aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/backref.c84
-rw-r--r--fs/btrfs/backref.h1
-rw-r--r--fs/btrfs/block-group.c2
-rw-r--r--fs/btrfs/compression.c31
-rw-r--r--fs/btrfs/extent-io-tree.c15
-rw-r--r--fs/btrfs/extent_io.c33
-rw-r--r--fs/btrfs/inode.c8
-rw-r--r--fs/btrfs/send.c5
-rw-r--r--fs/btrfs/send.h5
-rw-r--r--fs/btrfs/subpage.c2
-rw-r--r--fs/btrfs/tests/extent-io-tests.c32
11 files changed, 139 insertions, 79 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index dce3a16996b9..4ec18ceb2f21 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -138,6 +138,7 @@ struct share_check {
u64 root_objectid;
u64 inum;
int share_count;
+ bool have_delayed_delete_refs;
};
static inline int extent_is_shared(struct share_check *sc)
@@ -820,16 +821,11 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
struct preftrees *preftrees, struct share_check *sc)
{
struct btrfs_delayed_ref_node *node;
- struct btrfs_delayed_extent_op *extent_op = head->extent_op;
struct btrfs_key key;
- struct btrfs_key tmp_op_key;
struct rb_node *n;
int count;
int ret = 0;
- if (extent_op && extent_op->update_key)
- btrfs_disk_key_to_cpu(&tmp_op_key, &extent_op->key);
-
spin_lock(&head->lock);
for (n = rb_first_cached(&head->ref_tree); n; n = rb_next(n)) {
node = rb_entry(n, struct btrfs_delayed_ref_node,
@@ -855,10 +851,16 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
case BTRFS_TREE_BLOCK_REF_KEY: {
/* NORMAL INDIRECT METADATA backref */
struct btrfs_delayed_tree_ref *ref;
+ struct btrfs_key *key_ptr = NULL;
+
+ if (head->extent_op && head->extent_op->update_key) {
+ btrfs_disk_key_to_cpu(&key, &head->extent_op->key);
+ key_ptr = &key;
+ }
ref = btrfs_delayed_node_to_tree_ref(node);
ret = add_indirect_ref(fs_info, preftrees, ref->root,
- &tmp_op_key, ref->level + 1,
+ key_ptr, ref->level + 1,
node->bytenr, count, sc,
GFP_ATOMIC);
break;
@@ -884,13 +886,22 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
key.offset = ref->offset;
/*
- * Found a inum that doesn't match our known inum, we
- * know it's shared.
+ * If we have a share check context and a reference for
+ * another inode, we can't exit immediately. This is
+ * because even if this is a BTRFS_ADD_DELAYED_REF
+ * reference we may find next a BTRFS_DROP_DELAYED_REF
+ * which cancels out this ADD reference.
+ *
+ * If this is a DROP reference and there was no previous
+ * ADD reference, then we need to signal that when we
+ * process references from the extent tree (through
+ * add_inline_refs() and add_keyed_refs()), we should
+ * not exit early if we find a reference for another
+ * inode, because one of the delayed DROP references
+ * may cancel that reference in the extent tree.
*/
- if (sc && sc->inum && ref->objectid != sc->inum) {
- ret = BACKREF_FOUND_SHARED;
- goto out;
- }
+ if (sc && count < 0)
+ sc->have_delayed_delete_refs = true;
ret = add_indirect_ref(fs_info, preftrees, ref->root,
&key, 0, node->bytenr, count, sc,
@@ -920,7 +931,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
}
if (!ret)
ret = extent_is_shared(sc);
-out:
+
spin_unlock(&head->lock);
return ret;
}
@@ -1023,7 +1034,8 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info,
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = btrfs_extent_data_ref_offset(leaf, dref);
- if (sc && sc->inum && key.objectid != sc->inum) {
+ if (sc && sc->inum && key.objectid != sc->inum &&
+ !sc->have_delayed_delete_refs) {
ret = BACKREF_FOUND_SHARED;
break;
}
@@ -1033,6 +1045,7 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info,
ret = add_indirect_ref(fs_info, preftrees, root,
&key, 0, bytenr, count,
sc, GFP_NOFS);
+
break;
}
default:
@@ -1122,7 +1135,8 @@ static int add_keyed_refs(struct btrfs_root *extent_root,
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = btrfs_extent_data_ref_offset(leaf, dref);
- if (sc && sc->inum && key.objectid != sc->inum) {
+ if (sc && sc->inum && key.objectid != sc->inum &&
+ !sc->have_delayed_delete_refs) {
ret = BACKREF_FOUND_SHARED;
break;
}
@@ -1522,6 +1536,9 @@ static bool lookup_backref_shared_cache(struct btrfs_backref_shared_cache *cache
{
struct btrfs_backref_shared_cache_entry *entry;
+ if (!cache->use_cache)
+ return false;
+
if (WARN_ON_ONCE(level >= BTRFS_MAX_LEVEL))
return false;
@@ -1557,6 +1574,19 @@ static bool lookup_backref_shared_cache(struct btrfs_backref_shared_cache *cache
return false;
*is_shared = entry->is_shared;
+ /*
+ * If the node at this level is shared, than all nodes below are also
+ * shared. Currently some of the nodes below may be marked as not shared
+ * because we have just switched from one leaf to another, and switched
+ * also other nodes above the leaf and below the current level, so mark
+ * them as shared.
+ */
+ if (*is_shared) {
+ for (int i = 0; i < level; i++) {
+ cache->entries[i].is_shared = true;
+ cache->entries[i].gen = entry->gen;
+ }
+ }
return true;
}
@@ -1573,6 +1603,9 @@ static void store_backref_shared_cache(struct btrfs_backref_shared_cache *cache,
struct btrfs_backref_shared_cache_entry *entry;
u64 gen;
+ if (!cache->use_cache)
+ return;
+
if (WARN_ON_ONCE(level >= BTRFS_MAX_LEVEL))
return;
@@ -1648,6 +1681,7 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
.root_objectid = root->root_key.objectid,
.inum = inum,
.share_count = 0,
+ .have_delayed_delete_refs = false,
};
int level;
@@ -1669,6 +1703,7 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
/* -1 means we are in the bytenr of the data extent. */
level = -1;
ULIST_ITER_INIT(&uiter);
+ cache->use_cache = true;
while (1) {
bool is_shared;
bool cached;
@@ -1698,6 +1733,24 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
extent_gen > btrfs_root_last_snapshot(&root->root_item))
break;
+ /*
+ * If our data extent was not directly shared (without multiple
+ * reference items), than it might have a single reference item
+ * with a count > 1 for the same offset, which means there are 2
+ * (or more) file extent items that point to the data extent -
+ * this happens when a file extent item needs to be split and
+ * then one item gets moved to another leaf due to a b+tree leaf
+ * split when inserting some item. In this case the file extent
+ * items may be located in different leaves and therefore some
+ * of the leaves may be referenced through shared subtrees while
+ * others are not. Since our extent buffer cache only works for
+ * a single path (by far the most common case and simpler to
+ * deal with), we can not use it if we have multiple leaves
+ * (which implies multiple paths).
+ */
+ if (level == -1 && tmp->nnodes > 1)
+ cache->use_cache = false;
+
if (level >= 0)
store_backref_shared_cache(cache, root, bytenr,
level, false);
@@ -1713,6 +1766,7 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr,
break;
}
shared.share_count = 0;
+ shared.have_delayed_delete_refs = false;
cond_resched();
}
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 52ae6957b414..8e69584d538d 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -29,6 +29,7 @@ struct btrfs_backref_shared_cache {
* a given data extent should never exceed the maximum b+tree height.
*/
struct btrfs_backref_shared_cache_entry entries[BTRFS_MAX_LEVEL];
+ bool use_cache;
};
typedef int (iterate_extent_inodes_t)(u64 inum, u64 offset, u64 root,
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 32c415cfbdfe..deebc8ddbd93 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -774,10 +774,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait)
btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work);
out:
- /* REVIEW */
if (wait && caching_ctl)
ret = btrfs_caching_ctl_wait_done(cache, caching_ctl);
- /* wait_event(caching_ctl->wait, space_cache_v1_done(cache)); */
if (caching_ctl)
btrfs_put_caching_control(caching_ctl);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index c0a08064b0a7..f1f051ad3147 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -8,6 +8,7 @@
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
+#include <linux/pagevec.h>
#include <linux/highmem.h>
#include <linux/kthread.h>
#include <linux/time.h>
@@ -219,8 +220,7 @@ static noinline void end_compressed_writeback(struct inode *inode,
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
unsigned long index = cb->start >> PAGE_SHIFT;
unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_SHIFT;
- struct page *pages[16];
- unsigned long nr_pages = end_index - index + 1;
+ struct folio_batch fbatch;
const int errno = blk_status_to_errno(cb->status);
int i;
int ret;
@@ -228,24 +228,23 @@ static noinline void end_compressed_writeback(struct inode *inode,
if (errno)
mapping_set_error(inode->i_mapping, errno);
- while (nr_pages > 0) {
- ret = find_get_pages_contig(inode->i_mapping, index,
- min_t(unsigned long,
- nr_pages, ARRAY_SIZE(pages)), pages);
- if (ret == 0) {
- nr_pages -= 1;
- index += 1;
- continue;
- }
+ folio_batch_init(&fbatch);
+ while (index <= end_index) {
+ ret = filemap_get_folios(inode->i_mapping, &index, end_index,
+ &fbatch);
+
+ if (ret == 0)
+ return;
+
for (i = 0; i < ret; i++) {
+ struct folio *folio = fbatch.folios[i];
+
if (errno)
- SetPageError(pages[i]);
- btrfs_page_clamp_clear_writeback(fs_info, pages[i],
+ folio_set_error(folio);
+ btrfs_page_clamp_clear_writeback(fs_info, &folio->page,
cb->start, cb->len);
- put_page(pages[i]);
}
- nr_pages -= ret;
- index += ret;
+ folio_batch_release(&fbatch);
}
/* the inode may be gone now */
}
diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index 618275af19c4..83cb0378096f 100644
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -1641,16 +1641,17 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
int err;
u64 failed_start;
- while (1) {
+ err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start,
+ cached_state, NULL, GFP_NOFS);
+ while (err == -EEXIST) {
+ if (failed_start != start)
+ clear_extent_bit(tree, start, failed_start - 1,
+ EXTENT_LOCKED, cached_state);
+
+ wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED);
err = __set_extent_bit(tree, start, end, EXTENT_LOCKED,
&failed_start, cached_state, NULL,
GFP_NOFS);
- if (err == -EEXIST) {
- wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED);
- start = failed_start;
- } else
- break;
- WARN_ON(start > end);
}
return err;
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 1eae68fbae21..4dcf22e051ff 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -270,9 +270,8 @@ static int __process_pages_contig(struct address_space *mapping,
pgoff_t start_index = start >> PAGE_SHIFT;
pgoff_t end_index = end >> PAGE_SHIFT;
pgoff_t index = start_index;
- unsigned long nr_pages = end_index - start_index + 1;
unsigned long pages_processed = 0;
- struct page *pages[16];
+ struct folio_batch fbatch;
int err = 0;
int i;
@@ -281,16 +280,17 @@ static int __process_pages_contig(struct address_space *mapping,
ASSERT(processed_end && *processed_end == start);
}
- if ((page_ops & PAGE_SET_ERROR) && nr_pages > 0)
+ if ((page_ops & PAGE_SET_ERROR) && start_index <= end_index)
mapping_set_error(mapping, -EIO);
- while (nr_pages > 0) {
- int found_pages;
+ folio_batch_init(&fbatch);
+ while (index <= end_index) {
+ int found_folios;
+
+ found_folios = filemap_get_folios_contig(mapping, &index,
+ end_index, &fbatch);
- found_pages = find_get_pages_contig(mapping, index,
- min_t(unsigned long,
- nr_pages, ARRAY_SIZE(pages)), pages);
- if (found_pages == 0) {
+ if (found_folios == 0) {
/*
* Only if we're going to lock these pages, we can find
* nothing at @index.
@@ -300,23 +300,20 @@ static int __process_pages_contig(struct address_space *mapping,
goto out;
}
- for (i = 0; i < found_pages; i++) {
+ for (i = 0; i < found_folios; i++) {
int process_ret;
-
+ struct folio *folio = fbatch.folios[i];
process_ret = process_one_page(fs_info, mapping,
- pages[i], locked_page, page_ops,
+ &folio->page, locked_page, page_ops,
start, end);
if (process_ret < 0) {
- for (; i < found_pages; i++)
- put_page(pages[i]);
err = -EAGAIN;
+ folio_batch_release(&fbatch);
goto out;
}
- put_page(pages[i]);
- pages_processed++;
+ pages_processed += folio_nr_pages(folio);
}
- nr_pages -= found_pages;
- index += found_pages;
+ folio_batch_release(&fbatch);
cond_resched();
}
out:
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 45ebef8d3ea8..b0807c59e321 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10018,7 +10018,7 @@ static int btrfs_permission(struct user_namespace *mnt_userns,
}
static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
- struct dentry *dentry, umode_t mode)
+ struct file *file, umode_t mode)
{
struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
struct btrfs_trans_handle *trans;
@@ -10026,7 +10026,7 @@ static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
struct inode *inode;
struct btrfs_new_inode_args new_inode_args = {
.dir = dir,
- .dentry = dentry,
+ .dentry = file->f_path.dentry,
.orphan = true,
};
unsigned int trans_num_items;
@@ -10063,7 +10063,7 @@ static int btrfs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
set_nlink(inode, 1);
if (!ret) {
- d_tmpfile(dentry, inode);
+ d_tmpfile(file, inode);
unlock_new_inode(inode);
mark_inode_dirty(inode);
}
@@ -10075,7 +10075,7 @@ out_new_inode_args:
out_inode:
if (ret)
iput(inode);
- return ret;
+ return finish_open_simple(file, ret);
}
void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end)
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 4ef4167072b8..ec6e1752af2c 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -348,6 +348,7 @@ static bool proto_cmd_ok(const struct send_ctx *sctx, int cmd)
switch (sctx->proto) {
case 1: return cmd <= BTRFS_SEND_C_MAX_V1;
case 2: return cmd <= BTRFS_SEND_C_MAX_V2;
+ case 3: return cmd <= BTRFS_SEND_C_MAX_V3;
default: return false;
}
}
@@ -6469,7 +6470,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
if (ret < 0)
goto out;
}
- if (sctx->cur_inode_needs_verity) {
+
+ if (proto_cmd_ok(sctx, BTRFS_SEND_C_ENABLE_VERITY)
+ && sctx->cur_inode_needs_verity) {
ret = process_verity(sctx);
if (ret < 0)
goto out;
diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h
index 0a4537775e0c..f7585cfa7e52 100644
--- a/fs/btrfs/send.h
+++ b/fs/btrfs/send.h
@@ -10,7 +10,12 @@
#include <linux/types.h>
#define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
+/* Conditional support for the upcoming protocol version. */
+#ifdef CONFIG_BTRFS_DEBUG
+#define BTRFS_SEND_STREAM_VERSION 3
+#else
#define BTRFS_SEND_STREAM_VERSION 2
+#endif
/*
* In send stream v1, no command is larger than 64K. In send stream v2, no limit
diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index 6fc2b77ae5c3..9a176af847d7 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -337,7 +337,7 @@ bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
*
* Even with 0 returned, the page still need extra check to make sure
* it's really the correct page, as the caller is using
- * find_get_pages_contig(), which can race with page invalidating.
+ * filemap_get_folios_contig(), which can race with page invalidating.
*/
int btrfs_page_start_writer_lock(const struct btrfs_fs_info *fs_info,
struct page *page, u64 start, u32 len)
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index f69ec4d2d6eb..350da449db08 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -4,6 +4,7 @@
*/
#include <linux/pagemap.h>
+#include <linux/pagevec.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/sizes.h>
@@ -20,39 +21,40 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end,
unsigned long flags)
{
int ret;
- struct page *pages[16];
+ struct folio_batch fbatch;
unsigned long index = start >> PAGE_SHIFT;
unsigned long end_index = end >> PAGE_SHIFT;
- unsigned long nr_pages = end_index - index + 1;
int i;
int count = 0;
int loops = 0;
- while (nr_pages > 0) {
- ret = find_get_pages_contig(inode->i_mapping, index,
- min_t(unsigned long, nr_pages,
- ARRAY_SIZE(pages)), pages);
+ folio_batch_init(&fbatch);
+
+ while (index <= end_index) {
+ ret = filemap_get_folios_contig(inode->i_mapping, &index,
+ end_index, &fbatch);
for (i = 0; i < ret; i++) {
+ struct folio *folio = fbatch.folios[i];
+
if (flags & PROCESS_TEST_LOCKED &&
- !PageLocked(pages[i]))
+ !folio_test_locked(folio))
count++;
- if (flags & PROCESS_UNLOCK && PageLocked(pages[i]))
- unlock_page(pages[i]);
- put_page(pages[i]);
+ if (flags & PROCESS_UNLOCK && folio_test_locked(folio))
+ folio_unlock(folio);
if (flags & PROCESS_RELEASE)
- put_page(pages[i]);
+ folio_put(folio);
}
- nr_pages -= ret;
- index += ret;
+ folio_batch_release(&fbatch);
cond_resched();
loops++;
if (loops > 100000) {
printk(KERN_ERR
- "stuck in a loop, start %llu, end %llu, nr_pages %lu, ret %d\n",
- start, end, nr_pages, ret);
+ "stuck in a loop, start %llu, end %llu, ret %d\n",
+ start, end, ret);
break;
}
}
+
return count;
}
Powered by cgit, Gruvboxed by Blaster4385.