mm: introduce memalloc_retry_wait()

Various places in the kernel - largely in filesystems - respond to a
memory allocation failure by looping around and re-trying.  Some of
these cannot conveniently use __GFP_NOFAIL, for reasons such as:

 - a GFP_ATOMIC allocation, which __GFP_NOFAIL doesn't work on
 - a need to check for the process being signalled between failures
 - the possibility that other recovery actions could be performed
 - the allocation is quite deep in support code, and passing down an
   extra flag to say if __GFP_NOFAIL is wanted would be clumsy.

Many of these currently use congestion_wait() which (in almost all
cases) simply waits the given timeout - congestion isn't tracked for
most devices.

It isn't clear what the best delay is for loops, but it is clear that
the various filesystems shouldn't be responsible for choosing a timeout.

This patch introduces memalloc_retry_wait() with takes on that
responsibility.  Code that wants to retry a memory allocation can call
this function passing the GFP flags that were used.  It will wait
however is appropriate.

For now, it only considers __GFP_NORETRY and whatever
gfpflags_allow_blocking() tests.  If blocking is allowed without
__GFP_NORETRY, then alloc_page either made some reclaim progress, or
waited for a while, before failing.  So there is no need for much
further waiting.  memalloc_retry_wait() will wait until the current
jiffie ends.  If this condition is not met, then alloc_page() won't have
waited much if at all.  In that case memalloc_retry_wait() waits about
200ms.  This is the delay that most current loops uses.

linux/sched/mm.h needs to be included in some files now,
but linux/backing-dev.h does not.

Link: https://lkml.kernel.org/r/163754371968.13692.1277530886009912421@noble.neil.brown.name
Signed-off-by: NeilBrown <neilb@suse.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Chao Yu <chao@kernel.org>
Cc: Darrick J. Wong <djwong@kernel.org>
Cc: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

7 files changed, 16 insertions, 21 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 9f754aaef558..aacf5e4dcc57 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -8,9 +8,9 @@
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include <linux/buffer_head.h>
+#include <linux/sched/mm.h>
 #include <linux/mpage.h>
 #include <linux/writeback.h>
-#include <linux/backing-dev.h>
 #include <linux/pagevec.h>
 #include <linux/blkdev.h>
 #include <linux/bio.h>
@@ -2542,7 +2542,7 @@ retry_encrypt:
 		/* flush pending IOs and wait for a while in the ENOMEM case */
 		if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
 			f2fs_flush_merged_writes(fio->sbi);
-			congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
+			memalloc_retry_wait(GFP_NOFS);
 			gfp_flags |= __GFP_NOFAIL;
 			goto retry_encrypt;
 		}
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index a946ce0ead34..374bbb5294d9 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -7,7 +7,6 @@
  */
 #include <linux/fs.h>
 #include <linux/module.h>
-#include <linux/backing-dev.h>
 #include <linux/init.h>
 #include <linux/f2fs_fs.h>
 #include <linux/kthread.h>
@@ -15,6 +14,7 @@
 #include <linux/freezer.h>
 #include <linux/sched/signal.h>
 #include <linux/random.h>
+#include <linux/sched/mm.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -1375,8 +1375,7 @@ retry:
 		if (err) {
 			clear_page_private_gcing(page);
 			if (err == -ENOMEM) {
-				congestion_wait(BLK_RW_ASYNC,
-						DEFAULT_IO_TIMEOUT);
+				memalloc_retry_wait(GFP_NOFS);
 				goto retry;
 			}
 			if (is_dirty)
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 0f8b2df3e1e0..4c11254a07d4 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -8,8 +8,8 @@
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include <linux/buffer_head.h>
-#include <linux/backing-dev.h>
 #include <linux/writeback.h>
+#include <linux/sched/mm.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -562,7 +562,7 @@ retry:
 	inode = f2fs_iget(sb, ino);
 	if (IS_ERR(inode)) {
 		if (PTR_ERR(inode) == -ENOMEM) {
-			congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
+			memalloc_retry_wait(GFP_NOFS);
 			goto retry;
 		}
 	}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 556fcd8457f3..219506ca9a97 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -8,7 +8,7 @@
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include <linux/mpage.h>
-#include <linux/backing-dev.h>
+#include <linux/sched/mm.h>
 #include <linux/blkdev.h>
 #include <linux/pagevec.h>
 #include <linux/swap.h>
@@ -2750,7 +2750,7 @@ int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 retry:
 	ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false);
 	if (!ipage) {
-		congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
+		memalloc_retry_wait(GFP_NOFS);
 		goto retry;
 	}
 
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 6a1b4668d933..d1664a0567ef 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -8,6 +8,7 @@
 #include <asm/unaligned.h>
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
+#include <linux/sched/mm.h>
 #include "f2fs.h"
 #include "node.h"
 #include "segment.h"
@@ -587,7 +588,7 @@ retry_dn:
 	err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE);
 	if (err) {
 		if (err == -ENOMEM) {
-			congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT);
+			memalloc_retry_wait(GFP_NOFS);
 			goto retry_dn;
 		}
 		goto out;
@@ -670,8 +671,7 @@ retry_prev:
 			err = check_index_in_prev_nodes(sbi, dest, &dn);
 			if (err) {
 				if (err == -ENOMEM) {
-					congestion_wait(BLK_RW_ASYNC,
-							DEFAULT_IO_TIMEOUT);
+					memalloc_retry_wait(GFP_NOFS);
 					goto retry_prev;
 				}
 				goto err;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index df9ed75f0b7a..40fdb4a8daeb 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -9,6 +9,7 @@
 #include <linux/f2fs_fs.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/sched/mm.h>
 #include <linux/prefetch.h>
 #include <linux/kthread.h>
 #include <linux/swap.h>
@@ -245,9 +246,7 @@ retry:
 								LOOKUP_NODE);
 			if (err) {
 				if (err == -ENOMEM) {
-					congestion_wait(BLK_RW_ASYNC,
-							DEFAULT_IO_TIMEOUT);
-					cond_resched();
+					memalloc_retry_wait(GFP_NOFS);
 					goto retry;
 				}
 				err = -EAGAIN;
@@ -424,9 +423,7 @@ retry:
 			err = f2fs_do_write_data_page(&fio);
 			if (err) {
 				if (err == -ENOMEM) {
-					congestion_wait(BLK_RW_ASYNC,
-							DEFAULT_IO_TIMEOUT);
-					cond_resched();
+					memalloc_retry_wait(GFP_NOFS);
 					goto retry;
 				}
 				unlock_page(page);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 040b6d02e1d8..3bace24f8800 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -8,9 +8,9 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/fs.h>
+#include <linux/sched/mm.h>
 #include <linux/statfs.h>
 #include <linux/buffer_head.h>
-#include <linux/backing-dev.h>
 #include <linux/kthread.h>
 #include <linux/parser.h>
 #include <linux/mount.h>
@@ -2415,8 +2415,7 @@ repeat:
 		page = read_cache_page_gfp(mapping, blkidx, GFP_NOFS);
 		if (IS_ERR(page)) {
 			if (PTR_ERR(page) == -ENOMEM) {
-				congestion_wait(BLK_RW_ASYNC,
-						DEFAULT_IO_TIMEOUT);
+				memalloc_retry_wait(GFP_NOFS);
 				goto repeat;
 			}
 			set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);