linux-ext4 - [PATCH v2 2/8] buffer: Hoist GFP flags from grow_dev_page() to __getblk

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20230914150011.843330-3-willy@infradead.org>
Date:   Thu, 14 Sep 2023 16:00:05 +0100
From:   "Matthew Wilcox (Oracle)" <willy@...radead.org>
To:     akpm@...ux-foundation.org
Cc:     "Matthew Wilcox (Oracle)" <willy@...radead.org>,
        Hui Zhu <teawater@...group.com>, linux-fsdevel@...r.kernel.org,
        linux-ext4@...r.kernel.org
Subject: [PATCH v2 2/8] buffer: Hoist GFP flags from grow_dev_page() to __getblk_gfp()

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.

Signed-off-by: Matthew Wilcox (Oracle) <willy@...radead.org>
---
 fs/buffer.c                 | 60 ++++++++++++++++++++++++-------------
 include/linux/buffer_head.h |  2 ++
 2 files changed, 41 insertions(+), 21 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index a01b00d48de2..3fe293c9f3ca 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1043,20 +1043,11 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	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, sector_t block,
 			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 *bdev, sector_t block, unsigned size)
 }
 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);
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 79131e9941e7..e389f0fbba5a 100644
--- a/include/linux/buffer_head.h
+++ b/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 *);
-- 
2.40.1