summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorBenjamin Coddington <bcodding@redhat.com>2022-12-16 15:45:27 +0300
committerJakub Kicinski <kuba@kernel.org>2022-12-20 04:28:49 +0300
commit98123866fcf3fe95a0c1b198ef122dfdbd351916 (patch)
treebe2cbfb90c15868dfd2f3b29216109733055299b /drivers
parentfb87bd47516d9a26b6d549231aa743b20fd4a569 (diff)
downloadlinux-98123866fcf3fe95a0c1b198ef122dfdbd351916.tar.xz
Treewide: Stop corrupting socket's task_frag
Since moving to memalloc_nofs_save/restore, SUNRPC has stopped setting the GFP_NOIO flag on sk_allocation which the networking system uses to decide when it is safe to use current->task_frag. The results of this are unexpected corruption in task_frag when SUNRPC is involved in memory reclaim. The corruption can be seen in crashes, but the root cause is often difficult to ascertain as a crashing machine's stack trace will have no evidence of being near NFS or SUNRPC code. I believe this problem to be much more pervasive than reports to the community may indicate. Fix this by having kernel users of sockets that may corrupt task_frag due to reclaim set sk_use_task_frag = false. Preemptively correcting this situation for users that still set sk_allocation allows them to convert to memalloc_nofs_save/restore without the same unexpected corruptions that are sure to follow, unlikely to show up in testing, and difficult to bisect. CC: Philipp Reisner <philipp.reisner@linbit.com> CC: Lars Ellenberg <lars.ellenberg@linbit.com> CC: "Christoph Böhmwalder" <christoph.boehmwalder@linbit.com> CC: Jens Axboe <axboe@kernel.dk> CC: Josef Bacik <josef@toxicpanda.com> CC: Keith Busch <kbusch@kernel.org> CC: Christoph Hellwig <hch@lst.de> CC: Sagi Grimberg <sagi@grimberg.me> CC: Lee Duncan <lduncan@suse.com> CC: Chris Leech <cleech@redhat.com> CC: Mike Christie <michael.christie@oracle.com> CC: "James E.J. Bottomley" <jejb@linux.ibm.com> CC: "Martin K. Petersen" <martin.petersen@oracle.com> CC: Valentina Manea <valentina.manea.m@gmail.com> CC: Shuah Khan <shuah@kernel.org> CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org> CC: David Howells <dhowells@redhat.com> CC: Marc Dionne <marc.dionne@auristor.com> CC: Steve French <sfrench@samba.org> CC: Christine Caulfield <ccaulfie@redhat.com> CC: David Teigland <teigland@redhat.com> CC: Mark Fasheh <mark@fasheh.com> CC: Joel Becker <jlbec@evilplan.org> CC: Joseph Qi <joseph.qi@linux.alibaba.com> CC: Eric Van Hensbergen <ericvh@gmail.com> CC: Latchesar Ionkov <lucho@ionkov.net> CC: Dominique Martinet <asmadeus@codewreck.org> CC: Ilya Dryomov <idryomov@gmail.com> CC: Xiubo Li <xiubli@redhat.com> CC: Chuck Lever <chuck.lever@oracle.com> CC: Jeff Layton <jlayton@kernel.org> CC: Trond Myklebust <trond.myklebust@hammerspace.com> CC: Anna Schumaker <anna@kernel.org> CC: Steffen Klassert <steffen.klassert@secunet.com> CC: Herbert Xu <herbert@gondor.apana.org.au> Suggested-by: Guillaume Nault <gnault@redhat.com> Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Reviewed-by: Guillaume Nault <gnault@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/block/drbd/drbd_receiver.c3
-rw-r--r--drivers/block/nbd.c1
-rw-r--r--drivers/nvme/host/tcp.c1
-rw-r--r--drivers/scsi/iscsi_tcp.c1
-rw-r--r--drivers/usb/usbip/usbip_common.c1
5 files changed, 7 insertions, 0 deletions
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 0e58a3187345..757f4692b5bd 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1030,6 +1030,9 @@ randomize:
sock.socket->sk->sk_allocation = GFP_NOIO;
msock.socket->sk->sk_allocation = GFP_NOIO;
+ sock.socket->sk->sk_use_task_frag = false;
+ msock.socket->sk->sk_use_task_frag = false;
+
sock.socket->sk->sk_priority = TC_PRIO_INTERACTIVE_BULK;
msock.socket->sk->sk_priority = TC_PRIO_INTERACTIVE;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index e379ccc63c52..592cfa8b765a 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -512,6 +512,7 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
noreclaim_flag = memalloc_noreclaim_save();
do {
sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
+ sock->sk->sk_use_task_frag = false;
msg.msg_name = NULL;
msg.msg_namelen = 0;
msg.msg_control = NULL;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index b69b89166b6b..8cedc1ef496c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1537,6 +1537,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid)
queue->sock->sk->sk_rcvtimeo = 10 * HZ;
queue->sock->sk->sk_allocation = GFP_ATOMIC;
+ queue->sock->sk->sk_use_task_frag = false;
nvme_tcp_set_queue_io_cpu(queue);
queue->request = NULL;
queue->data_remaining = 0;
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 5fb1f364e815..1d1cf641937c 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -738,6 +738,7 @@ iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session,
sk->sk_reuse = SK_CAN_REUSE;
sk->sk_sndtimeo = 15 * HZ; /* FIXME: make it configurable */
sk->sk_allocation = GFP_ATOMIC;
+ sk->sk_use_task_frag = false;
sk_set_memalloc(sk);
sock_no_linger(sk);
diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
index f8b326eed54d..a2b2da1255dd 100644
--- a/drivers/usb/usbip/usbip_common.c
+++ b/drivers/usb/usbip/usbip_common.c
@@ -315,6 +315,7 @@ int usbip_recv(struct socket *sock, void *buf, int size)
do {
sock->sk->sk_allocation = GFP_NOIO;
+ sock->sk->sk_use_task_frag = false;
result = sock_recvmsg(sock, &msg, MSG_WAITALL);
if (result <= 0)