Hi Chao,
[snip]
> > > >
> > > > - /* No failure on bio allocation */
> > > > - bio = bio_alloc(GFP_NOIO, npages);
> > >
> > > How about using __GFP_NOFAIL flag to avoid failing in bio_alloc instead
> > > of adding opencode endless loop in code?
> > >
> > > We can see the reason in this commit 647757197cd3
> > > ("mm: clarify __GFP_NOFAIL deprecation status ")
> > >
> > > "__GFP_NOFAIL is documented as a deprecated flag since commit
> > > 478352e789f5 ("mm: add comment about deprecation of __GFP_NOFAIL").
> > >
> > > This has discouraged people from using it but in some cases an opencoded
> > > endless loop around allocator has been used instead. So the allocator
> > > is not aware of the de facto __GFP_NOFAIL allocation because this
> > > information was not communicated properly.
> > >
> > > Let's make clear that if the allocation context really cannot afford
> > > failure because there is no good failure policy then using __GFP_NOFAIL
> > > is preferable to opencoding the loop outside of the allocator."
> > >
> > > BTW, I found that f2fs_kmem_cache_alloc also could be replaced, we could
> > > fix them together.
> >
> > Agreed. I think that can be another patch like this.
> >
> > From 1579e0d1ada96994c4ec6619fb5b5d9386e77ab3 Mon Sep 17 00:00:00 2001
> > From: Jaegeuk Kim <jaeg...@kernel.org>
> > Date: Thu, 20 Aug 2015 08:51:56 -0700
> > Subject: [PATCH] f2fs: use __GFP_NOFAIL to avoid infinite loop
> >
> > __GFP_NOFAIL can avoid retrying the whole path of kmem_cache_alloc and
> > bio_alloc.
> >
> > Suggested-by: Chao Yu <chao2...@samsung.com>
> > Signed-off-by: Jaegeuk Kim <jaeg...@kernel.org>
> > ---
> > fs/f2fs/f2fs.h | 16 +++++-----------
> > 1 file changed, 5 insertions(+), 11 deletions(-)
> >
> > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
> > index 00591f7..c78b599 100644
> > --- a/fs/f2fs/f2fs.h
> > +++ b/fs/f2fs/f2fs.h
> > @@ -1244,13 +1244,10 @@ static inline void *f2fs_kmem_cache_alloc(struct
> > kmem_cache *cachep,
> > gfp_t flags)
> > {
> > void *entry;
> > -retry:
> > - entry = kmem_cache_alloc(cachep, flags);
> > - if (!entry) {
> > - cond_resched();
> > - goto retry;
> > - }
> >
> > + entry = kmem_cache_alloc(cachep, flags);
> > + if (!entry)
> > + entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL);
>
> The fast + slow path model looks good to me, expect one thing:
> In several paths of checkpoint, caller will grab slab cache with GFP_ATOMIC,
> so in slow path, our flags will be GFP_ATOMIC | __GFP_NOFAIL, I'm not sure
> that the two flags can be used together.
>
> Should we replace GFP_ATOMIC with GFP_NOFS in flags if caller passed
> GFP_ATOMIC?
Indeed, we need to avoid GFP_ATOMIC as much as possible to mitigate memory
pressure at this moment. Too much abused.
I wrote a patch like this.
>From a9209556d024cdce490695586ecee3164efda49c Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaeg...@kernel.org>
Date: Thu, 20 Aug 2015 08:51:56 -0700
Subject: [PATCH] f2fs: use __GFP_NOFAIL to avoid infinite loop
__GFP_NOFAIL can avoid retrying the whole path of kmem_cache_alloc and
bio_alloc.
And, it also fixes the use cases of GFP_ATOMIC correctly.
Suggested-by: Chao Yu <chao2...@samsung.com>
Signed-off-by: Jaegeuk Kim <jaeg...@kernel.org>
---
fs/f2fs/checkpoint.c | 21 ++++++++-------------
fs/f2fs/f2fs.h | 16 +++++-----------
fs/f2fs/node.c | 4 ++--
fs/f2fs/segment.c | 2 +-
4 files changed, 16 insertions(+), 27 deletions(-)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 890e4d4..c5a38e3 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -336,26 +336,18 @@ const struct address_space_operations f2fs_meta_aops = {
static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
struct inode_management *im = &sbi->im[type];
- struct ino_entry *e;
+ struct ino_entry *e, *tmp;
+
+ tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS);
retry:
- if (radix_tree_preload(GFP_NOFS)) {
- cond_resched();
- goto retry;
- }
+ radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
spin_lock(&im->ino_lock);
-
e = radix_tree_lookup(&im->ino_root, ino);
if (!e) {
- e = kmem_cache_alloc(ino_entry_slab, GFP_ATOMIC);
- if (!e) {
- spin_unlock(&im->ino_lock);
- radix_tree_preload_end();
- goto retry;
- }
+ e = tmp;
if (radix_tree_insert(&im->ino_root, ino, e)) {
spin_unlock(&im->ino_lock);
- kmem_cache_free(ino_entry_slab, e);
radix_tree_preload_end();
goto retry;
}
@@ -368,6 +360,9 @@ retry:
}
spin_unlock(&im->ino_lock);
radix_tree_preload_end();
+
+ if (e != tmp)
+ kmem_cache_free(ino_entry_slab, tmp);
}
static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 6641017..ece5e70 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1252,13 +1252,10 @@ static inline void *f2fs_kmem_cache_alloc(struct
kmem_cache *cachep,
gfp_t flags)
{
void *entry;
-retry:
- entry = kmem_cache_alloc(cachep, flags);
- if (!entry) {
- cond_resched();
- goto retry;
- }
+ entry = kmem_cache_alloc(cachep, flags);
+ if (!entry)
+ entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL);
return entry;
}
@@ -1267,12 +1264,9 @@ static inline struct bio *f2fs_bio_alloc(int npages)
struct bio *bio;
/* No failure on bio allocation */
-retry:
bio = bio_alloc(GFP_NOIO, npages);
- if (!bio) {
- cond_resched();
- goto retry;
- }
+ if (!bio)
+ bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
return bio;
}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 6bef5a2..777066d 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -159,7 +159,7 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
head = radix_tree_lookup(&nm_i->nat_set_root, set);
if (!head) {
- head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_ATOMIC);
+ head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_NOFS);
INIT_LIST_HEAD(&head->entry_list);
INIT_LIST_HEAD(&head->set_list);
@@ -246,7 +246,7 @@ static struct nat_entry *grab_nat_entry(struct f2fs_nm_info
*nm_i, nid_t nid)
{
struct nat_entry *new;
- new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC);
+ new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
f2fs_radix_tree_insert(&nm_i->nat_root, nid, new);
memset(new, 0, sizeof(struct nat_entry));
nat_set_nid(new, nid);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 6273e2c..78e6d06 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1753,7 +1753,7 @@ static struct page *get_next_sit_page(struct f2fs_sb_info
*sbi,
static struct sit_entry_set *grab_sit_entry_set(void)
{
struct sit_entry_set *ses =
- f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_ATOMIC);
+ f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_NOFS);
ses->entry_cnt = 0;
INIT_LIST_HEAD(&ses->set_list);
--
2.1.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
