NE), \ ata_opcode_name(ATA_CMD_CFA_TRANS_SECT), \ ata_opcode_name(ATA_CMD_CFA_ERASE), \ ata_opcode_name(ATA_CMD_CFA_WRITE_MULT_NE), \ ata_opcode_name(ATA_CMD_REQ_SENSE_DATA), \ ata_opcode_name(ATA_CMD_SANITIZE_DEVICE), \ ata_opcode_name(ATA_CMD_ZAC_MGMT_IN), \ ata_opcode_name(ATA_CMD_ZAC_MGMT_OUT), \ ata_opcode_name(ATA_CMD_RESTORE), \ ata_opcode_name(ATA_CMD_READ_LONG), \ ata_opcode_name(ATA_CMD_READ_LONG_ONCE), \ ata_opcode_name(ATA_CMD_WRITE_LONG), \ ata_opcode_name(ATA_CMD_WRITE_LONG_ONCE)) #define ata_error_name(result) { result, #result } #define show_error_name(val) \ __print_symbolic(val, \ ata_error_name(ATA_ICRC), \ ata_error_name(ATA_UNC), \ ata_error_name(ATA_MC), \ ata_error_name(ATA_IDNF), \ ata_error_name(ATA_MCR), \ ata_error_name(ATA_ABORTED), \ ata_error_name(ATA_TRK0NF), \ ata_error_name(ATA_AMNF)) #define ata_protocol_name(proto) { proto, #proto } #define show_protocol_name(val) \ __print_symbolic(val, \ ata_protocol_name(ATA_PROT_UNKNOWN), \ ata_protocol_name(ATA_PROT_NODATA), \ ata_protocol_name(ATA_PROT_PIO), \ ata_protocol_name(ATA_PROT_DMA), \ ata_protocol_name(ATA_PROT_NCQ), \ ata_protocol_name(ATA_PROT_NCQ_NODATA), \ ata_protocol_name(ATAPI_PROT_NODATA), \ ata_protocol_name(ATAPI_PROT_PIO), \ ata_protocol_name(ATAPI_PROT_DMA)) const char *libata_trace_parse_status(struct trace_seq*, unsigned char); #define __parse_status(s) libata_trace_parse_status(p, s) const char *libata_trace_parse_eh_action(struct trace_seq *, unsigned int); #define __parse_eh_action(a) libata_trace_parse_eh_action(p, a) const char *libata_trace_parse_eh_err_mask(struct trace_seq *, unsigned int); #define __parse_eh_err_mask(m) libata_trace_parse_eh_err_mask(p, m) const char *libata_trace_parse_qc_flags(struct trace_seq *, unsigned int); #define __parse_qc_flags(f) libata_trace_parse_qc_flags(p, f) const char *libata_trace_parse_subcmd(struct trace_seq *, unsigned char, unsigned char, unsigned char); #define __parse_subcmd(c,f,h) libata_trace_parse_subcmd(p, c, f, h) TRACE_EVENT(ata_qc_issue, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, tag ) __field( unsigned char, cmd ) __field( unsigned char, dev ) __field( unsigned char, lbal ) __field( unsigned char, lbam ) __field( unsigned char, lbah ) __field( unsigned char, nsect ) __field( unsigned char, feature ) __field( unsigned char, hob_lbal ) __field( unsigned char, hob_lbam ) __field( unsigned char, hob_lbah ) __field( unsigned char, hob_nsect ) __field( unsigned char, hob_feature ) __field( unsigned char, ctl ) __field( unsigned char, proto ) __field( unsigned long, flags ) ), TP_fast_assign( __entry->ata_port = qc->ap->print_id; __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; __entry->tag = qc->tag; __entry->proto = qc->tf.protocol; __entry->cmd = qc->tf.command; __entry->dev = qc->tf.device; __entry->lbal = qc->tf.lbal; __entry->lbam = qc->tf.lbam; __entry->lbah = qc->tf.lbah; __entry->hob_lbal = qc->tf.hob_lbal; __entry->hob_lbam = qc->tf.hob_lbam; __entry->hob_lbah = qc->tf.hob_lbah; __entry->feature = qc->tf.feature; __entry->hob_feature = qc->tf.hob_feature; __entry->nsect = qc->tf.nsect; __entry->hob_nsect = qc->tf.hob_nsect; ), TP_printk("ata_port=%u ata_dev=%u tag=%d proto=%s cmd=%s%s " \ " tf=(%02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x)", __entry->ata_port, __entry->ata_dev, __entry->tag, show_protocol_name(__entry->proto), show_opcode_name(__entry->cmd), __parse_subcmd(__entry->cmd, __entry->feature, __entry->hob_nsect), __entry->cmd, __entry->feature, __entry->nsect, __entry->lbal, __entry->lbam, __entry->lbah, __entry->hob_feature, __entry->hob_nsect, __entry->hob_lbal, __entry->hob_lbam, __entry->hob_lbah, __entry->dev) ); DECLARE_EVENT_CLASS(ata_qc_complete_template, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, tag ) __field( unsigned char, status ) __field( unsigned char, dev ) __field( unsigned char, lbal ) __field( unsigned char, lbam ) __field( unsigned char, lbah ) __field( unsigned char, nsect ) __field( unsigned char, error ) __field( unsigned char, hob_lbal ) __field( unsigned char, hob_lbam ) __field( unsigned char, hob_lbah ) __field( unsigned char, hob_nsect ) __field( unsigned char, hob_feature ) __field( unsigned char, ctl ) __field( unsigned long, flags ) ), TP_fast_assign( __entry->ata_port = qc->ap->print_id; __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; __entry->tag = qc->tag; __entry->status = qc->result_tf.command; __entry->dev = qc->result_tf.device; __entry->lbal = qc->result_tf.lbal; __entry->lbam = qc->result_tf.lbam; __entry->lbah = qc->result_tf.lbah; __entry->hob_lbal = qc->result_tf.hob_lbal; __entry->hob_lbam = qc->result_tf.hob_lbam; __entry->hob_lbah = qc->result_tf.hob_lbah; __entry->error = qc->result_tf.feature; __entry->hob_feature = qc->result_tf.hob_feature; __entry->nsect = qc->result_tf.nsect; __entry->hob_nsect = qc->result_tf.hob_nsect; __entry->flags = qc->flags; ), TP_printk("ata_port=%u ata_dev=%u tag=%d flags=%s status=%s " \ " res=(%02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x)", __entry->ata_port, __entry->ata_dev, __entry->tag, __parse_qc_flags(__entry->flags), __parse_status(__entry->status), __entry->status, __entry->error, __entry->nsect, __entry->lbal, __entry->lbam, __entry->lbah, __entry->hob_feature, __entry->hob_nsect, __entry->hob_lbal, __entry->hob_lbam, __entry->hob_lbah, __entry->dev) ); DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_internal, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc)); DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_failed, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc)); DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_done, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc)); TRACE_EVENT(ata_eh_link_autopsy, TP_PROTO(struct ata_device *dev, unsigned int eh_action, unsigned int eh_err_mask), TP_ARGS(dev, eh_action, eh_err_mask), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, eh_action ) __field( unsigned int, eh_err_mask) ), TP_fast_assign( __entry->ata_port = dev->link->ap->print_id; __entry->ata_dev = dev->link->pmp + dev->devno; __entry->eh_action = eh_action; __entry->eh_err_mask = eh_err_mask; ), TP_printk("ata_port=%u ata_dev=%u eh_action=%s err_mask=%s", __entry->ata_port, __entry->ata_dev, __parse_eh_action(__entry->eh_action), __parse_eh_err_mask(__entry->eh_err_mask)) ); TRACE_EVENT(ata_eh_link_autopsy_qc, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, tag ) __field( unsigned int, qc_flags ) __field( unsigned int, eh_err_mask) ), TP_fast_assign( __entry->ata_port = qc->ap->print_id; __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; __entry->tag = qc->tag; __entry->qc_flags = qc->flags; __entry->eh_err_mask = qc->err_mask; ), TP_printk("ata_port=%u ata_dev=%u tag=%d flags=%s err_mask=%s", __entry->ata_port, __entry->ata_dev, __entry->tag, __parse_qc_flags(__entry->qc_flags), __parse_eh_err_mask(__entry->eh_err_mask)) ); #endif /* _TRACE_LIBATA_H */ /* This part must be outside protection */ #include <trace/define_trace.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 /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/buffer_head.h * * Everything to do with buffer_heads. */ #ifndef _LINUX_BUFFER_HEAD_H #define _LINUX_BUFFER_HEAD_H #include <linux/types.h> #include <linux/fs.h> #include <linux/linkage.h> #include <linux/pagemap.h> #include <linux/wait.h> #include <linux/atomic.h> #ifdef CONFIG_BLOCK enum bh_state_bits { BH_Uptodate, /* Contains valid data */ BH_Dirty, /* Is dirty */ BH_Lock, /* Is locked */ BH_Req, /* Has been submitted for I/O */ BH_Mapped, /* Has a disk mapping */ BH_New, /* Disk mapping was newly created by get_block */ BH_Async_Read, /* Is under end_buffer_async_read I/O */ BH_Async_Write, /* Is under end_buffer_async_write I/O */ BH_Delay, /* Buffer is not yet allocated on disk */ BH_Boundary, /* Block is followed by a discontiguity */ BH_Write_EIO, /* I/O error on write */ BH_Unwritten, /* Buffer is allocated on disk but not written */ BH_Quiet, /* Buffer Error Prinks to be quiet */ BH_Meta, /* Buffer contains metadata */ BH_Prio, /* Buffer should be submitted with REQ_PRIO */ BH_Defer_Completion, /* Defer AIO completion to workqueue */ BH_PrivateStart,/* not a state bit, but the first bit available * for private allocation by other entities */ }; #define MAX_BUF_PER_PAGE (PAGE_SIZE / 512) struct page; struct buffer_head; struct address_space; typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate); /* * Historically, a buffer_head was used to map a single block * within a page, and of course as the unit of I/O through the * filesystem and block layers. Nowadays the basic I/O unit * is the bio, and buffer_heads are used for extracting block * mappings (via a get_block_t call), for tracking state within * a page (via a page_mapping) and for wrapping bio submission * for backward compatibility reasons (e.g. submit_bh). */ struct buffer_head { unsigned long b_state; /* buffer state bitmap (see above) */ struct buffer_head *b_this_page;/* circular list of page's buffers */ struct page *b_page; /* the page this bh is mapped to */ sector_t b_blocknr; /* start block number */ size_t b_size; /* size of mapping */ char *b_data; /* pointer to data within the page */ struct block_device *b_bdev; bh_end_io_t *b_end_io; /* I/O completion */ void *b_private; /* reserved for b_end_io */ struct list_head b_assoc_buffers; /* associated with another mapping */ struct address_space *b_assoc_map; /* mapping this buffer is associated with */ atomic_t b_count; /* users using this buffer_head */ spinlock_t b_uptodate_lock; /* Used by the first bh in a page, to * serialise IO completion of other * buffers in the page */ }; /* * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() * and buffer_foo() functions. * To avoid reset buffer flags that are already set, because that causes * a costly cache line transition, check the flag first. */ #define BUFFER_FNS(bit, name) \ static __always_inline void set_buffer_##name(struct buffer_head *bh) \ { \ if (!test_bit(BH_##bit, &(bh)->b_state)) \ set_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline void clear_buffer_##name(struct buffer_head *bh) \ { \ clear_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline int buffer_##name(const struct buffer_head *bh) \ { \ return test_bit(BH_##bit, &(bh)->b_state); \ } /* * test_set_buffer_foo() and test_clear_buffer_foo() */ #define TAS_BUFFER_FNS(bit, name) \ static __always_inline int test_set_buffer_##name(struct buffer_head *bh) \ { \ return test_and_set_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \ { \ return test_and_clear_bit(BH_##bit, &(bh)->b_state); \ } \ /* * Emit the buffer bitops functions. Note that there are also functions * of the form "mark_buffer_foo()". These are higher-level functions which * do something in addition to setting a b_state bit. */ BUFFER_FNS(Dirty, dirty) TAS_BUFFER_FNS(Dirty, dirty) BUFFER_FNS(Lock, locked) BUFFER_FNS(Req, req) TAS_BUFFER_FNS(Req, req) BUFFER_FNS(Mapped, mapped) BUFFER_FNS(New, new) BUFFER_FNS(Async_Read, async_read) BUFFER_FNS(Async_Write, async_write) BUFFER_FNS(Delay, delay) BUFFER_FNS(Boundary, boundary) BUFFER_FNS(Write_EIO, write_io_error) BUFFER_FNS(Unwritten, unwritten) BUFFER_FNS(Meta, meta) BUFFER_FNS(Prio, prio) BUFFER_FNS(Defer_Completion, defer_completion) static __always_inline void set_buffer_uptodate(struct buffer_head *bh) { /* * If somebody else already set this uptodate, they will * have done the memory barrier, and a reader will thus * see *some* valid buffer state. * * Any other serialization (with IO errors or whatever that * might clear the bit) has to come from other state (eg BH_Lock). */ if (test_bit(BH_Uptodate, &bh->b_state)) return; /* * make it consistent with folio_mark_uptodate * pairs with smp_load_acquire in buffer_uptodate */ smp_mb__before_atomic(); set_bit(BH_Uptodate, &bh->b_state); } static __always_inline void clear_buffer_uptodate(struct buffer_head *bh) { clear_bit(BH_Uptodate, &bh->b_state); } static __always_inline int buffer_uptodate(const struct buffer_head *bh) { /* * make it consistent with folio_test_uptodate * pairs with smp_mb__before_atomic in set_buffer_uptodate */ return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0; } #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) /* If we *know* page->private refers to buffer_heads */ #define page_buffers(page) \ ({ \ BUG_ON(!PagePrivate(page)); \ ((struct buffer_head *)page_private(page)); \ }) #define page_has_buffers(page) PagePrivate(page) void buffer_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback); /* * Declarations */ void mark_buffer_dirty(struct buffer_head *bh); void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); int try_to_free_buffers(struct page *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); void end_buffer_write_sync(struct buffer_head *bh, int uptodate); void end_buffer_async_write(struct buffer_head *bh, int uptodate); /* Things to do with buffers at mapping->private_list */ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode); int inode_has_buffers(struct inode *); void invalidate_inode_buffers(struct inode *); int remove_inode_buffers(struct inode *inode); int sync_mapping_buffers(struct address_space *mapping); void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len); static inline void clean_bdev_bh_alias(struct buffer_head *bh) { clean_bdev_aliases(bh->b_bdev, bh->b_blocknr, 1); } void mark_buffer_async_write(struct buffer_head *bh); void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, unsigned size); struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp); void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, gfp_t gfp); struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); void ll_rw_block(int, int, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, int op_flags); void write_dirty_buffer(struct buffer_head *bh, int op_flags); int submit_bh(int, int, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int bh_submit_read(struct buffer_head *bh); extern int buffer_heads_over_limit; /* * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ void block_invalidatepage(struct page *page, unsigned int offset, unsigned int length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); int block_read_full_page(struct page*, get_block_t*); int block_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); int generic_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); /* Convert errno to return value from ->page_mkwrite() call */ static inline vm_fault_t block_page_mkwrite_return(int err) { if (err == 0) return VM_FAULT_LOCKED; if (err == -EFAULT || err == -EAGAIN) return VM_FAULT_NOPAGE; if (err == -ENOMEM) return VM_FAULT_OOM; /* -ENOSPC, -EDQUOT, -EIO ... */ return VM_FAULT_SIGBUS; } sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); int nobh_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); int nobh_truncate_page(struct address_space *, loff_t, get_block_t *); int nobh_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc); void buffer_init(void); /* * inline definitions */ static inline void get_bh(struct buffer_head *bh) { atomic_inc(&bh->b_count); } static inline void put_bh(struct buffer_head *bh) { smp_mb__before_atomic(); atomic_dec(&bh->b_count); } static inline void brelse(struct buffer_head *bh) { if (bh) __brelse(bh); } static inline void bforget(struct buffer_head *bh) { if (bh) __bforget(bh); } static inline struct buffer_head * sb_bread(struct super_block *sb, sector_t block) { return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } static inline struct buffer_head * sb_bread_unmovable(struct super_block *sb, sector_t block) { return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0); } static inline void sb_breadahead(struct super_block *sb, sector_t block) { __breadahead(sb->s_bdev, block, sb->s_blocksize); } static inline void sb_breadahead_unmovable(struct super_block *sb, sector_t block) { __breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0); } static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } static inline struct buffer_head * sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp) { return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp); } static inline struct buffer_head * sb_find_get_block(struct super_block *sb, sector_t block) { return __find_get_block(sb->s_bdev, block, sb->s_blocksize); } static inline void map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block) { set_buffer_mapped(bh); bh->b_bdev = sb->s_bdev; bh->b_blocknr = block; bh->b_size = sb->s_blocksize; } static inline void wait_on_buffer(struct buffer_head *bh) { might_sleep(); if (buffer_locked(bh)) __wait_on_buffer(bh); } static inline int trylock_buffer(struct buffer_head *bh) { return likely(!test_and_set_bit_lock(BH_Lock, &bh->b_state)); } static inline void lock_buffer(struct buffer_head *bh) { might_sleep(); if (!trylock_buffer(bh)) __lock_buffer(bh); } static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, sector_t block, unsigned size) { return __getblk_gfp(bdev, block, size, 0); } static inline struct buffer_head *__getblk(struct block_device *bdev, sector_t block, unsigned size) { return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); } /** * __bread() - reads a specified block and returns the bh * @bdev: the block_device to read from * @block: number of block * @size: size (in bytes) to read * * Reads a specified block, and returns buffer head that contains it. * The page cache is allocated from movable area so that it can be migrated. * It returns NULL if the block was unreadable. */ static inline struct buffer_head * __bread(struct block_device *bdev, sector_t block, unsigned size) { return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } extern int __set_page_dirty_buffers(struct page *page); #else /* CONFIG_BLOCK */ static inline void buffer_init(void) {} static inline int try_to_free_buffers(struct page *page) { return 1; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } #define buffer_heads_over_limit 0 #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_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 /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #include <asm/thread_info.h> #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifdef CONFIG_HARDENED_USERCOPY extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); static __always_inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { } #endif /* CONFIG_HARDENED_USERCOPY */ extern void __compiletime_error("copy source size is too small") __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); static inline void copy_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __compiletime_object_size(addr); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); else if (is_source) __bad_copy_from(); else __bad_copy_to(); return false; } if (WARN_ON_ONCE(bytes > INT_MAX)) return false; check_object_size(addr, bytes, is_source); return true; } #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FUTEX_H #define _ASM_X86_FUTEX_H #ifdef __KERNEL__ #include <linux/futex.h> #include <linux/uaccess.h> #include <asm/asm.h> #include <asm/errno.h> #include <asm/processor.h> #include <asm/smap.h> #define unsafe_atomic_op1(insn, oval, uaddr, oparg, label) \ do { \ int oldval = 0, ret; \ asm volatile("1:\t" insn "\n" \ "2:\n" \ "\t.section .fixup,\"ax\"\n" \ "3:\tmov\t%3, %1\n" \ "\tjmp\t2b\n" \ "\t.previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : "=r" (oldval), "=r" (ret), "+m" (*uaddr) \ : "i" (-EFAULT), "0" (oparg), "1" (0)); \ if (ret) \ goto label; \ *oval = oldval; \ } while(0) #define unsafe_atomic_op2(insn, oval, uaddr, oparg, label) \ do { \ int oldval = 0, ret, tem; \ asm volatile("1:\tmovl %2, %0\n" \ "2:\tmovl\t%0, %3\n" \ "\t" insn "\n" \ "3:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \ "\tjnz\t2b\n" \ "4:\n" \ "\t.section .fixup,\"ax\"\n" \ "5:\tmov\t%5, %1\n" \ "\tjmp\t4b\n" \ "\t.previous\n" \ _ASM_EXTABLE_UA(1b, 5b) \ _ASM_EXTABLE_UA(3b, 5b) \ : "=&a" (oldval), "=&r" (ret), \ "+m" (*uaddr), "=&r" (tem) \ : "r" (oparg), "i" (-EFAULT), "1" (0)); \ if (ret) \ goto label; \ *oval = oldval; \ } while(0) static __always_inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { if (!user_access_begin(uaddr, sizeof(u32))) return -EFAULT; switch (op) { case FUTEX_OP_SET: unsafe_atomic_op1("xchgl %0, %2", oval, uaddr, oparg, Efault); break; case FUTEX_OP_ADD: unsafe_atomic_op1(LOCK_PREFIX "xaddl %0, %2", oval, uaddr, oparg, Efault); break; case FUTEX_OP_OR: unsafe_atomic_op2("orl %4, %3", oval, uaddr, oparg, Efault); break; case FUTEX_OP_ANDN: unsafe_atomic_op2("andl %4, %3", oval, uaddr, ~oparg, Efault); break; case FUTEX_OP_XOR: unsafe_atomic_op2("xorl %4, %3", oval, uaddr, oparg, Efault); break; default: user_access_end(); return -ENOSYS; } user_access_end(); return 0; Efault: user_access_end(); return -EFAULT; } static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { int ret = 0; if (!user_access_begin(uaddr, sizeof(u32))) return -EFAULT; asm volatile("\n" "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" "2:\n" "\t.section .fixup, \"ax\"\n" "3:\tmov %3, %0\n" "\tjmp 2b\n" "\t.previous\n" _ASM_EXTABLE_UA(1b, 3b) : "+r" (ret), "=a" (oldval), "+m" (*uaddr) : "i" (-EFAULT), "r" (newval), "1" (oldval) : "memory" ); user_access_end(); *uval = oldval; return ret; } #endif #endif /* _ASM_X86_FUTEX_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 /* SPDX-License-Identifier: GPL-2.0 OR MIT */ /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #ifndef _CRYPTO_BLAKE2S_H #define _CRYPTO_BLAKE2S_H #include <linux/bug.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> enum blake2s_lengths { BLAKE2S_BLOCK_SIZE = 64, BLAKE2S_HASH_SIZE = 32, BLAKE2S_KEY_SIZE = 32, BLAKE2S_128_HASH_SIZE = 16, BLAKE2S_160_HASH_SIZE = 20, BLAKE2S_224_HASH_SIZE = 28, BLAKE2S_256_HASH_SIZE = 32, }; struct blake2s_state { /* 'h', 't', and 'f' are used in assembly code, so keep them as-is. */ u32 h[8]; u32 t[2]; u32 f[2]; u8 buf[BLAKE2S_BLOCK_SIZE]; unsigned int buflen; unsigned int outlen; }; enum blake2s_iv { BLAKE2S_IV0 = 0x6A09E667UL, BLAKE2S_IV1 = 0xBB67AE85UL, BLAKE2S_IV2 = 0x3C6EF372UL, BLAKE2S_IV3 = 0xA54FF53AUL, BLAKE2S_IV4 = 0x510E527FUL, BLAKE2S_IV5 = 0x9B05688CUL, BLAKE2S_IV6 = 0x1F83D9ABUL, BLAKE2S_IV7 = 0x5BE0CD19UL, }; static inline void __blake2s_init(struct blake2s_state *state, size_t outlen, const void *key, size_t keylen) { state->h[0] = BLAKE2S_IV0 ^ (0x01010000 | keylen << 8 | outlen); state->h[1] = BLAKE2S_IV1; state->h[2] = BLAKE2S_IV2; state->h[3] = BLAKE2S_IV3; state->h[4] = BLAKE2S_IV4; state->h[5] = BLAKE2S_IV5; state->h[6] = BLAKE2S_IV6; state->h[7] = BLAKE2S_IV7; state->t[0] = 0; state->t[1] = 0; state->f[0] = 0; state->f[1] = 0; state->buflen = 0; state->outlen = outlen; if (keylen) { memcpy(state->buf, key, keylen); memset(&state->buf[keylen], 0, BLAKE2S_BLOCK_SIZE - keylen); state->buflen = BLAKE2S_BLOCK_SIZE; } } static inline void blake2s_init(struct blake2s_state *state, const size_t outlen) { __blake2s_init(state, outlen, NULL, 0); } static inline void blake2s_init_key(struct blake2s_state *state, const size_t outlen, const void *key, const size_t keylen) { WARN_ON(IS_ENABLED(DEBUG) && (!outlen || outlen > BLAKE2S_HASH_SIZE || !key || !keylen || keylen > BLAKE2S_KEY_SIZE)); __blake2s_init(state, outlen, key, keylen); } void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen); void blake2s_final(struct blake2s_state *state, u8 *out); static inline void blake2s(u8 *out, const u8 *in, const u8 *key, const size_t outlen, const size_t inlen, const size_t keylen) { struct blake2s_state state; WARN_ON(IS_ENABLED(DEBUG) && ((!in && inlen > 0) || !out || !outlen || outlen > BLAKE2S_HASH_SIZE || keylen > BLAKE2S_KEY_SIZE || (!key && keylen))); __blake2s_init(&state, outlen, key, keylen); blake2s_update(&state, in, inlen); blake2s_final(&state, out); } #endif /* _CRYPTO_BLAKE2S_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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Network device features. */ #ifndef _LINUX_NETDEV_FEATURES_H #define _LINUX_NETDEV_FEATURES_H #include <linux/types.h> #include <linux/bitops.h> #include <asm/byteorder.h> typedef u64 netdev_features_t; enum { NETIF_F_SG_BIT, /* Scatter/gather IO. */ NETIF_F_IP_CSUM_BIT, /* Can checksum TCP/UDP over IPv4. */ __UNUSED_NETIF_F_1, NETIF_F_HW_CSUM_BIT, /* Can checksum all the packets. */ NETIF_F_IPV6_CSUM_BIT, /* Can checksum TCP/UDP over IPV6 */ NETIF_F_HIGHDMA_BIT, /* Can DMA to high memory. */ NETIF_F_FRAGLIST_BIT, /* Scatter/gather IO. */ NETIF_F_HW_VLAN_CTAG_TX_BIT, /* Transmit VLAN CTAG HW acceleration */ NETIF_F_HW_VLAN_CTAG_RX_BIT, /* Receive VLAN CTAG HW acceleration */ NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */ NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */ NETIF_F_GSO_BIT, /* Enable software GSO. */ NETIF_F_LLTX_BIT, /* LockLess TX - deprecated. Please */ /* do not use LLTX in new drivers */ NETIF_F_NETNS_LOCAL_BIT, /* Does not change network namespaces */ NETIF_F_GRO_BIT, /* Generic receive offload */ NETIF_F_LRO_BIT, /* large receive offload */ /**/NETIF_F_GSO_SHIFT, /* keep the order of SKB_GSO_* bits */ NETIF_F_TSO_BIT /* ... TCPv4 segmentation */ = NETIF_F_GSO_SHIFT, NETIF_F_GSO_ROBUST_BIT, /* ... ->SKB_GSO_DODGY */ NETIF_F_TSO_ECN_BIT, /* ... TCP ECN support */ NETIF_F_TSO_MANGLEID_BIT, /* ... IPV4 ID mangling allowed */ NETIF_F_TSO6_BIT, /* ... TCPv6 segmentation */ NETIF_F_FSO_BIT, /* ... FCoE segmentation */ NETIF_F_GSO_GRE_BIT, /* ... GRE with TSO */ NETIF_F_GSO_GRE_CSUM_BIT, /* ... GRE with csum with TSO */ NETIF_F_GSO_IPXIP4_BIT, /* ... IP4 or IP6 over IP4 with TSO */ NETIF_F_GSO_IPXIP6_BIT, /* ... IP4 or IP6 over IP6 with TSO */ NETIF_F_GSO_UDP_TUNNEL_BIT, /* ... UDP TUNNEL with TSO */ NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */ NETIF_F_GSO_PARTIAL_BIT, /* ... Only segment inner-most L4 * in hardware and all other * headers in software. */ NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */ NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */ NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */ NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */ NETIF_F_GSO_UDP_L4_BIT, /* ... UDP payload GSO (not UFO) */ NETIF_F_GSO_FRAGLIST_BIT, /* ... Fraglist GSO */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ NETIF_F_GSO_FRAGLIST_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ NETIF_F_FCOE_MTU_BIT, /* Supports max FCoE MTU, 2158 bytes*/ NETIF_F_NTUPLE_BIT, /* N-tuple filters supported */ NETIF_F_RXHASH_BIT, /* Receive hashing offload */ NETIF_F_RXCSUM_BIT, /* Receive checksumming offload */ NETIF_F_NOCACHE_COPY_BIT, /* Use no-cache copyfromuser */ NETIF_F_LOOPBACK_BIT, /* Enable loopback */ NETIF_F_RXFCS_BIT, /* Append FCS to skb pkt data */ NETIF_F_RXALL_BIT, /* Receive errored frames too */ NETIF_F_HW_VLAN_STAG_TX_BIT, /* Transmit VLAN STAG HW acceleration */ NETIF_F_HW_VLAN_STAG_RX_BIT, /* Receive VLAN STAG HW acceleration */ NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */ NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */ NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */ NETIF_F_HW_TLS_TX_BIT, /* Hardware TLS TX offload */ NETIF_F_HW_TLS_RX_BIT, /* Hardware TLS RX offload */ NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */ NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */ NETIF_F_GRO_FRAGLIST_BIT, /* Fraglist GRO */ NETIF_F_HW_MACSEC_BIT, /* Offload MACsec operations */ /* * Add your fresh new feature above and remember to update * netdev_features_strings[] in net/ethtool/common.c and maybe * some feature mask #defines below. Please also describe it * in Documentation/networking/netdev-features.rst. */ /**/NETDEV_FEATURE_COUNT }; /* copy'n'paste compression ;) */ #define __NETIF_F_BIT(bit) ((netdev_features_t)1 << (bit)) #define __NETIF_F(name) __NETIF_F_BIT(NETIF_F_##name##_BIT) #define NETIF_F_FCOE_CRC __NETIF_F(FCOE_CRC) #define NETIF_F_FCOE_MTU __NETIF_F(FCOE_MTU) #define NETIF_F_FRAGLIST __NETIF_F(FRAGLIST) #define NETIF_F_FSO __NETIF_F(FSO) #define NETIF_F_GRO __NETIF_F(GRO) #define NETIF_F_GRO_HW __NETIF_F(GRO_HW) #define NETIF_F_GSO __NETIF_F(GSO) #define NETIF_F_GSO_ROBUST __NETIF_F(GSO_ROBUST) #define NETIF_F_HIGHDMA __NETIF_F(HIGHDMA) #define NETIF_F_HW_CSUM __NETIF_F(HW_CSUM) #define NETIF_F_HW_VLAN_CTAG_FILTER __NETIF_F(HW_VLAN_CTAG_FILTER) #define NETIF_F_HW_VLAN_CTAG_RX __NETIF_F(HW_VLAN_CTAG_RX) #define NETIF_F_HW_VLAN_CTAG_TX __NETIF_F(HW_VLAN_CTAG_TX) #define NETIF_F_IP_CSUM __NETIF_F(IP_CSUM) #define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM) #define NETIF_F_LLTX __NETIF_F(LLTX) #define NETIF_F_LOOPBACK __NETIF_F(LOOPBACK) #define NETIF_F_LRO __NETIF_F(LRO) #define NETIF_F_NETNS_LOCAL __NETIF_F(NETNS_LOCAL) #define NETIF_F_NOCACHE_COPY __NETIF_F(NOCACHE_COPY) #define NETIF_F_NTUPLE __NETIF_F(NTUPLE) #define NETIF_F_RXCSUM __NETIF_F(RXCSUM) #define NETIF_F_RXHASH __NETIF_F(RXHASH) #define NETIF_F_SCTP_CRC __NETIF_F(SCTP_CRC) #define NETIF_F_SG __NETIF_F(SG) #define NETIF_F_TSO6 __NETIF_F(TSO6) #define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN) #define NETIF_F_TSO __NETIF_F(TSO) #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) #define NETIF_F_GSO_GRE __NETIF_F(GSO_GRE) #define NETIF_F_GSO_GRE_CSUM __NETIF_F(GSO_GRE_CSUM) #define NETIF_F_GSO_IPXIP4 __NETIF_F(GSO_IPXIP4) #define NETIF_F_GSO_IPXIP6 __NETIF_F(GSO_IPXIP6) #define NETIF_F_GSO_UDP_TUNNEL __NETIF_F(GSO_UDP_TUNNEL) #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM) #define NETIF_F_TSO_MANGLEID __NETIF_F(TSO_MANGLEID) #define NETIF_F_GSO_PARTIAL __NETIF_F(GSO_PARTIAL) #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM) #define NETIF_F_GSO_SCTP __NETIF_F(GSO_SCTP) #define NETIF_F_GSO_ESP __NETIF_F(GSO_ESP) #define NETIF_F_GSO_UDP __NETIF_F(GSO_UDP) #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) #define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_HW_TC __NETIF_F(HW_TC) #define NETIF_F_HW_ESP __NETIF_F(HW_ESP) #define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM) #define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT) #define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD) #define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4) #define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX) #define NETIF_F_HW_TLS_RX __NETIF_F(HW_TLS_RX) #define NETIF_F_GRO_FRAGLIST __NETIF_F(GRO_FRAGLIST) #define NETIF_F_GSO_FRAGLIST __NETIF_F(GSO_FRAGLIST) #define NETIF_F_HW_MACSEC __NETIF_F(HW_MACSEC) /* Finds the next feature with the highest number of the range of start-1 till 0. */ static inline int find_next_netdev_feature(u64 feature, unsigned long start) { /* like BITMAP_LAST_WORD_MASK() for u64 * this sets the most significant 64 - start to 0. */ feature &= ~0ULL >> (-start & ((sizeof(feature) * 8) - 1)); return fls64(feature) - 1; } /* This goes for the MSB to the LSB through the set feature bits, * mask_addr should be a u64 and bit an int */ #define for_each_netdev_feature(mask_addr, bit) \ for ((bit) = find_next_netdev_feature((mask_addr), \ NETDEV_FEATURE_COUNT); \ (bit) >= 0; \ (bit) = find_next_netdev_feature((mask_addr), (bit))) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ #define NETIF_F_NEVER_CHANGE (NETIF_F_VLAN_CHALLENGED | \ NETIF_F_LLTX | NETIF_F_NETNS_LOCAL) /* remember that ((t)1 << t_BITS) is undefined in C99 */ #define NETIF_F_ETHTOOL_BITS ((__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) | \ (__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) - 1)) & \ ~NETIF_F_NEVER_CHANGE) /* Segmentation offload feature mask */ #define NETIF_F_GSO_MASK (__NETIF_F_BIT(NETIF_F_GSO_LAST + 1) - \ __NETIF_F_BIT(NETIF_F_GSO_SHIFT)) /* List of IP checksum features. Note that NETIF_F_HW_CSUM should not be * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set-- * this would be contradictory */ #define NETIF_F_CSUM_MASK (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \ NETIF_F_HW_CSUM) #define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | \ NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID) #define NETIF_F_ALL_FCOE (NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \ NETIF_F_FSO) /* List of features with software fallbacks. */ #define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | \ NETIF_F_GSO_SCTP) /* * If one device supports one of these features, then enable them * for all in netdev_increment_features. */ #define NETIF_F_ONE_FOR_ALL (NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \ NETIF_F_SG | NETIF_F_HIGHDMA | \ NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED) /* * If one device doesn't support one of these features, then disable it * for all in netdev_increment_features. */ #define NETIF_F_ALL_FOR_ALL (NETIF_F_NOCACHE_COPY | NETIF_F_FSO) /* * If upper/master device has these features disabled, they must be disabled * on all lower/slave devices as well. */ #define NETIF_F_UPPER_DISABLES NETIF_F_LRO /* changeable features with no special hardware requirements */ #define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) /* Changeable features with no special hardware requirements that defaults to off. */ #define NETIF_F_SOFT_FEATURES_OFF NETIF_F_GRO_FRAGLIST #define NETIF_F_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \ NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_CTAG_TX | \ NETIF_F_HW_VLAN_STAG_FILTER | \ NETIF_F_HW_VLAN_STAG_RX | \ NETIF_F_HW_VLAN_STAG_TX) #define NETIF_F_GSO_ENCAP_ALL (NETIF_F_GSO_GRE | \ NETIF_F_GSO_GRE_CSUM | \ NETIF_F_GSO_IPXIP4 | \ NETIF_F_GSO_IPXIP6 | \ NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) #endif /* _LINUX_NETDEV_FEATURES_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 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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the TCP module. * * Version: @(#)tcp.h 1.0.5 05/23/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _TCP_H #define _TCP_H #define FASTRETRANS_DEBUG 1 #include <linux/list.h> #include <linux/tcp.h> #include <linux/bug.h> #include <linux/slab.h> #include <linux/cache.h> #include <linux/percpu.h> #include <linux/skbuff.h> #include <linux/kref.h> #include <linux/ktime.h> #include <linux/indirect_call_wrapper.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> #include <net/inet_hashtables.h> #include <net/checksum.h> #include <net/request_sock.h> #include <net/sock_reuseport.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> #include <net/tcp_states.h> #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> #include <linux/bpf-cgroup.h> #include <linux/siphash.h> extern struct inet_hashinfo tcp_hashinfo; DECLARE_PER_CPU(unsigned int, tcp_orphan_count); int tcp_orphan_count_sum(void); void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) #define MAX_TCP_OPTION_SPACE 40 #define TCP_MIN_SND_MSS 48 #define TCP_MIN_GSO_SIZE (TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE) /* * Never offer a window over 32767 without using window scaling. Some * poor stacks do signed 16bit maths! */ #define MAX_TCP_WINDOW 32767U /* Minimal accepted MSS. It is (60+60+8) - (20+20). */ #define TCP_MIN_MSS 88U /* The initial MTU to use for probing */ #define TCP_BASE_MSS 1024 /* probing interval, default to 10 minutes as per RFC4821 */ #define TCP_PROBE_INTERVAL 600 /* Specify interval when tcp mtu probing will stop */ #define TCP_PROBE_THRESHOLD 8 /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH 3 /* Maximal number of ACKs sent quickly to accelerate slow-start. */ #define TCP_MAX_QUICKACKS 16U /* Maximal number of window scale according to RFC1323 */ #define TCP_MAX_WSCALE 14U /* urg_data states */ #define TCP_URG_VALID 0x0100 #define TCP_URG_NOTYET 0x0200 #define TCP_URG_READ 0x0400 #define TCP_RETR1 3 /* * This is how many retries it does before it * tries to figure out if the gateway is * down. Minimal RFC value is 3; it corresponds * to ~3sec-8min depending on RTO. */ #define TCP_RETR2 15 /* * This should take at least * 90 minutes to time out. * RFC1122 says that the limit is 100 sec. * 15 is ~13-30min depending on RTO. */ #define TCP_SYN_RETRIES 6 /* This is how many retries are done * when active opening a connection. * RFC1122 says the minimum retry MUST * be at least 180secs. Nevertheless * this value is corresponding to * 63secs of retransmission with the * current initial RTO. */ #define TCP_SYNACK_RETRIES 5 /* This is how may retries are done * when passive opening a connection. * This is corresponding to 31secs of * retransmission with the current * initial RTO. */ #define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT * state, about 60 seconds */ #define TCP_FIN_TIMEOUT TCP_TIMEWAIT_LEN /* BSD style FIN_WAIT2 deadlock breaker. * It used to be 3min, new value is 60sec, * to combine FIN-WAIT-2 timeout with * TIME-WAIT timer. */ #define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */ #define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */ #if HZ >= 100 #define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */ #define TCP_ATO_MIN ((unsigned)(HZ/25)) #else #define TCP_DELACK_MIN 4U #define TCP_ATO_MIN 4U #endif #define TCP_RTO_MAX ((unsigned)(120*HZ)) #define TCP_RTO_MIN ((unsigned)(HZ/5)) #define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now * used as a fallback RTO for the * initial data transmission if no * valid RTT sample has been acquired, * most likely due to retrans in 3WHS. */ #define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes * for local resources. */ #define TCP_KEEPALIVE_TIME (120*60*HZ) /* two hours */ #define TCP_KEEPALIVE_PROBES 9 /* Max of 9 keepalive probes */ #define TCP_KEEPALIVE_INTVL (75*HZ) #define MAX_TCP_KEEPIDLE 32767 #define MAX_TCP_KEEPINTVL 32767 #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 #define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */ #define TCP_PAWS_24DAYS (60 * 60 * 24 * 24) #define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated * after this time. It should be equal * (or greater than) TCP_TIMEWAIT_LEN * to provide reliability equal to one * provided by timewait state. */ #define TCP_PAWS_WINDOW 1 /* Replay window for per-host * timestamps. It must be less than * minimal timewait lifetime. */ /* * TCP option */ #define TCPOPT_NOP 1 /* Padding */ #define TCPOPT_EOL 0 /* End of options */ #define TCPOPT_MSS 2 /* Segment size negotiating */ #define TCPOPT_WINDOW 3 /* Window scaling */ #define TCPOPT_SACK_PERM 4 /* SACK Permitted */ #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ #define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */ #define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */ #define TCPOPT_EXP 254 /* Experimental */ /* Magic number to be after the option value for sharing TCP * experimental options. See draft-ietf-tcpm-experimental-options-00.txt */ #define TCPOPT_FASTOPEN_MAGIC 0xF989 #define TCPOPT_SMC_MAGIC 0xE2D4C3D9 /* * TCP option lengths */ #define TCPOLEN_MSS 4 #define TCPOLEN_WINDOW 3 #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 #define TCPOLEN_FASTOPEN_BASE 2 #define TCPOLEN_EXP_FASTOPEN_BASE 4 #define TCPOLEN_EXP_SMC_BASE 6 /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED 12 #define TCPOLEN_WSCALE_ALIGNED 4 #define TCPOLEN_SACKPERM_ALIGNED 4 #define TCPOLEN_SACK_BASE 2 #define TCPOLEN_SACK_BASE_ALIGNED 4 #define TCPOLEN_SACK_PERBLOCK 8 #define TCPOLEN_MD5SIG_ALIGNED 20 #define TCPOLEN_MSS_ALIGNED 4 #define TCPOLEN_EXP_SMC_BASE_ALIGNED 8 /* Flags in tp->nonagle */ #define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */ #define TCP_NAGLE_CORK 2 /* Socket is corked */ #define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */ /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ /* TCP initial congestion window as per rfc6928 */ #define TCP_INIT_CWND 10 /* Bit Flags for sysctl_tcp_fastopen */ #define TFO_CLIENT_ENABLE 1 #define TFO_SERVER_ENABLE 2 #define TFO_CLIENT_NO_COOKIE 4 /* Data in SYN w/o cookie option */ /* Accept SYN data w/o any cookie option */ #define TFO_SERVER_COOKIE_NOT_REQD 0x200 /* Force enable TFO on all listeners, i.e., not requiring the * TCP_FASTOPEN socket option. */ #define TFO_SERVER_WO_SOCKOPT1 0x400 /* sysctl variables for tcp */ extern int sysctl_tcp_max_orphans; extern long sysctl_tcp_mem[3]; #define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */ #define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */ #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) { if (mem_cgroup_sockets_enabled && sk->sk_memcg && mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; return READ_ONCE(tcp_memory_pressure); } /* * The next routines deal with comparing 32 bit unsigned ints * and worry about wraparound (automatic with unsigned arithmetic). */ static inline bool before(__u32 seq1, __u32 seq2) { return (__s32)(seq1-seq2) < 0; } #define after(seq2, seq1) before(seq1, seq2) /* is s2<=s1<=s3 ? */ static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3) { return seq3 - seq2 >= seq1 - seq2; } static inline bool tcp_out_of_memory(struct sock *sk) { if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) return true; return false; } void sk_forced_mem_schedule(struct sock *sk, int size); bool tcp_check_oom(struct sock *sk, int shift); extern struct proto tcp_prot; #define TCP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define __TCP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field) #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val) void tcp_tasklet_init(void); int tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal); void tcp_release_cb(struct sock *sk); void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.quick) { if (pkts >= icsk->icsk_ack.quick) { icsk->icsk_ack.quick = 0; /* Leaving quickack mode we deflate ATO. */ icsk->icsk_ack.ato = TCP_ATO_MIN; } else icsk->icsk_ack.quick -= pkts; } } #define TCP_ECN_OK 1 #define TCP_ECN_QUEUE_CWR 2 #define TCP_ECN_DEMAND_CWR 4 #define TCP_ECN_SEEN 8 enum tcp_tw_status { TCP_TW_SUCCESS = 0, TCP_TW_RST = 1, TCP_TW_ACK = 2, TCP_TW_SYN = 3 }; enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, bool fastopen, bool *lost_race); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag); void tcp_clear_retrans(struct tcp_sock *tp); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); #endif void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); /* * BPF SKB-less helpers */ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th); /* * TCP v4 functions exported for the inet6 API */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); void tcp_req_err(struct sock *sk, u32 seq, bool abort); void tcp_ld_RTO_revert(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); enum tcp_synack_type { TCP_SYNACK_NORMAL, TCP_SYNACK_FASTOPEN, TCP_SYNACK_COOKIE, }; struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size); void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, u32 tsoff); int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES /* Syncookies use a monotonic timer which increments every 60 seconds. * This counter is used both as a hash input and partially encoded into * the cookie value. A cookie is only validated further if the delta * between the current counter value and the encoded one is less than this, * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if * the counter advances immediately after a cookie is generated). */ #define MAX_SYNCOOKIE_AGE 2 #define TCP_SYNCOOKIE_PERIOD (60 * HZ) #define TCP_SYNCOOKIE_VALID (MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD) /* syncookies: remember time of last synqueue overflow * But do not dirty this field too often (once per second is enough) * It is racy as we do not hold a lock, but race is very minor. */ static inline void tcp_synq_overflow(const struct sock *sk) { unsigned int last_overflow; unsigned int now = jiffies; if (sk->sk_reuseport) { struct sock_reuseport *reuse; reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); if (!time_between32(now, last_overflow, last_overflow + HZ)) WRITE_ONCE(reuse->synq_overflow_ts, now); return; } } last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); if (!time_between32(now, last_overflow, last_overflow + HZ)) WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now); } /* syncookies: no recent synqueue overflow on this listening socket? */ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) { unsigned int last_overflow; unsigned int now = jiffies; if (sk->sk_reuseport) { struct sock_reuseport *reuse; reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); return !time_between32(now, last_overflow - HZ, last_overflow + TCP_SYNCOOKIE_VALID); } } last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); /* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID, * then we're under synflood. However, we have to use * 'last_overflow - HZ' as lower bound. That's because a concurrent * tcp_synq_overflow() could update .ts_recent_stamp after we read * jiffies but before we store .ts_recent_stamp into last_overflow, * which could lead to rejecting a valid syncookie. */ return !time_between32(now, last_overflow - HZ, last_overflow + TCP_SYNCOOKIE_VALID); } static inline u32 tcp_cookie_time(void) { u64 val = get_jiffies_64(); do_div(val, TCP_SYNCOOKIE_PERIOD); return val; } u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); u64 cookie_init_timestamp(struct request_sock *req, u64 now); bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *opt); bool cookie_ecn_ok(const struct tcp_options_received *opt, const struct net *net, const struct dst_entry *dst); /* From net/ipv6/syncookies.c */ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); void tcp_retransmit_timer(struct sock *sk); void tcp_xmit_retransmit_queue(struct sock *); void tcp_simple_retransmit(struct sock *); void tcp_enter_recovery(struct sock *sk, bool ece_ack); int tcp_trim_head(struct sock *, struct sk_buff *, u32); enum tcp_queue { TCP_FRAG_IN_WRITE_QUEUE, TCP_FRAG_IN_RTX_QUEUE, }; int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp); void tcp_send_probe0(struct sock *); void tcp_send_partial(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto); void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb); /* tcp_input.c */ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) { if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1) __sock_put(sk); if (hrtimer_try_to_cancel(&tcp_sk(sk)->compressed_ack_timer) == 1) __sock_put(sk); inet_csk_clear_xmit_timers(sk); } unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); unsigned int tcp_current_mss(struct sock *sk); u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when); /* Bound MSS / TSO packet size with the half of the window */ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) { int cutoff; /* When peer uses tiny windows, there is no use in packetizing * to sub-MSS pieces for the sake of SWS or making sure there * are enough packets in the pipe for fast recovery. * * On the other hand, for extremely large MSS devices, handling * smaller than MSS windows in this way does make sense. */ if (tp->max_window > TCP_MSS_DEFAULT) cutoff = (tp->max_window >> 1); else cutoff = tp->max_window; if (cutoff && pktsize > cutoff) return max_t(int, cutoff, 68U - tp->tcp_header_len); else return pktsize; } /* tcp.c */ void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); void tcp_initialize_rcv_mss(struct sock *sk); int tcp_mtu_to_mss(struct sock *sk, int pmtu); int tcp_mss_to_mtu(struct sock *sk, int mss); void tcp_mtup_init(struct sock *sk); static inline void tcp_bound_rto(const struct sock *sk) { if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX) inet_csk(sk)->icsk_rto = TCP_RTO_MAX; } static inline u32 __tcp_set_rto(const struct tcp_sock *tp) { return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { /* mptcp hooks are only on the slow path */ if (sk_is_mptcp((struct sock *)tp)) return; tp->pred_flags = htonl((tp->tcp_header_len << 26) | ntohl(TCP_FLAG_ACK) | snd_wnd); } static inline void tcp_fast_path_on(struct tcp_sock *tp) { __tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale); } static inline void tcp_fast_path_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (RB_EMPTY_ROOT(&tp->out_of_order_queue) && tp->rcv_wnd && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && !tp->urg_data) tcp_fast_path_on(tp); } /* Compute the actual rto_min value */ static inline u32 tcp_rto_min(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); u32 rto_min = inet_csk(sk)->icsk_rto_min; if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); return rto_min; } static inline u32 tcp_rto_min_us(struct sock *sk) { return jiffies_to_usecs(tcp_rto_min(sk)); } static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) { return dst_metric_locked(dst, RTAX_CC_ALGO); } /* Minimum RTT in usec. ~0 means not available. */ static inline u32 tcp_min_rtt(const struct tcp_sock *tp) { return minmax_get(&tp->rtt_min); } /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. */ static inline u32 tcp_receive_window(const struct tcp_sock *tp) { s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt; if (win < 0) win = 0; return (u32) win; } /* Choose a new window, without checks for shrinking, and without * scaling applied to the result. The caller does these things * if necessary. This is a "raw" window selection. */ u32 __tcp_select_window(struct sock *sk); void tcp_send_window_probe(struct sock *sk); /* TCP uses 32bit jiffies to save some space. * Note that this is different from tcp_time_stamp, which * historically has been the same until linux-4.13. */ #define tcp_jiffies32 ((u32)jiffies) /* * Deliver a 32bit value for TCP timestamp option (RFC 7323) * It is no longer tied to jiffies, but to 1 ms clock. * Note: double check if you want to use tcp_jiffies32 instead of this. */ #define TCP_TS_HZ 1000 static inline u64 tcp_clock_ns(void) { return ktime_get_ns(); } static inline u64 tcp_clock_us(void) { return div_u64(tcp_clock_ns(), NSEC_PER_USEC); } /* This should only be used in contexts where tp->tcp_mstamp is up to date */ static inline u32 tcp_time_stamp(const struct tcp_sock *tp) { return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ); } /* Convert a nsec timestamp into TCP TSval timestamp (ms based currently) */ static inline u32 tcp_ns_to_ts(u64 ns) { return div_u64(ns, NSEC_PER_SEC / TCP_TS_HZ); } /* Could use tcp_clock_us() / 1000, but this version uses a single divide */ static inline u32 tcp_time_stamp_raw(void) { return tcp_ns_to_ts(tcp_clock_ns()); } void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) { return max_t(s64, t1 - t0, 0); } static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { return tcp_ns_to_ts(skb->skb_mstamp_ns); } /* provide the departure time in us unit */ static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) { return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } #define tcp_flag_byte(th) (((u_int8_t *)th)[13]) #define TCPHDR_FIN 0x01 #define TCPHDR_SYN 0x02 #define TCPHDR_RST 0x04 #define TCPHDR_PSH 0x08 #define TCPHDR_ACK 0x10 #define TCPHDR_URG 0x20 #define TCPHDR_ECE 0x40 #define TCPHDR_CWR 0x80 #define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) /* This is what the send packet queuing engine uses to pass * TCP per-packet control information to the transmission code. * We also store the host-order sequence numbers in here too. * This is 44 bytes if IPV6 is enabled. * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately. */ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { /* Note : tcp_tw_isn is used in input path only * (isn chosen by tcp_timewait_state_process()) * * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ __u32 tcp_tw_isn; struct { u16 tcp_gso_segs; u16 tcp_gso_size; }; }; __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ __u8 sacked; /* State flags for SACK. */ #define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */ #define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ #define TCPCB_LOST 0x04 /* SKB is lost */ #define TCPCB_TAGBITS 0x07 /* All tag bits */ #define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp_ns) */ #define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ TCPCB_REPAIRED) __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ unused:5; __u32 ack_seq; /* Sequence number ACK'd */ union { struct { /* There is space for up to 24 bytes */ __u32 in_flight:30,/* Bytes in flight at transmit */ is_app_limited:1, /* cwnd not fully used? */ unused:1; /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ u64 first_tx_mstamp; /* when we reached the "delivered" count */ u64 delivered_mstamp; } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; /* For incoming skbs */ struct { __u32 flags; struct sock *sk_redir; void *data_end; } bpf; }; }; #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) { TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); } static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS; } static inline struct sock *tcp_skb_bpf_redirect_fetch(struct sk_buff *skb) { return TCP_SKB_CB(skb)->bpf.sk_redir; } static inline void tcp_skb_bpf_redirect_clear(struct sk_buff *skb) { TCP_SKB_CB(skb)->bpf.sk_redir = NULL; } extern const struct inet_connection_sock_af_ops ipv4_specific; #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, * as TCP moves IP6CB into a different location in skb->cb[] */ static inline int tcp_v6_iif(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->header.h6.iif; } static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) { bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; } /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v6_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags)) return TCP_SKB_CB(skb)->header.h6.iif; #endif return 0; } extern const struct inet_connection_sock_af_ops ipv6_specific; INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb)); void tcp_v6_early_demux(struct sk_buff *skb); #endif /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags)) return TCP_SKB_CB(skb)->header.h4.iif; #endif return 0; } /* Due to TSO, an SKB can be composed of multiple actual * packets. To keep these tracked properly, we use this. */ static inline int tcp_skb_pcount(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->tcp_gso_segs; } static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs) { TCP_SKB_CB(skb)->tcp_gso_segs = segs; } static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs) { TCP_SKB_CB(skb)->tcp_gso_segs += segs; } /* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */ static inline int tcp_skb_mss(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->tcp_gso_size; } static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) { return likely(!TCP_SKB_CB(skb)->eor); } static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from)); } /* Events passed to congestion control interface */ enum tcp_ca_event { CA_EVENT_TX_START, /* first transmit when no packets in flight */ CA_EVENT_CWND_RESTART, /* congestion window restart */ CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */ CA_EVENT_LOSS, /* loss timeout */ CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */ CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */ }; /* Information about inbound ACK, passed to cong_ops->in_ack_event() */ enum tcp_ca_ack_event_flags { CA_ACK_SLOWPATH = (1 << 0), /* In slow path processing */ CA_ACK_WIN_UPDATE = (1 << 1), /* ACK updated window */ CA_ACK_ECE = (1 << 2), /* ECE bit is set on ack */ }; /* * Interface for adding new TCP congestion control handlers */ #define TCP_CA_NAME_MAX 16 #define TCP_CA_MAX 128 #define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX) #define TCP_CA_UNSPEC 0 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */ #define TCP_CONG_NON_RESTRICTED 0x1 /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN 0x2 #define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) union tcp_cc_info; struct ack_sample { u32 pkts_acked; s32 rtt_us; u32 in_flight; }; /* A rate sample measures the number of (original/retransmitted) data * packets delivered "delivered" over an interval of time "interval_us". * The tcp_rate.c code fills in the rate sample, and congestion * control modules that define a cong_control function to run at the end * of ACK processing can optionally chose to consult this sample when * setting cwnd and pacing rate. * A sample is invalid if "delivered" or "interval_us" is negative. */ struct rate_sample { u64 prior_mstamp; /* starting timestamp for interval */ u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ long interval_us; /* time for tp->delivered to incr "delivered" */ u32 snd_interval_us; /* snd interval for delivered packets */ u32 rcv_interval_us; /* rcv interval for delivered packets */ long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ }; struct tcp_congestion_ops { struct list_head list; u32 key; u32 flags; /* initialize private data (optional) */ void (*init)(struct sock *sk); /* cleanup private data (optional) */ void (*release)(struct sock *sk); /* return slow start threshold (required) */ u32 (*ssthresh)(struct sock *sk); /* do new cwnd calculation (required) */ void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked); /* call before changing ca_state (optional) */ void (*set_state)(struct sock *sk, u8 new_state); /* call when cwnd event occurs (optional) */ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); /* call when ack arrives (optional) */ void (*in_ack_event)(struct sock *sk, u32 flags); /* new value of cwnd after loss (required) */ u32 (*undo_cwnd)(struct sock *sk); /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); /* override sysctl_tcp_min_tso_segs */ u32 (*min_tso_segs)(struct sock *sk); /* returns the multiplier used in tcp_sndbuf_expand (optional) */ u32 (*sndbuf_expand)(struct sock *sk); /* call when packets are delivered to update cwnd and pacing rate, * after all the ca_state processing. (optional) */ void (*cong_control)(struct sock *sk, const struct rate_sample *rs); /* get info for inet_diag (optional) */ size_t (*get_info)(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info); char name[TCP_CA_NAME_MAX]; struct module *owner; }; int tcp_register_congestion_control(struct tcp_congestion_ops *type); void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); void tcp_assign_congestion_control(struct sock *sk); void tcp_init_congestion_control(struct sock *sk); void tcp_cleanup_congestion_control(struct sock *sk); int tcp_set_default_congestion_control(struct net *net, const char *name); void tcp_get_default_congestion_control(struct net *net, char *name); void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool cap_net_admin); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); u32 tcp_reno_ssthresh(struct sock *sk); u32 tcp_reno_undo_cwnd(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); extern struct tcp_congestion_ops tcp_reno; struct tcp_congestion_ops *tcp_ca_find(const char *name); struct tcp_congestion_ops *tcp_ca_find_key(u32 key); u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca); #ifdef CONFIG_INET char *tcp_ca_get_name_by_key(u32 key, char *buffer); #else static inline char *tcp_ca_get_name_by_key(u32 key, char *buffer) { return NULL; } #endif static inline bool tcp_ca_needs_ecn(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->set_state) icsk->icsk_ca_ops->set_state(sk, ca_state); icsk->icsk_ca_state = ca_state; } static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->cwnd_event) icsk->icsk_ca_ops->cwnd_event(sk, event); } /* From tcp_rate.c */ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs); void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { return t1 > t2 || (t1 == t2 && after(seq1, seq2)); } /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. * * tcp_is_sack - SACK enabled * tcp_is_reno - No SACK */ static inline int tcp_is_sack(const struct tcp_sock *tp) { return likely(tp->rx_opt.sack_ok); } static inline bool tcp_is_reno(const struct tcp_sock *tp) { return !tcp_is_sack(tp); } static inline unsigned int tcp_left_out(const struct tcp_sock *tp) { return tp->sacked_out + tp->lost_out; } /* This determines how many packets are "in the network" to the best * of our knowledge. In many cases it is conservative, but where * detailed information is available from the receiver (via SACK * blocks etc.) we can make more aggressive calculations. * * Use this for decisions involving congestion control, use just * tp->packets_out to determine if the send queue is empty or not. * * Read this equation as: * * "Packets sent once on transmission queue" MINUS * "Packets left network, but not honestly ACKed yet" PLUS * "Packets fast retransmitted" */ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) { return tp->packets_out - tcp_left_out(tp) + tp->retrans_out; } #define TCP_INFINITE_SSTHRESH 0x7fffffff static inline bool tcp_in_slow_start(const struct tcp_sock *tp) { return tp->snd_cwnd < tp->snd_ssthresh; } static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) { return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; } static inline bool tcp_in_cwnd_reduction(const struct sock *sk) { return (TCPF_CA_CWR | TCPF_CA_Recovery) & (1 << inet_csk(sk)->icsk_ca_state); } /* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd. * The exception is cwnd reduction phase, when cwnd is decreasing towards * ssthresh. */ static inline __u32 tcp_current_ssthresh(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (tcp_in_cwnd_reduction(sk)) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, ((tp->snd_cwnd >> 1) + (tp->snd_cwnd >> 2))); } /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out) void tcp_enter_cwr(struct sock *sk); __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst); /* The maximum number of MSS of available cwnd for which TSO defers * sending if not using sysctl_tcp_tso_win_divisor. */ static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp) { return 3; } /* Returns end sequence number of the receiver's advertised window */ static inline u32 tcp_wnd_end(const struct tcp_sock *tp) { return tp->snd_una + tp->snd_wnd; } /* We follow the spirit of RFC2861 to validate cwnd but implement a more * flexible approach. The RFC suggests cwnd should not be raised unless * it was fully used previously. And that's exactly what we do in * congestion avoidance mode. But in slow start we allow cwnd to grow * as long as the application has used half the cwnd. * Example : * cwnd is 10 (IW10), but application sends 9 frames. * We allow cwnd to reach 18 when all frames are ACKed. * This check is safe because it's as aggressive as slow start which already * risks 100% overshoot. The advantage is that we discourage application to * either send more filler packets or data to artificially blow up the cwnd * usage, and allow application-limited process to probe bw more aggressively. */ static inline bool tcp_is_cwnd_limited(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (tp->is_cwnd_limited) return true; /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) return tp->snd_cwnd < 2 * tp->max_packets_out; return false; } /* BBR congestion control needs pacing. * Same remark for SO_MAX_PACING_RATE. * sch_fq packet scheduler is efficiently handling pacing, * but is not always installed/used. * Return true if TCP stack should pace packets itself. */ static inline bool tcp_needs_internal_pacing(const struct sock *sk) { return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; } /* Estimates in how many jiffies next packet for this flow can be sent. * Scheduling a retransmit timer too early would be silly. */ static inline unsigned long tcp_pacing_delay(const struct sock *sk) { s64 delay = tcp_sk(sk)->tcp_wstamp_ns - tcp_sk(sk)->tcp_clock_cache; return delay > 0 ? nsecs_to_jiffies(delay) : 0; } static inline void tcp_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, const unsigned long max_when) { inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk), max_when); } /* Something is really bad, we could not queue an additional packet, * because qdisc is full or receiver sent a 0 window, or we are paced. * We do not want to add fuel to the fire, or abort too early, * so make sure the timer we arm now is at least 200ms in the future, * regardless of current icsk_rto value (as it could be ~2ms) */ static inline unsigned long tcp_probe0_base(const struct sock *sk) { return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN); } /* Variant of inet_csk_rto_backoff() used for zero window probes */ static inline unsigned long tcp_probe0_when(const struct sock *sk, unsigned long max_when) { u64 when = (u64)tcp_probe0_base(sk) << inet_csk(sk)->icsk_backoff; return (unsigned long)min_t(u64, when, max_when); } static inline void tcp_check_probe_timer(struct sock *sk) { if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, tcp_probe0_base(sk), TCP_RTO_MAX); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; } static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; } /* * Calculate(/check) TCP checksum */ static inline __sum16 tcp_v4_check(int len, __be32 saddr, __be32 daddr, __wsum base) { return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_TCP, base); } static inline bool tcp_checksum_complete(struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && __skb_checksum_complete(skb); } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); int tcp_abort(struct sock *sk, int err); static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) { rx_opt->dsack = 0; rx_opt->num_sacks = 0; } void tcp_cwnd_restart(struct sock *sk, s32 delta); static inline void tcp_slow_start_after_idle_check(struct sock *sk) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); s32 delta; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) || tp->packets_out || ca_ops->cong_control) return; delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) tcp_cwnd_restart(sk, delta); } /* Determine a window scaling and initial window to offer. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd); static inline int tcp_win_from_space(const struct sock *sk, int space) { int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale); return tcp_adv_win_scale <= 0 ? (space>>(-tcp_adv_win_scale)) : space - (space>>tcp_adv_win_scale); } /* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - READ_ONCE(sk->sk_backlog.len) - atomic_read(&sk->sk_rmem_alloc)); } static inline int tcp_full_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } void tcp_cleanup_rbuf(struct sock *sk, int copied); /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override * SO_RCVLOWAT constraint, since we are receiving skbs with too small * len/truesize ratio. */ static inline bool tcp_rmem_pressure(const struct sock *sk) { int rcvbuf, threshold; if (tcp_under_memory_pressure(sk)) return true; rcvbuf = READ_ONCE(sk->sk_rcvbuf); threshold = rcvbuf - (rcvbuf >> 3); return atomic_read(&sk->sk_rmem_alloc) > threshold; } extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); void tcp_enter_memory_pressure(struct sock *sk); void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); return tp->keepalive_intvl ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); return tp->keepalive_time ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); return tp->keepalive_probes ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) { const struct inet_connection_sock *icsk = &tp->inet_conn; return min_t(u32, tcp_jiffies32 - icsk->icsk_ack.lrcvtime, tcp_jiffies32 - tp->rcv_tstamp); } static inline int tcp_fin_time(const struct sock *sk) { int fin_timeout = tcp_sk(sk)->linger2 ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout); const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) fin_timeout = (rto << 2) - (rto >> 1); return fin_timeout; } static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt, int paws_win) { if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win) return true; if (unlikely(!time_before32(ktime_get_seconds(), rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))) return true; /* * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, * then following tcp messages have valid values. Ignore 0 value, * or else 'negative' tsval might forbid us to accept their packets. */ if (!rx_opt->ts_recent) return true; return false; } static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, int rst) { if (tcp_paws_check(rx_opt, 0)) return false; /* RST segments are not recommended to carry timestamp, and, if they do, it is recommended to ignore PAWS because "their cleanup function should take precedence over timestamps." Certainly, it is mistake. It is necessary to understand the reasons of this constraint to relax it: if peer reboots, clock may go out-of-sync and half-open connections will not be reset. Actually, the problem would be not existing if all the implementations followed draft about maintaining clock via reboots. Linux-2.2 DOES NOT! However, we can relax time bounds for RST segments to MSL. */ if (rst && !time_before32(ktime_get_seconds(), rx_opt->ts_recent_stamp + TCP_PAWS_MSL)) return false; return true; } bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { /* See RFC 2012 */ TCP_ADD_STATS(net, TCP_MIB_RTOALGORITHM, 1); TCP_ADD_STATS(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ); TCP_ADD_STATS(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ); TCP_ADD_STATS(net, TCP_MIB_MAXCONN, -1); } /* from STCP */ static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp) { tp->lost_skb_hint = NULL; } static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) { tcp_clear_retrans_hints_partial(tp); tp->retransmit_skb_hint = NULL; } union tcp_md5_addr { struct in_addr a4; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr a6; #endif }; /* - key database */ struct tcp_md5sig_key { struct hlist_node node; u8 keylen; u8 family; /* AF_INET or AF_INET6 */ u8 prefixlen; union tcp_md5_addr addr; int l3index; /* set if key added with L3 scope */ u8 key[TCP_MD5SIG_MAXKEYLEN]; struct rcu_head rcu; }; /* - sock block */ struct tcp_md5sig_info { struct hlist_head head; struct rcu_head rcu; }; /* - pseudo header */ struct tcp4_pseudohdr { __be32 saddr; __be32 daddr; __u8 pad; __u8 protocol; __be16 len; }; struct tcp6_pseudohdr { struct in6_addr saddr; struct in6_addr daddr; __be32 len; __be32 protocol; /* including padding */ }; union tcp_md5sum_block { struct tcp4_pseudohdr ip4; #if IS_ENABLED(CONFIG_IPV6) struct tcp6_pseudohdr ip6; #endif }; /* - pool: digest algorithm, hash description and scratch buffer */ struct tcp_md5sig_pool { struct ahash_request *md5_req; void *scratch; }; /* - functions */ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG #include <linux/jump_label.h> extern struct static_key_false tcp_md5_needed; struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family); static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { if (!static_branch_unlikely(&tcp_md5_needed)) return NULL; return __tcp_md5_do_lookup(sk, l3index, addr, family); } #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { return NULL; } #define tcp_twsk_md5_key(twsk) NULL #endif bool tcp_alloc_md5sig_pool(void); struct tcp_md5sig_pool *tcp_get_md5sig_pool(void); static inline void tcp_put_md5sig_pool(void) { local_bh_enable(); } int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *, unsigned int header_len); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key); /* From tcp_fastopen.c */ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost, u16 try_exp); struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; struct msghdr *data; /* data in MSG_FASTOPEN */ size_t size; int copied; /* queued in tcp_connect() */ struct ubuf_info *uarg; }; void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void *primary_key, void *backup_key); int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, u64 *key); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, const struct dst_entry *dst); void tcp_fastopen_init_key_once(struct net *net); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); #define TCP_FASTOPEN_KEY_LENGTH sizeof(siphash_key_t) #define TCP_FASTOPEN_KEY_MAX 2 #define TCP_FASTOPEN_KEY_BUF_LENGTH \ (TCP_FASTOPEN_KEY_LENGTH * TCP_FASTOPEN_KEY_MAX) /* Fastopen key context */ struct tcp_fastopen_context { siphash_key_t key[TCP_FASTOPEN_KEY_MAX]; int num; struct rcu_head rcu; }; extern unsigned int sysctl_tcp_fastopen_blackhole_timeout; void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired); /* Caller needs to wrap with rcu_read_(un)lock() */ static inline struct tcp_fastopen_context *tcp_fastopen_get_ctx(const struct sock *sk) { struct tcp_fastopen_context *ctx; ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); if (!ctx) ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); return ctx; } static inline bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc, const struct tcp_fastopen_cookie *orig) { if (orig->len == TCP_FASTOPEN_COOKIE_SIZE && orig->len == foc->len && !memcmp(orig->val, foc->val, foc->len)) return true; return false; } static inline int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx) { return ctx->num; } /* Latencies incurred by various limits for a sender. They are * chronograph-like stats that are mutually exclusive. */ enum tcp_chrono { TCP_CHRONO_UNSPEC, TCP_CHRONO_BUSY, /* Actively sending data (non-empty write queue) */ TCP_CHRONO_RWND_LIMITED, /* Stalled by insufficient receive window */ TCP_CHRONO_SNDBUF_LIMITED, /* Stalled by insufficient send buffer */ __TCP_CHRONO_MAX, }; void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type); void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type); /* This helper is needed, because skb->tcp_tsorted_anchor uses * the same memory storage than skb->destructor/_skb_refdst */ static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb) { skb->destructor = NULL; skb->_skb_refdst = 0UL; } #define tcp_skb_tsorted_save(skb) { \ unsigned long _save = skb->_skb_refdst; \ skb->_skb_refdst = 0UL; #define tcp_skb_tsorted_restore(skb) \ skb->_skb_refdst = _save; \ } void tcp_write_queue_purge(struct sock *sk); static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk) { return skb_rb_first(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk) { return skb_rb_last(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk) { return skb_peek(&sk->sk_write_queue); } static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk) { return skb_peek_tail(&sk->sk_write_queue); } #define tcp_for_write_queue_from_safe(skb, tmp, sk) \ skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp) static inline struct sk_buff *tcp_send_head(const struct sock *sk) { return skb_peek(&sk->sk_write_queue); } static inline bool tcp_skb_is_last(const struct sock *sk, const struct sk_buff *skb) { return skb_queue_is_last(&sk->sk_write_queue, skb); } /** * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue * @sk: socket * * Since the write queue can have a temporary empty skb in it, * we must not use "return skb_queue_empty(&sk->sk_write_queue)" */ static inline bool tcp_write_queue_empty(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return tp->write_seq == tp->snd_nxt; } static inline bool tcp_rtx_queue_empty(const struct sock *sk) { return RB_EMPTY_ROOT(&sk->tcp_rtx_queue); } static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk) { return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk); } static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb) { __skb_queue_tail(&sk->sk_write_queue, skb); /* Queue it, remembering where we must start sending. */ if (sk->sk_write_queue.next == skb) tcp_chrono_start(sk, TCP_CHRONO_BUSY); } /* Insert new before skb on the write queue of sk. */ static inline void tcp_insert_write_queue_before(struct sk_buff *new, struct sk_buff *skb, struct sock *sk) { __skb_queue_before(&sk->sk_write_queue, skb, new); } static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk) { tcp_skb_tsorted_anchor_cleanup(skb); __skb_unlink(skb, &sk->sk_write_queue); } void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb); static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk) { tcp_skb_tsorted_anchor_cleanup(skb); rb_erase(&skb->rbnode, &sk->tcp_rtx_queue); } static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk) { list_del(&skb->tcp_tsorted_anchor); tcp_rtx_queue_unlink(skb, sk); sk_wmem_free_skb(sk, skb); } static inline void tcp_push_pending_frames(struct sock *sk) { if (tcp_send_head(sk)) { struct tcp_sock *tp = tcp_sk(sk); __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle); } } /* Start sequence of the skb just after the highest skb with SACKed * bit, valid only if sacked_out > 0 or when the caller has ensured * validity by itself. */ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp) { if (!tp->sacked_out) return tp->snd_una; if (tp->highest_sack == NULL) return tp->snd_nxt; return TCP_SKB_CB(tp->highest_sack)->seq; } static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb) { tcp_sk(sk)->highest_sack = skb_rb_next(skb); } static inline struct sk_buff *tcp_highest_sack(struct sock *sk) { return tcp_sk(sk)->highest_sack; } static inline void tcp_highest_sack_reset(struct sock *sk) { tcp_sk(sk)->highest_sack = tcp_rtx_queue_head(sk); } /* Called when old skb is about to be deleted and replaced by new skb */ static inline void tcp_highest_sack_replace(struct sock *sk, struct sk_buff *old, struct sk_buff *new) { if (old == tcp_highest_sack(sk)) tcp_sk(sk)->highest_sack = new; } /* This helper checks if socket has IP_TRANSPARENT set */ static inline bool inet_sk_transparent(const struct sock *sk) { switch (sk->sk_state) { case TCP_TIME_WAIT: return inet_twsk(sk)->tw_transparent; case TCP_NEW_SYN_RECV: return inet_rsk(inet_reqsk(sk))->no_srccheck; } return inet_sk(sk)->transparent; } /* Determines whether this is a thin stream (which may suffer from * increased latency). Used to trigger latency-reducing mechanisms. */ static inline bool tcp_stream_is_thin(struct tcp_sock *tp) { return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp); } /* /proc */ enum tcp_seq_states { TCP_SEQ_STATE_LISTENING, TCP_SEQ_STATE_ESTABLISHED, }; void *tcp_seq_start(struct seq_file *seq, loff_t *pos); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos); void tcp_seq_stop(struct seq_file *seq, void *v); struct tcp_seq_afinfo { sa_family_t family; }; struct tcp_iter_state { struct seq_net_private p; enum tcp_seq_states state; struct sock *syn_wait_sk; struct tcp_seq_afinfo *bpf_seq_afinfo; int bucket, offset, sbucket, num; loff_t last_pos; }; extern struct request_sock_ops tcp_request_sock_ops; extern struct request_sock_ops tcp6_request_sock_ops; void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb); INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)); int tcp_gro_complete(struct sk_buff *skb); void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } /* @wake is one when sk_stream_write_space() calls us. * This sends EPOLLOUT only if notsent_bytes is half the limit. * This mimics the strategy used in sock_def_write_space(). */ static inline bool tcp_stream_memory_free(const struct sock *sk, int wake) { const struct tcp_sock *tp = tcp_sk(sk); u32 notsent_bytes = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt); return (notsent_bytes << wake) < tcp_notsent_lowat(tp); } #ifdef CONFIG_PROC_FS int tcp4_proc_init(void); void tcp4_proc_exit(void); #endif int tcp_rtx_synack(const struct sock *sk, struct request_sock *req); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); /* TCP af-specific functions */ struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash)(char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); int (*md5_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen); #endif }; struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash) (char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); #endif void (*init_req)(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, const struct request_sock *req); u32 (*init_seq)(const struct sk_buff *skb); u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; #if IS_ENABLED(CONFIG_IPV6) extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops; #endif #ifdef CONFIG_SYN_COOKIES static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { tcp_synq_overflow(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); return ops->cookie_init_seq(skb, mss); } #else static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { return 0; } #endif int tcpv4_offload_init(void); void tcp_v4_init(void); void tcp_init(void); /* tcp_recovery.c */ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb); void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced); extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd); extern bool tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs); /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; } /* * Save and compile IPv4 options, return a pointer to it */ static inline struct ip_options_rcu *tcp_v4_save_options(struct net *net, struct sk_buff *skb) { const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; struct ip_options_rcu *dopt = NULL; if (opt->optlen) { int opt_size = sizeof(*dopt) + opt->optlen; dopt = kmalloc(opt_size, GFP_ATOMIC); if (dopt && __ip_options_echo(net, &dopt->opt, skb, opt)) { kfree(dopt); dopt = NULL; } } return dopt; } /* locally generated TCP pure ACKs have skb->truesize == 2 * (check tcp_send_ack() in net/ipv4/tcp_output.c ) * This is much faster than dissecting the packet to find out. * (Think of GRE encapsulations, IPv4, IPv6, ...) */ static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb) { return skb->truesize == 2; } static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) { skb->truesize = 2; } static inline int tcp_inq(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); int answ; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { answ = 0; } else if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || before(tp->urg_seq, tp->copied_seq) || !before(tp->urg_seq, tp->rcv_nxt)) { answ = tp->rcv_nxt - tp->copied_seq; /* Subtract 1, if FIN was received */ if (answ && sock_flag(sk, SOCK_DONE)) answ--; } else { answ = tp->urg_seq - tp->copied_seq; } return answ; } int tcp_peek_len(struct socket *sock); static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) { u16 segs_in; segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs); tp->segs_in += segs_in; if (skb->len > tcp_hdrlen(skb)) tp->data_segs_in += segs_in; } /* * TCP listen path runs lockless. * We forced "struct sock" to be const qualified to make sure * we don't modify one of its field by mistake. * Here, we increment sk_drops which is an atomic_t, so we can safely * make sock writable again. */ static inline void tcp_listendrop(const struct sock *sk) { atomic_inc(&((struct sock *)sk)->sk_drops); __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); } enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); /* * Interface for adding Upper Level Protocols over TCP */ #define TCP_ULP_NAME_MAX 16 #define TCP_ULP_MAX 128 #define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX) struct tcp_ulp_ops { struct list_head list; /* initialize ulp */ int (*init)(struct sock *sk); /* update ulp */ void (*update)(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ int (*get_info)(const struct sock *sk, struct sk_buff *skb); size_t (*get_info_size)(const struct sock *sk); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, const gfp_t priority); char name[TCP_ULP_NAME_MAX]; struct module *owner; }; int tcp_register_ulp(struct tcp_ulp_ops *type); void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); void tcp_update_ulp(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); #define MODULE_ALIAS_TCP_ULP(name) \ __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) struct sk_msg; struct sk_psock; #ifdef CONFIG_BPF_STREAM_PARSER struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #else static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { } #endif /* CONFIG_BPF_STREAM_PARSER */ #ifdef CONFIG_NET_SOCK_MSG int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, int flags); int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); #endif /* CONFIG_NET_SOCK_MSG */ #ifdef CONFIG_CGROUP_BPF static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { skops->skb = skb; skops->skb_data_end = skb->data + end_offset; } #else static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { } #endif /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF * program loaded). */ #ifdef CONFIG_BPF static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { struct bpf_sock_ops_kern sock_ops; int ret; memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); if (sk_fullsock(sk)) { sock_ops.is_fullsock = 1; sock_owned_by_me(sk); } sock_ops.sk = sk; sock_ops.op = op; if (nargs > 0) memcpy(sock_ops.args, args, nargs * sizeof(*args)); ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); if (ret == 0) ret = sock_ops.reply; else ret = -1; return ret; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { u32 args[2] = {arg1, arg2}; return tcp_call_bpf(sk, op, 2, args); } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { u32 args[3] = {arg1, arg2, arg3}; return tcp_call_bpf(sk, op, 3, args); } #else static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { return -EPERM; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { return -EPERM; } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { return -EPERM; } #endif static inline u32 tcp_timeout_init(struct sock *sk) { int timeout; timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL); if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; return timeout; } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) { int rwnd; rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL); if (rwnd < 0) rwnd = 0; return rwnd; } static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) { return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } static inline void tcp_bpf_rtt(struct sock *sk) { if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); } #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif #if IS_ENABLED(CONFIG_TLS_DEVICE) void clean_acked_data_enable(struct inet_connection_sock *icsk, void (*cad)(struct sock *sk, u32 ack_seq)); void clean_acked_data_disable(struct inet_connection_sock *icsk); void clean_acked_data_flush(void); #endif DECLARE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); static inline void tcp_add_tx_delay(struct sk_buff *skb, const struct tcp_sock *tp) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) skb->skb_mstamp_ns += (u64)tp->tcp_tx_delay * NSEC_PER_USEC; } /* Compute Earliest Departure Time for some control packets * like ACK or RST for TIME_WAIT or non ESTABLISHED sockets. */ static inline u64 tcp_transmit_time(const struct sock *sk) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) { u32 delay = (sk->sk_state == TCP_TIME_WAIT) ? tcp_twsk(sk)->tw_tx_delay : tcp_sk(sk)->tcp_tx_delay; return tcp_clock_ns() + (u64)delay * NSEC_PER_USEC; } return 0; } #endif /* _TCP_H */
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 // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/cpumask.h> #include <linux/export.h> #include <linux/memblock.h> #include <linux/numa.h> /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (ie. return will be > @n) * @srcp: the cpumask pointer * * Returns >= nr_cpu_ids if no further cpus set. */ unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next); /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (ie. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Returns >= nr_cpu_ids if no further cpus set in both. */ int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next_and); /** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Returns >= nr_cpu_ids if no cpus set. */ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } EXPORT_SYMBOL(cpumask_any_but); /** * cpumask_next_wrap - helper to implement for_each_cpu_wrap * @n: the cpu prior to the place to search * @mask: the cpumask pointer * @start: the start point of the iteration * @wrap: assume @n crossing @start terminates the iteration * * Returns >= nr_cpu_ids on completion * * Note: the @wrap argument is required for the start condition when * we cannot assume @start is set in @mask. */ int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { int next; again: next = cpumask_next(n, mask); if (wrap && n < start && next >= start) { return nr_cpumask_bits; } else if (next >= nr_cpumask_bits) { wrap = true; n = -1; goto again; } return next; } EXPORT_SYMBOL(cpumask_next_wrap); /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK /** * alloc_cpumask_var_node - allocate a struct cpumask on a given node * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>) * Returns TRUE if memory allocation succeeded, FALSE otherwise. * * In addition, mask will be NULL if this fails. Note that gcc is * usually smart enough to know that mask can never be NULL if * CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case * too. */ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { *mask = kmalloc_node(cpumask_size(), flags, node); #ifdef CONFIG_DEBUG_PER_CPU_MAPS if (!*mask) { printk(KERN_ERR "=> alloc_cpumask_var: failed!\n"); dump_stack(); } #endif return *mask != NULL; } EXPORT_SYMBOL(alloc_cpumask_var_node); bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } EXPORT_SYMBOL(zalloc_cpumask_var_node); /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. */ bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } EXPORT_SYMBOL(alloc_cpumask_var); bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } EXPORT_SYMBOL(zalloc_cpumask_var); /** * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena. * @mask: pointer to cpumask_var_t where the cpumask is returned * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop (in <linux/cpumask.h>). * Either returns an allocated (zero-filled) cpumask, or causes the * system to panic. */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { *mask = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES); if (!*mask) panic("%s: Failed to allocate %u bytes\n", __func__, cpumask_size()); } /** * free_cpumask_var - frees memory allocated for a struct cpumask. * @mask: cpumask to free * * This is safe on a NULL mask. */ void free_cpumask_var(cpumask_var_t mask) { kfree(mask); } EXPORT_SYMBOL(free_cpumask_var); /** * free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var * @mask: cpumask to free */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { memblock_free_early(__pa(mask), cpumask_size()); } #endif /** * cpumask_local_spread - select the i'th cpu with local numa cpu's first * @i: index number * @node: local numa_node * * This function selects an online CPU according to a numa aware policy; * local cpus are returned first, followed by non-local ones, then it * wraps around. * * It's not very efficient, but useful for setup. */ unsigned int cpumask_local_spread(unsigned int i, int node) { int cpu; /* Wrap: we always want a cpu. */ i %= num_online_cpus(); if (node == NUMA_NO_NODE) { for_each_cpu(cpu, cpu_online_mask) if (i-- == 0) return cpu; } else { /* NUMA first. */ for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask) if (i-- == 0) return cpu; for_each_cpu(cpu, cpu_online_mask) { /* Skip NUMA nodes, done above. */ if (cpumask_test_cpu(cpu, cpumask_of_node(node))) continue; if (i-- == 0) return cpu; } } BUG(); } EXPORT_SYMBOL(cpumask_local_spread); static DEFINE_PER_CPU(int, distribute_cpu_mask_prev); /** * Returns an arbitrary cpu within srcp1 & srcp2. * * Iterated calls using the same srcp1 and srcp2 will be distributed within * their intersection. * * Returns >= nr_cpu_ids if the intersection is empty. */ int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); next = cpumask_next_and(prev, src1p, src2p); if (next >= nr_cpu_ids) next = cpumask_first_and(src1p, src2p); if (next < nr_cpu_ids) __this_cpu_write(distribute_cpu_mask_prev, next); return next; } EXPORT_SYMBOL(cpumask_any_and_distribute);
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2001 Jens Axboe <axboe@suse.de> */ #ifndef __LINUX_BIO_H #define __LINUX_BIO_H #include <linux/highmem.h> #include <linux/mempool.h> #include <linux/ioprio.h> /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include <linux/blk_types.h> #define BIO_DEBUG #ifdef BIO_DEBUG #define BIO_BUG_ON BUG_ON #else #define BIO_BUG_ON #endif #define BIO_MAX_PAGES 256 #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) #define bio_iter_iovec(bio, iter) \ bvec_iter_bvec((bio)->bi_io_vec, (iter)) #define bio_iter_page(bio, iter) \ bvec_iter_page((bio)->bi_io_vec, (iter)) #define bio_iter_len(bio, iter) \ bvec_iter_len((bio)->bi_io_vec, (iter)) #define bio_iter_offset(bio, iter) \ bvec_iter_offset((bio)->bi_io_vec, (iter)) #define bio_page(bio) bio_iter_page((bio), (bio)->bi_iter) #define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) #define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) #define bvec_iter_sectors(iter) ((iter).bi_size >> 9) #define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter))) #define bio_sectors(bio) bvec_iter_sectors((bio)->bi_iter) #define bio_end_sector(bio) bvec_iter_end_sector((bio)->bi_iter) /* * Return the data direction, READ or WRITE. */ #define bio_data_dir(bio) \ (op_is_write(bio_op(bio)) ? WRITE : READ) /* * Check whether this bio carries any data or not. A NULL bio is allowed. */ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && bio_op(bio) != REQ_OP_DISCARD && bio_op(bio) != REQ_OP_SECURE_ERASE && bio_op(bio) != REQ_OP_WRITE_ZEROES) return true; return false; } static inline bool bio_no_advance_iter(const struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || bio_op(bio) == REQ_OP_WRITE_SAME || bio_op(bio) == REQ_OP_WRITE_ZEROES; } static inline bool bio_mergeable(struct bio *bio) { if (bio->bi_opf & REQ_NOMERGE_FLAGS) return false; return true; } static inline unsigned int bio_cur_bytes(struct bio *bio) { if (bio_has_data(bio)) return bio_iovec(bio).bv_len; else /* dataless requests such as discard */ return bio->bi_iter.bi_size; } static inline void *bio_data(struct bio *bio) { if (bio_has_data(bio)) return page_address(bio_page(bio)) + bio_offset(bio); return NULL; } /** * bio_full - check if the bio is full * @bio: bio to check * @len: length of one segment to be added * * Return true if @bio is full and one segment with @len bytes can't be * added to the bio, otherwise return false */ static inline bool bio_full(struct bio *bio, unsigned len) { if (bio->bi_vcnt >= bio->bi_max_vecs) return true; if (bio->bi_iter.bi_size > UINT_MAX - len) return true; return false; } static inline bool bio_next_segment(const struct bio *bio, struct bvec_iter_all *iter) { if (iter->idx >= bio->bi_vcnt) return false; bvec_advance(&bio->bi_io_vec[iter->idx], iter); return true; } /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it */ #define bio_for_each_segment_all(bvl, bio, iter) \ for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); ) static inline void bio_advance_iter(const struct bio *bio, struct bvec_iter *iter, unsigned int bytes) { iter->bi_sector += bytes >> 9; if (bio_no_advance_iter(bio)) iter->bi_size -= bytes; else bvec_iter_advance(bio->bi_io_vec, iter, bytes); /* TODO: It is reasonable to complete bio with error here. */ } #define __bio_for_each_segment(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bio_iter_iovec((bio), (iter))), 1); \ bio_advance_iter((bio), &(iter), (bvl).bv_len)) #define bio_for_each_segment(bvl, bio, iter) \ __bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter) #define __bio_for_each_bvec(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = mp_bvec_iter_bvec((bio)->bi_io_vec, (iter))), 1); \ bio_advance_iter((bio), &(iter), (bvl).bv_len)) /* iterate over multi-page bvec */ #define bio_for_each_bvec(bvl, bio, iter) \ __bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter) /* * Iterate over all multi-page bvecs. Drivers shouldn't use this version for the * same reasons as bio_for_each_segment_all(). */ #define bio_for_each_bvec_all(bvl, bio, i) \ for (i = 0, bvl = bio_first_bvec_all(bio); \ i < (bio)->bi_vcnt; i++, bvl++) \ #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) static inline unsigned bio_segments(struct bio *bio) { unsigned segs = 0; struct bio_vec bv; struct bvec_iter iter; /* * We special case discard/write same/write zeroes, because they * interpret bi_size differently: */ switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: case REQ_OP_WRITE_ZEROES: return 0; case REQ_OP_WRITE_SAME: return 1; default: break; } bio_for_each_segment(bv, bio, iter) segs++; return segs; } /* * get a reference to a bio, so it won't disappear. the intended use is * something like: * * bio_get(bio); * submit_bio(rw, bio); * if (bio->bi_flags ...) * do_something * bio_put(bio); * * without the bio_get(), it could potentially complete I/O before submit_bio * returns. and then bio would be freed memory when if (bio->bi_flags ...) * runs */ static inline void bio_get(struct bio *bio) { bio->bi_flags |= (1 << BIO_REFFED); smp_mb__before_atomic(); atomic_inc(&bio->__bi_cnt); } static inline void bio_cnt_set(struct bio *bio, unsigned int count) { if (count != 1) { bio->bi_flags |= (1 << BIO_REFFED); smp_mb(); } atomic_set(&bio->__bi_cnt, count); } static inline bool bio_flagged(struct bio *bio, unsigned int bit) { return (bio->bi_flags & (1U << bit)) != 0; } static inline void bio_set_flag(struct bio *bio, unsigned int bit) { bio->bi_flags |= (1U << bit); } static inline void bio_clear_flag(struct bio *bio, unsigned int bit) { bio->bi_flags &= ~(1U << bit); } static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) { *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) { struct bvec_iter iter = bio->bi_iter; int idx; bio_get_first_bvec(bio, bv); if (bv->bv_len == bio->bi_iter.bi_size) return; /* this bio only has a single bvec */ bio_advance_iter(bio, &iter, iter.bi_size); if (!iter.bi_bvec_done) idx = iter.bi_idx - 1; else /* in the middle of bvec */ idx = iter.bi_idx; *bv = bio->bi_io_vec[idx]; /* * iter.bi_bvec_done records actual length of the last bvec * if this bio ends in the middle of one io vector */ if (iter.bi_bvec_done) bv->bv_len = iter.bi_bvec_done; } static inline struct bio_vec *bio_first_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); return bio->bi_io_vec; } static inline struct page *bio_first_page_all(struct bio *bio) { return bio_first_bvec_all(bio)->bv_page; } static inline struct bio_vec *bio_last_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); return &bio->bi_io_vec[bio->bi_vcnt - 1]; } enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ BIP_CTRL_NOCHECK = 1 << 2, /* disable HBA integrity checking */ BIP_DISK_NOCHECK = 1 << 3, /* disable disk integrity checking */ BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */ }; /* * bio integrity payload */ struct bio_integrity_payload { struct bio *bip_bio; /* parent bio */ struct bvec_iter bip_iter; unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_max_vcnt; /* integrity bio_vec slots */ unsigned short bip_flags; /* control flags */ struct bvec_iter bio_iter; /* for rewinding parent bio */ struct work_struct bip_work; /* I/O completion */ struct bio_vec *bip_vec; struct bio_vec bip_inline_vecs[];/* embedded bvec array */ }; #if defined(CONFIG_BLK_DEV_INTEGRITY) static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) { if (bio->bi_opf & REQ_INTEGRITY) return bio->bi_integrity; return NULL; } static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { struct bio_integrity_payload *bip = bio_integrity(bio); if (bip) return bip->bip_flags & flag; return false; } static inline sector_t bip_get_seed(struct bio_integrity_payload *bip) { return bip->bip_iter.bi_sector; } static inline void bip_set_seed(struct bio_integrity_payload *bip, sector_t seed) { bip->bip_iter.bi_sector = seed; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ extern void bio_trim(struct bio *bio, int offset, int size); extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); /** * bio_next_split - get next @sectors from a bio, splitting if necessary * @bio: bio to split * @sectors: number of sectors to split from the front of @bio * @gfp: gfp mask * @bs: bio set to allocate from * * Returns a bio representing the next @sectors of @bio - if the bio is smaller * than @sectors, returns the original bio unchanged. */ static inline struct bio *bio_next_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) { if (sectors >= bio_sectors(bio)) return bio; return bio_split(bio, sectors, gfp, bs); } enum { BIOSET_NEED_BVECS = BIT(0), BIOSET_NEED_RESCUER = BIT(1), }; extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *); extern void bio_put(struct bio *); extern void __bio_clone_fast(struct bio *, struct bio *); extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); extern struct bio_set fs_bio_set; static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) { return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set); } static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs) { return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL); } extern blk_qc_t submit_bio(struct bio *); extern void bio_endio(struct bio *); static inline void bio_io_error(struct bio *bio) { bio->bi_status = BLK_STS_IOERR; bio_endio(bio); } static inline void bio_wouldblock_error(struct bio *bio) { bio_set_flag(bio, BIO_QUIET); bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); } struct request_queue; extern int submit_bio_wait(struct bio *bio); extern void bio_advance(struct bio *, unsigned); extern void bio_init(struct bio *bio, struct bio_vec *table, unsigned short max_vecs); extern void bio_uninit(struct bio *); extern void bio_reset(struct bio *); void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); bool __bio_try_merge_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off, bool *same_page); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); void bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter); extern void bio_copy_data(struct bio *dst, struct bio *src); extern void bio_list_copy_data(struct bio *dst, struct bio *src); extern void bio_free_pages(struct bio *bio); void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter); void bio_truncate(struct bio *bio, unsigned new_size); void guard_bio_eod(struct bio *bio); static inline void zero_fill_bio(struct bio *bio) { zero_fill_bio_iter(bio, bio->bi_iter); } extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); extern const char *bio_devname(struct bio *bio, char *buffer); #define bio_set_dev(bio, bdev) \ do { \ if ((bio)->bi_disk != (bdev)->bd_disk) \ bio_clear_flag(bio, BIO_THROTTLED);\ (bio)->bi_disk = (bdev)->bd_disk; \ (bio)->bi_partno = (bdev)->bd_partno; \ bio_associate_blkg(bio); \ } while (0) #define bio_copy_dev(dst, src) \ do { \ (dst)->bi_disk = (src)->bi_disk; \ (dst)->bi_partno = (src)->bi_partno; \ bio_clone_blkg_association(dst, src); \ } while (0) #define bio_dev(bio) \ disk_devt((bio)->bi_disk) #ifdef CONFIG_BLK_CGROUP void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { } static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM /* * remember never ever reenable interrupts between a bvec_kmap_irq and * bvec_kunmap_irq! */ static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) { unsigned long addr; /* * might not be a highmem page, but the preempt/irq count * balancing is a lot nicer this way */ local_irq_save(*flags); addr = (unsigned long) kmap_atomic(bvec->bv_page); BUG_ON(addr & ~PAGE_MASK); return (char *) addr + bvec->bv_offset; } static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) { unsigned long ptr = (unsigned long) buffer & PAGE_MASK; kunmap_atomic((void *) ptr); local_irq_restore(*flags); } #else static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) { return page_address(bvec->bv_page) + bvec->bv_offset; } static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) { *flags = 0; } #endif /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * * A bio_list anchors a singly-linked list of bios chained through the bi_next * member of the bio. The bio_list also caches the last list member to allow * fast access to the tail. */ struct bio_list { struct bio *head; struct bio *tail; }; static inline int bio_list_empty(const struct bio_list *bl) { return bl->head == NULL; } static inline void bio_list_init(struct bio_list *bl) { bl->head = bl->tail = NULL; } #define BIO_EMPTY_LIST { NULL, NULL } #define bio_list_for_each(bio, bl) \ for (bio = (bl)->head; bio; bio = bio->bi_next) static inline unsigned bio_list_size(const struct bio_list *bl) { unsigned sz = 0; struct bio *bio; bio_list_for_each(bio, bl) sz++; return sz; } static inline void bio_list_add(struct bio_list *bl, struct bio *bio) { bio->bi_next = NULL; if (bl->tail) bl->tail->bi_next = bio; else bl->head = bio; bl->tail = bio; } static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio) { bio->bi_next = bl->head; bl->head = bio; if (!bl->tail) bl->tail = bio; } static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) { if (!bl2->head) return; if (bl->tail) bl->tail->bi_next = bl2->head; else bl->head = bl2->head; bl->tail = bl2->tail; } static inline void bio_list_merge_head(struct bio_list *bl, struct bio_list *bl2) { if (!bl2->head) return; if (bl->head) bl2->tail->bi_next = bl->head; else bl->tail = bl2->tail; bl->head = bl2->head; } static inline struct bio *bio_list_peek(struct bio_list *bl) { return bl->head; } static inline struct bio *bio_list_pop(struct bio_list *bl) { struct bio *bio = bl->head; if (bio) { bl->head = bl->head->bi_next; if (!bl->head) bl->tail = NULL; bio->bi_next = NULL; } return bio; } static inline struct bio *bio_list_get(struct bio_list *bl) { struct bio *bio = bl->head; bl->head = bl->tail = NULL; return bio; } /* * Increment chain count for the bio. Make sure the CHAIN flag update * is visible before the raised count. */ static inline void bio_inc_remaining(struct bio *bio) { bio_set_flag(bio, BIO_CHAIN); smp_mb__before_atomic(); atomic_inc(&bio->__bi_remaining); } /* * bio_set is used to allow other portions of the IO system to * allocate their own private memory pools for bio and iovec structures. * These memory pools in turn all allocate from the bio_slab * and the bvec_slabs[]. */ #define BIO_POOL_SIZE 2 struct bio_set { struct kmem_cache *bio_slab; unsigned int front_pad; mempool_t bio_pool; mempool_t bvec_pool; #if defined(CONFIG_BLK_DEV_INTEGRITY) mempool_t bio_integrity_pool; mempool_t bvec_integrity_pool; #endif /* * Deadlock avoidance for stacking block drivers: see comments in * bio_alloc_bioset() for details */ spinlock_t rescue_lock; struct bio_list rescue_list; struct work_struct rescue_work; struct workqueue_struct *rescue_workqueue; }; struct biovec_slab { int nr_vecs; char *name; struct kmem_cache *slab; }; static inline bool bioset_initialized(struct bio_set *bs) { return bs->bio_slab != NULL; } /* * a small number of entries is fine, not going to be performance critical. * basically we just need to survive */ #define BIO_SPLIT_ENTRIES 2 #if defined(CONFIG_BLK_DEV_INTEGRITY) #define bip_for_each_vec(bvl, bip, iter) \ for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) #define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ for_each_bio(_bio) \ bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern bool bio_integrity_prep(struct bio *); extern void bio_integrity_advance(struct bio *, unsigned int); extern void bio_integrity_trim(struct bio *); extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); extern int bioset_integrity_create(struct bio_set *, int); extern void bioset_integrity_free(struct bio_set *); extern void bio_integrity_init(void); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline void *bio_integrity(struct bio *bio) { return NULL; } static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) { return 0; } static inline void bioset_integrity_free (struct bio_set *bs) { return; } static inline bool bio_integrity_prep(struct bio *bio) { return true; } static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) { return 0; } static inline void bio_integrity_advance(struct bio *bio, unsigned int bytes_done) { return; } static inline void bio_integrity_trim(struct bio *bio) { return; } static inline void bio_integrity_init(void) { return; } static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { return false; } static inline void *bio_integrity_alloc(struct bio * bio, gfp_t gfp, unsigned int nr) { return ERR_PTR(-EINVAL); } static inline int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { return 0; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ /* * Mark a bio as polled. Note that for async polled IO, the caller must * expect -EWOULDBLOCK if we cannot allocate a request (or other resources). * We cannot block waiting for requests on polled IO, as those completions * must be found by the caller. This is different than IRQ driven IO, where * it's safe to wait for IO to complete. */ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) { bio->bi_opf |= REQ_HIPRI; if (!is_sync_kiocb(kiocb)) bio->bi_opf |= REQ_NOWAIT; } #endif /* __LINUX_BIO_H */
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 // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <net/sock.h> #include "internal.h" unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int count) { unsigned int cpy, set; cpy = count / BITS_PER_BYTE; set = (nfdt->max_fds - count) / BITS_PER_BYTE; memcpy(nfdt->open_fds, ofdt->open_fds, cpy); memset((char *)nfdt->open_fds + cpy, 0, set); memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); memset((char *)nfdt->close_on_exec + cpy, 0, set); cpy = BITBIT_SIZE(count); set = BITBIT_SIZE(nfdt->max_fds) - cpy; memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); memset((char *)nfdt->full_fds_bits + cpy, 0, set); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". * * The ALIGN(nr, BITS_PER_LONG) here is for clarity: since we just multiplied * by that "1024/sizeof(ptr)" before, we already know there are sufficient * clear low bits. Clang seems to realize that, gcc ends up being confused. * * On a 128-bit machine, the ALIGN() would actually matter. In the meantime, * let's consider it documentation (and maybe a test-case for gcc to improve * its code generation ;) */ static struct fdtable * alloc_fdtable(unsigned int nr) { struct fdtable *fdt; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. */ nr /= (1024 / sizeof(struct file *)); nr = roundup_pow_of_two(nr + 1); nr *= (1024 / sizeof(struct file *)); nr = ALIGN(nr, BITS_PER_LONG); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. Deal * with that in caller, it's cheaper that way. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1; fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return NULL; } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 1 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr); /* make sure all __fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (!new_fdt) return -ENOMEM; /* * extremely unlikely race - sysctl_nr_open decreased between the check in * caller and alloc_fdtable(). Cheaper to catch it here... */ if (unlikely(new_fdt->max_fds <= nr)) { __free_fdtable(new_fdt); return -EMFILE; } cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in __fd_install() */ smp_wmb(); return 1; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 when nothing done; 1 when files were * expanded and execution may have blocked. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int expanded = 0; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return expanded; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); expanded = 1; wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; expanded = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return expanded; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->close_on_exec); } static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt) { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); } static unsigned int count_open_files(struct fdtable *fdt) { unsigned int size = fdt->max_fds; unsigned int i; /* Find the last open fd */ for (i = size / BITS_PER_LONG; i > 0; ) { if (fdt->open_fds[--i]) break; } i = (i + 1) * BITS_PER_LONG; return i; } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * 'max_fds' will normally already be properly aligned, but it * turns out that in the close_range() -> __close_range() -> * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end * up having a 'max_fds' value that isn't already aligned. * * Rather than make close_range() have to worry about this, * just make that BITS_PER_LONG alignment be part of a sane * fdtable size. Becuase that's really what it is. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds) { unsigned int count; count = count_open_files(fdt); if (max_fds < NR_OPEN_DEFAULT) max_fds = NR_OPEN_DEFAULT; return ALIGN(min(count, max_fds), BITS_PER_LONG); } /* * Allocate a new files structure and copy contents from the * passed in files structure. * errorp will be valid only when the returned files_struct is NULL. */ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; *errorp = -ENOMEM; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) goto out; atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files - 1); if (!new_fdt) { *errorp = -ENOMEM; goto out_release; } /* beyond sysctl_nr_open; nothing to do */ if (unlikely(new_fdt->max_fds < open_files)) { __free_fdtable(new_fdt); *errorp = -EMFILE; goto out_release; } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); } copy_fd_bitmaps(new_fdt, old_fdt, open_files); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; out_release: kmem_cache_free(files_cachep, newf); out: return NULL; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file * file = xchg(&fdt->fd[i], NULL); if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } struct files_struct *get_files_struct(struct task_struct *task) { struct files_struct *files; task_lock(task); files = task->files; if (files) atomic_inc(&files->count); task_unlock(task); return files; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void reset_files_struct(struct files_struct *files) { struct task_struct *tsk = current; struct files_struct *old; old = tsk->files; task_lock(tsk); tsk->files = files; task_unlock(tsk); put_files_struct(old); } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit > maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ int __alloc_fd(struct files_struct *files, unsigned start, unsigned end, unsigned flags) { unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (fd < fdt->max_fds) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (fd >= end) goto out; error = expand_files(files, fd); if (error < 0) goto out; /* * If we needed to expand the fs array we * might have blocked - try again. */ if (error) goto repeat; if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); error = fd; #if 1 /* Sanity check */ if (rcu_access_pointer(fdt->fd[fd]) != NULL) { printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } #endif out: spin_unlock(&files->file_lock); return error; } static int alloc_fd(unsigned start, unsigned flags) { return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags); } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return __alloc_fd(current->files, 0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * NOTE: __fd_install() variant is really, really low-level; don't * use it unless you are forced to by truly lousy API shoved down * your throat. 'files' *MUST* be either current->files or obtained * by get_files_struct(current) done by whoever had given it to you, * or really bad things will happen. Normally you want to use * fd_install() instead. */ void __fd_install(struct files_struct *files, unsigned int fd, struct file *file) { struct fdtable *fdt; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } /* * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { __fd_install(current->files, fd, file); } EXPORT_SYMBOL(fd_install); static struct file *pick_file(struct files_struct *files, unsigned fd) { struct file *file = NULL; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_unlock; file = fdt->fd[fd]; if (!file) goto out_unlock; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); out_unlock: spin_unlock(&files->file_lock); return file; } /* * The same warnings as for __alloc_fd()/__fd_install() apply here... */ int __close_fd(struct files_struct *files, unsigned fd) { struct file *file; file = pick_file(files, fd); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(__close_fd); /* for ksys_close() */ /** * __close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. */ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) { unsigned int cur_max; struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~CLOSE_RANGE_UNSHARE) return -EINVAL; if (fd > max_fd) return -EINVAL; rcu_read_lock(); cur_max = files_fdtable(cur_fds)->max_fds; rcu_read_unlock(); /* cap to last valid index into fdtable */ cur_max--; if (flags & CLOSE_RANGE_UNSHARE) { int ret; unsigned int max_unshare_fds = NR_OPEN_MAX; /* * If the requested range is greater than the current maximum, * we're closing everything so only copy all file descriptors * beneath the lowest file descriptor. */ if (max_fd >= cur_max) max_unshare_fds = fd; ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds); if (ret) return ret; /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ if (fds) swap(cur_fds, fds); } max_fd = min(max_fd, cur_max); while (fd <= max_fd) { struct file *file; file = pick_file(cur_fds, fd++); if (!file) continue; filp_close(file, cur_fds); cond_resched(); } if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /* * See close_fd_get_file() below, this variant assumes current->files->file_lock * is held. */ int __close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; struct file *file; struct fdtable *fdt; fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_err; file = fdt->fd[fd]; if (!file) goto out_err; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); get_file(file); *res = file; return 0; out_err: *res = NULL; return -ENOENT; } /* * variant of close_fd that gets a ref on the file for later fput. * The caller must ensure that filp_close() called on the file, and then * an fput(). */ int close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; int ret; spin_lock(&files->file_lock); ret = __close_fd_get_file(fd, res); spin_unlock(&files->file_lock); return ret; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask, unsigned int refs) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; if (unlikely(fd >= fdt->max_fds)) return NULL; fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds); file = rcu_dereference_raw(*fdentry); if (unlikely(!file)) return NULL; if (unlikely(file->f_mode & mask)) return NULL; /* * Ok, we have a file pointer. However, because we do * this all locklessly under RCU, we may be racing with * that file being closed. * * Such a race can take two forms: * * (a) the file ref already went down to zero, * and get_file_rcu_many() fails. Just try * again: */ if (unlikely(!get_file_rcu_many(file, refs))) continue; /* * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our refs and try again. */ if (unlikely(rcu_dereference_raw(files->fdt) != fdt) || unlikely(rcu_dereference_raw(*fdentry) != file)) { fput_many(file, refs); continue; } /* * Ok, we have a ref to the file, and checked that it * still exists. */ return file; } } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask, unsigned int refs) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask, refs); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs) { return __fget_files(current->files, fd, mask, refs); } struct file *fget_many(unsigned int fd, unsigned int refs) { return __fget(fd, FMODE_PATH, refs); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH, 1); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0, 1); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0, 1); task_unlock(task); return file; } /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ static unsigned long __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; if (atomic_read(&files->count) == 1) { file = __fcheck_files(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; return (unsigned long)file; } else { file = __fget(fd, mask, 1); if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; } } unsigned long __fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(__fdget); unsigned long __fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); if (file && (file->f_mode & FMODE_ATOMIC_POS)) { if (file_count(file) > 1) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } } return v; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (flag) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { struct files_struct *files = current->files; struct fdtable *fdt; bool res; rcu_read_lock(); fdt = files_fdtable(files); res = close_on_exec(fd, fdt); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return __close_fd(files, fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } /** * __receive_fd() - Install received file into file descriptor table * * @fd: fd to install into (if negative, a new fd will be allocated) * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; if (fd < 0) { new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; } else { new_fd = fd; } if (ufd) { error = put_user(new_fd, ufd); if (error) { if (fd < 0) put_unused_fd(new_fd); return error; } } if (fd < 0) { fd_install(new_fd, get_file(file)); } else { error = replace_fd(new_fd, file, o_flags); if (error) return error; } /* Bump the sock usage counts, if any. */ __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = fcheck(oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; int retval = oldfd; rcu_read_lock(); if (!fcheck_files(files, oldfd)) retval = -EBADF; rcu_read_unlock(); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { int err; if (from >= rlimit(RLIMIT_NOFILE)) return -EINVAL; err = alloc_fd(from, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd);
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/include/linux/nmi.h */ #ifndef LINUX_NMI_H #define LINUX_NMI_H #include <linux/sched.h> #include <asm/irq.h> #if defined(CONFIG_HAVE_NMI_WATCHDOG) #include <asm/nmi.h> #endif #ifdef CONFIG_LOCKUP_DETECTOR void lockup_detector_init(void); void lockup_detector_soft_poweroff(void); void lockup_detector_cleanup(void); bool is_hardlockup(void); extern int watchdog_user_enabled; extern int nmi_watchdog_user_enabled; extern int soft_watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; extern struct cpumask watchdog_cpumask; extern unsigned long *watchdog_cpumask_bits; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; #else #define sysctl_softlockup_all_cpu_backtrace 0 #define sysctl_hardlockup_all_cpu_backtrace 0 #endif /* !CONFIG_SMP */ #else /* CONFIG_LOCKUP_DETECTOR */ static inline void lockup_detector_init(void) { } static inline void lockup_detector_soft_poweroff(void) { } static inline void lockup_detector_cleanup(void) { } #endif /* !CONFIG_LOCKUP_DETECTOR */ #ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern unsigned int softlockup_panic; extern int lockup_detector_online_cpu(unsigned int cpu); extern int lockup_detector_offline_cpu(unsigned int cpu); #else /* CONFIG_SOFTLOCKUP_DETECTOR */ static inline void touch_softlockup_watchdog_sched(void) { } static inline void touch_softlockup_watchdog(void) { } static inline void touch_softlockup_watchdog_sync(void) { } static inline void touch_all_softlockup_watchdogs(void) { } #define lockup_detector_online_cpu NULL #define lockup_detector_offline_cpu NULL #endif /* CONFIG_SOFTLOCKUP_DETECTOR */ #ifdef CONFIG_DETECT_HUNG_TASK void reset_hung_task_detector(void); #else static inline void reset_hung_task_detector(void) { } #endif /* * The run state of the lockup detectors is controlled by the content of the * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. * * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and * 'soft_watchdog_user_enabled' are variables that are only used as an * 'interface' between the parameters in /proc/sys/kernel and the internal * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is * handled differently because its value is not boolean, and the lockup * detectors are 'suspended' while 'watchdog_thresh' is equal zero. */ #define NMI_WATCHDOG_ENABLED_BIT 0 #define SOFT_WATCHDOG_ENABLED_BIT 1 #define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT) #define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT) #if defined(CONFIG_HARDLOCKUP_DETECTOR) extern void hardlockup_detector_disable(void); extern unsigned int hardlockup_panic; #else static inline void hardlockup_detector_disable(void) {} #endif #if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) # define NMI_WATCHDOG_SYSCTL_PERM 0644 #else # define NMI_WATCHDOG_SYSCTL_PERM 0444 #endif #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) extern void arch_touch_nmi_watchdog(void); extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); extern void hardlockup_detector_perf_disable(void); extern void hardlockup_detector_perf_enable(void); extern void hardlockup_detector_perf_cleanup(void); extern int hardlockup_detector_perf_init(void); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } static inline void hardlockup_detector_perf_disable(void) { } static inline void hardlockup_detector_perf_enable(void) { } static inline void hardlockup_detector_perf_cleanup(void) { } # if !defined(CONFIG_HAVE_NMI_WATCHDOG) static inline int hardlockup_detector_perf_init(void) { return -ENODEV; } static inline void arch_touch_nmi_watchdog(void) {} # else static inline int hardlockup_detector_perf_init(void) { return 0; } # endif #endif void watchdog_nmi_stop(void); void watchdog_nmi_start(void); int watchdog_nmi_probe(void); int watchdog_nmi_enable(unsigned int cpu); void watchdog_nmi_disable(unsigned int cpu); void lockup_detector_reconfigure(void); /** * touch_nmi_watchdog - restart NMI watchdog timeout. * * If the architecture supports the NMI watchdog, touch_nmi_watchdog() * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. */ static inline void touch_nmi_watchdog(void) { arch_touch_nmi_watchdog(); touch_softlockup_watchdog(); } /* * Create trigger_all_cpu_backtrace() out of the arch-provided * base function. Return whether such support was available, * to allow calling code to fall back to some other mechanism: */ #ifdef arch_trigger_cpumask_backtrace static inline bool trigger_all_cpu_backtrace(void) { arch_trigger_cpumask_backtrace(cpu_online_mask, false); return true; } static inline bool trigger_allbutself_cpu_backtrace(void) { arch_trigger_cpumask_backtrace(cpu_online_mask, true); return true; } static inline bool trigger_cpumask_backtrace(struct cpumask *mask) { arch_trigger_cpumask_backtrace(mask, false); return true; } static inline bool trigger_single_cpu_backtrace(int cpu) { arch_trigger_cpumask_backtrace(cpumask_of(cpu), false); return true; } /* generic implementation */ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self, void (*raise)(cpumask_t *mask)); bool nmi_cpu_backtrace(struct pt_regs *regs); #else static inline bool trigger_all_cpu_backtrace(void) { return false; } static inline bool trigger_allbutself_cpu_backtrace(void) { return false; } static inline bool trigger_cpumask_backtrace(struct cpumask *mask) { return false; } static inline bool trigger_single_cpu_backtrace(int cpu) { return false; } #endif #ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF u64 hw_nmi_get_sample_period(int watchdog_thresh); #endif #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ defined(CONFIG_HARDLOCKUP_DETECTOR) void watchdog_update_hrtimer_threshold(u64 period); #else static inline void watchdog_update_hrtimer_threshold(u64 period) { } #endif struct ctl_table; int proc_watchdog(struct ctl_table *, int, void *, size_t *, loff_t *); int proc_nmi_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *); int proc_soft_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *); int proc_watchdog_thresh(struct ctl_table *, int , void *, size_t *, loff_t *); int proc_watchdog_cpumask(struct ctl_table *, int, void *, size_t *, loff_t *); #ifdef CONFIG_HAVE_ACPI_APEI_NMI #include <asm/nmi.h> #endif #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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* md.h : kernel internal structure of the Linux MD driver Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman */ #ifndef _MD_MD_H #define _MD_MD_H #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/badblocks.h> #include <linux/kobject.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/wait.h> #include <linux/workqueue.h> #include "md-cluster.h" #define MaxSector (~(sector_t)0) /* * These flags should really be called "NO_RETRY" rather than * "FAILFAST" because they don't make any promise about time lapse, * only about the number of retries, which will be zero. * REQ_FAILFAST_DRIVER is not included because * Commit: 4a27446f3e39 ("[SCSI] modify scsi to handle new fail fast flags.") * seems to suggest that the errors it avoids retrying should usually * be retried. */ #define MD_FAILFAST (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT) /* * The struct embedded in rdev is used to serialize IO. */ struct serial_in_rdev { struct rb_root_cached serial_rb; spinlock_t serial_lock; wait_queue_head_t serial_io_wait; }; /* * MD's 'extended' device */ struct md_rdev { struct list_head same_set; /* RAID devices within the same set */ sector_t sectors; /* Device size (in 512bytes sectors) */ struct mddev *mddev; /* RAID array if running */ int last_events; /* IO event timestamp */ /* * If meta_bdev is non-NULL, it means that a separate device is * being used to store the metadata (superblock/bitmap) which * would otherwise be contained on the same device as the data (bdev). */ struct block_device *meta_bdev; struct block_device *bdev; /* block device handle */ struct page *sb_page, *bb_page; int sb_loaded; __u64 sb_events; sector_t data_offset; /* start of data in array */ sector_t new_data_offset;/* only relevant while reshaping */ sector_t sb_start; /* offset of the super block (in 512byte sectors) */ int sb_size; /* bytes in the superblock */ int preferred_minor; /* autorun support */ struct kobject kobj; /* A device can be in one of three states based on two flags: * Not working: faulty==1 in_sync==0 * Fully working: faulty==0 in_sync==1 * Working, but not * in sync with array * faulty==0 in_sync==0 * * It can never have faulty==1, in_sync==1 * This reduces the burden of testing multiple flags in many cases */ unsigned long flags; /* bit set of 'enum flag_bits' bits. */ wait_queue_head_t blocked_wait; int desc_nr; /* descriptor index in the superblock */ int raid_disk; /* role of device in array */ int new_raid_disk; /* role that the device will have in * the array after a level-change completes. */ int saved_raid_disk; /* role that device used to have in the * array and could again if we did a partial * resync from the bitmap */ union { sector_t recovery_offset;/* If this device has been partially * recovered, this is where we were * up to. */ sector_t journal_tail; /* If this device is a journal device, * this is the journal tail (journal * recovery start point) */ }; atomic_t nr_pending; /* number of pending requests. * only maintained for arrays that * support hot removal */ atomic_t read_errors; /* number of consecutive read errors that * we have tried to ignore. */ time64_t last_read_error; /* monotonic time since our * last read error */ atomic_t corrected_errors; /* number of corrected read errors, * for reporting to userspace and storing * in superblock. */ struct serial_in_rdev *serial; /* used for raid1 io serialization */ struct work_struct del_work; /* used for delayed sysfs removal */ struct kernfs_node *sysfs_state; /* handle for 'state' * sysfs entry */ /* handle for 'unacknowledged_bad_blocks' sysfs dentry */ struct kernfs_node *sysfs_unack_badblocks; /* handle for 'bad_blocks' sysfs dentry */ struct kernfs_node *sysfs_badblocks; struct badblocks badblocks; struct { short offset; /* Offset from superblock to start of PPL. * Not used by external metadata. */ unsigned int size; /* Size in sectors of the PPL space */ sector_t sector; /* First sector of the PPL space */ } ppl; }; enum flag_bits { Faulty, /* device is known to have a fault */ In_sync, /* device is in_sync with rest of array */ Bitmap_sync, /* ..actually, not quite In_sync. Need a * bitmap-based recovery to get fully in sync. * The bit is only meaningful before device * has been passed to pers->hot_add_disk. */ WriteMostly, /* Avoid reading if at all possible */ AutoDetected, /* added by auto-detect */ Blocked, /* An error occurred but has not yet * been acknowledged by the metadata * handler, so don't allow writes * until it is cleared */ WriteErrorSeen, /* A write error has been seen on this * device */ FaultRecorded, /* Intermediate state for clearing * Blocked. The Fault is/will-be * recorded in the metadata, but that * metadata hasn't been stored safely * on disk yet. */ BlockedBadBlocks, /* A writer is blocked because they * found an unacknowledged bad-block. * This can safely be cleared at any * time, and the writer will re-check. * It may be set at any time, and at * worst the writer will timeout and * re-check. So setting it as * accurately as possible is good, but * not absolutely critical. */ WantReplacement, /* This device is a candidate to be * hot-replaced, either because it has * reported some faults, or because * of explicit request. */ Replacement, /* This device is a replacement for * a want_replacement device with same * raid_disk number. */ Candidate, /* For clustered environments only: * This device is seen locally but not * by the whole cluster */ Journal, /* This device is used as journal for * raid-5/6. * Usually, this device should be faster * than other devices in the array */ ClusterRemove, RemoveSynchronized, /* synchronize_rcu() was called after * this device was known to be faulty, * so it is safe to remove without * another synchronize_rcu() call. */ ExternalBbl, /* External metadata provides bad * block management for a disk */ FailFast, /* Minimal retries should be attempted on * this device, so use REQ_FAILFAST_DEV. * Also don't try to repair failed reads. * It is expects that no bad block log * is present. */ LastDev, /* Seems to be the last working dev as * it didn't fail, so don't use FailFast * any more for metadata */ CollisionCheck, /* * check if there is collision between raid1 * serial bios. */ }; static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors, sector_t *first_bad, int *bad_sectors) { if (unlikely(rdev->badblocks.count)) { int rv = badblocks_check(&rdev->badblocks, rdev->data_offset + s, sectors, first_bad, bad_sectors); if (rv) *first_bad -= rdev->data_offset; return rv; } return 0; } extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); struct md_cluster_info; /* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */ enum mddev_flags { MD_ARRAY_FIRST_USE, /* First use of array, needs initialization */ MD_CLOSING, /* If set, we are closing the array, do not open * it then */ MD_JOURNAL_CLEAN, /* A raid with journal is already clean */ MD_HAS_JOURNAL, /* The raid array has journal feature set */ MD_CLUSTER_RESYNC_LOCKED, /* cluster raid only, which means node * already took resync lock, need to * release the lock */ MD_FAILFAST_SUPPORTED, /* Using MD_FAILFAST on metadata writes is * supported as calls to md_error() will * never cause the array to become failed. */ MD_HAS_PPL, /* The raid array has PPL feature set */ MD_HAS_MULTIPLE_PPLS, /* The raid array has multiple PPLs feature set */ MD_ALLOW_SB_UPDATE, /* md_check_recovery is allowed to update * the metadata without taking reconfig_mutex. */ MD_UPDATING_SB, /* md_check_recovery is updating the metadata * without explicitly holding reconfig_mutex. */ MD_NOT_READY, /* do_md_run() is active, so 'array_state' * must not report that array is ready yet */ MD_BROKEN, /* This is used in RAID-0/LINEAR only, to stop * I/O in case an array member is gone/failed. */ }; enum mddev_sb_flags { MD_SB_CHANGE_DEVS, /* Some device status has changed */ MD_SB_CHANGE_CLEAN, /* transition to or from 'clean' */ MD_SB_CHANGE_PENDING, /* switch from 'clean' to 'active' in progress */ MD_SB_NEED_REWRITE, /* metadata write needs to be repeated */ }; #define NR_SERIAL_INFOS 8 /* record current range of serialize IOs */ struct serial_info { struct rb_node node; sector_t start; /* start sector of rb node */ sector_t last; /* end sector of rb node */ sector_t _subtree_last; /* highest sector in subtree of rb node */ }; struct mddev { void *private; struct md_personality *pers; dev_t unit; int md_minor; struct list_head disks; unsigned long flags; unsigned long sb_flags; int suspended; atomic_t active_io; int ro; int sysfs_active; /* set when sysfs deletes * are happening, so run/ * takeover/stop are not safe */ struct gendisk *gendisk; struct kobject kobj; int hold_active; #define UNTIL_IOCTL 1 #define UNTIL_STOP 2 /* Superblock information */ int major_version, minor_version, patch_version; int persistent; int external; /* metadata is * managed externally */ char metadata_type[17]; /* externally set*/ int chunk_sectors; time64_t ctime, utime; int level, layout; char clevel[16]; int raid_disks; int max_disks; sector_t dev_sectors; /* used size of * component devices */ sector_t array_sectors; /* exported array size */ int external_size; /* size managed * externally */ __u64 events; /* If the last 'event' was simply a clean->dirty transition, and * we didn't write it to the spares, then it is safe and simple * to just decrement the event count on a dirty->clean transition. * So we record that possibility here. */ int can_decrease_events; char uuid[16]; /* If the array is being reshaped, we need to record the * new shape and an indication of where we are up to. * This is written to the superblock. * If reshape_position is MaxSector, then no reshape is happening (yet). */ sector_t reshape_position; int delta_disks, new_level, new_layout; int new_chunk_sectors; int reshape_backwards; struct md_thread *thread; /* management thread */ struct md_thread *sync_thread; /* doing resync or reconstruct */ /* 'last_sync_action' is initialized to "none". It is set when a * sync operation (i.e "data-check", "requested-resync", "resync", * "recovery", or "reshape") is started. It holds this value even * when the sync thread is "frozen" (interrupted) or "idle" (stopped * or finished). It is overwritten when a new sync operation is begun. */ char *last_sync_action; sector_t curr_resync; /* last block scheduled */ /* As resync requests can complete out of order, we cannot easily track * how much resync has been completed. So we occasionally pause until * everything completes, then set curr_resync_completed to curr_resync. * As such it may be well behind the real resync mark, but it is a value * we are certain of. */ sector_t curr_resync_completed; unsigned long resync_mark; /* a recent timestamp */ sector_t resync_mark_cnt;/* blocks written at resync_mark */ sector_t curr_mark_cnt; /* blocks scheduled now */ sector_t resync_max_sectors; /* may be set by personality */ atomic64_t resync_mismatches; /* count of sectors where * parity/replica mismatch found */ /* allow user-space to request suspension of IO to regions of the array */ sector_t suspend_lo; sector_t suspend_hi; /* if zero, use the system-wide default */ int sync_speed_min; int sync_speed_max; /* resync even though the same disks are shared among md-devices */ int parallel_resync; int ok_start_degraded; unsigned long recovery; /* If a RAID personality determines that recovery (of a particular * device) will fail due to a read error on the source device, it * takes a copy of this number and does not attempt recovery again * until this number changes. */ int recovery_disabled; int in_sync; /* know to not need resync */ /* 'open_mutex' avoids races between 'md_open' and 'do_md_stop', so * that we are never stopping an array while it is open. * 'reconfig_mutex' protects all other reconfiguration. * These locks are separate due to conflicting interactions * with bdev->bd_mutex. * Lock ordering is: * reconfig_mutex -> bd_mutex * bd_mutex -> open_mutex: e.g. __blkdev_get -> md_open */ struct mutex open_mutex; struct mutex reconfig_mutex; atomic_t active; /* general refcount */ atomic_t openers; /* number of active opens */ int changed; /* True if we might need to * reread partition info */ int degraded; /* whether md should consider * adding a spare */ atomic_t recovery_active; /* blocks scheduled, but not written */ wait_queue_head_t recovery_wait; sector_t recovery_cp; sector_t resync_min; /* user requested sync * starts here */ sector_t resync_max; /* resync should pause * when it gets here */ struct kernfs_node *sysfs_state; /* handle for 'array_state' * file in sysfs. */ struct kernfs_node *sysfs_action; /* handle for 'sync_action' */ struct kernfs_node *sysfs_completed; /*handle for 'sync_completed' */ struct kernfs_node *sysfs_degraded; /*handle for 'degraded' */ struct kernfs_node *sysfs_level; /*handle for 'level' */ struct work_struct del_work; /* used for delayed sysfs removal */ /* "lock" protects: * flush_bio transition from NULL to !NULL * rdev superblocks, events * clearing MD_CHANGE_* * in_sync - and related safemode and MD_CHANGE changes * pers (also protected by reconfig_mutex and pending IO). * clearing ->bitmap * clearing ->bitmap_info.file * changing ->resync_{min,max} * setting MD_RECOVERY_RUNNING (which interacts with resync_{min,max}) */ spinlock_t lock; wait_queue_head_t sb_wait; /* for waiting on superblock updates */ atomic_t pending_writes; /* number of active superblock writes */ unsigned int safemode; /* if set, update "clean" superblock * when no writes pending. */ unsigned int safemode_delay; struct timer_list safemode_timer; struct percpu_ref writes_pending; int sync_checkers; /* # of threads checking writes_pending */ struct request_queue *queue; /* for plugging ... */ struct bitmap *bitmap; /* the bitmap for the device */ struct { struct file *file; /* the bitmap file */ loff_t offset; /* offset from superblock of * start of bitmap. May be * negative, but not '0' * For external metadata, offset * from start of device. */ unsigned long space; /* space available at this offset */ loff_t default_offset; /* this is the offset to use when * hot-adding a bitmap. It should * eventually be settable by sysfs. */ unsigned long default_space; /* space available at * default offset */ struct mutex mutex; unsigned long chunksize; unsigned long daemon_sleep; /* how many jiffies between updates? */ unsigned long max_write_behind; /* write-behind mode */ int external; int nodes; /* Maximum number of nodes in the cluster */ char cluster_name[64]; /* Name of the cluster */ } bitmap_info; atomic_t max_corr_read_errors; /* max read retries */ struct list_head all_mddevs; struct attribute_group *to_remove; struct bio_set bio_set; struct bio_set sync_set; /* for sync operations like * metadata and bitmap writes */ /* Generic flush handling. * The last to finish preflush schedules a worker to submit * the rest of the request (without the REQ_PREFLUSH flag). */ struct bio *flush_bio; atomic_t flush_pending; ktime_t start_flush, last_flush; /* last_flush is when the last completed * flush was started. */ struct work_struct flush_work; struct work_struct event_work; /* used by dm to report failure event */ mempool_t *serial_info_pool; void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); struct md_cluster_info *cluster_info; unsigned int good_device_nr; /* good device num within cluster raid */ unsigned int noio_flag; /* for memalloc scope API */ bool has_superblocks:1; bool fail_last_dev:1; bool serialize_policy:1; }; enum recovery_flags { /* * If neither SYNC or RESHAPE are set, then it is a recovery. */ MD_RECOVERY_RUNNING, /* a thread is running, or about to be started */ MD_RECOVERY_SYNC, /* actually doing a resync, not a recovery */ MD_RECOVERY_RECOVER, /* doing recovery, or need to try it. */ MD_RECOVERY_INTR, /* resync needs to be aborted for some reason */ MD_RECOVERY_DONE, /* thread is done and is waiting to be reaped */ MD_RECOVERY_NEEDED, /* we might need to start a resync/recover */ MD_RECOVERY_REQUESTED, /* user-space has requested a sync (used with SYNC) */ MD_RECOVERY_CHECK, /* user-space request for check-only, no repair */ MD_RECOVERY_RESHAPE, /* A reshape is happening */ MD_RECOVERY_FROZEN, /* User request to abort, and not restart, any action */ MD_RECOVERY_ERROR, /* sync-action interrupted because io-error */ MD_RECOVERY_WAIT, /* waiting for pers->start() to finish */ MD_RESYNCING_REMOTE, /* remote node is running resync thread */ }; static inline int __must_check mddev_lock(struct mddev *mddev) { return mutex_lock_interruptible(&mddev->reconfig_mutex); } /* Sometimes we need to take the lock in a situation where * failure due to interrupts is not acceptable. */ static inline void mddev_lock_nointr(struct mddev *mddev) { mutex_lock(&mddev->reconfig_mutex); } static inline int mddev_trylock(struct mddev *mddev) { return mutex_trylock(&mddev->reconfig_mutex); } extern void mddev_unlock(struct mddev *mddev); static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors) { atomic_add(nr_sectors, &bdev->bd_disk->sync_io); } static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors) { atomic_add(nr_sectors, &bio->bi_disk->sync_io); } struct md_personality { char *name; int level; struct list_head list; struct module *owner; bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio); /* * start up works that do NOT require md_thread. tasks that * requires md_thread should go into start() */ int (*run)(struct mddev *mddev); /* start up works that require md threads */ int (*start)(struct mddev *mddev); void (*free)(struct mddev *mddev, void *priv); void (*status)(struct seq_file *seq, struct mddev *mddev); /* error_handler must set ->faulty and clear ->in_sync * if appropriate, and should abort recovery if needed */ void (*error_handler)(struct mddev *mddev, struct md_rdev *rdev); int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev); int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev); int (*spare_active) (struct mddev *mddev); sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped); int (*resize) (struct mddev *mddev, sector_t sectors); sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks); int (*check_reshape) (struct mddev *mddev); int (*start_reshape) (struct mddev *mddev); void (*finish_reshape) (struct mddev *mddev); void (*update_reshape_pos) (struct mddev *mddev); /* quiesce suspends or resumes internal processing. * 1 - stop new actions and wait for action io to complete * 0 - return to normal behaviour */ void (*quiesce) (struct mddev *mddev, int quiesce); /* takeover is used to transition an array from one * personality to another. The new personality must be able * to handle the data in the current layout. * e.g. 2drive raid1 -> 2drive raid5 * ndrive raid5 -> degraded n+1drive raid6 with special layout * If the takeover succeeds, a new 'private' structure is returned. * This needs to be installed and then ->run used to activate the * array. */ void *(*takeover) (struct mddev *mddev); /* Changes the consistency policy of an active array. */ int (*change_consistency_policy)(struct mddev *mddev, const char *buf); }; struct md_sysfs_entry { struct attribute attr; ssize_t (*show)(struct mddev *, char *); ssize_t (*store)(struct mddev *, const char *, size_t); }; extern struct attribute_group md_bitmap_group; static inline struct kernfs_node *sysfs_get_dirent_safe(struct kernfs_node *sd, char *name) { if (sd) return sysfs_get_dirent(sd, name); return sd; } static inline void sysfs_notify_dirent_safe(struct kernfs_node *sd) { if (sd) sysfs_notify_dirent(sd); } static inline char * mdname (struct mddev * mddev) { return mddev->gendisk ? mddev->gendisk->disk_name : "mdX"; } static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; if (!test_bit(Replacement, &rdev->flags) && !test_bit(Journal, &rdev->flags) && mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); } else return 0; } static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; if (!test_bit(Replacement, &rdev->flags) && !test_bit(Journal, &rdev->flags) && mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); sysfs_remove_link(&mddev->kobj, nm); } } /* * iterates through some rdev ringlist. It's safe to remove the * current 'rdev'. Dont touch 'tmp' though. */ #define rdev_for_each_list(rdev, tmp, head) \ list_for_each_entry_safe(rdev, tmp, head, same_set) /* * iterates through the 'same array disks' ringlist */ #define rdev_for_each(rdev, mddev) \ list_for_each_entry(rdev, &((mddev)->disks), same_set) #define rdev_for_each_safe(rdev, tmp, mddev) \ list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set) #define rdev_for_each_rcu(rdev, mddev) \ list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set) struct md_thread { void (*run) (struct md_thread *thread); struct mddev *mddev; wait_queue_head_t wqueue; unsigned long flags; struct task_struct *tsk; unsigned long timeout; void *private; }; #define THREAD_WAKEUP 0 static inline void safe_put_page(struct page *p) { if (p) put_page(p); } extern int register_md_personality(struct md_personality *p); extern int unregister_md_personality(struct md_personality *p); extern int register_md_cluster_operations(struct md_cluster_operations *ops, struct module *module); extern int unregister_md_cluster_operations(void); extern int md_setup_cluster(struct mddev *mddev, int nodes); extern void md_cluster_stop(struct mddev *mddev); extern struct md_thread *md_register_thread( void (*run)(struct md_thread *thread), struct mddev *mddev, const char *name); extern void md_unregister_thread(struct md_thread **threadp); extern void md_wakeup_thread(struct md_thread *thread); extern void md_check_recovery(struct mddev *mddev); extern void md_reap_sync_thread(struct mddev *mddev); extern int mddev_init_writes_pending(struct mddev *mddev); extern bool md_write_start(struct mddev *mddev, struct bio *bi); extern void md_write_inc(struct mddev *mddev, struct bio *bi); extern void md_write_end(struct mddev *mddev); extern void md_done_sync(struct mddev *mddev, int blocks, int ok); extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); extern int md_super_wait(struct mddev *mddev); extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, struct page *page, int op, int op_flags, bool metadata_op); extern void md_do_sync(struct md_thread *thread); extern void md_new_event(struct mddev *mddev); extern void md_allow_write(struct mddev *mddev); extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); extern int md_integrity_register(struct mddev *mddev); extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); extern void mddev_init(struct mddev *mddev); extern int md_run(struct mddev *mddev); extern int md_start(struct mddev *mddev); extern void md_stop(struct mddev *mddev); extern void md_stop_writes(struct mddev *mddev); extern int md_rdev_init(struct md_rdev *rdev); extern void md_rdev_clear(struct md_rdev *rdev); extern void md_handle_request(struct mddev *mddev, struct bio *bio); extern void mddev_suspend(struct mddev *mddev); extern void mddev_resume(struct mddev *mddev); extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, struct mddev *mddev); extern void md_reload_sb(struct mddev *mddev, int raid_disk); extern void md_update_sb(struct mddev *mddev, int force); extern void md_kick_rdev_from_array(struct md_rdev * rdev); extern void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev, bool is_suspend); extern void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev, bool is_suspend); struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr); struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev); static inline bool is_mddev_broken(struct md_rdev *rdev, const char *md_type) { int flags = rdev->bdev->bd_disk->flags; if (!(flags & GENHD_FL_UP)) { if (!test_and_set_bit(MD_BROKEN, &rdev->mddev->flags)) pr_warn("md: %s: %s array has a missing/failed member\n", mdname(rdev->mddev), md_type); return true; } return false; } static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev) { int faulty = test_bit(Faulty, &rdev->flags); if (atomic_dec_and_test(&rdev->nr_pending) && faulty) { set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); } } extern struct md_cluster_operations *md_cluster_ops; static inline int mddev_is_clustered(struct mddev *mddev) { return mddev->cluster_info && mddev->bitmap_info.nodes > 1; } /* clear unsupported mddev_flags */ static inline void mddev_clear_unsupported_flags(struct mddev *mddev, unsigned long unsupported_flags) { mddev->flags &= ~unsupported_flags; } static inline void mddev_check_writesame(struct mddev *mddev, struct bio *bio) { if (bio_op(bio) == REQ_OP_WRITE_SAME && !bio->bi_disk->queue->limits.max_write_same_sectors) mddev->queue->limits.max_write_same_sectors = 0; } static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio) { if (bio_op(bio) == REQ_OP_WRITE_ZEROES && !bio->bi_disk->queue->limits.max_write_zeroes_sectors) mddev->queue->limits.max_write_zeroes_sectors = 0; } struct mdu_array_info_s; struct mdu_disk_info_s; extern int mdp_major; void md_autostart_arrays(int part); int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info); int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info); int do_md_run(struct mddev *mddev); extern const struct block_device_operations md_fops; #endif /* _MD_MD_H */
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 /* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * Released under the General Public License (GPL). * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_mutex (while writing or truncating, not reading or faulting) * mm->mmap_lock * page->flags PG_locked (lock_page) * (see huegtlbfs below) * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share) * mapping->i_mmap_rwsem * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * anon_vma->rwsem * mm->page_table_lock or pte_lock * pgdat->lru_lock (in mark_page_accessed, isolate_lru_page) * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) * mem_cgroup_{begin,end}_page_stat (memcg->move_lock) * i_pages lock (widely used) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mutex (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * * hugetlbfs PageHuge() pages take locks in this order: * mapping->i_mmap_rwsem * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * page->flags PG_locked (lock_page) */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <asm/tlbflush.h> #include <trace/events/tlb.h> #include "internal.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->num_children = 0; anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against page_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from page_lock_anon_vma_read(). This orders: * * page_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_link(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in page_lock_anon_vma_read() * and that may actually touch the spinlock even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. * * This must be called with the mmap_lock held for reading. */ int __anon_vma_prepare(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } /* * This is a useful helper function for locking the anon_vma root as * we traverse the vma->anon_vma_chain, looping over anon_vma's that * have the same vma. * * Such anon_vma's should have the same root, so you'd expect to see * just a single mutex_lock for the whole traversal. */ static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) { struct anon_vma *new_root = anon_vma->root; if (new_root != root) { if (WARN_ON_ONCE(root)) up_write(&root->rwsem); root = new_root; down_write(&root->rwsem); } return root; } static inline void unlock_anon_vma_root(struct anon_vma *root) { if (root) up_write(&root->rwsem); } /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * * anon_vma_clone() is called by __vma_split(), __split_vma(), copy_vma() and * anon_vma_fork(). The first three want an exact copy of src, while the last * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call, * we can identify this case by checking (!dst->anon_vma && src->anon_vma). * * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find * and reuse existing anon_vma which has no vmas and only one child anon_vma. * This prevents degradation of anon_vma hierarchy to endless linear chain in * case of constantly forking task. On the other hand, an anon_vma with more * than one child isn't reused even if there was no alive vma, thus rmap * walker has a good chance of avoiding scanning the whole hierarchy when it * searches where page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; struct anon_vma *root = NULL; list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { struct anon_vma *anon_vma; avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!avc)) { unlock_anon_vma_root(root); root = NULL; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; } anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma); /* * Reuse existing anon_vma if it has no vma and only one * anon_vma child. * * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && src->anon_vma && anon_vma->num_children < 2 && anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0; enomem_failure: /* * dst->anon_vma is dropped here otherwise its degree can be incorrectly * decremented in unlink_anon_vmas(). * We can safely do this because callers of anon_vma_clone() don't care * about dst->anon_vma if anon_vma_clone() failed. */ dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ error = anon_vma_clone(vma, pvma); if (error) return error; /* An existing anon_vma has been reused, all done then. */ if (vma->anon_vma) return 0; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; /* * The root anon_vma's spinlock is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; out_error_free_anon_vma: put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; } void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *root = NULL; /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->num_children--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } if (vma->anon_vma) vma->anon_vma->num_active_vmas--; unlock_anon_vma_root(root); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->num_children); VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against page_remove_rmap() * the best this function can do is return a locked anon_vma that might * have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * page_remove_rmap() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. */ struct anon_vma *page_get_anon_vma(struct page *page) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this page is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!page_mapped(page)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to page_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with page_get_anon_vma() and then block on the mutex. */ struct anon_vma *page_lock_anon_vma_read(struct page *page) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the page is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!page_mapped(page)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!page_mapped(page)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } void page_unlock_anon_vma_read(struct anon_vma *anon_vma) { anon_vma_unlock_read(anon_vma); } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc; if (!tlb_ubc->flush_required) return; arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc; arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); mm->tlb_flush_batched = true; /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { bool should_defer = false; if (!(flags & TTU_BATCH_FLUSH)) return false; /* If remote CPUs need to be flushed then defer batch the flush */ if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids) should_defer = true; put_cpu(); return should_defer; } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { if (data_race(mm->tlb_flush_batched)) { flush_tlb_mm(mm); /* * Do not allow the compiler to re-order the clearing of * tlb_flush_batched before the tlb is flushed. */ barrier(); mm->tlb_flush_batched = false; } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /* * At what user virtual address is page expected in vma? * Caller should check the page is actually part of the vma. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; } else if (!vma->vm_file) { return -EFAULT; } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) { return -EFAULT; } return vma_address(page, vma); } pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pmd_t pmde; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); /* * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at() * without holding anon_vma lock for write. So when looking for a * genuine pmde (in which to find pte), test present and !THP together. */ pmde = *pmd; barrier(); if (!pmd_present(pmde) || pmd_trans_huge(pmde)) pmd = NULL; out: return pmd; } struct page_referenced_arg { int mapcount; int referenced; unsigned long vm_flags; struct mem_cgroup *memcg; }; /* * arg: page_referenced_arg will be passed */ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct page_referenced_arg *pra = arg; struct page_vma_mapped_walk pvmw = { .page = page, .vma = vma, .address = address, }; int referenced = 0; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; if (vma->vm_flags & VM_LOCKED) { page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } if (pvmw.pte) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) { /* * Don't treat a reference through * a sequentially read mapping as such. * If the page has been used in another mapping, * we will catch it; if this other mapping is * already gone, the unmap path will have set * PG_referenced or activated the page. */ if (likely(!(vma->vm_flags & VM_SEQ_READ))) referenced++; } } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped page? */ WARN_ON_ONCE(1); } pra->mapcount--; } if (referenced) clear_page_idle(page); if (test_and_clear_page_young(page)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) { struct page_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; if (!mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * page_referenced - test if the page was referenced * @page: the page to test * @is_locked: caller holds lock on the page * @memcg: target memory cgroup * @vm_flags: collect encountered vma->vm_flags who actually referenced the page * * Quick test_and_clear_referenced for all mappings to a page, * returns the number of ptes which referenced the page. */ int page_referenced(struct page *page, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { int we_locked = 0; struct page_referenced_arg pra = { .mapcount = total_mapcount(page), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = page_referenced_one, .arg = (void *)&pra, .anon_lock = page_lock_anon_vma_read, }; *vm_flags = 0; if (!pra.mapcount) return 0; if (!page_rmapping(page)) return 0; if (!is_locked && (!PageAnon(page) || PageKsm(page))) { we_locked = trylock_page(page); if (!we_locked) return 1; } /* * If we are reclaiming on behalf of a cgroup, skip * counting on behalf of references from different * cgroups */ if (memcg) { rwc.invalid_vma = invalid_page_referenced_vma; } rmap_walk(page, &rwc); *vm_flags = pra.vm_flags; if (we_locked) unlock_page(page); return pra.referenced; } static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct page_vma_mapped_walk pvmw = { .page = page, .vma = vma, .address = address, .flags = PVMW_SYNC, }; struct mmu_notifier_range range; int *cleaned = arg; /* * We have to assume the worse case ie pmd for invalidation. Note that * the page can not be free from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, vma_address_end(page, vma)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { int ret = 0; address = pvmw.address; if (pvmw.pte) { pte_t entry; pte_t *pte = pvmw.pte; if (!pte_dirty(*pte) && !pte_write(*pte)) continue; flush_cache_page(vma, address, pte_pfn(*pte)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(vma->vm_mm, address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t *pmd = pvmw.pmd; pmd_t entry; if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; flush_cache_page(vma, address, page_to_pfn(page)); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped page? */ WARN_ON_ONCE(1); #endif } /* * No need to call mmu_notifier_invalidate_range() as we are * downgrading page table protection not changing it to point * to a new page. * * See Documentation/vm/mmu_notifier.rst */ if (ret) (*cleaned)++; } mmu_notifier_invalidate_range_end(&range); return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { if (vma->vm_flags & VM_SHARED) return false; return true; } int page_mkclean(struct page *page) { int cleaned = 0; struct address_space *mapping; struct rmap_walk_control rwc = { .arg = (void *)&cleaned, .rmap_one = page_mkclean_one, .invalid_vma = invalid_mkclean_vma, }; BUG_ON(!PageLocked(page)); if (!page_mapped(page)) return 0; mapping = page_mapping(page); if (!mapping) return 0; rmap_walk(page, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(page_mkclean); /** * page_move_anon_rmap - move a page to our anon_vma * @page: the page to move to our anon_vma * @vma: the vma the page belongs to * * When a page belongs exclusively to one process after a COW event, * that page can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling * processes. */ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; page = compound_head(page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; /* * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg page_referenced()'s * PageAnon()) will not see one without the other. */ WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); } /** * __page_set_anon_rmap - set up new anonymous rmap * @page: Page or Hugepage to add to rmap * @vma: VM area to add page to. * @address: User virtual address of the mapping * @exclusive: the page is exclusively owned by the current process */ static void __page_set_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, int exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); if (PageAnon(page)) return; /* * If the page isn't exclusively mapped into this vma, * we must use the _oldest_ possible anon_vma for the * page mapping! */ if (!exclusive) anon_vma = anon_vma->root; anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; page->mapping = (struct address_space *) anon_vma; page->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against page_add_anon_rmap because the caller * always holds the page locked, except if called from page_dup_rmap, * in which case the page is already known to be setup. * * We have exclusion against page_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to page_add_new_anon_rmap. */ VM_BUG_ON_PAGE(page_anon_vma(page)->root != vma->anon_vma->root, page); VM_BUG_ON_PAGE(page_to_pgoff(page) != linear_page_index(vma, address), page); } /** * page_add_anon_rmap - add pte mapping to an anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @compound: charge the page as compound or small page * * The caller needs to hold the pte lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that PageAnon is not being upgraded racily to PageKsm * (but PageKsm is never downgraded to PageAnon). */ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, bool compound) { do_page_add_anon_rmap(page, vma, address, compound ? RMAP_COMPOUND : 0); } /* * Special version of the above for do_swap_page, which often runs * into pages that are exclusively owned by the current process. * Everybody else should continue to use page_add_anon_rmap above. */ void do_page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, int flags) { bool compound = flags & RMAP_COMPOUND; bool first; if (unlikely(PageKsm(page))) lock_page_memcg(page); else VM_BUG_ON_PAGE(!PageLocked(page), page); if (compound) { atomic_t *mapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageTransHuge(page), page); mapcount = compound_mapcount_ptr(page); first = atomic_inc_and_test(mapcount); } else { first = atomic_inc_and_test(&page->_mapcount); } if (first) { int nr = compound ? thp_nr_pages(page) : 1; /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption * disabled. */ if (compound) __inc_lruvec_page_state(page, NR_ANON_THPS); __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } if (unlikely(PageKsm(page))) { unlock_page_memcg(page); return; } /* address might be in next vma when migration races vma_adjust */ if (first) __page_set_anon_rmap(page, vma, address, flags & RMAP_EXCLUSIVE); else __page_check_anon_rmap(page, vma, address); } /** * page_add_new_anon_rmap - add pte mapping to a new anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @compound: charge the page as compound or small page * * Same as page_add_anon_rmap but must only be called on *new* pages. * This means the inc-and-test can be bypassed. * Page does not have to be locked. */ void page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, bool compound) { int nr = compound ? thp_nr_pages(page) : 1; VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); __SetPageSwapBacked(page); if (compound) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); /* increment count (starts at -1) */ atomic_set(compound_mapcount_ptr(page), 0); if (hpage_pincount_available(page)) atomic_set(compound_pincount_ptr(page), 0); __inc_lruvec_page_state(page, NR_ANON_THPS); } else { /* Anon THP always mapped first with PMD */ VM_BUG_ON_PAGE(PageTransCompound(page), page); /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); } __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); __page_set_anon_rmap(page, vma, address, 1); } /** * page_add_file_rmap - add pte mapping to a file page * @page: the page to add the mapping to * @compound: charge the page as compound or small page * * The caller needs to hold the pte lock. */ void page_add_file_rmap(struct page *page, bool compound) { int i, nr = 1; VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page); lock_page_memcg(page); if (compound && PageTransHuge(page)) { for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { if (atomic_inc_and_test(&page[i]._mapcount)) nr++; } if (!atomic_inc_and_test(compound_mapcount_ptr(page))) goto out; if (PageSwapBacked(page)) __inc_node_page_state(page, NR_SHMEM_PMDMAPPED); else __inc_node_page_state(page, NR_FILE_PMDMAPPED); } else { if (PageTransCompound(page) && page_mapping(page)) { VM_WARN_ON_ONCE(!PageLocked(page)); SetPageDoubleMap(compound_head(page)); if (PageMlocked(page)) clear_page_mlock(compound_head(page)); } if (!atomic_inc_and_test(&page->_mapcount)) goto out; } __mod_lruvec_page_state(page, NR_FILE_MAPPED, nr); out: unlock_page_memcg(page); } static void page_remove_file_rmap(struct page *page, bool compound) { int i, nr = 1; VM_BUG_ON_PAGE(compound && !PageHead(page), page); /* Hugepages are not counted in NR_FILE_MAPPED for now. */ if (unlikely(PageHuge(page))) { /* hugetlb pages are always mapped with pmds */ atomic_dec(compound_mapcount_ptr(page)); return; } /* page still mapped by someone else? */ if (compound && PageTransHuge(page)) { for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { if (atomic_add_negative(-1, &page[i]._mapcount)) nr++; } if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) return; if (PageSwapBacked(page)) __dec_node_page_state(page, NR_SHMEM_PMDMAPPED); else __dec_node_page_state(page, NR_FILE_PMDMAPPED); } else { if (!atomic_add_negative(-1, &page->_mapcount)) return; } /* * We use the irq-unsafe __{inc|mod}_lruvec_page_state because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ __mod_lruvec_page_state(page, NR_FILE_MAPPED, -nr); if (unlikely(PageMlocked(page))) clear_page_mlock(page); } static void page_remove_anon_compound_rmap(struct page *page) { int i, nr; if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) return; /* Hugepages are not counted in NR_ANON_PAGES for now. */ if (unlikely(PageHuge(page))) return; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; __dec_lruvec_page_state(page, NR_ANON_THPS); if (TestClearPageDoubleMap(page)) { /* * Subpages can be mapped with PTEs too. Check how many of * them are still mapped. */ for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { if (atomic_add_negative(-1, &page[i]._mapcount)) nr++; } /* * Queue the page for deferred split if at least one small * page of the compound page is unmapped, but at least one * small page is still mapped. */ if (nr && nr < thp_nr_pages(page)) deferred_split_huge_page(page); } else { nr = thp_nr_pages(page); } if (unlikely(PageMlocked(page))) clear_page_mlock(page); if (nr) __mod_lruvec_page_state(page, NR_ANON_MAPPED, -nr); } /** * page_remove_rmap - take down pte mapping from a page * @page: page to remove mapping from * @compound: uncharge the page as compound or small page * * The caller needs to hold the pte lock. */ void page_remove_rmap(struct page *page, bool compound) { lock_page_memcg(page); if (!PageAnon(page)) { page_remove_file_rmap(page, compound); goto out; } if (compound) { page_remove_anon_compound_rmap(page); goto out; } /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) goto out; /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ __dec_lruvec_page_state(page, NR_ANON_MAPPED); if (unlikely(PageMlocked(page))) clear_page_mlock(page); if (PageTransCompound(page)) deferred_split_huge_page(compound_head(page)); /* * It would be tidy to reset the PageAnon mapping here, * but that might overwrite a racing page_add_anon_rmap * which increments mapcount after us but sets mapping * before us: so leave the reset to free_unref_page, * and remember that it's only reliable while mapped. * Leaving it set also helps swapoff to reinstate ptes * faster for those pages still in swapcache. */ out: unlock_page_memcg(page); } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; struct page_vma_mapped_walk pvmw = { .page = page, .vma = vma, .address = address, }; pte_t pteval; struct page *subpage; bool ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and page_remove_rmap(), * try_to_unmap() may return false when it is about to become true, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* munlock has nothing to gain from examining un-locked vmas */ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) return true; if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && is_zone_device_page(page) && !is_device_private_page(page)) return true; if (flags & TTU_SPLIT_HUGE_PMD) { split_huge_pmd_address(vma, address, flags & TTU_SPLIT_FREEZE, page); } /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ range.end = PageKsm(page) ? address + PAGE_SIZE : vma_address_end(page, vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, range.end); if (PageHuge(page)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION /* PMD-mapped THP migration entry */ if (!pvmw.pte && (flags & TTU_MIGRATION)) { VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page); set_pmd_migration_entry(&pvmw, page); continue; } #endif /* * If the page is mlock()d, we cannot swap it out. * If it's recently referenced (perhaps page_referenced * skipped over this mm) then we should reactivate it. */ if (!(flags & TTU_IGNORE_MLOCK)) { if (vma->vm_flags & VM_LOCKED) { /* PTE-mapped THP are never mlocked */ if (!PageTransCompound(page)) { /* * Holding pte lock, we do *not* need * mmap_lock here */ mlock_vma_page(page); } ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (flags & TTU_MUNLOCK) continue; } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_PAGE(!pvmw.pte, page); subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; if (PageHuge(page) && !PageAnon(page)) { /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. */ VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { /* * huge_pmd_unshare unmapped an entire PMD * page. There is no way of knowing exactly * which PMDs may be cached for this mm, so * we must flush them all. start/end were * already adjusted above to cover this range. */ flush_cache_range(vma, range.start, range.end); flush_tlb_range(vma, range.start, range.end); mmu_notifier_invalidate_range(mm, range.start, range.end); /* * The ref count of the PMD page was dropped * which is part of the way map counting * is done for shared PMDs. Return 'true' * here. When there is no other sharing, * huge_pmd_unshare returns false and we will * unmap the actual page and drop map count * to zero. */ page_vma_mapped_walk_done(&pvmw); break; } } if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && is_zone_device_page(page)) { swp_entry_t entry; pte_t swp_pte; pteval = ptep_get_and_clear(mm, pvmw.address, pvmw.pte); /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ entry = make_migration_entry(page, 0); swp_pte = swp_entry_to_pte(entry); /* * pteval maps a zone device page and is therefore * a swap pte. */ if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. * * The assignment to subpage above was computed from a * swap PTE which results in an invalid pointer. * Since only PAGE_SIZE pages can currently be * migrated, just set it to page. This will need to be * changed when hugepage migrations to device private * memory are supported. */ subpage = page; goto discard; } /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the page. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } /* Move the dirty bit to the page. Now the pte is gone. */ if (pte_dirty(pteval)) set_page_dirty(page); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (PageHuge(page)) { hugetlb_count_sub(compound_nr(page), mm); set_huge_swap_pte_at(mm, address, pvmw.pte, pteval, vma_mmu_pagesize(vma)); } else { dec_mm_counter(mm, mm_counter(page)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(page)); /* We have to invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) { swp_entry_t entry; pte_t swp_pte; if (arch_unmap_one(mm, vma, address, pteval) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ entry = make_migration_entry(subpage, pte_write(pteval)); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(subpage) }; pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(PageSwapBacked(page) != PageSwapCache(page))) { WARN_ON_ONCE(1); ret = false; /* We have to invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); page_vma_mapped_walk_done(&pvmw); break; } /* MADV_FREE page check */ if (!PageSwapBacked(page)) { int ref_count, map_count; /* * Synchronize with gup_pte_range(): * - clear PTE; barrier; read refcount * - inc refcount; barrier; read PTE */ smp_mb(); ref_count = page_ref_count(page); map_count = page_mapcount(page); /* * Order reads for page refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); /* * The only page refs must be one from isolation * plus the rmap(s) (dropped by discard:). */ if (ref_count == 1 + map_count && !PageDirty(page)) { /* Invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); dec_mm_counter(mm, MM_ANONPAGES); goto discard; } /* * If the page was redirtied, it cannot be * discarded. Remap the page to page table. */ set_pte_at(mm, address, pvmw.pte, pteval); SetPageSwapBacked(page); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (swap_duplicate(entry) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (arch_unmap_one(mm, vma, address, pteval) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); /* Invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); } else { /* * This is a locked file-backed page, thus it cannot * be removed from the page cache and replaced by a new * page before mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table to * point at new page while a device still is using this * page. * * See Documentation/vm/mmu_notifier.rst */ dec_mm_counter(mm, mm_counter_file(page)); } discard: /* * No need to call mmu_notifier_invalidate_range() it has be * done above for all cases requiring it to happen under page * table lock before mmu_notifier_invalidate_range_end() * * See Documentation/vm/mmu_notifier.rst */ page_remove_rmap(subpage, PageHuge(page)); put_page(page); } mmu_notifier_invalidate_range_end(&range); return ret; } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { return vma_is_temporary_stack(vma); } static int page_not_mapped(struct page *page) { return !page_mapped(page); } /** * try_to_unmap - try to remove all page table mappings to a page * @page: the page to get unmapped * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * page, used in the pageout path. Caller must hold the page lock. * * If unmap is successful, return true. Otherwise, false. */ bool try_to_unmap(struct page *page, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if ((flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE)) && !PageKsm(page) && PageAnon(page)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(page, &rwc); else rmap_walk(page, &rwc); /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and page_remove_rmap(), * try_to_unmap() may return false when it is about to become true, * if page table locking is skipped: use TTU_SYNC to wait for that. */ return !page_mapcount(page); } /** * try_to_munlock - try to munlock a page * @page: the page to be munlocked * * Called from munlock code. Checks all of the VMAs mapping the page * to make sure nobody else has this page mlocked. The page will be * returned with PG_mlocked cleared if no other vmas have it mlocked. */ void try_to_munlock(struct page *page) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)TTU_MUNLOCK, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); rmap_walk(page, &rwc); } void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); } static struct anon_vma *rmap_walk_anon_lock(struct page *page, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(page); /* * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = page_anon_vma(page); if (!anon_vma) return NULL; anon_vma_lock_read(anon_vma); return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @page: the page to be handled * @rwc: control variable according to each walk type * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the anon_vma struct it points to. * * When called from try_to_munlock(), the mmap_lock of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. */ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; if (locked) { anon_vma = page_anon_vma(page); /* anon_vma disappear under us? */ VM_BUG_ON_PAGE(!anon_vma, page); } else { anon_vma = rmap_walk_anon_lock(page, rwc); } if (!anon_vma) return; pgoff_start = page_to_pgoff(page); pgoff_end = pgoff_start + thp_nr_pages(page) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(page, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(page)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @page: the page to be handled * @rwc: control variable according to each walk type * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the address_space struct it points to. * * When called from try_to_munlock(), the mmap_lock of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. */ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = page_mapping(page); pgoff_t pgoff_start, pgoff_end; struct vm_area_struct *vma; /* * The page lock not only makes sure that page->mapping cannot * suddenly be NULLified by truncation, it makes sure that the * structure at mapping cannot be freed and reused yet, * so we can safely take mapping->i_mmap_rwsem. */ VM_BUG_ON_PAGE(!PageLocked(page), page); if (!mapping) return; pgoff_start = page_to_pgoff(page); pgoff_end = pgoff_start + thp_nr_pages(page) - 1; if (!locked) i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(page, vma); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(page, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(page)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } void rmap_walk(struct page *page, struct rmap_walk_control *rwc) { if (unlikely(PageKsm(page))) rmap_walk_ksm(page, rwc); else if (PageAnon(page)) rmap_walk_anon(page, rwc, false); else rmap_walk_file(page, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_PAGE(PageKsm(page), page); if (PageAnon(page)) rmap_walk_anon(page, rwc, true); else rmap_walk_file(page, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { struct anon_vma *anon_vma = vma->anon_vma; int first; BUG_ON(!PageLocked(page)); BUG_ON(!anon_vma); /* address might be in next vma when migration races vma_adjust */ first = atomic_inc_and_test(compound_mapcount_ptr(page)); if (first) __page_set_anon_rmap(page, vma, address, 0); } void hugepage_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { BUG_ON(address < vma->vm_start || address >= vma->vm_end); atomic_set(compound_mapcount_ptr(page), 0); if (hpage_pincount_available(page)) atomic_set(compound_pincount_ptr(page), 0); __page_set_anon_rmap(page, vma, address, 1); } #endif /* CONFIG_HUGETLB_PAGE */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H #include <linux/mmdebug.h> #include <linux/mmzone.h> #include <linux/stddef.h> #include <linux/linkage.h> #include <linux/topology.h> struct vm_area_struct; /* * In case of changes, please don't forget to update * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c */ /* Plain integer GFP bitmasks. Do not use this directly. */ #define ___GFP_DMA 0x01u #define ___GFP_HIGHMEM 0x02u #define ___GFP_DMA32 0x04u #define ___GFP_MOVABLE 0x08u #define ___GFP_RECLAIMABLE 0x10u #define ___GFP_HIGH 0x20u #define ___GFP_IO 0x40u #define ___GFP_FS 0x80u #define ___GFP_ZERO 0x100u #define ___GFP_ATOMIC 0x200u #define ___GFP_DIRECT_RECLAIM 0x400u #define ___GFP_KSWAPD_RECLAIM 0x800u #define ___GFP_WRITE 0x1000u #define ___GFP_NOWARN 0x2000u #define ___GFP_RETRY_MAYFAIL 0x4000u #define ___GFP_NOFAIL 0x8000u #define ___GFP_NORETRY 0x10000u #define ___GFP_MEMALLOC 0x20000u #define ___GFP_COMP 0x40000u #define ___GFP_NOMEMALLOC 0x80000u #define ___GFP_HARDWALL 0x100000u #define ___GFP_THISNODE 0x200000u #define ___GFP_ACCOUNT 0x400000u #ifdef CONFIG_LOCKDEP #define ___GFP_NOLOCKDEP 0x800000u #else #define ___GFP_NOLOCKDEP 0 #endif /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* * Physical address zone modifiers (see linux/mmzone.h - low four bits) * * Do not put any conditional on these. If necessary modify the definitions * without the underscores and use them consistently. The definitions here may * be used in bit comparisons. */ #define __GFP_DMA ((__force gfp_t)___GFP_DMA) #define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) #define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) #define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ #define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) /** * DOC: Page mobility and placement hints * * Page mobility and placement hints * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * These flags provide hints about how mobile the page is. Pages with similar * mobility are placed within the same pageblocks to minimise problems due * to external fragmentation. * * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be * moved by page migration during memory compaction or can be reclaimed. * * %__GFP_RECLAIMABLE is used for slab allocations that specify * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. * * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible, * these pages will be spread between local zones to avoid all the dirty * pages being in one zone (fair zone allocation policy). * * %__GFP_HARDWALL enforces the cpuset memory allocation policy. * * %__GFP_THISNODE forces the allocation to be satisfied from the requested * node with no fallbacks or placement policy enforcements. * * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) #define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) /** * DOC: Watermark modifiers * * Watermark modifiers -- controls access to emergency reserves * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * %__GFP_HIGH indicates that the caller is high-priority and that granting * the request is necessary before the system can make forward progress. * For example, creating an IO context to clean pages. * * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is * high priority. Users are typically interrupt handlers. This may be * used in conjunction with %__GFP_HIGH * * %__GFP_MEMALLOC allows access to all memory. This should only be used when * the caller guarantees the allocation will allow more memory to be freed * very shortly e.g. process exiting or swapping. Users either should * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). * Users of this flag have to be extremely careful to not deplete the reserve * completely and implement a throttling mechanism which controls the * consumption of the reserve based on the amount of freed memory. * Usage of a pre-allocated pool (e.g. mempool) should be always considered * before using this flag. * * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. * This takes precedence over the %__GFP_MEMALLOC flag if both are set. */ #define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) #define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) #define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /** * DOC: Reclaim modifiers * * Reclaim modifiers * ~~~~~~~~~~~~~~~~~ * Please note that all the following flags are only applicable to sleepable * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). * * %__GFP_IO can start physical IO. * * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the * allocator recursing into the filesystem which might already be holding * locks. * * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. * This flag can be cleared to avoid unnecessary delays when a fallback * option is available. * * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when * the low watermark is reached and have it reclaim pages until the high * watermark is reached. A caller may wish to clear this flag when fallback * options are available and the reclaim is likely to disrupt the system. The * canonical example is THP allocation where a fallback is cheap but * reclaim/compaction may cause indirect stalls. * * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * * The default allocator behavior depends on the request size. We have a concept * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER). * !costly allocations are too essential to fail so they are implicitly * non-failing by default (with some exceptions like OOM victims might fail so * the caller still has to check for failures) while costly requests try to be * not disruptive and back off even without invoking the OOM killer. * The following three modifiers might be used to override some of these * implicit rules * * %__GFP_NORETRY: The VM implementation will try only very lightweight * memory direct reclaim to get some memory under memory pressure (thus * it can sleep). It will avoid disruptive actions like OOM killer. The * caller must handle the failure which is quite likely to happen under * heavy memory pressure. The flag is suitable when failure can easily be * handled at small cost, such as reduced throughput * * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim * procedures that have previously failed if there is some indication * that progress has been made else where. It can wait for other * tasks to attempt high level approaches to freeing memory such as * compaction (which removes fragmentation) and page-out. * There is still a definite limit to the number of retries, but it is * a larger limit than with %__GFP_NORETRY. * Allocations with this flag may fail, but only when there is * genuinely little unused memory. While these allocations do not * directly trigger the OOM killer, their failure indicates that * the system is likely to need to use the OOM killer soon. The * caller must handle failure, but can reasonably do so by failing * a higher-level request, or completing it only in a much less * efficient manner. * If the allocation does fail, and the caller is in a position to * free some non-essential memory, doing so could benefit the system * as a whole. * * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller * cannot handle allocation failures. The allocation could block * indefinitely but will never return with failure. Testing for * failure is pointless. * New users should be evaluated carefully (and the flag should be * used only when there is no reasonable failure policy) but it is * definitely preferable to use the flag rather than opencode endless * loop around allocator. * Using this flag for costly allocations is _highly_ discouraged. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) #define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ #define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) #define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) /** * DOC: Action modifiers * * Action modifiers * ~~~~~~~~~~~~~~~~ * * %__GFP_NOWARN suppresses allocation failure reports. * * %__GFP_COMP address compound page metadata. * * %__GFP_ZERO returns a zeroed page on success. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ #define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** * DOC: Useful GFP flag combinations * * Useful GFP flag combinations * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Useful GFP flag combinations that are commonly used. It is recommended * that subsystems start with one of these combinations and then set/clear * %__GFP_FOO flags as necessary. * * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower * watermark is applied to allow access to "atomic reserves". * The current implementation doesn't support NMI and few other strict * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. * * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. * * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is * accounted to kmemcg. * * %GFP_NOWAIT is for kernel allocations that should not stall for direct * reclaim, start physical IO or use any filesystem callback. * * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages * that do not require the starting of any physical IO. * Please try to avoid using this flag directly and instead use * memalloc_noio_{save,restore} to mark the whole scope which cannot * perform any IO with a short explanation why. All allocation requests * will inherit GFP_NOIO implicitly. * * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. * Please try to avoid using this flag directly and instead use * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't * recurse into the FS layer with a short explanation why. All allocation * requests will inherit GFP_NOFS implicitly. * * %GFP_USER is for userspace allocations that also need to be directly * accessibly by the kernel or hardware. It is typically used by hardware * for buffers that are mapped to userspace (e.g. graphics) that hardware * still must DMA to. cpuset limits are enforced for these allocations. * * %GFP_DMA exists for historical reasons and should be avoided where possible. * The flags indicates that the caller requires that the lowest zone be * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but * it would require careful auditing as some users really require it and * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the * lowest zone as a type of emergency reserve. * * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit * address. * * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, * do not need to be directly accessible by the kernel but that cannot * move once in use. An example may be a hardware allocation that maps * data directly into userspace but has no addressing limitations. * * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not * need direct access to but can use kmap() when access is required. They * are expected to be movable via page reclaim or page migration. Typically, * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE. * * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They * are compound allocations that will generally fail quickly if memory is not * available and will not wake kswapd/kcompactd on failure. The _LIGHT * version does not attempt reclaim/compaction at all and is by default used * in page fault path, while the non-light is used by khugepaged. */ #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) #define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) #define GFP_NOIO (__GFP_RECLAIM) #define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) #define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) #define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) #define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) #define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } /** * gfpflags_normal_context - is gfp_flags a normal sleepable context? * @gfp_flags: gfp_flags to test * * Test whether @gfp_flags indicates that the allocation is from the * %current context and allowed to sleep. * * An allocation being allowed to block doesn't mean it owns the %current * context. When direct reclaim path tries to allocate memory, the * allocation context is nested inside whatever %current was doing at the * time of the original allocation. The nested allocation may be allowed * to block but modifying anything %current owns can corrupt the outer * context's expectations. * * %true result from this function indicates that the allocation context * can sleep and use anything that's associated with %current. */ static inline bool gfpflags_normal_context(const gfp_t gfp_flags) { return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == __GFP_DIRECT_RECLAIM; } #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else #define OPT_ZONE_HIGHMEM ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA #define OPT_ZONE_DMA ZONE_DMA #else #define OPT_ZONE_DMA ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA32 #define OPT_ZONE_DMA32 ZONE_DMA32 #else #define OPT_ZONE_DMA32 ZONE_NORMAL #endif /* * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT * bits long and there are 16 of them to cover all possible combinations of * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. * But GFP_MOVABLE is not only a zone specifier but also an allocation * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1". * * bit result * ================= * 0x0 => NORMAL * 0x1 => DMA or NORMAL * 0x2 => HIGHMEM or NORMAL * 0x3 => BAD (DMA+HIGHMEM) * 0x4 => DMA32 or NORMAL * 0x5 => BAD (DMA+DMA32) * 0x6 => BAD (HIGHMEM+DMA32) * 0x7 => BAD (HIGHMEM+DMA32+DMA) * 0x8 => NORMAL (MOVABLE+0) * 0x9 => DMA or NORMAL (MOVABLE+DMA) * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) * 0xb => BAD (MOVABLE+HIGHMEM+DMA) * 0xc => DMA32 or NORMAL (MOVABLE+DMA32) * 0xd => BAD (MOVABLE+DMA32+DMA) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) * * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms. */ #if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4 /* ZONE_DEVICE is not a valid GFP zone specifier */ #define GFP_ZONES_SHIFT 2 #else #define GFP_ZONES_SHIFT ZONES_SHIFT #endif #if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG #error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer #endif #define GFP_ZONE_TABLE ( \ (ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \ | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \ | (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \ | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\ | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\ ) /* * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per * entry starting with bit 0. Bit is set if the combination is not * allowed. */ #define GFP_ZONE_BAD ( \ 1 << (___GFP_DMA | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32) \ | 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \ ) static inline enum zone_type gfp_zone(gfp_t flags) { enum zone_type z; int bit = (__force int) (flags & GFP_ZONEMASK); z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) & ((1 << GFP_ZONES_SHIFT) - 1); VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1); return z; } /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such * can allocate highmem pages, the *get*page*() variants return * virtual kernel addresses to the allocated page(s). */ static inline int gfp_zonelist(gfp_t flags) { #ifdef CONFIG_NUMA if (unlikely(flags & __GFP_THISNODE)) return ZONELIST_NOFALLBACK; #endif return ZONELIST_FALLBACK; } /* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets * optimized to &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags); } #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { return 0; } #endif struct page * __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, nodemask_t *nodemask); static inline struct page * __alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid) { return __alloc_pages_nodemask(gfp_mask, order, preferred_nid, NULL); } /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). */ static inline struct page * __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid)); return __alloc_pages(gfp_mask, order, nid); } /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_node(nid, gfp_mask, order); } #ifdef CONFIG_NUMA extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order); static inline struct page * alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_current(gfp_mask, order); } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, int node, bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node(numa_node_id(), gfp_mask, order); } #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) #define __get_dma_pages(gfp_mask, order) \ __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); extern void free_unref_page(struct page *page); extern void free_unref_page_list(struct list_head *list); struct page_frag_cache; extern void __page_frag_cache_drain(struct page *page, unsigned int count); extern void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask); extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) void page_alloc_init(void); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are * enabled, it is set to __GFP_BITS_MASK while the system is running. During * hibernation, it is used by PM to avoid I/O during memory allocation while * devices are suspended. */ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); extern void pm_restrict_gfp_mask(void); extern void pm_restore_gfp_mask(void); #ifdef CONFIG_PM_SLEEP extern bool pm_suspended_storage(void); #else static inline bool pm_suspended_storage(void) { return false; } #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #endif void free_contig_range(unsigned long pfn, unsigned int nr_pages); #ifdef CONFIG_CMA /* CMA stuff */ extern void init_cma_reserved_pageblock(struct page *page); #endif #endif /* __LINUX_GFP_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PART_STAT_H #define _LINUX_PART_STAT_H #include <linux/genhd.h> struct disk_stats { u64 nsecs[NR_STAT_GROUPS]; unsigned long sectors[NR_STAT_GROUPS]; unsigned long ios[NR_STAT_GROUPS]; unsigned long merges[NR_STAT_GROUPS]; unsigned long io_ticks; local_t in_flight[2]; }; /* * Macros to operate on percpu disk statistics: * * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters and should * be called between disk_stat_lock() and disk_stat_unlock(). * * part_stat_read() can be called at any time. */ #define part_stat_lock() preempt_disable() #define part_stat_unlock() preempt_enable() #define part_stat_get_cpu(part, field, cpu) \ (per_cpu_ptr((part)->dkstats, (cpu))->field) #define part_stat_get(part, field) \ part_stat_get_cpu(part, field, smp_processor_id()) #define part_stat_read(part, field) \ ({ \ typeof((part)->dkstats->field) res = 0; \ unsigned int _cpu; \ for_each_possible_cpu(_cpu) \ res += per_cpu_ptr((part)->dkstats, _cpu)->field; \ res; \ }) static inline void part_stat_set_all(struct hd_struct *part, int value) { int i; for_each_possible_cpu(i) memset(per_cpu_ptr(part->dkstats, i), value, sizeof(struct disk_stats)); } #define part_stat_read_accum(part, field) \ (part_stat_read(part, field[STAT_READ]) + \ part_stat_read(part, field[STAT_WRITE]) + \ part_stat_read(part, field[STAT_DISCARD])) #define __part_stat_add(part, field, addnd) \ __this_cpu_add((part)->dkstats->field, addnd) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ if ((part)->partno) \ __part_stat_add(&part_to_disk((part))->part0, \ field, addnd); \ } while (0) #define part_stat_dec(gendiskp, field) \ part_stat_add(gendiskp, field, -1) #define part_stat_inc(gendiskp, field) \ part_stat_add(gendiskp, field, 1) #define part_stat_sub(gendiskp, field, subnd) \ part_stat_add(gendiskp, field, -subnd) #define part_stat_local_dec(gendiskp, field) \ local_dec(&(part_stat_get(gendiskp, field))) #define part_stat_local_inc(gendiskp, field) \ local_inc(&(part_stat_get(gendiskp, field))) #define part_stat_local_read(gendiskp, field) \ local_read(&(part_stat_get(gendiskp, field))) #define part_stat_local_read_cpu(gendiskp, field, cpu) \ local_read(&(part_stat_get_cpu(gendiskp, field, cpu))) #endif /* _LINUX_PART_STAT_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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM signal #if !defined(_TRACE_SIGNAL_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SIGNAL_H #include <linux/signal.h> #include <linux/sched.h> #include <linux/tracepoint.h> #define TP_STORE_SIGINFO(__entry, info) \ do { \ if (info == SEND_SIG_NOINFO) { \ __entry->errno = 0; \ __entry->code = SI_USER; \ } else if (info == SEND_SIG_PRIV) { \ __entry->errno = 0; \ __entry->code = SI_KERNEL; \ } else { \ __entry->errno = info->si_errno; \ __entry->code = info->si_code; \ } \ } while (0) #ifndef TRACE_HEADER_MULTI_READ enum { TRACE_SIGNAL_DELIVERED, TRACE_SIGNAL_IGNORED, TRACE_SIGNAL_ALREADY_PENDING, TRACE_SIGNAL_OVERFLOW_FAIL, TRACE_SIGNAL_LOSE_INFO, }; #endif /** * signal_generate - called when a signal is generated * @sig: signal number * @info: pointer to struct siginfo * @task: pointer to struct task_struct * @group: shared or private * @result: TRACE_SIGNAL_* * * Current process sends a 'sig' signal to 'task' process with * 'info' siginfo. If 'info' is SEND_SIG_NOINFO or SEND_SIG_PRIV, * 'info' is not a pointer and you can't access its field. Instead, * SEND_SIG_NOINFO means that si_code is SI_USER, and SEND_SIG_PRIV * means that si_code is SI_KERNEL. */ TRACE_EVENT(signal_generate, TP_PROTO(int sig, struct kernel_siginfo *info, struct task_struct *task, int group, int result), TP_ARGS(sig, info, task, group, result), TP_STRUCT__entry( __field( int, sig ) __field( int, errno ) __field( int, code ) __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, group ) __field( int, result ) ), TP_fast_assign( __entry->sig = sig; TP_STORE_SIGINFO(__entry, info); memcpy(__entry->comm, task->comm, TASK_COMM_LEN); __entry->pid = task->pid; __entry->group = group; __entry->result = result; ), TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d grp=%d res=%d", __entry->sig, __entry->errno, __entry->code, __entry->comm, __entry->pid, __entry->group, __entry->result) ); /** * signal_deliver - called when a signal is delivered * @sig: signal number * @info: pointer to struct siginfo * @ka: pointer to struct k_sigaction * * A 'sig' signal is delivered to current process with 'info' siginfo, * and it will be handled by 'ka'. ka->sa.sa_handler can be SIG_IGN or * SIG_DFL. * Note that some signals reported by signal_generate tracepoint can be * lost, ignored or modified (by debugger) before hitting this tracepoint. * This means, this can show which signals are actually delivered, but * matching generated signals and delivered signals may not be correct. */ TRACE_EVENT(signal_deliver, TP_PROTO(int sig, struct kernel_siginfo *info, struct k_sigaction *ka), TP_ARGS(sig, info, ka), TP_STRUCT__entry( __field( int, sig ) __field( int, errno ) __field( int, code ) __field( unsigned long, sa_handler ) __field( unsigned long, sa_flags ) ), TP_fast_assign( __entry->sig = sig; TP_STORE_SIGINFO(__entry, info); __entry->sa_handler = (unsigned long)ka->sa.sa_handler; __entry->sa_flags = ka->sa.sa_flags; ), TP_printk("sig=%d errno=%d code=%d sa_handler=%lx sa_flags=%lx", __entry->sig, __entry->errno, __entry->code, __entry->sa_handler, __entry->sa_flags) ); #endif /* _TRACE_SIGNAL_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Wrapper functions for accessing the file_struct fd array. */ #ifndef __LINUX_FILE_H #define __LINUX_FILE_H #include <linux/compiler.h> #include <linux/types.h> #include <linux/posix_types.h> #include <linux/errno.h> struct file; extern void fput(struct file *); extern void fput_many(struct file *, unsigned int); struct file_operations; struct task_struct; struct vfsmount; struct dentry; struct inode; struct path; extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); static inline void fput_light(struct file *file, int fput_needed) { if (fput_needed) fput(file); } struct fd { struct file *file; unsigned int flags; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 static inline void fdput(struct fd fd) { if (fd.flags & FDPUT_FPUT) fput(fd.file); } extern struct file *fget(unsigned int fd); extern struct file *fget_many(unsigned int fd, unsigned int refs); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern unsigned long __fdget(unsigned int fd); extern unsigned long __fdget_raw(unsigned int fd); extern unsigned long __fdget_pos(unsigned int fd); extern void __f_unlock_pos(struct file *); static inline struct fd __to_fd(unsigned long v) { return (struct fd){(struct file *)(v & ~3),v & 3}; } static inline struct fd fdget(unsigned int fd) { return __to_fd(__fdget(fd)); } static inline struct fd fdget_raw(unsigned int fd) { return __to_fd(__fdget_raw(fd)); } static inline struct fd fdget_pos(int fd) { return __to_fd(__fdget_pos(fd)); } static inline void fdput_pos(struct fd f) { if (f.flags & FDPUT_POS_UNLOCK) __f_unlock_pos(f.file); fdput(f); } extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); extern void fd_install(unsigned int fd, struct file *file); extern int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags); static inline int receive_fd_user(struct file *file, int __user *ufd, unsigned int o_flags) { if (ufd == NULL) return -EFAULT; return __receive_fd(-1, file, ufd, o_flags); } static inline int receive_fd(struct file *file, unsigned int o_flags) { return __receive_fd(-1, file, NULL, o_flags); } static inline int receive_fd_replace(int fd, struct file *file, unsigned int o_flags) { return __receive_fd(fd, file, NULL, o_flags); } extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; #endif /* __LINUX_FILE_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H #include <linux/mm.h> #include <linux/percpu_counter.h> #include <linux/atomic.h> #include <uapi/linux/mman.h> /* * Arrange for legacy / undefined architecture specific flags to be * ignored by mmap handling code. */ #ifndef MAP_32BIT #define MAP_32BIT 0 #endif #ifndef MAP_HUGE_2MB #define MAP_HUGE_2MB 0 #endif #ifndef MAP_HUGE_1GB #define MAP_HUGE_1GB 0 #endif #ifndef MAP_UNINITIALIZED #define MAP_UNINITIALIZED 0 #endif #ifndef MAP_SYNC #define MAP_SYNC 0 #endif /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ | MAP_FIXED \ | MAP_ANONYMOUS \ | MAP_DENYWRITE \ | MAP_EXECUTABLE \ | MAP_UNINITIALIZED \ | MAP_GROWSDOWN \ | MAP_LOCKED \ | MAP_NORESERVE \ | MAP_POPULATE \ | MAP_NONBLOCK \ | MAP_STACK \ | MAP_HUGETLB \ | MAP_32BIT \ | MAP_HUGE_2MB \ | MAP_HUGE_1GB) extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP extern s32 vm_committed_as_batch; extern void mm_compute_batch(int overcommit_policy); #else #define vm_committed_as_batch 0 static inline void mm_compute_batch(int overcommit_policy) { } #endif unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) { vm_acct_memory(-pages); } /* * Allow architectures to handle additional protection and flag bits. The * overriding macros must be defined in the arch-specific asm/mman.h file. */ #ifndef arch_calc_vm_prot_bits #define arch_calc_vm_prot_bits(prot, pkey) 0 #endif #ifndef arch_calc_vm_flag_bits #define arch_calc_vm_flag_bits(flags) 0 #endif #ifndef arch_vm_get_page_prot #define arch_vm_get_page_prot(vm_flags) __pgprot(0) #endif #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have * already been masked out. * * Returns true if the prot flags are valid */ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0; } #define arch_validate_prot arch_validate_prot #endif #ifndef arch_validate_flags /* * This is called from mmap() and mprotect() with the updated vma->vm_flags. * * Returns true if the VM_* flags are valid. */ static inline bool arch_validate_flags(unsigned long flags) { return true; } #define arch_validate_flags arch_validate_flags #endif /* * Optimisation macro. It is equivalent to: * (x & bit1) ? bit2 : 0 * but this version is faster. * ("bit1" and "bit2" must be single bits) */ #define _calc_vm_trans(x, bit1, bit2) \ ((!(bit1) || !(bit2)) ? 0 : \ ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \ : ((x) & (bit1)) / ((bit1) / (bit2)))) /* * Combine the mmap "prot" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { return _calc_vm_trans(prot, PROT_READ, VM_READ ) | _calc_vm_trans(prot, PROT_WRITE, VM_WRITE) | _calc_vm_trans(prot, PROT_EXEC, VM_EXEC) | arch_calc_vm_prot_bits(prot, pkey); } /* * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_flag_bits(unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | arch_calc_vm_flag_bits(flags); } unsigned long vm_commit_limit(void); #endif /* _LINUX_MMAN_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 #undef TRACE_SYSTEM #define TRACE_SYSTEM neigh #if !defined(_TRACE_NEIGH_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NEIGH_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <net/neighbour.h> #define neigh_state_str(state) \ __print_symbolic(state, \ { NUD_INCOMPLETE, "incomplete" }, \ { NUD_REACHABLE, "reachable" }, \ { NUD_STALE, "stale" }, \ { NUD_DELAY, "delay" }, \ { NUD_PROBE, "probe" }, \ { NUD_FAILED, "failed" }, \ { NUD_NOARP, "noarp" }, \ { NUD_PERMANENT, "permanent"}) TRACE_EVENT(neigh_create, TP_PROTO(struct neigh_table *tbl, struct net_device *dev, const void *pkey, const struct neighbour *n, bool exempt_from_gc), TP_ARGS(tbl, dev, pkey, n, exempt_from_gc), TP_STRUCT__entry( __field(u32, family) __dynamic_array(char, dev, IFNAMSIZ ) __field(int, entries) __field(u8, created) __field(u8, gc_exempt) __array(u8, primary_key4, 4) __array(u8, primary_key6, 16) ), TP_fast_assign( struct in6_addr *pin6; __be32 *p32; __entry->family = tbl->family; __assign_str(dev, (dev ? dev->name : "NULL")); __entry->entries = atomic_read(&tbl->gc_entries); __entry->created = n != NULL; __entry->gc_exempt = exempt_from_gc; pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (tbl->family == AF_INET) *p32 = *(__be32 *)pkey; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)pkey; } #endif ), TP_printk("family %d dev %s entries %d primary_key4 %pI4 primary_key6 %pI6c created %d gc_exempt %d", __entry->family, __get_str(dev), __entry->entries, __entry->primary_key4, __entry->primary_key6, __entry->created, __entry->gc_exempt) ); TRACE_EVENT(neigh_update, TP_PROTO(struct neighbour *n, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid), TP_ARGS(n, lladdr, new, flags, nlmsg_pid), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __array(u8, new_lladdr, MAX_ADDR_LEN) __field(u8, new_state) __field(u32, update_flags) __field(u32, pid) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev, (n->dev ? n->dev->name : "NULL")); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->updated; __entry->used = n->used; if (lladdr) memcpy(__entry->new_lladdr, lladdr, lladdr_len); __entry->new_state = new; __entry->update_flags = flags; __entry->pid = nlmsg_pid; ), TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " "confirmed %lu updated %lu used %lu new_lladdr %s " "new_state %s update_flags %02x pid %d", __entry->family, __get_str(dev), __print_hex_str(__entry->lladdr, __entry->lladdr_len), __entry->flags, neigh_state_str(__entry->nud_state), __entry->type, __entry->dead, __entry->refcnt, __entry->primary_key4, __entry->primary_key6, __entry->confirmed, __entry->updated, __entry->used, __print_hex_str(__entry->new_lladdr, __entry->lladdr_len), neigh_state_str(__entry->new_state), __entry->update_flags, __entry->pid) ); DECLARE_EVENT_CLASS(neigh__update, TP_PROTO(struct neighbour *n, int err), TP_ARGS(n, err), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __field(u32, err) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev, (n->dev ? n->dev->name : "NULL")); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->updated; __entry->used = n->used; __entry->err = err; ), TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " "confirmed %lu updated %lu used %lu err %d", __entry->family, __get_str(dev), __print_hex_str(__entry->lladdr, __entry->lladdr_len), __entry->flags, neigh_state_str(__entry->nud_state), __entry->type, __entry->dead, __entry->refcnt, __entry->primary_key4, __entry->primary_key6, __entry->confirmed, __entry->updated, __entry->used, __entry->err) ); DEFINE_EVENT(neigh__update, neigh_update_done, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_timer_handler, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_event_send_done, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_event_send_dead, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_cleanup_and_release, TP_PROTO(struct neighbour *neigh, int rc), TP_ARGS(neigh, rc) ); #endif /* _TRACE_NEIGH_H */ /* This part must be outside protection */ #include <trace/define_trace.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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_CRED_H #define _LINUX_CRED_H #include <linux/capability.h> #include <linux/init.h> #include <linux/key.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/sched.h> #include <linux/sched/user.h> struct cred; struct inode; /* * COW Supplementary groups list */ struct group_info { atomic_t usage; int ngroups; kgid_t gid[0]; } __randomize_layout; /** * get_group_info - Get a reference to a group info structure * @group_info: The group info to reference * * This gets a reference to a set of supplementary groups. * * If the caller is accessing a task's credentials, they must hold the RCU read * lock when reading. */ static inline struct group_info *get_group_info(struct group_info *gi) { atomic_inc(&gi->usage); return gi; } /** * put_group_info - Release a reference to a group info structure * @group_info: The group info to release */ #define put_group_info(group_info) \ do { \ if (atomic_dec_and_test(&(group_info)->usage)) \ groups_free(group_info); \ } while (0) extern struct group_info init_groups; #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); extern int groups_search(const struct group_info *, kgid_t); extern int set_current_groups(struct group_info *); extern void set_groups(struct cred *, struct group_info *); extern bool may_setgroups(void); extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { } static inline int in_group_p(kgid_t grp) { return 1; } static inline int in_egroup_p(kgid_t grp) { return 1; } static inline int groups_search(const struct group_info *group_info, kgid_t grp) { return 1; } #endif /* * The security context of a task * * The parts of the context break down into two categories: * * (1) The objective context of a task. These parts are used when some other * task is attempting to affect this one. * * (2) The subjective context. These details are used when the task is acting * upon another object, be that a file, a task, a key or whatever. * * Note that some members of this structure belong to both categories - the * LSM security pointer for instance. * * A task has two security pointers. task->real_cred points to the objective * context that defines that task's actual details. The objective part of this * context is used whenever that task is acted upon. * * task->cred points to the subjective context that defines the details of how * that task is going to act upon another object. This may be overridden * temporarily to point to another security context, but normally points to the * same context as task->real_cred. */ struct cred { atomic_t usage; #ifdef CONFIG_DEBUG_CREDENTIALS atomic_t subscribers; /* number of processes subscribed */ void *put_addr; unsigned magic; #define CRED_MAGIC 0x43736564 #define CRED_MAGIC_DEAD 0x44656144 #endif kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ kgid_t sgid; /* saved GID of the task */ kuid_t euid; /* effective UID of the task */ kgid_t egid; /* effective GID of the task */ kuid_t fsuid; /* UID for VFS ops */ kgid_t fsgid; /* GID for VFS ops */ unsigned securebits; /* SUID-less security management */ kernel_cap_t cap_inheritable; /* caps our children can inherit */ kernel_cap_t cap_permitted; /* caps we're permitted */ kernel_cap_t cap_effective; /* caps we can actually use */ kernel_cap_t cap_bset; /* capability bounding set */ kernel_cap_t cap_ambient; /* Ambient capability set */ #ifdef CONFIG_KEYS unsigned char jit_keyring; /* default keyring to attach requested * keys to */ struct key *session_keyring; /* keyring inherited over fork */ struct key *process_keyring; /* keyring private to this process */ struct key *thread_keyring; /* keyring private to this thread */ struct key *request_key_auth; /* assumed request_key authority */ #endif #ifdef CONFIG_SECURITY void *security; /* subjective LSM security */ #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { int non_rcu; /* Can we skip RCU deletion? */ struct rcu_head rcu; /* RCU deletion hook */ }; } __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); extern int copy_creds(struct task_struct *, unsigned long); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern const struct cred *override_creds(const struct cred *); extern void revert_creds(const struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); extern int change_create_files_as(struct cred *, struct inode *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); /* * check for validity of credentials */ #ifdef CONFIG_DEBUG_CREDENTIALS extern void __invalid_creds(const struct cred *, const char *, unsigned); extern void __validate_process_creds(struct task_struct *, const char *, unsigned); extern bool creds_are_invalid(const struct cred *cred); static inline void __validate_creds(const struct cred *cred, const char *file, unsigned line) { if (unlikely(creds_are_invalid(cred))) __invalid_creds(cred, file, line); } #define validate_creds(cred) \ do { \ __validate_creds((cred), __FILE__, __LINE__); \ } while(0) #define validate_process_creds() \ do { \ __validate_process_creds(current, __FILE__, __LINE__); \ } while(0) extern void validate_creds_for_do_exit(struct task_struct *); #else static inline void validate_creds(const struct cred *cred) { } static inline void validate_creds_for_do_exit(struct task_struct *tsk) { } static inline void validate_process_creds(void) { } #endif static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, cap_intersect(cred->cap_permitted, cred->cap_inheritable)); } /** * get_new_cred - Get a reference on a new set of credentials * @cred: The new credentials to reference * * Get a reference on the specified set of new credentials. The caller must * release the reference. */ static inline struct cred *get_new_cred(struct cred *cred) { atomic_inc(&cred->usage); return cred; } /** * get_cred - Get a reference on a set of credentials * @cred: The credentials to reference * * Get a reference on the specified set of credentials. The caller must * release the reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the * usage count. The purpose of this is to attempt to catch at compile time the * accidental alteration of a set of credentials that should be considered * immutable. */ static inline const struct cred *get_cred(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; validate_creds(cred); nonconst_cred->non_rcu = 0; return get_new_cred(nonconst_cred); } static inline const struct cred *get_cred_rcu(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; if (!atomic_inc_not_zero(&nonconst_cred->usage)) return NULL; validate_creds(cred); nonconst_cred->non_rcu = 0; return cred; } /** * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. * * This takes a const pointer to a set of credentials because the credentials * on task_struct are attached by const pointers to prevent accidental * alteration of otherwise immutable credential sets. */ static inline void put_cred(const struct cred *_cred) { struct cred *cred = (struct cred *) _cred; if (cred) { validate_creds(cred); if (atomic_dec_and_test(&(cred)->usage)) __put_cred(cred); } } /** * current_cred - Access the current task's subjective credentials * * Access the subjective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_cred() \ rcu_dereference_protected(current->cred, 1) /** * current_real_cred - Access the current task's objective credentials * * Access the objective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_real_cred() \ rcu_dereference_protected(current->real_cred, 1) /** * __task_cred - Access a task's objective credentials * @task: The task to query * * Access the objective credentials of a task. The caller must hold the RCU * readlock. * * The result of this function should not be passed directly to get_cred(); * rather get_task_cred() should be used instead. */ #define __task_cred(task) \ rcu_dereference((task)->real_cred) /** * get_current_cred - Get the current task's subjective credentials * * Get the subjective credentials of the current task, pinning them so that * they can't go away. Accessing the current task's credentials directly is * not permitted. */ #define get_current_cred() \ (get_cred(current_cred())) /** * get_current_user - Get the current task's user_struct * * Get the user record of the current task, pinning it so that it can't go * away. */ #define get_current_user() \ ({ \ struct user_struct *__u; \ const struct cred *__cred; \ __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) /** * get_current_groups - Get the current task's supplementary group list * * Get the supplementary group list of the current task, pinning it so that it * can't go away. */ #define get_current_groups() \ ({ \ struct group_info *__groups; \ const struct cred *__cred; \ __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) #define task_cred_xxx(task, xxx) \ ({ \ __typeof__(((struct cred *)NULL)->xxx) ___val; \ rcu_read_lock(); \ ___val = __task_cred((task))->xxx; \ rcu_read_unlock(); \ ___val; \ }) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) #define current_cred_xxx(xxx) \ ({ \ current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) #define current_gid() (current_cred_xxx(gid)) #define current_euid() (current_cred_xxx(euid)) #define current_egid() (current_cred_xxx(egid)) #define current_suid() (current_cred_xxx(suid)) #define current_sgid() (current_cred_xxx(sgid)) #define current_fsuid() (current_cred_xxx(fsuid)) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #else static inline struct user_namespace *current_user_ns(void) { return &init_user_ns; } #endif #define current_uid_gid(_uid, _gid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_uid) = __cred->uid; \ *(_gid) = __cred->gid; \ } while(0) #define current_euid_egid(_euid, _egid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_euid) = __cred->euid; \ *(_egid) = __cred->egid; \ } while(0) #define current_fsuid_fsgid(_fsuid, _fsgid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_fsuid) = __cred->fsuid; \ *(_fsgid) = __cred->fsgid; \ } while(0) #endif /* _LINUX_CRED_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_VMACACHE_H #define __LINUX_VMACACHE_H #include <linux/sched.h> #include <linux/mm.h> static inline void vmacache_flush(struct task_struct *tsk) { memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); } extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr); #ifndef CONFIG_MMU extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, unsigned long start, unsigned long end); #endif static inline void vmacache_invalidate(struct mm_struct *mm) { mm->vmacache_seqnum++; } #endif /* __LINUX_VMACACHE_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_NOSPEC_BRANCH_H_ #define _ASM_X86_NOSPEC_BRANCH_H_ #include <linux/static_key.h> #include <linux/objtool.h> #include <linux/linkage.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/msr-index.h> #include <asm/unwind_hints.h> #include <asm/percpu.h> #define RETPOLINE_THUNK_SIZE 32 /* * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an * infinite 'pause; lfence; jmp' loop to capture speculative execution. * * This is required in various cases for retpoline and IBRS-based * mitigations for the Spectre variant 2 vulnerability. Sometimes to * eliminate potentially bogus entries from the RSB, and sometimes * purely to ensure that it doesn't get empty, which on some CPUs would * allow predictions from other (unwanted!) sources to be used. * * We define a CPP macro such that it can be used from both .S files and * inline assembly. It's possible to do a .macro and then include that * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. */ #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ /* * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN. */ #define __FILL_RETURN_SLOT \ ANNOTATE_INTRA_FUNCTION_CALL; \ call 772f; \ int3; \ 772: /* * Stuff the entire RSB. * * Google experimented with loop-unrolling and this turned out to be * the optimal version — two calls, each with their own speculation * trap should their return address end up getting used, in a loop. */ #ifdef CONFIG_X86_64 #define __FILL_RETURN_BUFFER(reg, nr) \ mov $(nr/2), reg; \ 771: \ __FILL_RETURN_SLOT \ __FILL_RETURN_SLOT \ add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \ dec reg; \ jnz 771b; \ /* barrier for jnz misprediction */ \ lfence; #else /* * i386 doesn't unconditionally have LFENCE, as such it can't * do a loop. */ #define __FILL_RETURN_BUFFER(reg, nr) \ .rept nr; \ __FILL_RETURN_SLOT; \ .endr; \ add $(BITS_PER_LONG/8) * nr, %_ASM_SP; #endif /* * Stuff a single RSB slot. * * To mitigate Post-Barrier RSB speculation, one CALL instruction must be * forced to retire before letting a RET instruction execute. * * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed * before this point. */ #define __FILL_ONE_RETURN \ __FILL_RETURN_SLOT \ add $(BITS_PER_LONG/8), %_ASM_SP; \ lfence; #ifdef __ASSEMBLY__ /* * This should be used immediately before an indirect jump/call. It tells * objtool the subsequent indirect jump/call is vouched safe for retpoline * builds. */ .macro ANNOTATE_RETPOLINE_SAFE .Lannotate_\@: .pushsection .discard.retpoline_safe _ASM_PTR .Lannotate_\@ .popsection .endm /* * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions * vs RETBleed validation. */ #define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE /* * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should * eventually turn into it's own annotation. */ .macro ANNOTATE_UNRET_END #ifdef CONFIG_DEBUG_ENTRY ANNOTATE_RETPOLINE_SAFE nop #endif .endm /* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 * attack. */ .macro JMP_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(jmp __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE #else jmp *%\reg #endif .endm .macro CALL_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \ __stringify(call __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_LFENCE #else call *%\reg #endif .endm /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS) ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \ __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \ __stringify(__FILL_ONE_RETURN), \ftr2 .Lskip_rsb_\@: .endm #ifdef CONFIG_CPU_UNRET_ENTRY #define CALL_ZEN_UNTRAIN_RET "call zen_untrain_ret" #else #define CALL_ZEN_UNTRAIN_RET "" #endif /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the * return thunk isn't mapped into the userspace tables (then again, AMD * typically has NO_MELTDOWN). * * While zen_untrain_ret() doesn't clobber anything but requires stack, * entry_ibpb() will clobber AX, CX, DX. * * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. */ .macro UNTRAIN_RET #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) ANNOTATE_UNRET_END ALTERNATIVE_2 "", \ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif .endm #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ "999:\n\t" \ ".pushsection .discard.retpoline_safe\n\t" \ _ASM_PTR " 999b\n\t" \ ".popsection\n\t" extern void __x86_return_thunk(void); extern void zen_untrain_ret(void); extern void entry_ibpb(void); #ifdef CONFIG_RETPOLINE typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN extern retpoline_thunk_t __x86_indirect_thunk_array[]; #ifdef CONFIG_X86_64 /* * Inline asm uses the %V modifier which is only in newer GCC * which is ensured when CONFIG_RETPOLINE is defined. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ "call __x86_indirect_thunk_%V[thunk_target]\n", \ X86_FEATURE_RETPOLINE, \ "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "r" (addr) #else /* CONFIG_X86_32 */ /* * For i386 we use the original ret-equivalent retpoline, because * otherwise we'll run out of registers. We don't care about CET * here, anyway. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ " jmp 904f;\n" \ " .align 16\n" \ "901: call 903f;\n" \ "902: pause;\n" \ " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ "903: lea 4(%%esp), %%esp;\n" \ " pushl %[thunk_target];\n" \ " ret;\n" \ " .align 16\n" \ "904: call 901b;\n", \ X86_FEATURE_RETPOLINE, \ "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif #else /* No retpoline for C / inline asm */ # define CALL_NOSPEC "call *%[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, SPECTRE_V2_RETPOLINE, SPECTRE_V2_LFENCE, SPECTRE_V2_EIBRS, SPECTRE_V2_EIBRS_RETPOLINE, SPECTRE_V2_EIBRS_LFENCE, SPECTRE_V2_IBRS, }; /* The indirect branch speculation control variants */ enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, SPECTRE_V2_USER_STRICT_PREFERRED, SPECTRE_V2_USER_PRCTL, SPECTRE_V2_USER_SECCOMP, }; /* The Speculative Store Bypass disable variants */ enum ssb_mitigation { SPEC_STORE_BYPASS_NONE, SPEC_STORE_BYPASS_DISABLE, SPEC_STORE_BYPASS_PRCTL, SPEC_STORE_BYPASS_SECCOMP, }; extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; static __always_inline void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) { asm volatile(ALTERNATIVE("", "wrmsr", %c[feature]) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)), [feature] "i" (feature) : "memory"); } static inline void indirect_branch_prediction_barrier(void) { u64 val = PRED_CMD_IBPB; alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); } /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; DECLARE_PER_CPU(u64, x86_spec_ctrl_current); extern void update_spec_ctrl_cond(u64 val); extern u64 spec_ctrl_current(void); /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. * * (Implemented as CPP macros due to header hell.) */ #define firmware_restrict_branch_speculation_start() \ do { \ preempt_disable(); \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current() | SPEC_CTRL_IBRS, \ X86_FEATURE_USE_IBRS_FW); \ alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \ X86_FEATURE_USE_IBPB_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ do { \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current(), \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); #include <asm/segment.h> /** * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ static __always_inline void mds_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; /* * Has to be the memory-operand variant because only that * guarantees the CPU buffer flush functionality according to * documentation. The register-operand variant does not. * Works with any segment selector, but a valid writable * data segment is the fastest variant. * * "cc" clobber is required because VERW modifies ZF. */ asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); } /** * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ static __always_inline void mds_user_clear_cpu_buffers(void) { if (static_branch_likely(&mds_user_clear)) mds_clear_cpu_buffers(); } /** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ static inline void mds_idle_clear_cpu_buffers(void) { if (static_branch_likely(&mds_idle_clear)) mds_clear_cpu_buffers(); } #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_NOSPEC_BRANCH_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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright 2003-2004 Red Hat, Inc. All rights reserved. * Copyright 2003-2004 Jeff Garzik * * libata documentation is available via 'make {ps|pdf}docs', * as Documentation/driver-api/libata.rst * * Hardware documentation available from http://www.t13.org/ */ #ifndef __LINUX_ATA_H__ #define __LINUX_ATA_H__ #include <linux/kernel.h> #include <linux/string.h> #include <linux/types.h> #include <asm/byteorder.h> /* defines only for the constants which don't work well as enums */ #define ATA_DMA_BOUNDARY 0xffffUL #define ATA_DMA_MASK 0xffffffffULL enum { /* various global constants */ ATA_MAX_DEVICES = 2, /* per bus/port */ ATA_MAX_PRD = 256, /* we could make these 256/256 */ ATA_SECT_SIZE = 512, ATA_MAX_SECTORS_128 = 128, ATA_MAX_SECTORS = 256, ATA_MAX_SECTORS_1024 = 1024, ATA_MAX_SECTORS_LBA48 = 65535,/* avoid count to be 0000h */ ATA_MAX_SECTORS_TAPE = 65535, ATA_MAX_TRIM_RNUM = 64, /* 512-byte payload / (6-byte LBA + 2-byte range per entry) */ ATA_ID_WORDS = 256, ATA_ID_CONFIG = 0, ATA_ID_CYLS = 1, ATA_ID_HEADS = 3, ATA_ID_SECTORS = 6, ATA_ID_SERNO = 10, ATA_ID_BUF_SIZE = 21, ATA_ID_FW_REV = 23, ATA_ID_PROD = 27, ATA_ID_MAX_MULTSECT = 47, ATA_ID_DWORD_IO = 48, /* before ATA-8 */ ATA_ID_TRUSTED = 48, /* ATA-8 and later */ ATA_ID_CAPABILITY = 49, ATA_ID_OLD_PIO_MODES = 51, ATA_ID_OLD_DMA_MODES = 52, ATA_ID_FIELD_VALID = 53, ATA_ID_CUR_CYLS = 54, ATA_ID_CUR_HEADS = 55, ATA_ID_CUR_SECTORS = 56, ATA_ID_MULTSECT = 59, ATA_ID_LBA_CAPACITY = 60, ATA_ID_SWDMA_MODES = 62, ATA_ID_MWDMA_MODES = 63, ATA_ID_PIO_MODES = 64, ATA_ID_EIDE_DMA_MIN = 65, ATA_ID_EIDE_DMA_TIME = 66, ATA_ID_EIDE_PIO = 67, ATA_ID_EIDE_PIO_IORDY = 68, ATA_ID_ADDITIONAL_SUPP = 69, ATA_ID_QUEUE_DEPTH = 75, ATA_ID_SATA_CAPABILITY = 76, ATA_ID_SATA_CAPABILITY_2 = 77, ATA_ID_FEATURE_SUPP = 78, ATA_ID_MAJOR_VER = 80, ATA_ID_COMMAND_SET_1 = 82, ATA_ID_COMMAND_SET_2 = 83, ATA_ID_CFSSE = 84, ATA_ID_CFS_ENABLE_1 = 85, ATA_ID_CFS_ENABLE_2 = 86, ATA_ID_CSF_DEFAULT = 87, ATA_ID_UDMA_MODES = 88, ATA_ID_HW_CONFIG = 93, ATA_ID_SPG = 98, ATA_ID_LBA_CAPACITY_2 = 100, ATA_ID_SECTOR_SIZE = 106, ATA_ID_WWN = 108, ATA_ID_LOGICAL_SECTOR_SIZE = 117, /* and 118 */ ATA_ID_COMMAND_SET_3 = 119, ATA_ID_COMMAND_SET_4 = 120, ATA_ID_LAST_LUN = 126, ATA_ID_DLF = 128, ATA_ID_CSFO = 129, ATA_ID_CFA_POWER = 160, ATA_ID_CFA_KEY_MGMT = 162, ATA_ID_CFA_MODES = 163, ATA_ID_DATA_SET_MGMT = 169, ATA_ID_SCT_CMD_XPORT = 206, ATA_ID_ROT_SPEED = 217, ATA_ID_PIO4 = (1 << 1), ATA_ID_SERNO_LEN = 20, ATA_ID_FW_REV_LEN = 8, ATA_ID_PROD_LEN = 40, ATA_ID_WWN_LEN = 8, ATA_PCI_CTL_OFS = 2, ATA_PIO0 = (1 << 0), ATA_PIO1 = ATA_PIO0 | (1 << 1), ATA_PIO2 = ATA_PIO1 | (1 << 2), ATA_PIO3 = ATA_PIO2 | (1 << 3), ATA_PIO4 = ATA_PIO3 | (1 << 4), ATA_PIO5 = ATA_PIO4 | (1 << 5), ATA_PIO6 = ATA_PIO5 | (1 << 6), ATA_PIO4_ONLY = (1 << 4), ATA_SWDMA0 = (1 << 0), ATA_SWDMA1 = ATA_SWDMA0 | (1 << 1), ATA_SWDMA2 = ATA_SWDMA1 | (1 << 2), ATA_SWDMA2_ONLY = (1 << 2), ATA_MWDMA0 = (1 << 0), ATA_MWDMA1 = ATA_MWDMA0 | (1 << 1), ATA_MWDMA2 = ATA_MWDMA1 | (1 << 2), ATA_MWDMA3 = ATA_MWDMA2 | (1 << 3), ATA_MWDMA4 = ATA_MWDMA3 | (1 << 4), ATA_MWDMA12_ONLY = (1 << 1) | (1 << 2), ATA_MWDMA2_ONLY = (1 << 2), ATA_UDMA0 = (1 << 0), ATA_UDMA1 = ATA_UDMA0 | (1 << 1), ATA_UDMA2 = ATA_UDMA1 | (1 << 2), ATA_UDMA3 = ATA_UDMA2 | (1 << 3), ATA_UDMA4 = ATA_UDMA3 | (1 << 4), ATA_UDMA5 = ATA_UDMA4 | (1 << 5), ATA_UDMA6 = ATA_UDMA5 | (1 << 6), ATA_UDMA7 = ATA_UDMA6 | (1 << 7), /* ATA_UDMA7 is just for completeness... doesn't exist (yet?). */ ATA_UDMA24_ONLY = (1 << 2) | (1 << 4), ATA_UDMA_MASK_40C = ATA_UDMA2, /* udma0-2 */ /* DMA-related */ ATA_PRD_SZ = 8, ATA_PRD_TBL_SZ = (ATA_MAX_PRD * ATA_PRD_SZ), ATA_PRD_EOT = (1 << 31), /* end-of-table flag */ ATA_DMA_TABLE_OFS = 4, ATA_DMA_STATUS = 2, ATA_DMA_CMD = 0, ATA_DMA_WR = (1 << 3), ATA_DMA_START = (1 << 0), ATA_DMA_INTR = (1 << 2), ATA_DMA_ERR = (1 << 1), ATA_DMA_ACTIVE = (1 << 0), /* bits in ATA command block registers */ ATA_HOB = (1 << 7), /* LBA48 selector */ ATA_NIEN = (1 << 1), /* disable-irq flag */ ATA_LBA = (1 << 6), /* LBA28 selector */ ATA_DEV1 = (1 << 4), /* Select Device 1 (slave) */ ATA_DEVICE_OBS = (1 << 7) | (1 << 5), /* obs bits in dev reg */ ATA_DEVCTL_OBS = (1 << 3), /* obsolete bit in devctl reg */ ATA_BUSY = (1 << 7), /* BSY status bit */ ATA_DRDY = (1 << 6), /* device ready */ ATA_DF = (1 << 5), /* device fault */ ATA_DSC = (1 << 4), /* drive seek complete */ ATA_DRQ = (1 << 3), /* data request i/o */ ATA_CORR = (1 << 2), /* corrected data error */ ATA_SENSE = (1 << 1), /* sense code available */ ATA_ERR = (1 << 0), /* have an error */ ATA_SRST = (1 << 2), /* software reset */ ATA_ICRC = (1 << 7), /* interface CRC error */ ATA_BBK = ATA_ICRC, /* pre-EIDE: block marked bad */ ATA_UNC = (1 << 6), /* uncorrectable media error */ ATA_MC = (1 << 5), /* media changed */ ATA_IDNF = (1 << 4), /* ID not found */ ATA_MCR = (1 << 3), /* media change requested */ ATA_ABORTED = (1 << 2), /* command aborted */ ATA_TRK0NF = (1 << 1), /* track 0 not found */ ATA_AMNF = (1 << 0), /* address mark not found */ ATAPI_LFS = 0xF0, /* last failed sense */ ATAPI_EOM = ATA_TRK0NF, /* end of media */ ATAPI_ILI = ATA_AMNF, /* illegal length indication */ ATAPI_IO = (1 << 1), ATAPI_COD = (1 << 0), /* ATA command block registers */ ATA_REG_DATA = 0x00, ATA_REG_ERR = 0x01, ATA_REG_NSECT = 0x02, ATA_REG_LBAL = 0x03, ATA_REG_LBAM = 0x04, ATA_REG_LBAH = 0x05, ATA_REG_DEVICE = 0x06, ATA_REG_STATUS = 0x07, ATA_REG_FEATURE = ATA_REG_ERR, /* and their aliases */ ATA_REG_CMD = ATA_REG_STATUS, ATA_REG_BYTEL = ATA_REG_LBAM, ATA_REG_BYTEH = ATA_REG_LBAH, ATA_REG_DEVSEL = ATA_REG_DEVICE, ATA_REG_IRQ = ATA_REG_NSECT, /* ATA device commands */ ATA_CMD_DEV_RESET = 0x08, /* ATAPI device reset */ ATA_CMD_CHK_POWER = 0xE5, /* check power mode */ ATA_CMD_STANDBY = 0xE2, /* place in standby power mode */ ATA_CMD_IDLE = 0xE3, /* place in idle power mode */ ATA_CMD_EDD = 0x90, /* execute device diagnostic */ ATA_CMD_DOWNLOAD_MICRO = 0x92, ATA_CMD_DOWNLOAD_MICRO_DMA = 0x93, ATA_CMD_NOP = 0x00, ATA_CMD_FLUSH = 0xE7, ATA_CMD_FLUSH_EXT = 0xEA, ATA_CMD_ID_ATA = 0xEC, ATA_CMD_ID_ATAPI = 0xA1, ATA_CMD_SERVICE = 0xA2, ATA_CMD_READ = 0xC8, ATA_CMD_READ_EXT = 0x25, ATA_CMD_READ_QUEUED = 0x26, ATA_CMD_READ_STREAM_EXT = 0x2B, ATA_CMD_READ_STREAM_DMA_EXT = 0x2A, ATA_CMD_WRITE = 0xCA, ATA_CMD_WRITE_EXT = 0x35, ATA_CMD_WRITE_QUEUED = 0x36, ATA_CMD_WRITE_STREAM_EXT = 0x3B, ATA_CMD_WRITE_STREAM_DMA_EXT = 0x3A, ATA_CMD_WRITE_FUA_EXT = 0x3D, ATA_CMD_WRITE_QUEUED_FUA_EXT = 0x3E, ATA_CMD_FPDMA_READ = 0x60, ATA_CMD_FPDMA_WRITE = 0x61, ATA_CMD_NCQ_NON_DATA = 0x63, ATA_CMD_FPDMA_SEND = 0x64, ATA_CMD_FPDMA_RECV = 0x65, ATA_CMD_PIO_READ = 0x20, ATA_CMD_PIO_READ_EXT = 0x24, ATA_CMD_PIO_WRITE = 0x30, ATA_CMD_PIO_WRITE_EXT = 0x34, ATA_CMD_READ_MULTI = 0xC4, ATA_CMD_READ_MULTI_EXT = 0x29, ATA_CMD_WRITE_MULTI = 0xC5, ATA_CMD_WRITE_MULTI_EXT = 0x39, ATA_CMD_WRITE_MULTI_FUA_EXT = 0xCE, ATA_CMD_SET_FEATURES = 0xEF, ATA_CMD_SET_MULTI = 0xC6, ATA_CMD_PACKET = 0xA0, ATA_CMD_VERIFY = 0x40, ATA_CMD_VERIFY_EXT = 0x42, ATA_CMD_WRITE_UNCORR_EXT = 0x45, ATA_CMD_STANDBYNOW1 = 0xE0, ATA_CMD_IDLEIMMEDIATE = 0xE1, ATA_CMD_SLEEP = 0xE6, ATA_CMD_INIT_DEV_PARAMS = 0x91, ATA_CMD_READ_NATIVE_MAX = 0xF8, ATA_CMD_READ_NATIVE_MAX_EXT = 0x27, ATA_CMD_SET_MAX = 0xF9, ATA_CMD_SET_MAX_EXT = 0x37, ATA_CMD_READ_LOG_EXT = 0x2F, ATA_CMD_WRITE_LOG_EXT = 0x3F, ATA_CMD_READ_LOG_DMA_EXT = 0x47, ATA_CMD_WRITE_LOG_DMA_EXT = 0x57, ATA_CMD_TRUSTED_NONDATA = 0x5B, ATA_CMD_TRUSTED_RCV = 0x5C, ATA_CMD_TRUSTED_RCV_DMA = 0x5D, ATA_CMD_TRUSTED_SND = 0x5E, ATA_CMD_TRUSTED_SND_DMA = 0x5F, ATA_CMD_PMP_READ = 0xE4, ATA_CMD_PMP_READ_DMA = 0xE9, ATA_CMD_PMP_WRITE = 0xE8, ATA_CMD_PMP_WRITE_DMA = 0xEB, ATA_CMD_CONF_OVERLAY = 0xB1, ATA_CMD_SEC_SET_PASS = 0xF1, ATA_CMD_SEC_UNLOCK = 0xF2, ATA_CMD_SEC_ERASE_PREP = 0xF3, ATA_CMD_SEC_ERASE_UNIT = 0xF4, ATA_CMD_SEC_FREEZE_LOCK = 0xF5, ATA_CMD_SEC_DISABLE_PASS = 0xF6, ATA_CMD_CONFIG_STREAM = 0x51, ATA_CMD_SMART = 0xB0, ATA_CMD_MEDIA_LOCK = 0xDE, ATA_CMD_MEDIA_UNLOCK = 0xDF, ATA_CMD_DSM = 0x06, ATA_CMD_CHK_MED_CRD_TYP = 0xD1, ATA_CMD_CFA_REQ_EXT_ERR = 0x03, ATA_CMD_CFA_WRITE_NE = 0x38, ATA_CMD_CFA_TRANS_SECT = 0x87, ATA_CMD_CFA_ERASE = 0xC0, ATA_CMD_CFA_WRITE_MULT_NE = 0xCD, ATA_CMD_REQ_SENSE_DATA = 0x0B, ATA_CMD_SANITIZE_DEVICE = 0xB4, ATA_CMD_ZAC_MGMT_IN = 0x4A, ATA_CMD_ZAC_MGMT_OUT = 0x9F, /* marked obsolete in the ATA/ATAPI-7 spec */ ATA_CMD_RESTORE = 0x10, /* Subcmds for ATA_CMD_FPDMA_RECV */ ATA_SUBCMD_FPDMA_RECV_RD_LOG_DMA_EXT = 0x01, ATA_SUBCMD_FPDMA_RECV_ZAC_MGMT_IN = 0x02, /* Subcmds for ATA_CMD_FPDMA_SEND */ ATA_SUBCMD_FPDMA_SEND_DSM = 0x00, ATA_SUBCMD_FPDMA_SEND_WR_LOG_DMA_EXT = 0x02, /* Subcmds for ATA_CMD_NCQ_NON_DATA */ ATA_SUBCMD_NCQ_NON_DATA_ABORT_QUEUE = 0x00, ATA_SUBCMD_NCQ_NON_DATA_SET_FEATURES = 0x05, ATA_SUBCMD_NCQ_NON_DATA_ZERO_EXT = 0x06, ATA_SUBCMD_NCQ_NON_DATA_ZAC_MGMT_OUT = 0x07, /* Subcmds for ATA_CMD_ZAC_MGMT_IN */ ATA_SUBCMD_ZAC_MGMT_IN_REPORT_ZONES = 0x00, /* Subcmds for ATA_CMD_ZAC_MGMT_OUT */ ATA_SUBCMD_ZAC_MGMT_OUT_CLOSE_ZONE = 0x01, ATA_SUBCMD_ZAC_MGMT_OUT_FINISH_ZONE = 0x02, ATA_SUBCMD_ZAC_MGMT_OUT_OPEN_ZONE = 0x03, ATA_SUBCMD_ZAC_MGMT_OUT_RESET_WRITE_POINTER = 0x04, /* READ_LOG_EXT pages */ ATA_LOG_DIRECTORY = 0x0, ATA_LOG_SATA_NCQ = 0x10, ATA_LOG_NCQ_NON_DATA = 0x12, ATA_LOG_NCQ_SEND_RECV = 0x13, ATA_LOG_IDENTIFY_DEVICE = 0x30, /* Identify device log pages: */ ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, /* Identify device SATA settings log:*/ ATA_LOG_DEVSLP_OFFSET = 0x30, ATA_LOG_DEVSLP_SIZE = 0x08, ATA_LOG_DEVSLP_MDAT = 0x00, ATA_LOG_DEVSLP_MDAT_MASK = 0x1F, ATA_LOG_DEVSLP_DETO = 0x01, ATA_LOG_DEVSLP_VALID = 0x07, ATA_LOG_DEVSLP_VALID_MASK = 0x80, ATA_LOG_NCQ_PRIO_OFFSET = 0x09, /* NCQ send and receive log */ ATA_LOG_NCQ_SEND_RECV_SUBCMDS_OFFSET = 0x00, ATA_LOG_NCQ_SEND_RECV_SUBCMDS_DSM = (1 << 0), ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET = 0x04, ATA_LOG_NCQ_SEND_RECV_DSM_TRIM = (1 << 0), ATA_LOG_NCQ_SEND_RECV_RD_LOG_OFFSET = 0x08, ATA_LOG_NCQ_SEND_RECV_RD_LOG_SUPPORTED = (1 << 0), ATA_LOG_NCQ_SEND_RECV_WR_LOG_OFFSET = 0x0C, ATA_LOG_NCQ_SEND_RECV_WR_LOG_SUPPORTED = (1 << 0), ATA_LOG_NCQ_SEND_RECV_ZAC_MGMT_OFFSET = 0x10, ATA_LOG_NCQ_SEND_RECV_ZAC_MGMT_OUT_SUPPORTED = (1 << 0), ATA_LOG_NCQ_SEND_RECV_ZAC_MGMT_IN_SUPPORTED = (1 << 1), ATA_LOG_NCQ_SEND_RECV_SIZE = 0x14, /* NCQ Non-Data log */ ATA_LOG_NCQ_NON_DATA_SUBCMDS_OFFSET = 0x00, ATA_LOG_NCQ_NON_DATA_ABORT_OFFSET = 0x00, ATA_LOG_NCQ_NON_DATA_ABORT_NCQ = (1 << 0), ATA_LOG_NCQ_NON_DATA_ABORT_ALL = (1 << 1), ATA_LOG_NCQ_NON_DATA_ABORT_STREAMING = (1 << 2), ATA_LOG_NCQ_NON_DATA_ABORT_NON_STREAMING = (1 << 3), ATA_LOG_NCQ_NON_DATA_ABORT_SELECTED = (1 << 4), ATA_LOG_NCQ_NON_DATA_ZAC_MGMT_OFFSET = 0x1C, ATA_LOG_NCQ_NON_DATA_ZAC_MGMT_OUT = (1 << 0), ATA_LOG_NCQ_NON_DATA_SIZE = 0x40, /* READ/WRITE LONG (obsolete) */ ATA_CMD_READ_LONG = 0x22, ATA_CMD_READ_LONG_ONCE = 0x23, ATA_CMD_WRITE_LONG = 0x32, ATA_CMD_WRITE_LONG_ONCE = 0x33, /* SETFEATURES stuff */ SETFEATURES_XFER = 0x03, XFER_UDMA_7 = 0x47, XFER_UDMA_6 = 0x46, XFER_UDMA_5 = 0x45, XFER_UDMA_4 = 0x44, XFER_UDMA_3 = 0x43, XFER_UDMA_2 = 0x42, XFER_UDMA_1 = 0x41, XFER_UDMA_0 = 0x40, XFER_MW_DMA_4 = 0x24, /* CFA only */ XFER_MW_DMA_3 = 0x23, /* CFA only */ XFER_MW_DMA_2 = 0x22, XFER_MW_DMA_1 = 0x21, XFER_MW_DMA_0 = 0x20, XFER_SW_DMA_2 = 0x12, XFER_SW_DMA_1 = 0x11, XFER_SW_DMA_0 = 0x10, XFER_PIO_6 = 0x0E, /* CFA only */ XFER_PIO_5 = 0x0D, /* CFA only */ XFER_PIO_4 = 0x0C, XFER_PIO_3 = 0x0B, XFER_PIO_2 = 0x0A, XFER_PIO_1 = 0x09, XFER_PIO_0 = 0x08, XFER_PIO_SLOW = 0x00, SETFEATURES_WC_ON = 0x02, /* Enable write cache */ SETFEATURES_WC_OFF = 0x82, /* Disable write cache */ SETFEATURES_RA_ON = 0xaa, /* Enable read look-ahead */ SETFEATURES_RA_OFF = 0x55, /* Disable read look-ahead */ /* Enable/Disable Automatic Acoustic Management */ SETFEATURES_AAM_ON = 0x42, SETFEATURES_AAM_OFF = 0xC2, SETFEATURES_SPINUP = 0x07, /* Spin-up drive */ SETFEATURES_SPINUP_TIMEOUT = 30000, /* 30s timeout for drive spin-up from PUIS */ SETFEATURES_SATA_ENABLE = 0x10, /* Enable use of SATA feature */ SETFEATURES_SATA_DISABLE = 0x90, /* Disable use of SATA feature */ /* SETFEATURE Sector counts for SATA features */ SATA_FPDMA_OFFSET = 0x01, /* FPDMA non-zero buffer offsets */ SATA_FPDMA_AA = 0x02, /* FPDMA Setup FIS Auto-Activate */ SATA_DIPM = 0x03, /* Device Initiated Power Management */ SATA_FPDMA_IN_ORDER = 0x04, /* FPDMA in-order data delivery */ SATA_AN = 0x05, /* Asynchronous Notification */ SATA_SSP = 0x06, /* Software Settings Preservation */ SATA_DEVSLP = 0x09, /* Device Sleep */ SETFEATURE_SENSE_DATA = 0xC3, /* Sense Data Reporting feature */ /* feature values for SET_MAX */ ATA_SET_MAX_ADDR = 0x00, ATA_SET_MAX_PASSWD = 0x01, ATA_SET_MAX_LOCK = 0x02, ATA_SET_MAX_UNLOCK = 0x03, ATA_SET_MAX_FREEZE_LOCK = 0x04, ATA_SET_MAX_PASSWD_DMA = 0x05, ATA_SET_MAX_UNLOCK_DMA = 0x06, /* feature values for DEVICE CONFIGURATION OVERLAY */ ATA_DCO_RESTORE = 0xC0, ATA_DCO_FREEZE_LOCK = 0xC1, ATA_DCO_IDENTIFY = 0xC2, ATA_DCO_SET = 0xC3, /* feature values for SMART */ ATA_SMART_ENABLE = 0xD8, ATA_SMART_READ_VALUES = 0xD0, ATA_SMART_READ_THRESHOLDS = 0xD1, /* feature values for Data Set Management */ ATA_DSM_TRIM = 0x01, /* password used in LBA Mid / LBA High for executing SMART commands */ ATA_SMART_LBAM_PASS = 0x4F, ATA_SMART_LBAH_PASS = 0xC2, /* ATAPI stuff */ ATAPI_PKT_DMA = (1 << 0), ATAPI_DMADIR = (1 << 2), /* ATAPI data dir: 0=to device, 1=to host */ ATAPI_CDB_LEN = 16, /* PMP stuff */ SATA_PMP_MAX_PORTS = 15, SATA_PMP_CTRL_PORT = 15, SATA_PMP_GSCR_DWORDS = 128, SATA_PMP_GSCR_PROD_ID = 0, SATA_PMP_GSCR_REV = 1, SATA_PMP_GSCR_PORT_INFO = 2, SATA_PMP_GSCR_ERROR = 32, SATA_PMP_GSCR_ERROR_EN = 33, SATA_PMP_GSCR_FEAT = 64, SATA_PMP_GSCR_FEAT_EN = 96, SATA_PMP_PSCR_STATUS = 0, SATA_PMP_PSCR_ERROR = 1, SATA_PMP_PSCR_CONTROL = 2, SATA_PMP_FEAT_BIST = (1 << 0), SATA_PMP_FEAT_PMREQ = (1 << 1), SATA_PMP_FEAT_DYNSSC = (1 << 2), SATA_PMP_FEAT_NOTIFY = (1 << 3), /* cable types */ ATA_CBL_NONE = 0, ATA_CBL_PATA40 = 1, ATA_CBL_PATA80 = 2, ATA_CBL_PATA40_SHORT = 3, /* 40 wire cable to high UDMA spec */ ATA_CBL_PATA_UNK = 4, /* don't know, maybe 80c? */ ATA_CBL_PATA_IGN = 5, /* don't know, ignore cable handling */ ATA_CBL_SATA = 6, /* SATA Status and Control Registers */ SCR_STATUS = 0, SCR_ERROR = 1, SCR_CONTROL = 2, SCR_ACTIVE = 3, SCR_NOTIFICATION = 4, /* SError bits */ SERR_DATA_RECOVERED = (1 << 0), /* recovered data error */ SERR_COMM_RECOVERED = (1 << 1), /* recovered comm failure */ SERR_DATA = (1 << 8), /* unrecovered data error */ SERR_PERSISTENT = (1 << 9), /* persistent data/comm error */ SERR_PROTOCOL = (1 << 10), /* protocol violation */ SERR_INTERNAL = (1 << 11), /* host internal error */ SERR_PHYRDY_CHG = (1 << 16), /* PHY RDY changed */ SERR_PHY_INT_ERR = (1 << 17), /* PHY internal error */ SERR_COMM_WAKE = (1 << 18), /* Comm wake */ SERR_10B_8B_ERR = (1 << 19), /* 10b to 8b decode error */ SERR_DISPARITY = (1 << 20), /* Disparity */ SERR_CRC = (1 << 21), /* CRC error */ SERR_HANDSHAKE = (1 << 22), /* Handshake error */ SERR_LINK_SEQ_ERR = (1 << 23), /* Link sequence error */ SERR_TRANS_ST_ERROR = (1 << 24), /* Transport state trans. error */ SERR_UNRECOG_FIS = (1 << 25), /* Unrecognized FIS */ SERR_DEV_XCHG = (1 << 26), /* device exchanged */ }; enum ata_prot_flags { /* protocol flags */ ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ /* taskfile protocols */ ATA_PROT_UNKNOWN = (u8)-1, ATA_PROT_NODATA = 0, ATA_PROT_PIO = ATA_PROT_FLAG_PIO, ATA_PROT_DMA = ATA_PROT_FLAG_DMA, ATA_PROT_NCQ_NODATA = ATA_PROT_FLAG_NCQ, ATA_PROT_NCQ = ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ, ATAPI_PROT_NODATA = ATA_PROT_FLAG_ATAPI, ATAPI_PROT_PIO = ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO, ATAPI_PROT_DMA = ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA, }; enum ata_ioctls { ATA_IOC_GET_IO32 = 0x309, /* HDIO_GET_32BIT */ ATA_IOC_SET_IO32 = 0x324, /* HDIO_SET_32BIT */ }; /* core structures */ struct ata_bmdma_prd { __le32 addr; __le32 flags_len; }; /* * id tests */ #define ata_id_is_ata(id) (((id)[ATA_ID_CONFIG] & (1 << 15)) == 0) #define ata_id_has_lba(id) ((id)[ATA_ID_CAPABILITY] & (1 << 9)) #define ata_id_has_dma(id) ((id)[ATA_ID_CAPABILITY] & (1 << 8)) #define ata_id_has_ncq(id) ((id)[ATA_ID_SATA_CAPABILITY] & (1 << 8)) #define ata_id_queue_depth(id) (((id)[ATA_ID_QUEUE_DEPTH] & 0x1f) + 1) #define ata_id_removable(id) ((id)[ATA_ID_CONFIG] & (1 << 7)) #define ata_id_has_atapi_AN(id) \ ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ ((id)[ATA_ID_FEATURE_SUPP] & (1 << 5))) #define ata_id_has_fpdma_aa(id) \ ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ ((id)[ATA_ID_FEATURE_SUPP] & (1 << 2))) #define ata_id_has_devslp(id) \ ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ ((id)[ATA_ID_FEATURE_SUPP] & (1 << 8))) #define ata_id_has_ncq_autosense(id) \ ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ ((id)[ATA_ID_FEATURE_SUPP] & (1 << 7))) #define ata_id_has_dipm(id) \ ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ ((id)[ATA_ID_FEATURE_SUPP] & (1 << 3))) #define ata_id_iordy_disable(id) ((id)[ATA_ID_CAPABILITY] & (1 << 10)) #define ata_id_has_iordy(id) ((id)[ATA_ID_CAPABILITY] & (1 << 11)) #define ata_id_u32(id,n) \ (((u32) (id)[(n) + 1] << 16) | ((u32) (id)[(n)])) #define ata_id_u64(id,n) \ ( ((u64) (id)[(n) + 3] << 48) | \ ((u64) (id)[(n) + 2] << 32) | \ ((u64) (id)[(n) + 1] << 16) | \ ((u64) (id)[(n) + 0]) ) #define ata_id_cdb_intr(id) (((id)[ATA_ID_CONFIG] & 0x60) == 0x20) #define ata_id_has_da(id) ((id)[ATA_ID_SATA_CAPABILITY_2] & (1 << 4)) static inline bool ata_id_has_hipm(const u16 *id) { u16 val = id[ATA_ID_SATA_CAPABILITY]; if (val == 0 || val == 0xffff) return false; return val & (1 << 9); } static inline bool ata_id_has_fua(const u16 *id) { if ((id[ATA_ID_CFSSE] & 0xC000) != 0x4000) return false; return id[ATA_ID_CFSSE] & (1 << 6); } static inline bool ata_id_has_flush(const u16 *id) { if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000) return false; return id[ATA_ID_COMMAND_SET_2] & (1 << 12); } static inline bool ata_id_flush_enabled(const u16 *id) { if (ata_id_has_flush(id) == 0) return false; if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000) return false; return id[ATA_ID_CFS_ENABLE_2] & (1 << 12); } static inline bool ata_id_has_flush_ext(const u16 *id) { if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000) return false; return id[ATA_ID_COMMAND_SET_2] & (1 << 13); } static inline bool ata_id_flush_ext_enabled(const u16 *id) { if (ata_id_has_flush_ext(id) == 0) return false; if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000) return false; /* * some Maxtor disks have bit 13 defined incorrectly * so check bit 10 too */ return (id[ATA_ID_CFS_ENABLE_2] & 0x2400) == 0x2400; } static inline u32 ata_id_logical_sector_size(const u16 *id) { /* T13/1699-D Revision 6a, Sep 6, 2008. Page 128. * IDENTIFY DEVICE data, word 117-118. * 0xd000 ignores bit 13 (logical:physical > 1) */ if ((id[ATA_ID_SECTOR_SIZE] & 0xd000) == 0x5000) return (((id[ATA_ID_LOGICAL_SECTOR_SIZE+1] << 16) + id[ATA_ID_LOGICAL_SECTOR_SIZE]) * sizeof(u16)) ; return ATA_SECT_SIZE; } static inline u8 ata_id_log2_per_physical_sector(const u16 *id) { /* T13/1699-D Revision 6a, Sep 6, 2008. Page 128. * IDENTIFY DEVICE data, word 106. * 0xe000 ignores bit 12 (logical sector > 512 bytes) */ if ((id[ATA_ID_SECTOR_SIZE] & 0xe000) == 0x6000) return (id[ATA_ID_SECTOR_SIZE] & 0xf); return 0; } /* Offset of logical sectors relative to physical sectors. * * If device has more than one logical sector per physical sector * (aka 512 byte emulation), vendors might offset the "sector 0" address * so sector 63 is "naturally aligned" - e.g. FAT partition table. * This avoids Read/Mod/Write penalties when using FAT partition table * and updating "well aligned" (FS perspective) physical sectors on every * transaction. */ static inline u16 ata_id_logical_sector_offset(const u16 *id, u8 log2_per_phys) { u16 word_209 = id[209]; if ((log2_per_phys > 1) && (word_209 & 0xc000) == 0x4000) { u16 first = word_209 & 0x3fff; if (first > 0) return (1 << log2_per_phys) - first; } return 0; } static inline bool ata_id_has_lba48(const u16 *id) { if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000) return false; if (!ata_id_u64(id, ATA_ID_LBA_CAPACITY_2)) return false; return id[ATA_ID_COMMAND_SET_2] & (1 << 10); } static inline bool ata_id_lba48_enabled(const u16 *id) { if (ata_id_has_lba48(id) == 0) return false; if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000) return false; return id[ATA_ID_CFS_ENABLE_2] & (1 << 10); } static inline bool ata_id_hpa_enabled(const u16 *id) { /* Yes children, word 83 valid bits cover word 82 data */ if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000) return false; /* And 87 covers 85-87 */ if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000) return false; /* Check command sets enabled as well as supported */ if ((id[ATA_ID_CFS_ENABLE_1] & (1 << 10)) == 0) return false; return id[ATA_ID_COMMAND_SET_1] & (1 << 10); } static inline bool ata_id_has_wcache(const u16 *id) { /* Yes children, word 83 valid bits cover word 82 data */ if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000) return false; return id[ATA_ID_COMMAND_SET_1] & (1 << 5); } static inline bool ata_id_has_pm(const u16 *id) { if ((id[ATA_ID_COMMAND_SET_2] & 0xC000) != 0x4000) return false; return id[ATA_ID_COMMAND_SET_1] & (1 << 3); } static inline bool ata_id_rahead_enabled(const u16 *id) { if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000) return false; return id[ATA_ID_CFS_ENABLE_1] & (1 << 6); } static inline bool ata_id_wcache_enabled(const u16 *id) { if ((id[ATA_ID_CSF_DEFAULT] & 0xC000) != 0x4000) return false; return id[ATA_ID_CFS_ENABLE_1] & (1 << 5); } static inline bool ata_id_has_read_log_dma_ext(const u16 *id) { /* Word 86 must have bit 15 set */ if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15))) return false; /* READ LOG DMA EXT support can be signaled either from word 119 * or from word 120. The format is the same for both words: Bit * 15 must be cleared, bit 14 set and bit 3 set. */ if ((id[ATA_ID_COMMAND_SET_3] & 0xC008) == 0x4008 || (id[ATA_ID_COMMAND_SET_4] & 0xC008) == 0x4008) return true; return false; } static inline bool ata_id_has_sense_reporting(const u16 *id) { if (!(id[ATA_ID_CFS_ENABLE_2] & BIT(15))) return false; if ((id[ATA_ID_COMMAND_SET_3] & (BIT(15) | BIT(14))) != BIT(14)) return false; return id[ATA_ID_COMMAND_SET_3] & BIT(6); } static inline bool ata_id_sense_reporting_enabled(const u16 *id) { if (!ata_id_has_sense_reporting(id)) return false; /* ata_id_has_sense_reporting() == true, word 86 must have bit 15 set */ if ((id[ATA_ID_COMMAND_SET_4] & (BIT(15) | BIT(14))) != BIT(14)) return false; return id[ATA_ID_COMMAND_SET_4] & BIT(6); } /** * * Word: 206 - SCT Command Transport * 15:12 - Vendor Specific * 11:6 - Reserved * 5 - SCT Command Transport Data Tables supported * 4 - SCT Command Transport Features Control supported * 3 - SCT Command Transport Error Recovery Control supported * 2 - SCT Command Transport Write Same supported * 1 - SCT Command Transport Long Sector Access supported * 0 - SCT Command Transport supported */ static inline bool ata_id_sct_data_tables(const u16 *id) { return id[ATA_ID_SCT_CMD_XPORT] & (1 << 5) ? true : false; } static inline bool ata_id_sct_features_ctrl(const u16 *id) { return id[ATA_ID_SCT_CMD_XPORT] & (1 << 4) ? true : false; } static inline bool ata_id_sct_error_recovery_ctrl(const u16 *id) { return id[ATA_ID_SCT_CMD_XPORT] & (1