UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Ext4 regression and bug fixes: 

- Performance regression fix from 5.18 on a Rasberry Pi
 
 - Fix extent parsing bug which triggers a BUG_ON when a (corrupted)
   extent tree has has a non-root node when zero entries.
 
 - Fix a livelock where in the right (wrong) circumstances a large
   number of nfsd threads can try to write to a nearly full file
   system, and retry for hours(!)
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEK2m5VNv+CHkogTfJ8vlZVpUNgaMFAmMvsNEACgkQ8vlZVpUN
 gaMgsQf/b/JDCFXmki1/MLMvMP5LkX2rxTkq8P3lsZMP1yVOncSoir57jFvBWR6L
 h+So+k+ATfDIh3IeEf9S08deivRj6Se6BUwkewKwS8tPdmWUFpXr2TCGr4MTbkss
 4TxBOoarC0RsOrxHdbgsZDnhn8FtR58AS1lAeW/cOur1QcKxXXTz1baDKiTqB7ru
 LmXaFc15U+wxvVkijTHA1/RgnMd96gR9ilj7NP/UKQCYe+CloYrJDyjASNBmk2xP
 ZQiaHiMKBBfsLpBaqCgbkDAfEwzcBYGs2LDiiJ+wlmOHerE0pEJRNlREV3/Xt39O
 KwULSjZUlMMnVtHKn3IfWtkpmWZ6cg==
 =2uNr
 -----END PGP SIGNATURE-----

Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:
 "Regression and bug fixes:

   - Performance regression fix from 5.18 on a Rasberry Pi

   - Fix extent parsing bug which triggers a BUG_ON when a (corrupted)
     extent tree has has a non-root node when zero entries.

   - Fix a livelock where in the right (wrong) circumstances a large
     number of nfsd threads can try to write to a nearly full file
     system, and retry for hours(!)"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: limit the number of retries after discarding preallocations blocks
  ext4: fix bug in extents parsing when eh_entries == 0 and eh_depth > 0
  ext4: use buckets for cr 1 block scan instead of rbtree
  ext4: use locality group preallocation for small closed files
  ext4: make directory inode spreading reflect flexbg size
  ext4: avoid unnecessary spreading of allocations among groups
  ext4: make mballoc try target group first even with mb_optimize_scan
This commit is contained in:
Linus Torvalds 2022-09-25 09:03:31 -07:00
parent 4207d59567 80fa46d6b9
commit 5e049663f6
5 changed files with 154 additions and 181 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
fs/ext4/ext4.h
View File

@ -167,8 +167,6 @@ enum SHIFT_DIRECTION {
#define EXT4_MB_CR0_OPTIMIZED 0x8000
/* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */
#define EXT4_MB_CR1_OPTIMIZED 0x00010000
/* Perform linear traversal for one group */
#define EXT4_MB_SEARCH_NEXT_LINEAR 0x00020000
struct ext4_allocation_request {
/* target inode for block we're allocating */
struct inode *inode;
@ -1600,8 +1598,8 @@ struct ext4_sb_info {
struct list_head s_discard_list;
struct work_struct s_discard_work;
atomic_t s_retry_alloc_pending;
struct rb_root s_mb_avg_fragment_size_root;
rwlock_t s_mb_rb_lock;
struct list_head *s_mb_avg_fragment_size;
rwlock_t *s_mb_avg_fragment_size_locks;
struct list_head *s_mb_largest_free_orders;
rwlock_t *s_mb_largest_free_orders_locks;
@ -3413,6 +3411,8 @@ struct ext4_group_info {
ext4_grpblk_t bb_first_free; /* first free block */
ext4_grpblk_t bb_free; /* total free blocks */
ext4_grpblk_t bb_fragments; /* nr of freespace fragments */
int bb_avg_fragment_size_order; /* order of average
fragment in BG */
ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */
ext4_group_t bb_group; /* Group number */
struct list_head bb_prealloc_list;
@ -3420,7 +3420,7 @@ struct ext4_group_info {
void *bb_bitmap;
#endif
struct rw_semaphore alloc_sem;
struct rb_node bb_avg_fragment_size_rb;
struct list_head bb_avg_fragment_size_node;
struct list_head bb_largest_free_order_node;
ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block
* regions, index is order.

4
fs/ext4/extents.c
View File

@ -460,6 +460,10 @@ static int __ext4_ext_check(const char *function, unsigned int line,
error_msg = "invalid eh_entries";
goto corrupted;
}
if (unlikely((eh->eh_entries == 0) && (depth > 0))) {
error_msg = "eh_entries is 0 but eh_depth is > 0";
goto corrupted;
}
if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) {
error_msg = "invalid extent entries";
goto corrupted;

2
fs/ext4/ialloc.c
View File

@ -510,7 +510,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
goto fallback;
}
max_dirs = ndirs / ngroups + inodes_per_group / 16;
max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16;
min_inodes = avefreei - inodes_per_group*flex_size / 4;
if (min_inodes < 1)
min_inodes = 1;

318
fs/ext4/mballoc.c
View File

@ -140,13 +140,15 @@
* number of buddy bitmap orders possible) number of lists. Group-infos are
* placed in appropriate lists.
*
* 2) Average fragment size rb tree (sbi->s_mb_avg_fragment_size_root)
* 2) Average fragment size lists (sbi->s_mb_avg_fragment_size)
*
* Locking: sbi->s_mb_rb_lock (rwlock)
* Locking: sbi->s_mb_avg_fragment_size_locks(array of rw locks)
*
* This is a red black tree consisting of group infos and the tree is sorted
* by average fragment sizes (which is calculated as ext4_group_info->bb_free
* / ext4_group_info->bb_fragments).
* This is an array of lists where in the i-th list there are groups with
* average fragment size >= 2^i and < 2^(i+1). The average fragment size
* is computed as ext4_group_info->bb_free / ext4_group_info->bb_fragments.
* Note that we don't bother with a special list for completely empty groups
* so we only have MB_NUM_ORDERS(sb) lists.
*
* When "mb_optimize_scan" mount option is set, mballoc consults the above data
* structures to decide the order in which groups are to be traversed for
@ -160,7 +162,8 @@
*
* At CR = 1, we only consider groups where average fragment size > request
* size. So, we lookup a group which has average fragment size just above or
* equal to request size using our rb tree (data structure 2) in O(log N) time.
* equal to request size using our average fragment size group lists (data
* structure 2) in O(1) time.
*
* If "mb_optimize_scan" mount option is not set, mballoc traverses groups in
* linear order which requires O(N) search time for each CR 0 and CR 1 phase.
@ -802,65 +805,51 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
}
}
static void ext4_mb_rb_insert(struct rb_root *root, struct rb_node *new,
int (*cmp)(struct rb_node *, struct rb_node *))
static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len)
{
struct rb_node **iter = &root->rb_node, *parent = NULL;
int order;
while (*iter) {
parent = *iter;
if (cmp(new, *iter) > 0)
iter = &((*iter)->rb_left);
else
iter = &((*iter)->rb_right);
}
rb_link_node(new, parent, iter);
rb_insert_color(new, root);
/*
* We don't bother with a special lists groups with only 1 block free
* extents and for completely empty groups.
*/
order = fls(len) - 2;
if (order < 0)
return 0;
if (order == MB_NUM_ORDERS(sb))
order--;
return order;
}
static int
ext4_mb_avg_fragment_size_cmp(struct rb_node *rb1, struct rb_node *rb2)
{
struct ext4_group_info *grp1 = rb_entry(rb1,
struct ext4_group_info,
bb_avg_fragment_size_rb);
struct ext4_group_info *grp2 = rb_entry(rb2,
struct ext4_group_info,
bb_avg_fragment_size_rb);
int num_frags_1, num_frags_2;
num_frags_1 = grp1->bb_fragments ?
grp1->bb_free / grp1->bb_fragments : 0;
num_frags_2 = grp2->bb_fragments ?
grp2->bb_free / grp2->bb_fragments : 0;
return (num_frags_2 - num_frags_1);
}
/*
* Reinsert grpinfo into the avg_fragment_size tree with new average
* fragment size.
*/
/* Move group to appropriate avg_fragment_size list */
static void
mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
int new_order;
if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0)
return;
write_lock(&sbi->s_mb_rb_lock);
if (!RB_EMPTY_NODE(&grp->bb_avg_fragment_size_rb)) {
rb_erase(&grp->bb_avg_fragment_size_rb,
&sbi->s_mb_avg_fragment_size_root);
RB_CLEAR_NODE(&grp->bb_avg_fragment_size_rb);
}
new_order = mb_avg_fragment_size_order(sb,
grp->bb_free / grp->bb_fragments);
if (new_order == grp->bb_avg_fragment_size_order)
return;
ext4_mb_rb_insert(&sbi->s_mb_avg_fragment_size_root,
&grp->bb_avg_fragment_size_rb,
ext4_mb_avg_fragment_size_cmp);
write_unlock(&sbi->s_mb_rb_lock);
if (grp->bb_avg_fragment_size_order != -1) {
write_lock(&sbi->s_mb_avg_fragment_size_locks[
grp->bb_avg_fragment_size_order]);
list_del(&grp->bb_avg_fragment_size_node);
write_unlock(&sbi->s_mb_avg_fragment_size_locks[
grp->bb_avg_fragment_size_order]);
}
grp->bb_avg_fragment_size_order = new_order;
write_lock(&sbi->s_mb_avg_fragment_size_locks[
grp->bb_avg_fragment_size_order]);
list_add_tail(&grp->bb_avg_fragment_size_node,
&sbi->s_mb_avg_fragment_size[grp->bb_avg_fragment_size_order]);
write_unlock(&sbi->s_mb_avg_fragment_size_locks[
grp->bb_avg_fragment_size_order]);
}
/*
@ -909,86 +898,56 @@ static void ext4_mb_choose_next_group_cr0(struct ext4_allocation_context *ac,
*new_cr = 1;
} else {
*group = grp->bb_group;
ac->ac_last_optimal_group = *group;
ac->ac_flags |= EXT4_MB_CR0_OPTIMIZED;
}
}
/*
* Choose next group by traversing average fragment size tree. Updates *new_cr
* if cr lvel needs an update. Sets EXT4_MB_SEARCH_NEXT_LINEAR to indicate that
* the linear search should continue for one iteration since there's lock
* contention on the rb tree lock.
* Choose next group by traversing average fragment size list of suitable
* order. Updates *new_cr if cr level needs an update.
*/
static void ext4_mb_choose_next_group_cr1(struct ext4_allocation_context *ac,
int *new_cr, ext4_group_t *group, ext4_group_t ngroups)
{
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
int avg_fragment_size, best_so_far;
struct rb_node *node, *found;
struct ext4_group_info *grp;
/*
* If there is contention on the lock, instead of waiting for the lock
* to become available, just continue searching lineraly. We'll resume
* our rb tree search later starting at ac->ac_last_optimal_group.
*/
if (!read_trylock(&sbi->s_mb_rb_lock)) {
ac->ac_flags |= EXT4_MB_SEARCH_NEXT_LINEAR;
return;
}
struct ext4_group_info *grp, *iter;
int i;
if (unlikely(ac->ac_flags & EXT4_MB_CR1_OPTIMIZED)) {
if (sbi->s_mb_stats)
atomic_inc(&sbi->s_bal_cr1_bad_suggestions);
/* We have found something at CR 1 in the past */
grp = ext4_get_group_info(ac->ac_sb, ac->ac_last_optimal_group);
for (found = rb_next(&grp->bb_avg_fragment_size_rb); found != NULL;
found = rb_next(found)) {
grp = rb_entry(found, struct ext4_group_info,
bb_avg_fragment_size_rb);
}
for (i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len);
i < MB_NUM_ORDERS(ac->ac_sb); i++) {
if (list_empty(&sbi->s_mb_avg_fragment_size[i]))
continue;
read_lock(&sbi->s_mb_avg_fragment_size_locks[i]);
if (list_empty(&sbi->s_mb_avg_fragment_size[i])) {
read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]);
continue;
}
grp = NULL;
list_for_each_entry(iter, &sbi->s_mb_avg_fragment_size[i],
bb_avg_fragment_size_node) {
if (sbi->s_mb_stats)
atomic64_inc(&sbi->s_bal_cX_groups_considered[1]);
if (likely(ext4_mb_good_group(ac, grp->bb_group, 1)))
if (likely(ext4_mb_good_group(ac, iter->bb_group, 1))) {
grp = iter;
break;
}
goto done;
}
node = sbi->s_mb_avg_fragment_size_root.rb_node;
best_so_far = 0;
found = NULL;
while (node) {
grp = rb_entry(node, struct ext4_group_info,
bb_avg_fragment_size_rb);
avg_fragment_size = 0;
if (ext4_mb_good_group(ac, grp->bb_group, 1)) {
avg_fragment_size = grp->bb_fragments ?
grp->bb_free / grp->bb_fragments : 0;
if (!best_so_far || avg_fragment_size < best_so_far) {
best_so_far = avg_fragment_size;
found = node;
}
}
if (avg_fragment_size > ac->ac_g_ex.fe_len)
node = node->rb_right;
else
node = node->rb_left;
read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]);
if (grp)
break;
}
done:
if (found) {
grp = rb_entry(found, struct ext4_group_info,
bb_avg_fragment_size_rb);
if (grp) {
*group = grp->bb_group;
ac->ac_flags |= EXT4_MB_CR1_OPTIMIZED;
} else {
*new_cr = 2;
}
read_unlock(&sbi->s_mb_rb_lock);
ac->ac_last_optimal_group = *group;
}
static inline int should_optimize_scan(struct ext4_allocation_context *ac)
@ -1017,11 +976,6 @@ next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups)
goto inc_and_return;
}
if (ac->ac_flags & EXT4_MB_SEARCH_NEXT_LINEAR) {
ac->ac_flags &= ~EXT4_MB_SEARCH_NEXT_LINEAR;
goto inc_and_return;
}
return group;
inc_and_return:
/*
@ -1049,8 +1003,10 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
{
*new_cr = ac->ac_criteria;
if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining)
if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) {
*group = next_linear_group(ac, *group, ngroups);
return;
}
if (*new_cr == 0) {
ext4_mb_choose_next_group_cr0(ac, new_cr, group, ngroups);
@ -1075,23 +1031,25 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp)
struct ext4_sb_info *sbi = EXT4_SB(sb);
int i;
if (test_opt2(sb, MB_OPTIMIZE_SCAN) && grp->bb_largest_free_order >= 0) {
for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--)
if (grp->bb_counters[i] > 0)
break;
/* No need to move between order lists? */
if (!test_opt2(sb, MB_OPTIMIZE_SCAN) ||
i == grp->bb_largest_free_order) {
grp->bb_largest_free_order = i;
return;
}
if (grp->bb_largest_free_order >= 0) {
write_lock(&sbi->s_mb_largest_free_orders_locks[
grp->bb_largest_free_order]);
list_del_init(&grp->bb_largest_free_order_node);
write_unlock(&sbi->s_mb_largest_free_orders_locks[
grp->bb_largest_free_order]);
}
grp->bb_largest_free_order = -1; /* uninit */
for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) {
if (grp->bb_counters[i] > 0) {
grp->bb_largest_free_order = i;
break;
}
}
if (test_opt2(sb, MB_OPTIMIZE_SCAN) &&
grp->bb_largest_free_order >= 0 && grp->bb_free) {
grp->bb_largest_free_order = i;
if (grp->bb_largest_free_order >= 0 && grp->bb_free) {
write_lock(&sbi->s_mb_largest_free_orders_locks[
grp->bb_largest_free_order]);
list_add_tail(&grp->bb_largest_free_order_node,
@ -1148,13 +1106,13 @@ void ext4_mb_generate_buddy(struct super_block *sb,
EXT4_GROUP_INFO_BBITMAP_CORRUPT);
}
mb_set_largest_free_order(sb, grp);
mb_update_avg_fragment_size(sb, grp);
clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
period = get_cycles() - period;
atomic_inc(&sbi->s_mb_buddies_generated);
atomic64_add(period, &sbi->s_mb_generation_time);
mb_update_avg_fragment_size(sb, grp);
}
/* The buddy information is attached the buddy cache inode
@ -2636,7 +2594,7 @@ static noinline_for_stack int
ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
{
ext4_group_t prefetch_grp = 0, ngroups, group, i;
int cr = -1;
int cr = -1, new_cr;
int err = 0, first_err = 0;
unsigned int nr = 0, prefetch_ios = 0;
struct ext4_sb_info *sbi;
@ -2707,17 +2665,14 @@ repeat:
* from the goal value specified
*/
group = ac->ac_g_ex.fe_group;
ac->ac_last_optimal_group = group;
ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups;
prefetch_grp = group;
for (i = 0; i < ngroups; group = next_linear_group(ac, group, ngroups),
i++) {
int ret = 0, new_cr;
for (i = 0, new_cr = cr; i < ngroups; i++,
ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) {
int ret = 0;
cond_resched();
ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups);
if (new_cr != cr) {
cr = new_cr;
goto repeat;
@ -2991,9 +2946,7 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock)
struct super_block *sb = pde_data(file_inode(seq->file));
unsigned long position;
read_lock(&EXT4_SB(sb)->s_mb_rb_lock);
if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1)
if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb))
return NULL;
position = *pos + 1;
return (void *) ((unsigned long) position);
@ -3005,7 +2958,7 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof
unsigned long position;
++*pos;
if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1)
if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb))
return NULL;
position = *pos + 1;
return (void *) ((unsigned long) position);
@ -3017,29 +2970,22 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned long position = ((unsigned long) v);
struct ext4_group_info *grp;
struct rb_node *n;
unsigned int count, min, max;
unsigned int count;
position--;
if (position >= MB_NUM_ORDERS(sb)) {
seq_puts(seq, "fragment_size_tree:\n");
n = rb_first(&sbi->s_mb_avg_fragment_size_root);
if (!n) {
seq_puts(seq, "\ttree_min: 0\n\ttree_max: 0\n\ttree_nodes: 0\n");
return 0;
}
grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb);
min = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0;
count = 1;
while (rb_next(n)) {
count++;
n = rb_next(n);
}
grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb);
max = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0;
position -= MB_NUM_ORDERS(sb);
if (position == 0)
seq_puts(seq, "avg_fragment_size_lists:\n");
seq_printf(seq, "\ttree_min: %u\n\ttree_max: %u\n\ttree_nodes: %u\n",
min, max, count);
count = 0;
read_lock(&sbi->s_mb_avg_fragment_size_locks[position]);
list_for_each_entry(grp, &sbi->s_mb_avg_fragment_size[position],
bb_avg_fragment_size_node)
count++;
read_unlock(&sbi->s_mb_avg_fragment_size_locks[position]);
seq_printf(seq, "\tlist_order_%u_groups: %u\n",
(unsigned int)position, count);
return 0;
}
@ -3049,9 +2995,11 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
seq_puts(seq, "max_free_order_lists:\n");
}
count = 0;
read_lock(&sbi->s_mb_largest_free_orders_locks[position]);
list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position],
bb_largest_free_order_node)
count++;
read_unlock(&sbi->s_mb_largest_free_orders_locks[position]);
seq_printf(seq, "\tlist_order_%u_groups: %u\n",
(unsigned int)position, count);
@ -3059,11 +3007,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v)
}
static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v)
__releases(&EXT4_SB(sb)->s_mb_rb_lock)
{
struct super_block *sb = pde_data(file_inode(seq->file));
read_unlock(&EXT4_SB(sb)->s_mb_rb_lock);
}
const struct seq_operations ext4_mb_seq_structs_summary_ops = {
@ -3176,8 +3120,9 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
init_rwsem(&meta_group_info[i]->alloc_sem);
meta_group_info[i]->bb_free_root = RB_ROOT;
INIT_LIST_HEAD(&meta_group_info[i]->bb_largest_free_order_node);
RB_CLEAR_NODE(&meta_group_info[i]->bb_avg_fragment_size_rb);
INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node);
meta_group_info[i]->bb_largest_free_order = -1; /* uninit */
meta_group_info[i]->bb_avg_fragment_size_order = -1; /* uninit */
meta_group_info[i]->bb_group = group;
mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group);
@ -3426,7 +3371,24 @@ int ext4_mb_init(struct super_block *sb)
i++;
} while (i < MB_NUM_ORDERS(sb));
sbi->s_mb_avg_fragment_size_root = RB_ROOT;
sbi->s_mb_avg_fragment_size =
kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head),
GFP_KERNEL);
if (!sbi->s_mb_avg_fragment_size) {
ret = -ENOMEM;
goto out;
}
sbi->s_mb_avg_fragment_size_locks =
kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t),
GFP_KERNEL);
if (!sbi->s_mb_avg_fragment_size_locks) {
ret = -ENOMEM;
goto out;
}
for (i = 0; i < MB_NUM_ORDERS(sb); i++) {
INIT_LIST_HEAD(&sbi->s_mb_avg_fragment_size[i]);
rwlock_init(&sbi->s_mb_avg_fragment_size_locks[i]);
}
sbi->s_mb_largest_free_orders =
kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head),
GFP_KERNEL);
@ -3445,7 +3407,6 @@ int ext4_mb_init(struct super_block *sb)
INIT_LIST_HEAD(&sbi->s_mb_largest_free_orders[i]);
rwlock_init(&sbi->s_mb_largest_free_orders_locks[i]);
}
rwlock_init(&sbi->s_mb_rb_lock);
spin_lock_init(&sbi->s_md_lock);
sbi->s_mb_free_pending = 0;
@ -3516,6 +3477,8 @@ out_free_locality_groups:
free_percpu(sbi->s_locality_groups);
sbi->s_locality_groups = NULL;
out:
kfree(sbi->s_mb_avg_fragment_size);
kfree(sbi->s_mb_avg_fragment_size_locks);
kfree(sbi->s_mb_largest_free_orders);
kfree(sbi->s_mb_largest_free_orders_locks);
kfree(sbi->s_mb_offsets);
@ -3582,6 +3545,8 @@ int ext4_mb_release(struct super_block *sb)
kvfree(group_info);
rcu_read_unlock();
}
kfree(sbi->s_mb_avg_fragment_size);
kfree(sbi->s_mb_avg_fragment_size_locks);
kfree(sbi->s_mb_largest_free_orders);
kfree(sbi->s_mb_largest_free_orders_locks);
kfree(sbi->s_mb_offsets);
@ -5193,6 +5158,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
int bsbits = ac->ac_sb->s_blocksize_bits;
loff_t size, isize;
bool inode_pa_eligible, group_pa_eligible;
if (!(ac->ac_flags & EXT4_MB_HINT_DATA))
return;
@ -5200,25 +5166,27 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
return;
group_pa_eligible = sbi->s_mb_group_prealloc > 0;
inode_pa_eligible = true;
size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len);
isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)
>> bsbits;
/* No point in using inode preallocation for closed files */
if ((size == isize) && !ext4_fs_is_busy(sbi) &&
!inode_is_open_for_write(ac->ac_inode)) {
ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC;
return;
}
!inode_is_open_for_write(ac->ac_inode))
inode_pa_eligible = false;
if (sbi->s_mb_group_prealloc <= 0) {
ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
return;
}
/* don't use group allocation for large files */
size = max(size, isize);
if (size > sbi->s_mb_stream_request) {
ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
/* Don't use group allocation for large files */
if (size > sbi->s_mb_stream_request)
group_pa_eligible = false;
if (!group_pa_eligible) {
if (inode_pa_eligible)
ac->ac_flags |= EXT4_MB_STREAM_ALLOC;
else
ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC;
return;
}
@ -5565,6 +5533,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
ext4_fsblk_t block = 0;
unsigned int inquota = 0;
unsigned int reserv_clstrs = 0;
int retries = 0;
u64 seq;
might_sleep();
@ -5667,7 +5636,8 @@ repeat:
ar->len = ac->ac_b_ex.fe_len;
}
} else {
if (ext4_mb_discard_preallocations_should_retry(sb, ac, &seq))
if (++retries < 3 &&
ext4_mb_discard_preallocations_should_retry(sb, ac, &seq))
goto repeat;
/*
* If block allocation fails then the pa allocated above

1
fs/ext4/mballoc.h
View File

@ -178,7 +178,6 @@ struct ext4_allocation_context {
/* copy of the best found extent taken before preallocation efforts */
struct ext4_free_extent ac_f_ex;
ext4_group_t ac_last_optimal_group;
__u32 ac_groups_considered;
__u32 ac_flags; /* allocation hints */
__u16 ac_groups_scanned;