diff options
Diffstat (limited to 'fs')
52 files changed, 419 insertions, 335 deletions
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 1feb68ecef95..842d00048a65 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -94,25 +94,21 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev, { struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb); struct list_head *next; - struct dentry *p, *q; + struct dentry *q; spin_lock(&sbi->lookup_lock); + spin_lock(&root->d_lock); - if (prev == NULL) { - spin_lock(&root->d_lock); + if (prev) + next = prev->d_u.d_child.next; + else { prev = dget_dlock(root); next = prev->d_subdirs.next; - p = prev; - goto start; } - p = prev; - spin_lock(&p->d_lock); -again: - next = p->d_u.d_child.next; -start: +cont: if (next == &root->d_subdirs) { - spin_unlock(&p->d_lock); + spin_unlock(&root->d_lock); spin_unlock(&sbi->lookup_lock); dput(prev); return NULL; @@ -121,16 +117,15 @@ start: q = list_entry(next, struct dentry, d_u.d_child); spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED); - /* Negative dentry - try next */ - if (!simple_positive(q)) { - spin_unlock(&p->d_lock); - lock_set_subclass(&q->d_lock.dep_map, 0, _RET_IP_); - p = q; - goto again; + /* Already gone or negative dentry (under construction) - try next */ + if (q->d_count == 0 || !simple_positive(q)) { + spin_unlock(&q->d_lock); + next = q->d_u.d_child.next; + goto cont; } dget_dlock(q); spin_unlock(&q->d_lock); - spin_unlock(&p->d_lock); + spin_unlock(&root->d_lock); spin_unlock(&sbi->lookup_lock); dput(prev); @@ -404,11 +399,6 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, DPRINTK("checking mountpoint %p %.*s", dentry, (int)dentry->d_name.len, dentry->d_name.name); - /* Path walk currently on this dentry? */ - ino_count = atomic_read(&ino->count) + 2; - if (dentry->d_count > ino_count) - goto next; - /* Can we umount this guy */ if (autofs4_mount_busy(mnt, dentry)) goto next; @@ -1312,7 +1312,7 @@ EXPORT_SYMBOL(bio_copy_kern); * Note that this code is very hard to test under normal circumstances because * direct-io pins the pages with get_user_pages(). This makes * is_page_cache_freeable return false, and the VM will not clean the pages. - * But other code (eg, pdflush) could clean the pages if they are mapped + * But other code (eg, flusher threads) could clean the pages if they are mapped * pagecache. * * Simply disabling the call to bio_set_pages_dirty() is a good way to test the diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 83baec24946d..6e8f416773d4 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -324,7 +324,8 @@ static noinline int add_async_extent(struct async_cow *cow, * If this code finds it can't get good compression, it puts an * entry onto the work queue to write the uncompressed bytes. This * makes sure that both compressed inodes and uncompressed inodes - * are written in the same order that pdflush sent them down. + * are written in the same order that the flusher thread sent them + * down. */ static noinline int compress_file_range(struct inode *inode, struct page *locked_page, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index bc2f6ffff3cf..7bb755677a22 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -664,10 +664,6 @@ static noinline int btrfs_mksubvol(struct path *parent, struct dentry *dentry; int error; - error = mnt_want_write(parent->mnt); - if (error) - return error; - mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); dentry = lookup_one_len(name, parent->dentry, namelen); @@ -703,7 +699,6 @@ out_dput: dput(dentry); out_unlock: mutex_unlock(&dir->i_mutex); - mnt_drop_write(parent->mnt); return error; } diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 643335a4fe3c..051c7fe551dd 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -596,7 +596,7 @@ void btrfs_start_ordered_extent(struct inode *inode, /* * pages in the range can be dirty, clean or writeback. We * start IO on any dirty ones so the wait doesn't stall waiting - * for pdflush to find them + * for the flusher thread to find them */ if (!test_bit(BTRFS_ORDERED_DIRECT, &entry->flags)) filemap_fdatawrite_range(inode->i_mapping, start, end); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8c6e61d6eed5..f2eb24c477a3 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -100,10 +100,6 @@ static void __save_error_info(struct btrfs_fs_info *fs_info) fs_info->fs_state = BTRFS_SUPER_FLAG_ERROR; } -/* NOTE: - * We move write_super stuff at umount in order to avoid deadlock - * for umount hold all lock. - */ static void save_error_info(struct btrfs_fs_info *fs_info) { __save_error_info(fs_info); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b8708f994e67..e86ae04abe6a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1744,10 +1744,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) device->fs_devices = root->fs_info->fs_devices; - /* - * we don't want write_supers to jump in here with our device - * half setup - */ mutex_lock(&root->fs_info->fs_devices->device_list_mutex); list_add_rcu(&device->dev_list, &root->fs_info->fs_devices->devices); list_add(&device->dev_alloc_list, diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index fb962efdacee..6d59006bfa27 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -201,6 +201,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc) int err = -ENOMEM; dout("ceph_fs_debugfs_init\n"); + BUG_ON(!fsc->client->debugfs_dir); fsc->debugfs_congestion_kb = debugfs_create_file("writeback_congestion_kb", 0600, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 9fff9f3b17e4..4b5762ef7c2b 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -992,11 +992,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, if (rinfo->head->is_dentry) { struct inode *dir = req->r_locked_dir; - err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag, - session, req->r_request_started, -1, - &req->r_caps_reservation); - if (err < 0) - return err; + if (dir) { + err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag, + session, req->r_request_started, -1, + &req->r_caps_reservation); + if (err < 0) + return err; + } else { + WARN_ON_ONCE(1); + } } /* @@ -1004,6 +1008,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, * will have trouble splicing in the virtual snapdir later */ if (rinfo->head->is_dentry && !req->r_aborted && + req->r_locked_dir && (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name, fsc->mount_options->snapdir_name, req->r_dentry->d_name.len))) { diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index 8e3fb69fbe62..1396ceb46797 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -42,7 +42,8 @@ static long __validate_layout(struct ceph_mds_client *mdsc, /* validate striping parameters */ if ((l->object_size & ~PAGE_MASK) || (l->stripe_unit & ~PAGE_MASK) || - ((unsigned)l->object_size % (unsigned)l->stripe_unit)) + (l->stripe_unit != 0 && + ((unsigned)l->object_size % (unsigned)l->stripe_unit))) return -EINVAL; /* make sure it's a valid data pool */ diff --git a/fs/compat.c b/fs/compat.c index 6161255fac45..1bdb350ea5d3 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1155,11 +1155,14 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, struct file *file; int fput_needed; ssize_t ret; + loff_t pos; file = fget_light(fd, &fput_needed); if (!file) return -EBADF; - ret = compat_readv(file, vec, vlen, &file->f_pos); + pos = file->f_pos; + ret = compat_readv(file, vec, vlen, &pos); + file->f_pos = pos; fput_light(file, fput_needed); return ret; } @@ -1221,11 +1224,14 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, struct file *file; int fput_needed; ssize_t ret; + loff_t pos; file = fget_light(fd, &fput_needed); if (!file) return -EBADF; - ret = compat_writev(file, vec, vlen, &file->f_pos); + pos = file->f_pos; + ret = compat_writev(file, vec, vlen, &pos); + file->f_pos = pos; fput_light(file, fput_needed); return ret; } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 1c8b55670804..eedec84c1809 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1654,8 +1654,8 @@ SYSCALL_DEFINE1(epoll_create1, int, flags) error = PTR_ERR(file); goto out_free_fd; } - fd_install(fd, file); ep->file = file; + fd_install(fd, file); return fd; out_free_fd: diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 5badb0c039de..1562c27a2fab 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -37,15 +37,12 @@ #define EXOFS_DBGMSG2(M...) do {} while (0) -enum {MAX_PAGES_KMALLOC = PAGE_SIZE / sizeof(struct page *), }; - unsigned exofs_max_io_pages(struct ore_layout *layout, unsigned expected_pages) { - unsigned pages = min_t(unsigned, expected_pages, MAX_PAGES_KMALLOC); + unsigned pages = min_t(unsigned, expected_pages, + layout->max_io_length / PAGE_SIZE); - /* TODO: easily support bio chaining */ - pages = min_t(unsigned, pages, layout->max_io_length / PAGE_SIZE); return pages; } @@ -101,7 +98,8 @@ static void _pcol_reset(struct page_collect *pcol) * it might not end here. don't be left with nothing */ if (!pcol->expected_pages) - pcol->expected_pages = MAX_PAGES_KMALLOC; + pcol->expected_pages = + exofs_max_io_pages(&pcol->sbi->layout, ~0); } static int pcol_try_alloc(struct page_collect *pcol) @@ -389,6 +387,8 @@ static int readpage_strip(void *data, struct page *page) size_t len; int ret; + BUG_ON(!PageLocked(page)); + /* FIXME: Just for debugging, will be removed */ if (PageUptodate(page)) EXOFS_ERR("PageUptodate(0x%lx, 0x%lx)\n", pcol->inode->i_ino, @@ -572,8 +572,16 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) if (!pcol->that_locked_page || (pcol->that_locked_page->index != index)) { - struct page *page = find_get_page(pcol->inode->i_mapping, index); + struct page *page; + loff_t i_size = i_size_read(pcol->inode); + + if (offset >= i_size) { + *uptodate = true; + EXOFS_DBGMSG("offset >= i_size index=0x%lx\n", index); + return ZERO_PAGE(0); + } + page = find_get_page(pcol->inode->i_mapping, index); if (!page) { page = find_or_create_page(pcol->inode->i_mapping, index, GFP_NOFS); @@ -602,12 +610,13 @@ static void __r4w_put_page(void *priv, struct page *page) { struct page_collect *pcol = priv; - if (pcol->that_locked_page != page) { + if ((pcol->that_locked_page != page) && (ZERO_PAGE(0) != page)) { EXOFS_DBGMSG("index=0x%lx\n", page->index); page_cache_release(page); return; } - EXOFS_DBGMSG("that_locked_page index=0x%lx\n", page->index); + EXOFS_DBGMSG("that_locked_page index=0x%lx\n", + ZERO_PAGE(0) == page ? -1 : page->index); } static const struct _ore_r4w_op _r4w_op = { diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c index 24a49d47e935..1585db1aa365 100644 --- a/fs/exofs/ore.c +++ b/fs/exofs/ore.c @@ -837,11 +837,11 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp) bio->bi_rw |= REQ_WRITE; } - osd_req_write(or, _ios_obj(ios, dev), per_dev->offset, - bio, per_dev->length); + osd_req_write(or, _ios_obj(ios, cur_comp), + per_dev->offset, bio, per_dev->length); ORE_DBGMSG("write(0x%llx) offset=0x%llx " "length=0x%llx dev=%d\n", - _LLU(_ios_obj(ios, dev)->id), + _LLU(_ios_obj(ios, cur_comp)->id), _LLU(per_dev->offset), _LLU(per_dev->length), dev); } else if (ios->kern_buff) { @@ -853,20 +853,20 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp) (ios->si.unit_off + ios->length > ios->layout->stripe_unit)); - ret = osd_req_write_kern(or, _ios_obj(ios, per_dev->dev), + ret = osd_req_write_kern(or, _ios_obj(ios, cur_comp), per_dev->offset, ios->kern_buff, ios->length); if (unlikely(ret)) goto out; ORE_DBGMSG2("write_kern(0x%llx) offset=0x%llx " "length=0x%llx dev=%d\n", - _LLU(_ios_obj(ios, dev)->id), + _LLU(_ios_obj(ios, cur_comp)->id), _LLU(per_dev->offset), _LLU(ios->length), per_dev->dev); } else { - osd_req_set_attributes(or, _ios_obj(ios, dev)); + osd_req_set_attributes(or, _ios_obj(ios, cur_comp)); ORE_DBGMSG2("obj(0x%llx) set_attributes=%d dev=%d\n", - _LLU(_ios_obj(ios, dev)->id), + _LLU(_ios_obj(ios, cur_comp)->id), ios->out_attr_len, dev); } diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 433783624d10..dde41a75c7c8 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -400,8 +400,6 @@ static int exofs_sync_fs(struct super_block *sb, int wait) ret = ore_write(ios); if (unlikely(ret)) EXOFS_ERR("%s: ore_write failed.\n", __func__); - else - sb->s_dirt = 0; unlock_super(sb); @@ -412,14 +410,6 @@ out: return ret; } -static void exofs_write_super(struct super_block *sb) -{ - if (!(sb->s_flags & MS_RDONLY)) - exofs_sync_fs(sb, 1); - else - sb->s_dirt = 0; -} - static void _exofs_print_device(const char *msg, const char *dev_path, struct osd_dev *od, u64 pid) { @@ -952,7 +942,6 @@ static const struct super_operations exofs_sops = { .write_inode = exofs_write_inode, .evict_inode = exofs_evict_inode, .put_super = exofs_put_super, - .write_super = exofs_write_super, .sync_fs = exofs_sync_fs, .statfs = exofs_statfs, }; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 9a4a5c48b1c9..a07597307fd1 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -3459,14 +3459,6 @@ ext3_reserve_inode_write(handle_t *handle, struct inode *inode, * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. - * - * Is this efficient/effective? Well, we're being nice to the system - * by cleaning up our inodes proactively so they can be reaped - * without I/O. But we are potentially leaving up to five seconds' - * worth of inodes floating about which prune_icache wants us to - * write out. One way to fix that would be to get prune_icache() - * to do a write_super() to free up some memory. It has the desired - * effect. */ int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode) { diff --git a/fs/ext3/super.c b/fs/ext3/super.c index ff9bcdc5b0d5..8c892e93d8e7 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -64,11 +64,6 @@ static int ext3_freeze(struct super_block *sb); /* * Wrappers for journal_start/end. - * - * The only special thing we need to do here is to make sure that all - * journal_end calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. */ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) { @@ -90,12 +85,6 @@ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) return journal_start(journal, nblocks); } -/* - * The only special thing we need to do here is to make sure that all - * journal_stop calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - */ int __ext3_journal_stop(const char *where, handle_t *handle) { struct super_block *sb; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index d23b31ca9d7a..1b5089067d01 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -280,14 +280,18 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, return desc; } -static int ext4_valid_block_bitmap(struct super_block *sb, - struct ext4_group_desc *desc, - unsigned int block_group, - struct buffer_head *bh) +/* + * Return the block number which was discovered to be invalid, or 0 if + * the block bitmap is valid. + */ +static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) { ext4_grpblk_t offset; ext4_grpblk_t next_zero_bit; - ext4_fsblk_t bitmap_blk; + ext4_fsblk_t blk; ext4_fsblk_t group_first_block; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { @@ -297,37 +301,33 @@ static int ext4_valid_block_bitmap(struct super_block *sb, * or it has to also read the block group where the bitmaps * are located to verify they are set. */ - return 1; + return 0; } group_first_block = ext4_group_first_block_no(sb, block_group); /* check whether block bitmap block number is set */ - bitmap_blk = ext4_block_bitmap(sb, desc); - offset = bitmap_blk - group_first_block; + blk = ext4_block_bitmap(sb, desc); + offset = blk - group_first_block; if (!ext4_test_bit(offset, bh->b_data)) /* bad block bitmap */ - goto err_out; + return blk; /* check whether the inode bitmap block number is set */ - bitmap_blk = ext4_inode_bitmap(sb, desc); - offset = bitmap_blk - group_first_block; + blk = ext4_inode_bitmap(sb, desc); + offset = blk - group_first_block; if (!ext4_test_bit(offset, bh->b_data)) /* bad block bitmap */ - goto err_out; + return blk; /* check whether the inode table block number is set */ - bitmap_blk = ext4_inode_table(sb, desc); - offset = bitmap_blk - group_first_block; + blk = ext4_inode_table(sb, desc); + offset = blk - group_first_block; next_zero_bit = ext4_find_next_zero_bit(bh->b_data, offset + EXT4_SB(sb)->s_itb_per_group, offset); - if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group) - /* good bitmap for inode tables */ - return 1; - -err_out: - ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu", - block_group, bitmap_blk); + if (next_zero_bit < offset + EXT4_SB(sb)->s_itb_per_group) + /* bad bitmap for inode tables */ + return blk; return 0; } @@ -336,14 +336,26 @@ void ext4_validate_block_bitmap(struct super_block *sb, unsigned int block_group, struct buffer_head *bh) { + ext4_fsblk_t blk; + if (buffer_verified(bh)) return; ext4_lock_group(sb, block_group); - if (ext4_valid_block_bitmap(sb, desc, block_group, bh) && - ext4_block_bitmap_csum_verify(sb, block_group, desc, bh, - EXT4_BLOCKS_PER_GROUP(sb) / 8)) - set_buffer_verified(bh); + blk = ext4_valid_block_bitmap(sb, desc, block_group, bh); + if (unlikely(blk != 0)) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: block %llu: invalid block bitmap", + block_group, blk); + return; + } + if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, + desc, bh, EXT4_BLOCKS_PER_GROUP(sb) / 8))) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); + return; + } + set_buffer_verified(bh); ext4_unlock_group(sb, block_group); } diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index f8716eab9995..5c2d1813ebe9 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -79,7 +79,6 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, if (provided == calculated) return 1; - ext4_error(sb, "Bad block bitmap checksum: block_group = %u", group); return 0; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index cd0c7ed06772..aabbb3f53683 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2662,6 +2662,7 @@ cont: } path[0].p_depth = depth; path[0].p_hdr = ext_inode_hdr(inode); + i = 0; if (ext4_ext_check(inode, path[0].p_hdr, depth)) { err = -EIO; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6324f74e0342..dff171c3a123 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1970,7 +1970,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate); * This function can get called via... * - ext4_da_writepages after taking page lock (have journal handle) * - journal_submit_inode_data_buffers (no journal handle) - * - shrink_page_list via pdflush (no journal handle) + * - shrink_page_list via the kswapd/direct reclaim (no journal handle) * - grab_page_cache when doing write_begin (have journal handle) * * We don't do any block allocation in this function. If we have page with @@ -4589,14 +4589,6 @@ static int ext4_expand_extra_isize(struct inode *inode, * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. - * - * Is this efficient/effective? Well, we're being nice to the system - * by cleaning up our inodes proactively so they can be reaped - * without I/O. But we are potentially leaving up to five seconds' - * worth of inodes floating about which prune_icache wants us to - * write out. One way to fix that would be to get prune_icache() - * to do a write_super() to free up some memory. It has the desired - * effect. */ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d76ec8277d3f..c6e0cb3d1f4a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -326,11 +326,6 @@ static void ext4_put_nojournal(handle_t *handle) /* * Wrappers for jbd2_journal_start/end. - * - * The only special thing we need to do here is to make sure that all - * journal_end calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. */ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) { @@ -356,12 +351,6 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) return jbd2_journal_start(journal, nblocks); } -/* - * The only special thing we need to do here is to make sure that all - * jbd2_journal_stop calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - */ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) { struct super_block *sb; @@ -959,6 +948,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_reserved_meta_blocks = 0; ei->i_allocated_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; + ei->i_da_metadata_calc_last_lblock = 0; spin_lock_init(&(ei->i_block_reservation_lock)); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; @@ -3119,6 +3109,10 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp, ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) + return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + + sbi->s_itb_per_group + 2); + first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + (grp * EXT4_BLOCKS_PER_GROUP(sb)); last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1; @@ -4430,6 +4424,7 @@ static void ext4_clear_journal_err(struct super_block *sb, ext4_commit_super(sb, 1); jbd2_journal_clear_err(journal); + jbd2_journal_update_sb_errno(journal); } } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 8964cf3999b2..324bc0850534 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -383,6 +383,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, struct fuse_entry_out outentry; struct fuse_file *ff; + /* Userspace expects S_IFREG in create mode */ + BUG_ON((mode & S_IFMT) != S_IFREG); + forget = fuse_alloc_forget(); err = -ENOMEM; if (!forget) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 93d8d6c9494d..aba15f1b7ad2 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -703,13 +703,16 @@ static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); - if (pos + iov_length(iov, nr_segs) > i_size_read(inode)) { + /* + * In auto invalidate mode, always update attributes on read. + * Otherwise, only update if we attempt to read past EOF (to ensure + * i_size is up to date). + */ + if (fc->auto_inval_data || + (pos + iov_length(iov, nr_segs) > i_size_read(inode))) { int err; - /* - * If trying to read past EOF, make sure the i_size - * attribute is up-to-date. - */ err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL); if (err) return err; @@ -1700,7 +1703,7 @@ static int fuse_verify_ioctl_iov(struct iovec *iov, size_t count) size_t n; u32 max = FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT; - for (n = 0; n < count; n++) { + for (n = 0; n < count; n++, iov++) { if (iov->iov_len > (size_t) max) return -ENOMEM; max -= iov->iov_len; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 771fb6322c07..e24dd74e3068 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -484,6 +484,9 @@ struct fuse_conn { /** Is fallocate not implemented by fs? */ unsigned no_fallocate:1; + /** Use enhanced/automatic page cache invalidation. */ + unsigned auto_inval_data:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 1cd61652018c..ce0a2838ccd0 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -197,6 +197,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); loff_t oldsize; + struct timespec old_mtime; spin_lock(&fc->lock); if (attr_version != 0 && fi->attr_version > attr_version) { @@ -204,15 +205,35 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, return; } + old_mtime = inode->i_mtime; fuse_change_attributes_common(inode, attr, attr_valid); oldsize = inode->i_size; i_size_write(inode, attr->size); spin_unlock(&fc->lock); - if (S_ISREG(inode->i_mode) && oldsize != attr->size) { - truncate_pagecache(inode, oldsize, attr->size); - invalidate_inode_pages2(inode->i_mapping); + if (S_ISREG(inode->i_mode)) { + bool inval = false; + + if (oldsize != attr->size) { + truncate_pagecache(inode, oldsize, attr->size); + inval = true; + } else if (fc->auto_inval_data) { + struct timespec new_mtime = { + .tv_sec = attr->mtime, + .tv_nsec = attr->mtimensec, + }; + + /* + * Auto inval mode also checks and invalidates if mtime + * has changed. + */ + if (!timespec_equal(&old_mtime, &new_mtime)) + inval = true; + } + + if (inval) + invalidate_inode_pages2(inode->i_mapping); } } @@ -834,6 +855,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->big_writes = 1; if (arg->flags & FUSE_DONT_MASK) fc->dont_mask = 1; + if (arg->flags & FUSE_AUTO_INVAL_DATA) + fc->auto_inval_data = 1; } else { ra_pages = fc->max_read / PAGE_CACHE_SIZE; fc->no_lock = 1; @@ -859,7 +882,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE; arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | - FUSE_FLOCK_LOCKS; + FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | + FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 3a56c8d94de0..22255d96b27e 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -52,7 +52,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the page. Note that this can - * potentially cause a busy-wait loop from pdflush and kswapd + * potentially cause a busy-wait loop from flusher thread and kswapd * activity, but those code paths have their own higher-level * throttling. */ diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 5fd51a5833ff..b7ec224910c5 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -236,10 +236,10 @@ out: * hfs_mdb_commit() * * Description: - * This updates the MDB on disk (look also at hfs_write_super()). + * This updates the MDB on disk. * It does not check, if the superblock has been modified, or * if the filesystem has been mounted read-only. It is mainly - * called by hfs_write_super() and hfs_btree_extend(). + * called by hfs_sync_fs() and flush_mdb(). * Input Variable(s): * struct hfs_mdb *mdb: Pointer to the hfs MDB * int backup; diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 425c2f2cf170..09357508ec9a 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -534,8 +534,8 @@ int journal_start_commit(journal_t *journal, tid_t *ptid) ret = 1; } else if (journal->j_committing_transaction) { /* - * If ext3_write_super() recently started a commit, then we - * have to wait for completion of that transaction + * If commit has been started, then we have to wait for + * completion of that transaction. */ if (ptid) *ptid = journal->j_committing_transaction->t_tid; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index e9a3c4c85594..e149b99a7ffb 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -612,8 +612,8 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid) ret = 1; } else if (journal->j_committing_transaction) { /* - * If ext3_write_super() recently started a commit, then we - * have to wait for completion of that transaction + * If commit has been started, then we have to wait for + * completion of that transaction. */ if (ptid) *ptid = journal->j_committing_transaction->t_tid; @@ -1377,7 +1377,7 @@ static void jbd2_mark_journal_empty(journal_t *journal) * Update a journal's errno. Write updated superblock to disk waiting for IO * to complete. */ -static void jbd2_journal_update_sb_errno(journal_t *journal) +void jbd2_journal_update_sb_errno(journal_t *journal) { journal_superblock_t *sb = journal->j_superblock; @@ -1390,6 +1390,7 @@ static void jbd2_journal_update_sb_errno(journal_t *journal) jbd2_write_superblock(journal, WRITE_SYNC); } +EXPORT_SYMBOL(jbd2_journal_update_sb_errno); /* * Read the superblock for a given journal, performing initial diff --git a/fs/namei.c b/fs/namei.c index 1b464390dde8..dd1ed1b8e98e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -352,6 +352,7 @@ int __inode_permission(struct inode *inode, int mask) /** * sb_permission - Check superblock-level permissions * @sb: Superblock of inode to check permission on + * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. @@ -656,6 +657,7 @@ int sysctl_protected_hardlinks __read_mostly = 1; /** * may_follow_link - Check symlink following for unsafe situations * @link: The path of the symlink + * @nd: nameidata pathwalk data * * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is @@ -2414,7 +2416,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, goto out; } - mode = op->mode & S_IALLUGO; + mode = op->mode; if ((open_flag & O_CREAT) && !IS_POSIXACL(dir)) mode &= ~current_umask(); @@ -2452,7 +2454,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, } if (open_flag & O_CREAT) { - error = may_o_create(&nd->path, dentry, op->mode); + error = may_o_create(&nd->path, dentry, mode); if (error) { create_error = error; if (open_flag & O_EXCL) @@ -2489,6 +2491,10 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, dput(dentry); dentry = file->f_path.dentry; } + if (create_error && dentry->d_inode == NULL) { + error = create_error; + goto out; + } goto looked_up; } diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 8bf3a3f6925a..b7db60897f91 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -12,19 +12,19 @@ nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o -obj-$(CONFIG_NFS_V2) += nfs2.o -nfs2-y := nfs2super.o proc.o nfs2xdr.o +obj-$(CONFIG_NFS_V2) += nfsv2.o +nfsv2-y := nfs2super.o proc.o nfs2xdr.o -obj-$(CONFIG_NFS_V3) += nfs3.o -nfs3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o -nfs3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o +obj-$(CONFIG_NFS_V3) += nfsv3.o +nfsv3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o +nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o -obj-$(CONFIG_NFS_V4) += nfs4.o -nfs4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \ +obj-$(CONFIG_NFS_V4) += nfsv4.o +nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \ delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \ nfs4namespace.o nfs4getroot.o nfs4client.o -nfs4-$(CONFIG_SYSCTL) += nfs4sysctl.o -nfs4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o +nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o +nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 9fc0d9dfc91b..99694442b93f 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -105,7 +105,7 @@ struct nfs_subversion *get_nfs_version(unsigned int version) if (IS_ERR(nfs)) { mutex_lock(&nfs_version_mutex); - request_module("nfs%d", version); + request_module("nfsv%d", version); nfs = find_nfs_version(version); mutex_unlock(&nfs_version_mutex); } diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index b701358c39c3..a850079467d8 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -61,6 +61,12 @@ struct idmap { struct mutex idmap_mutex; }; +struct idmap_legacy_upcalldata { + struct rpc_pipe_msg pipe_msg; + struct idmap_msg idmap_msg; + struct idmap *idmap; +}; + /** * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields * @fattr: fully initialised struct nfs_fattr @@ -324,6 +330,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, ret = nfs_idmap_request_key(&key_type_id_resolver_legacy, name, namelen, type, data, data_size, idmap); + idmap->idmap_key_cons = NULL; mutex_unlock(&idmap->idmap_mutex); } return ret; @@ -380,11 +387,13 @@ static const match_table_t nfs_idmap_tokens = { static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *); static ssize_t idmap_pipe_downcall(struct file *, const char __user *, size_t); +static void idmap_release_pipe(struct inode *); static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *); static const struct rpc_pipe_ops idmap_upcall_ops = { .upcall = rpc_pipe_generic_upcall, .downcall = idmap_pipe_downcall, + .release_pipe = idmap_release_pipe, .destroy_msg = idmap_pipe_destroy_msg, }; @@ -616,7 +625,8 @@ void nfs_idmap_quit(void) nfs_idmap_quit_keyring(); } -static int nfs_idmap_prepare_message(char *desc, struct idmap_msg *im, +static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap, + struct idmap_msg *im, struct rpc_pipe_msg *msg) { substring_t substr; @@ -659,6 +669,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, const char *op, void *aux) { + struct idmap_legacy_upcalldata *data; struct rpc_pipe_msg *msg; struct idmap_msg *im; struct idmap *idmap = (struct idmap *)aux; @@ -666,15 +677,15 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, int ret = -ENOMEM; /* msg and im are freed in idmap_pipe_destroy_msg */ - msg = kmalloc(sizeof(*msg), GFP_KERNEL); - if (!msg) - goto out0; - - im = kmalloc(sizeof(*im), GFP_KERNEL); - if (!im) + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) goto out1; - ret = nfs_idmap_prepare_message(key->description, im, msg); + msg = &data->pipe_msg; + im = &data->idmap_msg; + data->idmap = idmap; + + ret = nfs_idmap_prepare_message(key->description, idmap, im, msg); if (ret < 0) goto out2; @@ -683,15 +694,15 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, ret = rpc_queue_upcall(idmap->idmap_pipe, msg); if (ret < 0) - goto out2; + goto out3; return ret; +out3: + idmap->idmap_key_cons = NULL; out2: - kfree(im); + kfree(data); out1: - kfree(msg); -out0: complete_request_key(cons, ret); return ret; } @@ -749,9 +760,8 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) } if (!(im.im_status & IDMAP_STATUS_SUCCESS)) { - ret = mlen; - complete_request_key(cons, -ENOKEY); - goto out_incomplete; + ret = -ENOKEY; + goto out; } namelen_in = strnlen(im.im_name, IDMAP_NAMESZ); @@ -768,16 +778,32 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) out: complete_request_key(cons, ret); -out_incomplete: return ret; } static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg) { + struct idmap_legacy_upcalldata *data = container_of(msg, + struct idmap_legacy_upcalldata, + pipe_msg); + struct idmap *idmap = data->idmap; + struct key_construction *cons; + if (msg->errno) { + cons = ACCESS_ONCE(idmap->idmap_key_cons); + idmap->idmap_key_cons = NULL; + complete_request_key(cons, msg->errno); + } /* Free memory allocated in nfs_idmap_legacy_upcall() */ - kfree(msg->data); - kfree(msg); + kfree(data); +} + +static void +idmap_release_pipe(struct inode *inode) +{ + struct rpc_inode *rpci = RPC_I(inode); + struct idmap *idmap = (struct idmap *)rpci->private; + idmap->idmap_key_cons = NULL; } int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid) diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 0952c791df36..d6b3b5f2d779 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -69,7 +69,7 @@ do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle, nfs_fattr_init(info->fattr); status = rpc_call_sync(client, &msg, 0); dprintk("%s: reply fsinfo: %d\n", __func__, status); - if (!(info->fattr->valid & NFS_ATTR_FATTR)) { + if (status == 0 && !(info->fattr->valid & NFS_ATTR_FATTR)) { msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR]; msg.rpc_resp = info->fattr; status = rpc_call_sync(client, &msg, 0); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 3b950dd81e81..da0618aeeadb 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -205,6 +205,9 @@ extern const struct dentry_operations nfs4_dentry_operations; int nfs_atomic_open(struct inode *, struct dentry *, struct file *, unsigned, umode_t, int *); +/* super.c */ +extern struct file_system_type nfs4_fs_type; + /* nfs4namespace.c */ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index cbcdfaf32505..24eb663f8ed5 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -74,7 +74,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) return clp; error: - kfree(clp); + nfs_free_client(clp); return ERR_PTR(err); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a99a8d948721..635274140b18 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3737,9 +3737,10 @@ out: static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len) { struct nfs4_cached_acl *acl; + size_t buflen = sizeof(*acl) + acl_len; - if (pages && acl_len <= PAGE_SIZE) { - acl = kmalloc(sizeof(*acl) + acl_len, GFP_KERNEL); + if (pages && buflen <= PAGE_SIZE) { + acl = kmalloc(buflen, GFP_KERNEL); if (acl == NULL) goto out; acl->cached = 1; @@ -3819,7 +3820,7 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu if (ret) goto out_free; - acl_len = res.acl_len - res.acl_data_offset; + acl_len = res.acl_len; if (acl_len > args.acl_len) nfs4_write_cached_acl(inode, NULL, 0, acl_len); else @@ -6223,11 +6224,58 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) dprintk("<-- %s\n", __func__); } +static size_t max_response_pages(struct nfs_server *server) +{ + u32 max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + return nfs_page_array_len(0, max_resp_sz); +} + +static void nfs4_free_pages(struct page **pages, size_t size) +{ + int i; + + if (!pages) + return; + + for (i = 0; i < size; i++) { + if (!pages[i]) + break; + __free_page(pages[i]); + } + kfree(pages); +} + +static struct page **nfs4_alloc_pages(size_t size, gfp_t gfp_flags) +{ + struct page **pages; + int i; + + pages = kcalloc(size, sizeof(struct page *), gfp_flags); + if (!pages) { + dprintk("%s: can't alloc array of %zu pages\n", __func__, size); + return NULL; + } + + for (i = 0; i < size; i++) { + pages[i] = alloc_page(gfp_flags); + if (!pages[i]) { + dprintk("%s: failed to allocate page\n", __func__); + nfs4_free_pages(pages, size); + return NULL; + } + } + + return pages; +} + static void nfs4_layoutget_release(void *calldata) { struct nfs4_layoutget *lgp = calldata; + struct nfs_server *server = NFS_SERVER(lgp->args.inode); + size_t max_pages = max_response_pages(server); dprintk("--> %s\n", __func__); + nfs4_free_pages(lgp->args.layout.pages, max_pages); put_nfs_open_context(lgp->args.ctx); kfree(calldata); dprintk("<-- %s\n", __func__); @@ -6239,9 +6287,10 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = { .rpc_release = nfs4_layoutget_release, }; -int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) +void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) { struct nfs_server *server = NFS_SERVER(lgp->args.inode); + size_t max_pages = max_response_pages(server); struct rpc_task *task; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTGET], @@ -6259,12 +6308,19 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) dprintk("--> %s\n", __func__); + lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); + if (!lgp->args.layout.pages) { + nfs4_layoutget_release(lgp); + return; + } + lgp->args.layout.pglen = max_pages * PAGE_SIZE; + lgp->res.layoutp = &lgp->args.layout; lgp->res.seq_res.sr_slot = NULL; nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) - return PTR_ERR(task); + return; status = nfs4_wait_for_completion_rpc_task(task); if (status == 0) status = task->tk_status; @@ -6272,7 +6328,7 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) status = pnfs_layout_process(lgp); rpc_put_task(task); dprintk("<-- %s status=%d\n", __func__, status); - return status; + return; } static void @@ -6304,12 +6360,8 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) return; } spin_lock(&lo->plh_inode->i_lock); - if (task->tk_status == 0) { - if (lrp->res.lrs_present) { - pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - } else - BUG_ON(!list_empty(&lo->plh_segs)); - } + if (task->tk_status == 0 && lrp->res.lrs_present) + pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); dprintk("<-- %s\n", __func__); diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 12a31a9dbcdd..bd61221ad2c5 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -23,14 +23,6 @@ static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data); -static struct file_system_type nfs4_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs_fs_mount, - .kill_sb = nfs_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, -}; - static struct file_system_type nfs4_remote_fs_type = { .owner = THIS_MODULE, .name = "nfs4", @@ -344,14 +336,8 @@ static int __init init_nfs_v4(void) if (err) goto out1; - err = register_filesystem(&nfs4_fs_type); - if (err < 0) - goto out2; - register_nfs_version(&nfs_v4); return 0; -out2: - nfs4_unregister_sysctl(); out1: nfs_idmap_quit(); out: @@ -361,7 +347,6 @@ out: static void __exit exit_nfs_v4(void) { unregister_nfs_version(&nfs_v4); - unregister_filesystem(&nfs4_fs_type); nfs4_unregister_sysctl(); nfs_idmap_quit(); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index ca13483edd60..1bfbd67c556d 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5045,22 +5045,19 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_getaclres *res) { unsigned int savep; - __be32 *bm_p; uint32_t attrlen, bitmap[3] = {0}; int status; - size_t page_len = xdr->buf->page_len; + unsigned int pg_offset; res->acl_len = 0; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) goto out; - bm_p = xdr->p; - res->acl_data_offset = be32_to_cpup(bm_p) + 2; - res->acl_data_offset <<= 2; - /* Check if the acl data starts beyond the allocated buffer */ - if (res->acl_data_offset > page_len) - return -ERANGE; + xdr_enter_page(xdr, xdr->buf->page_len); + + /* Calculate the offset of the page data */ + pg_offset = xdr->buf->head[0].iov_len; if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) goto out; @@ -5074,23 +5071,20 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, /* The bitmap (xdr len + bitmaps) and the attr xdr len words * are stored with the acl data to handle the problem of * variable length bitmaps.*/ - xdr->p = bm_p; + res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset; /* We ignore &savep and don't do consistency checks on * the attr length. Let userspace figure it out.... */ - attrlen += res->acl_data_offset; - if (attrlen > page_len) { + res->acl_len = attrlen; + if (attrlen > (xdr->nwords << 2)) { if (res->acl_flags & NFS4_ACL_LEN_REQUEST) { /* getxattr interface called with a NULL buf */ - res->acl_len = attrlen; goto out; } - dprintk("NFS: acl reply: attrlen %u > page_len %zu\n", - attrlen, page_len); + dprintk("NFS: acl reply: attrlen %u > page_len %u\n", + attrlen, xdr->nwords << 2); return -EINVAL; } - xdr_read_pages(xdr, attrlen); - res->acl_len = attrlen; } else status = -EOPNOTSUPP; diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index f50d3e8d6f22..ea6d111b03e9 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -570,17 +570,66 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio, return false; return pgio->pg_count + req->wb_bytes <= - OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; + (unsigned long)pgio->pg_layout_private; +} + +void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + pnfs_generic_pg_init_read(pgio, req); + if (unlikely(pgio->pg_lseg == NULL)) + return; /* Not pNFS */ + + pgio->pg_layout_private = (void *) + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; +} + +static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout, + unsigned long *stripe_end) +{ + u32 stripe_off; + unsigned stripe_size; + + if (layout->raid_algorithm == PNFS_OSD_RAID_0) + return true; + + stripe_size = layout->stripe_unit * + (layout->group_width - layout->parity); + + div_u64_rem(offset, stripe_size, &stripe_off); + if (!stripe_off) + return true; + + *stripe_end = stripe_size - stripe_off; + return false; +} + +void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + unsigned long stripe_end = 0; + + pnfs_generic_pg_init_write(pgio, req); + if (unlikely(pgio->pg_lseg == NULL)) + return; /* Not pNFS */ + + if (req->wb_offset || + !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE, + &OBJIO_LSEG(pgio->pg_lseg)->layout, + &stripe_end)) { + pgio->pg_layout_private = (void *)stripe_end; + } else { + pgio->pg_layout_private = (void *) + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; + } } static const struct nfs_pageio_ops objio_pg_read_ops = { - .pg_init = pnfs_generic_pg_init_read, + .pg_init = objio_init_read, .pg_test = objio_pg_test, .pg_doio = pnfs_generic_pg_readpages, }; static const struct nfs_pageio_ops objio_pg_write_ops = { - .pg_init = pnfs_generic_pg_init_write, + .pg_init = objio_init_write, .pg_test = objio_pg_test, .pg_doio = pnfs_generic_pg_writepages, }; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 1a6732ed04a4..311a79681e2b 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -49,6 +49,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->io_start = req_offset(hdr->req); hdr->good_bytes = desc->pg_count; hdr->dreq = desc->pg_dreq; + hdr->layout_private = desc->pg_layout_private; hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; if (hdr->completion_ops->init_hdr) @@ -268,6 +269,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_error = 0; desc->pg_lseg = NULL; desc->pg_dreq = NULL; + desc->pg_layout_private = NULL; } EXPORT_SYMBOL_GPL(nfs_pageio_init); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 76875bfcf19c..2e00feacd4be 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -583,9 +583,6 @@ send_layoutget(struct pnfs_layout_hdr *lo, struct nfs_server *server = NFS_SERVER(ino); struct nfs4_layoutget *lgp; struct pnfs_layout_segment *lseg = NULL; - struct page **pages = NULL; - int i; - u32 max_resp_sz, max_pages; dprintk("--> %s\n", __func__); @@ -594,20 +591,6 @@ send_layoutget(struct pnfs_layout_hdr *lo, if (lgp == NULL) return NULL; - /* allocate pages for xdr post processing */ - max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = nfs_page_array_len(0, max_resp_sz); - - pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags); - if (!pages) - goto out_err_free; - - for (i = 0; i < max_pages; i++) { - pages[i] = alloc_page(gfp_flags); - if (!pages[i]) - goto out_err_free; - } - lgp->args.minlength = PAGE_CACHE_SIZE; if (lgp->args.minlength > range->length) lgp->args.minlength = range->length; @@ -616,39 +599,19 @@ send_layoutget(struct pnfs_layout_hdr *lo, lgp->args.type = server->pnfs_curr_ld->id; lgp->args.inode = ino; lgp->args.ctx = get_nfs_open_context(ctx); - lgp->args.layout.pages = pages; - lgp->args.layout.pglen = max_pages * PAGE_SIZE; lgp->lsegpp = &lseg; lgp->gfp_flags = gfp_flags; /* Synchronously retrieve layout information from server and * store in lseg. */ - nfs4_proc_layoutget(lgp); + nfs4_proc_layoutget(lgp, gfp_flags); if (!lseg) { /* remember that LAYOUTGET failed and suspend trying */ set_bit(lo_fail_bit(range->iomode), &lo->plh_flags); } - /* free xdr pages */ - for (i = 0; i < max_pages; i++) - __free_page(pages[i]); - kfree(pages); - return lseg; - -out_err_free: - /* free any allocated xdr pages, lgp as it's not used */ - if (pages) { - for (i = 0; i < max_pages; i++) { - if (!pages[i]) - break; - __free_page(pages[i]); - } - kfree(pages); - } - kfree(lgp); - return NULL; } /* diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 2c6c80503ba4..745aa1b39e7c 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -172,7 +172,7 @@ extern int nfs4_proc_getdevicelist(struct nfs_server *server, struct pnfs_devicelist *devlist); extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *dev); -extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp); +extern void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags); extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp); /* pnfs.c */ diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ac6a3c55dce4..239aff7338eb 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -319,6 +319,34 @@ EXPORT_SYMBOL_GPL(nfs_sops); static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *); static int nfs4_validate_mount_data(void *options, struct nfs_parsed_mount_data *args, const char *dev_name); + +struct file_system_type nfs4_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .mount = nfs_fs_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; +EXPORT_SYMBOL_GPL(nfs4_fs_type); + +static int __init register_nfs4_fs(void) +{ + return register_filesystem(&nfs4_fs_type); +} + +static void unregister_nfs4_fs(void) +{ + unregister_filesystem(&nfs4_fs_type); +} +#else +static int __init register_nfs4_fs(void) +{ + return 0; +} + +static void unregister_nfs4_fs(void) +{ +} #endif static struct shrinker acl_shrinker = { @@ -337,12 +365,18 @@ int __init register_nfs_fs(void) if (ret < 0) goto error_0; - ret = nfs_register_sysctl(); + ret = register_nfs4_fs(); if (ret < 0) goto error_1; + + ret = nfs_register_sysctl(); + if (ret < 0) + goto error_2; register_shrinker(&acl_shrinker); return 0; +error_2: + unregister_nfs4_fs(); error_1: unregister_filesystem(&nfs_fs_type); error_0: @@ -356,6 +390,7 @@ void __exit unregister_nfs_fs(void) { unregister_shrinker(&acl_shrinker); nfs_unregister_sysctl(); + unregister_nfs4_fs(); unregister_filesystem(&nfs_fs_type); } @@ -2645,4 +2680,6 @@ MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 " module_param(send_implementation_id, ushort, 0644); MODULE_PARM_DESC(send_implementation_id, "Send implementation ID with NFSv4.1 exchange_id"); +MODULE_ALIAS("nfs4"); + #endif /* CONFIG_NFS_V4 */ diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5829d0ce7cfb..e3b55372726c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1814,19 +1814,19 @@ int __init nfs_init_writepagecache(void) nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE, nfs_wdata_cachep); if (nfs_wdata_mempool == NULL) - return -ENOMEM; + goto out_destroy_write_cache; nfs_cdata_cachep = kmem_cache_create("nfs_commit_data", sizeof(struct nfs_commit_data), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_cdata_cachep == NULL) - return -ENOMEM; + goto out_destroy_write_mempool; nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT, nfs_wdata_cachep); if (nfs_commit_mempool == NULL) - return -ENOMEM; + goto out_destroy_commit_cache; /* * NFS congestion size, scale with available memory. @@ -1849,11 +1849,20 @@ int __init nfs_init_writepagecache(void) nfs_congestion_kb = 256*1024; return 0; + +out_destroy_commit_cache: + kmem_cache_destroy(nfs_cdata_cachep); +out_destroy_write_mempool: + mempool_destroy(nfs_wdata_mempool); +out_destroy_write_cache: + kmem_cache_destroy(nfs_wdata_cachep); + return -ENOMEM; } void nfs_destroy_writepagecache(void) { mempool_destroy(nfs_commit_mempool); + kmem_cache_destroy(nfs_cdata_cachep); mempool_destroy(nfs_wdata_mempool); kmem_cache_destroy(nfs_wdata_cachep); } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 6522cac6057c..6a10812711c1 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -676,17 +676,13 @@ static const struct super_operations nilfs_sops = { .alloc_inode = nilfs_alloc_inode, .destroy_inode = nilfs_destroy_inode, .dirty_inode = nilfs_dirty_inode, - /* .write_inode = nilfs_write_inode, */ - /* .drop_inode = nilfs_drop_inode, */ .evict_inode = nilfs_evict_inode, .put_super = nilfs_put_super, - /* .write_super = nilfs_write_super, */ .sync_fs = nilfs_sync_fs, .freeze_fs = nilfs_freeze, .unfreeze_fs = nilfs_unfreeze, .statfs = nilfs_statfs, .remount_fs = nilfs_remount, - /* .umount_begin */ .show_options = nilfs_show_options }; diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 6eee4177807b..be1267a34cea 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -107,8 +107,6 @@ struct the_nilfs { * used for * - loading the latest checkpoint exclusively. * - allocating a new full segment. - * - protecting s_dirt in the super_block struct - * (see nilfs_write_super) and the following fields. */ struct buffer_head *ns_sbh[2]; struct nilfs_super_block *ns_sbp[2]; diff --git a/fs/open.c b/fs/open.c index f3d96e7e7b19..e1f2cdb91a4d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -717,7 +717,7 @@ cleanup_all: * here, so just reset the state. */ file_reset_write(f); - mnt_drop_write(f->f_path.mnt); + __mnt_drop_write(f->f_path.mnt); } } cleanup_file: @@ -852,9 +852,10 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o int lookup_flags = 0; int acc_mode; - if (!(flags & O_CREAT)) - mode = 0; - op->mode = mode; + if (flags & O_CREAT) + op->mode = (mode & S_IALLUGO) | S_IFREG; + else + op->mode = 0; /* Must never be set by userspace */ flags &= ~FMODE_NONOTIFY; diff --git a/fs/super.c b/fs/super.c index b05cf47463d0..0902cfa6a12e 100644 --- a/fs/super.c +++ b/fs/super.c @@ -537,46 +537,6 @@ void drop_super(struct super_block *sb) EXPORT_SYMBOL(drop_super); /** - * sync_supers - helper for periodic superblock writeback - * - * Call the write_super method if present on all dirty superblocks in - * the system. This is for the periodic writeback used by most older - * filesystems. For data integrity superblock writeback use - * sync_filesystems() instead. - * - * Note: check the dirty flag before waiting, so we don't - * hold up the sync while mounting a device. (The newly - * mounted device won't need syncing.) - */ -void sync_supers(void) -{ - struct super_block *sb, *p = NULL; - - spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { - if (hlist_unhashed(&sb->s_instances)) - continue; - if (sb->s_op->write_super && sb->s_dirt) { - sb->s_count++; - spin_unlock(&sb_lock); - - down_read(&sb->s_umount); - if (sb->s_root && sb->s_dirt && (sb->s_flags & MS_BORN)) - sb->s_op->write_super(sb); - up_read(&sb->s_umount); - - spin_lock(&sb_lock); - if (p) - __put_super(p); - p = sb; - } - } - if (p) - __put_super(p); - spin_unlock(&sb_lock); -} - -/** * iterate_supers - call function for all active superblocks * @f: function to call * @arg: argument to pass to it diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 35389ca2d267..7bd6e72afd11 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -37,11 +37,11 @@ * * A thing to keep in mind: inode @i_mutex is locked in most VFS operations we * implement. However, this is not true for 'ubifs_writepage()', which may be - * called with @i_mutex unlocked. For example, when pdflush is doing background - * write-back, it calls 'ubifs_writepage()' with unlocked @i_mutex. At "normal" - * work-paths the @i_mutex is locked in 'ubifs_writepage()', e.g. in the - * "sys_write -> alloc_pages -> direct reclaim path". So, in 'ubifs_writepage()' - * we are only guaranteed that the page is locked. + * called with @i_mutex unlocked. For example, when flusher thread is doing + * background write-back, it calls 'ubifs_writepage()' with unlocked @i_mutex. + * At "normal" work-paths the @i_mutex is locked in 'ubifs_writepage()', e.g. + * in the "sys_write -> alloc_pages -> direct reclaim path". So, in + * 'ubifs_writepage()' we are only guaranteed that the page is locked. * * Similarly, @i_mutex is not always locked in 'ubifs_readpage()', e.g., the * read-ahead path does not lock it ("sys_read -> generic_file_aio_read -> diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 1c766c39c038..c3fa6c5327a3 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -303,7 +303,7 @@ static int ubifs_write_inode(struct inode *inode, struct writeback_control *wbc) mutex_lock(&ui->ui_mutex); /* * Due to races between write-back forced by budgeting - * (see 'sync_some_inodes()') and pdflush write-back, the inode may + * (see 'sync_some_inodes()') and background write-back, the inode may * have already been synchronized, do not do this again. This might * also happen if it was synchronized in an VFS operation, e.g. * 'ubifs_link()'. |