diff --git a/Documentation/filesystems/files.rst b/Documentation/filesystems/files.rst index 9e38e4c221ca..eb770f891b27 100644 --- a/Documentation/filesystems/files.rst +++ b/Documentation/filesystems/files.rst @@ -116,7 +116,7 @@ before and after the reference count increment. This pattern can be seen in get_file_rcu() and __files_get_rcu(). In addition, it isn't possible to access or check fields in struct file -without first aqcuiring a reference on it under rcu lookup. Not doing +without first acquiring a reference on it under rcu lookup. Not doing that was always very dodgy and it was only usable for non-pointer data in struct file. With SLAB_TYPESAFE_BY_RCU it is necessary that callers either first acquire a reference or they must hold the files_lock of the diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index d5bf4b6b7509..e664061ed55d 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -29,7 +29,7 @@ prototypes:: char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen); struct vfsmount *(*d_automount)(struct path *path); int (*d_manage)(const struct path *, bool); - struct dentry *(*d_real)(struct dentry *, const struct inode *); + struct dentry *(*d_real)(struct dentry *, enum d_real_type type); locking rules: diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index eebcc0f9e2bc..6e903a903f8f 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -1264,7 +1264,7 @@ defined: char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); - struct dentry *(*d_real)(struct dentry *, const struct inode *); + struct dentry *(*d_real)(struct dentry *, enum d_real_type type); }; ``d_revalidate`` @@ -1419,16 +1419,14 @@ defined: the dentry being transited from. ``d_real`` - overlay/union type filesystems implement this method to return - one of the underlying dentries hidden by the overlay. It is - used in two different modes: + overlay/union type filesystems implement this method to return one + of the underlying dentries of a regular file hidden by the overlay. - Called from file_dentry() it returns the real dentry matching - the inode argument. The real dentry may be from a lower layer - already copied up, but still referenced from the file. This - mode is selected with a non-NULL inode argument. + The 'type' argument takes the values D_REAL_DATA or D_REAL_METADATA + for returning the real underlying dentry that refers to the inode + hosting the file's data or metadata respectively. - With NULL inode the topmost real underlying dentry is returned. + For non-regular files, the 'dentry' argument is returned. Each dentry has a pointer to its parent dentry, as well as a hash list of child dentries. Child dentries are basically like files in a diff --git a/fs/attr.c b/fs/attr.c index 5a13f0c8495f..49d23b5dbab4 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -352,7 +352,7 @@ int may_setattr(struct mnt_idmap *idmap, struct inode *inode, EXPORT_SYMBOL(may_setattr); /** - * notify_change - modify attributes of a filesytem object + * notify_change - modify attributes of a filesystem object * @idmap: idmap of the mount the inode was found from * @dentry: object affected * @attr: new attributes diff --git a/fs/backing-file.c b/fs/backing-file.c index a681f38d84d8..740185198db3 100644 --- a/fs/backing-file.c +++ b/fs/backing-file.c @@ -325,9 +325,7 @@ EXPORT_SYMBOL_GPL(backing_file_mmap); static int __init backing_aio_init(void) { - backing_aio_cachep = kmem_cache_create("backing_aio", - sizeof(struct backing_aio), - 0, SLAB_HWCACHE_ALIGN, NULL); + backing_aio_cachep = KMEM_CACHE(backing_aio, SLAB_HWCACHE_ALIGN); if (!backing_aio_cachep) return -ENOMEM; diff --git a/fs/buffer.c b/fs/buffer.c index d3bcf601d3e5..9a54077de87d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -464,7 +464,7 @@ EXPORT_SYMBOL(mark_buffer_async_write); * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * - * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(), + * The functions mark_buffer_dirty_inode(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the * management of a list of dependent buffers at ->i_mapping->i_private_list. * @@ -3121,12 +3121,8 @@ void __init buffer_init(void) unsigned long nrpages; int ret; - bh_cachep = kmem_cache_create("buffer_head", - sizeof(struct buffer_head), 0, - (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| - SLAB_MEM_SPREAD), - NULL); - + bh_cachep = KMEM_CACHE(buffer_head, + SLAB_RECLAIM_ACCOUNT|SLAB_PANIC); /* * Limit the bh occupancy to 10% of ZONE_NORMAL */ diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 0c7c2528791e..a50356c541f6 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -24,6 +24,8 @@ #include #include #include +#include +#include #include #include @@ -87,10 +89,10 @@ void coda_destroy_inodecache(void) kmem_cache_destroy(coda_inode_cachep); } -static int coda_remount(struct super_block *sb, int *flags, char *data) +static int coda_reconfigure(struct fs_context *fc) { - sync_filesystem(sb); - *flags |= SB_NOATIME; + sync_filesystem(fc->root->d_sb); + fc->sb_flags |= SB_NOATIME; return 0; } @@ -102,78 +104,102 @@ static const struct super_operations coda_super_operations = .evict_inode = coda_evict_inode, .put_super = coda_put_super, .statfs = coda_statfs, - .remount_fs = coda_remount, }; -static int get_device_index(struct coda_mount_data *data) +struct coda_fs_context { + int idx; +}; + +enum { + Opt_fd, +}; + +static const struct fs_parameter_spec coda_param_specs[] = { + fsparam_fd ("fd", Opt_fd), + {} +}; + +static int coda_parse_fd(struct fs_context *fc, int fd) { + struct coda_fs_context *ctx = fc->fs_private; struct fd f; struct inode *inode; int idx; - if (data == NULL) { - pr_warn("%s: Bad mount data\n", __func__); - return -1; - } - - if (data->version != CODA_MOUNT_VERSION) { - pr_warn("%s: Bad mount version\n", __func__); - return -1; - } - - f = fdget(data->fd); + f = fdget(fd); if (!f.file) - goto Ebadf; + return -EBADF; inode = file_inode(f.file); if (!S_ISCHR(inode->i_mode) || imajor(inode) != CODA_PSDEV_MAJOR) { fdput(f); - goto Ebadf; + return invalf(fc, "code: Not coda psdev"); } idx = iminor(inode); fdput(f); - if (idx < 0 || idx >= MAX_CODADEVS) { - pr_warn("%s: Bad minor number\n", __func__); - return -1; - } - - return idx; -Ebadf: - pr_warn("%s: Bad file\n", __func__); - return -1; + if (idx < 0 || idx >= MAX_CODADEVS) + return invalf(fc, "coda: Bad minor number"); + ctx->idx = idx; + return 0; } -static int coda_fill_super(struct super_block *sb, void *data, int silent) +static int coda_parse_param(struct fs_context *fc, struct fs_parameter *param) { + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, coda_param_specs, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_fd: + return coda_parse_fd(fc, result.uint_32); + } + + return 0; +} + +/* + * Parse coda's binary mount data form. We ignore any errors and go with index + * 0 if we get one for backward compatibility. + */ +static int coda_parse_monolithic(struct fs_context *fc, void *_data) +{ + struct coda_mount_data *data = _data; + + if (!data) + return invalf(fc, "coda: Bad mount data"); + + if (data->version != CODA_MOUNT_VERSION) + return invalf(fc, "coda: Bad mount version"); + + coda_parse_fd(fc, data->fd); + return 0; +} + +static int coda_fill_super(struct super_block *sb, struct fs_context *fc) +{ + struct coda_fs_context *ctx = fc->fs_private; struct inode *root = NULL; struct venus_comm *vc; struct CodaFid fid; int error; - int idx; - if (task_active_pid_ns(current) != &init_pid_ns) - return -EINVAL; + infof(fc, "coda: device index: %i\n", ctx->idx); - idx = get_device_index((struct coda_mount_data *) data); - - /* Ignore errors in data, for backward compatibility */ - if(idx == -1) - idx = 0; - - pr_info("%s: device index: %i\n", __func__, idx); - - vc = &coda_comms[idx]; + vc = &coda_comms[ctx->idx]; mutex_lock(&vc->vc_mutex); if (!vc->vc_inuse) { - pr_warn("%s: No pseudo device\n", __func__); + errorf(fc, "coda: No pseudo device"); error = -EINVAL; goto unlock_out; } if (vc->vc_sb) { - pr_warn("%s: Device already mounted\n", __func__); + errorf(fc, "coda: Device already mounted"); error = -EBUSY; goto unlock_out; } @@ -313,18 +339,45 @@ static int coda_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } -/* init_coda: used by filesystems.c to register coda */ - -static struct dentry *coda_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int coda_get_tree(struct fs_context *fc) { - return mount_nodev(fs_type, flags, data, coda_fill_super); + if (task_active_pid_ns(current) != &init_pid_ns) + return -EINVAL; + + return get_tree_nodev(fc, coda_fill_super); +} + +static void coda_free_fc(struct fs_context *fc) +{ + kfree(fc->fs_private); +} + +static const struct fs_context_operations coda_context_ops = { + .free = coda_free_fc, + .parse_param = coda_parse_param, + .parse_monolithic = coda_parse_monolithic, + .get_tree = coda_get_tree, + .reconfigure = coda_reconfigure, +}; + +static int coda_init_fs_context(struct fs_context *fc) +{ + struct coda_fs_context *ctx; + + ctx = kzalloc(sizeof(struct coda_fs_context), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + fc->fs_private = ctx; + fc->ops = &coda_context_ops; + return 0; } struct file_system_type coda_fs_type = { .owner = THIS_MODULE, .name = "coda", - .mount = coda_mount, + .init_fs_context = coda_init_fs_context, + .parameters = coda_param_specs, .kill_sb = kill_anon_super, .fs_flags = FS_BINARY_MOUNTDATA, }; diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 7b3fc189593a..0ad52fbe51c9 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -74,13 +74,7 @@ struct fscrypt_nokey_name { static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) { - if (str->len == 1 && str->name[0] == '.') - return true; - - if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') - return true; - - return false; + return is_dot_dotdot(str->name, str->len); } /** diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index 52504dd478d3..104771c3d3f6 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -102,11 +102,8 @@ int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, if (err && err != -ENOENT) return err; - if (fname->is_nokey_name) { - spin_lock(&dentry->d_lock); - dentry->d_flags |= DCACHE_NOKEY_NAME; - spin_unlock(&dentry->d_lock); - } + fscrypt_prepare_dentry(dentry, fname->is_nokey_name); + return err; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup); @@ -131,12 +128,10 @@ EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup); int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry) { int err = fscrypt_get_encryption_info(dir, true); + bool is_nokey_name = (!err && !fscrypt_has_encryption_key(dir)); + + fscrypt_prepare_dentry(dentry, is_nokey_name); - if (!err && !fscrypt_has_encryption_key(dir)) { - spin_lock(&dentry->d_lock); - dentry->d_flags |= DCACHE_NOKEY_NAME; - spin_unlock(&dentry->d_lock); - } return err; } EXPORT_SYMBOL_GPL(fscrypt_prepare_lookup_partial); diff --git a/fs/dcache.c b/fs/dcache.c index 6ebccba33336..71a8e943a0fa 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -3139,7 +3139,7 @@ static void __init dcache_init(void) * of the dcache. */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, - SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT, + SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, d_iname); /* Hash may have been set up in dcache_init_early */ diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 03bd55069d86..2fe0f3af1a08 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1949,16 +1949,6 @@ out: return rc; } -static bool is_dot_dotdot(const char *name, size_t name_size) -{ - if (name_size == 1 && name[0] == '.') - return true; - else if (name_size == 2 && name[0] == '.' && name[1] == '.') - return true; - - return false; -} - /** * ecryptfs_decode_and_decrypt_filename - converts the encoded cipher text name to decoded plaintext * @plaintext_name: The plaintext name diff --git a/fs/efs/super.c b/fs/efs/super.c index f17fdac76b2e..e4421c10caeb 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -14,19 +14,14 @@ #include #include #include - +#include +#include #include "efs.h" #include #include static int efs_statfs(struct dentry *dentry, struct kstatfs *buf); -static int efs_fill_super(struct super_block *s, void *d, int silent); - -static struct dentry *efs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) -{ - return mount_bdev(fs_type, flags, dev_name, data, efs_fill_super); -} +static int efs_init_fs_context(struct fs_context *fc); static void efs_kill_sb(struct super_block *s) { @@ -35,15 +30,6 @@ static void efs_kill_sb(struct super_block *s) kfree(sbi); } -static struct file_system_type efs_fs_type = { - .owner = THIS_MODULE, - .name = "efs", - .mount = efs_mount, - .kill_sb = efs_kill_sb, - .fs_flags = FS_REQUIRES_DEV, -}; -MODULE_ALIAS_FS("efs"); - static struct pt_types sgi_pt_types[] = { {0x00, "SGI vh"}, {0x01, "SGI trkrepl"}, @@ -63,6 +49,27 @@ static struct pt_types sgi_pt_types[] = { {0, NULL} }; +enum { + Opt_explicit_open, +}; + +static const struct fs_parameter_spec efs_param_spec[] = { + fsparam_flag ("explicit-open", Opt_explicit_open), + {} +}; + +/* + * File system definition and registration. + */ +static struct file_system_type efs_fs_type = { + .owner = THIS_MODULE, + .name = "efs", + .kill_sb = efs_kill_sb, + .fs_flags = FS_REQUIRES_DEV, + .init_fs_context = efs_init_fs_context, + .parameters = efs_param_spec, +}; +MODULE_ALIAS_FS("efs"); static struct kmem_cache * efs_inode_cachep; @@ -91,8 +98,8 @@ static int __init init_inodecache(void) { efs_inode_cachep = kmem_cache_create("efs_inode_cache", sizeof(struct efs_inode_info), 0, - SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| - SLAB_ACCOUNT, init_once); + SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, + init_once); if (efs_inode_cachep == NULL) return -ENOMEM; return 0; @@ -108,18 +115,10 @@ static void destroy_inodecache(void) kmem_cache_destroy(efs_inode_cachep); } -static int efs_remount(struct super_block *sb, int *flags, char *data) -{ - sync_filesystem(sb); - *flags |= SB_RDONLY; - return 0; -} - static const struct super_operations efs_superblock_operations = { .alloc_inode = efs_alloc_inode, .free_inode = efs_free_inode, .statfs = efs_statfs, - .remount_fs = efs_remount, }; static const struct export_operations efs_export_ops = { @@ -249,26 +248,26 @@ static int efs_validate_super(struct efs_sb_info *sb, struct efs_super *super) { return 0; } -static int efs_fill_super(struct super_block *s, void *d, int silent) +static int efs_fill_super(struct super_block *s, struct fs_context *fc) { struct efs_sb_info *sb; struct buffer_head *bh; struct inode *root; - sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL); + sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL); if (!sb) return -ENOMEM; s->s_fs_info = sb; s->s_time_min = 0; s->s_time_max = U32_MAX; - + s->s_magic = EFS_SUPER_MAGIC; if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) { pr_err("device does not support %d byte blocks\n", EFS_BLOCKSIZE); return -EINVAL; } - + /* read the vh (volume header) block */ bh = sb_bread(s, 0); @@ -294,7 +293,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) pr_err("cannot read superblock\n"); return -EIO; } - + if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) { #ifdef DEBUG pr_warn("invalid superblock at block %u\n", @@ -328,6 +327,61 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) return 0; } +static void efs_free_fc(struct fs_context *fc) +{ + kfree(fc->fs_private); +} + +static int efs_get_tree(struct fs_context *fc) +{ + return get_tree_bdev(fc, efs_fill_super); +} + +static int efs_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + int token; + struct fs_parse_result result; + + token = fs_parse(fc, efs_param_spec, param, &result); + if (token < 0) + return token; + return 0; +} + +static int efs_reconfigure(struct fs_context *fc) +{ + sync_filesystem(fc->root->d_sb); + + return 0; +} + +struct efs_context { + unsigned long s_mount_opts; +}; + +static const struct fs_context_operations efs_context_opts = { + .parse_param = efs_parse_param, + .get_tree = efs_get_tree, + .reconfigure = efs_reconfigure, + .free = efs_free_fc, +}; + +/* + * Set up the filesystem mount context. + */ +static int efs_init_fs_context(struct fs_context *fc) +{ + struct efs_context *ctx; + + ctx = kzalloc(sizeof(struct efs_context), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + fc->fs_private = ctx; + fc->ops = &efs_context_opts; + + return 0; +} + static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct efs_sb_info *sbi = SUPER_INFO(sb); diff --git a/fs/eventfd.c b/fs/eventfd.c index ad8186d47ba7..9afdb722fa92 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -251,7 +251,7 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c ssize_t res; __u64 ucnt; - if (count < sizeof(ucnt)) + if (count != sizeof(ucnt)) return -EINVAL; if (copy_from_user(&ucnt, buf, sizeof(ucnt))) return -EFAULT; @@ -283,13 +283,18 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c static void eventfd_show_fdinfo(struct seq_file *m, struct file *f) { struct eventfd_ctx *ctx = f->private_data; + __u64 cnt; spin_lock_irq(&ctx->wqh.lock); - seq_printf(m, "eventfd-count: %16llx\n", - (unsigned long long)ctx->count); + cnt = ctx->count; spin_unlock_irq(&ctx->wqh.lock); - seq_printf(m, "eventfd-id: %d\n", ctx->id); - seq_printf(m, "eventfd-semaphore: %d\n", + + seq_printf(m, + "eventfd-count: %16llx\n" + "eventfd-id: %d\n" + "eventfd-semaphore: %d\n", + cnt, + ctx->id, !!(ctx->flags & EFD_SEMAPHORE)); } #endif @@ -383,6 +388,7 @@ static int do_eventfd(unsigned int count, int flags) /* Check the EFD_* constants for consistency. */ BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK); + BUILD_BUG_ON(EFD_SEMAPHORE != (1 << 0)); if (flags & ~EFD_FLAGS_SET) return -EINVAL; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 3534d36a1474..39ac6fdf8bca 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -206,7 +206,7 @@ struct eventpoll { */ struct epitem *ovflist; - /* wakeup_source used when ep_scan_ready_list is running */ + /* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */ struct wakeup_source *ws; /* The user that created the eventpoll descriptor */ @@ -678,12 +678,6 @@ static void ep_done_scan(struct eventpoll *ep, write_unlock_irq(&ep->lock); } -static void epi_rcu_free(struct rcu_head *head) -{ - struct epitem *epi = container_of(head, struct epitem, rcu); - kmem_cache_free(epi_cache, epi); -} - static void ep_get(struct eventpoll *ep) { refcount_inc(&ep->refcount); @@ -767,7 +761,7 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make * use of the rbn field. */ - call_rcu(&epi->rcu, epi_rcu_free); + kfree_rcu(epi, rcu); percpu_counter_dec(&ep->user->epoll_watches); return ep_refcount_dec_and_test(ep); @@ -1153,7 +1147,7 @@ static inline bool chain_epi_lockless(struct epitem *epi) * This callback takes a read lock in order not to contend with concurrent * events from another file descriptor, thus all modifications to ->rdllist * or ->ovflist are lockless. Read lock is paired with the write lock from - * ep_scan_ready_list(), which stops all list modifications and guarantees + * ep_start/done_scan(), which stops all list modifications and guarantees * that lists state is seen correctly. * * Another thing worth to mention is that ep_poll_callback() can be called @@ -1751,7 +1745,7 @@ static int ep_send_events(struct eventpoll *ep, * availability. At this point, no one can insert * into ep->rdllist besides us. The epoll_ctl() * callers are locked out by - * ep_scan_ready_list() holding "mtx" and the + * ep_send_events() holding "mtx" and the * poll callback will queue them in ep->ovflist. */ list_add_tail(&epi->rdllink, &ep->rdllist); @@ -1904,7 +1898,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, __set_current_state(TASK_INTERRUPTIBLE); /* - * Do the final check under the lock. ep_scan_ready_list() + * Do the final check under the lock. ep_start/done_scan() * plays with two lists (->rdllist and ->ovflist) and there * is always a race when both lists are empty for short * period of time although events are pending, so lock is diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 3ae0154c5680..07ea3d62b298 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -255,7 +255,7 @@ static bool filldir_one(struct dir_context *ctx, const char *name, int len, container_of(ctx, struct getdents_callback, ctx); buf->sequence++; - if (buf->ino == ino && len <= NAME_MAX) { + if (buf->ino == ino && len <= NAME_MAX && !is_dot_dotdot(name, len)) { memcpy(buf->name, name, len); buf->name[len] = '\0'; buf->found = 1; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 05b647e6bc19..5e4f65c14dfb 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1762,7 +1762,6 @@ static struct buffer_head *ext4_lookup_entry(struct inode *dir, struct buffer_head *bh; err = ext4_fname_prepare_lookup(dir, dentry, &fname); - generic_set_encrypted_ci_d_ops(dentry); if (err == -ENOENT) return NULL; if (err) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0f931d0c227d..d068d550d271 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5484,6 +5484,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) goto failed_mount4; } + generic_set_sb_d_ops(sb); sb->s_root = d_make_root(root); if (!sb->s_root) { ext4_msg(sb, KERN_ERR, "get root dentry failed"); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 65294e3b0bef..dda0aed95464 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3364,17 +3364,6 @@ static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi) return is_set_ckpt_flags(sbi, CP_ERROR_FLAG); } -static inline bool is_dot_dotdot(const u8 *name, size_t len) -{ - if (len == 1 && name[0] == '.') - return true; - - if (len == 2 && name[0] == '.' && name[1] == '.') - return true; - - return false; -} - static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi, size_t size, gfp_t flags) { diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index b3bb815fc6aa..f7f63a567d86 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -531,7 +531,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, } err = f2fs_prepare_lookup(dir, dentry, &fname); - generic_set_encrypted_ci_d_ops(dentry); if (err == -ENOENT) goto out_splice; if (err) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index d45ab0992ae5..8d9bd880ffd8 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -4660,6 +4660,7 @@ try_onemore: goto free_node_inode; } + generic_set_sb_d_ops(sb); sb->s_root = d_make_root(root); /* allocate root dentry */ if (!sb->s_root) { err = -ENOMEM; diff --git a/fs/fcntl.c b/fs/fcntl.c index c80a6acad742..c3e342eb74af 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -846,12 +846,6 @@ int send_sigurg(struct fown_struct *fown) static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __ro_after_init; -static void fasync_free_rcu(struct rcu_head *head) -{ - kmem_cache_free(fasync_cache, - container_of(head, struct fasync_struct, fa_rcu)); -} - /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, @@ -877,7 +871,7 @@ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; - call_rcu(&fa->fa_rcu, fasync_free_rcu); + kfree_rcu(fa, fa_rcu); filp->f_flags &= ~FASYNC; result = 1; break; diff --git a/fs/fhandle.c b/fs/fhandle.c index 18b3ba8dc8ea..57a12614addf 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -36,7 +36,7 @@ static long do_sys_name_to_handle(const struct path *path, if (f_handle.handle_bytes > MAX_HANDLE_SZ) return -EINVAL; - handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes, GFP_KERNEL); if (!handle) return -ENOMEM; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 3d84fcc471c6..e4f17c53ddfc 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -141,6 +141,31 @@ static void wb_wakeup(struct bdi_writeback *wb) spin_unlock_irq(&wb->work_lock); } +/* + * This function is used when the first inode for this wb is marked dirty. It + * wakes-up the corresponding bdi thread which should then take care of the + * periodic background write-out of dirty inodes. Since the write-out would + * starts only 'dirty_writeback_interval' centisecs from now anyway, we just + * set up a timer which wakes the bdi thread up later. + * + * Note, we wouldn't bother setting up the timer, but this function is on the + * fast-path (used by '__mark_inode_dirty()'), so we save few context switches + * by delaying the wake-up. + * + * We have to be careful not to postpone flush work if it is scheduled for + * earlier. Thus we use queue_delayed_work(). + */ +static void wb_wakeup_delayed(struct bdi_writeback *wb) +{ + unsigned long timeout; + + timeout = msecs_to_jiffies(dirty_writeback_interval * 10); + spin_lock_irq(&wb->work_lock); + if (test_bit(WB_registered, &wb->state)) + queue_delayed_work(bdi_wq, &wb->dwork, timeout); + spin_unlock_irq(&wb->work_lock); +} + static void finish_writeback_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { diff --git a/fs/fs_parser.c b/fs/fs_parser.c index edb3712dcfa5..a4d6ca0b8971 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -83,8 +83,8 @@ static const struct fs_parameter_spec *fs_lookup_key( } /* - * fs_parse - Parse a filesystem configuration parameter - * @fc: The filesystem context to log errors through. + * __fs_parse - Parse a filesystem configuration parameter + * @log: The filesystem context to log errors through. * @desc: The parameter description to use. * @param: The parameter. * @result: Where to place the result of the parse diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index b0cb70400996..ce9346099c72 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -30,7 +30,7 @@ struct hfsplus_wd { * @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes * @buf: buffer for I/O * @data: output pointer for location of requested data - * @opf: request op flags + * @opf: I/O operation type and flags * * The unit of I/O is hfsplus_min_io_size(sb), which may be bigger than * HFSPLUS_SECTOR_SIZE, and @buf must be sized accordingly. On reads diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d746866ae3b6..6502c7e776d1 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -933,7 +933,7 @@ static int hugetlbfs_setattr(struct mnt_idmap *idmap, unsigned int ia_valid = attr->ia_valid; struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); - error = setattr_prepare(&nop_mnt_idmap, dentry, attr); + error = setattr_prepare(idmap, dentry, attr); if (error) return error; @@ -950,7 +950,7 @@ static int hugetlbfs_setattr(struct mnt_idmap *idmap, hugetlb_vmtruncate(inode, newsize); } - setattr_copy(&nop_mnt_idmap, inode, attr); + setattr_copy(idmap, inode, attr); mark_inode_dirty(inode); return 0; } @@ -985,6 +985,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, static struct lock_class_key hugetlbfs_i_mmap_rwsem_key; static struct inode *hugetlbfs_get_inode(struct super_block *sb, + struct mnt_idmap *idmap, struct inode *dir, umode_t mode, dev_t dev) { @@ -1006,7 +1007,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); inode->i_ino = get_next_ino(); - inode_init_owner(&nop_mnt_idmap, inode, dir, mode); + inode_init_owner(idmap, inode, dir, mode); lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; @@ -1050,7 +1051,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir, { struct inode *inode; - inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev); + inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, dev); if (!inode) return -ENOSPC; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); @@ -1062,7 +1063,7 @@ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir, static int hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { - int retval = hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry, + int retval = hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); @@ -1073,7 +1074,7 @@ static int hugetlbfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - return hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0); + return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0); } static int hugetlbfs_tmpfile(struct mnt_idmap *idmap, @@ -1082,7 +1083,7 @@ static int hugetlbfs_tmpfile(struct mnt_idmap *idmap, { struct inode *inode; - inode = hugetlbfs_get_inode(dir->i_sb, dir, mode | S_IFREG, 0); + inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode | S_IFREG, 0); if (!inode) return -ENOSPC; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); @@ -1094,10 +1095,11 @@ static int hugetlbfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { + const umode_t mode = S_IFLNK|S_IRWXUGO; struct inode *inode; int error = -ENOSPC; - inode = hugetlbfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0); + inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, 0); if (inode) { int l = strlen(symname)+1; error = page_symlink(inode, symname, l); @@ -1566,6 +1568,7 @@ static struct file_system_type hugetlbfs_fs_type = { .init_fs_context = hugetlbfs_init_fs_context, .parameters = hugetlb_fs_parameters, .kill_sb = kill_litter_super, + .fs_flags = FS_ALLOW_IDMAP, }; static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE]; @@ -1619,7 +1622,9 @@ struct file *hugetlb_file_setup(const char *name, size_t size, } file = ERR_PTR(-ENOSPC); - inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0); + /* hugetlbfs_vfsmount[] mounts do not use idmapped mounts. */ + inode = hugetlbfs_get_inode(mnt->mnt_sb, &nop_mnt_idmap, NULL, + S_IFREG | S_IRWXUGO, 0); if (!inode) goto out; if (creat_flags == HUGETLB_SHMFS_INODE) diff --git a/fs/inode.c b/fs/inode.c index 91048c4c9c9e..5c8a5250d0ac 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -588,7 +588,8 @@ void dump_mapping(const struct address_space *mapping) } dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); - if (get_kernel_nofault(dentry, dentry_ptr)) { + if (get_kernel_nofault(dentry, dentry_ptr) || + !dentry.d_parent || !dentry.d_name.name) { pr_warn("aops:%ps ino:%lx invalid dentry:%px\n", a_ops, ino, dentry_ptr); return; @@ -2285,7 +2286,7 @@ void __init inode_init(void) sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| - SLAB_MEM_SPREAD|SLAB_ACCOUNT), + SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ @@ -2509,7 +2510,7 @@ struct timespec64 inode_set_ctime_current(struct inode *inode) { struct timespec64 now = current_time(inode); - inode_set_ctime(inode, now.tv_sec, now.tv_nsec); + inode_set_ctime_to_ts(inode, now); return now; } EXPORT_SYMBOL(inode_set_ctime_current); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 8d8e556bd610..73f09a762b79 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -932,7 +932,7 @@ static int __init init_jfs_fs(void) jfs_inode_cachep = kmem_cache_create_usercopy("jfs_ip", sizeof(struct jfs_inode_info), - 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT, + 0, SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, offsetof(struct jfs_inode_info, i_inline_all), sizeof_field(struct jfs_inode_info, i_inline_all), init_once); diff --git a/fs/libfs.c b/fs/libfs.c index eec6031b0155..78c71a9e2e18 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -240,17 +240,22 @@ const struct inode_operations simple_dir_inode_operations = { }; EXPORT_SYMBOL(simple_dir_inode_operations); -static void offset_set(struct dentry *dentry, u32 offset) +/* 0 is '.', 1 is '..', so always start with offset 2 or more */ +enum { + DIR_OFFSET_MIN = 2, +}; + +static void offset_set(struct dentry *dentry, long offset) { - dentry->d_fsdata = (void *)((uintptr_t)(offset)); + dentry->d_fsdata = (void *)offset; } -static u32 dentry2offset(struct dentry *dentry) +static long dentry2offset(struct dentry *dentry) { - return (u32)((uintptr_t)(dentry->d_fsdata)); + return (long)dentry->d_fsdata; } -static struct lock_class_key simple_offset_xa_lock; +static struct lock_class_key simple_offset_lock_class; /** * simple_offset_init - initialize an offset_ctx @@ -259,11 +264,9 @@ static struct lock_class_key simple_offset_xa_lock; */ void simple_offset_init(struct offset_ctx *octx) { - xa_init_flags(&octx->xa, XA_FLAGS_ALLOC1); - lockdep_set_class(&octx->xa.xa_lock, &simple_offset_xa_lock); - - /* 0 is '.', 1 is '..', so always start with offset 2 */ - octx->next_offset = 2; + mt_init_flags(&octx->mt, MT_FLAGS_ALLOC_RANGE); + lockdep_set_class(&octx->mt.ma_lock, &simple_offset_lock_class); + octx->next_offset = DIR_OFFSET_MIN; } /** @@ -271,20 +274,19 @@ void simple_offset_init(struct offset_ctx *octx) * @octx: directory offset ctx to be updated * @dentry: new dentry being added * - * Returns zero on success. @so_ctx and the dentry offset are updated. + * Returns zero on success. @octx and the dentry's offset are updated. * Otherwise, a negative errno value is returned. */ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) { - static const struct xa_limit limit = XA_LIMIT(2, U32_MAX); - u32 offset; + unsigned long offset; int ret; if (dentry2offset(dentry) != 0) return -EBUSY; - ret = xa_alloc_cyclic(&octx->xa, &offset, dentry, limit, - &octx->next_offset, GFP_KERNEL); + ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN, + LONG_MAX, &octx->next_offset, GFP_KERNEL); if (ret < 0) return ret; @@ -300,16 +302,48 @@ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) */ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry) { - u32 offset; + long offset; offset = dentry2offset(dentry); if (offset == 0) return; - xa_erase(&octx->xa, offset); + mtree_erase(&octx->mt, offset); offset_set(dentry, 0); } +/** + * simple_offset_empty - Check if a dentry can be unlinked + * @dentry: dentry to be tested + * + * Returns 0 if @dentry is a non-empty directory; otherwise returns 1. + */ +int simple_offset_empty(struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + struct offset_ctx *octx; + struct dentry *child; + unsigned long index; + int ret = 1; + + if (!inode || !S_ISDIR(inode->i_mode)) + return ret; + + index = DIR_OFFSET_MIN; + octx = inode->i_op->get_offset_ctx(inode); + mt_for_each(&octx->mt, child, index, LONG_MAX) { + spin_lock(&child->d_lock); + if (simple_positive(child)) { + spin_unlock(&child->d_lock); + ret = 0; + break; + } + spin_unlock(&child->d_lock); + } + + return ret; +} + /** * simple_offset_rename_exchange - exchange rename with directory offsets * @old_dir: parent of dentry being moved @@ -327,8 +361,8 @@ int simple_offset_rename_exchange(struct inode *old_dir, { struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); - u32 old_index = dentry2offset(old_dentry); - u32 new_index = dentry2offset(new_dentry); + long old_index = dentry2offset(old_dentry); + long new_index = dentry2offset(new_dentry); int ret; simple_offset_remove(old_ctx, old_dentry); @@ -354,9 +388,9 @@ int simple_offset_rename_exchange(struct inode *old_dir, out_restore: offset_set(old_dentry, old_index); - xa_store(&old_ctx->xa, old_index, old_dentry, GFP_KERNEL); + mtree_store(&old_ctx->mt, old_index, old_dentry, GFP_KERNEL); offset_set(new_dentry, new_index); - xa_store(&new_ctx->xa, new_index, new_dentry, GFP_KERNEL); + mtree_store(&new_ctx->mt, new_index, new_dentry, GFP_KERNEL); return ret; } @@ -369,7 +403,7 @@ out_restore: */ void simple_offset_destroy(struct offset_ctx *octx) { - xa_destroy(&octx->xa); + mtree_destroy(&octx->mt); } /** @@ -399,15 +433,16 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) /* In this case, ->private_data is protected by f_pos_lock */ file->private_data = NULL; - return vfs_setpos(file, offset, U32_MAX); + return vfs_setpos(file, offset, LONG_MAX); } -static struct dentry *offset_find_next(struct xa_state *xas) +static struct dentry *offset_find_next(struct offset_ctx *octx, loff_t offset) { + MA_STATE(mas, &octx->mt, offset, offset); struct dentry *child, *found = NULL; rcu_read_lock(); - child = xas_next_entry(xas, U32_MAX); + child = mas_find(&mas, LONG_MAX); if (!child) goto out; spin_lock(&child->d_lock); @@ -421,8 +456,8 @@ out: static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) { - u32 offset = dentry2offset(dentry); struct inode *inode = d_inode(dentry); + long offset = dentry2offset(dentry); return ctx->actor(ctx, dentry->d_name.name, dentry->d_name.len, offset, inode->i_ino, fs_umode_to_dtype(inode->i_mode)); @@ -430,12 +465,11 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) { - struct offset_ctx *so_ctx = inode->i_op->get_offset_ctx(inode); - XA_STATE(xas, &so_ctx->xa, ctx->pos); + struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *dentry; while (true) { - dentry = offset_find_next(&xas); + dentry = offset_find_next(octx, ctx->pos); if (!dentry) return ERR_PTR(-ENOENT); @@ -444,8 +478,8 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) break; } + ctx->pos = dentry2offset(dentry) + 1; dput(dentry); - ctx->pos = xas.xa_index + 1; } return NULL; } @@ -481,7 +515,7 @@ static int offset_readdir(struct file *file, struct dir_context *ctx) return 0; /* In this case, ->private_data is protected by f_pos_lock */ - if (ctx->pos == 2) + if (ctx->pos == DIR_OFFSET_MIN) file->private_data = NULL; else if (file->private_data == ERR_PTR(-ENOENT)) return 0; @@ -1704,16 +1738,28 @@ bool is_empty_dir_inode(struct inode *inode) static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { - const struct dentry *parent = READ_ONCE(dentry->d_parent); - const struct inode *dir = READ_ONCE(parent->d_inode); - const struct super_block *sb = dentry->d_sb; - const struct unicode_map *um = sb->s_encoding; - struct qstr qstr = QSTR_INIT(str, len); + const struct dentry *parent; + const struct inode *dir; char strbuf[DNAME_INLINE_LEN]; - int ret; + struct qstr qstr; + /* + * Attempt a case-sensitive match first. It is cheaper and + * should cover most lookups, including all the sane + * applications that expect a case-sensitive filesystem. + * + * This comparison is safe under RCU because the caller + * guarantees the consistency between str and len. See + * __d_lookup_rcu_op_compare() for details. + */ + if (len == name->len && !memcmp(str, name->name, len)) + return 0; + + parent = READ_ONCE(dentry->d_parent); + dir = READ_ONCE(parent->d_inode); if (!dir || !IS_CASEFOLDED(dir)) - goto fallback; + return 1; + /* * If the dentry name is stored in-line, then it may be concurrently * modified by a rename. If this happens, the VFS will eventually retry @@ -1724,20 +1770,14 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, if (len <= DNAME_INLINE_LEN - 1) { memcpy(strbuf, str, len); strbuf[len] = 0; - qstr.name = strbuf; + str = strbuf; /* prevent compiler from optimizing out the temporary buffer */ barrier(); } - ret = utf8_strncasecmp(um, name, &qstr); - if (ret >= 0) - return ret; + qstr.len = len; + qstr.name = str; - if (sb_has_strict_encoding(sb)) - return -EINVAL; -fallback: - if (len != name->len) - return 1; - return !!memcmp(str, name->name, len); + return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr); } /** @@ -1752,7 +1792,7 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) const struct inode *dir = READ_ONCE(dentry->d_inode); struct super_block *sb = dentry->d_sb; const struct unicode_map *um = sb->s_encoding; - int ret = 0; + int ret; if (!dir || !IS_CASEFOLDED(dir)) return 0; @@ -1766,6 +1806,9 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) static const struct dentry_operations generic_ci_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, +#ifdef CONFIG_FS_ENCRYPTION + .d_revalidate = fscrypt_d_revalidate, +#endif }; #endif @@ -1775,64 +1818,33 @@ static const struct dentry_operations generic_encrypted_dentry_ops = { }; #endif -#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE) -static const struct dentry_operations generic_encrypted_ci_dentry_ops = { - .d_hash = generic_ci_d_hash, - .d_compare = generic_ci_d_compare, - .d_revalidate = fscrypt_d_revalidate, -}; -#endif - /** - * generic_set_encrypted_ci_d_ops - helper for setting d_ops for given dentry - * @dentry: dentry to set ops on + * generic_set_sb_d_ops - helper for choosing the set of + * filesystem-wide dentry operations for the enabled features + * @sb: superblock to be configured * - * Casefolded directories need d_hash and d_compare set, so that the dentries - * contained in them are handled case-insensitively. Note that these operations - * are needed on the parent directory rather than on the dentries in it, and - * while the casefolding flag can be toggled on and off on an empty directory, - * dentry_operations can't be changed later. As a result, if the filesystem has - * casefolding support enabled at all, we have to give all dentries the - * casefolding operations even if their inode doesn't have the casefolding flag - * currently (and thus the casefolding ops would be no-ops for now). - * - * Encryption works differently in that the only dentry operation it needs is - * d_revalidate, which it only needs on dentries that have the no-key name flag. - * The no-key flag can't be set "later", so we don't have to worry about that. - * - * Finally, to maximize compatibility with overlayfs (which isn't compatible - * with certain dentry operations) and to avoid taking an unnecessary - * performance hit, we use custom dentry_operations for each possible - * combination rather than always installing all operations. + * Filesystems supporting casefolding and/or fscrypt can call this + * helper at mount-time to configure sb->s_d_op to best set of dentry + * operations required for the enabled features. The helper must be + * called after these have been configured, but before the root dentry + * is created. */ -void generic_set_encrypted_ci_d_ops(struct dentry *dentry) +void generic_set_sb_d_ops(struct super_block *sb) { -#ifdef CONFIG_FS_ENCRYPTION - bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME; -#endif #if IS_ENABLED(CONFIG_UNICODE) - bool needs_ci_ops = dentry->d_sb->s_encoding; -#endif -#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE) - if (needs_encrypt_ops && needs_ci_ops) { - d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops); + if (sb->s_encoding) { + sb->s_d_op = &generic_ci_dentry_ops; return; } #endif #ifdef CONFIG_FS_ENCRYPTION - if (needs_encrypt_ops) { - d_set_d_op(dentry, &generic_encrypted_dentry_ops); - return; - } -#endif -#if IS_ENABLED(CONFIG_UNICODE) - if (needs_ci_ops) { - d_set_d_op(dentry, &generic_ci_dentry_ops); + if (sb->s_cop) { + sb->s_d_op = &generic_encrypted_dentry_ops; return; } #endif } -EXPORT_SYMBOL(generic_set_encrypted_ci_d_ops); +EXPORT_SYMBOL(generic_set_sb_d_ops); /** * inode_maybe_inc_iversion - increments i_version diff --git a/fs/mbcache.c b/fs/mbcache.c index 82aa7a35db26..e60a840999aa 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -426,9 +426,7 @@ EXPORT_SYMBOL(mb_cache_destroy); static int __init mbcache_init(void) { - mb_entry_cache = kmem_cache_create("mbcache", - sizeof(struct mb_cache_entry), 0, - SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL); + mb_entry_cache = KMEM_CACHE(mb_cache_entry, SLAB_RECLAIM_ACCOUNT); if (!mb_entry_cache) return -ENOMEM; return 0; diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 73f37f298087..7cbd2b9f4d11 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -87,7 +87,7 @@ static int __init init_inodecache(void) minix_inode_cachep = kmem_cache_create("minix_inode_cache", sizeof(struct minix_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_ACCOUNT), + SLAB_ACCOUNT), init_once); if (minix_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c index 64c5205e2b5e..3c60f1eaca61 100644 --- a/fs/mnt_idmapping.c +++ b/fs/mnt_idmapping.c @@ -214,7 +214,7 @@ static int copy_mnt_idmap(struct uid_gid_map *map_from, * anything at all. */ if (nr_extents == 0) - return 0; + return -EINVAL; /* * Here we know that nr_extents is greater than zero which means diff --git a/fs/namei.c b/fs/namei.c index 9342fa6a38c2..d0c4a3e9278e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2680,10 +2680,8 @@ static int lookup_one_common(struct mnt_idmap *idmap, if (!len) return -EACCES; - if (unlikely(name[0] == '.')) { - if (len < 2 || (len == 2 && name[1] == '.')) - return -EACCES; - } + if (is_dot_dotdot(name, len)) + return -EACCES; while (len--) { unsigned int c = *(const unsigned char *)name++; diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index cae41db0aaa7..084d19d78397 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -431,7 +431,7 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry, * fnd contains tree's path to insert to. * If fnd is not NULL then dir is locked. */ - inode = ntfs_create_inode(mnt_idmap(file->f_path.mnt), dir, dentry, uni, + inode = ntfs_create_inode(file_mnt_idmap(file), dir, dentry, uni, mode, 0, NULL, 0, fnd); err = IS_ERR(inode) ? PTR_ERR(inode) : finish_open(file, dentry, ntfs_file_open); diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index c4b65a6d41cc..4a0779e3ef79 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -446,7 +446,7 @@ static int __init init_openprom_fs(void) sizeof(struct op_inode_info), 0, (SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD | SLAB_ACCOUNT), + SLAB_ACCOUNT), op_inode_init_once); if (!op_inode_cachep) return -ENOMEM; diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index 112b4b12f825..36dcc530ac28 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -280,12 +280,20 @@ static int ovl_mount_dir_check(struct fs_context *fc, const struct path *path, { struct ovl_fs_context *ctx = fc->fs_private; - if (ovl_dentry_weird(path->dentry)) - return invalfc(fc, "filesystem on %s not supported", name); - if (!d_is_dir(path->dentry)) return invalfc(fc, "%s is not a directory", name); + /* + * Root dentries of case-insensitive capable filesystems might + * not have the dentry operations set, but still be incompatible + * with overlayfs. Check explicitly to prevent post-mount + * failures. + */ + if (sb_has_encoding(path->mnt->mnt_sb)) + return invalfc(fc, "case-insensitive capable filesystem on %s not supported", name); + + if (ovl_dentry_weird(path->dentry)) + return invalfc(fc, "filesystem on %s not supported", name); /* * Check whether upper path is read-only here to report failures diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 2eef6c70b2ae..36d4b8b1f784 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -28,41 +28,38 @@ MODULE_LICENSE("GPL"); struct ovl_dir_cache; -static struct dentry *ovl_d_real(struct dentry *dentry, - const struct inode *inode) +static struct dentry *ovl_d_real(struct dentry *dentry, enum d_real_type type) { - struct dentry *real = NULL, *lower; + struct dentry *upper, *lower; int err; - /* - * vfs is only expected to call d_real() with NULL from d_real_inode() - * and with overlay inode from file_dentry() on an overlay file. - * - * TODO: remove @inode argument from d_real() API, remove code in this - * function that deals with non-NULL @inode and remove d_real() call - * from file_dentry(). - */ - if (inode && d_inode(dentry) == inode) - return dentry; - else if (inode) + switch (type) { + case D_REAL_DATA: + case D_REAL_METADATA: + break; + default: goto bug; + } if (!d_is_reg(dentry)) { /* d_real_inode() is only relevant for regular files */ return dentry; } - real = ovl_dentry_upper(dentry); - if (real && (inode == d_inode(real))) - return real; + upper = ovl_dentry_upper(dentry); + if (upper && (type == D_REAL_METADATA || + ovl_has_upperdata(d_inode(dentry)))) + return upper; - if (real && !inode && ovl_has_upperdata(d_inode(dentry))) - return real; + if (type == D_REAL_METADATA) { + lower = ovl_dentry_lower(dentry); + goto real_lower; + } /* - * Best effort lazy lookup of lowerdata for !inode case to return + * Best effort lazy lookup of lowerdata for D_REAL_DATA case to return * the real lowerdata dentry. The only current caller of d_real() with - * NULL inode is d_real_inode() from trace_uprobe and this caller is + * D_REAL_DATA is d_real_inode() from trace_uprobe and this caller is * likely going to be followed reading from the file, before placing * uprobes on offset within the file, so lowerdata should be available * when setting the uprobe. @@ -73,18 +70,13 @@ static struct dentry *ovl_d_real(struct dentry *dentry, lower = ovl_dentry_lowerdata(dentry); if (!lower) goto bug; - real = lower; - /* Handle recursion */ - real = d_real(real, inode); +real_lower: + /* Handle recursion into stacked lower fs */ + return d_real(lower, type); - if (!inode || inode == d_inode(real)) - return real; bug: - WARN(1, "%s(%pd4, %s:%lu): real dentry (%p/%lu) not found\n", - __func__, dentry, inode ? inode->i_sb->s_id : "NULL", - inode ? inode->i_ino : 0, real, - real && d_inode(real) ? d_inode(real)->i_ino : 0); + WARN(1, "%s(%pd4, %d): real dentry not found\n", __func__, dentry, type); return dentry; } diff --git a/fs/pipe.c b/fs/pipe.c index f1adbfe743d4..50c8a8596b52 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -76,18 +76,20 @@ static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; * -- Manfred Spraul 2002-05-09 */ -static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass) +#define cmp_int(l, r) ((l > r) - (l < r)) + +#ifdef CONFIG_PROVE_LOCKING +static int pipe_lock_cmp_fn(const struct lockdep_map *a, + const struct lockdep_map *b) { - if (pipe->files) - mutex_lock_nested(&pipe->mutex, subclass); + return cmp_int((unsigned long) a, (unsigned long) b); } +#endif void pipe_lock(struct pipe_inode_info *pipe) { - /* - * pipe_lock() nests non-pipe inode locks (for writing to a file) - */ - pipe_lock_nested(pipe, I_MUTEX_PARENT); + if (pipe->files) + mutex_lock(&pipe->mutex); } EXPORT_SYMBOL(pipe_lock); @@ -98,28 +100,16 @@ void pipe_unlock(struct pipe_inode_info *pipe) } EXPORT_SYMBOL(pipe_unlock); -static inline void __pipe_lock(struct pipe_inode_info *pipe) -{ - mutex_lock_nested(&pipe->mutex, I_MUTEX_PARENT); -} - -static inline void __pipe_unlock(struct pipe_inode_info *pipe) -{ - mutex_unlock(&pipe->mutex); -} - void pipe_double_lock(struct pipe_inode_info *pipe1, struct pipe_inode_info *pipe2) { BUG_ON(pipe1 == pipe2); - if (pipe1 < pipe2) { - pipe_lock_nested(pipe1, I_MUTEX_PARENT); - pipe_lock_nested(pipe2, I_MUTEX_CHILD); - } else { - pipe_lock_nested(pipe2, I_MUTEX_PARENT); - pipe_lock_nested(pipe1, I_MUTEX_CHILD); - } + if (pipe1 > pipe2) + swap(pipe1, pipe2); + + pipe_lock(pipe1); + pipe_lock(pipe2); } static void anon_pipe_buf_release(struct pipe_inode_info *pipe, @@ -271,7 +261,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) return 0; ret = 0; - __pipe_lock(pipe); + mutex_lock(&pipe->mutex); /* * We only wake up writers if the pipe was full when we started @@ -368,7 +358,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) ret = -EAGAIN; break; } - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); /* * We only get here if we didn't actually read anything. @@ -400,13 +390,13 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; - __pipe_lock(pipe); + mutex_lock(&pipe->mutex); was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); wake_next_reader = true; } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); if (was_full) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); @@ -462,7 +452,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) if (unlikely(total_len == 0)) return 0; - __pipe_lock(pipe); + mutex_lock(&pipe->mutex); if (!pipe->readers) { send_sig(SIGPIPE, current, 0); @@ -582,19 +572,19 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) * after waiting we need to re-check whether the pipe * become empty while we dropped the lock. */ - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); if (was_empty) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); - __pipe_lock(pipe); + mutex_lock(&pipe->mutex); was_empty = pipe_empty(pipe->head, pipe->tail); wake_next_writer = true; } out: if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) wake_next_writer = false; - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); /* * If we do do a wakeup event, we do a 'sync' wakeup, because we @@ -629,7 +619,7 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) switch (cmd) { case FIONREAD: - __pipe_lock(pipe); + mutex_lock(&pipe->mutex); count = 0; head = pipe->head; tail = pipe->tail; @@ -639,16 +629,16 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) count += pipe->bufs[tail & mask].len; tail++; } - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); return put_user(count, (int __user *)arg); #ifdef CONFIG_WATCH_QUEUE case IOC_WATCH_QUEUE_SET_SIZE: { int ret; - __pipe_lock(pipe); + mutex_lock(&pipe->mutex); ret = watch_queue_set_size(pipe, arg); - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); return ret; } @@ -734,7 +724,7 @@ pipe_release(struct inode *inode, struct file *file) { struct pipe_inode_info *pipe = file->private_data; - __pipe_lock(pipe); + mutex_lock(&pipe->mutex); if (file->f_mode & FMODE_READ) pipe->readers--; if (file->f_mode & FMODE_WRITE) @@ -747,7 +737,7 @@ pipe_release(struct inode *inode, struct file *file) kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return 0; @@ -759,7 +749,7 @@ pipe_fasync(int fd, struct file *filp, int on) struct pipe_inode_info *pipe = filp->private_data; int retval = 0; - __pipe_lock(pipe); + mutex_lock(&pipe->mutex); if (filp->f_mode & FMODE_READ) retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); if ((filp->f_mode & FMODE_WRITE) && retval >= 0) { @@ -768,7 +758,7 @@ pipe_fasync(int fd, struct file *filp, int on) /* this can happen only if on == T */ fasync_helper(-1, filp, 0, &pipe->fasync_readers); } - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); return retval; } @@ -834,6 +824,7 @@ struct pipe_inode_info *alloc_pipe_info(void) pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); + lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL); return pipe; } @@ -1144,7 +1135,7 @@ static int fifo_open(struct inode *inode, struct file *filp) filp->private_data = pipe; /* OK, we have a pipe and it's pinned down */ - __pipe_lock(pipe); + mutex_lock(&pipe->mutex); /* We can only do regular read/write on fifos */ stream_open(inode, filp); @@ -1214,7 +1205,7 @@ static int fifo_open(struct inode *inode, struct file *filp) } /* Ok! */ - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); return 0; err_rd: @@ -1230,7 +1221,7 @@ err_wr: goto err; err: - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return ret; @@ -1411,7 +1402,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg) if (!pipe) return -EBADF; - __pipe_lock(pipe); + mutex_lock(&pipe->mutex); switch (cmd) { case F_SETPIPE_SZ: @@ -1425,7 +1416,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg) break; } - __pipe_unlock(pipe); + mutex_unlock(&pipe->mutex); return ret; } diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 05350f3c2812..dcd513dccf55 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -92,7 +92,7 @@ void __init proc_init_kmemcache(void) proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_ACCOUNT| + SLAB_ACCOUNT| SLAB_PANIC), init_once); pde_opener_cache = diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 6eb9bb369b57..7b5711f76709 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -21,6 +21,7 @@ #include #include #include +#include #include "qnx4.h" #define QNX4_VERSION 4 @@ -30,28 +31,33 @@ static const struct super_operations qnx4_sops; static struct inode *qnx4_alloc_inode(struct super_block *sb); static void qnx4_free_inode(struct inode *inode); -static int qnx4_remount(struct super_block *sb, int *flags, char *data); static int qnx4_statfs(struct dentry *, struct kstatfs *); +static int qnx4_get_tree(struct fs_context *fc); static const struct super_operations qnx4_sops = { .alloc_inode = qnx4_alloc_inode, .free_inode = qnx4_free_inode, .statfs = qnx4_statfs, - .remount_fs = qnx4_remount, }; -static int qnx4_remount(struct super_block *sb, int *flags, char *data) +static int qnx4_reconfigure(struct fs_context *fc) { + struct super_block *sb = fc->root->d_sb; struct qnx4_sb_info *qs; sync_filesystem(sb); qs = qnx4_sb(sb); qs->Version = QNX4_VERSION; - *flags |= SB_RDONLY; + fc->sb_flags |= SB_RDONLY; return 0; } +static const struct fs_context_operations qnx4_context_opts = { + .get_tree = qnx4_get_tree, + .reconfigure = qnx4_reconfigure, +}; + static int qnx4_get_block( struct inode *inode, sector_t iblock, struct buffer_head *bh, int create ) { unsigned long phys; @@ -183,12 +189,13 @@ static const char *qnx4_checkroot(struct super_block *sb, return "bitmap file not found."; } -static int qnx4_fill_super(struct super_block *s, void *data, int silent) +static int qnx4_fill_super(struct super_block *s, struct fs_context *fc) { struct buffer_head *bh; struct inode *root; const char *errmsg; struct qnx4_sb_info *qs; + int silent = fc->sb_flags & SB_SILENT; qs = kzalloc(sizeof(struct qnx4_sb_info), GFP_KERNEL); if (!qs) @@ -216,7 +223,7 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent) errmsg = qnx4_checkroot(s, (struct qnx4_super_block *) bh->b_data); brelse(bh); if (errmsg != NULL) { - if (!silent) + if (!silent) printk(KERN_ERR "qnx4: %s\n", errmsg); return -EINVAL; } @@ -235,6 +242,18 @@ static int qnx4_fill_super(struct super_block *s, void *data, int silent) return 0; } +static int qnx4_get_tree(struct fs_context *fc) +{ + return get_tree_bdev(fc, qnx4_fill_super); +} + +static int qnx4_init_fs_context(struct fs_context *fc) +{ + fc->ops = &qnx4_context_opts; + + return 0; +} + static void qnx4_kill_sb(struct super_block *sb) { struct qnx4_sb_info *qs = qnx4_sb(sb); @@ -376,18 +395,12 @@ static void destroy_inodecache(void) kmem_cache_destroy(qnx4_inode_cachep); } -static struct dentry *qnx4_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) -{ - return mount_bdev(fs_type, flags, dev_name, data, qnx4_fill_super); -} - static struct file_system_type qnx4_fs_type = { - .owner = THIS_MODULE, - .name = "qnx4", - .mount = qnx4_mount, - .kill_sb = qnx4_kill_sb, - .fs_flags = FS_REQUIRES_DEV, + .owner = THIS_MODULE, + .name = "qnx4", + .kill_sb = qnx4_kill_sb, + .fs_flags = FS_REQUIRES_DEV, + .init_fs_context = qnx4_init_fs_context, }; MODULE_ALIAS_FS("qnx4"); diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index a286c545717f..405913f4faff 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -615,7 +615,7 @@ static int init_inodecache(void) qnx6_inode_cachep = kmem_cache_create("qnx6_inode_cache", sizeof(struct qnx6_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_ACCOUNT), + SLAB_ACCOUNT), init_once); if (!qnx6_inode_cachep) return -ENOMEM; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 67b5510beded..2cc469d481a2 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -670,7 +670,6 @@ static int __init init_inodecache(void) sizeof(struct reiserfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD| SLAB_ACCOUNT), init_once); if (reiserfs_inode_cachep == NULL) diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 545ad44f96b8..85641c3f5782 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -630,8 +630,8 @@ static int __init init_romfs_fs(void) romfs_inode_cachep = kmem_cache_create("romfs_i", sizeof(struct romfs_inode_info), 0, - SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | - SLAB_ACCOUNT, romfs_i_init_once); + SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, + romfs_i_init_once); if (!romfs_inode_cachep) { pr_err("Failed to initialise inode cache\n"); diff --git a/fs/select.c b/fs/select.c index 0ee55af1a55c..9515c3fa1a03 100644 --- a/fs/select.c +++ b/fs/select.c @@ -476,7 +476,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in, wait->_key |= POLLOUT_SET; } -static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) +static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; @@ -839,7 +839,7 @@ SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) struct poll_list { struct poll_list *next; - int len; + unsigned int len; struct pollfd entries[]; }; @@ -975,14 +975,15 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, struct timespec64 *end_time) { struct poll_wqueues table; - int err = -EFAULT, fdcount, len; + int err = -EFAULT, fdcount; /* Allocate small arguments on the stack to save memory and be faster - use long to make sure the buffer is aligned properly on 64 bit archs to avoid unaligned access */ long stack_pps[POLL_STACK_ALLOC/sizeof(long)]; struct poll_list *const head = (struct poll_list *)stack_pps; struct poll_list *walk = head; - unsigned long todo = nfds; + unsigned int todo = nfds; + unsigned int len; if (nfds > rlimit(RLIMIT_NOFILE)) return -EINVAL; @@ -998,9 +999,9 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, sizeof(struct pollfd) * walk->len)) goto out_fds; - todo -= walk->len; - if (!todo) + if (walk->len >= todo) break; + todo -= walk->len; len = min(todo, POLLFD_PER_PAGE); walk = walk->next = kmalloc(struct_size(walk, entries, len), @@ -1020,7 +1021,7 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, for (walk = head; walk; walk = walk->next) { struct pollfd *fds = walk->entries; - int j; + unsigned int j; for (j = walk->len; j; fds++, ufds++, j--) unsafe_put_user(fds->revents, &ufds->revents, Efault); diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 5a915b2e68f5..76bc2d5e75a9 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -336,7 +336,7 @@ int __init sysv_init_icache(void) { sysv_inode_cachep = kmem_cache_create("sysv_inode_cache", sizeof(struct sysv_inode_info), 0, - SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT, + SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, init_once); if (!sysv_inode_cachep) return -ENOMEM; diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 410ab2a44d2f..19bcb51a2203 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -83,9 +83,6 @@ static inline sysv_zone_t *block_end(struct buffer_head *bh) return (sysv_zone_t*)((char*)bh->b_data + bh->b_size); } -/* - * Requires read_lock(&pointers_lock) or write_lock(&pointers_lock) - */ static Indirect *get_branch(struct inode *inode, int depth, int offsets[], @@ -105,15 +102,18 @@ static Indirect *get_branch(struct inode *inode, bh = sb_bread(sb, block); if (!bh) goto failure; + read_lock(&pointers_lock); if (!verify_chain(chain, p)) goto changed; add_chain(++p, bh, (sysv_zone_t*)bh->b_data + *++offsets); + read_unlock(&pointers_lock); if (!p->key) goto no_block; } return NULL; changed: + read_unlock(&pointers_lock); brelse(bh); *err = -EAGAIN; goto no_block; @@ -219,9 +219,7 @@ static int get_block(struct inode *inode, sector_t iblock, struct buffer_head *b goto out; reread: - read_lock(&pointers_lock); partial = get_branch(inode, depth, offsets, chain, &err); - read_unlock(&pointers_lock); /* Simplest case - block found, no allocation needed */ if (!partial) { @@ -291,9 +289,9 @@ static Indirect *find_shared(struct inode *inode, *top = 0; for (k = depth; k > 1 && !offsets[k-1]; k--) ; + partial = get_branch(inode, k, offsets, chain, &err); write_lock(&pointers_lock); - partial = get_branch(inode, k, offsets, chain, &err); if (!partial) partial = chain + k-1; /* diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index e413a9cf8ee3..551148de66cd 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -205,7 +205,6 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry, dbg_gen("'%pd' in dir ino %lu", dentry, dir->i_ino); err = fscrypt_prepare_lookup(dir, dentry, &nm); - generic_set_encrypted_ci_d_ops(dentry); if (err == -ENOENT) return d_splice_alias(NULL, dentry); if (err) diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 09e270d6ed02..304646b03e99 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2239,6 +2239,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) goto out_umount; } + generic_set_sb_d_ops(sb); sb->s_root = d_make_root(root); if (!sb->s_root) { err = -ENOMEM; diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 961f4d88f9ef..0c0695763bea 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -193,7 +193,6 @@ do { \ #ifndef smp_store_release #define smp_store_release(p, v) \ do { \ - compiletime_assert_atomic_type(*p); \ barrier(); \ WRITE_ONCE(*p, v); \ } while (0) @@ -203,7 +202,6 @@ do { \ #define smp_load_acquire(p) \ ({ \ __unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p); \ - compiletime_assert_atomic_type(*p); \ barrier(); \ (typeof(*p))___p1; \ }) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 1a97277f99b1..8e7af9a03b41 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -38,7 +38,6 @@ struct backing_dev_info *bdi_alloc(int node_id); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); -void wb_wakeup_delayed(struct bdi_writeback *wb); void wb_wait_for_completion(struct wb_completion *done); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d07cf2f1bb7d..bf53e3894aae 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -125,6 +125,11 @@ enum dentry_d_lock_class DENTRY_D_LOCK_NESTED }; +enum d_real_type { + D_REAL_DATA, + D_REAL_METADATA, +}; + struct dentry_operations { int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); @@ -139,7 +144,7 @@ struct dentry_operations { char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); - struct dentry *(*d_real)(struct dentry *, const struct inode *); + struct dentry *(*d_real)(struct dentry *, enum d_real_type type); } ____cacheline_aligned; /* @@ -547,24 +552,23 @@ static inline struct inode *d_backing_inode(const struct dentry *upper) /** * d_real - Return the real dentry * @dentry: the dentry to query - * @inode: inode to select the dentry from multiple layers (can be NULL) + * @type: the type of real dentry (data or metadata) * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. * * See also: Documentation/filesystems/vfs.rst */ -static inline struct dentry *d_real(struct dentry *dentry, - const struct inode *inode) +static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) - return dentry->d_op->d_real(dentry, inode); + return dentry->d_op->d_real(dentry, type); else return dentry; } /** - * d_real_inode - Return the real inode + * d_real_inode - Return the real inode hosting the data * @dentry: The dentry to query * * If dentry is on a union/overlay, then return the underlying, real inode. @@ -573,7 +577,7 @@ static inline struct dentry *d_real(struct dentry *dentry, static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ - return d_backing_inode(d_real((struct dentry *) dentry, NULL)); + return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA)); } struct name_snapshot { diff --git a/include/linux/fs.h b/include/linux/fs.h index 1fbc72c5f112..2ba751d097c1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -484,10 +485,10 @@ struct address_space { pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; - struct rw_semaphore i_mmap_rwsem; errseq_t wb_err; spinlock_t i_private_lock; struct list_head i_private_list; + struct rw_semaphore i_mmap_rwsem; void * i_private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* @@ -909,7 +910,8 @@ static inline loff_t i_size_read(const struct inode *inode) preempt_enable(); return i_size; #else - return inode->i_size; + /* Pairs with smp_store_release() in i_size_write() */ + return smp_load_acquire(&inode->i_size); #endif } @@ -931,7 +933,12 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) inode->i_size = i_size; preempt_enable(); #else - inode->i_size = i_size; + /* + * Pairs with smp_load_acquire() in i_size_read() to ensure + * changes related to inode size (such as page contents) are + * visible before we see the changed inode size. + */ + smp_store_release(&inode->i_size, i_size); #endif } @@ -1080,9 +1087,20 @@ static inline struct inode *file_inode(const struct file *f) return f->f_inode; } +/* + * file_dentry() is a relic from the days that overlayfs was using files with a + * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs. + * In those days, file_dentry() was needed to get the underlying fs dentry that + * matches f_inode. + * Files with "fake" path should not exist nowadays, so use an assertion to make + * sure that file_dentry() was not papering over filesystem bugs. + */ static inline struct dentry *file_dentry(const struct file *file) { - return d_real(file->f_path.dentry, file_inode(file)); + struct dentry *dentry = file->f_path.dentry; + + WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); + return dentry; } struct fasync_struct { @@ -2927,6 +2945,17 @@ extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); +/** + * is_dot_dotdot - returns true only if @name is "." or ".." + * @name: file name to check + * @len: length of file name, in bytes + */ +static inline bool is_dot_dotdot(const char *name, size_t len) +{ + return len && unlikely(name[0] == '.') && + (len == 1 || (len == 2 && name[1] == '.')); +} + #include /* needed for stackable file system support */ @@ -3259,13 +3288,14 @@ extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); struct offset_ctx { - struct xarray xa; - u32 next_offset; + struct maple_tree mt; + unsigned long next_offset; }; void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); +int simple_offset_empty(struct dentry *dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, @@ -3279,7 +3309,16 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); -extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry); +extern void generic_set_sb_d_ops(struct super_block *sb); + +static inline bool sb_has_encoding(const struct super_block *sb) +{ +#if IS_ENABLED(CONFIG_UNICODE) + return !!sb->s_encoding; +#else + return false; +#endif +} int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); @@ -3334,6 +3373,8 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; + if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) + return -EINVAL; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) @@ -3344,6 +3385,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; + if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { + if (IS_APPEND(file_inode(ki->ki_filp))) + return -EPERM; + ki->ki_flags &= ~IOCB_APPEND; + } + ki->ki_flags |= kiocb_flags; return 0; } diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 12f9e455d569..772f822dc6b8 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -192,6 +192,8 @@ struct fscrypt_operations { unsigned int *num_devs); }; +int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags); + static inline struct fscrypt_inode_info * fscrypt_get_inode_info(const struct inode *inode) { @@ -221,15 +223,29 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode) } /* - * When d_splice_alias() moves a directory's no-key alias to its plaintext alias - * as a result of the encryption key being added, DCACHE_NOKEY_NAME must be - * cleared. Note that we don't have to support arbitrary moves of this flag - * because fscrypt doesn't allow no-key names to be the source or target of a - * rename(). + * When d_splice_alias() moves a directory's no-key alias to its + * plaintext alias as a result of the encryption key being added, + * DCACHE_NOKEY_NAME must be cleared and there might be an opportunity + * to disable d_revalidate. Note that we don't have to support the + * inverse operation because fscrypt doesn't allow no-key names to be + * the source or target of a rename(). */ static inline void fscrypt_handle_d_move(struct dentry *dentry) { - dentry->d_flags &= ~DCACHE_NOKEY_NAME; + /* + * VFS calls fscrypt_handle_d_move even for non-fscrypt + * filesystems. + */ + if (dentry->d_flags & DCACHE_NOKEY_NAME) { + dentry->d_flags &= ~DCACHE_NOKEY_NAME; + + /* + * Other filesystem features might be handling dentry + * revalidation, in which case it cannot be disabled. + */ + if (dentry->d_op->d_revalidate == fscrypt_d_revalidate) + dentry->d_flags &= ~DCACHE_OP_REVALIDATE; + } } /** @@ -261,6 +277,35 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry) return dentry->d_flags & DCACHE_NOKEY_NAME; } +static inline void fscrypt_prepare_dentry(struct dentry *dentry, + bool is_nokey_name) +{ + /* + * This code tries to only take ->d_lock when necessary to write + * to ->d_flags. We shouldn't be peeking on d_flags for + * DCACHE_OP_REVALIDATE unlocked, but in the unlikely case + * there is a race, the worst it can happen is that we fail to + * unset DCACHE_OP_REVALIDATE and pay the cost of an extra + * d_revalidate. + */ + if (is_nokey_name) { + spin_lock(&dentry->d_lock); + dentry->d_flags |= DCACHE_NOKEY_NAME; + spin_unlock(&dentry->d_lock); + } else if (dentry->d_flags & DCACHE_OP_REVALIDATE && + dentry->d_op->d_revalidate == fscrypt_d_revalidate) { + /* + * Unencrypted dentries and encrypted dentries where the + * key is available are always valid from fscrypt + * perspective. Avoid the cost of calling + * fscrypt_d_revalidate unnecessarily. + */ + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~DCACHE_OP_REVALIDATE; + spin_unlock(&dentry->d_lock); + } +} + /* crypto.c */ void fscrypt_enqueue_decrypt_work(struct work_struct *); @@ -368,7 +413,6 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode, bool fscrypt_match_name(const struct fscrypt_name *fname, const u8 *de_name, u32 de_name_len); u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); -int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags); /* bio.c */ bool fscrypt_decrypt_bio(struct bio *bio); @@ -425,6 +469,11 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry) return false; } +static inline void fscrypt_prepare_dentry(struct dentry *dentry, + bool is_nokey_name) +{ +} + /* crypto.c */ static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) { @@ -982,6 +1031,9 @@ static inline int fscrypt_prepare_lookup(struct inode *dir, fname->usr_fname = &dentry->d_name; fname->disk_name.name = (unsigned char *)dentry->d_name.name; fname->disk_name.len = dentry->d_name.len; + + fscrypt_prepare_dentry(dentry, false); + return 0; } diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index b3d63123b945..a53ad4dabd7e 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -171,6 +171,7 @@ enum maple_type { #define MT_FLAGS_LOCK_IRQ 0x100 #define MT_FLAGS_LOCK_BH 0x200 #define MT_FLAGS_LOCK_EXTERN 0x300 +#define MT_FLAGS_ALLOC_WRAPPED 0x0800 #define MAPLE_HEIGHT_MAX 31 @@ -319,6 +320,9 @@ int mtree_insert_range(struct maple_tree *mt, unsigned long first, int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); +int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long range_lo, unsigned long range_hi, + unsigned long *next, gfp_t gfp); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp); @@ -499,6 +503,9 @@ void *mas_find_range(struct ma_state *mas, unsigned long max); void *mas_find_rev(struct ma_state *mas, unsigned long min); void *mas_find_range_rev(struct ma_state *mas, unsigned long max); int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp); +int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, + void *entry, unsigned long range_lo, unsigned long range_hi, + unsigned long *next, gfp_t gfp); bool mas_nomem(struct ma_state *mas, gfp_t gfp); void mas_pause(struct ma_state *mas); diff --git a/include/linux/poll.h b/include/linux/poll.h index a9e0e1c2d1f2..d1ea4f3714a8 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -14,11 +14,7 @@ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ -#ifdef __clang__ -#define MAX_STACK_ALLOC 768 -#else #define MAX_STACK_ALLOC 832 -#endif #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 48ad69f7722e..2203d3194b91 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -301,9 +301,12 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO O_APPEND */ #define RWF_APPEND ((__force __kernel_rwf_t)0x00000010) +/* per-IO negation of O_APPEND */ +#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND) + RWF_APPEND | RWF_NOAPPEND) /* Pagemap ioctl */ #define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) diff --git a/init/initramfs.c b/init/initramfs.c index 76deb48c38cb..d3c623dde01a 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -679,8 +679,6 @@ static void __init populate_initrd_image(char *err) struct file *file; loff_t pos = 0; - unpack_to_rootfs(__initramfs_start, __initramfs_size); - printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n", err); file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index cf2eb2b2f983..4a6a9f419bd7 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -691,12 +691,11 @@ EXPORT_SYMBOL(iov_iter_discard); static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask, unsigned len_mask) { + const struct iovec *iov = iter_iov(i); size_t size = i->count; size_t skip = i->iov_offset; - unsigned k; - for (k = 0; k < i->nr_segs; k++, skip = 0) { - const struct iovec *iov = iter_iov(i) + k; + do { size_t len = iov->iov_len - skip; if (len > size) @@ -706,34 +705,36 @@ static bool iov_iter_aligned_iovec(const struct iov_iter *i, unsigned addr_mask, if ((unsigned long)(iov->iov_base + skip) & addr_mask) return false; + iov++; size -= len; - if (!size) - break; - } + skip = 0; + } while (size); + return true; } static bool iov_iter_aligned_bvec(const struct iov_iter *i, unsigned addr_mask, unsigned len_mask) { - size_t size = i->count; + const struct bio_vec *bvec = i->bvec; unsigned skip = i->iov_offset; - unsigned k; + size_t size = i->count; - for (k = 0; k < i->nr_segs; k++, skip = 0) { - size_t len = i->bvec[k].bv_len - skip; + do { + size_t len = bvec->bv_len; if (len > size) len = size; if (len & len_mask) return false; - if ((unsigned long)(i->bvec[k].bv_offset + skip) & addr_mask) + if ((unsigned long)(bvec->bv_offset + skip) & addr_mask) return false; + bvec++; size -= len; - if (!size) - break; - } + skip = 0; + } while (size); + return true; } @@ -777,13 +778,12 @@ EXPORT_SYMBOL_GPL(iov_iter_is_aligned); static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i) { + const struct iovec *iov = iter_iov(i); unsigned long res = 0; size_t size = i->count; size_t skip = i->iov_offset; - unsigned k; - for (k = 0; k < i->nr_segs; k++, skip = 0) { - const struct iovec *iov = iter_iov(i) + k; + do { size_t len = iov->iov_len - skip; if (len) { res |= (unsigned long)iov->iov_base + skip; @@ -791,30 +791,31 @@ static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i) len = size; res |= len; size -= len; - if (!size) - break; } - } + iov++; + skip = 0; + } while (size); return res; } static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i) { + const struct bio_vec *bvec = i->bvec; unsigned res = 0; size_t size = i->count; unsigned skip = i->iov_offset; - unsigned k; - for (k = 0; k < i->nr_segs; k++, skip = 0) { - size_t len = i->bvec[k].bv_len - skip; - res |= (unsigned long)i->bvec[k].bv_offset + skip; + do { + size_t len = bvec->bv_len - skip; + res |= (unsigned long)bvec->bv_offset + skip; if (len > size) len = size; res |= len; + bvec++; size -= len; - if (!size) - break; - } + skip = 0; + } while (size); + return res; } @@ -1143,11 +1144,12 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) EXPORT_SYMBOL(dup_iter); static __noclone int copy_compat_iovec_from_user(struct iovec *iov, - const struct iovec __user *uvec, unsigned long nr_segs) + const struct iovec __user *uvec, u32 nr_segs) { const struct compat_iovec __user *uiov = (const struct compat_iovec __user *)uvec; - int ret = -EFAULT, i; + int ret = -EFAULT; + u32 i; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 6f241bb38799..af0970288727 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4290,6 +4290,56 @@ exists: } +/** + * mas_alloc_cyclic() - Internal call to find somewhere to store an entry + * @mas: The maple state. + * @startp: Pointer to ID. + * @range_lo: Lower bound of range to search. + * @range_hi: Upper bound of range to search. + * @entry: The entry to store. + * @next: Pointer to next ID to allocate. + * @gfp: The GFP_FLAGS to use for allocations. + * + * Return: 0 if the allocation succeeded without wrapping, 1 if the + * allocation succeeded after wrapping, or -EBUSY if there are no + * free entries. + */ +int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, + void *entry, unsigned long range_lo, unsigned long range_hi, + unsigned long *next, gfp_t gfp) +{ + unsigned long min = range_lo; + int ret = 0; + + range_lo = max(min, *next); + ret = mas_empty_area(mas, range_lo, range_hi, 1); + if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) { + mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED; + ret = 1; + } + if (ret < 0 && range_lo > min) { + ret = mas_empty_area(mas, min, range_hi, 1); + if (ret == 0) + ret = 1; + } + if (ret < 0) + return ret; + + do { + mas_insert(mas, entry); + } while (mas_nomem(mas, gfp)); + if (mas_is_err(mas)) + return xa_err(mas->node); + + *startp = mas->index; + *next = *startp + 1; + if (*next == 0) + mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED; + + return ret; +} +EXPORT_SYMBOL(mas_alloc_cyclic); + static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: @@ -6443,6 +6493,49 @@ unlock: } EXPORT_SYMBOL(mtree_alloc_range); +/** + * mtree_alloc_cyclic() - Find somewhere to store this entry in the tree. + * @mt: The maple tree. + * @startp: Pointer to ID. + * @range_lo: Lower bound of range to search. + * @range_hi: Upper bound of range to search. + * @entry: The entry to store. + * @next: Pointer to next ID to allocate. + * @gfp: The GFP_FLAGS to use for allocations. + * + * Finds an empty entry in @mt after @next, stores the new index into + * the @id pointer, stores the entry at that index, then updates @next. + * + * @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag. + * + * Context: Any context. Takes and releases the mt.lock. May sleep if + * the @gfp flags permit. + * + * Return: 0 if the allocation succeeded without wrapping, 1 if the + * allocation succeeded after wrapping, -ENOMEM if memory could not be + * allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no + * free entries. + */ +int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, + void *entry, unsigned long range_lo, unsigned long range_hi, + unsigned long *next, gfp_t gfp) +{ + int ret; + + MA_STATE(mas, mt, 0, 0); + + if (!mt_is_alloc(mt)) + return -EINVAL; + if (WARN_ON_ONCE(mt_is_reserved(entry))) + return -EINVAL; + mtree_lock(mt); + ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi, + next, gfp); + mtree_unlock(mt); + return ret; +} +EXPORT_SYMBOL(mtree_alloc_cyclic); + int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 29185ac5c727..399380db449c 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -3599,6 +3599,45 @@ static noinline void __init check_state_handling(struct maple_tree *mt) mas_unlock(&mas); } +static noinline void __init alloc_cyclic_testing(struct maple_tree *mt) +{ + unsigned long location; + unsigned long next; + int ret = 0; + MA_STATE(mas, mt, 0, 0); + + next = 0; + mtree_lock(mt); + for (int i = 0; i < 100; i++) { + mas_alloc_cyclic(&mas, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL); + MAS_BUG_ON(&mas, i != location - 2); + MAS_BUG_ON(&mas, mas.index != location); + MAS_BUG_ON(&mas, mas.last != location); + MAS_BUG_ON(&mas, i != next - 3); + } + + mtree_unlock(mt); + mtree_destroy(mt); + next = 0; + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + for (int i = 0; i < 100; i++) { + mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL); + MT_BUG_ON(mt, i != location - 2); + MT_BUG_ON(mt, i != next - 3); + MT_BUG_ON(mt, mtree_load(mt, location) != mt); + } + + mtree_destroy(mt); + /* Overflow test */ + next = ULONG_MAX - 1; + ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL); + MT_BUG_ON(mt, ret != 0); + ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL); + MT_BUG_ON(mt, ret != 0); + ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL); + MT_BUG_ON(mt, ret != 1); +} + static DEFINE_MTREE(tree); static int __init maple_tree_seed(void) { @@ -3880,6 +3919,11 @@ static int __init maple_tree_seed(void) check_state_handling(&tree); mtree_destroy(&tree); + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); + alloc_cyclic_testing(&tree); + mtree_destroy(&tree); + + #if defined(BENCH) skip: #endif diff --git a/mm/backing-dev.c b/mm/backing-dev.c index e039d05304dd..5f2be8c8df11 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -372,31 +372,6 @@ static int __init default_bdi_init(void) } subsys_initcall(default_bdi_init); -/* - * This function is used when the first inode for this wb is marked dirty. It - * wakes-up the corresponding bdi thread which should then take care of the - * periodic background write-out of dirty inodes. Since the write-out would - * starts only 'dirty_writeback_interval' centisecs from now anyway, we just - * set up a timer which wakes the bdi thread up later. - * - * Note, we wouldn't bother setting up the timer, but this function is on the - * fast-path (used by '__mark_inode_dirty()'), so we save few context switches - * by delaying the wake-up. - * - * We have to be careful not to postpone flush work if it is scheduled for - * earlier. Thus we use queue_delayed_work(). - */ -void wb_wakeup_delayed(struct bdi_writeback *wb) -{ - unsigned long timeout; - - timeout = msecs_to_jiffies(dirty_writeback_interval * 10); - spin_lock_irq(&wb->work_lock); - if (test_bit(WB_registered, &wb->state)) - queue_delayed_work(bdi_wq, &wb->dwork, timeout); - spin_unlock_irq(&wb->work_lock); -} - static void wb_update_bandwidth_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), diff --git a/mm/filemap.c b/mm/filemap.c index 4a30de98a8c7..8df4797c5287 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2608,15 +2608,6 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, goto put_folios; end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); - /* - * Pairs with a barrier in - * block_write_end()->mark_buffer_dirty() or other page - * dirtying routines like iomap_write_end() to ensure - * changes to page contents are visible before we see - * increased inode size. - */ - smp_rmb(); - /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: diff --git a/mm/shmem.c b/mm/shmem.c index d7c84ff62186..6fed524343cb 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3374,7 +3374,7 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry) static int shmem_rmdir(struct inode *dir, struct dentry *dentry) { - if (!simple_empty(dentry)) + if (!simple_offset_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); @@ -3431,7 +3431,7 @@ static int shmem_rename2(struct mnt_idmap *idmap, return simple_offset_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); - if (!simple_empty(new_dentry)) + if (!simple_offset_empty(new_dentry)) return -ENOTEMPTY; if (flags & RENAME_WHITEOUT) { diff --git a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c index e19ab0e85709..759f86e7d263 100644 --- a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c +++ b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -32,7 +31,11 @@ static int sys_fsmount(int fd, unsigned int flags, unsigned int attr_flags) { return syscall(__NR_fsmount, fd, flags, attr_flags); } - +static int sys_mount(const char *src, const char *tgt, const char *fst, + unsigned long flags, const void *data) +{ + return syscall(__NR_mount, src, tgt, fst, flags, data); +} static int sys_move_mount(int from_dfd, const char *from_pathname, int to_dfd, const char *to_pathname, unsigned int flags) @@ -166,8 +169,7 @@ int main(int argc, char **argv) ksft_test_result_skip("unable to create a new mount namespace\n"); return 1; } - - if (mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) { + if (sys_mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) { pr_perror("mount"); return 1; } diff --git a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c index 50ed5d475dd1..bcf51d785a37 100644 --- a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c +++ b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c @@ -218,7 +218,7 @@ static bool move_mount_set_group_supported(void) if (mount(NULL, SET_GROUP_FROM, NULL, MS_SHARED, 0)) return -1; - ret = syscall(SYS_move_mount, AT_FDCWD, SET_GROUP_FROM, + ret = syscall(__NR_move_mount, AT_FDCWD, SET_GROUP_FROM, AT_FDCWD, SET_GROUP_TO, MOVE_MOUNT_SET_GROUP); umount2("/tmp", MNT_DETACH); @@ -363,7 +363,7 @@ TEST_F(move_mount_set_group, complex_sharing_copying) CLONE_VM | CLONE_FILES); ASSERT_GT(pid, 0); ASSERT_EQ(wait_for_pid(pid), 0); - ASSERT_EQ(syscall(SYS_move_mount, ca_from.mntfd, "", + ASSERT_EQ(syscall(__NR_move_mount, ca_from.mntfd, "", ca_to.mntfd, "", MOVE_MOUNT_SET_GROUP | MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH), 0);