diff options
Diffstat (limited to 'fs')
69 files changed, 1248 insertions, 679 deletions
diff --git a/fs/Makefile b/fs/Makefile index 293733f61594..23fcd8c164a3 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -12,7 +12,8 @@ obj-y := open.o read_write.o file_table.o super.o \ attr.o bad_inode.o file.o filesystems.o namespace.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ pnode.o splice.o sync.o utimes.o d_path.o \ - stack.o fs_struct.o statfs.o fs_pin.o nsfs.o + stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \ + fs_types.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o block_dev.o direct-io.o mpage.o diff --git a/fs/afs/cell.c b/fs/afs/cell.c index cf445dbd5f2e..9de46116c749 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -173,6 +173,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, rcu_assign_pointer(cell->vl_servers, vllist); cell->dns_expiry = TIME64_MAX; + __clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags); } else { cell->dns_expiry = ktime_get_real_seconds(); } @@ -167,9 +167,13 @@ struct kioctx { unsigned id; }; +/* + * First field must be the file pointer in all the + * iocb unions! See also 'struct kiocb' in <linux/fs.h> + */ struct fsync_iocb { - struct work_struct work; struct file *file; + struct work_struct work; bool datasync; }; @@ -183,8 +187,15 @@ struct poll_iocb { struct work_struct work; }; +/* + * NOTE! Each of the iocb union members has the file pointer + * as the first entry in their struct definition. So you can + * access the file pointer through any of the sub-structs, + * or directly as just 'ki_filp' in this struct. + */ struct aio_kiocb { union { + struct file *ki_filp; struct kiocb rw; struct fsync_iocb fsync; struct poll_iocb poll; @@ -1060,6 +1071,8 @@ static inline void iocb_put(struct aio_kiocb *iocb) { if (refcount_read(&iocb->ki_refcnt) == 0 || refcount_dec_and_test(&iocb->ki_refcnt)) { + if (iocb->ki_filp) + fput(iocb->ki_filp); percpu_ref_put(&iocb->ki_ctx->reqs); kmem_cache_free(kiocb_cachep, iocb); } @@ -1424,7 +1437,6 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) file_end_write(kiocb->ki_filp); } - fput(kiocb->ki_filp); aio_complete(iocb, res, res2); } @@ -1432,9 +1444,6 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) { int ret; - req->ki_filp = fget(iocb->aio_fildes); - if (unlikely(!req->ki_filp)) - return -EBADF; req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; @@ -1451,7 +1460,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) ret = ioprio_check_cap(iocb->aio_reqprio); if (ret) { pr_debug("aio ioprio check cap error: %d\n", ret); - goto out_fput; + return ret; } req->ki_ioprio = iocb->aio_reqprio; @@ -1460,14 +1469,10 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags); if (unlikely(ret)) - goto out_fput; + return ret; req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */ return 0; - -out_fput: - fput(req->ki_filp); - return ret; } static int aio_setup_rw(int rw, const struct iocb *iocb, struct iovec **iovec, @@ -1521,24 +1526,19 @@ static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb, if (ret) return ret; file = req->ki_filp; - - ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_READ))) - goto out_fput; + return -EBADF; ret = -EINVAL; if (unlikely(!file->f_op->read_iter)) - goto out_fput; + return -EINVAL; ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter); if (ret) - goto out_fput; + return ret; ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) aio_rw_done(req, call_read_iter(file, req, &iter)); kfree(iovec); -out_fput: - if (unlikely(ret)) - fput(file); return ret; } @@ -1555,16 +1555,14 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, return ret; file = req->ki_filp; - ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_WRITE))) - goto out_fput; - ret = -EINVAL; + return -EBADF; if (unlikely(!file->f_op->write_iter)) - goto out_fput; + return -EINVAL; ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter); if (ret) - goto out_fput; + return ret; ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) { /* @@ -1582,9 +1580,6 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, aio_rw_done(req, call_write_iter(file, req, &iter)); } kfree(iovec); -out_fput: - if (unlikely(ret)) - fput(file); return ret; } @@ -1594,7 +1589,6 @@ static void aio_fsync_work(struct work_struct *work) int ret; ret = vfs_fsync(req->file, req->datasync); - fput(req->file); aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0); } @@ -1605,13 +1599,8 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, iocb->aio_rw_flags)) return -EINVAL; - req->file = fget(iocb->aio_fildes); - if (unlikely(!req->file)) - return -EBADF; - if (unlikely(!req->file->f_op->fsync)) { - fput(req->file); + if (unlikely(!req->file->f_op->fsync)) return -EINVAL; - } req->datasync = datasync; INIT_WORK(&req->work, aio_fsync_work); @@ -1621,10 +1610,7 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask) { - struct file *file = iocb->poll.file; - aio_complete(iocb, mangle_poll(mask), 0); - fput(file); } static void aio_poll_complete_work(struct work_struct *work) @@ -1680,6 +1666,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, struct poll_iocb *req = container_of(wait, struct poll_iocb, wait); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); __poll_t mask = key_to_poll(key); + unsigned long flags; req->woken = true; @@ -1688,10 +1675,15 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (!(mask & req->events)) return 0; - /* try to complete the iocb inline if we can: */ - if (spin_trylock(&iocb->ki_ctx->ctx_lock)) { + /* + * Try to complete the iocb inline if we can. Use + * irqsave/irqrestore because not all filesystems (e.g. fuse) + * call this function with IRQs disabled and because IRQs + * have to be disabled before ctx_lock is obtained. + */ + if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { list_del(&iocb->ki_list); - spin_unlock(&iocb->ki_ctx->ctx_lock); + spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); list_del_init(&req->wait.entry); aio_poll_complete(iocb, mask); @@ -1743,9 +1735,6 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) INIT_WORK(&req->work, aio_poll_complete_work); req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; - req->file = fget(iocb->aio_fildes); - if (unlikely(!req->file)) - return -EBADF; req->head = NULL; req->woken = false; @@ -1788,10 +1777,8 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) spin_unlock_irq(&ctx->ctx_lock); out: - if (unlikely(apt.error)) { - fput(req->file); + if (unlikely(apt.error)) return apt.error; - } if (mask) aio_poll_complete(aiocb, mask); @@ -1829,6 +1816,11 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, if (unlikely(!req)) goto out_put_reqs_available; + req->ki_filp = fget(iocb->aio_fildes); + ret = -EBADF; + if (unlikely(!req->ki_filp)) + goto out_put_req; + if (iocb->aio_flags & IOCB_FLAG_RESFD) { /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an @@ -2199,11 +2191,11 @@ SYSCALL_DEFINE6(io_pgetevents_time32, #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id, - compat_long_t, min_nr, - compat_long_t, nr, - struct io_event __user *, events, - struct old_timespec32 __user *, timeout) +SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id, + __s32, min_nr, + __s32, nr, + struct io_event __user *, events, + struct old_timespec32 __user *, timeout) { struct timespec64 t; int ret; diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index ca9725f18e00..1fefd87eb4b4 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -29,97 +29,14 @@ #include <linux/uaccess.h> #include <asm/cacheflush.h> -#include <asm/a.out-core.h> static int load_aout_binary(struct linux_binprm *); static int load_aout_library(struct file*); -#ifdef CONFIG_COREDUMP -/* - * Routine writes a core dump image in the current directory. - * Currently only a stub-function. - * - * Note that setuid/setgid files won't make a core-dump if the uid/gid - * changed due to the set[u|g]id. It's enforced by the "current->mm->dumpable" - * field, which also makes sure the core-dumps won't be recursive if the - * dumping of the process results in another error.. - */ -static int aout_core_dump(struct coredump_params *cprm) -{ - mm_segment_t fs; - int has_dumped = 0; - void __user *dump_start; - int dump_size; - struct user dump; -#ifdef __alpha__ -# define START_DATA(u) ((void __user *)u.start_data) -#else -# define START_DATA(u) ((void __user *)((u.u_tsize << PAGE_SHIFT) + \ - u.start_code)) -#endif -# define START_STACK(u) ((void __user *)u.start_stack) - - fs = get_fs(); - set_fs(KERNEL_DS); - has_dumped = 1; - strncpy(dump.u_comm, current->comm, sizeof(dump.u_comm)); - dump.u_ar0 = offsetof(struct user, regs); - dump.signal = cprm->siginfo->si_signo; - aout_dump_thread(cprm->regs, &dump); - -/* If the size of the dump file exceeds the rlimit, then see what would happen - if we wrote the stack, but not the data area. */ - if ((dump.u_dsize + dump.u_ssize+1) * PAGE_SIZE > cprm->limit) - dump.u_dsize = 0; - -/* Make sure we have enough room to write the stack and data areas. */ - if ((dump.u_ssize + 1) * PAGE_SIZE > cprm->limit) - dump.u_ssize = 0; - -/* make sure we actually have a data and stack area to dump */ - set_fs(USER_DS); - if (!access_ok(START_DATA(dump), dump.u_dsize << PAGE_SHIFT)) - dump.u_dsize = 0; - if (!access_ok(START_STACK(dump), dump.u_ssize << PAGE_SHIFT)) - dump.u_ssize = 0; - - set_fs(KERNEL_DS); -/* struct user */ - if (!dump_emit(cprm, &dump, sizeof(dump))) - goto end_coredump; -/* Now dump all of the user data. Include malloced stuff as well */ - if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump))) - goto end_coredump; -/* now we start writing out the user space info */ - set_fs(USER_DS); -/* Dump the data area */ - if (dump.u_dsize != 0) { - dump_start = START_DATA(dump); - dump_size = dump.u_dsize << PAGE_SHIFT; - if (!dump_emit(cprm, dump_start, dump_size)) - goto end_coredump; - } -/* Now prepare to dump the stack area */ - if (dump.u_ssize != 0) { - dump_start = START_STACK(dump); - dump_size = dump.u_ssize << PAGE_SHIFT; - if (!dump_emit(cprm, dump_start, dump_size)) - goto end_coredump; - } -end_coredump: - set_fs(fs); - return has_dumped; -} -#else -#define aout_core_dump NULL -#endif - static struct linux_binfmt aout_format = { .module = THIS_MODULE, .load_binary = load_aout_binary, .load_shlib = load_aout_library, - .core_dump = aout_core_dump, - .min_coredump = PAGE_SIZE }; #define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE) diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 1e11a683f63d..322ce9686bdb 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -47,7 +47,7 @@ static int derive_key_aes(const u8 *master_key, tfm = NULL; goto out; } - crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); req = skcipher_request_alloc(tfm, GFP_NOFS); if (!req) { res = -ENOMEM; @@ -257,7 +257,7 @@ allocate_skcipher_for_mode(struct fscrypt_mode *mode, const u8 *raw_key, mode->friendly_name, crypto_skcipher_alg(tfm)->base.cra_driver_name); } - crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); err = crypto_skcipher_setkey(tfm, raw_key, mode->keysize); if (err) goto err_free_tfm; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 29c68c5d44d5..95b5e78c22b1 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -423,8 +423,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file); * debugfs core. * * It is your responsibility to protect your struct file_operation - * methods against file removals by means of debugfs_use_file_start() - * and debugfs_use_file_finish(). ->open() is still protected by + * methods against file removals by means of debugfs_file_get() + * and debugfs_file_put(). ->open() is still protected by * debugfs though. * * Any struct file_operations defined by means of diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 76976d6e50f9..c98ad9777ad9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1089,12 +1089,12 @@ static void sctp_connect_to_sock(struct connection *con) * since O_NONBLOCK argument in connect() function does not work here, * then, we should restore the default value of this attribute. */ - kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv, + kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv, sizeof(tv)); result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len, 0); memset(&tv, 0, sizeof(tv)); - kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv, + kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv, sizeof(tv)); if (result == -EINPROGRESS) diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 4dd842f72846..f664da55234e 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -610,7 +610,8 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat) full_alg_name); goto out_free; } - crypto_skcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(crypt_stat->tfm, + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); rc = 0; out_free: kfree(full_alg_name); @@ -1590,7 +1591,7 @@ ecryptfs_process_key_cipher(struct crypto_skcipher **key_tfm, "[%s]; rc = [%d]\n", full_alg_name, rc); goto out; } - crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); if (*key_size == 0) *key_size = crypto_skcipher_default_keysize(*key_tfm); get_random_bytes(dummy_key, *key_size); diff --git a/fs/exec.c b/fs/exec.c index fb72d36f7823..74f3672146a7 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -932,7 +932,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size, bytes = kernel_read(file, *buf + pos, i_size - pos, &pos); if (bytes < 0) { ret = bytes; - goto out; + goto out_free; } if (bytes == 0) @@ -1189,7 +1189,7 @@ no_thread_group: flush_itimer_signals(); #endif - if (atomic_read(&oldsighand->count) != 1) { + if (refcount_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND @@ -1199,7 +1199,7 @@ no_thread_group: if (!newsighand) return -ENOMEM; - atomic_set(&newsighand->count, 1); + refcount_set(&newsighand->count, 1); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 3b8114def693..13318e255ebf 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -252,33 +252,10 @@ ext2_validate_entry(char *base, unsigned offset, unsigned mask) return (char *)p - base; } -static unsigned char ext2_filetype_table[EXT2_FT_MAX] = { - [EXT2_FT_UNKNOWN] = DT_UNKNOWN, - [EXT2_FT_REG_FILE] = DT_REG, - [EXT2_FT_DIR] = DT_DIR, - [EXT2_FT_CHRDEV] = DT_CHR, - [EXT2_FT_BLKDEV] = DT_BLK, - [EXT2_FT_FIFO] = DT_FIFO, - [EXT2_FT_SOCK] = DT_SOCK, - [EXT2_FT_SYMLINK] = DT_LNK, -}; - -#define S_SHIFT 12 -static unsigned char ext2_type_by_mode[S_IFMT >> S_SHIFT] = { - [S_IFREG >> S_SHIFT] = EXT2_FT_REG_FILE, - [S_IFDIR >> S_SHIFT] = EXT2_FT_DIR, - [S_IFCHR >> S_SHIFT] = EXT2_FT_CHRDEV, - [S_IFBLK >> S_SHIFT] = EXT2_FT_BLKDEV, - [S_IFIFO >> S_SHIFT] = EXT2_FT_FIFO, - [S_IFSOCK >> S_SHIFT] = EXT2_FT_SOCK, - [S_IFLNK >> S_SHIFT] = EXT2_FT_SYMLINK, -}; - static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode) { - umode_t mode = inode->i_mode; if (EXT2_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT2_FEATURE_INCOMPAT_FILETYPE)) - de->file_type = ext2_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; + de->file_type = fs_umode_to_ftype(inode->i_mode); else de->file_type = 0; } @@ -293,14 +270,14 @@ ext2_readdir(struct file *file, struct dir_context *ctx) unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); unsigned chunk_mask = ~(ext2_chunk_size(inode)-1); - unsigned char *types = NULL; bool need_revalidate = !inode_eq_iversion(inode, file->f_version); + bool has_filetype; if (pos > inode->i_size - EXT2_DIR_REC_LEN(1)) return 0; - if (EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE)) - types = ext2_filetype_table; + has_filetype = + EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE); for ( ; n < npages; n++, offset = 0) { char *kaddr, *limit; @@ -335,8 +312,8 @@ ext2_readdir(struct file *file, struct dir_context *ctx) if (de->inode) { unsigned char d_type = DT_UNKNOWN; - if (types && de->file_type < EXT2_FT_MAX) - d_type = types[de->file_type]; + if (has_filetype) + d_type = fs_ftype_to_dtype(de->file_type); if (!dir_emit(ctx, de->name, de->name_len, le32_to_cpu(de->inode), diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index e770cd100a6a..10ab238de9a6 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -604,22 +604,6 @@ struct ext2_dir_entry_2 { }; /* - * Ext2 directory file types. Only the low 3 bits are used. The - * other bits are reserved for now. - */ -enum { - EXT2_FT_UNKNOWN = 0, - EXT2_FT_REG_FILE = 1, - EXT2_FT_DIR = 2, - EXT2_FT_CHRDEV = 3, - EXT2_FT_BLKDEV = 4, - EXT2_FT_FIFO = 5, - EXT2_FT_SOCK = 6, - EXT2_FT_SYMLINK = 7, - EXT2_FT_MAX -}; - -/* * EXT2_DIR_PAD defines the directory entries boundaries * * NOTE: It must be a multiple of 4 @@ -774,6 +758,7 @@ extern int ext2_write_inode (struct inode *, struct writeback_control *); extern void ext2_evict_inode(struct inode *); extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int); extern int ext2_setattr (struct dentry *, struct iattr *); +extern int ext2_getattr (const struct path *, struct kstat *, u32, unsigned int); extern void ext2_set_inode_flags(struct inode *inode); extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 28b2609f25c1..39c4772e96c9 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -199,6 +199,7 @@ const struct inode_operations ext2_file_inode_operations = { #ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, #endif + .getattr = ext2_getattr, .setattr = ext2_setattr, .get_acl = ext2_get_acl, .set_acl = ext2_set_acl, diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 5c3d7b7e4975..a0c5ea91fcd4 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -222,8 +222,6 @@ static int find_group_dir(struct super_block *sb, struct inode *parent) best_desc = desc; } } - if (!best_desc) - return -1; return best_group; } diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index e4bb9386c045..c27c27300d95 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -717,7 +717,7 @@ static int ext2_get_blocks(struct inode *inode, /* the number of blocks need to allocate for [d,t]indirect blocks */ indirect_blks = (chain + depth) - partial - 1; /* - * Next look up the indirect map to count the totoal number of + * Next look up the indirect map to count the total number of * direct blocks to allocate for this branch. */ count = ext2_blks_to_allocate(partial, indirect_blks, @@ -1239,6 +1239,7 @@ do_indirects: mark_inode_dirty(inode); ext2_free_branches(inode, &nr, &nr+1, 1); } + /* fall through */ case EXT2_IND_BLOCK: nr = i_data[EXT2_DIND_BLOCK]; if (nr) { @@ -1246,6 +1247,7 @@ do_indirects: mark_inode_dirty(inode); ext2_free_branches(inode, &nr, &nr+1, 2); } + /* fall through */ case EXT2_DIND_BLOCK: nr = i_data[EXT2_TIND_BLOCK]; if (nr) { @@ -1635,6 +1637,32 @@ int ext2_write_inode(struct inode *inode, struct writeback_control *wbc) return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); } +int ext2_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int query_falgs) +{ + struct inode *inode = d_inode(path->dentry); + struct ext2_inode_info *ei = EXT2_I(inode); + unsigned int flags; + + flags = ei->i_flags & EXT2_FL_USER_VISIBLE; + if (flags & EXT2_APPEND_FL) + stat->attributes |= STATX_ATTR_APPEND; + if (flags & EXT2_COMPR_FL) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (flags & EXT2_IMMUTABLE_FL) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (flags & EXT2_NODUMP_FL) + stat->attributes |= STATX_ATTR_NODUMP; + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_COMPRESSED | + STATX_ATTR_ENCRYPTED | + STATX_ATTR_IMMUTABLE | + STATX_ATTR_NODUMP); + + generic_fillattr(inode, stat); + return 0; +} + int ext2_setattr(struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 0c26dcc5d850..ccfbbf59e2fc 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -416,6 +416,7 @@ const struct inode_operations ext2_dir_inode_operations = { #ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, #endif + .getattr = ext2_getattr, .setattr = ext2_setattr, .get_acl = ext2_get_acl, .set_acl = ext2_set_acl, @@ -426,6 +427,7 @@ const struct inode_operations ext2_special_inode_operations = { #ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, #endif + .getattr = ext2_getattr, .setattr = ext2_setattr, .get_acl = ext2_get_acl, .set_acl = ext2_set_acl, diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 73b2d528237f..0128010a0874 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -757,7 +757,8 @@ static loff_t ext2_max_size(int bits) { loff_t res = EXT2_NDIR_BLOCKS; int meta_blocks; - loff_t upper_limit; + unsigned int upper_limit; + unsigned int ppb = 1 << (bits-2); /* This is calculated to be the largest file size for a * dense, file such that the total number of @@ -771,24 +772,34 @@ static loff_t ext2_max_size(int bits) /* total blocks in file system block size */ upper_limit >>= (bits - 9); + /* Compute how many blocks we can address by block tree */ + res += 1LL << (bits-2); + res += 1LL << (2*(bits-2)); + res += 1LL << (3*(bits-2)); + /* Does block tree limit file size? */ + if (res < upper_limit) + goto check_lfs; + res = upper_limit; + /* How many metadata blocks are needed for addressing upper_limit? */ + upper_limit -= EXT2_NDIR_BLOCKS; /* indirect blocks */ meta_blocks = 1; + upper_limit -= ppb; /* double indirect blocks */ - meta_blocks += 1 + (1LL << (bits-2)); - /* tripple indirect blocks */ - meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2))); - - upper_limit -= meta_blocks; - upper_limit <<= bits; - - res += 1LL << (bits-2); - res += 1LL << (2*(bits-2)); - res += 1LL << (3*(bits-2)); + if (upper_limit < ppb * ppb) { + meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb); + res -= meta_blocks; + goto check_lfs; + } + meta_blocks += 1 + ppb; + upper_limit -= ppb * ppb; + /* tripple indirect blocks for the rest */ + meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb) + + DIV_ROUND_UP(upper_limit, ppb*ppb); + res -= meta_blocks; +check_lfs: res <<= bits; - if (res > upper_limit) - res = upper_limit; - if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; @@ -1024,8 +1035,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); - if (EXT2_INODE_SIZE(sb) == 0) - goto cantfind_ext2; sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0) goto cantfind_ext2; @@ -1087,12 +1096,14 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sizeof(struct buffer_head *), GFP_KERNEL); if (sbi->s_group_desc == NULL) { + ret = -ENOMEM; ext2_msg(sb, KERN_ERR, "error: not enough memory"); goto failed_mount; } bgl_lock_init(sbi->s_blockgroup_lock); sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL); if (!sbi->s_debts) { + ret = -ENOMEM; ext2_msg(sb, KERN_ERR, "error: not enough memory"); goto failed_mount_group_desc; } @@ -1148,6 +1159,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_EXT2_FS_XATTR sbi->s_ea_block_cache = ext2_xattr_create_cache(); if (!sbi->s_ea_block_cache) { + ret = -ENOMEM; ext2_msg(sb, KERN_ERR, "Failed to create ea_block_cache"); goto failed_mount3; } diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c index d5589ddcc281..00cdb8679486 100644 --- a/fs/ext2/symlink.c +++ b/fs/ext2/symlink.c @@ -23,6 +23,7 @@ const struct inode_operations ext2_symlink_inode_operations = { .get_link = page_get_link, + .getattr = ext2_getattr, .setattr = ext2_setattr, #ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, @@ -31,6 +32,7 @@ const struct inode_operations ext2_symlink_inode_operations = { const struct inode_operations ext2_fast_symlink_inode_operations = { .get_link = simple_get_link, + .getattr = ext2_getattr, .setattr = ext2_setattr, #ifdef CONFIG_EXT2_FS_XATTR .listxattr = ext2_listxattr, diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 4f30876ee325..1e33e0ac8cf1 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -342,6 +342,7 @@ static void ext2_xattr_update_super_block(struct super_block *sb) return; spin_lock(&EXT2_SB(sb)->s_lock); + ext2_update_dynamic_rev(sb); EXT2_SET_COMPAT_FEATURE(sb, EXT2_FEATURE_COMPAT_EXT_ATTR); spin_unlock(&EXT2_SB(sb)->s_lock); mark_buffer_dirty(EXT2_SB(sb)->s_sbh); diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index ebcc121920ba..fd7f170e2f2d 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -506,30 +506,16 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi) kvfree(si); } -int __init f2fs_create_root_stats(void) +void __init f2fs_create_root_stats(void) { - struct dentry *file; - f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL); - if (!f2fs_debugfs_root) - return -ENOMEM; - file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, - NULL, &stat_fops); - if (!file) { - debugfs_remove(f2fs_debugfs_root); - f2fs_debugfs_root = NULL; - return -ENOMEM; - } - - return 0; + debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, NULL, + &stat_fops); } void f2fs_destroy_root_stats(void) { - if (!f2fs_debugfs_root) - return; - debugfs_remove_recursive(f2fs_debugfs_root); f2fs_debugfs_root = NULL; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 12fabd6735dd..8f23ee6e8eb9 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3328,7 +3328,7 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) int f2fs_build_stats(struct f2fs_sb_info *sbi); void f2fs_destroy_stats(struct f2fs_sb_info *sbi); -int __init f2fs_create_root_stats(void); +void __init f2fs_create_root_stats(void); void f2fs_destroy_root_stats(void); #else #define stat_inc_cp_count(si) do { } while (0) @@ -3366,7 +3366,7 @@ void f2fs_destroy_root_stats(void); static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } -static inline int __init f2fs_create_root_stats(void) { return 0; } +static inline void __init f2fs_create_root_stats(void) { } static inline void f2fs_destroy_root_stats(void) { } #endif diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index c46a1d4318d4..3d3ce9eb6d13 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -3545,9 +3545,7 @@ static int __init init_f2fs_fs(void) err = register_filesystem(&f2fs_fs_type); if (err) goto free_shrinker; - err = f2fs_create_root_stats(); - if (err) - goto free_filesystem; + f2fs_create_root_stats(); err = f2fs_init_post_read_processing(); if (err) goto free_root_stats; @@ -3555,7 +3553,6 @@ static int __init init_f2fs_fs(void) free_root_stats: f2fs_destroy_root_stats(); -free_filesystem: unregister_filesystem(&f2fs_fs_type); free_shrinker: unregister_shrinker(&f2fs_shrinker_info); diff --git a/fs/file.c b/fs/file.c index 3209ee271c41..a10487aa0a84 100644 --- a/fs/file.c +++ b/fs/file.c @@ -457,6 +457,7 @@ struct files_struct init_files = { .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) diff --git a/fs/fs_types.c b/fs/fs_types.c new file mode 100644 index 000000000000..78365e5dc08c --- /dev/null +++ b/fs/fs_types.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/fs.h> +#include <linux/export.h> + +/* + * fs on-disk file type to dirent file type conversion + */ +static const unsigned char fs_dtype_by_ftype[FT_MAX] = { + [FT_UNKNOWN] = DT_UNKNOWN, + [FT_REG_FILE] = DT_REG, + [FT_DIR] = DT_DIR, + [FT_CHRDEV] = DT_CHR, + [FT_BLKDEV] = DT_BLK, + [FT_FIFO] = DT_FIFO, + [FT_SOCK] = DT_SOCK, + [FT_SYMLINK] = DT_LNK +}; + +/** + * fs_ftype_to_dtype() - fs on-disk file type to dirent type. + * @filetype: The on-disk file type to convert. + * + * This function converts the on-disk file type value (FT_*) to the directory + * entry type (DT_*). + * + * Context: Any context. + * Return: + * * DT_UNKNOWN - Unknown type + * * DT_FIFO - FIFO + * * DT_CHR - Character device + * * DT_DIR - Directory + * * DT_BLK - Block device + * * DT_REG - Regular file + * * DT_LNK - Symbolic link + * * DT_SOCK - Local-domain socket + */ +unsigned char fs_ftype_to_dtype(unsigned int filetype) +{ + if (filetype >= FT_MAX) + return DT_UNKNOWN; + + return fs_dtype_by_ftype[filetype]; +} +EXPORT_SYMBOL_GPL(fs_ftype_to_dtype); + +/* + * dirent file type to fs on-disk file type conversion + * Values not initialized explicitly are FT_UNKNOWN (0). + */ +static const unsigned char fs_ftype_by_dtype[DT_MAX] = { + [DT_REG] = FT_REG_FILE, + [DT_DIR] = FT_DIR, + [DT_LNK] = FT_SYMLINK, + [DT_CHR] = FT_CHRDEV, + [DT_BLK] = FT_BLKDEV, + [DT_FIFO] = FT_FIFO, + [DT_SOCK] = FT_SOCK, +}; + +/** + * fs_umode_to_ftype() - file mode to on-disk file type. + * @mode: The file mode to convert. + * + * This function converts the file mode value to the on-disk file type (FT_*). + * + * Context: Any context. + * Return: + * * FT_UNKNOWN - Unknown type + * * FT_REG_FILE - Regular file + * * FT_DIR - Directory + * * FT_CHRDEV - Character device + * * FT_BLKDEV - Block device + * * FT_FIFO - FIFO + * * FT_SOCK - Local-domain socket + * * FT_SYMLINK - Symbolic link + */ +unsigned char fs_umode_to_ftype(umode_t mode) +{ + return fs_ftype_by_dtype[S_DT(mode)]; +} +EXPORT_SYMBOL_GPL(fs_umode_to_ftype); + +/** + * fs_umode_to_dtype() - file mode to dirent file type. + * @mode: The file mode to convert. + * + * This function converts the file mode value to the directory + * entry type (DT_*). + * + * Context: Any context. + * Return: + * * DT_UNKNOWN - Unknown type + * * DT_FIFO - FIFO + * * DT_CHR - Character device + * * DT_DIR - Directory + * * DT_BLK - Block device + * * DT_REG - Regular file + * * DT_LNK - Symbolic link + * * DT_SOCK - Local-domain socket + */ +unsigned char fs_umode_to_dtype(umode_t mode) +{ + return fs_ftype_to_dtype(fs_umode_to_ftype(mode)); +} +EXPORT_SYMBOL_GPL(fs_umode_to_dtype); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 32920a10100e..b0eef008de67 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -530,7 +530,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) inode_lock(inode); /* protected by i_mutex */ - if (info->seals & F_SEAL_WRITE) { + if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { inode_unlock(inode); return -EPERM; } @@ -859,6 +859,18 @@ static int hugetlbfs_migrate_page(struct address_space *mapping, rc = migrate_huge_page_move_mapping(mapping, newpage, page); if (rc != MIGRATEPAGE_SUCCESS) return rc; + + /* + * page_private is subpool pointer in hugetlb pages. Transfer to + * new page. PagePrivate is not associated with page_private for + * hugetlb pages and can not be set here as only page_huge_active + * pages can be migrated. + */ + if (page_private(page)) { + set_page_private(newpage, page_private(page)); + set_page_private(page, 0); + } + if (mode != MIGRATE_SYNC_NO_COPY) migrate_page_copy(newpage, page); else diff --git a/fs/inode.c b/fs/inode.c index 73432e64f874..e9d97add2b36 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2093,14 +2093,8 @@ EXPORT_SYMBOL(inode_dio_wait); void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask) { - unsigned int old_flags, new_flags; - WARN_ON_ONCE(flags & ~mask); - do { - old_flags = READ_ONCE(inode->i_flags); - new_flags = (old_flags & ~mask) | flags; - } while (unlikely(cmpxchg(&inode->i_flags, old_flags, - new_flags) != old_flags)); + set_mask_bits(&inode->i_flags, mask, flags); } EXPORT_SYMBOL(inode_set_flags); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 4ca0b5c18192..b84d635567d3 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -536,8 +536,8 @@ void kernfs_put(struct kernfs_node *kn) security_release_secctx(kn->iattr->ia_secdata, kn->iattr->ia_secdata_len); simple_xattrs_free(&kn->iattr->xattrs); + kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } - kfree(kn->iattr); spin_lock(&kernfs_idr_lock); idr_remove(&root->ino_idr, kn->id.ino); spin_unlock(&kernfs_idr_lock); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index f8d5021a652e..ae948aaa4c53 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -832,26 +832,35 @@ void kernfs_drain_open_files(struct kernfs_node *kn) * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ +__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) +{ + struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry); + struct kernfs_open_node *on = kn->attr.open; + + poll_wait(of->file, &on->poll, wait); + + if (of->event != atomic_read(&on->event)) + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; + + return DEFAULT_POLLMASK; +} + static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); - struct kernfs_open_node *on = kn->attr.open; + __poll_t ret; if (!kernfs_get_active(kn)) - goto trigger; + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; - poll_wait(filp, &on->poll, wait); + if (kn->attr.ops->poll) + ret = kn->attr.ops->poll(of, wait); + else + ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); - - if (of->event != atomic_read(&on->event)) - goto trigger; - - return DEFAULT_POLLMASK; - - trigger: - return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; + return ret; } static void kernfs_notify_workfn(struct work_struct *work) diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 80cebcd94c90..0c1fd945ce42 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -42,7 +42,7 @@ static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) if (kn->iattr) goto out_unlock; - kn->iattr = kzalloc(sizeof(struct kernfs_iattrs), GFP_KERNEL); + kn->iattr = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL); if (!kn->iattr) goto out_unlock; iattrs = &kn->iattr->ia_iattr; diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 3d83b114bb08..dba810cd83b1 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -78,7 +78,7 @@ static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) } extern const struct super_operations kernfs_sops; -extern struct kmem_cache *kernfs_node_cache; +extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; /* * inode.c diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index fdf527b6d79c..f3ac352699cf 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -20,7 +20,7 @@ #include "kernfs-internal.h" -struct kmem_cache *kernfs_node_cache; +struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data) { @@ -196,8 +196,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, return dentry; knparent = find_next_ancestor(kn, NULL); - if (WARN_ON(!knparent)) + if (WARN_ON(!knparent)) { + dput(dentry); return ERR_PTR(-EINVAL); + } do { struct dentry *dtmp; @@ -206,8 +208,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, if (kn == knparent) return dentry; kntmp = find_next_ancestor(kn, knparent); - if (WARN_ON(!kntmp)) + if (WARN_ON(!kntmp)) { + dput(dentry); return ERR_PTR(-EINVAL); + } dtmp = lookup_one_len_unlocked(kntmp->name, dentry, strlen(kntmp->name)); dput(dentry); @@ -417,4 +421,9 @@ void __init kernfs_init(void) 0, SLAB_PANIC | SLAB_TYPESAFE_BY_RCU, NULL); + + /* Creates slab cache for kernfs inode attributes */ + kernfs_iattrs_cache = kmem_cache_create("kernfs_iattrs_cache", + sizeof(struct kernfs_iattrs), + 0, SLAB_PANIC, NULL); } diff --git a/fs/locks.c b/fs/locks.c index ff6af2c32601..eaa1cfaf73b0 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1058,7 +1058,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request) return -ENOMEM; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; @@ -1100,7 +1100,7 @@ find_conflict: out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); @@ -1138,7 +1138,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, new_fl2 = locks_alloc_lock(); } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If @@ -1312,7 +1312,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, } out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); /* * Free any unused locks. */ @@ -1584,7 +1584,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return error; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); @@ -1636,13 +1636,13 @@ restart: locks_insert_block(fl, new_fl, leases_conflict); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_blocker, break_time); - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); @@ -1659,7 +1659,7 @@ restart: } out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); locks_free_lock(new_fl); return error; @@ -1729,7 +1729,7 @@ int fcntl_getlease(struct file *filp) ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { @@ -1739,7 +1739,7 @@ int fcntl_getlease(struct file *filp) break; } spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } @@ -1813,7 +1813,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr return -EINVAL; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(dentry, arg, lease->fl_flags); @@ -1884,7 +1884,7 @@ out_setup: lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); @@ -1907,7 +1907,7 @@ static int generic_delete_lease(struct file *filp, void *owner) return error; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp && @@ -1920,7 +1920,7 @@ static int generic_delete_lease(struct file *filp, void *owner) if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); return error; } @@ -2643,13 +2643,13 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx) if (list_empty(&ctx->flc_lease)) return; - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) if (filp == fl->fl_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } diff --git a/fs/namespace.c b/fs/namespace.c index a677b59efd74..c4e83d94840c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2698,7 +2698,6 @@ static long exact_copy_from_user(void *to, const void __user * from, if (!access_ok(from, n)) return n; - current->kernel_uaccess_faults_ok++; while (n) { if (__get_user(c, f)) { memset(t, 0, n); @@ -2708,7 +2707,6 @@ static long exact_copy_from_user(void *to, const void __user * from, f++; n--; } - current->kernel_uaccess_faults_ok--; return n; } @@ -2746,7 +2744,7 @@ void *copy_mount_options(const void __user * data) char *copy_mount_string(const void __user *data) { - return data ? strndup_user(data, PAGE_SIZE) : NULL; + return data ? strndup_user(data, PATH_MAX) : NULL; } /* diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig index 41355ce74ac0..735bfb2e9190 100644 --- a/fs/notify/fanotify/Kconfig +++ b/fs/notify/fanotify/Kconfig @@ -2,6 +2,7 @@ config FANOTIFY bool "Filesystem wide access notification" select FSNOTIFY select ANON_INODES + select EXPORTFS default n ---help--- Say Y here to enable fanotify support. fanotify is a file access diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 3723f3d18d20..6b9c27548997 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -13,22 +13,40 @@ #include <linux/wait.h> #include <linux/audit.h> #include <linux/sched/mm.h> +#include <linux/statfs.h> #include "fanotify.h" static bool should_merge(struct fsnotify_event *old_fsn, struct fsnotify_event *new_fsn) { - struct fanotify_event_info *old, *new; + struct fanotify_event *old, *new; pr_debug("%s: old=%p new=%p\n", __func__, old_fsn, new_fsn); old = FANOTIFY_E(old_fsn); new = FANOTIFY_E(new_fsn); - if (old_fsn->inode == new_fsn->inode && old->pid == new->pid && - old->path.mnt == new->path.mnt && - old->path.dentry == new->path.dentry) - return true; + if (old_fsn->inode != new_fsn->inode || old->pid != new->pid || + old->fh_type != new->fh_type || old->fh_len != new->fh_len) + return false; + + if (fanotify_event_has_path(old)) { + return old->path.mnt == new->path.mnt && + old->path.dentry == new->path.dentry; + } else if (fanotify_event_has_fid(old)) { + /* + * We want to merge many dirent events in the same dir (i.e. + * creates/unlinks/renames), but we do not want to merge dirent + * events referring to subdirs with dirent events referring to + * non subdirs, otherwise, user won't be able to tell from a + * mask FAN_CREATE|FAN_DELETE|FAN_ONDIR if it describes mkdir+ + * unlink pair or rmdir+create pair of events. + */ + return (old->mask & FS_ISDIR) == (new->mask & FS_ISDIR) && + fanotify_fid_equal(&old->fid, &new->fid, old->fh_len); + } + + /* Do not merge events if we failed to encode fid */ return false; } @@ -36,20 +54,22 @@ static bool should_merge(struct fsnotify_event *old_fsn, static int fanotify_merge(struct list_head *list, struct fsnotify_event *event) { struct fsnotify_event *test_event; + struct fanotify_event *new; pr_debug("%s: list=%p event=%p\n", __func__, list, event); + new = FANOTIFY_E(event); /* * Don't merge a permission event with any other event so that we know * the event structure we have created in fanotify_handle_event() is the * one we should check for permission response. */ - if (fanotify_is_perm_event(event->mask)) + if (fanotify_is_perm_event(new->mask)) return 0; list_for_each_entry_reverse(test_event, list, list) { if (should_merge(test_event, event)) { - test_event->mask |= event->mask; + FANOTIFY_E(test_event)->mask |= new->mask; return 1; } } @@ -57,15 +77,44 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event) return 0; } +/* + * Wait for response to permission event. The function also takes care of + * freeing the permission event (or offloads that in case the wait is canceled + * by a signal). The function returns 0 in case access got allowed by userspace, + * -EPERM in case userspace disallowed the access, and -ERESTARTSYS in case + * the wait got interrupted by a signal. + */ static int fanotify_get_response(struct fsnotify_group *group, - struct fanotify_perm_event_info *event, + struct fanotify_perm_event *event, struct fsnotify_iter_info *iter_info) { int ret; pr_debug("%s: group=%p event=%p\n", __func__, group, event); - wait_event(group->fanotify_data.access_waitq, event->response); + ret = wait_event_killable(group->fanotify_data.access_waitq, + event->state == FAN_EVENT_ANSWERED); + /* Signal pending? */ + if (ret < 0) { + spin_lock(&group->notification_lock); + /* Event reported to userspace and no answer yet? */ + if (event->state == FAN_EVENT_REPORTED) { + /* Event will get freed once userspace answers to it */ + event->state = FAN_EVENT_CANCELED; + spin_unlock(&group->notification_lock); + return ret; + } + /* Event not yet reported? Just remove it. */ + if (event->state == FAN_EVENT_INIT) + fsnotify_remove_queued_event(group, &event->fae.fse); + /* + * Event may be also answered in case signal delivery raced + * with wakeup. In that case we have nothing to do besides + * freeing the event and reporting error. + */ + spin_unlock(&group->notification_lock); + goto out; + } /* userspace responded, convert to something usable */ switch (event->response & ~FAN_AUDIT) { @@ -81,11 +130,11 @@ static int fanotify_get_response(struct fsnotify_group *group, if (event->response & FAN_AUDIT) audit_fanotify(event->response & ~FAN_AUDIT); - event->response = 0; - pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__, group, event, ret); - +out: + fsnotify_destroy_event(group, &event->fae.fse); + return ret; } @@ -95,11 +144,13 @@ static int fanotify_get_response(struct fsnotify_group *group, * been included within the event mask, but have not been explicitly * requested by the user, will not be present in the returned mask. */ -static u32 fanotify_group_event_mask(struct fsnotify_iter_info *iter_info, - u32 event_mask, const void *data, - int data_type) +static u32 fanotify_group_event_mask(struct fsnotify_group *group, + struct fsnotify_iter_info *iter_info, + u32 event_mask, const void *data, + int data_type) { __u32 marks_mask = 0, marks_ignored_mask = 0; + __u32 test_mask, user_mask = FANOTIFY_OUTGOING_EVENTS; const struct path *path = data; struct fsnotify_mark *mark; int type; @@ -107,14 +158,14 @@ static u32 fanotify_group_event_mask(struct fsnotify_iter_info *iter_info, pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n", __func__, iter_info->report_mask, event_mask, data, data_type); - /* If we don't have enough info to send an event to userspace say no */ - if (data_type != FSNOTIFY_EVENT_PATH) - return 0; - - /* Sorry, fanotify only gives a damn about files and dirs */ - if (!d_is_reg(path->dentry) && - !d_can_lookup(path->dentry)) - return 0; + if (!FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { + /* Do we have path to open a file descriptor? */ + if (data_type != FSNOTIFY_EVENT_PATH) + return 0; + /* Path type events are only relevant for files and dirs */ + if (!d_is_reg(path->dentry) && !d_can_lookup(path->dentry)) + return 0; + } fsnotify_foreach_obj_type(type) { if (!fsnotify_iter_should_report_type(iter_info, type)) @@ -133,20 +184,106 @@ static u32 fanotify_group_event_mask(struct fsnotify_iter_info *iter_info, marks_ignored_mask |= mark->ignored_mask; } - if (d_is_dir(path->dentry) && + test_mask = event_mask & marks_mask & ~marks_ignored_mask; + + /* + * dirent modification events (create/delete/move) do not carry the + * child entry name/inode information. Instead, we report FAN_ONDIR + * for mkdir/rmdir so user can differentiate them from creat/unlink. + * + * For backward compatibility and consistency, do not report FAN_ONDIR + * to user in legacy fanotify mode (reporting fd) and report FAN_ONDIR + * to user in FAN_REPORT_FID mode for all event types. + */ + if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { + /* Do not report FAN_ONDIR without any event */ + if (!(test_mask & ~FAN_ONDIR)) + return 0; + } else { + user_mask &= ~FAN_ONDIR; + } + + if (event_mask & FS_ISDIR && !(marks_mask & FS_ISDIR & ~marks_ignored_mask)) return 0; - return event_mask & FANOTIFY_OUTGOING_EVENTS & marks_mask & - ~marks_ignored_mask; + return test_mask & user_mask; +} + +static int fanotify_encode_fid(struct fanotify_event *event, + struct inode *inode, gfp_t gfp, + __kernel_fsid_t *fsid) +{ + struct fanotify_fid *fid = &event->fid; + int dwords, bytes = 0; + int err, type; + + fid->ext_fh = NULL; + dwords = 0; + err = -ENOENT; + type = exportfs_encode_inode_fh(inode, NULL, &dwords, NULL); + if (!dwords) + goto out_err; + + bytes = dwords << 2; + if (bytes > FANOTIFY_INLINE_FH_LEN) { + /* Treat failure to allocate fh as failure to allocate event */ + err = -ENOMEM; + fid->ext_fh = kmalloc(bytes, gfp); + if (!fid->ext_fh) + goto out_err; + } + + type = exportfs_encode_inode_fh(inode, fanotify_fid_fh(fid, bytes), + &dwords, NULL); + err = -EINVAL; + if (!type || type == FILEID_INVALID || bytes != dwords << 2) + goto out_err; + + fid->fsid = *fsid; + event->fh_len = bytes; + + return type; + +out_err: + pr_warn_ratelimited("fanotify: failed to encode fid (fsid=%x.%x, " + "type=%d, bytes=%d, err=%i)\n", + fsid->val[0], fsid->val[1], type, bytes, err); + kfree(fid->ext_fh); + fid->ext_fh = NULL; + event->fh_len = 0; + + return FILEID_INVALID; } -struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group, - struct inode *inode, u32 mask, - const struct path *path) +/* + * The inode to use as identifier when reporting fid depends on the event. + * Report the modified directory inode on dirent modification events. + * Report the "victim" inode otherwise. + * For example: + * FS_ATTRIB reports the child inode even if reported on a watched parent. + * FS_CREATE reports the modified dir inode and not the created inode. + */ +static struct inode *fanotify_fid_inode(struct inode *to_tell, u32 event_mask, + const void *data, int data_type) { - struct fanotify_event_info *event = NULL; + if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) + return to_tell; + else if (data_type == FSNOTIFY_EVENT_INODE) + return (struct inode *)data; + else if (data_type == FSNOTIFY_EVENT_PATH) + return d_inode(((struct path *)data)->dentry); + return NULL; +} + +struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, + struct inode *inode, u32 mask, + const void *data, int data_type, + __kernel_fsid_t *fsid) +{ + struct fanotify_event *event = NULL; gfp_t gfp = GFP_KERNEL_ACCOUNT; + struct inode *id = fanotify_fid_inode(inode, mask, data, data_type); /* * For queues with unlimited length lost events are not expected and @@ -160,28 +297,36 @@ struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group, memalloc_use_memcg(group->memcg); if (fanotify_is_perm_event(mask)) { - struct fanotify_perm_event_info *pevent; + struct fanotify_perm_event *pevent; pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp); if (!pevent) goto out; event = &pevent->fae; pevent->response = 0; + pevent->state = FAN_EVENT_INIT; goto init; } event = kmem_cache_alloc(fanotify_event_cachep, gfp); if (!event) goto out; init: __maybe_unused - fsnotify_init_event(&event->fse, inode, mask); + fsnotify_init_event(&event->fse, inode); + event->mask = mask; if (FAN_GROUP_FLAG(group, FAN_REPORT_TID)) event->pid = get_pid(task_pid(current)); else event->pid = get_pid(task_tgid(current)); - if (path) { - event->path = *path; + event->fh_len = 0; + if (id && FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { + /* Report the event without a file identifier on encode error */ + event->fh_type = fanotify_encode_fid(event, id, gfp, fsid); + } else if (data_type == FSNOTIFY_EVENT_PATH) { + event->fh_type = FILEID_ROOT; + event->path = *((struct path *)data); path_get(&event->path); } else { + event->fh_type = FILEID_INVALID; event->path.mnt = NULL; event->path.dentry = NULL; } @@ -190,6 +335,29 @@ out: return event; } +/* + * Get cached fsid of the filesystem containing the object from any connector. + * All connectors are supposed to have the same fsid, but we do not verify that + * here. + */ +static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info) +{ + int type; + __kernel_fsid_t fsid = {}; + + fsnotify_foreach_obj_type(type) { + if (!fsnotify_iter_should_report_type(iter_info, type)) + continue; + + fsid = iter_info->marks[type]->connector->fsid; + if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1])) + continue; + return fsid; + } + + return fsid; +} + static int fanotify_handle_event(struct fsnotify_group *group, struct inode *inode, u32 mask, const void *data, int data_type, @@ -197,14 +365,22 @@ static int fanotify_handle_event(struct fsnotify_group *group, struct fsnotify_iter_info *iter_info) { int ret = 0; - struct fanotify_event_info *event; + struct fanotify_event *event; struct fsnotify_event *fsn_event; + __kernel_fsid_t fsid = {}; BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS); BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY); + BUILD_BUG_ON(FAN_ATTRIB != FS_ATTRIB); BUILD_BUG_ON(FAN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE); BUILD_BUG_ON(FAN_CLOSE_WRITE != FS_CLOSE_WRITE); BUILD_BUG_ON(FAN_OPEN != FS_OPEN); + BUILD_BUG_ON(FAN_MOVED_TO != FS_MOVED_TO); + BUILD_BUG_ON(FAN_MOVED_FROM != FS_MOVED_FROM); + BUILD_BUG_ON(FAN_CREATE != FS_CREATE); + BUILD_BUG_ON(FAN_DELETE != FS_DELETE); + BUILD_BUG_ON(FAN_DELETE_SELF != FS_DELETE_SELF); + BUILD_BUG_ON(FAN_MOVE_SELF != FS_MOVE_SELF); BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD); BUILD_BUG_ON(FAN_Q_OVERFLOW != FS_Q_OVERFLOW); BUILD_BUG_ON(FAN_OPEN_PERM != FS_OPEN_PERM); @@ -213,9 +389,10 @@ static int fanotify_handle_event(struct fsnotify_group *group, BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC); BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 12); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19); - mask = fanotify_group_event_mask(iter_info, mask, data, data_type); + mask = fanotify_group_event_mask(group, iter_info, mask, data, + data_type); if (!mask) return 0; @@ -231,7 +408,11 @@ static int fanotify_handle_event(struct fsnotify_group *group, return 0; } - event = fanotify_alloc_event(group, inode, mask, data); + if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) + fsid = fanotify_get_fsid(iter_info); + + event = fanotify_alloc_event(group, inode, mask, data, data_type, + &fsid); ret = -ENOMEM; if (unlikely(!event)) { /* @@ -255,7 +436,6 @@ static int fanotify_handle_event(struct fsnotify_group *group, } else if (fanotify_is_perm_event(mask)) { ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event), iter_info); - fsnotify_destroy_event(group, fsn_event); } finish: if (fanotify_is_perm_event(mask)) @@ -275,12 +455,15 @@ static void fanotify_free_group_priv(struct fsnotify_group *group) static void fanotify_free_event(struct fsnotify_event *fsn_event) { - struct fanotify_event_info *event; + struct fanotify_event *event; event = FANOTIFY_E(fsn_event); - path_put(&event->path); + if (fanotify_event_has_path(event)) + path_put(&event->path); + else if (fanotify_event_has_ext_fh(event)) + kfree(event->fid.ext_fh); put_pid(event->pid); - if (fanotify_is_perm_event(fsn_event->mask)) { + if (fanotify_is_perm_event(event->mask)) { kmem_cache_free(fanotify_perm_event_cachep, FANOTIFY_PE(fsn_event)); return; diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index ea05b8a401e7..68b30504284c 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -2,26 +2,112 @@ #include <linux/fsnotify_backend.h> #include <linux/path.h> #include <linux/slab.h> +#include <linux/exportfs.h> extern struct kmem_cache *fanotify_mark_cache; extern struct kmem_cache *fanotify_event_cachep; extern struct kmem_cache *fanotify_perm_event_cachep; +/* Possible states of the permission event */ +enum { + FAN_EVENT_INIT, + FAN_EVENT_REPORTED, + FAN_EVENT_ANSWERED, + FAN_EVENT_CANCELED, +}; + +/* + * 3 dwords are sufficient for most local fs (64bit ino, 32bit generation). + * For 32bit arch, fid increases the size of fanotify_event by 12 bytes and + * fh_* fields increase the size of fanotify_event by another 4 bytes. + * For 64bit arch, fid increases the size of fanotify_fid by 8 bytes and + * fh_* fields are packed in a hole after mask. + */ +#if BITS_PER_LONG == 32 +#define FANOTIFY_INLINE_FH_LEN (3 << 2) +#else +#define FANOTIFY_INLINE_FH_LEN (4 << 2) +#endif + +struct fanotify_fid { + __kernel_fsid_t fsid; + union { + unsigned char fh[FANOTIFY_INLINE_FH_LEN]; + unsigned char *ext_fh; + }; +}; + +static inline void *fanotify_fid_fh(struct fanotify_fid *fid, + unsigned int fh_len) +{ + return fh_len <= FANOTIFY_INLINE_FH_LEN ? fid->fh : fid->ext_fh; +} + +static inline bool fanotify_fid_equal(struct fanotify_fid *fid1, + struct fanotify_fid *fid2, + unsigned int fh_len) +{ + return fid1->fsid.val[0] == fid2->fsid.val[0] && + fid1->fsid.val[1] == fid2->fsid.val[1] && + !memcmp(fanotify_fid_fh(fid1, fh_len), + fanotify_fid_fh(fid2, fh_len), fh_len); +} + /* * Structure for normal fanotify events. It gets allocated in * fanotify_handle_event() and freed when the information is retrieved by * userspace */ -struct fanotify_event_info { +struct fanotify_event { struct fsnotify_event fse; + u32 mask; /* - * We hold ref to this path so it may be dereferenced at any point - * during this object's lifetime + * Those fields are outside fanotify_fid to pack fanotify_event nicely + * on 64bit arch and to use fh_type as an indication of whether path + * or fid are used in the union: + * FILEID_ROOT (0) for path, > 0 for fid, FILEID_INVALID for neither. */ - struct path path; + u8 fh_type; + u8 fh_len; + u16 pad; + union { + /* + * We hold ref to this path so it may be dereferenced at any + * point during this object's lifetime + */ + struct path path; + /* + * With FAN_REPORT_FID, we do not hold any reference on the + * victim object. Instead we store its NFS file handle and its + * filesystem's fsid as a unique identifier. + */ + struct fanotify_fid fid; + }; struct pid *pid; }; +static inline bool fanotify_event_has_path(struct fanotify_event *event) +{ + return event->fh_type == FILEID_ROOT; +} + +static inline bool fanotify_event_has_fid(struct fanotify_event *event) +{ + return event->fh_type != FILEID_ROOT && + event->fh_type != FILEID_INVALID; +} + +static inline bool fanotify_event_has_ext_fh(struct fanotify_event *event) +{ + return fanotify_event_has_fid(event) && + event->fh_len > FANOTIFY_INLINE_FH_LEN; +} + +static inline void *fanotify_event_fh(struct fanotify_event *event) +{ + return fanotify_fid_fh(&event->fid, event->fh_len); +} + /* * Structure for permission fanotify events. It gets allocated and freed in * fanotify_handle_event() since we wait there for user response. When the @@ -29,16 +115,17 @@ struct fanotify_event_info { * group->notification_list to group->fanotify_data.access_list to wait for * user response. */ -struct fanotify_perm_event_info { - struct fanotify_event_info fae; - int response; /* userspace answer to question */ +struct fanotify_perm_event { + struct fanotify_event fae; + unsigned short response; /* userspace answer to the event */ + unsigned short state; /* state of the event */ int fd; /* fd we passed to userspace for this event */ }; -static inline struct fanotify_perm_event_info * +static inline struct fanotify_perm_event * FANOTIFY_PE(struct fsnotify_event *fse) { - return container_of(fse, struct fanotify_perm_event_info, fae.fse); + return container_of(fse, struct fanotify_perm_event, fae.fse); } static inline bool fanotify_is_perm_event(u32 mask) @@ -47,11 +134,12 @@ static inline bool fanotify_is_perm_event(u32 mask) mask & FANOTIFY_PERM_EVENTS; } -static inline struct fanotify_event_info *FANOTIFY_E(struct fsnotify_event *fse) +static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse) { - return container_of(fse, struct fanotify_event_info, fse); + return container_of(fse, struct fanotify_event, fse); } -struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group, - struct inode *inode, u32 mask, - const struct path *path); +struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, + struct inode *inode, u32 mask, + const void *data, int data_type, + __kernel_fsid_t *fsid); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 9c870b0d2b56..56992b32c6bb 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -17,6 +17,8 @@ #include <linux/compat.h> #include <linux/sched/signal.h> #include <linux/memcontrol.h> +#include <linux/statfs.h> +#include <linux/exportfs.h> #include <asm/ioctls.h> @@ -47,33 +49,55 @@ struct kmem_cache *fanotify_mark_cache __read_mostly; struct kmem_cache *fanotify_event_cachep __read_mostly; struct kmem_cache *fanotify_perm_event_cachep __read_mostly; +#define FANOTIFY_EVENT_ALIGN 4 + +static int fanotify_event_info_len(struct fanotify_event *event) +{ + if (!fanotify_event_has_fid(event)) + return 0; + + return roundup(sizeof(struct fanotify_event_info_fid) + + sizeof(struct file_handle) + event->fh_len, + FANOTIFY_EVENT_ALIGN); +} + /* * Get an fsnotify notification event if one exists and is small * enough to fit in "count". Return an error pointer if the count - * is not large enough. - * - * Called with the group->notification_lock held. + * is not large enough. When permission event is dequeued, its state is + * updated accordingly. */ static struct fsnotify_event *get_one_event(struct fsnotify_group *group, size_t count) { - assert_spin_locked(&group->notification_lock); + size_t event_size = FAN_EVENT_METADATA_LEN; + struct fsnotify_event *fsn_event = NULL; pr_debug("%s: group=%p count=%zd\n", __func__, group, count); + spin_lock(&group->notification_lock); if (fsnotify_notify_queue_is_empty(group)) - return NULL; + goto out; - if (FAN_EVENT_METADATA_LEN > count) - return ERR_PTR(-EINVAL); + if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { + event_size += fanotify_event_info_len( + FANOTIFY_E(fsnotify_peek_first_event(group))); + } - /* held the notification_lock the whole time, so this is the - * same event we peeked above */ - return fsnotify_remove_first_event(group); + if (event_size > count) { + fsn_event = ERR_PTR(-EINVAL); + goto out; + } + fsn_event = fsnotify_remove_first_event(group); + if (fanotify_is_perm_event(FANOTIFY_E(fsn_event)->mask)) + FANOTIFY_PE(fsn_event)->state = FAN_EVENT_REPORTED; +out: + spin_unlock(&group->notification_lock); + return fsn_event; } static int create_fd(struct fsnotify_group *group, - struct fanotify_event_info *event, + struct fanotify_event *event, struct file **file) { int client_fd; @@ -114,62 +138,32 @@ static int create_fd(struct fsnotify_group *group, return client_fd; } -static int fill_event_metadata(struct fsnotify_group *group, - struct fanotify_event_metadata *metadata, - struct fsnotify_event *fsn_event, - struct file **file) -{ - int ret = 0; - struct fanotify_event_info *event; - - pr_debug("%s: group=%p metadata=%p event=%p\n", __func__, - group, metadata, fsn_event); - - *file = NULL; - event = container_of(fsn_event, struct fanotify_event_info, fse); - metadata->event_len = FAN_EVENT_METADATA_LEN; - metadata->metadata_len = FAN_EVENT_METADATA_LEN; - metadata->vers = FANOTIFY_METADATA_VERSION; - metadata->reserved = 0; - metadata->mask = fsn_event->mask & FANOTIFY_OUTGOING_EVENTS; - metadata->pid = pid_vnr(event->pid); - if (unlikely(fsn_event->mask & FAN_Q_OVERFLOW)) - metadata->fd = FAN_NOFD; - else { - metadata->fd = create_fd(group, event, file); - if (metadata->fd < 0) - ret = metadata->fd; - } - - return ret; -} - -static struct fanotify_perm_event_info *dequeue_event( - struct fsnotify_group *group, int fd) +/* + * Finish processing of permission event by setting it to ANSWERED state and + * drop group->notification_lock. + */ +static void finish_permission_event(struct fsnotify_group *group, + struct fanotify_perm_event *event, + unsigned int response) + __releases(&group->notification_lock) { - struct fanotify_perm_event_info *event, *return_e = NULL; - - spin_lock(&group->notification_lock); - list_for_each_entry(event, &group->fanotify_data.access_list, - fae.fse.list) { - if (event->fd != fd) - continue; + bool destroy = false; - list_del_init(&event->fae.fse.list); - return_e = event; - break; - } + assert_spin_locked(&group->notification_lock); + event->response = response; + if (event->state == FAN_EVENT_CANCELED) + destroy = true; + else + event->state = FAN_EVENT_ANSWERED; spin_unlock(&group->notification_lock); - - pr_debug("%s: found return_re=%p\n", __func__, return_e); - - return return_e; + if (destroy) + fsnotify_destroy_event(group, &event->fae.fse); } static int process_access_response(struct fsnotify_group *group, struct fanotify_response *response_struct) { - struct fanotify_perm_event_info *event; + struct fanotify_perm_event *event; int fd = response_struct->fd; int response = response_struct->response; @@ -194,48 +188,115 @@ static int process_access_response(struct fsnotify_group *group, if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT)) return -EINVAL; - event = dequeue_event(group, fd); - if (!event) - return -ENOENT; + spin_lock(&group->notification_lock); + list_for_each_entry(event, &group->fanotify_data.access_list, + fae.fse.list) { + if (event->fd != fd) + continue; - event->response = response; - wake_up(&group->fanotify_data.access_waitq); + list_del_init(&event->fae.fse.list); + finish_permission_event(group, event, response); + wake_up(&group->fanotify_data.access_waitq); + return 0; + } + spin_unlock(&group->notification_lock); + + return -ENOENT; +} + +static int copy_fid_to_user(struct fanotify_event *event, char __user *buf) +{ + struct fanotify_event_info_fid info = { }; + struct file_handle handle = { }; + size_t fh_len = event->fh_len; + size_t len = fanotify_event_info_len(event); + + if (!len) + return 0; + + if (WARN_ON_ONCE(len < sizeof(info) + sizeof(handle) + fh_len)) + return -EFAULT; + + /* Copy event info fid header followed by vaiable sized file handle */ + info.hdr.info_type = FAN_EVENT_INFO_TYPE_FID; + info.hdr.len = len; + info.fsid = event->fid.fsid; + if (copy_to_user(buf, &info, sizeof(info))) + return -EFAULT; + + buf += sizeof(info); + len -= sizeof(info); + handle.handle_type = event->fh_type; + handle.handle_bytes = fh_len; + if (copy_to_user(buf, &handle, sizeof(handle))) + return -EFAULT; + + buf += sizeof(handle); + len -= sizeof(handle); + if (copy_to_user(buf, fanotify_event_fh(event), fh_len)) + return -EFAULT; + + /* Pad with 0's */ + buf += fh_len; + len -= fh_len; + WARN_ON_ONCE(len < 0 || len >= FANOTIFY_EVENT_ALIGN); + if (len > 0 && clear_user(buf, len)) + return -EFAULT; return 0; } static ssize_t copy_event_to_user(struct fsnotify_group *group, - struct fsnotify_event *event, + struct fsnotify_event *fsn_event, char __user *buf, size_t count) { - struct fanotify_event_metadata fanotify_event_metadata; - struct file *f; - int fd, ret; - - pr_debug("%s: group=%p event=%p\n", __func__, group, event); - - ret = fill_event_metadata(group, &fanotify_event_metadata, event, &f); - if (ret < 0) - return ret; + struct fanotify_event_metadata metadata; + struct fanotify_event *event; + struct file *f = NULL; + int ret, fd = FAN_NOFD; + + pr_debug("%s: group=%p event=%p\n", __func__, group, fsn_event); + + event = container_of(fsn_event, struct fanotify_event, fse); + metadata.event_len = FAN_EVENT_METADATA_LEN; + metadata.metadata_len = FAN_EVENT_METADATA_LEN; + metadata.vers = FANOTIFY_METADATA_VERSION; + metadata.reserved = 0; + metadata.mask = event->mask & FANOTIFY_OUTGOING_EVENTS; + metadata.pid = pid_vnr(event->pid); + + if (fanotify_event_has_path(event)) { + fd = create_fd(group, event, &f); + if (fd < 0) + return fd; + } else if (fanotify_event_has_fid(event)) { + metadata.event_len += fanotify_event_info_len(event); + } + metadata.fd = fd; - fd = fanotify_event_metadata.fd; ret = -EFAULT; /* * Sanity check copy size in case get_one_event() and * fill_event_metadata() event_len sizes ever get out of sync. */ - if (WARN_ON_ONCE(fanotify_event_metadata.event_len > count)) + if (WARN_ON_ONCE(metadata.event_len > count)) goto out_close_fd; - if (copy_to_user(buf, &fanotify_event_metadata, - fanotify_event_metadata.event_len)) + + if (copy_to_user(buf, &metadata, FAN_EVENT_METADATA_LEN)) goto out_close_fd; if (fanotify_is_perm_event(event->mask)) - FANOTIFY_PE(event)->fd = fd; + FANOTIFY_PE(fsn_event)->fd = fd; - if (fd != FAN_NOFD) + if (fanotify_event_has_path(event)) { fd_install(fd, f); - return fanotify_event_metadata.event_len; + } else if (fanotify_event_has_fid(event)) { + ret = copy_fid_to_user(event, buf + FAN_EVENT_METADATA_LEN); + if (ret < 0) + return ret; + } + + return metadata.event_len; out_close_fd: if (fd != FAN_NOFD) { @@ -276,10 +337,7 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, add_wait_queue(&group->notification_waitq, &wait); while (1) { - spin_lock(&group->notification_lock); kevent = get_one_event(group, count); - spin_unlock(&group->notification_lock); - if (IS_ERR(kevent)) { ret = PTR_ERR(kevent); break; @@ -316,11 +374,13 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, * Permission events get queued to wait for response. Other * events can be destroyed now. */ - if (!fanotify_is_perm_event(kevent->mask)) { + if (!fanotify_is_perm_event(FANOTIFY_E(kevent)->mask)) { fsnotify_destroy_event(group, kevent); } else { if (ret <= 0) { - FANOTIFY_PE(kevent)->response = FAN_DENY; + spin_lock(&group->notification_lock); + finish_permission_event(group, + FANOTIFY_PE(kevent), FAN_DENY); wake_up(&group->fanotify_data.access_waitq); } else { spin_lock(&group->notification_lock); @@ -370,7 +430,7 @@ static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t static int fanotify_release(struct inode *ignored, struct file *file) { struct fsnotify_group *group = file->private_data; - struct fanotify_perm_event_info *event, *next; + struct fanotify_perm_event *event; struct fsnotify_event *fsn_event; /* @@ -385,13 +445,12 @@ static int fanotify_release(struct inode *ignored, struct file *file) * and simulate reply from userspace. */ spin_lock(&group->notification_lock); - list_for_each_entry_safe(event, next, &group->fanotify_data.access_list, - fae.fse.list) { - pr_debug("%s: found group=%p event=%p\n", __func__, group, - event); - + while (!list_empty(&group->fanotify_data.access_list)) { + event = list_first_entry(&group->fanotify_data.access_list, + struct fanotify_perm_event, fae.fse.list); list_del_init(&event->fae.fse.list); - event->response = FAN_ALLOW; + finish_permission_event(group, event, FAN_ALLOW); + spin_lock(&group->notification_lock); } /* @@ -401,13 +460,14 @@ static int fanotify_release(struct inode *ignored, struct file *file) */ while (!fsnotify_notify_queue_is_empty(group)) { fsn_event = fsnotify_remove_first_event(group); - if (!(fsn_event->mask & FANOTIFY_PERM_EVENTS)) { + if (!(FANOTIFY_E(fsn_event)->mask & FANOTIFY_PERM_EVENTS)) { spin_unlock(&group->notification_lock); fsnotify_destroy_event(group, fsn_event); - spin_lock(&group->notification_lock); } else { - FANOTIFY_PE(fsn_event)->response = FAN_ALLOW; + finish_permission_event(group, FANOTIFY_PE(fsn_event), + FAN_ALLOW); } + spin_lock(&group->notification_lock); } spin_unlock(&group->notification_lock); @@ -598,7 +658,8 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group, fsnotify_connp_t *connp, - unsigned int type) + unsigned int type, + __kernel_fsid_t *fsid) { struct fsnotify_mark *mark; int ret; @@ -611,7 +672,7 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group, return ERR_PTR(-ENOMEM); fsnotify_init_mark(mark, group); - ret = fsnotify_add_mark_locked(mark, connp, type, 0); + ret = fsnotify_add_mark_locked(mark, connp, type, 0, fsid); if (ret) { fsnotify_put_mark(mark); return ERR_PTR(ret); @@ -623,7 +684,8 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group, static int fanotify_add_mark(struct fsnotify_group *group, fsnotify_connp_t *connp, unsigned int type, - __u32 mask, unsigned int flags) + __u32 mask, unsigned int flags, + __kernel_fsid_t *fsid) { struct fsnotify_mark *fsn_mark; __u32 added; @@ -631,7 +693,7 @@ static int fanotify_add_mark(struct fsnotify_group *group, mutex_lock(&group->mark_mutex); fsn_mark = fsnotify_find_mark(connp, group); if (!fsn_mark) { - fsn_mark = fanotify_add_new_mark(group, connp, type); + fsn_mark = fanotify_add_new_mark(group, connp, type, fsid); if (IS_ERR(fsn_mark)) { mutex_unlock(&group->mark_mutex); return PTR_ERR(fsn_mark); @@ -648,23 +710,23 @@ static int fanotify_add_mark(struct fsnotify_group *group, static int fanotify_add_vfsmount_mark(struct fsnotify_group *group, struct vfsmount *mnt, __u32 mask, - unsigned int flags) + unsigned int flags, __kernel_fsid_t *fsid) { return fanotify_add_mark(group, &real_mount(mnt)->mnt_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags); + FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags, fsid); } static int fanotify_add_sb_mark(struct fsnotify_group *group, - struct super_block *sb, __u32 mask, - unsigned int flags) + struct super_block *sb, __u32 mask, + unsigned int flags, __kernel_fsid_t *fsid) { return fanotify_add_mark(group, &sb->s_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_SB, mask, flags); + FSNOTIFY_OBJ_TYPE_SB, mask, flags, fsid); } static int fanotify_add_inode_mark(struct fsnotify_group *group, struct inode *inode, __u32 mask, - unsigned int flags) + unsigned int flags, __kernel_fsid_t *fsid) { pr_debug("%s: group=%p inode=%p\n", __func__, group, inode); @@ -679,7 +741,7 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group, return 0; return fanotify_add_mark(group, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, mask, flags); + FSNOTIFY_OBJ_TYPE_INODE, mask, flags, fsid); } /* fanotify syscalls */ @@ -688,7 +750,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) struct fsnotify_group *group; int f_flags, fd; struct user_struct *user; - struct fanotify_event_info *oevent; + struct fanotify_event *oevent; pr_debug("%s: flags=%x event_f_flags=%x\n", __func__, flags, event_f_flags); @@ -715,6 +777,10 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) return -EINVAL; } + if ((flags & FAN_REPORT_FID) && + (flags & FANOTIFY_CLASS_BITS) != FAN_CLASS_NOTIF) + return -EINVAL; + user = get_current_user(); if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) { free_uid(user); @@ -739,7 +805,8 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) atomic_inc(&user->fanotify_listeners); group->memcg = get_mem_cgroup_from_mm(current->mm); - oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL); + oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL, + FSNOTIFY_EVENT_NONE, NULL); if (unlikely(!oevent)) { fd = -ENOMEM; goto out_destroy_group; @@ -801,6 +868,48 @@ out_destroy_group: return fd; } +/* Check if filesystem can encode a unique fid */ +static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) +{ + __kernel_fsid_t root_fsid; + int err; + + /* + * Make sure path is not in filesystem with zero fsid (e.g. tmpfs). + */ + err = vfs_get_fsid(path->dentry, fsid); + if (err) + return err; + + if (!fsid->val[0] && !fsid->val[1]) + return -ENODEV; + + /* + * Make sure path is not inside a filesystem subvolume (e.g. btrfs) + * which uses a different fsid than sb root. + */ + err = vfs_get_fsid(path->dentry->d_sb->s_root, &root_fsid); + if (err) + return err; + + if (root_fsid.val[0] != fsid->val[0] || + root_fsid.val[1] != fsid->val[1]) + return -EXDEV; + + /* + * We need to make sure that the file system supports at least + * encoding a file handle so user can use name_to_handle_at() to + * compare fid returned with event to the file handle of watched + * objects. However, name_to_handle_at() requires that the + * filesystem also supports decoding file handles. + */ + if (!path->dentry->d_sb->s_export_op || + !path->dentry->d_sb->s_export_op->fh_to_dentry) + return -EOPNOTSUPP; + + return 0; +} + static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, int dfd, const char __user *pathname) { @@ -809,6 +918,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, struct fsnotify_group *group; struct fd f; struct path path; + __kernel_fsid_t __fsid, *fsid = NULL; u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS; unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; int ret; @@ -871,6 +981,18 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, group->priority == FS_PRIO_0) goto fput_and_out; + /* + * Events with data type inode do not carry enough information to report + * event->fd, so we do not allow setting a mask for inode events unless + * group supports reporting fid. + * inode events are not supported on a mount mark, because they do not + * carry enough information (i.e. path) to be filtered by mount point. + */ + if (mask & FANOTIFY_INODE_EVENTS && + (!FAN_GROUP_FLAG(group, FAN_REPORT_FID) || + mark_type == FAN_MARK_MOUNT)) + goto fput_and_out; + if (flags & FAN_MARK_FLUSH) { ret = 0; if (mark_type == FAN_MARK_MOUNT) @@ -886,6 +1008,14 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (ret) goto fput_and_out; + if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { + ret = fanotify_test_fid(&path, &__fsid); + if (ret) + goto path_put_and_out; + + fsid = &__fsid; + } + /* inode held in place by reference to path; group by fget on fd */ if (mark_type == FAN_MARK_INODE) inode = path.dentry->d_inode; @@ -896,24 +1026,31 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) { case FAN_MARK_ADD: if (mark_type == FAN_MARK_MOUNT) - ret = fanotify_add_vfsmount_mark(group, mnt, mask, flags); + ret = fanotify_add_vfsmount_mark(group, mnt, mask, + flags, fsid); else if (mark_type == FAN_MARK_FILESYSTEM) - ret = fanotify_add_sb_mark(group, mnt->mnt_sb, mask, flags); + ret = fanotify_add_sb_mark(group, mnt->mnt_sb, mask, + flags, fsid); else - ret = fanotify_add_inode_mark(group, inode, mask, flags); + ret = fanotify_add_inode_mark(group, inode, mask, + flags, fsid); break; case FAN_MARK_REMOVE: if (mark_type == FAN_MARK_MOUNT) - ret = fanotify_remove_vfsmount_mark(group, mnt, mask, flags); + ret = fanotify_remove_vfsmount_mark(group, mnt, mask, + flags); else if (mark_type == FAN_MARK_FILESYSTEM) - ret = fanotify_remove_sb_mark(group, mnt->mnt_sb, mask, flags); + ret = fanotify_remove_sb_mark(group, mnt->mnt_sb, mask, + flags); else - ret = fanotify_remove_inode_mark(group, inode, mask, flags); + ret = fanotify_remove_inode_mark(group, inode, mask, + flags); break; default: ret = -EINVAL; } +path_put_and_out: path_put(&path); fput_and_out: fdput(f); @@ -950,15 +1087,15 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark, */ static int __init fanotify_user_setup(void) { - BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 7); + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 8); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9); fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); - fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC); + fanotify_event_cachep = KMEM_CACHE(fanotify_event, SLAB_PANIC); if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) { fanotify_perm_event_cachep = - KMEM_CACHE(fanotify_perm_event_info, SLAB_PANIC); + KMEM_CACHE(fanotify_perm_event, SLAB_PANIC); } return 0; diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index ecf09b6243d9..df06f3da166c 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -328,16 +328,15 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, const unsigned char *file_name, u32 cookie) { struct fsnotify_iter_info iter_info = {}; - struct super_block *sb = NULL; + struct super_block *sb = to_tell->i_sb; struct mount *mnt = NULL; - __u32 mnt_or_sb_mask = 0; + __u32 mnt_or_sb_mask = sb->s_fsnotify_mask; int ret = 0; __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS); if (data_is == FSNOTIFY_EVENT_PATH) { mnt = real_mount(((const struct path *)data)->mnt); - sb = mnt->mnt.mnt_sb; - mnt_or_sb_mask = mnt->mnt_fsnotify_mask | sb->s_fsnotify_mask; + mnt_or_sb_mask |= mnt->mnt_fsnotify_mask; } /* An event "on child" is not intended for a mount/sb mark */ if (mask & FS_EVENT_ON_CHILD) @@ -350,8 +349,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, * SRCU because we have no references to any objects and do not * need SRCU to keep them "alive". */ - if (!to_tell->i_fsnotify_marks && - (!mnt || (!mnt->mnt_fsnotify_marks && !sb->s_fsnotify_marks))) + if (!to_tell->i_fsnotify_marks && !sb->s_fsnotify_marks && + (!mnt || !mnt->mnt_fsnotify_marks)) return 0; /* * if this is a modify event we may need to clear the ignored masks @@ -366,11 +365,11 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = fsnotify_first_mark(&to_tell->i_fsnotify_marks); + iter_info.marks[FSNOTIFY_OBJ_TYPE_SB] = + fsnotify_first_mark(&sb->s_fsnotify_marks); if (mnt) { iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); - iter_info.marks[FSNOTIFY_OBJ_TYPE_SB] = - fsnotify_first_mark(&sb->s_fsnotify_marks); } /* diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h index 7e4578d35b61..74ae60305189 100644 --- a/fs/notify/inotify/inotify.h +++ b/fs/notify/inotify/inotify.h @@ -5,6 +5,7 @@ struct inotify_event_info { struct fsnotify_event fse; + u32 mask; int wd; u32 sync_cookie; int name_len; diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index f4184b4f3815..ff30abd6a49b 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -43,11 +43,11 @@ static bool event_compare(struct fsnotify_event *old_fsn, { struct inotify_event_info *old, *new; - if (old_fsn->mask & FS_IN_IGNORED) - return false; old = INOTIFY_E(old_fsn); new = INOTIFY_E(new_fsn); - if ((old_fsn->mask == new_fsn->mask) && + if (old->mask & FS_IN_IGNORED) + return false; + if ((old->mask == new->mask) && (old_fsn->inode == new_fsn->inode) && (old->name_len == new->name_len) && (!old->name_len || !strcmp(old->name, new->name))) @@ -113,8 +113,18 @@ int inotify_handle_event(struct fsnotify_group *group, return -ENOMEM; } + /* + * We now report FS_ISDIR flag with MOVE_SELF and DELETE_SELF events + * for fanotify. inotify never reported IN_ISDIR with those events. + * It looks like an oversight, but to avoid the risk of breaking + * existing inotify programs, mask the flag out from those events. + */ + if (mask & (IN_MOVE_SELF | IN_DELETE_SELF)) + mask &= ~IN_ISDIR; + fsn_event = &event->fse; - fsnotify_init_event(fsn_event, inode, mask); + fsnotify_init_event(fsn_event, inode); + event->mask = mask; event->wd = i_mark->wd; event->sync_cookie = cookie; event->name_len = len; diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 798f1253141a..e2901fbb9f76 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -189,7 +189,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, */ pad_name_len = round_event_name_len(fsn_event); inotify_event.len = pad_name_len; - inotify_event.mask = inotify_mask_to_arg(fsn_event->mask); + inotify_event.mask = inotify_mask_to_arg(event->mask); inotify_event.wd = event->wd; inotify_event.cookie = event->sync_cookie; @@ -634,7 +634,8 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events) return ERR_PTR(-ENOMEM); } group->overflow_event = &oevent->fse; - fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW); + fsnotify_init_event(group->overflow_event, NULL); + oevent->mask = FS_Q_OVERFLOW; oevent->wd = -1; oevent->sync_cookie = 0; oevent->name_len = 0; diff --git a/fs/notify/mark.c b/fs/notify/mark.c index d2dd16cb5989..d593d4269561 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -82,6 +82,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/srcu.h> +#include <linux/ratelimit.h> #include <linux/atomic.h> @@ -481,7 +482,8 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, - unsigned int type) + unsigned int type, + __kernel_fsid_t *fsid) { struct inode *inode = NULL; struct fsnotify_mark_connector *conn; @@ -493,6 +495,11 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, INIT_HLIST_HEAD(&conn->list); conn->type = type; conn->obj = connp; + /* Cache fsid of filesystem containing the object */ + if (fsid) + conn->fsid = *fsid; + else + conn->fsid.val[0] = conn->fsid.val[1] = 0; if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) inode = igrab(fsnotify_conn_inode(conn)); /* @@ -544,7 +551,7 @@ out: */ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int type, - int allow_dups) + int allow_dups, __kernel_fsid_t *fsid) { struct fsnotify_mark *lmark, *last = NULL; struct fsnotify_mark_connector *conn; @@ -553,15 +560,36 @@ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, if (WARN_ON(!fsnotify_valid_obj_type(type))) return -EINVAL; + + /* Backend is expected to check for zero fsid (e.g. tmpfs) */ + if (fsid && WARN_ON_ONCE(!fsid->val[0] && !fsid->val[1])) + return -ENODEV; + restart: spin_lock(&mark->lock); conn = fsnotify_grab_connector(connp); if (!conn) { spin_unlock(&mark->lock); - err = fsnotify_attach_connector_to_object(connp, type); + err = fsnotify_attach_connector_to_object(connp, type, fsid); if (err) return err; goto restart; + } else if (fsid && (conn->fsid.val[0] || conn->fsid.val[1]) && + (fsid->val[0] != conn->fsid.val[0] || + fsid->val[1] != conn->fsid.val[1])) { + /* + * Backend is expected to check for non uniform fsid + * (e.g. btrfs), but maybe we missed something? + * Only allow setting conn->fsid once to non zero fsid. + * inotify and non-fid fanotify groups do not set nor test + * conn->fsid. + */ + pr_warn_ratelimited("%s: fsid mismatch on object of type %u: " + "%x.%x != %x.%x\n", __func__, conn->type, + fsid->val[0], fsid->val[1], + conn->fsid.val[0], conn->fsid.val[1]); + err = -EXDEV; + goto out_err; } /* is mark the first mark? */ @@ -606,7 +634,7 @@ out_err: */ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int type, - int allow_dups) + int allow_dups, __kernel_fsid_t *fsid) { struct fsnotify_group *group = mark->group; int ret = 0; @@ -627,7 +655,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_get_mark(mark); /* for g_list */ spin_unlock(&mark->lock); - ret = fsnotify_add_mark_list(mark, connp, type, allow_dups); + ret = fsnotify_add_mark_list(mark, connp, type, allow_dups, fsid); if (ret) goto err; @@ -648,13 +676,13 @@ err: } int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, - unsigned int type, int allow_dups) + unsigned int type, int allow_dups, __kernel_fsid_t *fsid) { int ret; struct fsnotify_group *group = mark->group; mutex_lock(&group->mark_mutex); - ret = fsnotify_add_mark_locked(mark, connp, type, allow_dups); + ret = fsnotify_add_mark_locked(mark, connp, type, allow_dups, fsid); mutex_unlock(&group->mark_mutex); return ret; } diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 3c3e36745f59..5f3a54d444b5 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -71,7 +71,7 @@ void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event) { /* Overflow events are per-group and we don't want to free them */ - if (!event || event->mask == FS_Q_OVERFLOW) + if (!event || event == group->overflow_event) return; /* * If the event is still queued, we have a problem... Do an unreliable @@ -141,6 +141,18 @@ queue: return ret; } +void fsnotify_remove_queued_event(struct fsnotify_group *group, + struct fsnotify_event *event) +{ + assert_spin_locked(&group->notification_lock); + /* + * We need to init list head for the case of overflow event so that + * check in fsnotify_add_event() works + */ + list_del_init(&event->list); + group->q_len--; +} + /* * Remove and return the first event from the notification list. It is the * responsibility of the caller to destroy the obtained event @@ -155,13 +167,7 @@ struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group) event = list_first_entry(&group->notification_list, struct fsnotify_event, list); - /* - * We need to init list head for the case of overflow event so that - * check in fsnotify_add_event() works - */ - list_del_init(&event->list); - group->q_len--; - + fsnotify_remove_queued_event(group, event); return event; } @@ -194,23 +200,3 @@ void fsnotify_flush_notify(struct fsnotify_group *group) } spin_unlock(&group->notification_lock); } - -/* - * fsnotify_create_event - Allocate a new event which will be sent to each - * group's handle_event function if the group was interested in this - * particular event. - * - * @inode the inode which is supposed to receive the event (sometimes a - * parent of the inode to which the event happened. - * @mask what actually happened. - * @data pointer to the object which was actually affected - * @data_type flag indication if the data is a file, path, inode, nothing... - * @name the filename, if available - */ -void fsnotify_init_event(struct fsnotify_event *event, struct inode *inode, - u32 mask) -{ - INIT_LIST_HEAD(&event->list); - event->inode = inode; - event->mask = mask; -} diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index d1cbb27808e2..6f0999015a44 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7532,10 +7532,11 @@ static int ocfs2_trim_group(struct super_block *sb, return count; } -int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) +static +int ocfs2_trim_mainbm(struct super_block *sb, struct fstrim_range *range) { struct ocfs2_super *osb = OCFS2_SB(sb); - u64 start, len, trimmed, first_group, last_group, group; + u64 start, len, trimmed = 0, first_group, last_group = 0, group = 0; int ret, cnt; u32 first_bit, last_bit, minlen; struct buffer_head *main_bm_bh = NULL; @@ -7543,7 +7544,6 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) struct buffer_head *gd_bh = NULL; struct ocfs2_dinode *main_bm; struct ocfs2_group_desc *gd = NULL; - struct ocfs2_trim_fs_info info, *pinfo = NULL; start = range->start >> osb->s_clustersize_bits; len = range->len >> osb->s_clustersize_bits; @@ -7552,6 +7552,9 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) if (minlen >= osb->bitmap_cpg || range->len < sb->s_blocksize) return -EINVAL; + trace_ocfs2_trim_mainbm(start, len, minlen); + +next_group: main_bm_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); @@ -7570,64 +7573,34 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) } main_bm = (struct ocfs2_dinode *)main_bm_bh->b_data; - if (start >= le32_to_cpu(main_bm->i_clusters)) { - ret = -EINVAL; - goto out_unlock; - } - - len = range->len >> osb->s_clustersize_bits; - if (start + len > le32_to_cpu(main_bm->i_clusters)) - len = le32_to_cpu(main_bm->i_clusters) - start; - - trace_ocfs2_trim_fs(start, len, minlen); - - ocfs2_trim_fs_lock_res_init(osb); - ret = ocfs2_trim_fs_lock(osb, NULL, 1); - if (ret < 0) { - if (ret != -EAGAIN) { - mlog_errno(ret); - ocfs2_trim_fs_lock_res_uninit(osb); + /* + * Do some check before trim the first group. + */ + if (!group) { + if (start >= le32_to_cpu(main_bm->i_clusters)) { + ret = -EINVAL; goto out_unlock; } - mlog(ML_NOTICE, "Wait for trim on device (%s) to " - "finish, which is running from another node.\n", - osb->dev_str); - ret = ocfs2_trim_fs_lock(osb, &info, 0); - if (ret < 0) { - mlog_errno(ret); - ocfs2_trim_fs_lock_res_uninit(osb); - goto out_unlock; - } + if (start + len > le32_to_cpu(main_bm->i_clusters)) + len = le32_to_cpu(main_bm->i_clusters) - start; - if (info.tf_valid && info.tf_success && - info.tf_start == start && info.tf_len == len && - info.tf_minlen == minlen) { - /* Avoid sending duplicated trim to a shared device */ - mlog(ML_NOTICE, "The same trim on device (%s) was " - "just done from node (%u), return.\n", - osb->dev_str, info.tf_nodenum); - range->len = info.tf_trimlen; - goto out_trimunlock; - } + /* + * Determine first and last group to examine based on + * start and len + */ + first_group = ocfs2_which_cluster_group(main_bm_inode, start); + if (first_group == osb->first_cluster_group_blkno) + first_bit = start; + else + first_bit = start - ocfs2_blocks_to_clusters(sb, + first_group); + last_group = ocfs2_which_cluster_group(main_bm_inode, + start + len - 1); + group = first_group; } - info.tf_nodenum = osb->node_num; - info.tf_start = start; - info.tf_len = len; - info.tf_minlen = minlen; - - /* Determine first and last group to examine based on start and len */ - first_group = ocfs2_which_cluster_group(main_bm_inode, start); - if (first_group == osb->first_cluster_group_blkno) - first_bit = start; - else - first_bit = start - ocfs2_blocks_to_clusters(sb, first_group); - last_group = ocfs2_which_cluster_group(main_bm_inode, start + len - 1); - last_bit = osb->bitmap_cpg; - - trimmed = 0; - for (group = first_group; group <= last_group;) { + do { if (first_bit + len >= osb->bitmap_cpg) last_bit = osb->bitmap_cpg; else @@ -7659,21 +7632,81 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) group = ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg); else group += ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg); - } - range->len = trimmed * sb->s_blocksize; + } while (0); - info.tf_trimlen = range->len; - info.tf_success = (ret ? 0 : 1); - pinfo = &info; -out_trimunlock: - ocfs2_trim_fs_unlock(osb, pinfo); - ocfs2_trim_fs_lock_res_uninit(osb); out_unlock: ocfs2_inode_unlock(main_bm_inode, 0); brelse(main_bm_bh); + main_bm_bh = NULL; out_mutex: inode_unlock(main_bm_inode); iput(main_bm_inode); + + /* + * If all the groups trim are not done or failed, but we should release + * main_bm related locks for avoiding the current IO starve, then go to + * trim the next group + */ + if (ret >= 0 && group <= last_group) + goto next_group; out: + range->len = trimmed * sb->s_blocksize; + return ret; +} + +int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) +{ + int ret; + struct ocfs2_super *osb = OCFS2_SB(sb); + struct ocfs2_trim_fs_info info, *pinfo = NULL; + + ocfs2_trim_fs_lock_res_init(osb); + + trace_ocfs2_trim_fs(range->start, range->len, range->minlen); + + ret = ocfs2_trim_fs_lock(osb, NULL, 1); + if (ret < 0) { + if (ret != -EAGAIN) { + mlog_errno(ret); + ocfs2_trim_fs_lock_res_uninit(osb); + return ret; + } + + mlog(ML_NOTICE, "Wait for trim on device (%s) to " + "finish, which is running from another node.\n", + osb->dev_str); + ret = ocfs2_trim_fs_lock(osb, &info, 0); + if (ret < 0) { + mlog_errno(ret); + ocfs2_trim_fs_lock_res_uninit(osb); + return ret; + } + + if (info.tf_valid && info.tf_success && + info.tf_start == range->start && + info.tf_len == range->len && + info.tf_minlen == range->minlen) { + /* Avoid sending duplicated trim to a shared device */ + mlog(ML_NOTICE, "The same trim on device (%s) was " + "just done from node (%u), return.\n", + osb->dev_str, info.tf_nodenum); + range->len = info.tf_trimlen; + goto out; + } + } + + info.tf_nodenum = osb->node_num; + info.tf_start = range->start; + info.tf_len = range->len; + info.tf_minlen = range->minlen; + + ret = ocfs2_trim_mainbm(sb, range); + + info.tf_trimlen = range->len; + info.tf_success = (ret < 0 ? 0 : 1); + pinfo = &info; +out: + ocfs2_trim_fs_unlock(osb, pinfo); + ocfs2_trim_fs_lock_res_uninit(osb); return ret; } diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index 0e4166cc23a0..4ac775e32240 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -621,13 +621,15 @@ static void o2nm_node_group_drop_item(struct config_group *group, struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster = to_o2nm_cluster(group->cg_item.ci_parent); - o2net_disconnect_node(node); + if (cluster->cl_nodes[node->nd_num] == node) { + o2net_disconnect_node(node); - if (cluster->cl_has_local && - (cluster->cl_local_node == node->nd_num)) { - cluster->cl_has_local = 0; - cluster->cl_local_node = O2NM_INVALID_NODE_NUM; - o2net_stop_listening(node); + if (cluster->cl_has_local && + (cluster->cl_local_node == node->nd_num)) { + cluster->cl_has_local = 0; + cluster->cl_local_node = O2NM_INVALID_NODE_NUM; + o2net_stop_listening(node); + } } /* XXX call into net to stop this node from trading messages */ diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 7c835824247e..af405586c5b1 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -686,6 +686,9 @@ void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb) { struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres; + /* Only one trimfs thread are allowed to work at the same time. */ + mutex_lock(&osb->obs_trim_fs_mutex); + ocfs2_lock_res_init_once(lockres); ocfs2_build_lock_name(OCFS2_LOCK_TYPE_TRIM_FS, 0, 0, lockres->l_name); ocfs2_lock_res_init_common(osb, lockres, OCFS2_LOCK_TYPE_TRIM_FS, @@ -698,6 +701,8 @@ void ocfs2_trim_fs_lock_res_uninit(struct ocfs2_super *osb) ocfs2_simple_drop_lockres(osb, lockres); ocfs2_lock_res_free(lockres); + + mutex_unlock(&osb->obs_trim_fs_mutex); } static void ocfs2_orphan_scan_lock_res_init(struct ocfs2_lock_res *res, diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 4f86ac0027b5..1f029fbe8b8d 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -407,6 +407,7 @@ struct ocfs2_super struct ocfs2_lock_res osb_rename_lockres; struct ocfs2_lock_res osb_nfs_sync_lockres; struct ocfs2_lock_res osb_trim_fs_lockres; + struct mutex obs_trim_fs_mutex; struct ocfs2_dlm_debug *osb_dlm_debug; struct dentry *osb_debug_root; diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index 2ee76a90ba8f..dc4bce1649c1 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -712,6 +712,8 @@ TRACE_EVENT(ocfs2_trim_extent, DEFINE_OCFS2_ULL_UINT_UINT_UINT_EVENT(ocfs2_trim_group); +DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_mainbm); + DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_fs); /* End of trace events for fs/ocfs2/alloc.c. */ diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c index d7407994f308..ea0756d83250 100644 --- a/fs/ocfs2/slot_map.c +++ b/fs/ocfs2/slot_map.c @@ -55,7 +55,7 @@ struct ocfs2_slot_info { unsigned int si_blocks; struct buffer_head **si_bh; unsigned int si_num_slots; - struct ocfs2_slot *si_slots; + struct ocfs2_slot si_slots[]; }; @@ -420,9 +420,7 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb) struct inode *inode = NULL; struct ocfs2_slot_info *si; - si = kzalloc(sizeof(struct ocfs2_slot_info) + - (sizeof(struct ocfs2_slot) * osb->max_slots), - GFP_KERNEL); + si = kzalloc(struct_size(si, si_slots, osb->max_slots), GFP_KERNEL); if (!si) { status = -ENOMEM; mlog_errno(status); @@ -431,8 +429,6 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb) si->si_extended = ocfs2_uses_extended_slot_map(osb); si->si_num_slots = osb->max_slots; - si->si_slots = (struct ocfs2_slot *)((char *)si + - sizeof(struct ocfs2_slot_info)); inode = ocfs2_get_system_file_inode(osb, SLOT_MAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 3415e0b09398..96ae7cedd487 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1847,6 +1847,8 @@ static int ocfs2_mount_volume(struct super_block *sb) if (ocfs2_is_hard_readonly(osb)) goto leave; + mutex_init(&osb->obs_trim_fs_mutex); + status = ocfs2_dlm_init(osb); if (status < 0) { mlog_errno(status); diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index a5a2fe76568f..b094d3d79354 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -398,8 +398,6 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter loff_t pos = iocb->ki_pos; ssize_t rc = 0; - BUG_ON(iocb->private); - gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_read_iter\n"); orangefs_stats.reads++; @@ -416,8 +414,6 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite loff_t pos; ssize_t rc; - BUG_ON(iocb->private); - gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n"); inode_lock(file->f_mapping->host); diff --git a/fs/pipe.c b/fs/pipe.c index bdc5d3c0977d..51d5fd8840ab 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -140,8 +140,7 @@ static int anon_pipe_buf_steal(struct pipe_inode_info *pipe, struct page *page = buf->page; if (page_count(page) == 1) { - if (memcg_kmem_enabled()) - memcg_kmem_uncharge(page, 0); + memcg_kmem_uncharge(page, 0); __SetPageLocked(page); return 0; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 9d428d5a0ac8..2edbb657f859 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -343,28 +343,28 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode); #endif - seq_printf(m, "\nSpeculation_Store_Bypass:\t"); + seq_puts(m, "\nSpeculation_Store_Bypass:\t"); switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { case -EINVAL: - seq_printf(m, "unknown"); + seq_puts(m, "unknown"); break; case PR_SPEC_NOT_AFFECTED: - seq_printf(m, "not vulnerable"); + seq_puts(m, "not vulnerable"); break; case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE: - seq_printf(m, "thread force mitigated"); + seq_puts(m, "thread force mitigated"); break; case PR_SPEC_PRCTL | PR_SPEC_DISABLE: - seq_printf(m, "thread mitigated"); + seq_puts(m, "thread mitigated"); break; case PR_SPEC_PRCTL | PR_SPEC_ENABLE: - seq_printf(m, "thread vulnerable"); + seq_puts(m, "thread vulnerable"); break; case PR_SPEC_DISABLE: - seq_printf(m, "globally mitigated"); + seq_puts(m, "globally mitigated"); break; default: - seq_printf(m, "vulnerable"); + seq_puts(m, "vulnerable"); break; } seq_putc(m, '\n'); diff --git a/fs/proc/base.c b/fs/proc/base.c index f5ed9512d193..511b279ec69c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -456,7 +456,7 @@ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { if (unlikely(!sched_info_on())) - seq_printf(m, "0 0 0\n"); + seq_puts(m, "0 0 0\n"); else seq_printf(m, "%llu %llu %lu\n", (unsigned long long)task->se.sum_exec_runtime, @@ -3161,7 +3161,7 @@ static struct dentry *proc_pid_instantiate(struct dentry * dentry, return d_splice_alias(inode, dentry); } -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) +struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) { struct task_struct *task; unsigned tgid; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 95b14196f284..4fc5a9b68f76 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -162,7 +162,7 @@ extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struc extern void pid_update_inode(struct task_struct *, struct inode *); extern int pid_delete_dentry(const struct dentry *); extern int proc_pid_readdir(struct file *, struct dir_context *); -extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int); +struct dentry *proc_pid_lookup(struct dentry *, unsigned int); extern loff_t mem_lseek(struct file *, loff_t, int); /* Lookups */ diff --git a/fs/proc/page.c b/fs/proc/page.c index 40b05e0d4274..544d1ee15aee 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -152,8 +152,8 @@ u64 stable_page_flags(struct page *page) else if (page_count(page) == 0 && is_free_buddy_page(page)) u |= 1 << KPF_BUDDY; - if (PageBalloon(page)) - u |= 1 << KPF_BALLOON; + if (PageOffline(page)) + u |= 1 << KPF_OFFLINE; if (PageTable(page)) u |= 1 << KPF_PGTABLE; diff --git a/fs/proc/root.c b/fs/proc/root.c index f4b1a9d2eca6..621e6ec322ca 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -154,7 +154,7 @@ static int proc_root_getattr(const struct path *path, struct kstat *stat, static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { - if (!proc_pid_lookup(dir, dentry, flags)) + if (!proc_pid_lookup(dentry, flags)) return NULL; return proc_lookup(dir, dentry, flags); diff --git a/fs/proc/self.c b/fs/proc/self.c index 127265e5c55f..57c0a1047250 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -38,6 +38,7 @@ int proc_setup_self(struct super_block *s) struct inode *root_inode = d_inode(s->s_root); struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *self; + int ret = -ENOMEM; inode_lock(root_inode); self = d_alloc_name(s->s_root, "self"); @@ -51,20 +52,19 @@ int proc_setup_self(struct super_block *s) inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_self_inode_operations; d_add(self, inode); + ret = 0; } else { dput(self); - self = ERR_PTR(-ENOMEM); } - } else { - self = ERR_PTR(-ENOMEM); } inode_unlock(root_inode); - if (IS_ERR(self)) { + + if (ret) pr_err("proc_fill_super: can't allocate /proc/self\n"); - return PTR_ERR(self); - } - ns->proc_self = self; - return 0; + else + ns->proc_self = self; + + return ret; } void __init proc_self_init(void) diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 535eda7857cf..80c305f206bb 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -23,21 +23,21 @@ #ifdef arch_idle_time -static u64 get_idle_time(int cpu) +static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle; - idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + idle = kcs->cpustat[CPUTIME_IDLE]; if (cpu_online(cpu) && !nr_iowait_cpu(cpu)) idle += arch_idle_time(cpu); return idle; } -static u64 get_iowait_time(int cpu) +static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) { u64 iowait; - iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + iowait = kcs->cpustat[CPUTIME_IOWAIT]; if (cpu_online(cpu) && nr_iowait_cpu(cpu)) iowait += arch_idle_time(cpu); return iowait; @@ -45,7 +45,7 @@ static u64 get_iowait_time(int cpu) #else -static u64 get_idle_time(int cpu) +static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle, idle_usecs = -1ULL; @@ -54,14 +54,14 @@ static u64 get_idle_time(int cpu) if (idle_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.idle */ - idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + idle = kcs->cpustat[CPUTIME_IDLE]; else idle = idle_usecs * NSEC_PER_USEC; return idle; } -static u64 get_iowait_time(int cpu) +static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) { u64 iowait, iowait_usecs = -1ULL; @@ -70,7 +70,7 @@ static u64 get_iowait_time(int cpu) if (iowait_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.iowait */ - iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + iowait = kcs->cpustat[CPUTIME_IOWAIT]; else iowait = iowait_usecs * NSEC_PER_USEC; @@ -79,6 +79,31 @@ static u64 get_iowait_time(int cpu) #endif +static void show_irq_gap(struct seq_file *p, unsigned int gap) +{ + static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0"; + + while (gap > 0) { + unsigned int inc; + + inc = min_t(unsigned int, gap, ARRAY_SIZE(zeros) / 2); + seq_write(p, zeros, 2 * inc); + gap -= inc; + } +} + +static void show_all_irqs(struct seq_file *p) +{ + unsigned int i, next = 0; + + for_each_active_irq(i) { + show_irq_gap(p, i - next); + seq_put_decimal_ull(p, " ", kstat_irqs_usr(i)); + next = i + 1; + } + show_irq_gap(p, nr_irqs - next); +} + static int show_stat(struct seq_file *p, void *v) { int i, j; @@ -95,16 +120,18 @@ static int show_stat(struct seq_file *p, void *v) getboottime64(&boottime); for_each_possible_cpu(i) { - user += kcpustat_cpu(i).cpustat[CPUTIME_USER]; - nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE]; - system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; - idle += get_idle_time(i); - iowait += get_iowait_time(i); - irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; - softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; - steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; - guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; - guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; + struct kernel_cpustat *kcs = &kcpustat_cpu(i); + + user += kcs->cpustat[CPUTIME_USER]; + nice += kcs->cpustat[CPUTIME_NICE]; + system += kcs->cpustat[CPUTIME_SYSTEM]; + idle += get_idle_time(kcs, i); + iowait += get_iowait_time(kcs, i); + irq += kcs->cpustat[CPUTIME_IRQ]; + softirq += kcs->cpustat[CPUTIME_SOFTIRQ]; + steal += kcs->cpustat[CPUTIME_STEAL]; + guest += kcs->cpustat[CPUTIME_GUEST]; + guest_nice += kcs->cpustat[CPUTIME_GUEST_NICE]; sum += kstat_cpu_irqs_sum(i); sum += arch_irq_stat_cpu(i); @@ -130,17 +157,19 @@ static int show_stat(struct seq_file *p, void *v) seq_putc(p, '\n'); for_each_online_cpu(i) { + struct kernel_cpustat *kcs = &kcpustat_cpu(i); + /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ - user = kcpustat_cpu(i).cpustat[CPUTIME_USER]; - nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE]; - system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; - idle = get_idle_time(i); - iowait = get_iowait_time(i); - irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; - softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; - steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; - guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; - guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; + user = kcs->cpustat[CPUTIME_USER]; + nice = kcs->cpustat[CPUTIME_NICE]; + system = kcs->cpustat[CPUTIME_SYSTEM]; + idle = get_idle_time(kcs, i); + iowait = get_iowait_time(kcs, i); + irq = kcs->cpustat[CPUTIME_IRQ]; + softirq = kcs->cpustat[CPUTIME_SOFTIRQ]; + steal = kcs->cpustat[CPUTIME_STEAL]; + guest = kcs->cpustat[CPUTIME_GUEST]; + guest_nice = kcs->cpustat[CPUTIME_GUEST_NICE]; seq_printf(p, "cpu%d", i); seq_put_decimal_ull(p, " ", nsec_to_clock_t(user)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice)); @@ -156,9 +185,7 @@ static int show_stat(struct seq_file *p, void *v) } seq_put_decimal_ull(p, "intr ", (unsigned long long)sum); - /* sum again ? it could be updated? */ - for_each_irq_nr(j) - seq_put_decimal_ull(p, " ", kstat_irqs_usr(j)); + show_all_irqs(p); seq_printf(p, "\nctxt %llu\n" diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 85b0ef890b28..beccb0b1d57c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -948,10 +948,12 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, pte_t ptent = *pte; if (pte_present(ptent)) { - ptent = ptep_modify_prot_start(vma->vm_mm, addr, pte); - ptent = pte_wrprotect(ptent); + pte_t old_pte; + + old_pte = ptep_modify_prot_start(vma, addr, pte); + ptent = pte_wrprotect(old_pte); ptent = pte_clear_soft_dirty(ptent); - ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent); + ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent); } else if (is_swap_pte(ptent)) { ptent = pte_swp_clear_soft_dirty(ptent); set_pte_at(vma->vm_mm, addr, pte, ptent); diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 0b63d68dedb2..36bf0f2e102e 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -64,7 +64,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) else bytes += kobjsize(current->files); - if (current->sighand && atomic_read(¤t->sighand->count) > 1) + if (current->sighand && refcount_read(¤t->sighand->count) > 1) sbytes += kobjsize(current->sighand); else bytes += kobjsize(current->sighand); @@ -178,7 +178,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) seq_file_path(m, file, ""); } else if (mm && is_stack(vma)) { seq_pad(m, ' '); - seq_printf(m, "[stack]"); + seq_puts(m, "[stack]"); } seq_putc(m, '\n'); diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index b905010ca9eb..f61ae53533f5 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -38,6 +38,7 @@ int proc_setup_thread_self(struct super_block *s) struct inode *root_inode = d_inode(s->s_root); struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *thread_self; + int ret = -ENOMEM; inode_lock(root_inode); thread_self = d_alloc_name(s->s_root, "thread-self"); @@ -51,20 +52,19 @@ int proc_setup_thread_self(struct super_block *s) inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_thread_self_inode_operations; d_add(thread_self, inode); + ret = 0; } else { dput(thread_self); - thread_self = ERR_PTR(-ENOMEM); } - } else { - thread_self = ERR_PTR(-ENOMEM); } inode_unlock(root_inode); - if (IS_ERR(thread_self)) { + + if (ret) pr_err("proc_fill_super: can't allocate /proc/thread_self\n"); - return PTR_ERR(thread_self); - } - ns->proc_thread_self = thread_self; - return 0; + else + ns->proc_thread_self = thread_self; + + return ret; } void __init proc_thread_self_init(void) diff --git a/fs/read_write.c b/fs/read_write.c index ff3c5e6f87cf..30df848b7451 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -426,7 +426,7 @@ ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) ssize_t result; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ result = vfs_read(file, (void __user *)buf, count, pos); set_fs(old_fs); @@ -499,7 +499,7 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t return -EINVAL; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); p = (__force const char __user *)buf; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; @@ -521,7 +521,7 @@ ssize_t kernel_write(struct file *file, const void *buf, size_t count, ssize_t res; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ res = vfs_write(file, (__force const char __user *)buf, count, pos); set_fs(old_fs); diff --git a/fs/select.c b/fs/select.c index d0f35dbc0e8f..6cbc9ff56ba0 100644 --- a/fs/select.c +++ b/fs/select.c @@ -1379,7 +1379,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, +COMPAT_SYSCALL_DEFINE6(pselect6_time32, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { @@ -1402,7 +1402,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, #endif #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, +COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { diff --git a/fs/splice.c b/fs/splice.c index de2ede048473..6489fb9436e4 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -357,7 +357,7 @@ static ssize_t kernel_readv(struct file *file, const struct kvec *vec, ssize_t res; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0); set_fs(old_fs); @@ -1123,6 +1123,9 @@ static long do_splice(struct file *in, loff_t __user *off_in, if (ipipe == opipe) return -EINVAL; + if ((in->f_flags | out->f_flags) & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + return splice_pipe_to_pipe(ipipe, opipe, len, flags); } @@ -1148,6 +1151,9 @@ static long do_splice(struct file *in, loff_t __user *off_in, if (unlikely(ret < 0)) return ret; + if (in->f_flags & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + file_start_write(out); ret = do_splice_from(ipipe, out, &offset, len, flags); file_end_write(out); @@ -1172,6 +1178,9 @@ static long do_splice(struct file *in, loff_t __user *off_in, offset = in->f_pos; } + if (out->f_flags & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + pipe_lock(opipe); ret = wait_for_space(opipe, flags); if (!ret) @@ -1717,6 +1726,9 @@ static long do_tee(struct file *in, struct file *out, size_t len, * copying the data. */ if (ipipe && opipe && ipipe != opipe) { + if ((in->f_flags | out->f_flags) & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + /* * Keep going, unless we encounter an error. The ipipe/opipe * ordering doesn't really matter. diff --git a/fs/statfs.c b/fs/statfs.c index f0216629621d..eea7af6f2f22 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -67,6 +67,20 @@ static int statfs_by_dentry(struct dentry *dentry, struct kstatfs *buf) return retval; } +int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid) +{ + struct kstatfs st; + int error; + + error = statfs_by_dentry(dentry, &st); + if (error) + return error; + + *fsid = st.f_fsid; + return 0; +} +EXPORT_SYMBOL(vfs_get_fsid); + int vfs_statfs(const struct path *path, struct kstatfs *buf) { int error; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 51398457fe00..130fc6fbcc03 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -17,7 +17,6 @@ #include <linux/seq_file.h> #include "sysfs.h" -#include "../kernfs/kernfs-internal.h" /* * Determine ktype->sysfs_ops for the given kernfs_node. This function @@ -497,6 +496,7 @@ bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr) void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *ptr) { int i; + for (i = 0; ptr[i]; i++) sysfs_remove_file(kobj, ptr[i]); } diff --git a/fs/timerfd.c b/fs/timerfd.c index 803ca070d42e..6a6fc8aa1de7 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -560,7 +560,7 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, +SYSCALL_DEFINE4(timerfd_settime32, int, ufd, int, flags, const struct old_itimerspec32 __user *, utmr, struct old_itimerspec32 __user *, otmr) { @@ -577,7 +577,7 @@ COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, return ret; } -COMPAT_SYSCALL_DEFINE2(timerfd_gettime, int, ufd, +SYSCALL_DEFINE2(timerfd_gettime32, int, ufd, struct old_itimerspec32 __user *, otmr) { struct itimerspec64 kotmr; diff --git a/fs/udf/super.c b/fs/udf/super.c index e3d684ea3203..ffd8038ff728 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1474,6 +1474,17 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, if (lvd->integritySeqExt.extLength) udf_load_logicalvolint(sb, leea_to_cpu(lvd->integritySeqExt)); ret = 0; + + if (!sbi->s_lvid_bh) { + /* We can't generate unique IDs without a valid LVID */ + if (sb_rdonly(sb)) { + UDF_SET_FLAG(sb, UDF_FLAG_RW_INCOMPAT); + } else { + udf_warn(sb, "Damaged or missing LVID, forcing " + "readonly mount\n"); + ret = -EACCES; + } + } out_bh: brelse(bh); return ret; @@ -1943,13 +1954,24 @@ static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt, return 0; } +static void udf_finalize_lvid(struct logicalVolIntegrityDesc *lvid) +{ + struct timespec64 ts; + + ktime_get_real_ts64(&ts); + udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts); + lvid->descTag.descCRC = cpu_to_le16( + crc_itu_t(0, (char *)lvid + sizeof(struct tag), + le16_to_cpu(lvid->descTag.descCRCLength))); + lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag); +} + static void udf_open_lvid(struct super_block *sb) { struct udf_sb_info *sbi = UDF_SB(sb); struct buffer_head *bh = sbi->s_lvid_bh; struct logicalVolIntegrityDesc *lvid; struct logicalVolIntegrityDescImpUse *lvidiu; - struct timespec64 ts; if (!bh) return; @@ -1961,18 +1983,12 @@ static void udf_open_lvid(struct super_block *sb) mutex_lock(&sbi->s_alloc_mutex); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; - ktime_get_real_ts64(&ts); - udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts); if (le32_to_cpu(lvid->integrityType) == LVID_INTEGRITY_TYPE_CLOSE) lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_OPEN); else UDF_SET_FLAG(sb, UDF_FLAG_INCONSISTENT); - lvid->descTag.descCRC = cpu_to_le16( - crc_itu_t(0, (char *)lvid + sizeof(struct tag), - le16_to_cpu(lvid->descTag.descCRCLength))); - - lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag); + udf_finalize_lvid(lvid); mark_buffer_dirty(bh); sbi->s_lvid_dirty = 0; mutex_unlock(&sbi->s_alloc_mutex); @@ -1986,7 +2002,6 @@ static void udf_close_lvid(struct super_block *sb) struct buffer_head *bh = sbi->s_lvid_bh; struct logicalVolIntegrityDesc *lvid; struct logicalVolIntegrityDescImpUse *lvidiu; - struct timespec64 ts; if (!bh) return; @@ -1998,8 +2013,6 @@ static void udf_close_lvid(struct super_block *sb) mutex_lock(&sbi->s_alloc_mutex); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; - ktime_get_real_ts64(&ts); - udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts); if (UDF_MAX_WRITE_VERSION > le16_to_cpu(lvidiu->maxUDFWriteRev)) lvidiu->maxUDFWriteRev = cpu_to_le16(UDF_MAX_WRITE_VERSION); if (sbi->s_udfrev > le16_to_cpu(lvidiu->minUDFReadRev)) @@ -2009,17 +2022,13 @@ static void udf_close_lvid(struct super_block *sb) if (!UDF_QUERY_FLAG(sb, UDF_FLAG_INCONSISTENT)) lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_CLOSE); - lvid->descTag.descCRC = cpu_to_le16( - crc_itu_t(0, (char *)lvid + sizeof(struct tag), - le16_to_cpu(lvid->descTag.descCRCLength))); - - lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag); /* * We set buffer uptodate unconditionally here to avoid spurious * warnings from mark_buffer_dirty() when previous EIO has marked * the buffer as !uptodate */ set_buffer_uptodate(bh); + udf_finalize_lvid(lvid); mark_buffer_dirty(bh); sbi->s_lvid_dirty = 0; mutex_unlock(&sbi->s_alloc_mutex); @@ -2048,8 +2057,8 @@ u64 lvid_get_unique_id(struct super_block *sb) if (!(++uniqueID & 0xFFFFFFFF)) uniqueID += 16; lvhd->uniqueID = cpu_to_le64(uniqueID); + udf_updated_lvid(sb); mutex_unlock(&sbi->s_alloc_mutex); - mark_buffer_dirty(bh); return ret; } @@ -2320,11 +2329,17 @@ static int udf_sync_fs(struct super_block *sb, int wait) mutex_lock(&sbi->s_alloc_mutex); if (sbi->s_lvid_dirty) { + struct buffer_head *bh = sbi->s_lvid_bh; + struct logicalVolIntegrityDesc *lvid; + + lvid = (struct logicalVolIntegrityDesc *)bh->b_data; + udf_finalize_lvid(lvid); + /* * Blockdevice will be synced later so we don't have to submit * the buffer for IO */ - mark_buffer_dirty(sbi->s_lvid_bh); + mark_buffer_dirty(bh); sbi->s_lvid_dirty = 0; } mutex_unlock(&sbi->s_alloc_mutex); diff --git a/fs/utimes.c b/fs/utimes.c index bdcf2daf39c1..350c9c16ace1 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -224,8 +224,8 @@ SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times) * of sys_utimes. */ #ifdef __ARCH_WANT_SYS_UTIME32 -COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, - struct old_utimbuf32 __user *, t) +SYSCALL_DEFINE2(utime32, const char __user *, filename, + struct old_utimbuf32 __user *, t) { struct timespec64 tv[2]; @@ -240,7 +240,7 @@ COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, } #endif -COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) +SYSCALL_DEFINE4(utimensat_time32, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) { struct timespec64 tv[2]; @@ -276,14 +276,14 @@ static long do_compat_futimesat(unsigned int dfd, const char __user *filename, return do_utimes(dfd, filename, t ? tv : NULL, 0); } -COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, +SYSCALL_DEFINE3(futimesat_time32, unsigned int, dfd, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(dfd, filename, t); } -COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct old_timeval32 __user *, t) +SYSCALL_DEFINE2(utimes_time32, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(AT_FDCWD, filename, t); } |