prctl: PR_{G,S}ET_IO_FLUSHER to support controlling memory reclaim

There are several storage drivers like dm-multipath, iscsi, tcmu-runner,
amd nbd that have userspace components that can run in the IO path. For
example, iscsi and nbd's userspace deamons may need to recreate a socket
and/or send IO on it, and dm-multipath's daemon multipathd may need to
send SG IO or read/write IO to figure out the state of paths and re-set
them up.

In the kernel these drivers have access to GFP_NOIO/GFP_NOFS and the
memalloc_*_save/restore functions to control the allocation behavior,
but for userspace we would end up hitting an allocation that ended up
writing data back to the same device we are trying to allocate for.
The device is then in a state of deadlock, because to execute IO the
device needs to allocate memory, but to allocate memory the memory
layers want execute IO to the device.

Here is an example with nbd using a local userspace daemon that performs
network IO to a remote server. We are using XFS on top of the nbd device,
but it can happen with any FS or other modules layered on top of the nbd
device that can write out data to free memory.  Here a nbd daemon helper
thread, msgr-worker-1, is performing a write/sendmsg on a socket to execute
a request. This kicks off a reclaim operation which results in a WRITE to
the nbd device and the nbd thread calling back into the mm layer.

[ 1626.609191] msgr-worker-1   D    0  1026      1 0x00004000
[ 1626.609193] Call Trace:
[ 1626.609195]  ? __schedule+0x29b/0x630
[ 1626.609197]  ? wait_for_completion+0xe0/0x170
[ 1626.609198]  schedule+0x30/0xb0
[ 1626.609200]  schedule_timeout+0x1f6/0x2f0
[ 1626.609202]  ? blk_finish_plug+0x21/0x2e
[ 1626.609204]  ? _xfs_buf_ioapply+0x2e6/0x410
[ 1626.609206]  ? wait_for_completion+0xe0/0x170
[ 1626.609208]  wait_for_completion+0x108/0x170
[ 1626.609210]  ? wake_up_q+0x70/0x70
[ 1626.609212]  ? __xfs_buf_submit+0x12e/0x250
[ 1626.609214]  ? xfs_bwrite+0x25/0x60
[ 1626.609215]  xfs_buf_iowait+0x22/0xf0
[ 1626.609218]  __xfs_buf_submit+0x12e/0x250
[ 1626.609220]  xfs_bwrite+0x25/0x60
[ 1626.609222]  xfs_reclaim_inode+0x2e8/0x310
[ 1626.609224]  xfs_reclaim_inodes_ag+0x1b6/0x300
[ 1626.609227]  xfs_reclaim_inodes_nr+0x31/0x40
[ 1626.609228]  super_cache_scan+0x152/0x1a0
[ 1626.609231]  do_shrink_slab+0x12c/0x2d0
[ 1626.609233]  shrink_slab+0x9c/0x2a0
[ 1626.609235]  shrink_node+0xd7/0x470
[ 1626.609237]  do_try_to_free_pages+0xbf/0x380
[ 1626.609240]  try_to_free_pages+0xd9/0x1f0
[ 1626.609245]  __alloc_pages_slowpath+0x3a4/0xd30
[ 1626.609251]  ? ___slab_alloc+0x238/0x560
[ 1626.609254]  __alloc_pages_nodemask+0x30c/0x350
[ 1626.609259]  skb_page_frag_refill+0x97/0xd0
[ 1626.609274]  sk_page_frag_refill+0x1d/0x80
[ 1626.609279]  tcp_sendmsg_locked+0x2bb/0xdd0
[ 1626.609304]  tcp_sendmsg+0x27/0x40
[ 1626.609307]  sock_sendmsg+0x54/0x60
[ 1626.609308]  ___sys_sendmsg+0x29f/0x320
[ 1626.609313]  ? sock_poll+0x66/0xb0
[ 1626.609318]  ? ep_item_poll.isra.15+0x40/0xc0
[ 1626.609320]  ? ep_send_events_proc+0xe6/0x230
[ 1626.609322]  ? hrtimer_try_to_cancel+0x54/0xf0
[ 1626.609324]  ? ep_read_events_proc+0xc0/0xc0
[ 1626.609326]  ? _raw_write_unlock_irq+0xa/0x20
[ 1626.609327]  ? ep_scan_ready_list.constprop.19+0x218/0x230
[ 1626.609329]  ? __hrtimer_init+0xb0/0xb0
[ 1626.609331]  ? _raw_spin_unlock_irq+0xa/0x20
[ 1626.609334]  ? ep_poll+0x26c/0x4a0
[ 1626.609337]  ? tcp_tsq_write.part.54+0xa0/0xa0
[ 1626.609339]  ? release_sock+0x43/0x90
[ 1626.609341]  ? _raw_spin_unlock_bh+0xa/0x20
[ 1626.609342]  __sys_sendmsg+0x47/0x80
[ 1626.609347]  do_syscall_64+0x5f/0x1c0
[ 1626.609349]  ? prepare_exit_to_usermode+0x75/0xa0
[ 1626.609351]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

This patch adds a new prctl command that daemons can use after they have
done their initial setup, and before they start to do allocations that
are in the IO path. It sets the PF_MEMALLOC_NOIO and PF_LESS_THROTTLE
flags so both userspace block and FS threads can use it to avoid the
allocation recursion and try to prevent from being throttled while
writing out data to free up memory.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Tested-by: Masato Suzuki <masato.suzuki@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Link: https://lore.kernel.org/r/20191112001900.9206-1-mchristi@redhat.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

1 files changed, 25 insertions, 0 deletions

diff --git a/kernel/sys.c b/kernel/sys.c
index a9331f101883..f9bc5c303e3f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2261,6 +2261,8 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
 	return -EINVAL;
 }
 
+#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LESS_THROTTLE)
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -2488,6 +2490,29 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			return -EINVAL;
 		error = GET_TAGGED_ADDR_CTRL();
 		break;
+	case PR_SET_IO_FLUSHER:
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+
+		if (arg2 == 1)
+			current->flags |= PR_IO_FLUSHER;
+		else if (!arg2)
+			current->flags &= ~PR_IO_FLUSHER;
+		else
+			return -EINVAL;
+		break;
+	case PR_GET_IO_FLUSHER:
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+
+		error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER;
+		break;
 	default:
 		error = -EINVAL;
 		break;