[dpdk-stable] patch 'vhost: protect active rings from async ring changes' has been queued to LTS release 17.11.1

[Yuanhan Liu]

Hi,

FYI, your patch has been queued to LTS release 17.11.1

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 01/26/18. So please
shout if anyone has objections.

Thanks.

	--yliu

---
>From b45011203c45861834237dd9103047d3b3009348 Mon Sep 17 00:00:00 2001
From: Victor Kaplansky <victork at redhat.com>
Date: Wed, 17 Jan 2018 15:49:25 +0200
Subject: [PATCH] vhost: protect active rings from async ring changes

[ upstream commit a3688046995f88c518fa27c45b39ae389260b18d ]

When performing live migration or memory hot-plugging,
the changes to the device and vrings made by message handler
done independently from vring usage by PMD threads.

This causes for example segfaults during live-migration
with MQ enable, but in general virtually any request
sent by qemu changing the state of device can cause
problems.

These patches fixes all above issues by adding a spinlock
to every vring and requiring message handler to start operation
only after ensuring that all PMD threads related to the device
are out of critical section accessing the vring data.

Each vring has its own lock in order to not create contention
between PMD threads of different vrings and to prevent
performance degradation by scaling queue pair number.

See https://bugzilla.redhat.com/show_bug.cgi?id=1450680

Signed-off-by: Victor Kaplansky <victork at redhat.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin at redhat.com>
Acked-by: Yuanhan Liu <yliu at fridaylinux.org>
---
 lib/librte_vhost/vhost.c      |  1 +
 lib/librte_vhost/vhost.h      |  6 ++--
 lib/librte_vhost/vhost_user.c | 70 +++++++++++++++++++++++++++++++++++++++++++
 lib/librte_vhost/virtio_net.c | 26 ++++++++++++++--
 4 files changed, 98 insertions(+), 5 deletions(-)

diff --git a/lib/librte_vhost/vhost.c b/lib/librte_vhost/vhost.c
index 4f8b73a..dcc42fc 100644
--- a/lib/librte_vhost/vhost.c
+++ b/lib/librte_vhost/vhost.c
@@ -259,6 +259,7 @@ alloc_vring_queue(struct virtio_net *dev, uint32_t vring_idx)
 
 	dev->virtqueue[vring_idx] = vq;
 	init_vring_queue(dev, vring_idx);
+	rte_spinlock_init(&vq->access_lock);
 
 	dev->nr_vring += 1;
 
diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index 1cc81c1..c8f2a81 100644
--- a/lib/librte_vhost/vhost.h
+++ b/lib/librte_vhost/vhost.h
@@ -108,12 +108,14 @@ struct vhost_virtqueue {
 
 	/* Backend value to determine if device should started/stopped */
 	int			backend;
+	int			enabled;
+	int			access_ok;
+	rte_spinlock_t		access_lock;
+
 	/* Used to notify the guest (trigger interrupt) */
 	int			callfd;
 	/* Currently unused as polling mode is enabled */
 	int			kickfd;
-	int			enabled;
-	int			access_ok;
 
 	/* Physical address of used ring, for logging */
 	uint64_t		log_guest_addr;
diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index 6f3869c..3acaacf 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -1224,12 +1224,47 @@ vhost_user_check_and_alloc_queue_pair(struct virtio_net *dev, VhostUserMsg *msg)
 	return alloc_vring_queue(dev, vring_idx);
 }
 
+static void
+vhost_user_lock_all_queue_pairs(struct virtio_net *dev)
+{
+	unsigned int i = 0;
+	unsigned int vq_num = 0;
+
+	while (vq_num < dev->nr_vring) {
+		struct vhost_virtqueue *vq = dev->virtqueue[i];
+
+		if (vq) {
+			rte_spinlock_lock(&vq->access_lock);
+			vq_num++;
+		}
+		i++;
+	}
+}
+
+static void
+vhost_user_unlock_all_queue_pairs(struct virtio_net *dev)
+{
+	unsigned int i = 0;
+	unsigned int vq_num = 0;
+
+	while (vq_num < dev->nr_vring) {
+		struct vhost_virtqueue *vq = dev->virtqueue[i];
+
+		if (vq) {
+			rte_spinlock_unlock(&vq->access_lock);
+			vq_num++;
+		}
+		i++;
+	}
+}
+
 int
 vhost_user_msg_handler(int vid, int fd)
 {
 	struct virtio_net *dev;
 	struct VhostUserMsg msg;
 	int ret;
+	int unlock_required = 0;
 
 	dev = get_device(vid);
 	if (dev == NULL)
@@ -1275,6 +1310,38 @@ vhost_user_msg_handler(int vid, int fd)
 		return -1;
 	}
 
+	/*
+	 * Note: we don't lock all queues on VHOST_USER_GET_VRING_BASE,
+	 * since it is sent when virtio stops and device is destroyed.
+	 * destroy_device waits for queues to be inactive, so it is safe.
+	 * Otherwise taking the access_lock would cause a dead lock.
+	 */
+	switch (msg.request.master) {
+	case VHOST_USER_SET_FEATURES:
+	case VHOST_USER_SET_PROTOCOL_FEATURES:
+	case VHOST_USER_SET_OWNER:
+	case VHOST_USER_RESET_OWNER:
+	case VHOST_USER_SET_MEM_TABLE:
+	case VHOST_USER_SET_LOG_BASE:
+	case VHOST_USER_SET_LOG_FD:
+	case VHOST_USER_SET_VRING_NUM:
+	case VHOST_USER_SET_VRING_ADDR:
+	case VHOST_USER_SET_VRING_BASE:
+	case VHOST_USER_SET_VRING_KICK:
+	case VHOST_USER_SET_VRING_CALL:
+	case VHOST_USER_SET_VRING_ERR:
+	case VHOST_USER_SET_VRING_ENABLE:
+	case VHOST_USER_SEND_RARP:
+	case VHOST_USER_NET_SET_MTU:
+	case VHOST_USER_SET_SLAVE_REQ_FD:
+		vhost_user_lock_all_queue_pairs(dev);
+		unlock_required = 1;
+		break;
+	default:
+		break;
+
+	}
+
 	switch (msg.request.master) {
 	case VHOST_USER_GET_FEATURES:
 		msg.payload.u64 = vhost_user_get_features(dev);
@@ -1376,6 +1443,9 @@ vhost_user_msg_handler(int vid, int fd)
 
 	}
 
+	if (unlock_required)
+		vhost_user_unlock_all_queue_pairs(dev);
+
 	if (msg.flags & VHOST_USER_NEED_REPLY) {
 		msg.payload.u64 = !!ret;
 		msg.size = sizeof(msg.payload.u64);
diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index 17158c1..d347030 100644
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -44,6 +44,7 @@
 #include <rte_udp.h>
 #include <rte_sctp.h>
 #include <rte_arp.h>
+#include <rte_spinlock.h>
 
 #include "iotlb.h"
 #include "vhost.h"
@@ -326,8 +327,11 @@ virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id,
 	}
 
 	vq = dev->virtqueue[queue_id];
+
+	rte_spinlock_lock(&vq->access_lock);
+
 	if (unlikely(vq->enabled == 0))
-		return 0;
+		goto out_access_unlock;
 
 	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
 		vhost_user_iotlb_rd_lock(vq);
@@ -419,6 +423,9 @@ out:
 	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
 		vhost_user_iotlb_rd_unlock(vq);
 
+out_access_unlock:
+	rte_spinlock_unlock(&vq->access_lock);
+
 	return count;
 }
 
@@ -651,8 +658,11 @@ virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id,
 	}
 
 	vq = dev->virtqueue[queue_id];
+
+	rte_spinlock_lock(&vq->access_lock);
+
 	if (unlikely(vq->enabled == 0))
-		return 0;
+		goto out_access_unlock;
 
 	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
 		vhost_user_iotlb_rd_lock(vq);
@@ -715,6 +725,9 @@ out:
 	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
 		vhost_user_iotlb_rd_unlock(vq);
 
+out_access_unlock:
+	rte_spinlock_unlock(&vq->access_lock);
+
 	return pkt_idx;
 }
 
@@ -1197,9 +1210,13 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
 	}
 
 	vq = dev->virtqueue[queue_id];
-	if (unlikely(vq->enabled == 0))
+
+	if (unlikely(rte_spinlock_trylock(&vq->access_lock) == 0))
 		return 0;
 
+	if (unlikely(vq->enabled == 0))
+		goto out_access_unlock;
+
 	vq->batch_copy_nb_elems = 0;
 
 	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
@@ -1374,6 +1391,9 @@ out:
 	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
 		vhost_user_iotlb_rd_unlock(vq);
 
+out_access_unlock:
+	rte_spinlock_unlock(&vq->access_lock);
+
 	if (unlikely(rarp_mbuf != NULL)) {
 		/*
 		 * Inject it to the head of "pkts" array, so that switch's mac
-- 
2.7.4