NFS: swap IO handling is slightly different for O_DIRECT IO

[ Upstream commit 64158668ac8b31626a8ce48db4cad08496eb8340 ]

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>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 3c0335c..28afc31 100644 (file)
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -172,8 +172,8 @@ ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
        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);
+               return nfs_file_direct_read(iocb, iter, true);
+       return nfs_file_direct_write(iocb, iter, true);
 }
 
 static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
@@ -424,6 +424,7 @@ 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
@@ -439,7 +440,8 @@ 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;
@@ -481,12 +483,14 @@ 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);
@@ -875,6 +879,7 @@ 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
@@ -891,7 +896,8 @@ 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;
@@ -905,7 +911,11 @@ 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)
+               /* bypass generic checks */
+               result =  iov_iter_count(iter);
+       else
+               result = generic_write_checks(iocb, iter);
        if (result <= 0)
                return result;
        count = result;
@@ -936,16 +946,20 @@ 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) {
+               requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);
+       } else {
+               nfs_start_io_direct(inode);
 
-       requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);
+               requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);
 
-       if (mapping->nrpages) {
-               invalidate_inode_pages2_range(mapping,
-                                             pos >> PAGE_SHIFT, end);
-       }
+               if (mapping->nrpages) {
+                       invalidate_inode_pages2_range(mapping,
+                                                     pos >> PAGE_SHIFT, end);
+               }
 
-       nfs_end_io_direct(inode);
+               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 aa353fd..42a1699 100644 (file)
--- 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,
@@ -616,7 +616,7 @@ 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 4a733f1..41102e0 100644 (file)
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -494,10 +494,10 @@ 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_file_direct_read(struct kiocb *iocb,
-                       struct iov_iter *iter);
-extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
-                       struct iov_iter *iter);
+ssize_t nfs_file_direct_read(struct kiocb *iocb,
+                            struct iov_iter *iter, bool swap);
+ssize_t nfs_file_direct_write(struct kiocb *iocb,
+                             struct iov_iter *iter, bool swap);
 
 /*
  * linux/fs/nfs/dir.c