* context.
*/
static struct extent_buffer *find_extent_buffer_nolock(
- const struct btrfs_fs_info *fs_info, u64 start)
+ struct btrfs_fs_info *fs_info, u64 start)
{
struct extent_buffer *eb;
+ unsigned long index = (start >> fs_info->sectorsize_bits);
rcu_read_lock();
- eb = radix_tree_lookup(&fs_info->buffer_radix,
- start >> fs_info->sectorsize_bits);
- if (eb && atomic_inc_not_zero(&eb->refs)) {
- rcu_read_unlock();
- return eb;
- }
+ eb = xa_load(&fs_info->buffer_tree, index);
+ if (eb && !atomic_inc_not_zero(&eb->refs))
+ eb = NULL;
rcu_read_unlock();
- return NULL;
+ return eb;
}
static void end_bbio_meta_write(struct btrfs_bio *bbio)
if (!btrfs_meta_is_subpage(fs_info)) {
/*
- * We do this since we'll remove the pages after we've
- * removed the eb from the radix tree, so we could race
- * and have this page now attached to the new eb. So
- * only clear folio if it's still connected to
- * this eb.
+ * We do this since we'll remove the pages after we've removed
+ * the eb from the xarray, so we could race and have this page
+ * now attached to the new eb. So only clear folio if it's
+ * still connected to this eb.
*/
if (folio_test_private(folio) && folio_get_private(folio) == eb) {
BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
{
int refs;
/*
- * The TREE_REF bit is first set when the extent_buffer is added
- * to the radix tree. It is also reset, if unset, when a new reference
- * is created by find_extent_buffer.
+ * The TREE_REF bit is first set when the extent_buffer is added to the
+ * xarray. It is also reset, if unset, when a new reference is created
+ * by find_extent_buffer.
*
* It is only cleared in two cases: freeing the last non-tree
* reference to the extent_buffer when its STALE bit is set or
* conditions between the calls to check_buffer_tree_ref in those
* codepaths and clearing TREE_REF in try_release_extent_buffer.
*
- * The actual lifetime of the extent_buffer in the radix tree is
- * adequately protected by the refcount, but the TREE_REF bit and
- * its corresponding reference are not. To protect against this
- * class of races, we call check_buffer_tree_ref from the codepaths
- * which trigger io. Note that once io is initiated, TREE_REF can no
- * longer be cleared, so that is the moment at which any such race is
- * best fixed.
+ * The actual lifetime of the extent_buffer in the xarray is adequately
+ * protected by the refcount, but the TREE_REF bit and its corresponding
+ * reference are not. To protect against this class of races, we call
+ * check_buffer_tree_ref() from the code paths which trigger io. Note that
+ * once io is initiated, TREE_REF can no longer be cleared, so that is
+ * the moment at which any such race is best fixed.
*/
refs = atomic_read(&eb->refs);
if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
return ERR_PTR(-ENOMEM);
eb->fs_info = fs_info;
again:
- ret = radix_tree_preload(GFP_NOFS);
- if (ret) {
- exists = ERR_PTR(ret);
- goto free_eb;
+ xa_lock_irq(&fs_info->buffer_tree);
+ exists = __xa_cmpxchg(&fs_info->buffer_tree, start >> fs_info->sectorsize_bits,
+ NULL, eb, GFP_NOFS);
+ if (xa_is_err(exists)) {
+ ret = xa_err(exists);
+ xa_unlock_irq(&fs_info->buffer_tree);
+ btrfs_release_extent_buffer(eb);
+ return ERR_PTR(ret);
}
- spin_lock(&fs_info->buffer_lock);
- ret = radix_tree_insert(&fs_info->buffer_radix,
- start >> fs_info->sectorsize_bits, eb);
- spin_unlock(&fs_info->buffer_lock);
- radix_tree_preload_end();
- if (ret == -EEXIST) {
- exists = find_extent_buffer(fs_info, start);
- if (exists)
- goto free_eb;
- else
+ if (exists) {
+ if (!atomic_inc_not_zero(&exists->refs)) {
+ /* The extent buffer is being freed, retry. */
+ xa_unlock_irq(&fs_info->buffer_tree);
goto again;
+ }
+ xa_unlock_irq(&fs_info->buffer_tree);
+ goto free_eb;
}
+ xa_unlock_irq(&fs_info->buffer_tree);
check_buffer_tree_ref(eb);
return eb;
lockdep_assert_held(&folio->mapping->i_private_lock);
/*
- * For subpage case, we completely rely on radix tree to ensure we
- * don't try to insert two ebs for the same bytenr. So here we always
- * return NULL and just continue.
+ * For subpage case, we completely rely on xarray to ensure we don't try
+ * to insert two ebs for the same bytenr. So here we always return NULL
+ * and just continue.
*/
if (btrfs_meta_is_subpage(fs_info))
return NULL;
/*
* To inform we have an extra eb under allocation, so that
* detach_extent_buffer_page() won't release the folio private when the
- * eb hasn't been inserted into radix tree yet.
+ * eb hasn't been inserted into the xarray yet.
*
* The ref will be decreased when the eb releases the page, in
* detach_extent_buffer_page(). Thus needs no special handling in the
/*
* We can't unlock the pages just yet since the extent buffer
- * hasn't been properly inserted in the radix tree, this
- * opens a race with btree_release_folio which can free a page
- * while we are still filling in all pages for the buffer and
- * we could crash.
+ * hasn't been properly inserted into the xarray, this opens a
+ * race with btree_release_folio() which can free a page while we
+ * are still filling in all pages for the buffer and we could crash.
*/
}
if (uptodate)
if (page_contig)
eb->addr = folio_address(eb->folios[0]) + offset_in_page(eb->start);
again:
- ret = radix_tree_preload(GFP_NOFS);
- if (ret)
+ xa_lock_irq(&fs_info->buffer_tree);
+ existing_eb = __xa_cmpxchg(&fs_info->buffer_tree,
+ start >> fs_info->sectorsize_bits, NULL, eb,
+ GFP_NOFS);
+ if (xa_is_err(existing_eb)) {
+ ret = xa_err(existing_eb);
+ xa_unlock_irq(&fs_info->buffer_tree);
goto out;
-
- spin_lock(&fs_info->buffer_lock);
- ret = radix_tree_insert(&fs_info->buffer_radix,
- start >> fs_info->sectorsize_bits, eb);
- spin_unlock(&fs_info->buffer_lock);
- radix_tree_preload_end();
- if (ret == -EEXIST) {
- ret = 0;
- existing_eb = find_extent_buffer(fs_info, start);
- if (existing_eb)
- goto out;
- else
+ }
+ if (existing_eb) {
+ if (!atomic_inc_not_zero(&existing_eb->refs)) {
+ xa_unlock_irq(&fs_info->buffer_tree);
goto again;
+ }
+ xa_unlock_irq(&fs_info->buffer_tree);
+ goto out;
}
+ xa_unlock_irq(&fs_info->buffer_tree);
+
/* add one reference for the tree */
check_buffer_tree_ref(eb);
spin_unlock(&eb->refs_lock);
- spin_lock(&fs_info->buffer_lock);
- radix_tree_delete_item(&fs_info->buffer_radix,
- eb->start >> fs_info->sectorsize_bits, eb);
- spin_unlock(&fs_info->buffer_lock);
+ /*
+ * We're erasing, theoretically there will be no allocations, so
+ * just use GFP_ATOMIC.
+ *
+ * We use cmpxchg instead of erase because we do not know if
+ * this eb is actually in the tree or not, we could be cleaning
+ * up an eb that we allocated but never inserted into the tree.
+ * Thus use cmpxchg to remove it from the tree if it is there,
+ * or leave the other entry if this isn't in the tree.
+ *
+ * The documentation says that putting a NULL value is the same
+ * as erase as long as XA_FLAGS_ALLOC is not set, which it isn't
+ * in this case.
+ */
+ xa_cmpxchg_irq(&fs_info->buffer_tree,
+ eb->start >> fs_info->sectorsize_bits, eb, NULL,
+ GFP_ATOMIC);
btrfs_leak_debug_del_eb(eb);
/* Should be safe to release folios at this point. */
}
}
-#define GANG_LOOKUP_SIZE 16
-static struct extent_buffer *get_next_extent_buffer(
- const struct btrfs_fs_info *fs_info, struct folio *folio, u64 bytenr)
-{
- struct extent_buffer *gang[GANG_LOOKUP_SIZE];
- struct extent_buffer *found = NULL;
- u64 folio_start = folio_pos(folio);
- u64 cur = folio_start;
-
- ASSERT(in_range(bytenr, folio_start, PAGE_SIZE));
- lockdep_assert_held(&fs_info->buffer_lock);
-
- while (cur < folio_start + PAGE_SIZE) {
- int ret;
- int i;
-
- ret = radix_tree_gang_lookup(&fs_info->buffer_radix,
- (void **)gang, cur >> fs_info->sectorsize_bits,
- min_t(unsigned int, GANG_LOOKUP_SIZE,
- PAGE_SIZE / fs_info->nodesize));
- if (ret == 0)
- goto out;
- for (i = 0; i < ret; i++) {
- /* Already beyond page end */
- if (gang[i]->start >= folio_start + PAGE_SIZE)
- goto out;
- /* Found one */
- if (gang[i]->start >= bytenr) {
- found = gang[i];
- goto out;
- }
- }
- cur = gang[ret - 1]->start + gang[ret - 1]->len;
- }
-out:
- return found;
-}
-
static int try_release_subpage_extent_buffer(struct folio *folio)
{
struct btrfs_fs_info *fs_info = folio_to_fs_info(folio);
- u64 cur = folio_pos(folio);
- const u64 end = cur + PAGE_SIZE;
+ struct extent_buffer *eb;
+ unsigned long start = (folio_pos(folio) >> fs_info->sectorsize_bits);
+ unsigned long index = start;
+ unsigned long end = index + (PAGE_SIZE >> fs_info->sectorsize_bits) - 1;
int ret;
- while (cur < end) {
- struct extent_buffer *eb = NULL;
-
- /*
- * Unlike try_release_extent_buffer() which uses folio private
- * to grab buffer, for subpage case we rely on radix tree, thus
- * we need to ensure radix tree consistency.
- *
- * We also want an atomic snapshot of the radix tree, thus go
- * with spinlock rather than RCU.
- */
- spin_lock(&fs_info->buffer_lock);
- eb = get_next_extent_buffer(fs_info, folio, cur);
- if (!eb) {
- /* No more eb in the page range after or at cur */
- spin_unlock(&fs_info->buffer_lock);
- break;
- }
- cur = eb->start + eb->len;
-
+ xa_lock_irq(&fs_info->buffer_tree);
+ xa_for_each_range(&fs_info->buffer_tree, index, eb, start, end) {
/*
* The same as try_release_extent_buffer(), to ensure the eb
* won't disappear out from under us.
spin_lock(&eb->refs_lock);
if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
spin_unlock(&eb->refs_lock);
- spin_unlock(&fs_info->buffer_lock);
- break;
+ continue;
}
- spin_unlock(&fs_info->buffer_lock);
+ xa_unlock_irq(&fs_info->buffer_tree);
/*
* If tree ref isn't set then we know the ref on this eb is a
* release_extent_buffer() will release the refs_lock.
*/
release_extent_buffer(eb);
+ xa_lock_irq(&fs_info->buffer_tree);
}
+ xa_unlock_irq(&fs_info->buffer_tree);
+
/*
* Finally to check if we have cleared folio private, as if we have
* released all ebs in the page, the folio private should be cleared now.
projects / users / dwmw2 / linux.git / commitdiff