aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/balloc.c4
-rw-r--r--fs/ext4/extents.c23
-rw-r--r--fs/ext4/extents_status.c73
-rw-r--r--fs/ext4/inode.c19
-rw-r--r--fs/ext4/mballoc.c11
-rw-r--r--fs/ext4/namei.c2
-rw-r--r--fs/ext4/page-io.c35
-rw-r--r--fs/ext4/super.c14
8 files changed, 112 insertions, 69 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 58339393fa6e..ddd715e42a5c 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -38,8 +38,8 @@ ext4_group_t ext4_get_group_number(struct super_block *sb,
ext4_group_t group;
if (test_opt2(sb, STD_GROUP_SIZE))
- group = (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
- block) >>
+ group = (block -
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) >>
(EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3);
else
ext4_get_group_no_and_offset(sb, block, &group, NULL);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7097b0f680e6..a61873808f76 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2835,6 +2835,9 @@ again:
err = -EIO;
break;
}
+ /* Yield here to deal with large extent trees.
+ * Should be a no-op if we did IO above. */
+ cond_resched();
if (WARN_ON(i + 1 > depth)) {
err = -EIO;
break;
@@ -4261,8 +4264,8 @@ got_allocated_blocks:
/* not a good idea to call discard here directly,
* but otherwise we'd need to call it every free() */
ext4_discard_preallocations(inode);
- ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex),
- ext4_ext_get_actual_len(&newex), fb_flags);
+ ext4_free_blocks(handle, inode, NULL, newblock,
+ EXT4_C2B(sbi, allocated_clusters), fb_flags);
goto out2;
}
@@ -4382,8 +4385,9 @@ out2:
}
out3:
- trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated);
-
+ trace_ext4_ext_map_blocks_exit(inode, flags, map,
+ err ? err : allocated);
+ ext4_es_lru_add(inode);
return err ? err : allocated;
}
@@ -4405,9 +4409,20 @@ void ext4_ext_truncate(handle_t *handle, struct inode *inode)
last_block = (inode->i_size + sb->s_blocksize - 1)
>> EXT4_BLOCK_SIZE_BITS(sb);
+retry:
err = ext4_es_remove_extent(inode, last_block,
EXT_MAX_BLOCKS - last_block);
+ if (err == ENOMEM) {
+ cond_resched();
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
+ }
+ if (err) {
+ ext4_std_error(inode->i_sb, err);
+ return;
+ }
err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
+ ext4_std_error(inode->i_sb, err);
}
static void ext4_falloc_update_inode(struct inode *inode,
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index ee018d5f397e..91cb110da1b4 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -148,6 +148,8 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t end);
static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
int nr_to_scan);
+static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
+ struct ext4_inode_info *locked_ei);
int __init ext4_init_es(void)
{
@@ -439,7 +441,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
*/
if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) {
if (in_range(es->es_lblk, ee_block, ee_len)) {
- pr_warn("ES insert assertation failed for "
+ pr_warn("ES insert assertion failed for "
"inode: %lu we can find an extent "
"at block [%d/%d/%llu/%c], but we "
"want to add an delayed/hole extent "
@@ -458,7 +460,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
*/
if (es->es_lblk < ee_block ||
ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) {
- pr_warn("ES insert assertation failed for inode: %lu "
+ pr_warn("ES insert assertion failed for inode: %lu "
"ex_status [%d/%d/%llu/%c] != "
"es_status [%d/%d/%llu/%c]\n", inode->i_ino,
ee_block, ee_len, ee_start,
@@ -468,7 +470,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
}
if (ee_status ^ es_status) {
- pr_warn("ES insert assertation failed for inode: %lu "
+ pr_warn("ES insert assertion failed for inode: %lu "
"ex_status [%d/%d/%llu/%c] != "
"es_status [%d/%d/%llu/%c]\n", inode->i_ino,
ee_block, ee_len, ee_start,
@@ -481,7 +483,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
* that we don't want to add an written/unwritten extent.
*/
if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) {
- pr_warn("ES insert assertation failed for inode: %lu "
+ pr_warn("ES insert assertion failed for inode: %lu "
"can't find an extent at block %d but we want "
"to add an written/unwritten extent "
"[%d/%d/%llu/%llx]\n", inode->i_ino,
@@ -519,7 +521,7 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode,
* We want to add a delayed/hole extent but this
* block has been allocated.
*/
- pr_warn("ES insert assertation failed for inode: %lu "
+ pr_warn("ES insert assertion failed for inode: %lu "
"We can find blocks but we want to add a "
"delayed/hole extent [%d/%d/%llu/%llx]\n",
inode->i_ino, es->es_lblk, es->es_len,
@@ -527,13 +529,13 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode,
return;
} else if (ext4_es_is_written(es)) {
if (retval != es->es_len) {
- pr_warn("ES insert assertation failed for "
+ pr_warn("ES insert assertion failed for "
"inode: %lu retval %d != es_len %d\n",
inode->i_ino, retval, es->es_len);
return;
}
if (map.m_pblk != ext4_es_pblock(es)) {
- pr_warn("ES insert assertation failed for "
+ pr_warn("ES insert assertion failed for "
"inode: %lu m_pblk %llu != "
"es_pblk %llu\n",
inode->i_ino, map.m_pblk,
@@ -549,7 +551,7 @@ static void ext4_es_insert_extent_ind_check(struct inode *inode,
}
} else if (retval == 0) {
if (ext4_es_is_written(es)) {
- pr_warn("ES insert assertation failed for inode: %lu "
+ pr_warn("ES insert assertion failed for inode: %lu "
"We can't find the block but we want to add "
"an written extent [%d/%d/%llu/%llx]\n",
inode->i_ino, es->es_lblk, es->es_len,
@@ -632,10 +634,8 @@ out:
}
/*
- * ext4_es_insert_extent() adds a space to a extent status tree.
- *
- * ext4_es_insert_extent is called by ext4_da_write_begin and
- * ext4_es_remove_extent.
+ * ext4_es_insert_extent() adds information to an inode's extent
+ * status tree.
*
* Return 0 on success, error code on failure.
*/
@@ -667,7 +667,13 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
err = __es_remove_extent(inode, lblk, end);
if (err != 0)
goto error;
+retry:
err = __es_insert_extent(inode, &newes);
+ if (err == -ENOMEM && __ext4_es_shrink(EXT4_SB(inode->i_sb), 1,
+ EXT4_I(inode)))
+ goto retry;
+ if (err == -ENOMEM && !ext4_es_is_delayed(&newes))
+ err = 0;
error:
write_unlock(&EXT4_I(inode)->i_es_lock);
@@ -746,8 +752,10 @@ 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 = 0;
+ int err;
+retry:
+ err = 0;
es = __es_tree_search(&tree->root, lblk);
if (!es)
goto out;
@@ -782,6 +790,10 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
if (err) {
es->es_lblk = orig_es.es_lblk;
es->es_len = orig_es.es_len;
+ if ((err == -ENOMEM) &&
+ __ext4_es_shrink(EXT4_SB(inode->i_sb), 1,
+ EXT4_I(inode)))
+ goto retry;
goto out;
}
} else {
@@ -891,22 +903,14 @@ static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a,
return -1;
}
-static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
+ struct ext4_inode_info *locked_ei)
{
- struct ext4_sb_info *sbi = container_of(shrink,
- struct ext4_sb_info, s_es_shrinker);
struct ext4_inode_info *ei;
struct list_head *cur, *tmp;
LIST_HEAD(skiped);
- int nr_to_scan = sc->nr_to_scan;
int ret, nr_shrunk = 0;
- ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
- trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret);
-
- if (!nr_to_scan)
- return ret;
-
spin_lock(&sbi->s_es_lru_lock);
/*
@@ -935,7 +939,7 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
continue;
}
- if (ei->i_es_lru_nr == 0)
+ if (ei->i_es_lru_nr == 0 || ei == locked_ei)
continue;
write_lock(&ei->i_es_lock);
@@ -954,6 +958,27 @@ static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
list_splice_tail(&skiped, &sbi->s_es_lru);
spin_unlock(&sbi->s_es_lru_lock);
+ if (locked_ei && nr_shrunk == 0)
+ nr_shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
+
+ return nr_shrunk;
+}
+
+static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
+{
+ struct ext4_sb_info *sbi = container_of(shrink,
+ struct ext4_sb_info, s_es_shrinker);
+ int nr_to_scan = sc->nr_to_scan;
+ int ret, nr_shrunk;
+
+ ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
+ trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret);
+
+ if (!nr_to_scan)
+ return ret;
+
+ nr_shrunk = __ext4_es_shrink(sbi, nr_to_scan, NULL);
+
ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
return ret;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0188e65e1f58..ba33c67d6e48 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -465,7 +465,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
if (es_map->m_lblk != map->m_lblk ||
es_map->m_flags != map->m_flags ||
es_map->m_pblk != map->m_pblk) {
- printk("ES cache assertation failed for inode: %lu "
+ printk("ES cache assertion failed for inode: %lu "
"es_cached ex [%d/%d/%llu/%x] != "
"found ex [%d/%d/%llu/%x] retval %d flags %x\n",
inode->i_ino, es_map->m_lblk, es_map->m_len,
@@ -514,10 +514,9 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
"logical block %lu\n", inode->i_ino, flags, map->m_len,
(unsigned long) map->m_lblk);
- ext4_es_lru_add(inode);
-
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
+ ext4_es_lru_add(inode);
if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
map->m_pblk = ext4_es_pblock(&es) +
map->m_lblk - es.es_lblk;
@@ -558,7 +557,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
#ifdef ES_AGGRESSIVE_TEST
if (retval != map->m_len) {
- printk("ES len assertation failed for inode: %lu "
+ printk("ES len assertion failed for inode: %lu "
"retval %d != map->m_len %d "
"in %s (lookup)\n", inode->i_ino, retval,
map->m_len, __func__);
@@ -659,7 +658,7 @@ found:
#ifdef ES_AGGRESSIVE_TEST
if (retval != map->m_len) {
- printk("ES len assertation failed for inode: %lu "
+ printk("ES len assertion failed for inode: %lu "
"retval %d != map->m_len %d "
"in %s (allocation)\n", inode->i_ino, retval,
map->m_len, __func__);
@@ -1529,11 +1528,9 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
"logical block %lu\n", inode->i_ino, map->m_len,
(unsigned long) map->m_lblk);
- ext4_es_lru_add(inode);
-
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, iblock, &es)) {
-
+ ext4_es_lru_add(inode);
if (ext4_es_is_hole(&es)) {
retval = 0;
down_read((&EXT4_I(inode)->i_data_sem));
@@ -1642,7 +1639,7 @@ add_delayed:
#ifdef ES_AGGRESSIVE_TEST
if (retval != map->m_len) {
- printk("ES len assertation failed for inode: %lu "
+ printk("ES len assertion failed for inode: %lu "
"retval %d != map->m_len %d "
"in %s (lookup)\n", inode->i_ino, retval,
map->m_len, __func__);
@@ -2163,7 +2160,7 @@ static int mpage_map_and_submit_extent(handle_t *handle,
mpd->io_submit.io_end->offset =
((loff_t)map->m_lblk) << inode->i_blkbits;
- while (map->m_len) {
+ do {
err = mpage_map_one_extent(handle, mpd);
if (err < 0) {
struct super_block *sb = inode->i_sb;
@@ -2201,7 +2198,7 @@ static int mpage_map_and_submit_extent(handle_t *handle,
err = mpage_map_and_submit_buffers(mpd);
if (err < 0)
return err;
- }
+ } while (map->m_len);
/* Update on-disk size after IO is submitted */
disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a9ff5e5137ca..4bbbf13bd743 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4740,11 +4740,16 @@ do_more:
* blocks being freed are metadata. these blocks shouldn't
* be used until this transaction is committed
*/
+ retry:
new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
if (!new_entry) {
- ext4_mb_unload_buddy(&e4b);
- err = -ENOMEM;
- goto error_return;
+ /*
+ * We use a retry loop because
+ * ext4_free_blocks() is not allowed to fail.
+ */
+ cond_resched();
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
}
new_entry->efd_start_cluster = bit;
new_entry->efd_group = block_group;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 234b834d5a97..35f55a0dbc4b 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2316,11 +2316,11 @@ retry:
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
+ d_tmpfile(dentry, inode);
err = ext4_orphan_add(handle, inode);
if (err)
goto err_drop_inode;
mark_inode_dirty(inode);
- d_tmpfile(dentry, inode);
unlock_new_inode(inode);
}
if (handle)
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 48786cdb5e6c..6625d210fb45 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -25,6 +25,7 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/mm.h>
+#include <linux/ratelimit.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -55,7 +56,7 @@ void ext4_exit_pageio(void)
static void buffer_io_error(struct buffer_head *bh)
{
char b[BDEVNAME_SIZE];
- printk(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
+ printk_ratelimited(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
bdevname(bh->b_bdev, b),
(unsigned long long)bh->b_blocknr);
}
@@ -308,6 +309,7 @@ ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end)
return io_end;
}
+/* BIO completion function for page writeback */
static void ext4_end_bio(struct bio *bio, int error)
{
ext4_io_end_t *io_end = bio->bi_private;
@@ -318,18 +320,6 @@ static void ext4_end_bio(struct bio *bio, int error)
if (test_bit(BIO_UPTODATE, &bio->bi_flags))
error = 0;
- if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
- /*
- * Link bio into list hanging from io_end. We have to do it
- * atomically as bio completions can be racing against each
- * other.
- */
- bio->bi_private = xchg(&io_end->bio, bio);
- } else {
- ext4_finish_bio(bio);
- bio_put(bio);
- }
-
if (error) {
struct inode *inode = io_end->inode;
@@ -341,7 +331,24 @@ static void ext4_end_bio(struct bio *bio, int error)
(unsigned long long)
bi_sector >> (inode->i_blkbits - 9));
}
- ext4_put_io_end_defer(io_end);
+
+ if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
+ /*
+ * Link bio into list hanging from io_end. We have to do it
+ * atomically as bio completions can be racing against each
+ * other.
+ */
+ bio->bi_private = xchg(&io_end->bio, bio);
+ ext4_put_io_end_defer(io_end);
+ } else {
+ /*
+ * Drop io_end reference early. Inode can get freed once
+ * we finish the bio.
+ */
+ ext4_put_io_end_defer(io_end);
+ ext4_finish_bio(bio);
+ bio_put(bio);
+ }
}
void ext4_io_submit(struct ext4_io_submit *io)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 85b3dd60169b..bca26f34edf4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1702,12 +1702,6 @@ static inline void ext4_show_quota_options(struct seq_file *seq,
if (sbi->s_qf_names[GRPQUOTA])
seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
-
- if (test_opt(sb, USRQUOTA))
- seq_puts(seq, ",usrquota");
-
- if (test_opt(sb, GRPQUOTA))
- seq_puts(seq, ",grpquota");
#endif
}
@@ -3624,10 +3618,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
- /* Do we have standard group size of blocksize * 8 blocks ? */
- if (sbi->s_blocks_per_group == blocksize << 3)
- set_opt2(sb, STD_GROUP_SIZE);
-
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
@@ -3697,6 +3687,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount;
}
+ /* Do we have standard group size of clustersize * 8 blocks ? */
+ if (sbi->s_blocks_per_group == clustersize << 3)
+ set_opt2(sb, STD_GROUP_SIZE);
+
/*
* Test whether we have more sectors than will fit in sector_t,
* and whether the max offset is addressable by the page cache.
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.