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>

3 files changed, 10 insertions, 12 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0ecf819bf189..5582fba36b44 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -27,8 +27,8 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/fiemap.h>
-#include <linux/backing-dev.h>
 #include <linux/iomap.h>
+#include <linux/sched/mm.h>
 #include "ext4_jbd2.h"
 #include "ext4_extents.h"
 #include "xattr.h"
@@ -4407,8 +4407,7 @@ 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);
+		memalloc_retry_wait(GFP_ATOMIC);
 		goto retry;
 	}
 	if (err)
@@ -4416,8 +4415,7 @@ retry:
 retry_remove_space:
 	err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
 	if (err == -ENOMEM) {
-		cond_resched();
-		congestion_wait(BLK_RW_ASYNC, HZ/50);
+		memalloc_retry_wait(GFP_ATOMIC);
 		goto retry_remove_space;
 	}
 	return err;
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 39a1ab129fdc..635bcf68a67e 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -7,7 +7,7 @@
 #include <linux/iomap.h>
 #include <linux/fiemap.h>
 #include <linux/iversion.h>
-#include <linux/backing-dev.h>
+#include <linux/sched/mm.h>
 
 #include "ext4_jbd2.h"
 #include "ext4.h"
@@ -1929,8 +1929,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 retry:
 			err = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 			if (err == -ENOMEM) {
-				cond_resched();
-				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				memalloc_retry_wait(GFP_ATOMIC);
 				goto retry;
 			}
 			if (err)
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 9cb261714991..1d370364230e 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -24,7 +24,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
-#include <linux/backing-dev.h>
+#include <linux/sched/mm.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -523,12 +523,13 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 			ret = PTR_ERR(bounce_page);
 			if (ret == -ENOMEM &&
 			    (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) {
-				gfp_flags = GFP_NOFS;
+				gfp_t new_gfp_flags = GFP_NOFS;
 				if (io->io_bio)
 					ext4_io_submit(io);
 				else
-					gfp_flags |= __GFP_NOFAIL;
-				congestion_wait(BLK_RW_ASYNC, HZ/50);
+					new_gfp_flags |= __GFP_NOFAIL;
+				memalloc_retry_wait(gfp_flags);
+				gfp_flags = new_gfp_flags;
 				goto retry_encrypt;
 			}