[PATCH AUTOSEL 4.19 25/73] nfs: don't dirty kernel pages read by direct-io

[PATCH AUTOSEL 4.19 25/73] nfs: don't dirty kernel pages read by direct-io

[Sasha Levin]

From: Dave Kleikamp <dave.kleikamp@oracle.com>

[ Upstream commit ad3cba223ac02dc769c3bbe88efe277bbb457566 ]

When we use direct_IO with an NFS backing store, we can trigger a
WARNING in __set_page_dirty(), as below, since we're dirtying the page
unnecessarily in nfs_direct_read_completion().

To fix, replicate the logic in commit 53cbf3b157a0 ("fs: direct-io:
don't dirtying pages for ITER_BVEC/ITER_KVEC direct read").

Other filesystems that implement direct_IO handle this; most use
blockdev_direct_IO(). ceph and cifs have similar logic.

mount 127.0.0.1:/export /nfs
dd if=/dev/zero of=/nfs/image bs=1M count=200
losetup --direct-io=on -f /nfs/image
mkfs.btrfs /dev/loop0
mount -t btrfs /dev/loop0 /mnt/

kernel: WARNING: CPU: 0 PID: 8067 at fs/buffer.c:580 __set_page_dirty+0xaf/0xd0
kernel: Modules linked in: loop(E) nfsv3(E) rpcsec_gss_krb5(E) nfsv4(E) dns_resolver(E) nfs(E) fscache(E) nfsd(E) auth_rpcgss(E) nfs_acl(E) lockd(E) grace(E) fuse(E) tun(E) ip6t_rpfilter(E) ipt_REJECT(E) nf_
kernel:  snd_seq(E) snd_seq_device(E) snd_pcm(E) video(E) snd_timer(E) snd(E) soundcore(E) ip_tables(E) xfs(E) libcrc32c(E) sd_mod(E) sr_mod(E) cdrom(E) ata_generic(E) pata_acpi(E) crc32c_intel(E) ahci(E) li
kernel: CPU: 0 PID: 8067 Comm: kworker/0:2 Tainted: G            E     4.20.0-rc1.master.20181111.ol7.x86_64 #1
kernel: Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
kernel: Workqueue: nfsiod rpc_async_release [sunrpc]
kernel: RIP: 0010:__set_page_dirty+0xaf/0xd0
kernel: Code: c3 48 8b 02 f6 c4 04 74 d4 48 89 df e8 ba 05 f7 ff 48 89 c6 eb cb 48 8b 43 08 a8 01 75 1f 48 89 d8 48 8b 00 a8 04 74 02 eb 87 <0f> 0b eb 83 48 83 e8 01 eb 9f 48 83 ea 01 0f 1f 00 eb 8b 48 83 e8
kernel: RSP: 0000:ffffc1c8825b7d78 EFLAGS: 00013046
kernel: RAX: 000fffffc0020089 RBX: fffff2b603308b80 RCX: 0000000000000001
kernel: RDX: 0000000000000001 RSI: ffff9d11478115c8 RDI: ffff9d11478115d0
kernel: RBP: ffffc1c8825b7da0 R08: 0000646f6973666e R09: 8080808080808080
kernel: R10: 0000000000000001 R11: 0000000000000000 R12: ffff9d11478115d0
kernel: R13: ffff9d11478115c8 R14: 0000000000003246 R15: 0000000000000001
kernel: FS:  0000000000000000(0000) GS:ffff9d115ba00000(0000) knlGS:0000000000000000
kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
kernel: CR2: 00007f408686f640 CR3: 0000000104d8e004 CR4: 00000000000606f0
kernel: DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
kernel: DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
kernel: Call Trace:
kernel:  __set_page_dirty_buffers+0xb6/0x110
kernel:  set_page_dirty+0x52/0xb0
kernel:  nfs_direct_read_completion+0xc4/0x120 [nfs]
kernel:  nfs_pgio_release+0x10/0x20 [nfs]
kernel:  rpc_free_task+0x30/0x70 [sunrpc]
kernel:  rpc_async_release+0x12/0x20 [sunrpc]
kernel:  process_one_work+0x174/0x390
kernel:  worker_thread+0x4f/0x3e0
kernel:  kthread+0x102/0x140
kernel:  ? drain_workqueue+0x130/0x130
kernel:  ? kthread_stop+0x110/0x110
kernel:  ret_from_fork+0x35/0x40
kernel: ---[ end trace 01341980905412c9 ]---

Signed-off-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>

[forward-ported to v4.20]
Signed-off-by: Calum Mackay <calum.mackay@oracle.com>
Reviewed-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfs/direct.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index aa12c3063bae..33824a0a57bf 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -98,8 +98,11 @@ struct nfs_direct_req {
 	struct pnfs_ds_commit_info ds_cinfo;	/* Storage for cinfo */
 	struct work_struct	work;
 	int			flags;
+	/* for write */
 #define NFS_ODIRECT_DO_COMMIT		(1)	/* an unstable reply was received */
 #define NFS_ODIRECT_RESCHED_WRITES	(2)	/* write verification failed */
+	/* for read */
+#define NFS_ODIRECT_SHOULD_DIRTY	(3)	/* dirty user-space page after read */
 	struct nfs_writeverf	verf;		/* unstable write verifier */
 };
 
@@ -412,7 +415,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 		struct page *page = req->wb_page;
 
-		if (!PageCompound(page) && bytes < hdr->good_bytes)
+		if (!PageCompound(page) && bytes < hdr->good_bytes &&
+		    (dreq->flags == NFS_ODIRECT_SHOULD_DIRTY))
 			set_page_dirty(page);
 		bytes += req->wb_bytes;
 		nfs_list_remove_request(req);
@@ -587,6 +591,9 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
+	if (iter_is_iovec(iter))
+		dreq->flags = NFS_ODIRECT_SHOULD_DIRTY;
+
 	nfs_start_io_direct(inode);
 
 	NFS_I(inode)->read_io += count;
-- 
2.19.1

[PATCH AUTOSEL 4.19 26/73] SUNRPC: Fix leak of krb5p encode pages

[Sasha Levin]

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit 8dae5398ab1ac107b1517e8195ed043d5f422bd0 ]

call_encode can be invoked more than once per RPC call. Ensure that
each call to gss_wrap_req_priv does not overwrite pointers to
previously allocated memory.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Cc: stable@kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/auth_gss/auth_gss.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 21c0aa0a0d1d..8cb7d812ccb8 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1768,6 +1768,7 @@ priv_release_snd_buf(struct rpc_rqst *rqstp)
 	for (i=0; i < rqstp->rq_enc_pages_num; i++)
 		__free_page(rqstp->rq_enc_pages[i]);
 	kfree(rqstp->rq_enc_pages);
+	rqstp->rq_release_snd_buf = NULL;
 }
 
 static int
@@ -1776,6 +1777,9 @@ alloc_enc_pages(struct rpc_rqst *rqstp)
 	struct xdr_buf *snd_buf = &rqstp->rq_snd_buf;
 	int first, last, i;
 
+	if (rqstp->rq_release_snd_buf)
+		rqstp->rq_release_snd_buf(rqstp);
+
 	if (snd_buf->page_len == 0) {
 		rqstp->rq_enc_pages_num = 0;
 		return 0;
-- 
2.19.1

[PATCH AUTOSEL 4.19 27/73] SUNRPC: Fix a potential race in xprt_connect()

[Sasha Levin]

From: Trond Myklebust <trond.myklebust@hammerspace.com>

[ Upstream commit 0a9a4304f3614e25d9de9b63502ca633c01c0d70 ]

If an asynchronous connection attempt completes while another task is
in xprt_connect(), then the call to rpc_sleep_on() could end up
racing with the call to xprt_wake_pending_tasks().
So add a second test of the connection state after we've put the
task to sleep and set the XPRT_CONNECTING flag, when we know that there
can be no asynchronous connection attempts still in progress.

Fixes: 0b9e79431377d ("SUNRPC: Move the test for XPRT_CONNECTING into...")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/xprt.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index a8db2e3f8904..d066aae3cb6d 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -781,8 +781,15 @@ void xprt_connect(struct rpc_task *task)
 			return;
 		if (xprt_test_and_set_connecting(xprt))
 			return;
-		xprt->stat.connect_start = jiffies;
-		xprt->ops->connect(xprt, task);
+		/* Race breaker */
+		if (!xprt_connected(xprt)) {
+			xprt->stat.connect_start = jiffies;
+			xprt->ops->connect(xprt, task);
+		} else {
+			xprt_clear_connecting(xprt);
+			task->tk_status = 0;
+			rpc_wake_up_queued_task(&xprt->pending, task);
+		}
 	}
 	xprt_release_write(xprt, task);
 }
-- 
2.19.1