diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-05-26 19:34:26 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-05-26 19:34:26 -0700 |
commit | 315227f6da389f3a560f27f7777080857278e1b4 (patch) | |
tree | 11306e1e8d8b66044ab48901b90141b5362c12e3 /fs/block_dev.c | |
parent | a10c38a4f385f5d7c173a263ff6bb2d36021b3bb (diff) | |
parent | 40543f62cbdce42633e3fe10923099feee272e1f (diff) | |
download | op-kernel-dev-315227f6da389f3a560f27f7777080857278e1b4.zip op-kernel-dev-315227f6da389f3a560f27f7777080857278e1b4.tar.gz |
Merge tag 'dax-misc-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull misc DAX updates from Vishal Verma:
"DAX error handling for 4.7
- Until now, dax has been disabled if media errors were found on any
device. This enables the use of DAX in the presence of these
errors by making all sector-aligned zeroing go through the driver.
- The driver (already) has the ability to clear errors on writes that
are sent through the block layer using 'DSMs' defined in ACPI 6.1.
Other misc changes:
- When mounting DAX filesystems, check to make sure the partition is
page aligned. This is a requirement for DAX, and previously, we
allowed such unaligned mounts to succeed, but subsequent
reads/writes would fail.
- Misc/cleanup fixes from Jan that remove unused code from DAX
related to zeroing, writeback, and some size checks"
* tag 'dax-misc-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
dax: fix a comment in dax_zero_page_range and dax_truncate_page
dax: for truncate/hole-punch, do zeroing through the driver if possible
dax: export a low-level __dax_zero_page_range helper
dax: use sb_issue_zerout instead of calling dax_clear_sectors
dax: enable dax in the presence of known media errors (badblocks)
dax: fallback from pmd to pte on error
block: Update blkdev_dax_capable() for consistency
xfs: Add alignment check for DAX mount
ext2: Add alignment check for DAX mount
ext4: Add alignment check for DAX mount
block: Add bdev_dax_supported() for dax mount checks
block: Add vfs_msg() interface
dax: Remove redundant inode size checks
dax: Remove pointless writeback from dax_do_io()
dax: Remove zeroing from dax_io()
dax: Remove dead zeroing code from fault handlers
ext2: Avoid DAX zeroing to corrupt data
ext2: Fix block zeroing in ext2_get_blocks() for DAX
dax: Remove complete_unwritten argument
DAX: move RADIX_DAX_ definitions to dax.c
Diffstat (limited to 'fs/block_dev.c')
-rw-r--r-- | fs/block_dev.c | 114 |
1 files changed, 84 insertions, 30 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c index 1089dbf..71ccab1 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -51,6 +51,18 @@ struct block_device *I_BDEV(struct inode *inode) } EXPORT_SYMBOL(I_BDEV); +void __vfs_msg(struct super_block *sb, const char *prefix, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk_ratelimited("%sVFS (%s): %pV\n", prefix, sb->s_id, &vaf); + va_end(args); +} + static void bdev_write_inode(struct block_device *bdev) { struct inode *inode = bdev->bd_inode; @@ -489,7 +501,7 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax) sector += get_start_sect(bdev); if (sector % (PAGE_SIZE / 512)) return -EINVAL; - avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn); + avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn, size); if (!avail) return -ERANGE; if (avail > 0 && avail & ~PAGE_MASK) @@ -498,6 +510,75 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax) } EXPORT_SYMBOL_GPL(bdev_direct_access); +/** + * bdev_dax_supported() - Check if the device supports dax for filesystem + * @sb: The superblock of the device + * @blocksize: The block size of the device + * + * This is a library function for filesystems to check if the block device + * can be mounted with dax option. + * + * Return: negative errno if unsupported, 0 if supported. + */ +int bdev_dax_supported(struct super_block *sb, int blocksize) +{ + struct blk_dax_ctl dax = { + .sector = 0, + .size = PAGE_SIZE, + }; + int err; + + if (blocksize != PAGE_SIZE) { + vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax"); + return -EINVAL; + } + + err = bdev_direct_access(sb->s_bdev, &dax); + if (err < 0) { + switch (err) { + case -EOPNOTSUPP: + vfs_msg(sb, KERN_ERR, + "error: device does not support dax"); + break; + case -EINVAL: + vfs_msg(sb, KERN_ERR, + "error: unaligned partition for dax"); + break; + default: + vfs_msg(sb, KERN_ERR, + "error: dax access failed (%d)", err); + } + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(bdev_dax_supported); + +/** + * bdev_dax_capable() - Return if the raw device is capable for dax + * @bdev: The device for raw block device access + */ +bool bdev_dax_capable(struct block_device *bdev) +{ + struct blk_dax_ctl dax = { + .size = PAGE_SIZE, + }; + + if (!IS_ENABLED(CONFIG_FS_DAX)) + return false; + + dax.sector = 0; + if (bdev_direct_access(bdev, &dax) < 0) + return false; + + dax.sector = bdev->bd_part->nr_sects - (PAGE_SIZE / 512); + if (bdev_direct_access(bdev, &dax) < 0) + return false; + + return true; +} + /* * pseudo-fs */ @@ -1160,33 +1241,6 @@ void bd_set_size(struct block_device *bdev, loff_t size) } EXPORT_SYMBOL(bd_set_size); -static bool blkdev_dax_capable(struct block_device *bdev) -{ - struct gendisk *disk = bdev->bd_disk; - - if (!disk->fops->direct_access || !IS_ENABLED(CONFIG_FS_DAX)) - return false; - - /* - * If the partition is not aligned on a page boundary, we can't - * do dax I/O to it. - */ - if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) - || (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) - return false; - - /* - * If the device has known bad blocks, force all I/O through the - * driver / page cache. - * - * TODO: support finer grained dax error handling - */ - if (disk->bb && disk->bb->count) - return false; - - return true; -} - static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); /* @@ -1266,7 +1320,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); - if (!blkdev_dax_capable(bdev)) + if (!bdev_dax_capable(bdev)) bdev->bd_inode->i_flags &= ~S_DAX; } @@ -1303,7 +1357,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); - if (!blkdev_dax_capable(bdev)) + if (!bdev_dax_capable(bdev)) bdev->bd_inode->i_flags &= ~S_DAX; } } else { |