aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4/extents_status.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/extents_status.c')
-rw-r--r--fs/ext4/extents_status.c310
1 files changed, 218 insertions, 92 deletions
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 80b5288cc0e9b2..3346a9252063bd 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -144,14 +144,17 @@
static struct kmem_cache *ext4_es_cachep;
static struct kmem_cache *ext4_pending_cachep;
-static int __es_insert_extent(struct inode *inode, struct extent_status *newes);
+static int __es_insert_extent(struct inode *inode, struct extent_status *newes,
+ struct extent_status *prealloc);
static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
- ext4_lblk_t end, int *reserved);
+ ext4_lblk_t end, int *reserved,
+ struct extent_status *prealloc);
static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan);
static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
struct ext4_inode_info *locked_ei);
-static void __revise_pending(struct inode *inode, ext4_lblk_t lblk,
- ext4_lblk_t len);
+static int __revise_pending(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len,
+ struct pending_reservation **prealloc);
int __init ext4_init_es(void)
{
@@ -439,22 +442,49 @@ static void ext4_es_list_del(struct inode *inode)
spin_unlock(&sbi->s_es_lock);
}
-static struct extent_status *
-ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
- ext4_fsblk_t pblk)
+static inline struct pending_reservation *__alloc_pending(bool nofail)
+{
+ if (!nofail)
+ return kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC);
+
+ return kmem_cache_zalloc(ext4_pending_cachep, GFP_KERNEL | __GFP_NOFAIL);
+}
+
+static inline void __free_pending(struct pending_reservation *pr)
+{
+ kmem_cache_free(ext4_pending_cachep, pr);
+}
+
+/*
+ * Returns true if we cannot fail to allocate memory for this extent_status
+ * entry and cannot reclaim it until its status changes.
+ */
+static inline bool ext4_es_must_keep(struct extent_status *es)
+{
+ /* fiemap, bigalloc, and seek_data/hole need to use it. */
+ if (ext4_es_is_delayed(es))
+ return true;
+
+ return false;
+}
+
+static inline struct extent_status *__es_alloc_extent(bool nofail)
+{
+ if (!nofail)
+ return kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC);
+
+ return kmem_cache_zalloc(ext4_es_cachep, GFP_KERNEL | __GFP_NOFAIL);
+}
+
+static void ext4_es_init_extent(struct inode *inode, struct extent_status *es,
+ ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk)
{
- struct extent_status *es;
- es = kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC);
- if (es == NULL)
- return NULL;
es->es_lblk = lblk;
es->es_len = len;
es->es_pblk = pblk;
- /*
- * We don't count delayed extent because we never try to reclaim them
- */
- if (!ext4_es_is_delayed(es)) {
+ /* We never try to reclaim a must kept extent, so we don't count it. */
+ if (!ext4_es_must_keep(es)) {
if (!EXT4_I(inode)->i_es_shk_nr++)
ext4_es_list_add(inode);
percpu_counter_inc(&EXT4_SB(inode->i_sb)->
@@ -463,8 +493,11 @@ ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
EXT4_I(inode)->i_es_all_nr++;
percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
+}
- return es;
+static inline void __es_free_extent(struct extent_status *es)
+{
+ kmem_cache_free(ext4_es_cachep, es);
}
static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
@@ -472,8 +505,8 @@ static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
EXT4_I(inode)->i_es_all_nr--;
percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt);
- /* Decrease the shrink counter when this es is not delayed */
- if (!ext4_es_is_delayed(es)) {
+ /* Decrease the shrink counter when we can reclaim the extent. */
+ if (!ext4_es_must_keep(es)) {
BUG_ON(EXT4_I(inode)->i_es_shk_nr == 0);
if (!--EXT4_I(inode)->i_es_shk_nr)
ext4_es_list_del(inode);
@@ -481,7 +514,7 @@ static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
s_es_stats.es_stats_shk_cnt);
}
- kmem_cache_free(ext4_es_cachep, es);
+ __es_free_extent(es);
}
/*
@@ -743,7 +776,8 @@ static inline void ext4_es_insert_extent_check(struct inode *inode,
}
#endif
-static int __es_insert_extent(struct inode *inode, struct extent_status *newes)
+static int __es_insert_extent(struct inode *inode, struct extent_status *newes,
+ struct extent_status *prealloc)
{
struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct rb_node **p = &tree->root.rb_node;
@@ -783,10 +817,15 @@ static int __es_insert_extent(struct inode *inode, struct extent_status *newes)
}
}
- es = ext4_es_alloc_extent(inode, newes->es_lblk, newes->es_len,
- newes->es_pblk);
+ if (prealloc)
+ es = prealloc;
+ else
+ es = __es_alloc_extent(false);
if (!es)
return -ENOMEM;
+ ext4_es_init_extent(inode, es, newes->es_lblk, newes->es_len,
+ newes->es_pblk);
+
rb_link_node(&es->rb_node, parent, p);
rb_insert_color(&es->rb_node, &tree->root);
@@ -807,8 +846,12 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
{
struct extent_status newes;
ext4_lblk_t end = lblk + len - 1;
- int err = 0;
+ int err1 = 0, err2 = 0, err3 = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct extent_status *es1 = NULL;
+ struct extent_status *es2 = NULL;
+ struct pending_reservation *pr = NULL;
+ bool revise_pending = false;
es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n",
lblk, len, pblk, status, inode->i_ino);
@@ -833,29 +876,57 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_es_insert_extent_check(inode, &newes);
+ revise_pending = sbi->s_cluster_ratio > 1 &&
+ test_opt(inode->i_sb, DELALLOC) &&
+ (status & (EXTENT_STATUS_WRITTEN |
+ EXTENT_STATUS_UNWRITTEN));
+retry:
+ if (err1 && !es1)
+ es1 = __es_alloc_extent(true);
+ if ((err1 || err2) && !es2)
+ es2 = __es_alloc_extent(true);
+ if ((err1 || err2 || err3) && revise_pending && !pr)
+ pr = __alloc_pending(true);
write_lock(&EXT4_I(inode)->i_es_lock);
- err = __es_remove_extent(inode, lblk, end, NULL);
- if (err != 0)
+
+ err1 = __es_remove_extent(inode, lblk, end, NULL, es1);
+ if (err1 != 0)
goto error;
-retry:
- err = __es_insert_extent(inode, &newes);
- if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb),
- 128, EXT4_I(inode)))
- goto retry;
- if (err == -ENOMEM && !ext4_es_is_delayed(&newes))
- err = 0;
+ /* Free preallocated extent if it didn't get used. */
+ if (es1) {
+ if (!es1->es_len)
+ __es_free_extent(es1);
+ es1 = NULL;
+ }
- if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) &&
- (status & EXTENT_STATUS_WRITTEN ||
- status & EXTENT_STATUS_UNWRITTEN))
- __revise_pending(inode, lblk, len);
+ err2 = __es_insert_extent(inode, &newes, es2);
+ if (err2 == -ENOMEM && !ext4_es_must_keep(&newes))
+ err2 = 0;
+ if (err2 != 0)
+ goto error;
+ /* Free preallocated extent if it didn't get used. */
+ if (es2) {
+ if (!es2->es_len)
+ __es_free_extent(es2);
+ es2 = NULL;
+ }
+ if (revise_pending) {
+ err3 = __revise_pending(inode, lblk, len, &pr);
+ if (err3 != 0)
+ goto error;
+ if (pr) {
+ __free_pending(pr);
+ pr = NULL;
+ }
+ }
error:
write_unlock(&EXT4_I(inode)->i_es_lock);
+ if (err1 || err2 || err3)
+ goto retry;
ext4_es_print_tree(inode);
-
- return err;
+ return 0;
}
/*
@@ -885,7 +956,7 @@ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk);
if (!es || es->es_lblk > end)
- __es_insert_extent(inode, &newes);
+ __es_insert_extent(inode, &newes, NULL);
write_unlock(&EXT4_I(inode)->i_es_lock);
}
@@ -1253,7 +1324,7 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
rc->ndelonly--;
node = rb_next(&pr->rb_node);
rb_erase(&pr->rb_node, &tree->root);
- kmem_cache_free(ext4_pending_cachep, pr);
+ __free_pending(pr);
if (!node)
break;
pr = rb_entry(node, struct pending_reservation,
@@ -1272,6 +1343,7 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
* @lblk - first block in range
* @end - last block in range
* @reserved - number of cluster reservations released
+ * @prealloc - pre-allocated es to avoid memory allocation failures
*
* If @reserved is not NULL and delayed allocation is enabled, counts
* block/cluster reservations freed by removing range and if bigalloc
@@ -1279,7 +1351,8 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end,
* error code on failure.
*/
static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
- ext4_lblk_t end, int *reserved)
+ ext4_lblk_t end, int *reserved,
+ struct extent_status *prealloc)
{
struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct rb_node *node;
@@ -1287,14 +1360,12 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
struct extent_status orig_es;
ext4_lblk_t len1, len2;
ext4_fsblk_t block;
- int err;
+ int err = 0;
bool count_reserved = true;
struct rsvd_count rc;
if (reserved == NULL || !test_opt(inode->i_sb, DELALLOC))
count_reserved = false;
-retry:
- err = 0;
es = __es_tree_search(&tree->root, lblk);
if (!es)
@@ -1328,14 +1399,13 @@ retry:
orig_es.es_len - len2;
ext4_es_store_pblock_status(&newes, block,
ext4_es_status(&orig_es));
- err = __es_insert_extent(inode, &newes);
+ err = __es_insert_extent(inode, &newes, prealloc);
if (err) {
+ if (!ext4_es_must_keep(&newes))
+ return 0;
+
es->es_lblk = orig_es.es_lblk;
es->es_len = orig_es.es_len;
- if ((err == -ENOMEM) &&
- __es_shrink(EXT4_SB(inode->i_sb),
- 128, EXT4_I(inode)))
- goto retry;
goto out;
}
} else {
@@ -1348,8 +1418,8 @@ retry:
}
}
if (count_reserved)
- count_rsvd(inode, lblk, orig_es.es_len - len1 - len2,
- &orig_es, &rc);
+ count_rsvd(inode, orig_es.es_lblk + len1,
+ orig_es.es_len - len1 - len2, &orig_es, &rc);
goto out_get_reserved;
}
@@ -1415,6 +1485,7 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t end;
int err = 0;
int reserved = 0;
+ struct extent_status *es = NULL;
trace_ext4_es_remove_extent(inode, lblk, len);
es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
@@ -1426,17 +1497,29 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
end = lblk + len - 1;
BUG_ON(end < lblk);
+retry:
+ if (err && !es)
+ es = __es_alloc_extent(true);
/*
* ext4_clear_inode() depends on us taking i_es_lock unconditionally
* so that we are sure __es_shrink() is done with the inode before it
* is reclaimed.
*/
write_lock(&EXT4_I(inode)->i_es_lock);
- err = __es_remove_extent(inode, lblk, end, &reserved);
+ err = __es_remove_extent(inode, lblk, end, &reserved, es);
+ /* Free preallocated extent if it didn't get used. */
+ if (es) {
+ if (!es->es_len)
+ __es_free_extent(es);
+ es = NULL;
+ }
write_unlock(&EXT4_I(inode)->i_es_lock);
+ if (err)
+ goto retry;
+
ext4_es_print_tree(inode);
ext4_da_release_space(inode, reserved);
- return err;
+ return 0;
}
static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
@@ -1683,11 +1766,8 @@ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end,
(*nr_to_scan)--;
node = rb_next(&es->rb_node);
- /*
- * We can't reclaim delayed extent from status tree because
- * fiemap, bigallic, and seek_data/hole need to use it.
- */
- if (ext4_es_is_delayed(es))
+
+ if (ext4_es_must_keep(es))
goto next;
if (ext4_es_is_referenced(es)) {
ext4_es_clear_referenced(es);
@@ -1751,7 +1831,7 @@ void ext4_clear_inode_es(struct inode *inode)
while (node) {
es = rb_entry(node, struct extent_status, rb_node);
node = rb_next(node);
- if (!ext4_es_is_delayed(es)) {
+ if (!ext4_es_must_keep(es)) {
rb_erase(&es->rb_node, &tree->root);
ext4_es_free_extent(inode, es);
}
@@ -1838,11 +1918,13 @@ static struct pending_reservation *__get_pending(struct inode *inode,
*
* @inode - file containing the cluster
* @lblk - logical block in the cluster to be added
+ * @prealloc - preallocated pending entry
*
* Returns 0 on successful insertion and -ENOMEM on failure. If the
* pending reservation is already in the set, returns successfully.
*/
-static int __insert_pending(struct inode *inode, ext4_lblk_t lblk)
+static int __insert_pending(struct inode *inode, ext4_lblk_t lblk,
+ struct pending_reservation **prealloc)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree;
@@ -1868,10 +1950,15 @@ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk)
}
}
- pr = kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC);
- if (pr == NULL) {
- ret = -ENOMEM;
- goto out;
+ if (likely(*prealloc == NULL)) {
+ pr = __alloc_pending(false);
+ if (!pr) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ } else {
+ pr = *prealloc;
+ *prealloc = NULL;
}
pr->lclu = lclu;
@@ -1901,7 +1988,7 @@ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk)
if (pr != NULL) {
tree = &EXT4_I(inode)->i_pending_tree;
rb_erase(&pr->rb_node, &tree->root);
- kmem_cache_free(ext4_pending_cachep, pr);
+ __free_pending(pr);
}
}
@@ -1962,7 +2049,10 @@ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
bool allocated)
{
struct extent_status newes;
- int err = 0;
+ int err1 = 0, err2 = 0, err3 = 0;
+ struct extent_status *es1 = NULL;
+ struct extent_status *es2 = NULL;
+ struct pending_reservation *pr = NULL;
es_debug("add [%u/1) delayed to extent status tree of inode %lu\n",
lblk, inode->i_ino);
@@ -1974,29 +2064,52 @@ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
ext4_es_insert_extent_check(inode, &newes);
+retry:
+ if (err1 && !es1)
+ es1 = __es_alloc_extent(true);
+ if ((err1 || err2) && !es2)
+ es2 = __es_alloc_extent(true);
+ if ((err1 || err2 || err3) && allocated && !pr)
+ pr = __alloc_pending(true);
write_lock(&EXT4_I(inode)->i_es_lock);
- err = __es_remove_extent(inode, lblk, lblk, NULL);
- if (err != 0)
- goto error;
-retry:
- err = __es_insert_extent(inode, &newes);
- if (err == -ENOMEM && __es_shrink(EXT4_SB(inode->i_sb),
- 128, EXT4_I(inode)))
- goto retry;
- if (err != 0)
+ err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1);
+ if (err1 != 0)
goto error;
+ /* Free preallocated extent if it didn't get used. */
+ if (es1) {
+ if (!es1->es_len)
+ __es_free_extent(es1);
+ es1 = NULL;
+ }
- if (allocated)
- __insert_pending(inode, lblk);
+ err2 = __es_insert_extent(inode, &newes, es2);
+ if (err2 != 0)
+ goto error;
+ /* Free preallocated extent if it didn't get used. */
+ if (es2) {
+ if (!es2->es_len)
+ __es_free_extent(es2);
+ es2 = NULL;
+ }
+ if (allocated) {
+ err3 = __insert_pending(inode, lblk, &pr);
+ if (err3 != 0)
+ goto error;
+ if (pr) {
+ __free_pending(pr);
+ pr = NULL;
+ }
+ }
error:
write_unlock(&EXT4_I(inode)->i_es_lock);
+ if (err1 || err2 || err3)
+ goto retry;
ext4_es_print_tree(inode);
ext4_print_pending_tree(inode);
-
- return err;
+ return 0;
}
/*
@@ -2097,21 +2210,24 @@ unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk,
* @inode - file containing the range
* @lblk - logical block defining the start of range
* @len - length of range in blocks
+ * @prealloc - preallocated pending entry
*
* Used after a newly allocated extent is added to the extents status tree.
* Requires that the extents in the range have either written or unwritten
* status. Must be called while holding i_es_lock.
*/
-static void __revise_pending(struct inode *inode, ext4_lblk_t lblk,
- ext4_lblk_t len)
+static int __revise_pending(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len,
+ struct pending_reservation **prealloc)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_lblk_t end = lblk + len - 1;
ext4_lblk_t first, last;
bool f_del = false, l_del = false;
+ int ret = 0;
if (len == 0)
- return;
+ return 0;
/*
* Two cases - block range within single cluster and block range
@@ -2132,7 +2248,9 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk,
f_del = __es_scan_range(inode, &ext4_es_is_delonly,
first, lblk - 1);
if (f_del) {
- __insert_pending(inode, first);
+ ret = __insert_pending(inode, first, prealloc);
+ if (ret < 0)
+ goto out;
} else {
last = EXT4_LBLK_CMASK(sbi, end) +
sbi->s_cluster_ratio - 1;
@@ -2140,9 +2258,11 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk,
l_del = __es_scan_range(inode,
&ext4_es_is_delonly,
end + 1, last);
- if (l_del)
- __insert_pending(inode, last);
- else
+ if (l_del) {
+ ret = __insert_pending(inode, last, prealloc);
+ if (ret < 0)
+ goto out;
+ } else
__remove_pending(inode, last);
}
} else {
@@ -2150,18 +2270,24 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk,
if (first != lblk)
f_del = __es_scan_range(inode, &ext4_es_is_delonly,
first, lblk - 1);
- if (f_del)
- __insert_pending(inode, first);
- else
+ if (f_del) {
+ ret = __insert_pending(inode, first, prealloc);
+ if (ret < 0)
+ goto out;
+ } else
__remove_pending(inode, first);
last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1;
if (last != end)
l_del = __es_scan_range(inode, &ext4_es_is_delonly,
end + 1, last);
- if (l_del)
- __insert_pending(inode, last);
- else
+ if (l_del) {
+ ret = __insert_pending(inode, last, prealloc);
+ if (ret < 0)
+ goto out;
+ } else
__remove_pending(inode, last);
}
+out:
+ return ret;
}
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-31 08:30:54 +0000