Skip to contentSkip to conversation

Fix CVE-2019-3900 in stable v4.14

PATCH In review Balbir Singh 2 participants 9 messages Jul 3, 2019 – Jul 5, 2019

Subsystems (4)
lore
Share & tools
lore
#0 lore raw

cover Fix CVE-2019-3900 in stable v4.14

These series of patches are required to fix the specified CVE in v4.14. I've tested these patches with a VM running vhost. Jason Wang who originally wrote the patches, helped identify other patches to backport and also tested this version and provided feedback on the patches.

Jason Wang (5):
vhost_net: introduce vhost_exceeds_weight()
vhost: introduce vhost_exceeds_weight()
vhost_net: fix possible infinite loop
vhost: vsock: add weight support
vhost: scsi: add weight support

Paolo Abeni (1):
vhost_net: use packet weight for rx handler, too

haibinzhang(张海斌) (1):
vhost-net: set packet weight of tx polling to 2 * vq size

 drivers/vhost/net.c   | 33 +++++++++++++++++++--------------
 drivers/vhost/scsi.c  | 14 ++++++++++----
 drivers/vhost/vhost.c | 20 +++++++++++++++++++-
 drivers/vhost/vhost.h |  6 +++++-
 drivers/vhost/vsock.c | 27 ++++++++++++++++++++-------
 5 files changed, 73 insertions(+), 27 deletions(-)
Signature · 1 line
2.16.5
#1 lore raw

PATCH 1/7 vhost-net: set packet weight of tx polling to 2 * vq size

From: haibinzhang(张海斌) <[email protected]>

handle_tx will delay rx for tens or even hundreds of milliseconds when tx busy polling udp packets with small length(e.g. 1byte udp payload), because setting VHOST_NET_WEIGHT takes into account only sent-bytes but no single packet length.

Ping-Latencies shown below were tested between two Virtual Machines using netperf (UDP_STREAM, len=1), and then another machine pinged the client:

vq size=256
Packet-Weight Ping-Latencies(millisecond)
min avg max

Origin           3.319   18.489    57.303
64               1.643    2.021     2.552
128              1.825    2.600     3.224
256              1.997    2.710     4.295
512              1.860    3.171     4.631
1024             2.002    4.173     9.056
2048             2.257    5.650     9.688
4096             2.093    8.508    15.943

vq size=512
Packet-Weight Ping-Latencies(millisecond)
min avg max

Origin           6.537   29.177    66.245
64               2.798    3.614     4.403
128              2.861    3.820     4.775
256              3.008    4.018     4.807
512              3.254    4.523     5.824
1024             3.079    5.335     7.747
2048             3.944    8.201    12.762
4096             4.158   11.057    19.985

Seems pretty consistent, a small dip at 2 VQ sizes.
Ring size is a hint from device about a burst size it can tolerate. Based on benchmarks, set the weight to 2 * vq size.

To evaluate this change, another tests were done using netperf(RR, TX) between two machines with Intel(R) Xeon(R) Gold 6133 CPU @ 2.50GHz, and vq size was tweaked through qemu. Results shown below does not show obvious changes.

vq size=256 TCP_RR vq size=512 TCP_RR
size/sessions/+thu%/+normalize% size/sessions/+thu%/+normalize%

   1/       1/  -7%/        -2%      1/       1/   0%/        -2%
   1/       4/  +1%/         0%      1/       4/  +1%/         0%
   1/       8/  +1%/        -2%      1/       8/   0%/        +1%
  64/       1/  -6%/         0%     64/       1/  +7%/        +3%
  64/       4/   0%/        +2%     64/       4/  -1%/        +1%
  64/       8/   0%/         0%     64/       8/  -1%/        -2%
 256/       1/  -3%/        -4%    256/       1/  -4%/        -2%
 256/       4/  +3%/        +4%    256/       4/  +1%/        +2%
 256/       8/  +2%/         0%    256/       8/  +1%/        -1%

vq size=256 UDP_RR vq size=512 UDP_RR
size/sessions/+thu%/+normalize% size/sessions/+thu%/+normalize%

   1/       1/  -5%/        +1%      1/       1/  -3%/        -2%
   1/       4/  +4%/        +1%      1/       4/  -2%/        +2%
   1/       8/  -1%/        -1%      1/       8/  -1%/         0%
  64/       1/  -2%/        -3%     64/       1/  +1%/        +1%
  64/       4/  -5%/        -1%     64/       4/  +2%/         0%
  64/       8/   0%/        -1%     64/       8/  -2%/        +1%
 256/       1/  +7%/        +1%    256/       1/  -7%/         0%
 256/       4/  +1%/        +1%    256/       4/  -3%/        -4%
 256/       8/  +2%/        +2%    256/       8/  +1%/        +1%

vq size=256 TCP_STREAM vq size=512 TCP_STREAM
size/sessions/+thu%/+normalize% size/sessions/+thu%/+normalize%

  64/       1/   0%/        -3%     64/       1/   0%/         0%
  64/       4/  +3%/        -1%     64/       4/  -2%/        +4%
  64/       8/  +9%/        -4%     64/       8/  -1%/        +2%
 256/       1/  +1%/        -4%    256/       1/  +1%/        +1%
 256/       4/  -1%/        -1%    256/       4/  -3%/         0%
 256/       8/  +7%/        +5%    256/       8/  -3%/         0%
 512/       1/  +1%/         0%    512/       1/  -1%/        -1%
 512/       4/  +1%/        -1%    512/       4/   0%/         0%
 512/       8/  +7%/        -5%    512/       8/  +6%/        -1%
1024/       1/   0%/        -1%   1024/       1/   0%/        +1%
1024/       4/  +3%/         0%   1024/       4/  +1%/         0%
1024/       8/  +8%/        +5%   1024/       8/  -1%/         0%
2048/       1/  +2%/        +2%   2048/       1/  -1%/         0%
2048/       4/  +1%/         0%   2048/       4/   0%/        -1%
2048/       8/  -2%/         0%   2048/       8/   5%/        -1%
4096/       1/  -2%/         0%   4096/       1/  -2%/         0%
4096/       4/  +2%/         0%   4096/       4/   0%/         0%
4096/       8/  +9%/        -2%   4096/       8/  -5%/        -1%
---
 drivers/vhost/net.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)
drivers/vhost/net.c +7 -1
index 4eba9ee179e3..a60fcf07f86c 100644
@@ -44,6 +44,10 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
  * Using this limit prevents one virtqueue from starving others. */
 #define VHOST_NET_WEIGHT 0x80000
 
+/* Max number of packets transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving rx. */
+#define VHOST_NET_PKT_WEIGHT(vq) ((vq)->num * 2)
+
 /* MAX number of TX used buffers for outstanding zerocopy */
 #define VHOST_MAX_PEND 128
 #define VHOST_GOODCOPY_LEN 256
@@ -461,6 +465,7 @@ static void handle_tx(struct vhost_net *net)
 	struct socket *sock;
 	struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
 	bool zcopy, zcopy_used;
+	int sent_pkts = 0;
 
 	mutex_lock(&vq->mutex);
 	sock = vq->private_data;
@@ -572,7 +577,8 @@ static void handle_tx(struct vhost_net *net)
 		else
 			vhost_zerocopy_signal_used(net, vq);
 		vhost_net_tx_packet(net);
-		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
+		if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
+		    unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT(vq))) {
 			vhost_poll_queue(&vq->poll);
 			break;
 		}
Signature · 1 line
2.16.5
#2 lore raw

PATCH 2/7 vhost_net: use packet weight for rx handler, too

In reply to Balbir Singh

From: Paolo Abeni <[email protected]>

Similar to commit a2ac99905f1e ("vhost-net: set packet weight of tx polling to 2 * vq size"), we need a packet-based limit for handler_rx, too - elsewhere, under rx flood with small packets, tx can be delayed for a very long time, even without busypolling.

The pkt limit applied to handle_rx must be the same applied by handle_tx, or we will get unfair scheduling between rx and tx. Tying such limit to the queue length makes it less effective for large queue length values and can introduce large process scheduler latencies, so a constant valued is used - likewise the existing bytes limit.

The selected limit has been validated with PVP[1] performance test with different queue sizes:

queue size 256 512 1024

baseline 366 354 362
weight 128 715 723 670
weight 256 740 745 733
weight 512 600 460 583
weight 1024 423 427 418

A packet weight of 256 gives peek performances in under all the tested scenarios.

No measurable regression in unidirectional performance tests has been detected.

[1] https://developers.redhat.com/blog/2017/06/05/measuring-and-comparing-open-vswitch-performance/

[upstream - db688c24eada63b1efe6d0d7d835e5c3bdd71fd3]
---
 drivers/vhost/net.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)
drivers/vhost/net.c +8 -4
index a60fcf07f86c..9fcf7bf25249 100644
@@ -45,8 +45,10 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
 #define VHOST_NET_WEIGHT 0x80000
 
 /* Max number of packets transferred before requeueing the job.
- * Using this limit prevents one virtqueue from starving rx. */
-#define VHOST_NET_PKT_WEIGHT(vq) ((vq)->num * 2)
+ * Using this limit prevents one virtqueue from starving others with small
+ * pkts.
+ */
+#define VHOST_NET_PKT_WEIGHT 256
 
 /* MAX number of TX used buffers for outstanding zerocopy */
 #define VHOST_MAX_PEND 128
@@ -578,7 +580,7 @@ static void handle_tx(struct vhost_net *net)
 			vhost_zerocopy_signal_used(net, vq);
 		vhost_net_tx_packet(net);
 		if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
-		    unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT(vq))) {
+		    unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT)) {
 			vhost_poll_queue(&vq->poll);
 			break;
 		}
@@ -760,6 +762,7 @@ static void handle_rx(struct vhost_net *net)
 	struct socket *sock;
 	struct iov_iter fixup;
 	__virtio16 num_buffers;
+	int recv_pkts = 0;
 
 	mutex_lock_nested(&vq->mutex, 0);
 	sock = vq->private_data;
@@ -860,7 +863,8 @@ static void handle_rx(struct vhost_net *net)
 			vhost_log_write(vq, vq_log, log, vhost_len,
 					vq->iov, in);
 		total_len += vhost_len;
-		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
+		if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
+		    unlikely(++recv_pkts >= VHOST_NET_PKT_WEIGHT)) {
 			vhost_poll_queue(&vq->poll);
 			goto out;
 		}
Signature · 1 line
2.16.5
#3 lore raw

PATCH 3/7 vhost_net: introduce vhost_exceeds_weight()

In reply to Balbir Singh

From: Jason Wang <[email protected]>

[upstream - 272f35cba53d088085e5952fd81d7a133ab90789 Balbir - Backport to stable 4.14]

---
 drivers/vhost/net.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)
drivers/vhost/net.c +8 -5
index 9fcf7bf25249..81b9c908ca56 100644
@@ -446,6 +446,12 @@ static bool vhost_exceeds_maxpend(struct vhost_net *net)
 		== nvq->done_idx;
 }
 
+static bool vhost_exceeds_weight(int pkts, int total_len)
+{
+	return total_len >= VHOST_NET_WEIGHT ||
+	       pkts >= VHOST_NET_PKT_WEIGHT;
+}
+
 /* Expects to be always run from workqueue - which acts as
  * read-size critical section for our kind of RCU. */
 static void handle_tx(struct vhost_net *net)
@@ -550,7 +556,6 @@ static void handle_tx(struct vhost_net *net)
 			msg.msg_control = NULL;
 			ubufs = NULL;
 		}
-
 		total_len += len;
 		if (total_len < VHOST_NET_WEIGHT &&
 		    !vhost_vq_avail_empty(&net->dev, vq) &&
@@ -579,8 +584,7 @@ static void handle_tx(struct vhost_net *net)
 		else
 			vhost_zerocopy_signal_used(net, vq);
 		vhost_net_tx_packet(net);
-		if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
-		    unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT)) {
+		if (unlikely(vhost_exceeds_weight(++sent_pkts, total_len))) {
 			vhost_poll_queue(&vq->poll);
 			break;
 		}
@@ -863,8 +867,7 @@ static void handle_rx(struct vhost_net *net)
 			vhost_log_write(vq, vq_log, log, vhost_len,
 					vq->iov, in);
 		total_len += vhost_len;
-		if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
-		    unlikely(++recv_pkts >= VHOST_NET_PKT_WEIGHT)) {
+		if (unlikely(vhost_exceeds_weight(++recv_pkts, total_len))) {
 			vhost_poll_queue(&vq->poll);
 			goto out;
 		}
Signature · 1 line
2.16.5
#4 lore raw

PATCH 4/7 vhost: introduce vhost_exceeds_weight()

In reply to Balbir Singh

From: Jason Wang <[email protected]>

We used to have vhost_exceeds_weight() for vhost-net to:

- prevent vhost kthread from hogging the cpu
- balance the time spent between TX and RX

This function could be useful for vsock and scsi as well. So move it to vhost.c. Device must specify a weight which counts the number of requests, or it can also specific a byte_weight which counts the number of bytes that has been processed.

[upstream e82b9b0727ff6d665fff2d326162b460dded554d Balbir - backport to stable 4.14]

---
 drivers/vhost/net.c   | 18 +++++-------------
 drivers/vhost/scsi.c  |  8 +++++++-
 drivers/vhost/vhost.c | 20 +++++++++++++++++++-
 drivers/vhost/vhost.h |  6 +++++-
 drivers/vhost/vsock.c | 11 ++++++++++-
 5 files changed, 46 insertions(+), 17 deletions(-)
drivers/vhost/net.c +5 -13
index 81b9c908ca56..a4ca0346da3e 100644
@@ -446,12 +446,6 @@ static bool vhost_exceeds_maxpend(struct vhost_net *net)
 		== nvq->done_idx;
 }
 
-static bool vhost_exceeds_weight(int pkts, int total_len)
-{
-	return total_len >= VHOST_NET_WEIGHT ||
-	       pkts >= VHOST_NET_PKT_WEIGHT;
-}
-
 /* Expects to be always run from workqueue - which acts as
  * read-size critical section for our kind of RCU. */
 static void handle_tx(struct vhost_net *net)
@@ -584,10 +578,9 @@ static void handle_tx(struct vhost_net *net)
 		else
 			vhost_zerocopy_signal_used(net, vq);
 		vhost_net_tx_packet(net);
-		if (unlikely(vhost_exceeds_weight(++sent_pkts, total_len))) {
-			vhost_poll_queue(&vq->poll);
+		if (unlikely(vhost_exceeds_weight(vq, ++sent_pkts,
+						  total_len)))
 			break;
-		}
 	}
 out:
 	mutex_unlock(&vq->mutex);
@@ -867,10 +860,8 @@ static void handle_rx(struct vhost_net *net)
 			vhost_log_write(vq, vq_log, log, vhost_len,
 					vq->iov, in);
 		total_len += vhost_len;
-		if (unlikely(vhost_exceeds_weight(++recv_pkts, total_len))) {
-			vhost_poll_queue(&vq->poll);
+		if (unlikely(vhost_exceeds_weight(vq, ++recv_pkts, total_len)))
 			goto out;
-		}
 	}
 	vhost_net_enable_vq(net, vq);
 out:
@@ -949,7 +940,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		n->vqs[i].sock_hlen = 0;
 		vhost_net_buf_init(&n->vqs[i].rxq);
 	}
-	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
+	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX,
+		       VHOST_NET_WEIGHT, VHOST_NET_PKT_WEIGHT);
 
 	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
 	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
drivers/vhost/scsi.c +7 -1
index 35ebf06d9ecb..0abb7cbf54b7 100644
@@ -58,6 +58,12 @@
 #define VHOST_SCSI_PREALLOC_UPAGES 2048
 #define VHOST_SCSI_PREALLOC_PROT_SGLS 512
 
+/* Max number of requests before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others with
+ * request.
+ */
+#define VHOST_SCSI_WEIGHT 256
+
 struct vhost_scsi_inflight {
 	/* Wait for the flush operation to finish */
 	struct completion comp;
@@ -1427,7 +1433,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 		vqs[i] = &vs->vqs[i].vq;
 		vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
 	}
-	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ);
+	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, VHOST_SCSI_WEIGHT, 0);
 
 	vhost_scsi_init_inflight(vs, NULL);
 
drivers/vhost/vhost.c +19 -1
index 0e93ac888a5f..88fa81c482e8 100644
@@ -412,8 +412,24 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev)
 		vhost_vq_free_iovecs(dev->vqs[i]);
 }
 
+bool vhost_exceeds_weight(struct vhost_virtqueue *vq,
+			  int pkts, int total_len)
+{
+	struct vhost_dev *dev = vq->dev;
+
+	if ((dev->byte_weight && total_len >= dev->byte_weight) ||
+	    pkts >= dev->weight) {
+		vhost_poll_queue(&vq->poll);
+		return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(vhost_exceeds_weight);
+
 void vhost_dev_init(struct vhost_dev *dev,
-		    struct vhost_virtqueue **vqs, int nvqs)
+		    struct vhost_virtqueue **vqs, int nvqs,
+		    int weight, int byte_weight)
 {
 	struct vhost_virtqueue *vq;
 	int i;
@@ -427,6 +443,8 @@ void vhost_dev_init(struct vhost_dev *dev,
 	dev->iotlb = NULL;
 	dev->mm = NULL;
 	dev->worker = NULL;
+	dev->weight = weight;
+	dev->byte_weight = byte_weight;
 	init_llist_head(&dev->work_list);
 	init_waitqueue_head(&dev->wait);
 	INIT_LIST_HEAD(&dev->read_list);
drivers/vhost/vhost.h +5 -1
index 75d21d4a8354..950c5c4e4ee3 100644
@@ -173,9 +173,13 @@ struct vhost_dev {
 	struct list_head read_list;
 	struct list_head pending_list;
 	wait_queue_head_t wait;
+	int weight;
+	int byte_weight;
 };
 
-void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
+bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len);
+void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
+		    int nvqs, int weight, int byte_weight);
 long vhost_dev_set_owner(struct vhost_dev *dev);
 bool vhost_dev_has_owner(struct vhost_dev *dev);
 long vhost_dev_check_owner(struct vhost_dev *);
drivers/vhost/vsock.c +10 -1
index d0cf3d5aa570..d67663983656 100644
@@ -21,6 +21,14 @@
 #include "vhost.h"
 
 #define VHOST_VSOCK_DEFAULT_HOST_CID	2
+/* Max number of bytes transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others. */
+#define VHOST_VSOCK_WEIGHT 0x80000
+/* Max number of packets transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others with
+ * small pkts.
+ */
+#define VHOST_VSOCK_PKT_WEIGHT 256
 
 enum {
 	VHOST_VSOCK_FEATURES = VHOST_FEATURES,
@@ -531,7 +539,8 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 	vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick;
 	vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick;
 
-	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs));
+	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs),
+		       VHOST_VSOCK_PKT_WEIGHT, VHOST_VSOCK_WEIGHT);
 
 	file->private_data = vsock;
 	spin_lock_init(&vsock->send_pkt_list_lock);
Signature · 1 line
2.16.5
#5 lore raw

PATCH 5/7 vhost_net: fix possible infinite loop

In reply to Balbir Singh

From: Jason Wang <[email protected]>

When the rx buffer is too small for a packet, we will discard the vq descriptor and retry it for the next packet:

while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk,

                                              &busyloop_intr))) {
...
        /* On overrun, truncate and discard */
        if (unlikely(headcount > UIO_MAXIOV)) {
                iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1);
                err = sock->ops->recvmsg(sock, &msg,
                                         1, MSG_DONTWAIT | MSG_TRUNC);
                pr_debug("Discarded rx packet: len %zd\n", sock_len);
                continue;
        }

...
}

This makes it possible to trigger a infinite while..continue loop through the co-opreation of two VMs like:

1) Malicious VM1 allocate 1 byte rx buffer and try to slow down the vhost process as much as possible e.g using indirect descriptors or other.
2) Malicious VM2 generate packets to VM1 as fast as possible

Fixing this by checking against weight at the end of RX and TX loop. This also eliminate other similar cases when:

- userspace is consuming the packets in the meanwhile
- theoretical TOCTOU attack if guest moving avail index back and forth to hit the continue after vhost find guest just add new buffers

This addresses CVE-2019-3900.

[upstream e2412c07f8f3040593dfb88207865a3cd58680c0 Balbir - backport to stable 4.14]

Fixes d8316f3991d20 ("vhost: fix total length when packets are too short")
Fixes 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server")
---
 drivers/vhost/net.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)
drivers/vhost/net.c +10 -10
index a4ca0346da3e..b40e8ded49c6 100644
@@ -482,7 +482,7 @@ static void handle_tx(struct vhost_net *net)
 	hdr_size = nvq->vhost_hlen;
 	zcopy = nvq->ubufs;
 
-	for (;;) {
+	do {
 		/* Release DMAs done buffers first */
 		if (zcopy)
 			vhost_zerocopy_signal_used(net, vq);
@@ -578,10 +578,7 @@ static void handle_tx(struct vhost_net *net)
 		else
 			vhost_zerocopy_signal_used(net, vq);
 		vhost_net_tx_packet(net);
-		if (unlikely(vhost_exceeds_weight(vq, ++sent_pkts,
-						  total_len)))
-			break;
-	}
+	} while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len)));
 out:
 	mutex_unlock(&vq->mutex);
 }
@@ -779,7 +776,11 @@ static void handle_rx(struct vhost_net *net)
 		vq->log : NULL;
 	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
 
-	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
+	do {
+		sock_len = vhost_net_rx_peek_head_len(net, sock->sk);
+
+		if (!sock_len)
+			break;
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
 		headcount = get_rx_bufs(vq, vq->heads, vhost_len,
@@ -860,9 +861,8 @@ static void handle_rx(struct vhost_net *net)
 			vhost_log_write(vq, vq_log, log, vhost_len,
 					vq->iov, in);
 		total_len += vhost_len;
-		if (unlikely(vhost_exceeds_weight(vq, ++recv_pkts, total_len)))
-			goto out;
-	}
+	} while (likely(!vhost_exceeds_weight(vq, ++recv_pkts, total_len)));
+
 	vhost_net_enable_vq(net, vq);
 out:
 	mutex_unlock(&vq->mutex);
@@ -941,7 +941,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		vhost_net_buf_init(&n->vqs[i].rxq);
 	}
 	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX,
-		       VHOST_NET_WEIGHT, VHOST_NET_PKT_WEIGHT);
+		       VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT);
 
 	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
 	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
Signature · 1 line
2.16.5
#6 lore raw

PATCH 6/7 vhost: vsock: add weight support

In reply to Balbir Singh

From: Jason Wang <[email protected]>

This patch will check the weight and exit the loop if we exceeds the weight. This is useful for preventing vsock kthread from hogging cpu which is guest triggerable. The weight can help to avoid starving the request from on direction while another direction is being processed.

The value of weight is picked from vhost-net.

This addresses CVE-2019-3900.

[upstream e79b431fb901ba1106670bcc80b9b617b25def7d]
Cc Stefan Hajnoczi <[email protected]>
Fixes 433fc58e6bf2 ("VSOCK: Introduce vhost_vsock.ko")
---
 drivers/vhost/vsock.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)
drivers/vhost/vsock.c +10 -6
index d67663983656..5b9db5deffbb 100644
@@ -86,6 +86,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			    struct vhost_virtqueue *vq)
 {
 	struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
+	int pkts = 0, total_len = 0;
 	bool added = false;
 	bool restart_tx = false;
 
@@ -97,7 +98,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 	/* Avoid further vmexits, we're already processing the virtqueue */
 	vhost_disable_notify(&vsock->dev, vq);
 
-	for (;;) {
+	do {
 		struct virtio_vsock_pkt *pkt;
 		struct iov_iter iov_iter;
 		unsigned out, in;
@@ -182,8 +183,9 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		 */
 		virtio_transport_deliver_tap_pkt(pkt);
 
+		total_len += pkt->len;
 		virtio_transport_free_pkt(pkt);
-	}
+	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 	if (added)
 		vhost_signal(&vsock->dev, vq);
 
@@ -358,7 +360,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 	struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock,
 						 dev);
 	struct virtio_vsock_pkt *pkt;
-	int head;
+	int head, pkts = 0, total_len = 0;
 	unsigned int out, in;
 	bool added = false;
 
@@ -368,7 +370,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 		goto out;
 
 	vhost_disable_notify(&vsock->dev, vq);
-	for (;;) {
+	do {
 		u32 len;
 
 		if (!vhost_vsock_more_replies(vsock)) {
@@ -409,9 +411,11 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 		else
 			virtio_transport_free_pkt(pkt);
 
-		vhost_add_used(vq, head, sizeof(pkt->hdr) + len);
+		len += sizeof(pkt->hdr);
+		vhost_add_used(vq, head, len);
+		total_len += len;
 		added = true;
-	}
+	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 
 no_more_replies:
 	if (added)
Signature · 1 line
2.16.5
#7 lore raw

PATCH 7/7 vhost: scsi: add weight support

In reply to Balbir Singh

From: Jason Wang <[email protected]>

This patch will check the weight and exit the loop if we exceeds the weight. This is useful for preventing scsi kthread from hogging cpu which is guest triggerable.

This addresses CVE-2019-3900.

[upstream c1ea02f15ab5efb3e93fc3144d895410bf79fcf2 Balbir - backport to stable 4.14 ]

Cc Paolo Bonzini <[email protected]>
Cc Stefan Hajnoczi <[email protected]>
Fixes 057cbf49a1f0 ("tcm_vhost: Initial merge for vhost level target fabric driver")
---
 drivers/vhost/scsi.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/vhost/scsi.c +3 -3
index 0abb7cbf54b7..cb4ab5b955ad 100644
@@ -846,7 +846,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 	u64 tag;
 	u32 exp_data_len, data_direction;
 	unsigned int out = 0, in = 0;
-	int head, ret, prot_bytes;
+	int head, ret, prot_bytes, c = 0;
 	size_t req_size, rsp_size = sizeof(struct virtio_scsi_cmd_resp);
 	size_t out_size, in_size;
 	u16 lun;
@@ -865,7 +865,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 
 	vhost_disable_notify(&vs->dev, vq);
 
-	for (;;) {
+	do {
 		head = vhost_get_vq_desc(vq, vq->iov,
 					 ARRAY_SIZE(vq->iov), &out, &in,
 					 NULL, NULL);
@@ -1080,7 +1080,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 		 */
 		INIT_WORK(&cmd->work, vhost_scsi_submission_work);
 		queue_work(vhost_scsi_workqueue, &cmd->work);
-	}
+	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
 out:
 	mutex_unlock(&vq->mutex);
 }
Signature · 1 line
2.16.5
maintainer
#8 lore raw
In reply to Balbir Singh
Quoted 12 lines · Balbir Singh

These series of patches are required to fix the specified CVE in v4.14. I've tested these patches with a VM running vhost. Jason Wang who originally wrote the patches, helped identify other patches to backport and also tested this version and provided feedback on the patches.

Jason Wang (5):
vhost_net: introduce vhost_exceeds_weight()
vhost: introduce vhost_exceeds_weight()
vhost_net: fix possible infinite loop
vhost: vsock: add weight support
vhost: scsi: add weight support

Quoted 5 lines

Paolo Abeni (1):
vhost_net: use packet weight for rx handler, too

haibinzhang(张海斌) (1):
vhost-net: set packet weight of tx polling to 2 * vq size

All now queued up, thanks for doing the backport!

greg k-h