leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

iomap: report collisions between directio and buffered writes to userspace

Browse Source 
If two programs simultaneously try to write to the same part of a file
via direct IO and buffered IO, there's a chance that the post-diowrite
pagecache invalidation will fail on the dirty page.  When this happens,
the dio write succeeded, which means that the page cache is no longer
coherent with the disk!

Programs are not supposed to mix IO types and this is a clear case of
data corruption, so store an EIO which will be reflected to userspace
during the next fsync.  Replace the WARN_ON with a ratelimited pr_crit
so that the developers have /some/ kind of breadcrumb to track down the
offending program(s) and file(s) involved.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
This commit is contained in:
Darrick J. Wong 2018-01-08 10:41:39 -08:00
parent c017cb5ddf
commit 5a9d929d6e
3 changed files with 34 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
fs/direct-io.c
View File

@ -219,6 +219,27 @@ static inline struct page *dio_get_page(struct dio *dio,
return dio->pages[sdio->head];
}
/*
* Warn about a page cache invalidation failure during a direct io write.
*/
void dio_warn_stale_pagecache(struct file *filp)
{
static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST);
char pathname[128];
struct inode *inode = file_inode(filp);
char *path;
errseq_set(&inode->i_mapping->wb_err, -EIO);
if (__ratelimit(&_rs)) {
path = file_path(filp, pathname, sizeof(pathname));
if (IS_ERR(path))
path = "(unknown)";
pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n");
pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid,
current->comm);
}
}
/**
* dio_complete() - called when all DIO BIO I/O has been completed
* @offset: the byte offset in the file of the completed operation
@ -290,7 +311,8 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
err = invalidate_inode_pages2_range(dio->inode->i_mapping,
offset >> PAGE_SHIFT,
(offset + ret - 1) >> PAGE_SHIFT);
WARN_ON_ONCE(err);
if (err)
dio_warn_stale_pagecache(dio->iocb->ki_filp);
}
if (!(dio->flags & DIO_SKIP_DIO_COUNT))

12
fs/iomap.c
View File

@ -753,7 +753,8 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
err = invalidate_inode_pages2_range(inode->i_mapping,
offset >> PAGE_SHIFT,
(offset + dio->size - 1) >> PAGE_SHIFT);
WARN_ON_ONCE(err);
if (err)
dio_warn_stale_pagecache(iocb->ki_filp);
}
inode_dio_end(file_inode(iocb->ki_filp));
@ -1018,9 +1019,16 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (ret)
goto out_free_dio;
/*
* Try to invalidate cache pages for the range we're direct
* writing. If this invalidation fails, tough, the write will
* still work, but racing two incompatible write paths is a
* pretty crazy thing to do, so we don't support it 100%.
*/
ret = invalidate_inode_pages2_range(mapping,
start >> PAGE_SHIFT, end >> PAGE_SHIFT);
WARN_ON_ONCE(ret);
if (ret)
dio_warn_stale_pagecache(iocb->ki_filp);
ret = 0;
if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&

1
include/linux/fs.h
View File

@ -2992,6 +2992,7 @@ enum {
};
void dio_end_io(struct bio *bio);
void dio_warn_stale_pagecache(struct file *filp);
ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, struct iov_iter *iter,