diff mbox series

[-next,RFC,01/14] block: add some bdev apis

Message ID 20231205123728.1866699-2-yukuai1@huaweicloud.com
State New
Headers show
Series [-next,RFC,01/14] block: add some bdev apis | expand

Commit Message

Yu Kuai Dec. 5, 2023, 12:37 p.m. UTC 
From: Yu Kuai <yukuai3@huawei.com>

Those apis will be used for other modules, so that bd_inode won't be
accessed directly from other modules.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 block/bdev.c           | 116 +++++++++++++++++++++++++++++++++++++++++
 block/bio.c            |   1 +
 block/blk.h            |   2 -
 include/linux/blkdev.h |  27 ++++++++++
 4 files changed, 144 insertions(+), 2 deletions(-)

Comments

Christoph Hellwig Dec. 6, 2023, 5:57 p.m. UTC | #1 
On Wed, Dec 06, 2023 at 12:50:38PM -0500, Theodore Ts'o wrote:
> This was added because pulling a mounted a USB thumb drive (or a HDD
> drops off the SATA bus) while the file system is mounted and actively
> in use, would result in a kernel OOPS.  If that's no longer true,
> that's great, but it would be good to test to make sure this is the
> case....

And, surprise, surprise - that didn't just affect ext4.  So I ended
up fixing this properly in the block layer.

> If we really want to remove it, I'd suggest doing this as a separate
> commit, so that after we see syzbot reports, or users complaining
> about kernel crashes, we can revert the removal if necessary.

Yes, this should of course be separate, well documented commit.
diff mbox series

Patch

diff --git a/block/bdev.c b/block/bdev.c
index 6f73b02d549c..fcba5c1bd113 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -92,6 +92,13 @@  void invalidate_bdev(struct block_device *bdev)
 }
 EXPORT_SYMBOL(invalidate_bdev);
 
+void invalidate_bdev_range(struct block_device *bdev, pgoff_t start,
+			   pgoff_t end)
+{
+	invalidate_mapping_pages(bdev->bd_inode->i_mapping, start, end);
+}
+EXPORT_SYMBOL_GPL(invalidate_bdev_range);
+
 /*
  * Drop all buffers & page cache for given bdev range. This function bails
  * with error if bdev has other exclusive owner (such as filesystem).
@@ -124,6 +131,7 @@  int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode,
 					     lstart >> PAGE_SHIFT,
 					     lend >> PAGE_SHIFT);
 }
+EXPORT_SYMBOL_GPL(truncate_bdev_range);
 
 static void set_init_blocksize(struct block_device *bdev)
 {
@@ -138,6 +146,18 @@  static void set_init_blocksize(struct block_device *bdev)
 	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
 }
 
+loff_t bdev_size(struct block_device *bdev)
+{
+	loff_t size;
+
+	spin_lock(&bdev->bd_size_lock);
+	size = i_size_read(bdev->bd_inode);
+	spin_unlock(&bdev->bd_size_lock);
+
+	return size;
+}
+EXPORT_SYMBOL_GPL(bdev_size);
+
 int set_blocksize(struct block_device *bdev, int size)
 {
 	/* Size must be a power of two, and between 512 and PAGE_SIZE */
@@ -1144,3 +1164,99 @@  static int __init setup_bdev_allow_write_mounted(char *str)
 	return 1;
 }
 __setup("bdev_allow_write_mounted=", setup_bdev_allow_write_mounted);
+
+struct folio *bdev_read_folio(struct block_device *bdev, pgoff_t index)
+{
+	return read_mapping_folio(bdev->bd_inode->i_mapping, index, NULL);
+}
+EXPORT_SYMBOL_GPL(bdev_read_folio);
+
+struct folio *bdev_read_folio_gfp(struct block_device *bdev, pgoff_t index,
+				  gfp_t gfp)
+{
+	return mapping_read_folio_gfp(bdev->bd_inode->i_mapping, index, gfp);
+}
+EXPORT_SYMBOL_GPL(bdev_read_folio_gfp);
+
+struct folio *bdev_get_folio(struct block_device *bdev, pgoff_t index)
+{
+	return filemap_get_folio(bdev->bd_inode->i_mapping, index);
+}
+EXPORT_SYMBOL_GPL(bdev_get_folio);
+
+struct folio *bdev_find_or_create_folio(struct block_device *bdev,
+					pgoff_t index, gfp_t gfp)
+{
+	return __filemap_get_folio(bdev->bd_inode->i_mapping, index,
+				   FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp);
+}
+EXPORT_SYMBOL_GPL(bdev_find_or_create_folio);
+
+int bdev_wb_err_check(struct block_device *bdev, errseq_t since)
+{
+	return errseq_check(&bdev->bd_inode->i_mapping->wb_err, since);
+}
+EXPORT_SYMBOL_GPL(bdev_wb_err_check);
+
+int bdev_wb_err_check_and_advance(struct block_device *bdev, errseq_t *since)
+{
+	return errseq_check_and_advance(&bdev->bd_inode->i_mapping->wb_err,
+					since);
+}
+EXPORT_SYMBOL_GPL(bdev_wb_err_check_and_advance);
+
+void bdev_balance_dirty_pages_ratelimited(struct block_device *bdev)
+{
+	return balance_dirty_pages_ratelimited(bdev->bd_inode->i_mapping);
+}
+EXPORT_SYMBOL_GPL(bdev_balance_dirty_pages_ratelimited);
+
+void bdev_sync_readahead(struct block_device *bdev, struct file_ra_state *ra,
+			 struct file *file, pgoff_t index,
+			 unsigned long req_count)
+{
+	struct file_ra_state tmp_ra = {};
+
+	if (!ra) {
+		ra = &tmp_ra;
+		file_ra_state_init(ra, bdev->bd_inode->i_mapping);
+	}
+	page_cache_sync_readahead(bdev->bd_inode->i_mapping, ra, file, index,
+				  req_count);
+}
+EXPORT_SYMBOL_GPL(bdev_sync_readahead);
+
+void bdev_attach_wb(struct block_device *bdev)
+{
+	inode_attach_wb(bdev->bd_inode, NULL);
+}
+EXPORT_SYMBOL_GPL(bdev_attach_wb);
+
+void bdev_correlate_mapping(struct block_device *bdev,
+			    struct address_space *mapping)
+{
+	mapping->host = bdev->bd_inode;
+}
+EXPORT_SYMBOL_GPL(bdev_correlate_mapping);
+
+gfp_t bdev_gfp_constraint(struct block_device *bdev, gfp_t gfp)
+{
+	return mapping_gfp_constraint(bdev->bd_inode->i_mapping, gfp);
+}
+EXPORT_SYMBOL_GPL(bdev_gfp_constraint);
+
+/*
+ * The del_gendisk() function uninitializes the disk-specific data
+ * structures, including the bdi structure, without telling anyone
+ * else.  Once this happens, any attempt to call mark_buffer_dirty()
+ * (for example, by ext4_commit_super), will cause a kernel OOPS.
+ * This is a kludge to prevent these oops until we can put in a proper
+ * hook in del_gendisk() to inform the VFS and file system layers.
+ */
+int bdev_ejected(struct block_device *bdev)
+{
+	struct backing_dev_info *bdi = inode_to_bdi(bdev->bd_inode);
+
+	return bdi->dev == NULL;
+}
+EXPORT_SYMBOL_GPL(bdev_ejected);
diff --git a/block/bio.c b/block/bio.c
index 816d412c06e9..f7123ad9b4ee 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1119,6 +1119,7 @@  void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
 	WARN_ON_ONCE(off > UINT_MAX);
 	__bio_add_page(bio, &folio->page, len, off);
 }
+EXPORT_SYMBOL_GPL(bio_add_folio_nofail);
 
 /**
  * bio_add_folio - Attempt to add part of a folio to a bio.
diff --git a/block/blk.h b/block/blk.h
index 08a358bc0919..da4becd4f7e9 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -467,8 +467,6 @@  extern struct device_attribute dev_attr_events_poll_msecs;
 extern struct attribute_group blk_trace_attr_group;
 
 blk_mode_t file_to_blk_mode(struct file *file);
-int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode,
-		loff_t lstart, loff_t lend);
 long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3f8a21cd9233..a55db77274a4 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1342,6 +1342,11 @@  static inline unsigned int block_size(struct block_device *bdev)
 	return 1 << bdev->bd_inode->i_blkbits;
 }
 
+static inline u8 block_bits(struct block_device *bdev)
+{
+	return bdev->bd_inode->i_blkbits;
+}
+
 int kblockd_schedule_work(struct work_struct *work);
 int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
 
@@ -1515,6 +1520,28 @@  struct block_device *blkdev_get_no_open(dev_t dev);
 void blkdev_put_no_open(struct block_device *bdev);
 
 struct block_device *I_BDEV(struct inode *inode);
+loff_t bdev_size(struct block_device *bdev);
+void invalidate_bdev_range(struct block_device *bdev, pgoff_t start,
+			   pgoff_t end);
+int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode,
+		loff_t lstart, loff_t lend);
+struct folio *bdev_get_folio(struct block_device *bdev, pgoff_t index);
+struct folio *bdev_find_or_create_folio(struct block_device *bdev,
+					pgoff_t index, gfp_t gfp);
+struct folio *bdev_read_folio(struct block_device *bdev, pgoff_t index);
+struct folio *bdev_read_folio_gfp(struct block_device *bdev, pgoff_t index,
+				  gfp_t gfp);
+int bdev_wb_err_check(struct block_device *bdev, errseq_t since);
+int bdev_wb_err_check_and_advance(struct block_device *bdev, errseq_t *since);
+void bdev_balance_dirty_pages_ratelimited(struct block_device *bdev);
+void bdev_sync_readahead(struct block_device *bdev, struct file_ra_state *ra,
+			 struct file *file, pgoff_t index,
+			 unsigned long req_count);
+void bdev_attach_wb(struct block_device *bdev);
+void bdev_correlate_mapping(struct block_device *bdev,
+			    struct address_space *mapping);
+gfp_t bdev_gfp_constraint(struct block_device *bdev, gfp_t gfp);
+int bdev_ejected(struct block_device *bdev);
 
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);