lkml.org 
[lkml]   [2021]   [Dec]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Subject[PATCH 10/18] NFS: swap IO handling is slightly different for O_DIRECT IO
From
Date
1/ Taking the i_rwsem for swap IO triggers lockdep warnings regarding
possible deadlocks with "fs_reclaim". These deadlocks could, I believe,
eventuate if a buffered read on the swapfile was attempted.

We don't need coherence with the page cache for a swap file, and
buffered writes are forbidden anyway. There is no other need for
i_rwsem during direct IO. So never take it for swap_rw()

2/ generic_write_checks() explicitly forbids writes to swap, and
performs checks that are not needed for swap. So bypass it
for swap_rw().

Signed-off-by: NeilBrown <neilb@suse.de>
---
fs/nfs/direct.c | 30 +++++++++++++++++++++---------
fs/nfs/file.c | 4 ++--
include/linux/nfs_fs.h | 4 ++--
3 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index f1e169f3050a..eeff1b4e1a7c 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -165,9 +165,9 @@ int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter)
VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);

if (iov_iter_rw(iter) == READ)
- ret = nfs_file_direct_read(iocb, iter);
+ ret = nfs_file_direct_read(iocb, iter, true);
else
- ret = nfs_file_direct_write(iocb, iter);
+ ret = nfs_file_direct_write(iocb, iter, true);
if (ret < 0)
return ret;
return 0;
@@ -421,6 +421,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
* nfs_file_direct_read - file direct read operation for NFS files
* @iocb: target I/O control block
* @iter: vector of user buffers into which to read data
+ * @swap: flag indicating this is swap IO, not O_DIRECT IO
*
* We use this function for direct reads instead of calling
* generic_file_aio_read() in order to avoid gfar's check to see if
@@ -436,7 +437,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
* client must read the updated atime from the server back into its
* cache.
*/
-ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
+ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
+ bool swap)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -478,12 +480,14 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
if (iter_is_iovec(iter))
dreq->flags = NFS_ODIRECT_SHOULD_DIRTY;

- nfs_start_io_direct(inode);
+ if (!swap)
+ nfs_start_io_direct(inode);

NFS_I(inode)->read_io += count;
requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);

- nfs_end_io_direct(inode);
+ if (!swap)
+ nfs_end_io_direct(inode);

if (requested > 0) {
result = nfs_direct_wait(dreq);
@@ -872,6 +876,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
* nfs_file_direct_write - file direct write operation for NFS files
* @iocb: target I/O control block
* @iter: vector of user buffers from which to write data
+ * @swap: flag indicating this is swap IO, not O_DIRECT IO
*
* We use this function for direct writes instead of calling
* generic_file_aio_write() in order to avoid taking the inode
@@ -888,7 +893,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
* Note that O_APPEND is not supported for NFS direct writes, as there
* is no atomic O_APPEND write facility in the NFS protocol.
*/
-ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
+ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
+ bool swap)
{
ssize_t result, requested;
size_t count;
@@ -902,7 +908,11 @@ 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 (!swap)
+ result = generic_write_checks(iocb, iter);
+ else
+ /* bypass generic checks */
+ result = iov_iter_count(iter);
if (result <= 0)
return result;
count = result;
@@ -933,7 +943,8 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
dreq->iocb = iocb;
pnfs_init_ds_commit_info_ops(&dreq->ds_cinfo, inode);

- nfs_start_io_direct(inode);
+ if (!swap)
+ nfs_start_io_direct(inode);

requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);

@@ -942,7 +953,8 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
pos >> PAGE_SHIFT, end);
}

- nfs_end_io_direct(inode);
+ if (!swap)
+ nfs_end_io_direct(inode);

if (requested > 0) {
result = nfs_direct_wait(dreq);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index b620fe697158..996dfb3c74b2 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -161,7 +161,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
ssize_t result;

if (iocb->ki_flags & IOCB_DIRECT)
- return nfs_file_direct_read(iocb, to);
+ return nfs_file_direct_read(iocb, to, false);

dprintk("NFS: read(%pD2, %zu@%lu)\n",
iocb->ki_filp,
@@ -625,7 +625,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
return result;

if (iocb->ki_flags & IOCB_DIRECT)
- return nfs_file_direct_write(iocb, from);
+ return nfs_file_direct_write(iocb, from, false);

dprintk("NFS: write(%pD2, %zu@%Ld)\n",
file, iov_iter_count(from), (long long) iocb->ki_pos);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 6329e6958718..3a210478f665 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -512,9 +512,9 @@ static inline const struct cred *nfs_file_cred(struct file *file)
*/
extern int nfs_swap_rw(struct kiocb *, struct iov_iter *);
extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
- struct iov_iter *iter);
+ struct iov_iter *iter, bool swap);
extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
- struct iov_iter *iter);
+ struct iov_iter *iter, bool swap);

/*
* linux/fs/nfs/dir.c

\
 
 \ /
  Last update: 2021-12-17 00:54    [W:0.233 / U:0.980 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site