From 473c7391ce731adb482c03e420964676ed8b494d Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:30 +0200 Subject: [PATCH 1/5] vsock/virtio: limit the memory used per-socket Since virtio-vsock was introduced, the buffers filled by the host and pushed to the guest using the vring, are directly queued in a per-socket list. These buffers are preallocated by the guest with a fixed size (4 KB). The maximum amount of memory used by each socket should be controlled by the credit mechanism. The default credit available per-socket is 256 KB, but if we use only 1 byte per packet, the guest can queue up to 262144 of 4 KB buffers, using up to 1 GB of memory per-socket. In addition, the guest will continue to fill the vring with new 4 KB free buffers to avoid starvation of other sockets. This patch mitigates this issue copying the payload of small packets (< 128 bytes) into the buffer of last packet queued, in order to avoid wasting memory. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/vhost/vsock.c | 2 + include/linux/virtio_vsock.h | 1 + net/vmw_vsock/virtio_transport.c | 1 + net/vmw_vsock/virtio_transport_common.c | 60 +++++++++++++++++++++---- 4 files changed, 55 insertions(+), 9 deletions(-) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 6a50e1d0529c..6c8390a2af52 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -329,6 +329,8 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, return NULL; } + pkt->buf_len = pkt->len; + nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter); if (nbytes != pkt->len) { vq_err(vq, "Expected %u byte payload, got %zu bytes\n", diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index e223e2632edd..7d973903f52e 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -52,6 +52,7 @@ struct virtio_vsock_pkt { /* socket refcnt not held, only use for cancellation */ struct vsock_sock *vsk; void *buf; + u32 buf_len; u32 len; u32 off; bool reply; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 0815d1357861..082a30936690 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -307,6 +307,7 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) break; } + pkt->buf_len = buf_len; pkt->len = buf_len; sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 6f1a8aff65c5..095221f94786 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -26,6 +26,9 @@ /* How long to wait for graceful shutdown of a connection */ #define VSOCK_CLOSE_TIMEOUT (8 * HZ) +/* Threshold for detecting small packets to copy */ +#define GOOD_COPY_LEN 128 + static const struct virtio_transport *virtio_transport_get_ops(void) { const struct vsock_transport *t = vsock_core_get_transport(); @@ -64,6 +67,9 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, pkt->buf = kmalloc(len, GFP_KERNEL); if (!pkt->buf) goto out_pkt; + + pkt->buf_len = len; + err = memcpy_from_msg(pkt->buf, info->msg, len); if (err) goto out; @@ -841,24 +847,60 @@ destroy: return err; } +static void +virtio_transport_recv_enqueue(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + bool free_pkt = false; + + pkt->len = le32_to_cpu(pkt->hdr.len); + pkt->off = 0; + + spin_lock_bh(&vvs->rx_lock); + + virtio_transport_inc_rx_pkt(vvs, pkt); + + /* Try to copy small packets into the buffer of last packet queued, + * to avoid wasting memory queueing the entire buffer with a small + * payload. + */ + if (pkt->len <= GOOD_COPY_LEN && !list_empty(&vvs->rx_queue)) { + struct virtio_vsock_pkt *last_pkt; + + last_pkt = list_last_entry(&vvs->rx_queue, + struct virtio_vsock_pkt, list); + + /* If there is space in the last packet queued, we copy the + * new packet in its buffer. + */ + if (pkt->len <= last_pkt->buf_len - last_pkt->len) { + memcpy(last_pkt->buf + last_pkt->len, pkt->buf, + pkt->len); + last_pkt->len += pkt->len; + free_pkt = true; + goto out; + } + } + + list_add_tail(&pkt->list, &vvs->rx_queue); + +out: + spin_unlock_bh(&vvs->rx_lock); + if (free_pkt) + virtio_transport_free_pkt(pkt); +} + static int virtio_transport_recv_connected(struct sock *sk, struct virtio_vsock_pkt *pkt) { struct vsock_sock *vsk = vsock_sk(sk); - struct virtio_vsock_sock *vvs = vsk->trans; int err = 0; switch (le16_to_cpu(pkt->hdr.op)) { case VIRTIO_VSOCK_OP_RW: - pkt->len = le32_to_cpu(pkt->hdr.len); - pkt->off = 0; - - spin_lock_bh(&vvs->rx_lock); - virtio_transport_inc_rx_pkt(vvs, pkt); - list_add_tail(&pkt->list, &vvs->rx_queue); - spin_unlock_bh(&vvs->rx_lock); - + virtio_transport_recv_enqueue(vsk, pkt); sk->sk_data_ready(sk); return err; case VIRTIO_VSOCK_OP_CREDIT_UPDATE: From b89d882dc9fc279c8acbf1df71d51b22394186d5 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:31 +0200 Subject: [PATCH 2/5] vsock/virtio: reduce credit update messages In order to reduce the number of credit update messages, we send them only when the space available seen by the transmitter is less than VIRTIO_VSOCK_MAX_PKT_BUF_SIZE. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 1 + net/vmw_vsock/virtio_transport_common.c | 16 +++++++++++++--- 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 7d973903f52e..49fc9d20bc43 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -41,6 +41,7 @@ struct virtio_vsock_sock { /* Protected by rx_lock */ u32 fwd_cnt; + u32 last_fwd_cnt; u32 rx_bytes; struct list_head rx_queue; }; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 095221f94786..a85559d4d974 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -211,6 +211,7 @@ static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) { spin_lock_bh(&vvs->tx_lock); + vvs->last_fwd_cnt = vvs->fwd_cnt; pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); spin_unlock_bh(&vvs->tx_lock); @@ -261,6 +262,7 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, struct virtio_vsock_sock *vvs = vsk->trans; struct virtio_vsock_pkt *pkt; size_t bytes, total = 0; + u32 free_space; int err = -EFAULT; spin_lock_bh(&vvs->rx_lock); @@ -291,11 +293,19 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, virtio_transport_free_pkt(pkt); } } + + free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt); + spin_unlock_bh(&vvs->rx_lock); - /* Send a credit pkt to peer */ - virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, - NULL); + /* We send a credit update only when the space available seen + * by the transmitter is less than VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + */ + if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { + virtio_transport_send_credit_update(vsk, + VIRTIO_VSOCK_TYPE_STREAM, + NULL); + } return total; From 9632e9f61bc4191411c47933abe5f2d93c578f5e Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:32 +0200 Subject: [PATCH 3/5] vsock/virtio: fix locking in virtio_transport_inc_tx_pkt() fwd_cnt and last_fwd_cnt are protected by rx_lock, so we should use the same spinlock also if we are in the TX path. Move also buf_alloc under the same lock. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 2 +- net/vmw_vsock/virtio_transport_common.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 49fc9d20bc43..4c7781f4b29b 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -35,7 +35,6 @@ struct virtio_vsock_sock { /* Protected by tx_lock */ u32 tx_cnt; - u32 buf_alloc; u32 peer_fwd_cnt; u32 peer_buf_alloc; @@ -43,6 +42,7 @@ struct virtio_vsock_sock { u32 fwd_cnt; u32 last_fwd_cnt; u32 rx_bytes; + u32 buf_alloc; struct list_head rx_queue; }; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index a85559d4d974..34a2b42313b7 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -210,11 +210,11 @@ static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) { - spin_lock_bh(&vvs->tx_lock); + spin_lock_bh(&vvs->rx_lock); vvs->last_fwd_cnt = vvs->fwd_cnt; pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); - spin_unlock_bh(&vvs->tx_lock); + spin_unlock_bh(&vvs->rx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); From 6dbd3e66e7785a2f055bf84d98de9b8fd31ff3f5 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:33 +0200 Subject: [PATCH 4/5] vhost/vsock: split packets to send using multiple buffers If the packets to sent to the guest are bigger than the buffer available, we can split them, using multiple buffers and fixing the length in the packet header. This is safe since virtio-vsock supports only stream sockets. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/vhost/vsock.c | 66 ++++++++++++++++++------- net/vmw_vsock/virtio_transport_common.c | 15 ++++-- 2 files changed, 60 insertions(+), 21 deletions(-) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 6c8390a2af52..9f57736fe15e 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -102,7 +102,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, struct iov_iter iov_iter; unsigned out, in; size_t nbytes; - size_t len; + size_t iov_len, payload_len; int head; spin_lock_bh(&vsock->send_pkt_list_lock); @@ -147,8 +147,24 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - len = iov_length(&vq->iov[out], in); - iov_iter_init(&iov_iter, READ, &vq->iov[out], in, len); + iov_len = iov_length(&vq->iov[out], in); + if (iov_len < sizeof(pkt->hdr)) { + virtio_transport_free_pkt(pkt); + vq_err(vq, "Buffer len [%zu] too small\n", iov_len); + break; + } + + iov_iter_init(&iov_iter, READ, &vq->iov[out], in, iov_len); + payload_len = pkt->len - pkt->off; + + /* If the packet is greater than the space available in the + * buffer, we split it using multiple buffers. + */ + if (payload_len > iov_len - sizeof(pkt->hdr)) + payload_len = iov_len - sizeof(pkt->hdr); + + /* Set the correct length in the header */ + pkt->hdr.len = cpu_to_le32(payload_len); nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter); if (nbytes != sizeof(pkt->hdr)) { @@ -157,33 +173,47 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - nbytes = copy_to_iter(pkt->buf, pkt->len, &iov_iter); - if (nbytes != pkt->len) { + nbytes = copy_to_iter(pkt->buf + pkt->off, payload_len, + &iov_iter); + if (nbytes != payload_len) { virtio_transport_free_pkt(pkt); vq_err(vq, "Faulted on copying pkt buf\n"); break; } - vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len); + vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); added = true; - if (pkt->reply) { - int val; - - val = atomic_dec_return(&vsock->queued_replies); - - /* Do we have resources to resume tx processing? */ - if (val + 1 == tx_vq->num) - restart_tx = true; - } - /* Deliver to monitoring devices all correctly transmitted * packets. */ virtio_transport_deliver_tap_pkt(pkt); - total_len += pkt->len; - virtio_transport_free_pkt(pkt); + pkt->off += payload_len; + total_len += payload_len; + + /* If we didn't send all the payload we can requeue the packet + * to send it with the next available buffer. + */ + if (pkt->off < pkt->len) { + spin_lock_bh(&vsock->send_pkt_list_lock); + list_add(&pkt->list, &vsock->send_pkt_list); + spin_unlock_bh(&vsock->send_pkt_list_lock); + } else { + if (pkt->reply) { + int val; + + val = atomic_dec_return(&vsock->queued_replies); + + /* Do we have resources to resume tx + * processing? + */ + if (val + 1 == tx_vq->num) + restart_tx = true; + } + + virtio_transport_free_pkt(pkt); + } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) vhost_signal(&vsock->dev, vq); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 34a2b42313b7..56fab3f03d0e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -97,8 +97,17 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) struct virtio_vsock_pkt *pkt = opaque; struct af_vsockmon_hdr *hdr; struct sk_buff *skb; + size_t payload_len; + void *payload_buf; - skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + pkt->len, + /* A packet could be split to fit the RX buffer, so we can retrieve + * the payload length from the header and the buffer pointer taking + * care of the offset in the original packet. + */ + payload_len = le32_to_cpu(pkt->hdr.len); + payload_buf = pkt->buf + pkt->off; + + skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + payload_len, GFP_ATOMIC); if (!skb) return NULL; @@ -138,8 +147,8 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr)); - if (pkt->len) { - skb_put_data(skb, pkt->buf, pkt->len); + if (payload_len) { + skb_put_data(skb, payload_buf, payload_len); } return skb; From 0038ff357f05fee242aa4e5ec5e75f83fa1ed28c Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 30 Jul 2019 17:43:34 +0200 Subject: [PATCH 5/5] vsock/virtio: change the maximum packet size allowed Since now we are able to split packets, we can avoid limiting their sizes to VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE. Instead, we can use VIRTIO_VSOCK_MAX_PKT_BUF_SIZE as the max packet size. Signed-off-by: Stefano Garzarella Reviewed-by: Stefan Hajnoczi Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport_common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 56fab3f03d0e..94cc0fa3e848 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -181,8 +181,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, vvs = vsk->trans; /* we can send less than pkt_len bytes */ - if (pkt_len > VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE) - pkt_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; + if (pkt_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) + pkt_len = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE; /* virtio_transport_get_credit might return less than pkt_len credit */ pkt_len = virtio_transport_get_credit(vvs, pkt_len);