The patch titled
Subject: buffer: hoist GFP flags from grow_dev_page() to __getblk_gfp()
has been added to the -mm mm-unstable branch. Its filename is
buffer-hoist-gfp-flags-from-grow_dev_page-to-__getblk_gfp.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/buffer-hoist-gfp-flags-from-grow_dev_page-to-__getblk_gfp.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
Subject: buffer: hoist GFP flags from grow_dev_page() to __getblk_gfp()
Date: Thu, 14 Sep 2023 16:00:05 +0100
grow_dev_page() is only called by grow_buffers(). grow_buffers() is only
called by __getblk_slow() and __getblk_slow() is only called from
__getblk_gfp(), so it is safe to move the GFP flags setting all the way
up. With that done, add a new bdev_getblk() entry point that leaves the
GFP flags the way the caller specified them.
Link: https://lkml.kernel.org/r/20230914150011.843330-3-willy@xxxxxxxxxxxxx
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Hui Zhu <teawater@xxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/buffer.c | 60 ++++++++++++++++++++++------------
include/linux/buffer_head.h | 2 +
2 files changed, 41 insertions(+), 21 deletions(-)
--- a/fs/buffer.c~buffer-hoist-gfp-flags-from-grow_dev_page-to-__getblk_gfp
+++ a/fs/buffer.c
@@ -1043,20 +1043,11 @@ grow_dev_page(struct block_device *bdev,
struct buffer_head *bh;
sector_t end_block;
int ret = 0;
- gfp_t gfp_mask;
-
- gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp;
-
- /*
- * XXX: __getblk_slow() can not really deal with failure and
- * will endlessly loop on improvised global reclaim. Prefer
- * looping in the allocator rather than here, at least that
- * code knows what it's doing.
- */
- gfp_mask |= __GFP_NOFAIL;
folio = __filemap_get_folio(inode->i_mapping, index,
- FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp_mask);
+ FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
bh = folio_buffers(folio);
if (bh) {
@@ -1069,7 +1060,9 @@ grow_dev_page(struct block_device *bdev,
goto failed;
}
- bh = folio_alloc_buffers(folio, size, gfp_mask | __GFP_ACCOUNT);
+ bh = folio_alloc_buffers(folio, size, gfp | __GFP_ACCOUNT);
+ if (!bh)
+ goto failed;
/*
* Link the folio to the buffers and initialise them. Take the
@@ -1420,24 +1413,49 @@ __find_get_block(struct block_device *bd
}
EXPORT_SYMBOL(__find_get_block);
+/**
+ * bdev_getblk - Get a buffer_head in a block device's buffer cache.
+ * @bdev: The block device.
+ * @block: The block number.
+ * @size: The size of buffer_heads for this @bdev.
+ * @gfp: The memory allocation flags to use.
+ *
+ * In contrast to __getblk_gfp(), the @gfp flags must be all of the flags;
+ * they are not augmented with the mapping's GFP flags.
+ *
+ * Return: The buffer head, or NULL if memory could not be allocated.
+ */
+struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
+ unsigned size, gfp_t gfp)
+{
+ struct buffer_head *bh = __find_get_block(bdev, block, size);
+
+ might_alloc(gfp);
+ if (bh)
+ return bh;
+
+ return __getblk_slow(bdev, block, size, gfp);
+}
+EXPORT_SYMBOL(bdev_getblk);
+
/*
* __getblk_gfp() will locate (and, if necessary, create) the buffer_head
* which corresponds to the passed block_device, block and size. The
* returned buffer has its reference count incremented.
- *
- * __getblk_gfp() will lock up the machine if grow_dev_page's
- * try_to_free_buffers() attempt is failing. FIXME, perhaps?
*/
struct buffer_head *
__getblk_gfp(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp)
{
- struct buffer_head *bh = __find_get_block(bdev, block, size);
+ gfp |= mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS);
- might_sleep();
- if (bh == NULL)
- bh = __getblk_slow(bdev, block, size, gfp);
- return bh;
+ /*
+ * Prefer looping in the allocator rather than here, at least that
+ * code knows what it's doing.
+ */
+ gfp |= __GFP_NOFAIL;
+
+ return bdev_getblk(bdev, block, size, gfp);
}
EXPORT_SYMBOL(__getblk_gfp);
--- a/include/linux/buffer_head.h~buffer-hoist-gfp-flags-from-grow_dev_page-to-__getblk_gfp
+++ a/include/linux/buffer_head.h
@@ -224,6 +224,8 @@ void __wait_on_buffer(struct buffer_head
wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
unsigned size);
+struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
+ unsigned size, gfp_t gfp);
struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block,
unsigned size, gfp_t gfp);
void __brelse(struct buffer_head *);
_
Patches currently in -mm which might be from willy@xxxxxxxxxxxxx are
mm-convert-dax-lock-unlock-page-to-lock-unlock-folio.patch
buffer-pass-gfp-flags-to-folio_alloc_buffers.patch
buffer-hoist-gfp-flags-from-grow_dev_page-to-__getblk_gfp.patch
ext4-use-bdev_getblk-to-avoid-memory-reclaim-in-readahead-path.patch
buffer-use-bdev_getblk-to-avoid-memory-reclaim-in-readahead-path.patch
buffer-convert-getblk_unmovable-and-__getblk-to-use-bdev_getblk.patch
buffer-convert-sb_getblk-to-call-__getblk.patch
ext4-call-bdev_getblk-from-sb_getblk_gfp.patch
buffer-remove-__getblk_gfp.patch
