diff options
Diffstat (limited to 'fs')
41 files changed, 1309 insertions, 597 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 08405a3da6b1..b90cd3776f8e 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -560,13 +560,13 @@ static int __add_missing_keys(struct btrfs_fs_info *fs_info, */ static void __merge_refs(struct list_head *head, int mode) { - struct __prelim_ref *ref1; + struct __prelim_ref *pos1; - list_for_each_entry(ref1, head, list) { - struct __prelim_ref *ref2 = ref1, *tmp; + list_for_each_entry(pos1, head, list) { + struct __prelim_ref *pos2 = pos1, *tmp; - list_for_each_entry_safe_continue(ref2, tmp, head, list) { - struct __prelim_ref *xchg; + list_for_each_entry_safe_continue(pos2, tmp, head, list) { + struct __prelim_ref *xchg, *ref1 = pos1, *ref2 = pos2; struct extent_inode_elem *eie; if (!ref_for_same_block(ref1, ref2)) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 97ad9bbeb35d..bfe4a337fb4d 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1614,7 +1614,7 @@ struct btrfs_fs_info { spinlock_t delayed_iput_lock; struct list_head delayed_iputs; - struct rw_semaphore delayed_iput_sem; + struct mutex cleaner_delayed_iput_mutex; /* this protects tree_mod_seq_list */ spinlock_t tree_mod_seq_lock; @@ -3641,6 +3641,7 @@ int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans, int __get_raid_index(u64 flags); int btrfs_start_write_no_snapshoting(struct btrfs_root *root); void btrfs_end_write_no_snapshoting(struct btrfs_root *root); +void btrfs_wait_for_snapshot_creation(struct btrfs_root *root); void check_system_chunk(struct btrfs_trans_handle *trans, struct btrfs_root *root, const u64 type); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 1e668fb7dd4c..cbb7dbfb3fff 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -614,7 +614,7 @@ static void btrfs_dev_replace_update_device_in_mapping_tree( em = lookup_extent_mapping(em_tree, start, (u64)-1); if (!em) break; - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; for (i = 0; i < map->num_stripes; i++) if (srcdev == map->stripes[i].dev) map->stripes[i].dev = tgtdev; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e99ccd6ffb2c..dd08e29f5117 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -55,6 +55,12 @@ #include <asm/cpufeature.h> #endif +#define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\ + BTRFS_HEADER_FLAG_RELOC |\ + BTRFS_SUPER_FLAG_ERROR |\ + BTRFS_SUPER_FLAG_SEEDING |\ + BTRFS_SUPER_FLAG_METADUMP) + static const struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); static void free_fs_root(struct btrfs_root *root); @@ -1583,8 +1589,23 @@ int btrfs_init_fs_root(struct btrfs_root *root) ret = get_anon_bdev(&root->anon_dev); if (ret) goto free_writers; + + mutex_lock(&root->objectid_mutex); + ret = btrfs_find_highest_objectid(root, + &root->highest_objectid); + if (ret) { + mutex_unlock(&root->objectid_mutex); + goto free_root_dev; + } + + ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + + mutex_unlock(&root->objectid_mutex); + return 0; +free_root_dev: + free_anon_bdev(root->anon_dev); free_writers: btrfs_free_subvolume_writers(root->subv_writers); fail: @@ -1786,7 +1807,10 @@ static int cleaner_kthread(void *arg) goto sleep; } + mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex); btrfs_run_delayed_iputs(root); + mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex); + again = btrfs_clean_one_deleted_snapshot(root); mutex_unlock(&root->fs_info->cleaner_mutex); @@ -2556,8 +2580,8 @@ int open_ctree(struct super_block *sb, mutex_init(&fs_info->delete_unused_bgs_mutex); mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); + mutex_init(&fs_info->cleaner_delayed_iput_mutex); seqlock_init(&fs_info->profiles_lock); - init_rwsem(&fs_info->delayed_iput_sem); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); INIT_LIST_HEAD(&fs_info->space_info); @@ -2742,26 +2766,6 @@ int open_ctree(struct super_block *sb, goto fail_alloc; } - /* - * Leafsize and nodesize were always equal, this is only a sanity check. - */ - if (le32_to_cpu(disk_super->__unused_leafsize) != - btrfs_super_nodesize(disk_super)) { - printk(KERN_ERR "BTRFS: couldn't mount because metadata " - "blocksizes don't match. node %d leaf %d\n", - btrfs_super_nodesize(disk_super), - le32_to_cpu(disk_super->__unused_leafsize)); - err = -EINVAL; - goto fail_alloc; - } - if (btrfs_super_nodesize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) { - printk(KERN_ERR "BTRFS: couldn't mount because metadata " - "blocksize (%d) was too large\n", - btrfs_super_nodesize(disk_super)); - err = -EINVAL; - goto fail_alloc; - } - features = btrfs_super_incompat_flags(disk_super); features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO) @@ -2833,17 +2837,6 @@ int open_ctree(struct super_block *sb, sb->s_blocksize = sectorsize; sb->s_blocksize_bits = blksize_bits(sectorsize); - if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) { - printk(KERN_ERR "BTRFS: valid FS not found on %s\n", sb->s_id); - goto fail_sb_buffer; - } - - if (sectorsize != PAGE_SIZE) { - printk(KERN_ERR "BTRFS: incompatible sector size (%lu) " - "found on %s\n", (unsigned long)sectorsize, sb->s_id); - goto fail_sb_buffer; - } - mutex_lock(&fs_info->chunk_mutex); ret = btrfs_read_sys_array(tree_root); mutex_unlock(&fs_info->chunk_mutex); @@ -2915,6 +2908,18 @@ retry_root_backup: tree_root->commit_root = btrfs_root_node(tree_root); btrfs_set_root_refs(&tree_root->root_item, 1); + mutex_lock(&tree_root->objectid_mutex); + ret = btrfs_find_highest_objectid(tree_root, + &tree_root->highest_objectid); + if (ret) { + mutex_unlock(&tree_root->objectid_mutex); + goto recovery_tree_root; + } + + ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID); + + mutex_unlock(&tree_root->objectid_mutex); + ret = btrfs_read_roots(fs_info, tree_root); if (ret) goto recovery_tree_root; @@ -4018,8 +4023,17 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, int read_only) { struct btrfs_super_block *sb = fs_info->super_copy; + u64 nodesize = btrfs_super_nodesize(sb); + u64 sectorsize = btrfs_super_sectorsize(sb); int ret = 0; + if (btrfs_super_magic(sb) != BTRFS_MAGIC) { + printk(KERN_ERR "BTRFS: no valid FS found\n"); + ret = -EINVAL; + } + if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) + printk(KERN_WARNING "BTRFS: unrecognized super flag: %llu\n", + btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP); if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) { printk(KERN_ERR "BTRFS: tree_root level too big: %d >= %d\n", btrfs_super_root_level(sb), BTRFS_MAX_LEVEL); @@ -4037,31 +4051,46 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, } /* - * The common minimum, we don't know if we can trust the nodesize/sectorsize - * items yet, they'll be verified later. Issue just a warning. + * Check sectorsize and nodesize first, other check will need it. + * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here. */ - if (!IS_ALIGNED(btrfs_super_root(sb), 4096)) + if (!is_power_of_2(sectorsize) || sectorsize < 4096 || + sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) { + printk(KERN_ERR "BTRFS: invalid sectorsize %llu\n", sectorsize); + ret = -EINVAL; + } + /* Only PAGE SIZE is supported yet */ + if (sectorsize != PAGE_CACHE_SIZE) { + printk(KERN_ERR "BTRFS: sectorsize %llu not supported yet, only support %lu\n", + sectorsize, PAGE_CACHE_SIZE); + ret = -EINVAL; + } + if (!is_power_of_2(nodesize) || nodesize < sectorsize || + nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) { + printk(KERN_ERR "BTRFS: invalid nodesize %llu\n", nodesize); + ret = -EINVAL; + } + if (nodesize != le32_to_cpu(sb->__unused_leafsize)) { + printk(KERN_ERR "BTRFS: invalid leafsize %u, should be %llu\n", + le32_to_cpu(sb->__unused_leafsize), + nodesize); + ret = -EINVAL; + } + + /* Root alignment check */ + if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) { printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n", btrfs_super_root(sb)); - if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096)) + ret = -EINVAL; + } + if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) { printk(KERN_WARNING "BTRFS: chunk_root block unaligned: %llu\n", btrfs_super_chunk_root(sb)); - if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096)) - printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n", - btrfs_super_log_root(sb)); - - /* - * Check the lower bound, the alignment and other constraints are - * checked later. - */ - if (btrfs_super_nodesize(sb) < 4096) { - printk(KERN_ERR "BTRFS: nodesize too small: %u < 4096\n", - btrfs_super_nodesize(sb)); ret = -EINVAL; } - if (btrfs_super_sectorsize(sb) < 4096) { - printk(KERN_ERR "BTRFS: sectorsize too small: %u < 4096\n", - btrfs_super_sectorsize(sb)); + if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) { + printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n", + btrfs_super_log_root(sb)); ret = -EINVAL; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 60cc1399c64f..e2287c7c10be 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4139,8 +4139,10 @@ commit_trans: !atomic_read(&root->fs_info->open_ioctl_trans)) { need_commit--; - if (need_commit > 0) + if (need_commit > 0) { + btrfs_start_delalloc_roots(fs_info, 0, -1); btrfs_wait_ordered_roots(fs_info, -1); + } trans = btrfs_join_transaction(root); if (IS_ERR(trans)) @@ -4153,11 +4155,12 @@ commit_trans: if (ret) return ret; /* - * make sure that all running delayed iput are - * done + * The cleaner kthread might still be doing iput + * operations. Wait for it to finish so that + * more space is released. */ - down_write(&root->fs_info->delayed_iput_sem); - up_write(&root->fs_info->delayed_iput_sem); + mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex); + mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex); goto again; } else { btrfs_end_transaction(trans, root); @@ -10399,7 +10402,7 @@ btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info, * more device items and remove one chunk item), but this is done at * btrfs_remove_chunk() through a call to check_system_chunk(). */ - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; num_items = 3 + map->num_stripes; free_extent_map(em); @@ -10586,7 +10589,7 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info) disk_super = fs_info->super_copy; if (!btrfs_super_root(disk_super)) - return 1; + return -EINVAL; features = btrfs_super_incompat_flags(disk_super); if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) @@ -10816,3 +10819,23 @@ int btrfs_start_write_no_snapshoting(struct btrfs_root *root) } return 1; } + +static int wait_snapshoting_atomic_t(atomic_t *a) +{ + schedule(); + return 0; +} + +void btrfs_wait_for_snapshot_creation(struct btrfs_root *root) +{ + while (true) { + int ret; + + ret = btrfs_start_write_no_snapshoting(root); + if (ret) + break; + wait_on_atomic_t(&root->will_be_snapshoted, + wait_snapshoting_atomic_t, + TASK_UNINTERRUPTIBLE); + } +} diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 6a98bddd8f33..84fb56d5c018 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -76,7 +76,7 @@ void free_extent_map(struct extent_map *em) WARN_ON(extent_map_in_tree(em)); WARN_ON(!list_empty(&em->list)); if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags)) - kfree(em->bdev); + kfree(em->map_lookup); kmem_cache_free(extent_map_cache, em); } } diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h index b2991fd8583e..eb8b8fae036b 100644 --- a/fs/btrfs/extent_map.h +++ b/fs/btrfs/extent_map.h @@ -32,7 +32,15 @@ struct extent_map { u64 block_len; u64 generation; unsigned long flags; - struct block_device *bdev; + union { + struct block_device *bdev; + + /* + * used for chunk mappings + * flags & EXTENT_FLAG_FS_MAPPING must be set + */ + struct map_lookup *map_lookup; + }; atomic_t refs; unsigned int compress_type; struct list_head list; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 83d7859d7619..9f5cc1e8e126 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -406,8 +406,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info) /* simple helper to fault in pages and copy. This should go away * and be replaced with calls into generic code. */ -static noinline int btrfs_copy_from_user(loff_t pos, int num_pages, - size_t write_bytes, +static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes, struct page **prepared_pages, struct iov_iter *i) { @@ -1588,8 +1587,7 @@ again: ret = 0; } - copied = btrfs_copy_from_user(pos, num_pages, - write_bytes, pages, i); + copied = btrfs_copy_from_user(pos, write_bytes, pages, i); /* * if we have trouble faulting in the pages, fall diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 8b57c17b3fb3..e50316c4af15 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -515,7 +515,7 @@ out: return ret; } -static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) +int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid) { struct btrfs_path *path; int ret; @@ -555,13 +555,6 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid) int ret; mutex_lock(&root->objectid_mutex); - if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) { - ret = btrfs_find_highest_objectid(root, - &root->highest_objectid); - if (ret) - goto out; - } - if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) { ret = -ENOSPC; goto out; diff --git a/fs/btrfs/inode-map.h b/fs/btrfs/inode-map.h index ddb347bfee23..c8e864b2d530 100644 --- a/fs/btrfs/inode-map.h +++ b/fs/btrfs/inode-map.h @@ -9,5 +9,6 @@ int btrfs_save_ino_cache(struct btrfs_root *root, struct btrfs_trans_handle *trans); int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid); +int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid); #endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 247830107686..1b79dc9b12e4 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3134,7 +3134,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; - down_read(&fs_info->delayed_iput_sem); spin_lock(&fs_info->delayed_iput_lock); while (!list_empty(&fs_info->delayed_iputs)) { struct btrfs_inode *inode; @@ -3153,7 +3152,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root) spin_lock(&fs_info->delayed_iput_lock); } spin_unlock(&fs_info->delayed_iput_lock); - up_read(&root->fs_info->delayed_iput_sem); } /* @@ -4874,26 +4872,6 @@ next: return err; } -static int wait_snapshoting_atomic_t(atomic_t *a) -{ - schedule(); - return 0; -} - -static void wait_for_snapshot_creation(struct btrfs_root *root) -{ - while (true) { - int ret; - - ret = btrfs_start_write_no_snapshoting(root); - if (ret) - break; - wait_on_atomic_t(&root->will_be_snapshoted, - wait_snapshoting_atomic_t, - TASK_UNINTERRUPTIBLE); - } -} - static int btrfs_setsize(struct inode *inode, struct iattr *attr) { struct btrfs_root *root = BTRFS_I(inode)->root; @@ -4925,7 +4903,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) * truncation, it must capture all writes that happened before * this truncation. */ - wait_for_snapshot_creation(root); + btrfs_wait_for_snapshot_creation(root); ret = btrfs_cont_expand(inode, oldsize, newsize); if (ret) { btrfs_end_write_no_snapshoting(root); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 2a47a3148ec8..9028737ee9b5 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -568,6 +568,10 @@ static noinline int create_subvol(struct inode *dir, goto fail; } + mutex_lock(&new_root->objectid_mutex); + new_root->highest_objectid = new_dirid; + mutex_unlock(&new_root->objectid_mutex); + /* * insert the directory item */ diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 6d707545f775..55161369fab1 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -609,13 +609,28 @@ static int rbio_can_merge(struct btrfs_raid_bio *last, return 1; } +static int rbio_stripe_page_index(struct btrfs_raid_bio *rbio, int stripe, + int index) +{ + return stripe * rbio->stripe_npages + index; +} + +/* + * these are just the pages from the rbio array, not from anything + * the FS sent down to us + */ +static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe, + int index) +{ + return rbio->stripe_pages[rbio_stripe_page_index(rbio, stripe, index)]; +} + /* * helper to index into the pstripe */ static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index) { - index += (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT; - return rbio->stripe_pages[index]; + return rbio_stripe_page(rbio, rbio->nr_data, index); } /* @@ -626,10 +641,7 @@ static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index) { if (rbio->nr_data + 1 == rbio->real_stripes) return NULL; - - index += ((rbio->nr_data + 1) * rbio->stripe_len) >> - PAGE_CACHE_SHIFT; - return rbio->stripe_pages[index]; + return rbio_stripe_page(rbio, rbio->nr_data + 1, index); } /* @@ -889,6 +901,7 @@ static void raid_write_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; int err = bio->bi_error; + int max_errors; if (err) fail_bio_stripe(rbio, bio); @@ -901,7 +914,9 @@ static void raid_write_end_io(struct bio *bio) err = 0; /* OK, we have read all the stripes we need to. */ - if (atomic_read(&rbio->error) > rbio->bbio->max_errors) + max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ? + 0 : rbio->bbio->max_errors; + if (atomic_read(&rbio->error) > max_errors) err = -EIO; rbio_orig_end_io(rbio, err); @@ -947,8 +962,7 @@ static struct page *page_in_rbio(struct btrfs_raid_bio *rbio, */ static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes) { - unsigned long nr = stripe_len * nr_stripes; - return DIV_ROUND_UP(nr, PAGE_CACHE_SIZE); + return DIV_ROUND_UP(stripe_len, PAGE_CACHE_SIZE) * nr_stripes; } /* @@ -966,8 +980,8 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root, void *p; rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2 + - DIV_ROUND_UP(stripe_npages, BITS_PER_LONG / 8), - GFP_NOFS); + DIV_ROUND_UP(stripe_npages, BITS_PER_LONG) * + sizeof(long), GFP_NOFS); if (!rbio) return ERR_PTR(-ENOMEM); @@ -1021,18 +1035,17 @@ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio) if (!page) return -ENOMEM; rbio->stripe_pages[i] = page; - ClearPageUptodate(page); } return 0; } -/* allocate pages for just the p/q stripes */ +/* only allocate pages for p/q stripes */ static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio) { int i; struct page *page; - i = (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT; + i = rbio_stripe_page_index(rbio, rbio->nr_data, 0); for (; i < rbio->nr_pages; i++) { if (rbio->stripe_pages[i]) @@ -1121,18 +1134,6 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio) } /* - * these are just the pages from the rbio array, not from anything - * the FS sent down to us - */ -static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe, int page) -{ - int index; - index = stripe * (rbio->stripe_len >> PAGE_CACHE_SHIFT); - index += page; - return rbio->stripe_pages[index]; -} - -/* * helper function to walk our bio list and populate the bio_pages array with * the result. This seems expensive, but it is faster than constantly * searching through the bio list as we setup the IO in finish_rmw or stripe @@ -1175,7 +1176,6 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) { struct btrfs_bio *bbio = rbio->bbio; void *pointers[rbio->real_stripes]; - int stripe_len = rbio->stripe_len; int nr_data = rbio->nr_data; int stripe; int pagenr; @@ -1183,7 +1183,6 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) int q_stripe = -1; struct bio_list bio_list; struct bio *bio; - int pages_per_stripe = stripe_len >> PAGE_CACHE_SHIFT; int ret; bio_list_init(&bio_list); @@ -1226,7 +1225,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) else clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags); - for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) { + for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { struct page *p; /* first collect one page from each data stripe */ for (stripe = 0; stripe < nr_data; stripe++) { @@ -1268,7 +1267,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) * everything else. */ for (stripe = 0; stripe < rbio->real_stripes; stripe++) { - for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) { + for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { struct page *page; if (stripe < rbio->nr_data) { page = page_in_rbio(rbio, stripe, pagenr, 1); @@ -1292,7 +1291,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio) if (!bbio->tgtdev_map[stripe]) continue; - for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) { + for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { struct page *page; if (stripe < rbio->nr_data) { page = page_in_rbio(rbio, stripe, pagenr, 1); @@ -1506,7 +1505,6 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) int bios_to_read = 0; struct bio_list bio_list; int ret; - int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE); int pagenr; int stripe; struct bio *bio; @@ -1525,7 +1523,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) * stripe */ for (stripe = 0; stripe < rbio->nr_data; stripe++) { - for (pagenr = 0; pagenr < nr_pages; pagenr++) { + for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { struct page *page; /* * we want to find all the pages missing from @@ -1801,7 +1799,6 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) int pagenr, stripe; void **pointers; int faila = -1, failb = -1; - int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE); struct page *page; int err; int i; @@ -1824,7 +1821,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) index_rbio_pages(rbio); - for (pagenr = 0; pagenr < nr_pages; pagenr++) { + for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { /* * Now we just use bitmap to mark the horizontal stripes in * which we have data when doing parity scrub. @@ -1935,7 +1932,7 @@ pstripe: * other endio functions will fiddle the uptodate bits */ if (rbio->operation == BTRFS_RBIO_WRITE) { - for (i = 0; i < nr_pages; i++) { + for (i = 0; i < rbio->stripe_npages; i++) { if (faila != -1) { page = rbio_stripe_page(rbio, faila, i); SetPageUptodate(page); @@ -2031,7 +2028,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) int bios_to_read = 0; struct bio_list bio_list; int ret; - int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE); int pagenr; int stripe; struct bio *bio; @@ -2055,7 +2051,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) continue; } - for (pagenr = 0; pagenr < nr_pages; pagenr++) { + for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) { struct page *p; /* @@ -2279,37 +2275,11 @@ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio) if (!page) return -ENOMEM; rbio->stripe_pages[index] = page; - ClearPageUptodate(page); } } return 0; } -/* - * end io function used by finish_rmw. When we finally - * get here, we've written a full stripe - */ -static void raid_write_parity_end_io(struct bio *bio) -{ - struct btrfs_raid_bio *rbio = bio->bi_private; - int err = bio->bi_error; - - if (bio->bi_error) - fail_bio_stripe(rbio, bio); - - bio_put(bio); - - if (!atomic_dec_and_test(&rbio->stripes_pending)) - return; - - err = 0; - - if (atomic_read(&rbio->error)) - err = -EIO; - - rbio_orig_end_io(rbio, err); -} - static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check) { @@ -2462,7 +2432,7 @@ submit_write: break; bio->bi_private = rbio; - bio->bi_end_io = raid_write_parity_end_io; + bio->bi_end_io = raid_write_end_io; submit_bio(WRITE, bio); } return; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 0c981ebe2acb..b1a68530e911 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2813,7 +2813,7 @@ out: static inline int scrub_calc_parity_bitmap_len(int nsectors) { - return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * (BITS_PER_LONG / 8); + return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * sizeof(long); } static void scrub_parity_get(struct scrub_parity *sparity) @@ -3458,7 +3458,7 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx, return ret; } - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; if (em->start != chunk_offset) goto out; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 9b9eab6d048e..d41e09fe8e38 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -383,6 +383,9 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) int ret = 0; char *compress_type; bool compress_force = false; + enum btrfs_compression_type saved_compress_type; + bool saved_compress_force; + int no_compress = 0; cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy); if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE)) @@ -462,6 +465,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) /* Fallthrough */ case Opt_compress: case Opt_compress_type: + saved_compress_type = btrfs_test_opt(root, COMPRESS) ? + info->compress_type : BTRFS_COMPRESS_NONE; + saved_compress_force = + btrfs_test_opt(root, FORCE_COMPRESS); if (token == Opt_compress || token == Opt_compress_force || strcmp(args[0].from, "zlib") == 0) { @@ -470,6 +477,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) btrfs_set_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, NODATACOW); btrfs_clear_opt(info->mount_opt, NODATASUM); + no_compress = 0; } else if (strcmp(args[0].from, "lzo") == 0) { compress_type = "lzo"; info->compress_type = BTRFS_COMPRESS_LZO; @@ -477,25 +485,21 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) btrfs_clear_opt(info->mount_opt, NODATACOW); btrfs_clear_opt(info->mount_opt, NODATASUM); btrfs_set_fs_incompat(info, COMPRESS_LZO); + no_compress = 0; } else if (strncmp(args[0].from, "no", 2) == 0) { compress_type = "no"; btrfs_clear_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); compress_force = false; + no_compress++; } else { ret = -EINVAL; goto out; } if (compress_force) { - btrfs_set_and_info(root, FORCE_COMPRESS, - "force %s compression", - compress_type); + btrfs_set_opt(info->mount_opt, FORCE_COMPRESS); } else { - if (!btrfs_test_opt(root, COMPRESS)) - btrfs_info(root->fs_info, - "btrfs: use %s compression", - compress_type); /* * If we remount from compress-force=xxx to * compress=xxx, we need clear FORCE_COMPRESS @@ -504,6 +508,17 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) */ btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS); } + if ((btrfs_test_opt(root, COMPRESS) && + (info->compress_type != saved_compress_type || + compress_force != saved_compress_force)) || + (!btrfs_test_opt(root, COMPRESS) && + no_compress == 1)) { + btrfs_info(root->fs_info, + "%s %s compression", + (compress_force) ? "force" : "use", + compress_type); + } + compress_force = false; break; case Opt_ssd: btrfs_set_and_info(root, SSD, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index c32abbca9d77..366b335946fa 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -108,7 +108,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = { }, }; -const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = { +const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = { [BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10, [BTRFS_RAID_RAID1] = BTRFS_BLOCK_GROUP_RAID1, [BTRFS_RAID_DUP] = BTRFS_BLOCK_GROUP_DUP, @@ -233,6 +233,7 @@ static struct btrfs_device *__alloc_device(void) spin_lock_init(&dev->reada_lock); atomic_set(&dev->reada_in_flight, 0); atomic_set(&dev->dev_stats_ccnt, 0); + btrfs_device_data_ordered_init(dev); INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); @@ -1183,7 +1184,7 @@ again: struct map_lookup *map; int i; - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; for (i = 0; i < map->num_stripes; i++) { u64 end; @@ -2755,7 +2756,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, free_extent_map(em); return -EINVAL; } - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; lock_chunks(root->fs_info->chunk_root); check_system_chunk(trans, extent_root, map->type); unlock_chunks(root->fs_info->chunk_root); @@ -3751,7 +3752,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, if (btrfs_get_num_tolerated_disk_barrier_failures(bctl->meta.target) < btrfs_get_num_tolerated_disk_barrier_failures(bctl->data.target)) { btrfs_warn(fs_info, - "metatdata profile 0x%llx has lower redundancy than data profile 0x%llx", + "metadata profile 0x%llx has lower redundancy than data profile 0x%llx", bctl->meta.target, bctl->data.target); } @@ -4718,7 +4719,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, goto error; } set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags); - em->bdev = (struct block_device *)map; + em->map_lookup = map; em->start = start; em->len = num_bytes; em->block_start = 0; @@ -4813,7 +4814,7 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, return -EINVAL; } - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; item_size = btrfs_chunk_item_size(map->num_stripes); stripe_size = em->orig_block_len; @@ -4968,7 +4969,7 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset) if (!em) return 1; - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; for (i = 0; i < map->num_stripes; i++) { if (map->stripes[i].dev->missing) { miss_ndevs++; @@ -5048,7 +5049,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len) return 1; } - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1)) ret = map->num_stripes; else if (map->type & BTRFS_BLOCK_GROUP_RAID10) @@ -5084,7 +5085,7 @@ unsigned long btrfs_full_stripe_len(struct btrfs_root *root, BUG_ON(!em); BUG_ON(em->start > logical || em->start + em->len < logical); - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) len = map->stripe_len * nr_data_stripes(map); free_extent_map(em); @@ -5105,7 +5106,7 @@ int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree, BUG_ON(!em); BUG_ON(em->start > logical || em->start + em->len < logical); - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) ret = 1; free_extent_map(em); @@ -5264,7 +5265,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, return -EINVAL; } - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; offset = logical - em->start; stripe_len = map->stripe_len; @@ -5378,35 +5379,33 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, * target drive. */ for (i = 0; i < tmp_num_stripes; i++) { - if (tmp_bbio->stripes[i].dev->devid == srcdev_devid) { - /* - * In case of DUP, in order to keep it - * simple, only add the mirror with the - * lowest physical address - */ - if (found && - physical_of_found <= - tmp_bbio->stripes[i].physical) - continue; - index_srcdev = i; - found = 1; - physical_of_found = - tmp_bbio->stripes[i].physical; - } + if (tmp_bbio->stripes[i].dev->devid != srcdev_devid) + continue; + + /* + * In case of DUP, in order to keep it simple, only add + * the mirror with the lowest physical address + */ + if (found && + physical_of_found <= tmp_bbio->stripes[i].physical) + continue; + + index_srcdev = i; + found = 1; + physical_of_found = tmp_bbio->stripes[i].physical; } - if (found) { - mirror_num = index_srcdev + 1; - patch_the_first_stripe_for_dev_replace = 1; - physical_to_patch_in_first_stripe = physical_of_found; - } else { + btrfs_put_bbio(tmp_bbio); + + if (!found) { WARN_ON(1); ret = -EIO; - btrfs_put_bbio(tmp_bbio); goto out; } - btrfs_put_bbio(tmp_bbio); + mirror_num = index_srcdev + 1; + patch_the_first_stripe_for_dev_replace = 1; + physical_to_patch_in_first_stripe = physical_of_found; } else if (mirror_num > map->num_stripes) { mirror_num = 0; } @@ -5806,7 +5805,7 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, free_extent_map(em); return -EIO; } - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; length = em->len; rmap_len = map->stripe_len; @@ -6069,7 +6068,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, bbio->fs_info = root->fs_info; atomic_set(&bbio->stripes_pending, bbio->num_stripes); - if (bbio->raid_map) { + if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) && + ((rw & WRITE) || (mirror_num > 1))) { /* In this case, map_length has been set to the length of a single stripe; not the whole write */ if (rw & WRITE) { @@ -6210,6 +6210,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, struct extent_map *em; u64 logical; u64 length; + u64 stripe_len; u64 devid; u8 uuid[BTRFS_UUID_SIZE]; int num_stripes; @@ -6218,6 +6219,37 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, logical = key->offset; length = btrfs_chunk_length(leaf, chunk); + stripe_len = btrfs_chunk_stripe_len(leaf, chunk); + num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + /* Validation check */ + if (!num_stripes) { + btrfs_err(root->fs_info, "invalid chunk num_stripes: %u", + num_stripes); + return -EIO; + } + if (!IS_ALIGNED(logical, root->sectorsize)) { + btrfs_err(root->fs_info, + "invalid chunk logical %llu", logical); + return -EIO; + } + if (!length || !IS_ALIGNED(length, root->sectorsize)) { + btrfs_err(root->fs_info, + "invalid chunk length %llu", length); + return -EIO; + } + if (!is_power_of_2(stripe_len)) { + btrfs_err(root->fs_info, "invalid chunk stripe length: %llu", + stripe_len); + return -EIO; + } + if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) & + btrfs_chunk_type(leaf, chunk)) { + btrfs_err(root->fs_info, "unrecognized chunk type: %llu", + ~(BTRFS_BLOCK_GROUP_TYPE_MASK | + BTRFS_BLOCK_GROUP_PROFILE_MASK) & + btrfs_chunk_type(leaf, chunk)); + return -EIO; + } read_lock(&map_tree->map_tree.lock); em = lookup_extent_mapping(&map_tree->map_tree, logical, 1); @@ -6234,7 +6266,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, em = alloc_extent_map(); if (!em) return -ENOMEM; - num_stripes = btrfs_chunk_num_stripes(leaf, chunk); map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS); if (!map) { free_extent_map(em); @@ -6242,7 +6273,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, } set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags); - em->bdev = (struct block_device *)map; + em->map_lookup = map; em->start = logical; em->len = length; em->orig_start = 0; @@ -6944,7 +6975,7 @@ void btrfs_update_commit_device_bytes_used(struct btrfs_root *root, /* In order to kick the device replace finish process */ lock_chunks(root); list_for_each_entry(em, &transaction->pending_chunks, list) { - map = (struct map_lookup *)em->bdev; + map = em->map_lookup; for (i = 0; i < map->num_stripes; i++) { dev = map->stripes[i].dev; diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 1925d6d222b8..58c2f4a21b7f 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -516,7 +516,7 @@ static ssize_t device_write(struct file *file, const char __user *buf, return -EINVAL; kbuf = memdup_user_nul(buf, count); - if (!IS_ERR(kbuf)) + if (IS_ERR(kbuf)) return PTR_ERR(kbuf); if (check_version(kbuf)) { diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index 1a0835073663..c8021208a7eb 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -384,14 +384,12 @@ int ext4_decrypt(struct page *page) EXT4_DECRYPT, page->index, page, page); } -int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex) +int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, ext4_lblk_t len) { struct ext4_crypto_ctx *ctx; struct page *ciphertext_page = NULL; struct bio *bio; - ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); - ext4_fsblk_t pblk = ext4_ext_pblock(ex); - unsigned int len = ext4_ext_get_actual_len(ex); int ret, err = 0; #if 0 diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c index c5882b36e558..9a16d1e75a49 100644 --- a/fs/ext4/crypto_key.c +++ b/fs/ext4/crypto_key.c @@ -213,9 +213,11 @@ retry: res = -ENOKEY; goto out; } + down_read(&keyring_key->sem); ukp = user_key_payload(keyring_key); if (ukp->datalen != sizeof(struct ext4_encryption_key)) { res = -EINVAL; + up_read(&keyring_key->sem); goto out; } master_key = (struct ext4_encryption_key *)ukp->data; @@ -226,10 +228,12 @@ retry: "ext4: key size incorrect: %d\n", master_key->size); res = -ENOKEY; + up_read(&keyring_key->sem); goto out; } res = ext4_derive_key_aes(ctx.nonce, master_key->raw, raw_key); + up_read(&keyring_key->sem); if (res) goto out; got_key: diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index cc7ca4e87144..1c127213363a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -378,14 +378,22 @@ struct flex_groups { #define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */ -#define EXT4_FL_USER_MODIFIABLE 0x004380FF /* User modifiable flags */ +#define EXT4_FL_USER_VISIBLE 0x304BDFFF /* User visible flags */ +#define EXT4_FL_USER_MODIFIABLE 0x204380FF /* User modifiable flags */ + +#define EXT4_FL_XFLAG_VISIBLE (EXT4_SYNC_FL | \ + EXT4_IMMUTABLE_FL | \ + EXT4_APPEND_FL | \ + EXT4_NODUMP_FL | \ + EXT4_NOATIME_FL | \ + EXT4_PROJINHERIT_FL) /* Flags that should be inherited by new inodes from their parent. */ #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\ EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\ EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\ - EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL) + EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\ + EXT4_PROJINHERIT_FL) /* Flags that are appropriate for regular files (all but dir-specific ones). */ #define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL)) @@ -555,10 +563,12 @@ enum { #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 /* Request will not result in inode size update (user for fallocate) */ #define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080 - /* Do not take i_data_sem locking in ext4_map_blocks */ -#define EXT4_GET_BLOCKS_NO_LOCK 0x0100 /* Convert written extents to unwritten */ -#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0200 +#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0100 + /* Write zeros to newly created written extents */ +#define EXT4_GET_BLOCKS_ZERO 0x0200 +#define EXT4_GET_BLOCKS_CREATE_ZERO (EXT4_GET_BLOCKS_CREATE |\ + EXT4_GET_BLOCKS_ZERO) /* * The bit position of these flags must not overlap with any of the @@ -616,6 +626,46 @@ enum { #define EXT4_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16]) #define EXT4_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct ext4_encryption_policy) +#ifndef FS_IOC_FSGETXATTR +/* Until the uapi changes get merged for project quota... */ + +#define FS_IOC_FSGETXATTR _IOR('X', 31, struct fsxattr) +#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr) + +/* + * Structure for FS_IOC_FSGETXATTR and FS_IOC_FSSETXATTR. + */ +struct fsxattr { + __u32 fsx_xflags; /* xflags field value (get/set) */ + __u32 fsx_extsize; /* extsize field value (get/set)*/ + __u32 fsx_nextents; /* nextents field value (get) */ + __u32 fsx_projid; /* project identifier (get/set) */ + unsigned char fsx_pad[12]; +}; + +/* + * Flags for the fsx_xflags field + */ +#define FS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */ +#define FS_XFLAG_PREALLOC 0x00000002 /* preallocated file extents */ +#define FS_XFLAG_IMMUTABLE 0x00000008 /* file cannot be modified */ +#define FS_XFLAG_APPEND 0x00000010 /* all writes append */ +#define FS_XFLAG_SYNC 0x00000020 /* all writes synchronous */ +#define FS_XFLAG_NOATIME 0x00000040 /* do not update access time */ +#define FS_XFLAG_NODUMP 0x00000080 /* do not include in backups */ +#define FS_XFLAG_RTINHERIT 0x00000100 /* create with rt bit set */ +#define FS_XFLAG_PROJINHERIT 0x00000200 /* create with parents projid */ +#define FS_XFLAG_NOSYMLINKS 0x00000400 /* disallow symlink creation */ +#define FS_XFLAG_EXTSIZE 0x00000800 /* extent size allocator hint */ +#define FS_XFLAG_EXTSZINHERIT 0x00001000 /* inherit inode extent size */ +#define FS_XFLAG_NODEFRAG 0x00002000 /* do not defragment */ +#define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ +#define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ +#endif /* !defined(FS_IOC_FSGETXATTR) */ + +#define EXT4_IOC_FSGETXATTR FS_IOC_FSGETXATTR +#define EXT4_IOC_FSSETXATTR FS_IOC_FSSETXATTR + #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* * ioctl commands in 32 bit emulation @@ -910,6 +960,15 @@ struct ext4_inode_info { * by other means, so we have i_data_sem. */ struct rw_semaphore i_data_sem; + /* + * i_mmap_sem is for serializing page faults with truncate / punch hole + * operations. We have to make sure that new page cannot be faulted in + * a section of the inode that is being punched. We cannot easily use + * i_data_sem for this since we need protection for the whole punch + * operation and i_data_sem ranks below transaction start so we have + * to occasionally drop it. + */ + struct rw_semaphore i_mmap_sem; struct inode vfs_inode; struct jbd2_inode *jinode; @@ -993,6 +1052,7 @@ struct ext4_inode_info { /* Encryption params */ struct ext4_crypt_info *i_crypt_info; #endif + kprojid_t i_projid; }; /* @@ -1248,7 +1308,7 @@ struct ext4_super_block { #endif /* Number of quota types we support */ -#define EXT4_MAXQUOTAS 2 +#define EXT4_MAXQUOTAS 3 /* * fourth extended-fs super-block data in memory @@ -1754,7 +1814,8 @@ EXT4_FEATURE_INCOMPAT_FUNCS(encrypt, ENCRYPT) EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\ - EXT4_FEATURE_RO_COMPAT_QUOTA) + EXT4_FEATURE_RO_COMPAT_QUOTA |\ + EXT4_FEATURE_RO_COMPAT_PROJECT) #define EXTN_FEATURE_FUNCS(ver) \ static inline bool ext4_has_unknown_ext##ver##_compat_features(struct super_block *sb) \ @@ -1796,6 +1857,11 @@ static inline bool ext4_has_incompat_features(struct super_block *sb) #define EXT4_DEF_RESUID 0 #define EXT4_DEF_RESGID 0 +/* + * Default project ID + */ +#define EXT4_DEF_PROJID 0 + #define EXT4_DEF_INODE_READAHEAD_BLKS 32 /* @@ -2234,7 +2300,8 @@ void ext4_restore_control_page(struct page *data_page); struct page *ext4_encrypt(struct inode *inode, struct page *plaintext_page); int ext4_decrypt(struct page *page); -int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex); +int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, ext4_lblk_t len); #ifdef CONFIG_EXT4_FS_ENCRYPTION int ext4_init_crypto(void); @@ -2440,8 +2507,8 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int); struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int); int ext4_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); -int ext4_get_block_dax(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create); +int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create); int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, @@ -2484,9 +2551,13 @@ extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t lend); extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); +extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); +extern int ext4_get_projid(struct inode *inode, kprojid_t *projid); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); +extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, ext4_lblk_t len); /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, @@ -2848,6 +2919,9 @@ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize) return changed; } +int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, + loff_t len); + struct ext4_group_info { unsigned long bb_state; struct rb_root bb_free_root; @@ -2986,8 +3060,7 @@ extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, struct page *page); extern int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, - struct dentry *dentry, - struct inode *inode); + struct inode *dir, struct inode *inode); extern int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent, struct inode *inode); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 551353b1b17a..b52fea3b7219 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3119,19 +3119,11 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) { ext4_fsblk_t ee_pblock; unsigned int ee_len; - int ret; ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); - - if (ext4_encrypted_inode(inode)) - return ext4_encrypted_zeroout(inode, ex); - - ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS); - if (ret > 0) - ret = 0; - - return ret; + return ext4_issue_zeroout(inode, le32_to_cpu(ex->ee_block), ee_pblock, + ee_len); } /* @@ -4052,6 +4044,14 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, } /* IO end_io complete, convert the filled extent to written */ if (flags & EXT4_GET_BLOCKS_CONVERT) { + if (flags & EXT4_GET_BLOCKS_ZERO) { + if (allocated > map->m_len) + allocated = map->m_len; + err = ext4_issue_zeroout(inode, map->m_lblk, newblock, + allocated); + if (err < 0) + goto out2; + } ret = ext4_convert_unwritten_extents_endio(handle, inode, map, ppath); if (ret >= 0) { @@ -4685,10 +4685,6 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, if (len <= EXT_UNWRITTEN_MAX_LEN) flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - /* * credits to insert 1 extent into extent tree */ @@ -4752,8 +4748,6 @@ retry: goto retry; } - ext4_inode_resume_unlocked_dio(inode); - return ret > 0 ? ret2 : ret; } @@ -4770,7 +4764,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, int partial_begin, partial_end; loff_t start, end; ext4_lblk_t lblk; - struct address_space *mapping = inode->i_mapping; unsigned int blkbits = inode->i_blkbits; trace_ext4_zero_range(inode, offset, len, mode); @@ -4786,17 +4779,6 @@ static long ext4_zero_range(struct file *file, loff_t offset, } /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - ret = filemap_write_and_wait_range(mapping, offset, - offset + len - 1); - if (ret) - return ret; - } - - /* * Round up offset. This is not fallocate, we neet to zero out * blocks, so convert interior block aligned part of the range to * unwritten and possibly manually zero out unaligned parts of the @@ -4839,6 +4821,10 @@ static long ext4_zero_range(struct file *file, loff_t offset, if (mode & FALLOC_FL_KEEP_SIZE) flags |= EXT4_GET_BLOCKS_KEEP_SIZE; + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, @@ -4847,7 +4833,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, round_down(offset, 1 << blkbits)) >> blkbits, new_size, flags, mode); if (ret) - goto out_mutex; + goto out_dio; } @@ -4856,16 +4842,23 @@ static long ext4_zero_range(struct file *file, loff_t offset, flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE); - /* Now release the pages and zero block aligned part of pages*/ + /* + * Prevent page faults from reinstantiating pages we have + * released from page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + ret = ext4_update_disksize_before_punch(inode, offset, len); + if (ret) { + up_write(&EXT4_I(inode)->i_mmap_sem); + goto out_dio; + } + /* Now release the pages and zero block aligned part of pages */ truncate_pagecache_range(inode, start, end - 1); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); - ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags, mode); + up_write(&EXT4_I(inode)->i_mmap_sem); if (ret) goto out_dio; } @@ -4998,8 +4991,13 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) goto out; } + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags, mode); + ext4_inode_resume_unlocked_dio(inode); if (ret) goto out; @@ -5494,21 +5492,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) return ret; } - /* - * Need to round down offset to be aligned with page size boundary - * for page size > block size. - */ - ioffset = round_down(offset, PAGE_SIZE); - - /* Write out all dirty pages */ - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - LLONG_MAX); - if (ret) - return ret; - - /* Take mutex lock */ mutex_lock(&inode->i_mutex); - /* * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation @@ -5524,17 +5508,43 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) goto out_mutex; } - truncate_pagecache(inode, ioffset); - /* Wait for existing dio to complete */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + /* + * Need to round down offset to be aligned with page size boundary + * for page size > block size. + */ + ioffset = round_down(offset, PAGE_SIZE); + /* + * Write tail of the last page before removed range since it will get + * removed from the page cache below. + */ + ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset); + if (ret) + goto out_mmap; + /* + * Write data that will be shifted to preserve them when discarding + * page cache below. We are also protected from pages becoming dirty + * by i_mmap_sem. + */ + ret = filemap_write_and_wait_range(inode->i_mapping, offset + len, + LLONG_MAX); + if (ret) + goto out_mmap; + truncate_pagecache(inode, ioffset); + credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out_dio; + goto out_mmap; } down_write(&EXT4_I(inode)->i_data_sem); @@ -5573,7 +5583,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) out_stop: ext4_journal_stop(handle); -out_dio: +out_mmap: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); @@ -5627,21 +5638,7 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) return ret; } - /* - * Need to round down to align start offset to page size boundary - * for page size > block size. - */ - ioffset = round_down(offset, PAGE_SIZE); - - /* Write out all dirty pages */ - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - LLONG_MAX); - if (ret) - return ret; - - /* Take mutex lock */ mutex_lock(&inode->i_mutex); - /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ret = -EOPNOTSUPP; @@ -5660,17 +5657,32 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) goto out_mutex; } - truncate_pagecache(inode, ioffset); - /* Wait for existing dio to complete */ ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); + /* + * Need to round down to align start offset to page size boundary + * for page size > block size. + */ + ioffset = round_down(offset, PAGE_SIZE); + /* Write out all dirty pages */ + ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, + LLONG_MAX); + if (ret) + goto out_mmap; + truncate_pagecache(inode, ioffset); + credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); - goto out_dio; + goto out_mmap; } /* Expand file to avoid data loss if there is error while shifting */ @@ -5741,7 +5753,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) out_stop: ext4_journal_stop(handle); -out_dio: +out_mmap: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 113837e7ba98..749b222e6498 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -193,43 +193,35 @@ out: } #ifdef CONFIG_FS_DAX -static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate) -{ - struct inode *inode = bh->b_assoc_map->host; - /* XXX: breaks on 32-bit > 16TB. Is that even supported? */ - loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits; - int err; - if (!uptodate) - return; - WARN_ON(!buffer_unwritten(bh)); - err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size); -} - static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { int result; handle_t *handle = NULL; - struct super_block *sb = file_inode(vma->vm_file)->i_sb; + struct inode *inode = file_inode(vma->vm_file); + struct super_block *sb = inode->i_sb; bool write = vmf->flags & FAULT_FLAG_WRITE; if (write) { sb_start_pagefault(sb); file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, EXT4_DATA_TRANS_BLOCKS(sb)); - } + } else + down_read(&EXT4_I(inode)->i_mmap_sem); if (IS_ERR(handle)) result = VM_FAULT_SIGBUS; else - result = __dax_fault(vma, vmf, ext4_get_block_dax, - ext4_end_io_unwritten); + result = __dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL); if (write) { if (!IS_ERR(handle)) ext4_journal_stop(handle); + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); - } + } else + up_read(&EXT4_I(inode)->i_mmap_sem); return result; } @@ -246,44 +238,86 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, if (write) { sb_start_pagefault(sb); file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, ext4_chunk_trans_blocks(inode, PMD_SIZE / PAGE_SIZE)); - } + } else + down_read(&EXT4_I(inode)->i_mmap_sem); if (IS_ERR(handle)) result = VM_FAULT_SIGBUS; else result = __dax_pmd_fault(vma, addr, pmd, flags, - ext4_get_block_dax, ext4_end_io_unwritten); + ext4_dax_mmap_get_block, NULL); if (write) { if (!IS_ERR(handle)) ext4_journal_stop(handle); + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(sb); - } + } else + up_read(&EXT4_I(inode)->i_mmap_sem); return result; } static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { - return dax_mkwrite(vma, vmf, ext4_get_block_dax, - ext4_end_io_unwritten); + int err; + struct inode *inode = file_inode(vma->vm_file); + + sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); + err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL); + up_read(&EXT4_I(inode)->i_mmap_sem); + sb_end_pagefault(inode->i_sb); + + return err; +} + +/* + * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite() + * handler we check for races agaist truncate. Note that since we cycle through + * i_mmap_sem, we are sure that also any hole punching that began before we + * were called is finished by now and so if it included part of the file we + * are working on, our pte will get unmapped and the check for pte_same() in + * wp_pfn_shared() fails. Thus fault gets retried and things work out as + * desired. + */ +static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vma->vm_file); + struct super_block *sb = inode->i_sb; + int ret = VM_FAULT_NOPAGE; + loff_t size; + + sb_start_pagefault(sb); + file_update_time(vma->vm_file); + down_read(&EXT4_I(inode)->i_mmap_sem); + size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (vmf->pgoff >= size) + ret = VM_FAULT_SIGBUS; + up_read(&EXT4_I(inode)->i_mmap_sem); + sb_end_pagefault(sb); + + return ret; } static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .pmd_fault = ext4_dax_pmd_fault, .page_mkwrite = ext4_dax_mkwrite, - .pfn_mkwrite = dax_pfn_mkwrite, + .pfn_mkwrite = ext4_dax_pfn_mkwrite, }; #else #define ext4_dax_vm_ops ext4_file_vm_ops #endif static const struct vm_operations_struct ext4_file_vm_ops = { - .fault = filemap_fault, + .fault = ext4_filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ext4_page_mkwrite, }; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 1b8024d26f65..3fcfd50a2e8a 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -799,6 +799,13 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, inode->i_gid = dir->i_gid; } else inode_init_owner(inode, dir, mode); + + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) && + ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) + ei->i_projid = EXT4_I(dir)->i_projid; + else + ei->i_projid = make_kprojid(&init_user_ns, EXT4_DEF_PROJID); + err = dquot_initialize(inode); if (err) goto out; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index d884989cc83d..dfe3b9bafc0d 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -995,12 +995,11 @@ void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, */ static int ext4_add_dirent_to_inline(handle_t *handle, struct ext4_filename *fname, - struct dentry *dentry, + struct inode *dir, struct inode *inode, struct ext4_iloc *iloc, void *inline_start, int inline_size) { - struct inode *dir = d_inode(dentry->d_parent); int err; struct ext4_dir_entry_2 *de; @@ -1245,12 +1244,11 @@ out: * the new created block. */ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, - struct dentry *dentry, struct inode *inode) + struct inode *dir, struct inode *inode) { int ret, inline_size; void *inline_start; struct ext4_iloc iloc; - struct inode *dir = d_inode(dentry->d_parent); ret = ext4_get_inode_loc(dir, &iloc); if (ret) @@ -1264,7 +1262,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; - ret = ext4_add_dirent_to_inline(handle, fname, dentry, inode, &iloc, + ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc, inline_start, inline_size); if (ret != -ENOSPC) goto out; @@ -1285,7 +1283,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, if (inline_size) { inline_start = ext4_get_inline_xattr_pos(dir, &iloc); - ret = ext4_add_dirent_to_inline(handle, fname, dentry, + ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc, inline_start, inline_size); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b3bd912df6bf..d964195ea0e2 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -383,6 +383,21 @@ static int __check_block_validity(struct inode *inode, const char *func, return 0; } +int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, + ext4_lblk_t len) +{ + int ret; + + if (ext4_encrypted_inode(inode)) + return ext4_encrypted_zeroout(inode, lblk, pblk, len); + + ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS); + if (ret > 0) + ret = 0; + + return ret; +} + #define check_block_validity(inode, map) \ __check_block_validity((inode), __func__, __LINE__, (map)) @@ -403,8 +418,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, * out taking i_data_sem. So at the time the unwritten extent * could be converted. */ - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - down_read(&EXT4_I(inode)->i_data_sem); + down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); @@ -412,8 +426,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, retval = ext4_ind_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); } - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - up_read((&EXT4_I(inode)->i_data_sem)); + up_read((&EXT4_I(inode)->i_data_sem)); /* * We don't check m_len because extent will be collpased in status @@ -509,8 +522,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, * Try to see if we can get the block without requesting a new * file system block. */ - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - down_read(&EXT4_I(inode)->i_data_sem); + down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags & EXT4_GET_BLOCKS_KEEP_SIZE); @@ -541,8 +553,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, if (ret < 0) retval = ret; } - if (!(flags & EXT4_GET_BLOCKS_NO_LOCK)) - up_read((&EXT4_I(inode)->i_data_sem)); + up_read((&EXT4_I(inode)->i_data_sem)); found: if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { @@ -626,13 +637,29 @@ found: } /* + * We have to zeroout blocks before inserting them into extent + * status tree. Otherwise someone could look them up there and + * use them before they are really zeroed. + */ + if (flags & EXT4_GET_BLOCKS_ZERO && + map->m_flags & EXT4_MAP_MAPPED && + map->m_flags & EXT4_MAP_NEW) { + ret = ext4_issue_zeroout(inode, map->m_lblk, + map->m_pblk, map->m_len); + if (ret) { + retval = ret; + goto out_sem; + } + } + + /* * If the extent has been zeroed out, we don't need to update * extent status tree. */ if ((flags & EXT4_GET_BLOCKS_PRE_IO) && ext4_es_lookup_extent(inode, map->m_lblk, &es)) { if (ext4_es_is_written(&es)) - goto has_zeroout; + goto out_sem; } status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; @@ -643,11 +670,13 @@ found: status |= EXTENT_STATUS_DELAYED; ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); - if (ret < 0) + if (ret < 0) { retval = ret; + goto out_sem; + } } -has_zeroout: +out_sem: up_write((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { ret = check_block_validity(inode, map); @@ -674,7 +703,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, map.m_lblk = iblock; map.m_len = bh->b_size >> inode->i_blkbits; - if (flags && !(flags & EXT4_GET_BLOCKS_NO_LOCK) && !handle) { + if (flags && !handle) { /* Direct IO write... */ if (map.m_len > DIO_MAX_BLOCKS) map.m_len = DIO_MAX_BLOCKS; @@ -694,16 +723,6 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, map_bh(bh, inode->i_sb, map.m_pblk); bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; - if (IS_DAX(inode) && buffer_unwritten(bh)) { - /* - * dgc: I suspect unwritten conversion on ext4+DAX is - * fundamentally broken here when there are concurrent - * read/write in progress on this inode. - */ - WARN_ON_ONCE(io_end); - bh->b_assoc_map = inode->i_mapping; - bh->b_private = (void *)(unsigned long)iblock; - } if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN) set_buffer_defer_completion(bh); bh->b_size = inode->i_sb->s_blocksize * map.m_len; @@ -879,9 +898,6 @@ int do_journal_get_write_access(handle_t *handle, return ret; } -static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create); - #ifdef CONFIG_EXT4_FS_ENCRYPTION static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) @@ -3054,25 +3070,96 @@ int ext4_get_block_write(struct inode *inode, sector_t iblock, EXT4_GET_BLOCKS_IO_CREATE_EXT); } -static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, +static int ext4_get_block_overwrite(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { - ext4_debug("ext4_get_block_write_nolock: inode %lu, create flag %d\n", + int ret; + + ext4_debug("ext4_get_block_overwrite: inode %lu, create flag %d\n", inode->i_ino, create); - return _ext4_get_block(inode, iblock, bh_result, - EXT4_GET_BLOCKS_NO_LOCK); + ret = _ext4_get_block(inode, iblock, bh_result, 0); + /* + * Blocks should have been preallocated! ext4_file_write_iter() checks + * that. + */ + WARN_ON_ONCE(!buffer_mapped(bh_result)); + + return ret; } -int ext4_get_block_dax(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) +#ifdef CONFIG_FS_DAX +int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) { - int flags = EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_UNWRIT_EXT; - if (create) - flags |= EXT4_GET_BLOCKS_CREATE; - ext4_debug("ext4_get_block_dax: inode %lu, create flag %d\n", + int ret, err; + int credits; + struct ext4_map_blocks map; + handle_t *handle = NULL; + int flags = 0; + + ext4_debug("ext4_dax_mmap_get_block: inode %lu, create flag %d\n", inode->i_ino, create); - return _ext4_get_block(inode, iblock, bh_result, flags); + map.m_lblk = iblock; + map.m_len = bh_result->b_size >> inode->i_blkbits; + credits = ext4_chunk_trans_blocks(inode, map.m_len); + if (create) { + flags |= EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_CREATE_ZERO; + handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + return ret; + } + } + + ret = ext4_map_blocks(handle, inode, &map, flags); + if (create) { + err = ext4_journal_stop(handle); + if (ret >= 0 && err < 0) + ret = err; + } + if (ret <= 0) + goto out; + if (map.m_flags & EXT4_MAP_UNWRITTEN) { + int err2; + + /* + * We are protected by i_mmap_sem so we know block cannot go + * away from under us even though we dropped i_data_sem. + * Convert extent to written and write zeros there. + * + * Note: We may get here even when create == 0. + */ + handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + + err = ext4_map_blocks(handle, inode, &map, + EXT4_GET_BLOCKS_CONVERT | EXT4_GET_BLOCKS_CREATE_ZERO); + if (err < 0) + ret = err; + err2 = ext4_journal_stop(handle); + if (err2 < 0 && ret > 0) + ret = err2; + } +out: + WARN_ON_ONCE(ret == 0 && create); + if (ret > 0) { + map_bh(bh_result, inode->i_sb, map.m_pblk); + bh_result->b_state = (bh_result->b_state & ~EXT4_MAP_FLAGS) | + map.m_flags; + /* + * At least for now we have to clear BH_New so that DAX code + * doesn't attempt to zero blocks again in a racy way. + */ + bh_result->b_state &= ~(1 << BH_New); + bh_result->b_size = map.m_len << inode->i_blkbits; + ret = 0; + } + return ret; } +#endif static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, ssize_t size, void *private) @@ -3143,10 +3230,8 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, /* If we do a overwrite dio, i_mutex locking can be released */ overwrite = *((int *)iocb->private); - if (overwrite) { - down_read(&EXT4_I(inode)->i_data_sem); + if (overwrite) mutex_unlock(&inode->i_mutex); - } /* * We could direct write to holes and fallocate. @@ -3189,7 +3274,7 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, } if (overwrite) { - get_block_func = ext4_get_block_write_nolock; + get_block_func = ext4_get_block_overwrite; } else { get_block_func = ext4_get_block_write; dio_flags = DIO_LOCKING; @@ -3245,10 +3330,8 @@ retake_lock: if (iov_iter_rw(iter) == WRITE) inode_dio_end(inode); /* take i_mutex locking again if we do a ovewrite dio */ - if (overwrite) { - up_read(&EXT4_I(inode)->i_data_sem); + if (overwrite) mutex_lock(&inode->i_mutex); - } return ret; } @@ -3559,6 +3642,35 @@ int ext4_can_truncate(struct inode *inode) } /* + * We have to make sure i_disksize gets properly updated before we truncate + * page cache due to hole punching or zero range. Otherwise i_disksize update + * can get lost as it may have been postponed to submission of writeback but + * that will never happen after we truncate page cache. + */ +int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, + loff_t len) +{ + handle_t *handle; + loff_t size = i_size_read(inode); + + WARN_ON(!mutex_is_locked(&inode->i_mutex)); + if (offset > size || offset + len < size) + return 0; + + if (EXT4_I(inode)->i_disksize >= size) + return 0; + + handle = ext4_journal_start(inode, EXT4_HT_MISC, 1); + if (IS_ERR(handle)) + return PTR_ERR(handle); + ext4_update_i_disksize(inode, size); + ext4_mark_inode_dirty(handle, inode); + ext4_journal_stop(handle); + + return 0; +} + +/* * ext4_punch_hole: punches a hole in a file by releaseing the blocks * associated with the given offset and length * @@ -3623,17 +3735,26 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) } + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + + /* + * Prevent page faults from reinstantiating pages we have released from + * page cache. + */ + down_write(&EXT4_I(inode)->i_mmap_sem); first_block_offset = round_up(offset, sb->s_blocksize); last_block_offset = round_down((offset + length), sb->s_blocksize) - 1; /* Now release the pages and zero block aligned part of pages*/ - if (last_block_offset > first_block_offset) + if (last_block_offset > first_block_offset) { + ret = ext4_update_disksize_before_punch(inode, offset, length); + if (ret) + goto out_dio; truncate_pagecache_range(inode, first_block_offset, last_block_offset); - - /* Wait all existing dio workers, newcomers will block on i_mutex */ - ext4_inode_block_unlocked_dio(inode); - inode_dio_wait(inode); + } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_writepage_trans_blocks(inode); @@ -3680,16 +3801,12 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) if (IS_SYNC(inode)) ext4_handle_sync(handle); - /* Now release the pages again to reduce race window */ - if (last_block_offset > first_block_offset) - truncate_pagecache_range(inode, first_block_offset, - last_block_offset); - inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); out_stop: ext4_journal_stop(handle); out_dio: + up_write(&EXT4_I(inode)->i_mmap_sem); ext4_inode_resume_unlocked_dio(inode); out_mutex: mutex_unlock(&inode->i_mutex); @@ -4076,6 +4193,14 @@ static inline void ext4_iget_extra_inode(struct inode *inode, EXT4_I(inode)->i_inline_off = 0; } +int ext4_get_projid(struct inode *inode, kprojid_t *projid) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_PROJECT)) + return -EOPNOTSUPP; + *projid = EXT4_I(inode)->i_projid; + return 0; +} + struct inode *ext4_iget(struct super_block *sb, unsigned long ino) { struct ext4_iloc iloc; @@ -4087,6 +4212,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) int block; uid_t i_uid; gid_t i_gid; + projid_t i_projid; inode = iget_locked(sb, ino); if (!inode) @@ -4136,12 +4262,20 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_mode = le16_to_cpu(raw_inode->i_mode); i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) && + EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) + i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid); + else + i_projid = EXT4_DEF_PROJID; + if (!(test_opt(inode->i_sb, NO_UID32))) { i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); + ei->i_projid = make_kprojid(&init_user_ns, i_projid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ @@ -4440,6 +4574,7 @@ static int ext4_do_update_inode(handle_t *handle, int need_datasync = 0, set_large_file = 0; uid_t i_uid; gid_t i_gid; + projid_t i_projid; spin_lock(&ei->i_raw_lock); @@ -4452,6 +4587,7 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_mode = cpu_to_le16(inode->i_mode); i_uid = i_uid_read(inode); i_gid = i_gid_read(inode); + i_projid = from_kprojid(&init_user_ns, ei->i_projid); if (!(test_opt(inode->i_sb, NO_UID32))) { raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); @@ -4529,6 +4665,15 @@ static int ext4_do_update_inode(handle_t *handle, cpu_to_le16(ei->i_extra_isize); } } + + BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_PROJECT) && + i_projid != EXT4_DEF_PROJID); + + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) + raw_inode->i_projid = cpu_to_le32(i_projid); + ext4_inode_csum_set(inode, raw_inode, ei); spin_unlock(&ei->i_raw_lock); if (inode->i_sb->s_flags & MS_LAZYTIME) @@ -4824,6 +4969,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } else ext4_wait_for_tail_page_commit(inode); } + down_write(&EXT4_I(inode)->i_mmap_sem); /* * Truncate pagecache after we've waited for commit * in data=journal mode to make pages freeable. @@ -4831,6 +4977,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) truncate_pagecache(inode, inode->i_size); if (shrink) ext4_truncate(inode); + up_write(&EXT4_I(inode)->i_mmap_sem); } if (!rc) { @@ -5279,6 +5426,8 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); file_update_time(vma->vm_file); + + down_read(&EXT4_I(inode)->i_mmap_sem); /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && @@ -5348,6 +5497,19 @@ retry_alloc: out_ret: ret = block_page_mkwrite_return(ret); out: + up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(inode->i_sb); return ret; } + +int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vma->vm_file); + int err; + + down_read(&EXT4_I(inode)->i_mmap_sem); + err = filemap_fault(vma, vmf); + up_read(&EXT4_I(inode)->i_mmap_sem); + + return err; +} diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 5e872fd40e5e..2b0cb84255eb 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -14,6 +14,7 @@ #include <linux/mount.h> #include <linux/file.h> #include <linux/random.h> +#include <linux/quotaops.h> #include <asm/uaccess.h> #include "ext4_jbd2.h" #include "ext4.h" @@ -202,6 +203,238 @@ static int uuid_is_zero(__u8 u[16]) return 1; } +static int ext4_ioctl_setflags(struct inode *inode, + unsigned int flags) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + handle_t *handle = NULL; + int err = EPERM, migrate = 0; + struct ext4_iloc iloc; + unsigned int oldflags, mask, i; + unsigned int jflag; + + /* Is it quota file? Do not allow user to mess with it */ + if (IS_NOQUOTA(inode)) + goto flags_out; + + oldflags = ei->i_flags; + + /* The JOURNAL_DATA flag is modifiable only by root */ + jflag = flags & EXT4_JOURNAL_DATA_FL; + + /* + * The IMMUTABLE and APPEND_ONLY flags can only be changed by + * the relevant capability. + * + * This test looks nicer. Thanks to Pauline Middelink + */ + if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) { + if (!capable(CAP_LINUX_IMMUTABLE)) + goto flags_out; + } + + /* + * The JOURNAL_DATA flag can only be changed by + * the relevant capability. + */ + if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { + if (!capable(CAP_SYS_RESOURCE)) + goto flags_out; + } + if ((flags ^ oldflags) & EXT4_EXTENTS_FL) + migrate = 1; + + if (flags & EXT4_EOFBLOCKS_FL) { + /* we don't support adding EOFBLOCKS flag */ + if (!(oldflags & EXT4_EOFBLOCKS_FL)) { + err = -EOPNOTSUPP; + goto flags_out; + } + } else if (oldflags & EXT4_EOFBLOCKS_FL) + ext4_truncate(inode); + + handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto flags_out; + } + if (IS_SYNC(inode)) + ext4_handle_sync(handle); + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + goto flags_err; + + for (i = 0, mask = 1; i < 32; i++, mask <<= 1) { + if (!(mask & EXT4_FL_USER_MODIFIABLE)) + continue; + if (mask & flags) + ext4_set_inode_flag(inode, i); + else + ext4_clear_inode_flag(inode, i); + } + + ext4_set_inode_flags(inode); + inode->i_ctime = ext4_current_time(inode); + + err = ext4_mark_iloc_dirty(handle, inode, &iloc); +flags_err: + ext4_journal_stop(handle); + if (err) + goto flags_out; + + if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) + err = ext4_change_inode_journal_flag(inode, jflag); + if (err) + goto flags_out; + if (migrate) { + if (flags & EXT4_EXTENTS_FL) + err = ext4_ext_migrate(inode); + else + err = ext4_ind_migrate(inode); + } + +flags_out: + return err; +} + +#ifdef CONFIG_QUOTA +static int ext4_ioctl_setproject(struct file *filp, __u32 projid) +{ + struct inode *inode = file_inode(filp); + struct super_block *sb = inode->i_sb; + struct ext4_inode_info *ei = EXT4_I(inode); + int err, rc; + handle_t *handle; + kprojid_t kprojid; + struct ext4_iloc iloc; + struct ext4_inode *raw_inode; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_PROJECT)) { + if (projid != EXT4_DEF_PROJID) + return -EOPNOTSUPP; + else + return 0; + } + + if (EXT4_INODE_SIZE(sb) <= EXT4_GOOD_OLD_INODE_SIZE) + return -EOPNOTSUPP; + + kprojid = make_kprojid(&init_user_ns, (projid_t)projid); + + if (projid_eq(kprojid, EXT4_I(inode)->i_projid)) + return 0; + + err = mnt_want_write_file(filp); + if (err) + return err; + + err = -EPERM; + mutex_lock(&inode->i_mutex); + /* Is it quota file? Do not allow user to mess with it */ + if (IS_NOQUOTA(inode)) + goto out_unlock; + + err = ext4_get_inode_loc(inode, &iloc); + if (err) + goto out_unlock; + + raw_inode = ext4_raw_inode(&iloc); + if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) { + err = -EOVERFLOW; + brelse(iloc.bh); + goto out_unlock; + } + brelse(iloc.bh); + + dquot_initialize(inode); + + handle = ext4_journal_start(inode, EXT4_HT_QUOTA, + EXT4_QUOTA_INIT_BLOCKS(sb) + + EXT4_QUOTA_DEL_BLOCKS(sb) + 3); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out_unlock; + } + + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + goto out_stop; + + if (sb_has_quota_limits_enabled(sb, PRJQUOTA)) { + struct dquot *transfer_to[MAXQUOTAS] = { }; + + transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); + if (transfer_to[PRJQUOTA]) { + err = __dquot_transfer(inode, transfer_to); + dqput(transfer_to[PRJQUOTA]); + if (err) + goto out_dirty; + } + } + EXT4_I(inode)->i_projid = kprojid; + inode->i_ctime = ext4_current_time(inode); +out_dirty: + rc = ext4_mark_iloc_dirty(handle, inode, &iloc); + if (!err) + err = rc; +out_stop: + ext4_journal_stop(handle); +out_unlock: + mutex_unlock(&inode->i_mutex); + mnt_drop_write_file(filp); + return err; +} +#else +static int ext4_ioctl_setproject(struct file *filp, __u32 projid) +{ + if (projid != EXT4_DEF_PROJID) + return -EOPNOTSUPP; + return 0; +} +#endif + +/* Transfer internal flags to xflags */ +static inline __u32 ext4_iflags_to_xflags(unsigned long iflags) +{ + __u32 xflags = 0; + + if (iflags & EXT4_SYNC_FL) + xflags |= FS_XFLAG_SYNC; + if (iflags & EXT4_IMMUTABLE_FL) + xflags |= FS_XFLAG_IMMUTABLE; + if (iflags & EXT4_APPEND_FL) + xflags |= FS_XFLAG_APPEND; + if (iflags & EXT4_NODUMP_FL) + xflags |= FS_XFLAG_NODUMP; + if (iflags & EXT4_NOATIME_FL) + xflags |= FS_XFLAG_NOATIME; + if (iflags & EXT4_PROJINHERIT_FL) + xflags |= FS_XFLAG_PROJINHERIT; + return xflags; +} + +/* Transfer xflags flags to internal */ +static inline unsigned long ext4_xflags_to_iflags(__u32 xflags) +{ + unsigned long iflags = 0; + + if (xflags & FS_XFLAG_SYNC) + iflags |= EXT4_SYNC_FL; + if (xflags & FS_XFLAG_IMMUTABLE) + iflags |= EXT4_IMMUTABLE_FL; + if (xflags & FS_XFLAG_APPEND) + iflags |= EXT4_APPEND_FL; + if (xflags & FS_XFLAG_NODUMP) + iflags |= EXT4_NODUMP_FL; + if (xflags & FS_XFLAG_NOATIME) + iflags |= EXT4_NOATIME_FL; + if (xflags & FS_XFLAG_PROJINHERIT) + iflags |= EXT4_PROJINHERIT_FL; + + return iflags; +} + long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -217,11 +450,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) flags = ei->i_flags & EXT4_FL_USER_VISIBLE; return put_user(flags, (int __user *) arg); case EXT4_IOC_SETFLAGS: { - handle_t *handle = NULL; - int err, migrate = 0; - struct ext4_iloc iloc; - unsigned int oldflags, mask, i; - unsigned int jflag; + int err; if (!inode_owner_or_capable(inode)) return -EACCES; @@ -235,89 +464,8 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) flags = ext4_mask_flags(inode->i_mode, flags); - err = -EPERM; mutex_lock(&inode->i_mutex); - /* Is it quota file? Do not allow user to mess with it */ - if (IS_NOQUOTA(inode)) - goto flags_out; - - oldflags = ei->i_flags; - - /* The JOURNAL_DATA flag is modifiable only by root */ - jflag = flags & EXT4_JOURNAL_DATA_FL; - - /* - * The IMMUTABLE and APPEND_ONLY flags can only be changed by - * the relevant capability. - * - * This test looks nicer. Thanks to Pauline Middelink - */ - if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) { - if (!capable(CAP_LINUX_IMMUTABLE)) - goto flags_out; - } - - /* - * The JOURNAL_DATA flag can only be changed by - * the relevant capability. - */ - if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { - if (!capable(CAP_SYS_RESOURCE)) - goto flags_out; - } - if ((flags ^ oldflags) & EXT4_EXTENTS_FL) - migrate = 1; - - if (flags & EXT4_EOFBLOCKS_FL) { - /* we don't support adding EOFBLOCKS flag */ - if (!(oldflags & EXT4_EOFBLOCKS_FL)) { - err = -EOPNOTSUPP; - goto flags_out; - } - } else if (oldflags & EXT4_EOFBLOCKS_FL) - ext4_truncate(inode); - - handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); - if (IS_ERR(handle)) { - err = PTR_ERR(handle); - goto flags_out; - } - if (IS_SYNC(inode)) - ext4_handle_sync(handle); - err = ext4_reserve_inode_write(handle, inode, &iloc); - if (err) - goto flags_err; - - for (i = 0, mask = 1; i < 32; i++, mask <<= 1) { - if (!(mask & EXT4_FL_USER_MODIFIABLE)) - continue; - if (mask & flags) - ext4_set_inode_flag(inode, i); - else - ext4_clear_inode_flag(inode, i); - } - - ext4_set_inode_flags(inode); - inode->i_ctime = ext4_current_time(inode); - - err = ext4_mark_iloc_dirty(handle, inode, &iloc); -flags_err: - ext4_journal_stop(handle); - if (err) - goto flags_out; - - if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) - err = ext4_change_inode_journal_flag(inode, jflag); - if (err) - goto flags_out; - if (migrate) { - if (flags & EXT4_EXTENTS_FL) - err = ext4_ext_migrate(inode); - else - err = ext4_ind_migrate(inode); - } - -flags_out: + err = ext4_ioctl_setflags(inode, flags); mutex_unlock(&inode->i_mutex); mnt_drop_write_file(filp); return err; @@ -689,6 +837,60 @@ encryption_policy_out: return -EOPNOTSUPP; #endif } + case EXT4_IOC_FSGETXATTR: + { + struct fsxattr fa; + + memset(&fa, 0, sizeof(struct fsxattr)); + ext4_get_inode_flags(ei); + fa.fsx_xflags = ext4_iflags_to_xflags(ei->i_flags & EXT4_FL_USER_VISIBLE); + + if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_PROJECT)) { + fa.fsx_projid = (__u32)from_kprojid(&init_user_ns, + EXT4_I(inode)->i_projid); + } + + if (copy_to_user((struct fsxattr __user *)arg, + &fa, sizeof(fa))) + return -EFAULT; + return 0; + } + case EXT4_IOC_FSSETXATTR: + { + struct fsxattr fa; + int err; + + if (copy_from_user(&fa, (struct fsxattr __user *)arg, + sizeof(fa))) + return -EFAULT; + + /* Make sure caller has proper permission */ + if (!inode_owner_or_capable(inode)) + return -EACCES; + + err = mnt_want_write_file(filp); + if (err) + return err; + + flags = ext4_xflags_to_iflags(fa.fsx_xflags); + flags = ext4_mask_flags(inode->i_mode, flags); + + mutex_lock(&inode->i_mutex); + flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) | + (flags & EXT4_FL_XFLAG_VISIBLE); + err = ext4_ioctl_setflags(inode, flags); + mutex_unlock(&inode->i_mutex); + mnt_drop_write_file(filp); + if (err) + return err; + + err = ext4_ioctl_setproject(filp, fa.fsx_projid); + if (err) + return err; + + return 0; + } default: return -ENOTTY; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index f27e0c2598c5..854f75de4599 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -273,7 +273,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir); static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, - struct dentry *dentry, struct inode *inode); + struct inode *dir, struct inode *inode); /* checksumming functions */ void initialize_dirent_tail(struct ext4_dir_entry_tail *t, @@ -1928,10 +1928,9 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, * directory, and adds the dentry to the indexed directory. */ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, - struct dentry *dentry, + struct inode *dir, struct inode *inode, struct buffer_head *bh) { - struct inode *dir = d_inode(dentry->d_parent); struct buffer_head *bh2; struct dx_root *root; struct dx_frame frames[2], *frame; @@ -2086,8 +2085,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, return retval; if (ext4_has_inline_data(dir)) { - retval = ext4_try_add_inline_entry(handle, &fname, - dentry, inode); + retval = ext4_try_add_inline_entry(handle, &fname, dir, inode); if (retval < 0) goto out; if (retval == 1) { @@ -2097,7 +2095,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, } if (is_dx(dir)) { - retval = ext4_dx_add_entry(handle, &fname, dentry, inode); + retval = ext4_dx_add_entry(handle, &fname, dir, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) goto out; ext4_clear_inode_flag(dir, EXT4_INODE_INDEX); @@ -2119,7 +2117,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, if (blocks == 1 && !dx_fallback && ext4_has_feature_dir_index(sb)) { - retval = make_indexed_dir(handle, &fname, dentry, + retval = make_indexed_dir(handle, &fname, dir, inode, bh); bh = NULL; /* make_indexed_dir releases bh */ goto out; @@ -2154,12 +2152,11 @@ out: * Returns 0 for success, or a negative error value */ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, - struct dentry *dentry, struct inode *inode) + struct inode *dir, struct inode *inode) { struct dx_frame frames[2], *frame; struct dx_entry *entries, *at; struct buffer_head *bh; - struct inode *dir = d_inode(dentry->d_parent); struct super_block *sb = dir->i_sb; struct ext4_dir_entry_2 *de; int err; @@ -3212,6 +3209,12 @@ static int ext4_link(struct dentry *old_dentry, if (ext4_encrypted_inode(dir) && !ext4_is_child_context_consistent_with_parent(dir, inode)) return -EPERM; + + if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) && + (!projid_eq(EXT4_I(dir)->i_projid, + EXT4_I(old_dentry->d_inode)->i_projid))) + return -EXDEV; + err = dquot_initialize(dir); if (err) return err; @@ -3492,6 +3495,11 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, int credits; u8 old_file_type; + if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT)) && + (!projid_eq(EXT4_I(new_dir)->i_projid, + EXT4_I(old_dentry->d_inode)->i_projid))) + return -EXDEV; + retval = dquot_initialize(old.dir); if (retval) return retval; @@ -3701,6 +3709,14 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, new.inode))) return -EPERM; + if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT) && + !projid_eq(EXT4_I(new_dir)->i_projid, + EXT4_I(old_dentry->d_inode)->i_projid)) || + (ext4_test_inode_flag(old_dir, EXT4_INODE_PROJINHERIT) && + !projid_eq(EXT4_I(old_dir)->i_projid, + EXT4_I(new_dentry->d_inode)->i_projid))) + return -EXDEV; + retval = dquot_initialize(old.dir); if (retval) return retval; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f1b56ff01208..00c98fab6333 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -80,6 +80,36 @@ static void ext4_destroy_lazyinit_thread(void); static void ext4_unregister_li_request(struct super_block *sb); static void ext4_clear_request_list(void); +/* + * Lock ordering + * + * Note the difference between i_mmap_sem (EXT4_I(inode)->i_mmap_sem) and + * i_mmap_rwsem (inode->i_mmap_rwsem)! + * + * page fault path: + * mmap_sem -> sb_start_pagefault -> i_mmap_sem (r) -> transaction start -> + * page lock -> i_data_sem (rw) + * + * buffered write path: + * sb_start_write -> i_mutex -> mmap_sem + * sb_start_write -> i_mutex -> transaction start -> page lock -> + * i_data_sem (rw) + * + * truncate: + * sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (w) -> i_mmap_sem (w) -> + * i_mmap_rwsem (w) -> page lock + * sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (w) -> i_mmap_sem (w) -> + * transaction start -> i_data_sem (rw) + * + * direct IO: + * sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (r) -> mmap_sem + * sb_start_write -> i_mutex -> EXT4_STATE_DIOREAD_LOCK (r) -> + * transaction start -> i_data_sem (rw) + * + * writepages: + * transaction start -> page lock(s) -> i_data_sem (rw) + */ + #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT2) static struct file_system_type ext2_fs_type = { .owner = THIS_MODULE, @@ -958,6 +988,7 @@ static void init_once(void *foo) INIT_LIST_HEAD(&ei->i_orphan); init_rwsem(&ei->xattr_sem); init_rwsem(&ei->i_data_sem); + init_rwsem(&ei->i_mmap_sem); inode_init_once(&ei->vfs_inode); } @@ -1066,8 +1097,8 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, } #ifdef CONFIG_QUOTA -#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group") -#define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA)) +static char *quotatypes[] = INITQFNAMES; +#define QTYPE2NAME(t) (quotatypes[t]) static int ext4_write_dquot(struct dquot *dquot); static int ext4_acquire_dquot(struct dquot *dquot); @@ -1100,6 +1131,7 @@ static const struct dquot_operations ext4_quota_operations = { .write_info = ext4_write_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, + .get_projid = ext4_get_projid, }; static const struct quotactl_ops ext4_qctl_operations = { @@ -2526,6 +2558,12 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) "without CONFIG_QUOTA"); return 0; } + if (ext4_has_feature_project(sb) && !readonly) { + ext4_msg(sb, KERN_ERR, + "Filesystem with project quota feature cannot be mounted RDWR " + "without CONFIG_QUOTA"); + return 0; + } #endif /* CONFIG_QUOTA */ return 1; } @@ -3654,7 +3692,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_qcop = &dquot_quotactl_sysfile_ops; else sb->s_qcop = &ext4_qctl_operations; - sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; + sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); @@ -4790,6 +4828,48 @@ restore_opts: return err; } +#ifdef CONFIG_QUOTA +static int ext4_statfs_project(struct super_block *sb, + kprojid_t projid, struct kstatfs *buf) +{ + struct kqid qid; + struct dquot *dquot; + u64 limit; + u64 curblock; + + qid = make_kqid_projid(projid); + dquot = dqget(sb, qid); + if (IS_ERR(dquot)) + return PTR_ERR(dquot); + spin_lock(&dq_data_lock); + + limit = (dquot->dq_dqb.dqb_bsoftlimit ? + dquot->dq_dqb.dqb_bsoftlimit : + dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits; + if (limit && buf->f_blocks > limit) { + curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits; + buf->f_blocks = limit; + buf->f_bfree = buf->f_bavail = + (buf->f_blocks > curblock) ? + (buf->f_blocks - curblock) : 0; + } + + limit = dquot->dq_dqb.dqb_isoftlimit ? + dquot->dq_dqb.dqb_isoftlimit : + dquot->dq_dqb.dqb_ihardlimit; + if (limit && buf->f_files > limit) { + buf->f_files = limit; + buf->f_ffree = + (buf->f_files > dquot->dq_dqb.dqb_curinodes) ? + (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0; + } + + spin_unlock(&dq_data_lock); + dqput(dquot); + return 0; +} +#endif + static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; @@ -4822,6 +4902,11 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL; buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL; +#ifdef CONFIG_QUOTA + if (ext4_test_inode_flag(dentry->d_inode, EXT4_INODE_PROJINHERIT) && + sb_has_quota_limits_enabled(sb, PRJQUOTA)) + ext4_statfs_project(sb, EXT4_I(dentry->d_inode)->i_projid, buf); +#endif return 0; } @@ -4986,7 +5071,8 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, struct inode *qf_inode; unsigned long qf_inums[EXT4_MAXQUOTAS] = { le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), - le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum) + le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum), + le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum) }; BUG_ON(!ext4_has_feature_quota(sb)); @@ -5014,7 +5100,8 @@ static int ext4_enable_quotas(struct super_block *sb) int type, err = 0; unsigned long qf_inums[EXT4_MAXQUOTAS] = { le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum), - le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum) + le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum), + le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum) }; sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h index 011ba6670d99..c70d06a383e2 100644 --- a/fs/ext4/truncate.h +++ b/fs/ext4/truncate.h @@ -10,8 +10,10 @@ */ static inline void ext4_truncate_failed_write(struct inode *inode) { + down_write(&EXT4_I(inode)->i_mmap_sem); truncate_inode_pages(inode->i_mapping, inode->i_size); ext4_truncate(inode); + up_write(&EXT4_I(inode)->i_mmap_sem); } /* diff --git a/fs/filesystems.c b/fs/filesystems.c index 5797d45a78cb..c5618db110be 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -46,9 +46,9 @@ void put_filesystem(struct file_system_type *fs) static struct file_system_type **find_filesystem(const char *name, unsigned len) { struct file_system_type **p; - for (p=&file_systems; *p; p=&(*p)->next) - if (strlen((*p)->name) == len && - strncmp((*p)->name, name, len) == 0) + for (p = &file_systems; *p; p = &(*p)->next) + if (strncmp((*p)->name, name, len) == 0 && + !(*p)->name[len]) break; return p; } diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index f92612e4b9d6..474e57f834e6 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1390,6 +1390,7 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb, unsigned int gen; int noqueue_attempted = 0; int dlm_locked = 0; + int kick_dc = 0; if (!(lockres->l_flags & OCFS2_LOCK_INITIALIZED)) { mlog_errno(-EINVAL); @@ -1524,7 +1525,12 @@ update_holders: unlock: lockres_clear_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING); + /* ocfs2_unblock_lock reques on seeing OCFS2_LOCK_UPCONVERT_FINISHING */ + kick_dc = (lockres->l_flags & OCFS2_LOCK_BLOCKED); + spin_unlock_irqrestore(&lockres->l_lock, flags); + if (kick_dc) + ocfs2_wake_downconvert_thread(osb); out: /* * This is helping work around a lock inversion between the page lock diff --git a/fs/pipe.c b/fs/pipe.c index 42cf8ddf0e55..ab8dad3ccb6a 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -38,6 +38,12 @@ unsigned int pipe_max_size = 1048576; */ unsigned int pipe_min_size = PAGE_SIZE; +/* Maximum allocatable pages per user. Hard limit is unset by default, soft + * matches default values. + */ +unsigned long pipe_user_pages_hard; +unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; + /* * We use a start+len construction, which provides full use of the * allocated memory. @@ -583,20 +589,49 @@ pipe_fasync(int fd, struct file *filp, int on) return retval; } +static void account_pipe_buffers(struct pipe_inode_info *pipe, + unsigned long old, unsigned long new) +{ + atomic_long_add(new - old, &pipe->user->pipe_bufs); +} + +static bool too_many_pipe_buffers_soft(struct user_struct *user) +{ + return pipe_user_pages_soft && + atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_soft; +} + +static bool too_many_pipe_buffers_hard(struct user_struct *user) +{ + return pipe_user_pages_hard && + atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_hard; +} + struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL); if (pipe) { - pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * PIPE_DEF_BUFFERS, GFP_KERNEL); + unsigned long pipe_bufs = PIPE_DEF_BUFFERS; + struct user_struct *user = get_current_user(); + + if (!too_many_pipe_buffers_hard(user)) { + if (too_many_pipe_buffers_soft(user)) + pipe_bufs = 1; + pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * pipe_bufs, GFP_KERNEL); + } + if (pipe->bufs) { init_waitqueue_head(&pipe->wait); pipe->r_counter = pipe->w_counter = 1; - pipe->buffers = PIPE_DEF_BUFFERS; + pipe->buffers = pipe_bufs; + pipe->user = user; + account_pipe_buffers(pipe, 0, pipe_bufs); mutex_init(&pipe->mutex); return pipe; } + free_uid(user); kfree(pipe); } @@ -607,6 +642,8 @@ void free_pipe_info(struct pipe_inode_info *pipe) { int i; + account_pipe_buffers(pipe, pipe->buffers, 0); + free_uid(pipe->user); for (i = 0; i < pipe->buffers; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) @@ -998,6 +1035,7 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages) memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer)); } + account_pipe_buffers(pipe, pipe->buffers, nr_pages); pipe->curbuf = 0; kfree(pipe->bufs); pipe->bufs = bufs; @@ -1069,6 +1107,11 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) { ret = -EPERM; goto out; + } else if ((too_many_pipe_buffers_hard(pipe->user) || + too_many_pipe_buffers_soft(pipe->user)) && + !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out; } ret = pipe_set_size(pipe, nr_pages); break; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 71ffc91060f6..85d16c67c33e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -602,7 +602,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pte_t *pte; spinlock_t *ptl; - if (pmd_trans_huge_lock(pmd, vma, &ptl)) { + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { smaps_pmd_entry(pmd, addr, walk); spin_unlock(ptl); return 0; @@ -913,7 +914,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, spinlock_t *ptl; struct page *page; - if (pmd_trans_huge_lock(pmd, vma, &ptl)) { + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { if (cp->type == CLEAR_REFS_SOFT_DIRTY) { clear_soft_dirty_pmd(vma, addr, pmd); goto out; @@ -1187,7 +1189,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, int err = 0; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (pmd_trans_huge_lock(pmdp, vma, &ptl)) { + ptl = pmd_trans_huge_lock(pmdp, vma); + if (ptl) { u64 flags = 0, frame = 0; pmd_t pmd = *pmdp; @@ -1519,7 +1522,8 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, pte_t *orig_pte; pte_t *pte; - if (pmd_trans_huge_lock(pmd, vma, &ptl)) { + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { pte_t huge_pte = *(pte_t *)pmd; struct page *page; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 05db7473bcb5..c0306ec8ed7b 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -288,7 +288,7 @@ static int finish_unfinished(struct super_block *s) pathrelse(&path); inode = reiserfs_iget(s, &obj_key); - if (!inode) { + if (IS_ERR_OR_NULL(inode)) { /* * the unlink almost completed, it just did not * manage to remove "save" link and release objectid diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index e2536bb1c760..dc97eb21af07 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -984,8 +984,6 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev) /* * Values for di_flags - * There should be a one-to-one correspondence between these flags and the - * XFS_XFLAG_s. */ #define XFS_DIFLAG_REALTIME_BIT 0 /* file's blocks come from rt area */ #define XFS_DIFLAG_PREALLOC_BIT 1 /* file space has been preallocated */ @@ -1026,6 +1024,15 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev) XFS_DIFLAG_EXTSZINHERIT | XFS_DIFLAG_NODEFRAG | XFS_DIFLAG_FILESTREAM) /* + * Values for di_flags2 These start by being exposed to userspace in the upper + * 16 bits of the XFS_XFLAG_s range. + */ +#define XFS_DIFLAG2_DAX_BIT 0 /* use DAX for this inode */ +#define XFS_DIFLAG2_DAX (1 << XFS_DIFLAG2_DAX_BIT) + +#define XFS_DIFLAG2_ANY (XFS_DIFLAG2_DAX) + +/* * Inode number format: * low inopblog bits - offset in block * next agblklog bits - block number in ag diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index b2b73a998d42..fffe3d01bd9f 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -36,40 +36,6 @@ struct dioattr { #endif /* - * Structure for XFS_IOC_FSGETXATTR[A] and XFS_IOC_FSSETXATTR. - */ -#ifndef HAVE_FSXATTR -struct fsxattr { - __u32 fsx_xflags; /* xflags field value (get/set) */ - __u32 fsx_extsize; /* extsize field value (get/set)*/ - __u32 fsx_nextents; /* nextents field value (get) */ - __u32 fsx_projid; /* project identifier (get/set) */ - unsigned char fsx_pad[12]; -}; -#endif - -/* - * Flags for the bs_xflags/fsx_xflags field - * There should be a one-to-one correspondence between these flags and the - * XFS_DIFLAG_s. - */ -#define XFS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */ -#define XFS_XFLAG_PREALLOC 0x00000002 /* preallocated file extents */ -#define XFS_XFLAG_IMMUTABLE 0x00000008 /* file cannot be modified */ -#define XFS_XFLAG_APPEND 0x00000010 /* all writes append */ -#define XFS_XFLAG_SYNC 0x00000020 /* all writes synchronous */ -#define XFS_XFLAG_NOATIME 0x00000040 /* do not update access time */ -#define XFS_XFLAG_NODUMP 0x00000080 /* do not include in backups */ -#define XFS_XFLAG_RTINHERIT 0x00000100 /* create with rt bit set */ -#define XFS_XFLAG_PROJINHERIT 0x00000200 /* create with parents projid */ -#define XFS_XFLAG_NOSYMLINKS 0x00000400 /* disallow symlink creation */ -#define XFS_XFLAG_EXTSIZE 0x00000800 /* extent size allocator hint */ -#define XFS_XFLAG_EXTSZINHERIT 0x00001000 /* inherit inode extent size */ -#define XFS_XFLAG_NODEFRAG 0x00002000 /* do not defragment */ -#define XFS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ -#define XFS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ - -/* * Structure for XFS_IOC_GETBMAP. * On input, fill in bmv_offset and bmv_length of the first structure * to indicate the area of interest in the file, and bmv_entries with @@ -514,8 +480,8 @@ typedef struct xfs_swapext #define XFS_IOC_ALLOCSP _IOW ('X', 10, struct xfs_flock64) #define XFS_IOC_FREESP _IOW ('X', 11, struct xfs_flock64) #define XFS_IOC_DIOINFO _IOR ('X', 30, struct dioattr) -#define XFS_IOC_FSGETXATTR _IOR ('X', 31, struct fsxattr) -#define XFS_IOC_FSSETXATTR _IOW ('X', 32, struct fsxattr) +#define XFS_IOC_FSGETXATTR FS_IOC_FSGETXATTR +#define XFS_IOC_FSSETXATTR FS_IOC_FSSETXATTR #define XFS_IOC_ALLOCSP64 _IOW ('X', 36, struct xfs_flock64) #define XFS_IOC_FREESP64 _IOW ('X', 37, struct xfs_flock64) #define XFS_IOC_GETBMAP _IOWR('X', 38, struct getbmap) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index daed4bfb85b2..435c7de42e5f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1527,6 +1527,16 @@ xfs_wait_buftarg( LIST_HEAD(dispose); int loop = 0; + /* + * We need to flush the buffer workqueue to ensure that all IO + * completion processing is 100% done. Just waiting on buffer locks is + * not sufficient for async IO as the reference count held over IO is + * not released until after the buffer lock is dropped. Hence we need to + * ensure here that all reference counts have been dropped before we + * start walking the LRU list. + */ + drain_workqueue(btp->bt_mount->m_buf_workqueue); + /* loop until there is nothing left on the lru list. */ while (list_lru_count(&btp->bt_lru)) { list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele, diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index ae3758a90ed6..ceba1a83cacc 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -610,60 +610,69 @@ __xfs_iflock( STATIC uint _xfs_dic2xflags( - __uint16_t di_flags) + __uint16_t di_flags, + uint64_t di_flags2, + bool has_attr) { uint flags = 0; if (di_flags & XFS_DIFLAG_ANY) { if (di_flags & XFS_DIFLAG_REALTIME) - flags |= XFS_XFLAG_REALTIME; + flags |= FS_XFLAG_REALTIME; if (di_flags & XFS_DIFLAG_PREALLOC) - flags |= XFS_XFLAG_PREALLOC; + flags |= FS_XFLAG_PREALLOC; if (di_flags & XFS_DIFLAG_IMMUTABLE) - flags |= XFS_XFLAG_IMMUTABLE; + flags |= FS_XFLAG_IMMUTABLE; if (di_flags & XFS_DIFLAG_APPEND) - flags |= XFS_XFLAG_APPEND; + flags |= FS_XFLAG_APPEND; if (di_flags & XFS_DIFLAG_SYNC) - flags |= XFS_XFLAG_SYNC; + flags |= FS_XFLAG_SYNC; if (di_flags & XFS_DIFLAG_NOATIME) - flags |= XFS_XFLAG_NOATIME; + flags |= FS_XFLAG_NOATIME; if (di_flags & XFS_DIFLAG_NODUMP) - flags |= XFS_XFLAG_NODUMP; + flags |= FS_XFLAG_NODUMP; if (di_flags & XFS_DIFLAG_RTINHERIT) - flags |= XFS_XFLAG_RTINHERIT; + flags |= FS_XFLAG_RTINHERIT; if (di_flags & XFS_DIFLAG_PROJINHERIT) - flags |= XFS_XFLAG_PROJINHERIT; + flags |= FS_XFLAG_PROJINHERIT; if (di_flags & XFS_DIFLAG_NOSYMLINKS) - flags |= XFS_XFLAG_NOSYMLINKS; + flags |= FS_XFLAG_NOSYMLINKS; if (di_flags & XFS_DIFLAG_EXTSIZE) - flags |= XFS_XFLAG_EXTSIZE; + flags |= FS_XFLAG_EXTSIZE; if (di_flags & XFS_DIFLAG_EXTSZINHERIT) - flags |= XFS_XFLAG_EXTSZINHERIT; + flags |= FS_XFLAG_EXTSZINHERIT; if (di_flags & XFS_DIFLAG_NODEFRAG) - flags |= XFS_XFLAG_NODEFRAG; + flags |= FS_XFLAG_NODEFRAG; if (di_flags & XFS_DIFLAG_FILESTREAM) - flags |= XFS_XFLAG_FILESTREAM; + flags |= FS_XFLAG_FILESTREAM; } + if (di_flags2 & XFS_DIFLAG2_ANY) { + if (di_flags2 & XFS_DIFLAG2_DAX) + flags |= FS_XFLAG_DAX; + } + + if (has_attr) + flags |= FS_XFLAG_HASATTR; + return flags; } uint xfs_ip2xflags( - xfs_inode_t *ip) + struct xfs_inode *ip) { - xfs_icdinode_t *dic = &ip->i_d; + struct xfs_icdinode *dic = &ip->i_d; - return _xfs_dic2xflags(dic->di_flags) | - (XFS_IFORK_Q(ip) ? XFS_XFLAG_HASATTR : 0); + return _xfs_dic2xflags(dic->di_flags, dic->di_flags2, XFS_IFORK_Q(ip)); } uint xfs_dic2xflags( - xfs_dinode_t *dip) + struct xfs_dinode *dip) { - return _xfs_dic2xflags(be16_to_cpu(dip->di_flags)) | - (XFS_DFORK_Q(dip) ? XFS_XFLAG_HASATTR : 0); + return _xfs_dic2xflags(be16_to_cpu(dip->di_flags), + be64_to_cpu(dip->di_flags2), XFS_DFORK_Q(dip)); } /* @@ -862,7 +871,8 @@ xfs_ialloc( case S_IFREG: case S_IFDIR: if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) { - uint di_flags = 0; + uint64_t di_flags2 = 0; + uint di_flags = 0; if (S_ISDIR(mode)) { if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT) @@ -898,7 +908,11 @@ xfs_ialloc( di_flags |= XFS_DIFLAG_NODEFRAG; if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM) di_flags |= XFS_DIFLAG_FILESTREAM; + if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) + di_flags2 |= XFS_DIFLAG2_DAX; + ip->i_d.di_flags |= di_flags; + ip->i_d.di_flags2 |= di_flags2; } /* FALLTHROUGH */ case S_IFLNK: diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index d42738deec6d..478d04e07f95 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -859,25 +859,25 @@ xfs_merge_ioc_xflags( unsigned int xflags = start; if (flags & FS_IMMUTABLE_FL) - xflags |= XFS_XFLAG_IMMUTABLE; + xflags |= FS_XFLAG_IMMUTABLE; else - xflags &= ~XFS_XFLAG_IMMUTABLE; + xflags &= ~FS_XFLAG_IMMUTABLE; if (flags & FS_APPEND_FL) - xflags |= XFS_XFLAG_APPEND; + xflags |= FS_XFLAG_APPEND; else - xflags &= ~XFS_XFLAG_APPEND; + xflags &= ~FS_XFLAG_APPEND; if (flags & FS_SYNC_FL) - xflags |= XFS_XFLAG_SYNC; + xflags |= FS_XFLAG_SYNC; else - xflags &= ~XFS_XFLAG_SYNC; + xflags &= ~FS_XFLAG_SYNC; if (flags & FS_NOATIME_FL) - xflags |= XFS_XFLAG_NOATIME; + xflags |= FS_XFLAG_NOATIME; else - xflags &= ~XFS_XFLAG_NOATIME; + xflags &= ~FS_XFLAG_NOATIME; if (flags & FS_NODUMP_FL) - xflags |= XFS_XFLAG_NODUMP; + xflags |= FS_XFLAG_NODUMP; else - xflags &= ~XFS_XFLAG_NODUMP; + xflags &= ~FS_XFLAG_NODUMP; return xflags; } @@ -945,40 +945,51 @@ xfs_set_diflags( unsigned int xflags) { unsigned int di_flags; + uint64_t di_flags2; /* can't set PREALLOC this way, just preserve it */ di_flags = (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC); - if (xflags & XFS_XFLAG_IMMUTABLE) + if (xflags & FS_XFLAG_IMMUTABLE) di_flags |= XFS_DIFLAG_IMMUTABLE; - if (xflags & XFS_XFLAG_APPEND) + if (xflags & FS_XFLAG_APPEND) di_flags |= XFS_DIFLAG_APPEND; - if (xflags & XFS_XFLAG_SYNC) + if (xflags & FS_XFLAG_SYNC) di_flags |= XFS_DIFLAG_SYNC; - if (xflags & XFS_XFLAG_NOATIME) + if (xflags & FS_XFLAG_NOATIME) di_flags |= XFS_DIFLAG_NOATIME; - if (xflags & XFS_XFLAG_NODUMP) + if (xflags & FS_XFLAG_NODUMP) di_flags |= XFS_DIFLAG_NODUMP; - if (xflags & XFS_XFLAG_NODEFRAG) + if (xflags & FS_XFLAG_NODEFRAG) di_flags |= XFS_DIFLAG_NODEFRAG; - if (xflags & XFS_XFLAG_FILESTREAM) + if (xflags & FS_XFLAG_FILESTREAM) di_flags |= XFS_DIFLAG_FILESTREAM; if (S_ISDIR(ip->i_d.di_mode)) { - if (xflags & XFS_XFLAG_RTINHERIT) + if (xflags & FS_XFLAG_RTINHERIT) di_flags |= XFS_DIFLAG_RTINHERIT; - if (xflags & XFS_XFLAG_NOSYMLINKS) + if (xflags & FS_XFLAG_NOSYMLINKS) di_flags |= XFS_DIFLAG_NOSYMLINKS; - if (xflags & XFS_XFLAG_EXTSZINHERIT) + if (xflags & FS_XFLAG_EXTSZINHERIT) di_flags |= XFS_DIFLAG_EXTSZINHERIT; - if (xflags & XFS_XFLAG_PROJINHERIT) + if (xflags & FS_XFLAG_PROJINHERIT) di_flags |= XFS_DIFLAG_PROJINHERIT; } else if (S_ISREG(ip->i_d.di_mode)) { - if (xflags & XFS_XFLAG_REALTIME) + if (xflags & FS_XFLAG_REALTIME) di_flags |= XFS_DIFLAG_REALTIME; - if (xflags & XFS_XFLAG_EXTSIZE) + if (xflags & FS_XFLAG_EXTSIZE) di_flags |= XFS_DIFLAG_EXTSIZE; } - ip->i_d.di_flags = di_flags; + + /* diflags2 only valid for v3 inodes. */ + if (ip->i_d.di_version < 3) + return; + + di_flags2 = 0; + if (xflags & FS_XFLAG_DAX) + di_flags2 |= XFS_DIFLAG2_DAX; + + ip->i_d.di_flags2 = di_flags2; + } STATIC void @@ -988,22 +999,27 @@ xfs_diflags_to_linux( struct inode *inode = VFS_I(ip); unsigned int xflags = xfs_ip2xflags(ip); - if (xflags & XFS_XFLAG_IMMUTABLE) + if (xflags & FS_XFLAG_IMMUTABLE) inode->i_flags |= S_IMMUTABLE; else inode->i_flags &= ~S_IMMUTABLE; - if (xflags & XFS_XFLAG_APPEND) + if (xflags & FS_XFLAG_APPEND) inode->i_flags |= S_APPEND; else inode->i_flags &= ~S_APPEND; - if (xflags & XFS_XFLAG_SYNC) + if (xflags & FS_XFLAG_SYNC) inode->i_flags |= S_SYNC; else inode->i_flags &= ~S_SYNC; - if (xflags & XFS_XFLAG_NOATIME) + if (xflags & FS_XFLAG_NOATIME) inode->i_flags |= S_NOATIME; else inode->i_flags &= ~S_NOATIME; + if (xflags & FS_XFLAG_DAX) + inode->i_flags |= S_DAX; + else + inode->i_flags &= ~S_DAX; + } static int @@ -1016,11 +1032,11 @@ xfs_ioctl_setattr_xflags( /* Can't change realtime flag if any extents are allocated. */ if ((ip->i_d.di_nextents || ip->i_delayed_blks) && - XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & XFS_XFLAG_REALTIME)) + XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & FS_XFLAG_REALTIME)) return -EINVAL; /* If realtime flag is set then must have realtime device */ - if (fa->fsx_xflags & XFS_XFLAG_REALTIME) { + if (fa->fsx_xflags & FS_XFLAG_REALTIME) { if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 || (ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) return -EINVAL; @@ -1031,7 +1047,7 @@ xfs_ioctl_setattr_xflags( * we have appropriate permission. */ if (((ip->i_d.di_flags & (XFS_DIFLAG_IMMUTABLE | XFS_DIFLAG_APPEND)) || - (fa->fsx_xflags & (XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) && + (fa->fsx_xflags & (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND))) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; @@ -1095,8 +1111,8 @@ out_cancel: * extent size hint validation is somewhat cumbersome. Rules are: * * 1. extent size hint is only valid for directories and regular files - * 2. XFS_XFLAG_EXTSIZE is only valid for regular files - * 3. XFS_XFLAG_EXTSZINHERIT is only valid for directories. + * 2. FS_XFLAG_EXTSIZE is only valid for regular files + * 3. FS_XFLAG_EXTSZINHERIT is only valid for directories. * 4. can only be changed on regular files if no extents are allocated * 5. can be changed on directories at any time * 6. extsize hint of 0 turns off hints, clears inode flags. @@ -1112,10 +1128,10 @@ xfs_ioctl_setattr_check_extsize( { struct xfs_mount *mp = ip->i_mount; - if ((fa->fsx_xflags & XFS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode)) + if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode)) return -EINVAL; - if ((fa->fsx_xflags & XFS_XFLAG_EXTSZINHERIT) && + if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && !S_ISDIR(ip->i_d.di_mode)) return -EINVAL; @@ -1132,7 +1148,7 @@ xfs_ioctl_setattr_check_extsize( return -EINVAL; if (XFS_IS_REALTIME_INODE(ip) || - (fa->fsx_xflags & XFS_XFLAG_REALTIME)) { + (fa->fsx_xflags & FS_XFLAG_REALTIME)) { size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; } else { size = mp->m_sb.sb_blocksize; @@ -1143,7 +1159,7 @@ xfs_ioctl_setattr_check_extsize( if (fa->fsx_extsize % size) return -EINVAL; } else - fa->fsx_xflags &= ~(XFS_XFLAG_EXTSIZE | XFS_XFLAG_EXTSZINHERIT); + fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); return 0; } @@ -1168,7 +1184,7 @@ xfs_ioctl_setattr_check_projid( if (xfs_get_projid(ip) != fa->fsx_projid) return -EINVAL; - if ((fa->fsx_xflags & XFS_XFLAG_PROJINHERIT) != + if ((fa->fsx_xflags & FS_XFLAG_PROJINHERIT) != (ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)) return -EINVAL; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 06eafafe636e..76b71a1c6c32 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1205,8 +1205,8 @@ xfs_diflags_to_iflags( inode->i_flags |= S_SYNC; if (flags & XFS_DIFLAG_NOATIME) inode->i_flags |= S_NOATIME; - /* XXX: Also needs an on-disk per inode flag! */ - if (ip->i_mount->m_flags & XFS_MOUNT_DAX) + if (ip->i_mount->m_flags & XFS_MOUNT_DAX || + ip->i_d.di_flags2 & XFS_DIFLAG2_DAX) inode->i_flags |= S_DAX; } diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index aa67339b9537..4f18fd92ca13 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -497,7 +497,6 @@ xfsaild( long tout = 0; /* milliseconds */ current->flags |= PF_MEMALLOC; - set_freezable(); while (!kthread_should_stop()) { if (tout && tout <= 20) |