Trying to use a swapfile on NFS results in every DIO write failing with
ETXTBSY because generic_write_checks(), as called by nfs_direct_write()
from nfs_direct_IO(), forbids writes to swapfiles.
Fix this implementing the ->swap_rw() method for NFS, and using that to
bypass the checks in generic_write_checks(). [I'm not sure if we still
need to do some of the checks]
Without this patch, the following is seen:
Write error on dio swapfile (3800334336)
Altering __swap_writepage() to show the error shows:
Write error (-26) on dio swapfile (3800334336)
Tested by swapping off all swap partitions and then swapping on a prepared
NFS file (CONFIG_NFS_SWAP=y is also needed). Enough copies of the
following program then need to be run to force swapping to occur (at least
one per gigabyte of RAM):
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/mman.h>
int main()
{
unsigned int pid = getpid(), iterations = 0;
size_t i, j, size = 1024 * 1024 * 1024;
char *p;
bool mismatch;
p = malloc(size);
if (!p) {
perror("malloc");
exit(1);
}
srand(pid);
for (i = 0; i < size; i += 4)
*(unsigned int *)(p + i) = rand();
do {
for (j = 0; j < 16; j++) {
for (i = 0; i < size; i += 4096)
*(unsigned int *)(p + i) += 1;
iterations++;
}
mismatch = false;
srand(pid);
for (i = 0; i < size; i += 4) {
unsigned int r = rand();
unsigned int v = *(unsigned int *)(p + i);
if (i % 4096 == 0)
v -= iterations;
if (v != r) {
fprintf(stderr, "mismatch %zx: %x != %x (diff %x)\n",
i, v, r, v - r);
mismatch = true;
}
}
} while (!mismatch);
exit(1);
}
Fixes: dc617f29dbe5 ("vfs: don't allow writes to swap files")
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
cc: Anna Schumaker <anna.schumaker@xxxxxxxxxx>
cc: "NeilBrown" <neilb@xxxxxxx>
cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
cc: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
cc: Christoph Hellwig <hch@xxxxxx>
cc: linux-nfs@xxxxxxxxxxxxxxx
cc: linux-mm@xxxxxxxxx
cc: linux-fsdevel@xxxxxxxxxxxxxxx
---
fs/nfs/direct.c | 28 +++++++---------------------
fs/nfs/file.c | 14 ++++++--------
include/linux/nfs_fs.h | 2 +-
3 files changed, 14 insertions(+), 30 deletions(-)
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 2e894fec036b..71da8054df7e 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -152,28 +152,18 @@ nfs_direct_count_bytes(struct nfs_direct_req *dreq,
}
/**
- * nfs_direct_IO - NFS address space operation for direct I/O
+ * nfs_swap_rw - Do direct I/O to a swapfile on NFS
* @iocb: target I/O control block
* @iter: I/O buffer
*
* The presence of this routine in the address space ops vector means
- * the NFS client supports direct I/O. However, for most direct IO, we
- * shunt off direct read and write requests before the VFS gets them,
- * so this method is only ever called for swap.
+ * the NFS client supports direct I/O for swap.
*/
-ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+ssize_t nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter)
{
- struct inode *inode = iocb->ki_filp->f_mapping->host;
-
- /* we only support swap file calling nfs_direct_IO */
- if (!IS_SWAPFILE(inode))
- return 0;
-
- VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
-
- if (iov_iter_rw(iter) == READ)
- return nfs_file_direct_read(iocb, iter);
- return nfs_file_direct_write(iocb, iter);
+ if (iocb->ki_flags & IOCB_WRITE)
+ return nfs_file_direct_write(iocb, iter);
+ return nfs_file_direct_read(iocb, iter);
}
static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
@@ -894,7 +884,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
{
ssize_t result, requested;
- size_t count;
+ size_t count = iov_iter_count(iter);
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
@@ -905,10 +895,6 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n",
file, iov_iter_count(iter), (long long) iocb->ki_pos);
- result = generic_write_checks(iocb, iter);
- if (result <= 0)
- return result;
- count = result;
nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);
pos = iocb->ki_pos;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 7403ec6317cb..70dd49994751 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -523,7 +523,7 @@ const struct address_space_operations nfs_file_aops = {
.write_end = nfs_write_end,
.invalidatepage = nfs_invalidate_page,
.releasepage = nfs_release_page,
- .direct_IO = nfs_direct_IO,
+ .swap_rw = nfs_swap_rw,
#ifdef CONFIG_MIGRATION
.migratepage = nfs_migrate_page,
#endif
@@ -616,14 +616,16 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
if (result)
return result;
- if (iocb->ki_flags & IOCB_DIRECT)
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ result = generic_write_checks(iocb, from);
+ if (result <= 0)
+ return result;
return nfs_file_direct_write(iocb, from);
+ }
dprintk("NFS: write(%pD2, %zu@%Ld)\n",
file, iov_iter_count(from), (long long) iocb->ki_pos);
- if (IS_SWAPFILE(inode))
- goto out_swapfile;
/*
* O_APPEND implies that we must revalidate the file length.
*/
@@ -678,10 +680,6 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
out:
return result;
-
-out_swapfile:
- printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
- return -ETXTBSY;
}
EXPORT_SYMBOL_GPL(nfs_file_write);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index b9a8b925db43..4a8bd9e48237 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -493,7 +493,7 @@ static inline const struct cred *nfs_file_cred(struct file *file)
/*
* linux/fs/nfs/direct.c
*/
-extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *);
+extern ssize_t nfs_swap_rw(struct kiocb *, struct iov_iter *);
extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
struct iov_iter *iter);
extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
