diff options
33 files changed, 488 insertions, 465 deletions
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index cb713df..b30dd81 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -384,3 +384,5 @@ 375 i386 membarrier sys_membarrier 376 i386 mlock2 sys_mlock2 377 i386 copy_file_range sys_copy_file_range +378 i386 preadv2 sys_preadv2 +379 i386 pwritev2 sys_pwritev2 diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 2e5b565..cac6d17 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -333,6 +333,8 @@ 324 common membarrier sys_membarrier 325 common mlock2 sys_mlock2 326 common copy_file_range sys_copy_file_range +327 64 preadv2 sys_preadv2 +328 64 pwritev2 sys_pwritev2 # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 9328b58..7ab9239 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -542,8 +542,6 @@ static struct dentry *autofs4_lookup(struct inode *dir, ino->dentry = dentry; autofs4_add_active(dentry); - - d_instantiate(dentry, NULL); } return NULL; } diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 452e98d..1ee54ff 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -162,6 +162,8 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, size_t buflen, loff_t *pos) { struct cachefiles_cache *cache = file->private_data; + unsigned long long b_released; + unsigned f_released; char buffer[256]; int n; @@ -174,6 +176,8 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, cachefiles_has_space(cache, 0, 0); /* summarise */ + f_released = atomic_xchg(&cache->f_released, 0); + b_released = atomic_long_xchg(&cache->b_released, 0); clear_bit(CACHEFILES_STATE_CHANGED, &cache->flags); n = snprintf(buffer, sizeof(buffer), @@ -183,15 +187,18 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, " fstop=%llx" " brun=%llx" " bcull=%llx" - " bstop=%llx", + " bstop=%llx" + " freleased=%x" + " breleased=%llx", test_bit(CACHEFILES_CULLING, &cache->flags) ? '1' : '0', (unsigned long long) cache->frun, (unsigned long long) cache->fcull, (unsigned long long) cache->fstop, (unsigned long long) cache->brun, (unsigned long long) cache->bcull, - (unsigned long long) cache->bstop - ); + (unsigned long long) cache->bstop, + f_released, + b_released); if (n > buflen) return -EMSGSIZE; diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index 675a333..861d611 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -291,15 +291,8 @@ static void cachefiles_drop_object(struct fscache_object *_object) } /* note that the object is now inactive */ - if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) { - write_lock(&cache->active_lock); - if (!test_and_clear_bit(CACHEFILES_OBJECT_ACTIVE, - &object->flags)) - BUG(); - rb_erase(&object->active_node, &cache->active_nodes); - wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE); - write_unlock(&cache->active_lock); - } + if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) + cachefiles_mark_object_inactive(cache, object); dput(object->dentry); object->dentry = NULL; diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 9c4b737..2fcde1a 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -66,6 +66,8 @@ struct cachefiles_cache { struct rb_root active_nodes; /* active nodes (can't be culled) */ rwlock_t active_lock; /* lock for active_nodes */ atomic_t gravecounter; /* graveyard uniquifier */ + atomic_t f_released; /* number of objects released lately */ + atomic_long_t b_released; /* number of blocks released lately */ unsigned frun_percent; /* when to stop culling (% files) */ unsigned fcull_percent; /* when to start culling (% files) */ unsigned fstop_percent; /* when to stop allocating (% files) */ @@ -157,6 +159,8 @@ extern char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type); /* * namei.c */ +extern void cachefiles_mark_object_inactive(struct cachefiles_cache *cache, + struct cachefiles_object *object); extern int cachefiles_delete_object(struct cachefiles_cache *cache, struct cachefiles_object *object); extern int cachefiles_walk_to_object(struct cachefiles_object *parent, diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 1c2334c..4ae7500 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -258,6 +258,28 @@ requeue: } /* + * Mark an object as being inactive. + */ +void cachefiles_mark_object_inactive(struct cachefiles_cache *cache, + struct cachefiles_object *object) +{ + write_lock(&cache->active_lock); + rb_erase(&object->active_node, &cache->active_nodes); + clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); + write_unlock(&cache->active_lock); + + wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE); + + /* This object can now be culled, so we need to let the daemon know + * that there is something it can remove if it needs to. + */ + atomic_long_add(d_backing_inode(object->dentry)->i_blocks, + &cache->b_released); + if (atomic_inc_return(&cache->f_released)) + cachefiles_state_changed(cache); +} + +/* * delete an object representation from the cache * - file backed objects are unlinked * - directory backed objects are stuffed into the graveyard for userspace to @@ -684,11 +706,7 @@ mark_active_timed_out: check_error: _debug("check error %d", ret); - write_lock(&cache->active_lock); - rb_erase(&object->active_node, &cache->active_nodes); - clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); - wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE); - write_unlock(&cache->active_lock); + cachefiles_mark_object_inactive(cache, object); release_dentry: dput(object->dentry); object->dentry = NULL; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 5849b88..e48fd8b 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -977,13 +977,8 @@ out_unlock: /* * splice a dentry to an inode. * caller must hold directory i_mutex for this to be safe. - * - * we will only rehash the resulting dentry if @prehash is - * true; @prehash will be set to false (for the benefit of - * the caller) if we fail. */ -static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, - bool *prehash) +static struct dentry *splice_dentry(struct dentry *dn, struct inode *in) { struct dentry *realdn; @@ -996,8 +991,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, if (IS_ERR(realdn)) { pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n", PTR_ERR(realdn), dn, in, ceph_vinop(in)); - if (prehash) - *prehash = false; /* don't rehash on error */ dn = realdn; /* note realdn contains the error */ goto out; } else if (realdn) { @@ -1013,8 +1006,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, dout("dn %p attached to %p ino %llx.%llx\n", dn, d_inode(dn), ceph_vinop(d_inode(dn))); } - if ((!prehash || *prehash) && d_unhashed(dn)) - d_rehash(dn); out: return dn; } @@ -1247,10 +1238,8 @@ retry_lookup: dout("d_delete %p\n", dn); d_delete(dn); } else { - dout("d_instantiate %p NULL\n", dn); - d_instantiate(dn, NULL); if (have_lease && d_unhashed(dn)) - d_rehash(dn); + d_add(dn, NULL); update_dentry_lease(dn, rinfo->dlease, session, req->r_request_started); @@ -1262,7 +1251,7 @@ retry_lookup: if (d_really_is_negative(dn)) { ceph_dir_clear_ordered(dir); ihold(in); - dn = splice_dentry(dn, in, &have_lease); + dn = splice_dentry(dn, in); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; @@ -1292,7 +1281,7 @@ retry_lookup: dout(" linking snapped dir %p to dn %p\n", in, dn); ceph_dir_clear_ordered(dir); ihold(in); - dn = splice_dentry(dn, in, NULL); + dn = splice_dentry(dn, in); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; @@ -1503,7 +1492,7 @@ retry_lookup: } if (d_really_is_negative(dn)) { - struct dentry *realdn = splice_dentry(dn, in, NULL); + struct dentry *realdn = splice_dentry(dn, in); if (IS_ERR(realdn)) { err = PTR_ERR(realdn); d_drop(dn); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index fd8805d..1d86fc6 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -642,9 +642,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) while (*s && *s != sep) s++; - inode_lock(dir); - child = lookup_one_len(p, dentry, s - p); - inode_unlock(dir); + child = lookup_one_len_unlocked(p, dentry, s - p); dput(dentry); dentry = child; } while (!IS_ERR(dentry)); diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index b51ce67..ea59c89 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -432,14 +432,9 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den (sd->s_type & CONFIGFS_ITEM_BIN_ATTR) ? configfs_init_bin_file : configfs_init_file); - if (error) { + if (error) configfs_put(sd); - return error; - } - - d_rehash(dentry); - - return 0; + return error; } static struct dentry * configfs_lookup(struct inode *dir, diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 5f24ad3..03d124a 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -201,9 +201,17 @@ int configfs_create(struct dentry * dentry, umode_t mode, void (*init)(struct in configfs_set_inode_lock_class(sd, inode); init(inode); - d_instantiate(dentry, inode); - if (S_ISDIR(mode) || S_ISLNK(mode)) + if (S_ISDIR(mode) || S_ISLNK(mode)) { + /* + * ->symlink(), ->mkdir(), configfs_register_subsystem() or + * create_default_group() - already hashed. + */ + d_instantiate(dentry, inode); dget(dentry); /* pin link and directory dentries in core */ + } else { + /* ->lookup() */ + d_add(dentry, inode); + } return error; } diff --git a/fs/dcache.c b/fs/dcache.c index 2398f9f9..32ceae3 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1745,13 +1745,12 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) unsigned add_flags = d_flags_for_inode(inode); spin_lock(&dentry->d_lock); - if (inode) - hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); + hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); + __fsnotify_d_instantiate(dentry); spin_unlock(&dentry->d_lock); - fsnotify_d_instantiate(dentry, inode); } /** @@ -1772,91 +1771,16 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); - if (inode) + if (inode) { spin_lock(&inode->i_lock); - __d_instantiate(entry, inode); - if (inode) + __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); + } security_d_instantiate(entry, inode); } EXPORT_SYMBOL(d_instantiate); /** - * d_instantiate_unique - instantiate a non-aliased dentry - * @entry: dentry to instantiate - * @inode: inode to attach to this dentry - * - * Fill in inode information in the entry. On success, it returns NULL. - * If an unhashed alias of "entry" already exists, then we return the - * aliased dentry instead and drop one reference to inode. - * - * Note that in order to avoid conflicts with rename() etc, the caller - * had better be holding the parent directory semaphore. - * - * This also assumes that the inode count has been incremented - * (or otherwise set) by the caller to indicate that it is now - * in use by the dcache. - */ -static struct dentry *__d_instantiate_unique(struct dentry *entry, - struct inode *inode) -{ - struct dentry *alias; - int len = entry->d_name.len; - const char *name = entry->d_name.name; - unsigned int hash = entry->d_name.hash; - - if (!inode) { - __d_instantiate(entry, NULL); - return NULL; - } - - hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { - /* - * Don't need alias->d_lock here, because aliases with - * d_parent == entry->d_parent are not subject to name or - * parent changes, because the parent inode i_mutex is held. - */ - if (alias->d_name.hash != hash) - continue; - if (alias->d_parent != entry->d_parent) - continue; - if (alias->d_name.len != len) - continue; - if (dentry_cmp(alias, name, len)) - continue; - __dget(alias); - return alias; - } - - __d_instantiate(entry, inode); - return NULL; -} - -struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode) -{ - struct dentry *result; - - BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); - - if (inode) - spin_lock(&inode->i_lock); - result = __d_instantiate_unique(entry, inode); - if (inode) - spin_unlock(&inode->i_lock); - - if (!result) { - security_d_instantiate(entry, inode); - return NULL; - } - - BUG_ON(!d_unhashed(result)); - iput(inode); - return result; -} - -EXPORT_SYMBOL(d_instantiate_unique); - -/** * d_instantiate_no_diralias - instantiate a non-aliased dentry * @entry: dentry to complete * @inode: inode to attach to this dentry @@ -2436,6 +2360,86 @@ void d_rehash(struct dentry * entry) } EXPORT_SYMBOL(d_rehash); + +/* inode->i_lock held if inode is non-NULL */ + +static inline void __d_add(struct dentry *dentry, struct inode *inode) +{ + if (inode) { + __d_instantiate(dentry, inode); + spin_unlock(&inode->i_lock); + } + security_d_instantiate(dentry, inode); + d_rehash(dentry); +} + +/** + * d_add - add dentry to hash queues + * @entry: dentry to add + * @inode: The inode to attach to this dentry + * + * This adds the entry to the hash queues and initializes @inode. + * The entry was actually filled in earlier during d_alloc(). + */ + +void d_add(struct dentry *entry, struct inode *inode) +{ + if (inode) + spin_lock(&inode->i_lock); + __d_add(entry, inode); +} +EXPORT_SYMBOL(d_add); + +/** + * d_exact_alias - find and hash an exact unhashed alias + * @entry: dentry to add + * @inode: The inode to go with this dentry + * + * If an unhashed dentry with the same name/parent and desired + * inode already exists, hash and return it. Otherwise, return + * NULL. + * + * Parent directory should be locked. + */ +struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) +{ + struct dentry *alias; + int len = entry->d_name.len; + const char *name = entry->d_name.name; + unsigned int hash = entry->d_name.hash; + + spin_lock(&inode->i_lock); + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { + /* + * Don't need alias->d_lock here, because aliases with + * d_parent == entry->d_parent are not subject to name or + * parent changes, because the parent inode i_mutex is held. + */ + if (alias->d_name.hash != hash) + continue; + if (alias->d_parent != entry->d_parent) + continue; + if (alias->d_name.len != len) + continue; + if (dentry_cmp(alias, name, len)) + continue; + spin_lock(&alias->d_lock); + if (!d_unhashed(alias)) { + spin_unlock(&alias->d_lock); + alias = NULL; + } else { + __dget_dlock(alias); + _d_rehash(alias); + spin_unlock(&alias->d_lock); + } + spin_unlock(&inode->i_lock); + return alias; + } + spin_unlock(&inode->i_lock); + return NULL; +} +EXPORT_SYMBOL(d_exact_alias); + /** * dentry_update_name_case - update case insensitive dentry with a new name * @dentry: dentry to be updated @@ -2772,10 +2776,9 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) BUG_ON(!d_unhashed(dentry)); - if (!inode) { - __d_instantiate(dentry, NULL); + if (!inode) goto out; - } + spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); @@ -2809,12 +2812,8 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) return new; } } - /* already taking inode->i_lock, so d_add() by hand */ - __d_instantiate(dentry, inode); - spin_unlock(&inode->i_lock); out: - security_d_instantiate(dentry, inode); - d_rehash(dentry); + __d_add(dentry, inode); return NULL; } EXPORT_SYMBOL(d_splice_alias); diff --git a/fs/direct-io.c b/fs/direct-io.c index d6a9012..0a8d937 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -445,7 +445,8 @@ static struct bio *dio_await_one(struct dio *dio) __set_current_state(TASK_UNINTERRUPTIBLE); dio->waiter = current; spin_unlock_irqrestore(&dio->bio_lock, flags); - if (!blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie)) + if (!(dio->iocb->ki_flags & IOCB_HIPRI) || + !blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie)) io_schedule(); /* wake up sets us TASK_RUNNING */ spin_lock_irqsave(&dio->bio_lock, flags); diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 11255cb..64026e5 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1492,16 +1492,14 @@ out: */ static int ecryptfs_encrypt_filename(struct ecryptfs_filename *filename, - struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_mount_crypt_stat *mount_crypt_stat) { int rc = 0; filename->encrypted_filename = NULL; filename->encrypted_filename_size = 0; - if ((crypt_stat && (crypt_stat->flags & ECRYPTFS_ENCFN_USE_MOUNT_FNEK)) - || (mount_crypt_stat && (mount_crypt_stat->flags - & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))) { + if (mount_crypt_stat && (mount_crypt_stat->flags + & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) { size_t packet_size; size_t remaining_bytes; @@ -1933,7 +1931,6 @@ out: int ecryptfs_encrypt_and_encode_filename( char **encoded_name, size_t *encoded_name_size, - struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_mount_crypt_stat *mount_crypt_stat, const char *name, size_t name_size) { @@ -1942,9 +1939,8 @@ int ecryptfs_encrypt_and_encode_filename( (*encoded_name) = NULL; (*encoded_name_size) = 0; - if ((crypt_stat && (crypt_stat->flags & ECRYPTFS_ENCRYPT_FILENAMES)) - || (mount_crypt_stat && (mount_crypt_stat->flags - & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES))) { + if (mount_crypt_stat && (mount_crypt_stat->flags + & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) { struct ecryptfs_filename *filename; filename = kzalloc(sizeof(*filename), GFP_KERNEL); @@ -1957,8 +1953,7 @@ int ecryptfs_encrypt_and_encode_filename( } filename->filename = (char *)name; filename->filename_size = name_size; - rc = ecryptfs_encrypt_filename(filename, crypt_stat, - mount_crypt_stat); + rc = ecryptfs_encrypt_filename(filename, mount_crypt_stat); if (rc) { printk(KERN_ERR "%s: Error attempting to encrypt " "filename; rc = [%d]\n", __func__, rc); @@ -1969,11 +1964,9 @@ int ecryptfs_encrypt_and_encode_filename( NULL, &encoded_name_no_prefix_size, filename->encrypted_filename, filename->encrypted_filename_size); - if ((crypt_stat && (crypt_stat->flags - & ECRYPTFS_ENCFN_USE_MOUNT_FNEK)) - || (mount_crypt_stat + if (mount_crypt_stat && (mount_crypt_stat->flags - & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))) + & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) (*encoded_name_size) = (ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE + encoded_name_no_prefix_size); @@ -1991,11 +1984,9 @@ int ecryptfs_encrypt_and_encode_filename( kfree(filename); goto out; } - if ((crypt_stat && (crypt_stat->flags - & ECRYPTFS_ENCFN_USE_MOUNT_FNEK)) - || (mount_crypt_stat + if (mount_crypt_stat && (mount_crypt_stat->flags - & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))) { + & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) { memcpy((*encoded_name), ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index b7f8128..d123fba 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -569,7 +569,6 @@ int ecryptfs_fill_zeros(struct file *file, loff_t new_length); int ecryptfs_encrypt_and_encode_filename( char **encoded_name, size_t *encoded_name_size, - struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_mount_crypt_stat *mount_crypt_stat, const char *name, size_t name_size); struct dentry *ecryptfs_lower_dentry(struct dentry *this_dentry); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 0a8f1b4..121114e 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -396,11 +396,9 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, int rc = 0; lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent); - inode_lock(d_inode(lower_dir_dentry)); - lower_dentry = lookup_one_len(ecryptfs_dentry->d_name.name, + lower_dentry = lookup_one_len_unlocked(ecryptfs_dentry->d_name.name, lower_dir_dentry, ecryptfs_dentry->d_name.len); - inode_unlock(d_inode(lower_dir_dentry)); if (IS_ERR(lower_dentry)) { rc = PTR_ERR(lower_dentry); ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " @@ -418,18 +416,16 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, dput(lower_dentry); rc = ecryptfs_encrypt_and_encode_filename( &encrypted_and_encoded_name, &encrypted_and_encoded_name_size, - NULL, mount_crypt_stat, ecryptfs_dentry->d_name.name, + mount_crypt_stat, ecryptfs_dentry->d_name.name, ecryptfs_dentry->d_name.len); if (rc) { printk(KERN_ERR "%s: Error attempting to encrypt and encode " "filename; rc = [%d]\n", __func__, rc); goto out; } - inode_lock(d_inode(lower_dir_dentry)); - lower_dentry = lookup_one_len(encrypted_and_encoded_name, + lower_dentry = lookup_one_len_unlocked(encrypted_and_encoded_name, lower_dir_dentry, encrypted_and_encoded_name_size); - inode_unlock(d_inode(lower_dir_dentry)); if (IS_ERR(lower_dentry)) { rc = PTR_ERR(lower_dentry); ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " @@ -501,7 +497,6 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry, dir->i_sb)->mount_crypt_stat; rc = ecryptfs_encrypt_and_encode_filename(&encoded_symname, &encoded_symlen, - NULL, mount_crypt_stat, symname, strlen(symname)); if (rc) @@ -1220,8 +1220,8 @@ static int follow_managed(struct path *path, struct nameidata *nd) if (need_mntput && path->mnt == mnt) mntput(path->mnt); - if (ret == -EISDIR) - ret = 0; + if (ret == -EISDIR || !ret) + ret = 1; if (need_mntput) nd->flags |= LOOKUP_JUMPED; if (unlikely(ret < 0)) @@ -1444,40 +1444,26 @@ static int follow_dotdot(struct nameidata *nd) * This looks up the name in dcache, possibly revalidates the old dentry and * allocates a new one if not found or not valid. In the need_lookup argument * returns whether i_op->lookup is necessary. - * - * dir->d_inode->i_mutex must be held */ -static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir, - unsigned int flags, bool *need_lookup) +static struct dentry *lookup_dcache(const struct qstr *name, + struct dentry *dir, + unsigned int flags) { struct dentry *dentry; int error; - *need_lookup = false; dentry = d_lookup(dir, name); if (dentry) { if (dentry->d_flags & DCACHE_OP_REVALIDATE) { error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { - if (error < 0) { - dput(dentry); - return ERR_PTR(error); - } else { + if (!error) d_invalidate(dentry); - dput(dentry); - dentry = NULL; - } + dput(dentry); + return ERR_PTR(error); } } } - - if (!dentry) { - dentry = d_alloc(dir, name); - if (unlikely(!dentry)) - return ERR_PTR(-ENOMEM); - - *need_lookup = true; - } return dentry; } @@ -1506,45 +1492,44 @@ static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry, return dentry; } -static struct dentry *__lookup_hash(struct qstr *name, +static struct dentry *__lookup_hash(const struct qstr *name, struct dentry *base, unsigned int flags) { - bool need_lookup; - struct dentry *dentry; + struct dentry *dentry = lookup_dcache(name, base, flags); - dentry = lookup_dcache(name, base, flags, &need_lookup); - if (!need_lookup) + if (dentry) return dentry; + dentry = d_alloc(base, name); + if (unlikely(!dentry)) + return ERR_PTR(-ENOMEM); + return lookup_real(base->d_inode, dentry, flags); } -/* - * It's more convoluted than I'd like it to be, but... it's still fairly - * small and for now I'd prefer to have fast path as straight as possible. - * It _is_ time-critical. - */ static int lookup_fast(struct nameidata *nd, struct path *path, struct inode **inode, unsigned *seqp) { struct vfsmount *mnt = nd->path.mnt; struct dentry *dentry, *parent = nd->path.dentry; - int need_reval = 1; int status = 1; int err; /* * Rename seqlock is not required here because in the off chance - * of a false negative due to a concurrent rename, we're going to - * do the non-racy lookup, below. + * of a false negative due to a concurrent rename, the caller is + * going to fall back to non-racy lookup. */ if (nd->flags & LOOKUP_RCU) { unsigned seq; bool negative; dentry = __d_lookup_rcu(parent, &nd->last, &seq); - if (!dentry) - goto unlazy; + if (unlikely(!dentry)) { + if (unlazy_walk(nd, NULL, 0)) + return -ECHILD; + return 0; + } /* * This sequence count validates that the inode matches @@ -1552,7 +1537,7 @@ static int lookup_fast(struct nameidata *nd, */ *inode = d_backing_inode(dentry); negative = d_is_negative(dentry); - if (read_seqcount_retry(&dentry->d_seq, seq)) + if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) return -ECHILD; /* @@ -1562,81 +1547,89 @@ static int lookup_fast(struct nameidata *nd, * The memory barrier in read_seqcount_begin of child is * enough, we can use __read_seqcount_retry here. */ - if (__read_seqcount_retry(&parent->d_seq, nd->seq)) + if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq))) return -ECHILD; *seqp = seq; - if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) { + if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) status = d_revalidate(dentry, nd->flags); - if (unlikely(status <= 0)) { - if (status != -ECHILD) - need_reval = 0; - goto unlazy; - } + if (unlikely(status <= 0)) { + if (unlazy_walk(nd, dentry, seq)) + return -ECHILD; + if (status == -ECHILD) + status = d_revalidate(dentry, nd->flags); + } else { + /* + * Note: do negative dentry check after revalidation in + * case that drops it. + */ + if (unlikely(negative)) + return -ENOENT; + path->mnt = mnt; + path->dentry = dentry; + if (likely(__follow_mount_rcu(nd, path, inode, seqp))) + return 1; + if (unlazy_walk(nd, dentry, seq)) + return -ECHILD; } - /* - * Note: do negative dentry check after revalidation in - * case that drops it. - */ - if (negative) - return -ENOENT; - path->mnt = mnt; - path->dentry = dentry; - if (likely(__follow_mount_rcu(nd, path, inode, seqp))) - return 0; -unlazy: - if (unlazy_walk(nd, dentry, seq)) - return -ECHILD; } else { dentry = __d_lookup(parent, &nd->last); + if (unlikely(!dentry)) + return 0; + if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) + status = d_revalidate(dentry, nd->flags); } - - if (unlikely(!dentry)) - goto need_lookup; - - if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval) - status = d_revalidate(dentry, nd->flags); if (unlikely(status <= 0)) { - if (status < 0) { - dput(dentry); - return status; - } - d_invalidate(dentry); + if (!status) + d_invalidate(dentry); dput(dentry); - goto need_lookup; + return status; } - if (unlikely(d_is_negative(dentry))) { dput(dentry); return -ENOENT; } + path->mnt = mnt; path->dentry = dentry; err = follow_managed(path, nd); - if (likely(!err)) + if (likely(err > 0)) *inode = d_backing_inode(path->dentry); return err; - -need_lookup: - return 1; } /* Fast lookup failed, do it the slow way */ -static int lookup_slow(struct nameidata *nd, struct path *path) +static struct dentry *lookup_slow(const struct qstr *name, + struct dentry *dir, + unsigned int flags) { - struct dentry *dentry, *parent; - - parent = nd->path.dentry; - BUG_ON(nd->inode != parent->d_inode); - - inode_lock(parent->d_inode); - dentry = __lookup_hash(&nd->last, parent, nd->flags); - inode_unlock(parent->d_inode); - if (IS_ERR(dentry)) - return PTR_ERR(dentry); - path->mnt = nd->path.mnt; - path->dentry = dentry; - return follow_managed(path, nd); + struct dentry *dentry; + inode_lock(dir->d_inode); + dentry = d_lookup(dir, name); + if (unlikely(dentry)) { + if ((dentry->d_flags & DCACHE_OP_REVALIDATE) && + !(flags & LOOKUP_NO_REVAL)) { + int error = d_revalidate(dentry, flags); + if (unlikely(error <= 0)) { + if (!error) + d_invalidate(dentry); + dput(dentry); + dentry = ERR_PTR(error); + } + } + if (dentry) { + inode_unlock(dir->d_inode); + return dentry; + } + } + dentry = d_alloc(dir, name); + if (unlikely(!dentry)) { + inode_unlock(dir->d_inode); + return ERR_PTR(-ENOMEM); + } + dentry = lookup_real(dir->d_inode, dentry, flags); + inode_unlock(dir->d_inode); + return dentry; } static inline int may_lookup(struct nameidata *nd) @@ -1740,18 +1733,23 @@ static int walk_component(struct nameidata *nd, int flags) return err; } err = lookup_fast(nd, &path, &inode, &seq); - if (unlikely(err)) { + if (unlikely(err <= 0)) { if (err < 0) return err; - - err = lookup_slow(nd, &path); - if (err < 0) + path.dentry = lookup_slow(&nd->last, nd->path.dentry, + nd->flags); + if (IS_ERR(path.dentry)) + return PTR_ERR(path.dentry); + if (unlikely(d_is_negative(path.dentry))) { + dput(path.dentry); + return -ENOENT; + } + path.mnt = nd->path.mnt; + err = follow_managed(&path, nd); + if (unlikely(err < 0)) return err; seq = 0; /* we are already out of RCU mode */ - err = -ENOENT; - if (d_is_negative(path.dentry)) - goto out_path_put; inode = d_backing_inode(path.dentry); } @@ -1764,10 +1762,6 @@ static int walk_component(struct nameidata *nd, int flags) nd->inode = inode; nd->seq = seq; return 0; - -out_path_put: - path_to_nameidata(&path, nd); - return err; } /* @@ -2373,21 +2367,9 @@ struct dentry *lookup_one_len_unlocked(const char *name, if (err) return ERR_PTR(err); - /* - * __d_lookup() is used to try to get a quick answer and avoid the - * mutex. A false-negative does no harm. - */ - ret = __d_lookup(base, &this); - if (ret && unlikely(ret->d_flags & DCACHE_OP_REVALIDATE)) { - dput(ret); - ret = NULL; - } - if (ret) - return ret; - - inode_lock(base->d_inode); - ret = __lookup_hash(&this, base, 0); - inode_unlock(base->d_inode); + ret = lookup_dcache(&this, base, 0); + if (!ret) + ret = lookup_slow(&this, base, 0); return ret; } EXPORT_SYMBOL(lookup_one_len_unlocked); @@ -2465,31 +2447,21 @@ mountpoint_last(struct nameidata *nd, struct path *path) if (error) return error; dentry = dget(nd->path.dentry); - goto done; - } - - inode_lock(dir->d_inode); - dentry = d_lookup(dir, &nd->last); - if (!dentry) { - /* - * No cached dentry. Mounted dentries are pinned in the cache, - * so that means that this dentry is probably a symlink or the - * path doesn't actually point to a mounted dentry. - */ - dentry = d_alloc(dir, &nd->last); + } else { + dentry = d_lookup(dir, &nd->last); if (!dentry) { - inode_unlock(dir->d_inode); - return -ENOMEM; - } - dentry = lookup_real(dir->d_inode, dentry, nd->flags); - if (IS_ERR(dentry)) { - inode_unlock(dir->d_inode); - return PTR_ERR(dentry); + /* + * No cached dentry. Mounted dentries are pinned in the + * cache, so that means that this dentry is probably + * a symlink or the path doesn't actually point + * to a mounted dentry. + */ + dentry = lookup_slow(&nd->last, dir, + nd->flags | LOOKUP_NO_REVAL); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); } } - inode_unlock(dir->d_inode); - -done: if (d_is_negative(dentry)) { dput(dentry); return -ENOENT; @@ -3018,16 +2990,22 @@ static int lookup_open(struct nameidata *nd, struct path *path, struct inode *dir_inode = dir->d_inode; struct dentry *dentry; int error; - bool need_lookup; + bool need_lookup = false; *opened &= ~FILE_CREATED; - dentry = lookup_dcache(&nd->last, dir, nd->flags, &need_lookup); + dentry = lookup_dcache(&nd->last, dir, nd->flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); - /* Cached positive dentry: will open in f_op->open */ - if (!need_lookup && dentry->d_inode) + if (!dentry) { + dentry = d_alloc(dir, &nd->last); + if (unlikely(!dentry)) + return -ENOMEM; + need_lookup = true; + } else if (dentry->d_inode) { + /* Cached positive dentry: will open in f_op->open */ goto out_no_open; + } if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) { return atomic_open(nd, dentry, path, file, op, got_write, @@ -3111,13 +3089,14 @@ static int do_last(struct nameidata *nd, nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; /* we _can_ be in RCU mode here */ error = lookup_fast(nd, &path, &inode, &seq); - if (likely(!error)) + if (likely(error > 0)) goto finish_lookup; if (error < 0) return error; BUG_ON(nd->inode != dir->d_inode); + BUG_ON(nd->flags & LOOKUP_RCU); } else { /* create side of things */ /* @@ -3172,12 +3151,6 @@ retry_lookup: } /* - * create/update audit record if it already exists. - */ - if (d_is_positive(path.dentry)) - audit_inode(nd->name, path.dentry, 0); - - /* * If atomic_open() acquired write access it is dropped now due to * possible mount and symlink following (this might be optimized away if * necessary...) @@ -3187,6 +3160,16 @@ retry_lookup: got_write = false; } + if (unlikely(d_is_negative(path.dentry))) { + path_to_nameidata(&path, nd); + return -ENOENT; + } + + /* + * create/update audit record if it already exists. + */ + audit_inode(nd->name, path.dentry, 0); + if (unlikely((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))) { path_to_nameidata(&path, nd); return -EEXIST; @@ -3196,12 +3179,7 @@ retry_lookup: if (unlikely(error < 0)) return error; - BUG_ON(nd->flags & LOOKUP_RCU); seq = 0; /* out of RCU mode, so the value doesn't matter */ - if (unlikely(d_is_negative(path.dentry))) { - path_to_nameidata(&path, nd); - return -ENOENT; - } inode = d_backing_inode(path.dentry); finish_lookup: if (nd->depth) @@ -3707,31 +3685,6 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) return sys_mkdirat(AT_FDCWD, pathname, mode); } -/* - * The dentry_unhash() helper will try to drop the dentry early: we - * should have a usage count of 1 if we're the only user of this - * dentry, and if that is true (possibly after pruning the dcache), - * then we drop the dentry now. - * - * A low-level filesystem can, if it choses, legally - * do a - * - * if (!d_unhashed(dentry)) - * return -EBUSY; - * - * if it cannot handle the case of removing a directory - * that is still in use by something else.. - */ -void dentry_unhash(struct dentry *dentry) -{ - shrink_dcache_parent(dentry); - spin_lock(&dentry->d_lock); - if (dentry->d_lockref.count == 1) - __d_drop(dentry); - spin_unlock(&dentry->d_lock); -} -EXPORT_SYMBOL(dentry_unhash); - int vfs_rmdir(struct inode *dir, struct dentry *dentry) { int error = may_delete(dir, dentry, 1); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 9cce670..4bfa7d8 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1360,19 +1360,15 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in dfprintk(VFS, "NFS: lookup(%pd2)\n", dentry); nfs_inc_stats(dir, NFSIOS_VFSLOOKUP); - res = ERR_PTR(-ENAMETOOLONG); - if (dentry->d_name.len > NFS_SERVER(dir)->namelen) - goto out; + if (unlikely(dentry->d_name.len > NFS_SERVER(dir)->namelen)) + return ERR_PTR(-ENAMETOOLONG); /* * If we're doing an exclusive create, optimize away the lookup * but don't hash the dentry. */ - if (nfs_is_exclusive_create(dir, flags)) { - d_instantiate(dentry, NULL); - res = NULL; - goto out; - } + if (nfs_is_exclusive_create(dir, flags)) + return NULL; res = ERR_PTR(-ENOMEM); fhandle = nfs_alloc_fhandle(); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 1488159..400a70b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2461,14 +2461,15 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dentry = opendata->dentry; if (d_really_is_negative(dentry)) { - /* FIXME: Is this d_drop() ever needed? */ + struct dentry *alias; d_drop(dentry); - dentry = d_add_unique(dentry, igrab(state->inode)); - if (dentry == NULL) { - dentry = opendata->dentry; - } else { + alias = d_exact_alias(dentry, state->inode); + if (!alias) + alias = d_splice_alias(igrab(state->inode), dentry); + /* d_splice_alias() can't fail here - it's a non-directory */ + if (alias) { dput(ctx->dentry); - ctx->dentry = dentry; + ctx->dentry = dentry = alias; } nfs_set_verifier(dentry, nfs_save_change_attribute(d_inode(opendata->dir))); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 5d2a57e..d40010e 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -870,7 +870,7 @@ __be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen, oldfs = get_fs(); set_fs(KERNEL_DS); - host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset); + host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset, 0); set_fs(oldfs); return nfsd_finish_read(file, count, host_err); } @@ -957,7 +957,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, /* Write the data. */ oldfs = get_fs(); set_fs(KERNEL_DS); - host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos); + host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, 0); set_fs(oldfs); if (host_err < 0) goto out_nfserr; diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 2256e7e..3f1190d 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -199,6 +199,8 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) if (sb->s_op->show_devname) { seq_puts(m, "device "); err = sb->s_op->show_devname(m, mnt_path.dentry); + if (err) + goto out; } else { if (r->mnt_devname) { seq_puts(m, "device "); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 3c3b81b..04ca0cc 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2430,9 +2430,7 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name, struct dentry *dentry; int error; - inode_lock(d_inode(sb->s_root)); - dentry = lookup_one_len(qf_name, sb->s_root, strlen(qf_name)); - inode_unlock(d_inode(sb->s_root)); + dentry = lookup_one_len_unlocked(qf_name, sb->s_root, strlen(qf_name)); if (IS_ERR(dentry)) return PTR_ERR(dentry); diff --git a/fs/read_write.c b/fs/read_write.c index dadf24e..cf377cf 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -693,12 +693,17 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) EXPORT_SYMBOL(iov_shorten); static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, iter_fn_t fn) + loff_t *ppos, iter_fn_t fn, int flags) { struct kiocb kiocb; ssize_t ret; + if (flags & ~RWF_HIPRI) + return -EOPNOTSUPP; + init_sync_kiocb(&kiocb, filp); + if (flags & RWF_HIPRI) + kiocb.ki_flags |= IOCB_HIPRI; kiocb.ki_pos = *ppos; ret = fn(&kiocb, iter); @@ -709,10 +714,13 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, io_fn_t fn) + loff_t *ppos, io_fn_t fn, int flags) { ssize_t ret = 0; + if (flags & ~RWF_HIPRI) + return -EOPNOTSUPP; + while (iov_iter_count(iter)) { struct iovec iovec = iov_iter_iovec(iter); ssize_t nr; @@ -813,7 +821,8 @@ out: static ssize_t do_readv_writev(int type, struct file *file, const struct iovec __user * uvector, - unsigned long nr_segs, loff_t *pos) + unsigned long nr_segs, loff_t *pos, + int flags) { size_t tot_len; struct iovec iovstack[UIO_FASTIOV]; @@ -845,9 +854,9 @@ static ssize_t do_readv_writev(int type, struct file *file, } if (iter_fn) - ret = do_iter_readv_writev(file, &iter, pos, iter_fn); + ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags); else - ret = do_loop_readv_writev(file, &iter, pos, fn); + ret = do_loop_readv_writev(file, &iter, pos, fn, flags); if (type != READ) file_end_write(file); @@ -864,40 +873,40 @@ out: } ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos) + unsigned long vlen, loff_t *pos, int flags) { if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; - return do_readv_writev(READ, file, vec, vlen, pos); + return do_readv_writev(READ, file, vec, vlen, pos, flags); } EXPORT_SYMBOL(vfs_readv); ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos) + unsigned long vlen, loff_t *pos, int flags) { if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; - return do_readv_writev(WRITE, file, vec, vlen, pos); + return do_readv_writev(WRITE, file, vec, vlen, pos, flags); } EXPORT_SYMBOL(vfs_writev); -SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen) +static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, int flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos = file_pos_read(f.file); - ret = vfs_readv(f.file, vec, vlen, &pos); + ret = vfs_readv(f.file, vec, vlen, &pos, flags); if (ret >= 0) file_pos_write(f.file, pos); fdput_pos(f); @@ -909,15 +918,15 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, return ret; } -SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen) +static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, int flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos = file_pos_read(f.file); - ret = vfs_writev(f.file, vec, vlen, &pos); + ret = vfs_writev(f.file, vec, vlen, &pos, flags); if (ret >= 0) file_pos_write(f.file, pos); fdput_pos(f); @@ -935,10 +944,9 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } -SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) +static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, loff_t pos, int flags) { - loff_t pos = pos_from_hilo(pos_h, pos_l); struct fd f; ssize_t ret = -EBADF; @@ -949,7 +957,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) - ret = vfs_readv(f.file, vec, vlen, &pos); + ret = vfs_readv(f.file, vec, vlen, &pos, flags); fdput(f); } @@ -959,10 +967,9 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, return ret; } -SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) +static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, loff_t pos, int flags) { - loff_t pos = pos_from_hilo(pos_h, pos_l); struct fd f; ssize_t ret = -EBADF; @@ -973,7 +980,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) - ret = vfs_writev(f.file, vec, vlen, &pos); + ret = vfs_writev(f.file, vec, vlen, &pos, flags); fdput(f); } @@ -983,11 +990,64 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, return ret; } +SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen) +{ + return do_readv(fd, vec, vlen, 0); +} + +SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen) +{ + return do_writev(fd, vec, vlen, 0); +} + +SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) +{ + loff_t pos = pos_from_hilo(pos_h, pos_l); + + return do_preadv(fd, vec, vlen, pos, 0); +} + +SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, + int, flags) +{ + loff_t pos = pos_from_hilo(pos_h, pos_l); + + if (pos == -1) + return do_readv(fd, vec, vlen, flags); + + return do_preadv(fd, vec, vlen, pos, flags); +} + +SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) +{ + loff_t pos = pos_from_hilo(pos_h, pos_l); + + return do_pwritev(fd, vec, vlen, pos, 0); +} + +SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, + int, flags) +{ + loff_t pos = pos_from_hilo(pos_h, pos_l); + + if (pos == -1) + return do_writev(fd, vec, vlen, flags); + + return do_pwritev(fd, vec, vlen, pos, flags); +} + #ifdef CONFIG_COMPAT static ssize_t compat_do_readv_writev(int type, struct file *file, const struct compat_iovec __user *uvector, - unsigned long nr_segs, loff_t *pos) + unsigned long nr_segs, loff_t *pos, + int flags) { compat_ssize_t tot_len; struct iovec iovstack[UIO_FASTIOV]; @@ -1019,9 +1079,9 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, } if (iter_fn) - ret = do_iter_readv_writev(file, &iter, pos, iter_fn); + ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags); else - ret = do_loop_readv_writev(file, &iter, pos, fn); + ret = do_loop_readv_writev(file, &iter, pos, fn, flags); if (type != READ) file_end_write(file); @@ -1039,7 +1099,7 @@ out: static size_t compat_readv(struct file *file, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos) + unsigned long vlen, loff_t *pos, int flags) { ssize_t ret = -EBADF; @@ -1050,7 +1110,7 @@ static size_t compat_readv(struct file *file, if (!(file->f_mode & FMODE_CAN_READ)) goto out; - ret = compat_do_readv_writev(READ, file, vec, vlen, pos); + ret = compat_do_readv_writev(READ, file, vec, vlen, pos, flags); out: if (ret > 0) @@ -1059,9 +1119,9 @@ out: return ret; } -COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, - const struct compat_iovec __user *,vec, - compat_ulong_t, vlen) +static size_t do_compat_readv(compat_ulong_t fd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, int flags) { struct fd f = fdget_pos(fd); ssize_t ret; @@ -1070,16 +1130,24 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, if (!f.file) return -EBADF; pos = f.file->f_pos; - ret = compat_readv(f.file, vec, vlen, &pos); + ret = compat_readv(f.file, vec, vlen, &pos, flags); if (ret >= 0) f.file->f_pos = pos; fdput_pos(f); return ret; + +} + +COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, + const struct compat_iovec __user *,vec, + compat_ulong_t, vlen) +{ + return do_compat_readv(fd, vec, vlen, 0); } -static long __compat_sys_preadv64(unsigned long fd, +static long do_compat_preadv64(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos) + unsigned long vlen, loff_t pos, int flags) { struct fd f; ssize_t ret; @@ -1091,7 +1159,7 @@ static long __compat_sys_preadv64(unsigned long fd, return -EBADF; ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) - ret = compat_readv(f.file, vec, vlen, &pos); + ret = compat_readv(f.file, vec, vlen, &pos, flags); fdput(f); return ret; } @@ -1101,7 +1169,7 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct compat_iovec __user *,vec, unsigned long, vlen, loff_t, pos) { - return __compat_sys_preadv64(fd, vec, vlen, pos); + return do_compat_preadv64(fd, vec, vlen, pos, 0); } #endif @@ -1111,12 +1179,25 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, { loff_t pos = ((loff_t)pos_high << 32) | pos_low; - return __compat_sys_preadv64(fd, vec, vlen, pos); + return do_compat_preadv64(fd, vec, vlen, pos, 0); +} + +COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, + const struct compat_iovec __user *,vec, + compat_ulong_t, vlen, u32, pos_low, u32, pos_high, + int, flags) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + + if (pos == -1) + return do_compat_readv(fd, vec, vlen, flags); + + return do_compat_preadv64(fd, vec, vlen, pos, flags); } static size_t compat_writev(struct file *file, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos) + unsigned long vlen, loff_t *pos, int flags) { ssize_t ret = -EBADF; @@ -1127,7 +1208,7 @@ static size_t compat_writev(struct file *file, if (!(file->f_mode & FMODE_CAN_WRITE)) goto out; - ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos); + ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, 0); out: if (ret > 0) @@ -1136,9 +1217,9 @@ out: return ret; } -COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, - const struct compat_iovec __user *, vec, - compat_ulong_t, vlen) +static size_t do_compat_writev(compat_ulong_t fd, + const struct compat_iovec __user* vec, + compat_ulong_t vlen, int flags) { struct fd f = fdget_pos(fd); ssize_t ret; @@ -1147,16 +1228,23 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, if (!f.file) return -EBADF; pos = f.file->f_pos; - ret = compat_writev(f.file, vec, vlen, &pos); + ret = compat_writev(f.file, vec, vlen, &pos, flags); if (ret >= 0) f.file->f_pos = pos; fdput_pos(f); return ret; } -static long __compat_sys_pwritev64(unsigned long fd, +COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, + const struct compat_iovec __user *, vec, + compat_ulong_t, vlen) +{ + return do_compat_writev(fd, vec, vlen, 0); +} + +static long do_compat_pwritev64(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos) + unsigned long vlen, loff_t pos, int flags) { struct fd f; ssize_t ret; @@ -1168,7 +1256,7 @@ static long __compat_sys_pwritev64(unsigned long fd, return -EBADF; ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) - ret = compat_writev(f.file, vec, vlen, &pos); + ret = compat_writev(f.file, vec, vlen, &pos, flags); fdput(f); return ret; } @@ -1178,7 +1266,7 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct compat_iovec __user *,vec, unsigned long, vlen, loff_t, pos) { - return __compat_sys_pwritev64(fd, vec, vlen, pos); + return do_compat_pwritev64(fd, vec, vlen, pos, 0); } #endif @@ -1188,8 +1276,21 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, { loff_t pos = ((loff_t)pos_high << 32) | pos_low; - return __compat_sys_pwritev64(fd, vec, vlen, pos); + return do_compat_pwritev64(fd, vec, vlen, pos, 0); +} + +COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, + const struct compat_iovec __user *,vec, + compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + + if (pos == -1) + return do_compat_writev(fd, vec, vlen, flags); + + return do_compat_pwritev64(fd, vec, vlen, pos, flags); } + #endif static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, diff --git a/fs/splice.c b/fs/splice.c index 82bc0d6..9947b5c 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -185,6 +185,9 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, unsigned int spd_pages = spd->nr_pages; int ret, do_wakeup, page_nr; + if (!spd_pages) + return 0; + ret = 0; do_wakeup = 0; page_nr = 0; @@ -577,7 +580,7 @@ static ssize_t kernel_readv(struct file *file, const struct iovec *vec, old_fs = get_fs(); set_fs(get_ds()); /* The cast to a user pointer is valid due to the set_fs() */ - res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos); + res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0); set_fs(old_fs); return res; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8a11b69..7e5d7e0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -499,7 +499,8 @@ struct request_queue { #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ - (1 << QUEUE_FLAG_SAME_COMP)) + (1 << QUEUE_FLAG_SAME_COMP) | \ + (1 << QUEUE_FLAG_POLL)) static inline void queue_lockdep_assert_held(struct request_queue *q) { diff --git a/include/linux/compat.h b/include/linux/compat.h index a76c917..fe4ccd0 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -340,6 +340,12 @@ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, const struct compat_iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); +asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); +asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c4b5f4b..1c51d2d 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -246,6 +246,7 @@ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); +extern struct dentry * d_exact_alias(struct dentry *, struct inode *); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); @@ -272,38 +273,8 @@ extern int have_submounts(struct dentry *); * This adds the entry to the hash queues. */ extern void d_rehash(struct dentry *); - -/** - * d_add - add dentry to hash queues - * @entry: dentry to add - * @inode: The inode to attach to this dentry - * - * This adds the entry to the hash queues and initializes @inode. - * The entry was actually filled in earlier during d_alloc(). - */ -static inline void d_add(struct dentry *entry, struct inode *inode) -{ - d_instantiate(entry, inode); - d_rehash(entry); -} - -/** - * d_add_unique - add dentry to hash queues without aliasing - * @entry: dentry to add - * @inode: The inode to attach to this dentry - * - * This adds the entry to the hash queues and initializes @inode. - * The entry was actually filled in earlier during d_alloc(). - */ -static inline struct dentry *d_add_unique(struct dentry *entry, struct inode *inode) -{ - struct dentry *res; - - res = d_instantiate_unique(entry, inode); - d_rehash(res != NULL ? res : entry); - return res; -} +extern void d_add(struct dentry *, struct inode *); extern void dentry_update_name_case(struct dentry *, struct qstr *); diff --git a/include/linux/fs.h b/include/linux/fs.h index e514f76..bb703ef 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -320,6 +320,7 @@ struct writeback_control; #define IOCB_EVENTFD (1 << 0) #define IOCB_APPEND (1 << 1) #define IOCB_DIRECT (1 << 2) +#define IOCB_HIPRI (1 << 3) struct kiocb { struct file *ki_filp; @@ -1540,11 +1541,6 @@ extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct de extern int vfs_whiteout(struct inode *, struct dentry *); /* - * VFS dentry helper functions. - */ -extern void dentry_unhash(struct dentry *dentry); - -/* * VFS file helper functions. */ extern void inode_init_owner(struct inode *inode, const struct inode *dir, @@ -1709,9 +1705,9 @@ extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *) extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, - unsigned long, loff_t *); + unsigned long, loff_t *, int); extern ssize_t vfs_writev(struct file *, const struct iovec __user *, - unsigned long, loff_t *); + unsigned long, loff_t *, int); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 7ee1774..0141f25 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -16,15 +16,6 @@ #include <linux/slab.h> #include <linux/bug.h> -/* - * fsnotify_d_instantiate - instantiate a dentry for inode - */ -static inline void fsnotify_d_instantiate(struct dentry *dentry, - struct inode *inode) -{ - __fsnotify_d_instantiate(dentry, inode); -} - /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) { diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 533c440..1259e53 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -290,14 +290,9 @@ static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) /* * fsnotify_d_instantiate - instantiate a dentry for inode */ -static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode) +static inline void __fsnotify_d_instantiate(struct dentry *dentry) { - if (!inode) - return; - - spin_lock(&dentry->d_lock); __fsnotify_update_dcache_flags(dentry); - spin_unlock(&dentry->d_lock); } /* called from fsnotify listeners, such as fanotify or dnotify */ @@ -396,7 +391,7 @@ static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) {} -static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode) +static inline void __fsnotify_d_instantiate(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) diff --git a/include/linux/namei.h b/include/linux/namei.h index d0f25d8..77d0170 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -31,6 +31,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_PARENT 0x0010 #define LOOKUP_REVAL 0x0020 #define LOOKUP_RCU 0x0040 +#define LOOKUP_NO_REVAL 0x0080 /* * Intent data diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 185815c..d795472 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -575,8 +575,14 @@ asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); +asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, unsigned long pos_l, unsigned long pos_h, + int flags); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); +asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, unsigned long pos_l, unsigned long pos_h, + int flags); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode); asmlinkage long sys_chdir(const char __user *filename); diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 149bec8..d246339 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -304,4 +304,7 @@ struct fsxattr { #define SYNC_FILE_RANGE_WRITE 2 #define SYNC_FILE_RANGE_WAIT_AFTER 4 +/* flags for preadv2/pwritev2: */ +#define RWF_HIPRI 0x00000001 /* high priority request, poll if possible */ + #endif /* _UAPI_LINUX_FS_H */ |
