From 25074a44ac4e5dae5b4a25dcb9bbfcbd00f15ae2 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Wed, 8 Mar 2023 10:49:33 +0800 Subject: virtio_net: reorder some funcs The purpose of this is to facilitate the subsequent addition of new functions without introducing a separate declaration. Signed-off-by: Xuan Zhuo Acked-by: Michael S. Tsirkin Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 92 ++++++++++++++++++++++++------------------------ 1 file changed, 46 insertions(+), 46 deletions(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index fb5e68ed3ec27..8b31a04052f2f 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -545,6 +545,52 @@ ok: return skb; } +static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) +{ + unsigned int len; + unsigned int packets = 0; + unsigned int bytes = 0; + void *ptr; + + while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { + if (likely(!is_xdp_frame(ptr))) { + struct sk_buff *skb = ptr; + + pr_debug("Sent skb %p\n", skb); + + bytes += skb->len; + napi_consume_skb(skb, in_napi); + } else { + struct xdp_frame *frame = ptr_to_xdp(ptr); + + bytes += xdp_get_frame_len(frame); + xdp_return_frame(frame); + } + packets++; + } + + /* Avoid overhead when no packets have been processed + * happens when called speculatively from start_xmit. + */ + if (!packets) + return; + + u64_stats_update_begin(&sq->stats.syncp); + sq->stats.bytes += bytes; + sq->stats.packets += packets; + u64_stats_update_end(&sq->stats.syncp); +} + +static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) +{ + if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) + return false; + else if (q < vi->curr_queue_pairs) + return true; + else + return false; +} + static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, struct send_queue *sq, struct xdp_frame *xdpf) @@ -1714,52 +1760,6 @@ static int virtnet_receive(struct receive_queue *rq, int budget, return stats.packets; } -static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) -{ - unsigned int len; - unsigned int packets = 0; - unsigned int bytes = 0; - void *ptr; - - while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { - if (likely(!is_xdp_frame(ptr))) { - struct sk_buff *skb = ptr; - - pr_debug("Sent skb %p\n", skb); - - bytes += skb->len; - napi_consume_skb(skb, in_napi); - } else { - struct xdp_frame *frame = ptr_to_xdp(ptr); - - bytes += xdp_get_frame_len(frame); - xdp_return_frame(frame); - } - packets++; - } - - /* Avoid overhead when no packets have been processed - * happens when called speculatively from start_xmit. - */ - if (!packets) - return; - - u64_stats_update_begin(&sq->stats.syncp); - sq->stats.bytes += bytes; - sq->stats.packets += packets; - u64_stats_update_end(&sq->stats.syncp); -} - -static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) -{ - if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) - return false; - else if (q < vi->curr_queue_pairs) - return true; - else - return false; -} - static void virtnet_poll_cleantx(struct receive_queue *rq) { struct virtnet_info *vi = rq->vq->vdev->priv; -- cgit v1.2.3 From b8ef4809bc7faa22e63de921ef56de21ed191af0 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Wed, 8 Mar 2023 10:49:34 +0800 Subject: virtio_net: separate the logic of checking whether sq is full Separate the logic of checking whether sq is full. The subsequent patch will reuse this func. Signed-off-by: Xuan Zhuo Reviewed-by: Alexander Duyck Acked-by: Michael S. Tsirkin Acked-by: Jason Wang Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 60 +++++++++++++++++++++++++++++------------------- 1 file changed, 36 insertions(+), 24 deletions(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 8b31a04052f2f..46bbddaadb0d3 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -591,6 +591,41 @@ static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) return false; } +static void check_sq_full_and_disable(struct virtnet_info *vi, + struct net_device *dev, + struct send_queue *sq) +{ + bool use_napi = sq->napi.weight; + int qnum; + + qnum = sq - vi->sq; + + /* If running out of space, stop queue to avoid getting packets that we + * are then unable to transmit. + * An alternative would be to force queuing layer to requeue the skb by + * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be + * returned in a normal path of operation: it means that driver is not + * maintaining the TX queue stop/start state properly, and causes + * the stack to do a non-trivial amount of useless work. + * Since most packets only take 1 or 2 ring slots, stopping the queue + * early means 16 slots are typically wasted. + */ + if (sq->vq->num_free < 2+MAX_SKB_FRAGS) { + netif_stop_subqueue(dev, qnum); + if (use_napi) { + if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) + virtqueue_napi_schedule(&sq->napi, sq->vq); + } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { + /* More just got used, free them then recheck. */ + free_old_xmit_skbs(sq, false); + if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) { + netif_start_subqueue(dev, qnum); + virtqueue_disable_cb(sq->vq); + } + } + } +} + static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, struct send_queue *sq, struct xdp_frame *xdpf) @@ -1989,30 +2024,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) nf_reset_ct(skb); } - /* If running out of space, stop queue to avoid getting packets that we - * are then unable to transmit. - * An alternative would be to force queuing layer to requeue the skb by - * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be - * returned in a normal path of operation: it means that driver is not - * maintaining the TX queue stop/start state properly, and causes - * the stack to do a non-trivial amount of useless work. - * Since most packets only take 1 or 2 ring slots, stopping the queue - * early means 16 slots are typically wasted. - */ - if (sq->vq->num_free < 2+MAX_SKB_FRAGS) { - netif_stop_subqueue(dev, qnum); - if (use_napi) { - if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) - virtqueue_napi_schedule(&sq->napi, sq->vq); - } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { - /* More just got used, free them then recheck. */ - free_old_xmit_skbs(sq, false); - if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) { - netif_start_subqueue(dev, qnum); - virtqueue_disable_cb(sq->vq); - } - } - } + check_sq_full_and_disable(vi, dev, sq); if (kick || netif_xmit_stopped(txq)) { if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { -- cgit v1.2.3 From cd1c604aa1d8c641f5edcb58b76352d4eba06ec1 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Wed, 8 Mar 2023 10:49:35 +0800 Subject: virtio_net: add checking sq is full inside xdp xmit If the queue of xdp xmit is not an independent queue, then when the xdp xmit used all the desc, the xmit from the __dev_queue_xmit() may encounter the following error. net ens4: Unexpected TXQ (0) queue failure: -28 This patch adds a check whether sq is full in xdp xmit. Fixes: 56434a01b12e ("virtio_net: add XDP_TX support") Reported-by: Yichun Zhang Signed-off-by: Xuan Zhuo Reviewed-by: Alexander Duyck Acked-by: Michael S. Tsirkin Acked-by: Jason Wang Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 46bbddaadb0d3..1a309cfb4976a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -767,6 +767,9 @@ static int virtnet_xdp_xmit(struct net_device *dev, } ret = nxmit; + if (!is_xdp_raw_buffer_queue(vi, sq - vi->sq)) + check_sq_full_and_disable(vi, dev, sq); + if (flags & XDP_XMIT_FLUSH) { if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) kicks = 1; -- cgit v1.2.3 From be50da3e9d4ad1958f7b11322d44d94d5c25a4c1 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 9 Mar 2023 10:45:59 +0100 Subject: net: virtio_net: implement exact header length guest feature Virtio spec introduced a feature VIRTIO_NET_F_GUEST_HDRLEN which when set implicates that device benefits from knowing the exact size of the header. For compatibility, to signal to the device that the header is reliable driver also needs to set this feature. Without this feature set by driver, device has to figure out the header size itself. Quoting the original virtio spec: "hdr_len is a hint to the device as to how much of the header needs to be kept to copy into each packet" "a hint" might not be clear for the reader what does it mean, if it is "maybe like that" of "exactly like that". This feature just makes it crystal clear and let the device count on the hdr_len being filled up by the exact length of header. Also note the spec already has following note about hdr_len: "Due to various bugs in implementations, this field is not useful as a guarantee of the transport header size." Without this feature the device needs to parse the header in core data path handling. Accurate information helps the device to eliminate such header parsing and directly use the hardware accelerators for GSO operation. virtio_net_hdr_from_skb() fills up hdr_len to skb_headlen(skb). The driver already complies to fill the correct value. Introduce the feature and advertise it. Note that virtio spec also includes following note for device implementation: "Caution should be taken by the implementation so as to prevent a malicious driver from attacking the device by setting an incorrect hdr_len." There is a plan to support this feature in our emulated device. A device of SolidRun offers this feature bit. They claim this feature will save the device a few cycles for every GSO packet. Link: https://docs.oasis-open.org/virtio/virtio/v1.2/cs01/virtio-v1.2-cs01.html#x1-230006x3 Signed-off-by: Jiri Pirko Reviewed-by: Parav Pandit Reviewed-by: Alvaro Karsz Acked-by: Michael S. Tsirkin Acked-by: Willem de Bruijn Link: https://lore.kernel.org/r/20230309094559.917857-1-jiri@resnulli.us Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 6 ++++-- include/uapi/linux/virtio_net.h | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index fb5e68ed3ec27..e85b03988733e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -62,7 +62,8 @@ static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_UFO, VIRTIO_NET_F_GUEST_CSUM, VIRTIO_NET_F_GUEST_USO4, - VIRTIO_NET_F_GUEST_USO6 + VIRTIO_NET_F_GUEST_USO6, + VIRTIO_NET_F_GUEST_HDRLEN }; #define GUEST_OFFLOAD_GRO_HW_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \ @@ -4213,7 +4214,8 @@ static struct virtio_device_id id_table[] = { VIRTIO_NET_F_CTRL_MAC_ADDR, \ VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \ VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \ - VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL + VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL, \ + VIRTIO_NET_F_GUEST_HDRLEN static unsigned int features[] = { VIRTNET_FEATURES, diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index b4062bed186a6..12c1c9699935e 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -61,6 +61,7 @@ #define VIRTIO_NET_F_GUEST_USO6 55 /* Guest can handle USOv6 in. */ #define VIRTIO_NET_F_HOST_USO 56 /* Host can handle USO in. */ #define VIRTIO_NET_F_HASH_REPORT 57 /* Supports hash report */ +#define VIRTIO_NET_F_GUEST_HDRLEN 59 /* Guest provides the exact hdr_len value. */ #define VIRTIO_NET_F_RSS 60 /* Supports RSS RX steering */ #define VIRTIO_NET_F_RSC_EXT 61 /* extended coalescing info */ #define VIRTIO_NET_F_STANDBY 62 /* Act as standby for another device -- cgit v1.2.3 From fa0f1ba7c8233118b6fdaa65e2f5ded563d3e1fa Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Wed, 15 Mar 2023 09:52:22 +0800 Subject: virtio_net: fix page_to_skb() miss headroom Because headroom is not passed to page_to_skb(), this causes the shinfo exceeds the range. Then the frags of shinfo are changed by other process. [ 157.724634] stack segment: 0000 [#1] PREEMPT SMP NOPTI [ 157.725358] CPU: 3 PID: 679 Comm: xdp_pass_user_f Tainted: G E 6.2.0+ #150 [ 157.726401] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/4 [ 157.727820] RIP: 0010:skb_release_data+0x11b/0x180 [ 157.728449] Code: 44 24 02 48 83 c3 01 39 d8 7e be 48 89 d8 48 c1 e0 04 41 80 7d 7e 00 49 8b 6c 04 30 79 0c 48 89 ef e8 89 b [ 157.730751] RSP: 0018:ffffc90000178b48 EFLAGS: 00010202 [ 157.731383] RAX: 0000000000000010 RBX: 0000000000000001 RCX: 0000000000000000 [ 157.732270] RDX: 0000000000000000 RSI: 0000000000000002 RDI: ffff888100dd0b00 [ 157.733117] RBP: 5d5d76010f6e2408 R08: ffff888100dd0b2c R09: 0000000000000000 [ 157.734013] R10: ffffffff82effd30 R11: 000000000000a14e R12: ffff88810981ffc0 [ 157.734904] R13: ffff888100dd0b00 R14: 0000000000000002 R15: 0000000000002310 [ 157.735793] FS: 00007f06121d9740(0000) GS:ffff88842fcc0000(0000) knlGS:0000000000000000 [ 157.736794] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 157.737522] CR2: 00007ffd9a56c084 CR3: 0000000104bda001 CR4: 0000000000770ee0 [ 157.738420] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 157.739283] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 157.740146] PKRU: 55555554 [ 157.740502] Call Trace: [ 157.740843] [ 157.741117] kfree_skb_reason+0x50/0x120 [ 157.741613] __udp4_lib_rcv+0x52b/0x5e0 [ 157.742132] ip_protocol_deliver_rcu+0xaf/0x190 [ 157.742715] ip_local_deliver_finish+0x77/0xa0 [ 157.743280] ip_sublist_rcv_finish+0x80/0x90 [ 157.743834] ip_list_rcv_finish.constprop.0+0x16f/0x190 [ 157.744493] ip_list_rcv+0x126/0x140 [ 157.744952] __netif_receive_skb_list_core+0x29b/0x2c0 [ 157.745602] __netif_receive_skb_list+0xed/0x160 [ 157.746190] ? udp4_gro_receive+0x275/0x350 [ 157.746732] netif_receive_skb_list_internal+0xf2/0x1b0 [ 157.747398] napi_gro_receive+0xd1/0x210 [ 157.747911] virtnet_receive+0x75/0x1c0 [ 157.748422] virtnet_poll+0x48/0x1b0 [ 157.748878] __napi_poll+0x29/0x1b0 [ 157.749330] net_rx_action+0x27a/0x340 [ 157.749812] __do_softirq+0xf3/0x2fb [ 157.750298] do_softirq+0xa2/0xd0 [ 157.750745] [ 157.751563] [ 157.752329] __local_bh_enable_ip+0x6d/0x80 [ 157.753178] virtnet_xdp_set+0x482/0x860 [ 157.754159] ? __pfx_virtnet_xdp+0x10/0x10 [ 157.755129] dev_xdp_install+0xa4/0xe0 [ 157.756033] dev_xdp_attach+0x20b/0x5e0 [ 157.756933] do_setlink+0x82e/0xc90 [ 157.757777] ? __nla_validate_parse+0x12b/0x1e0 [ 157.758744] rtnl_setlink+0xd8/0x170 [ 157.759549] ? mod_objcg_state+0xcb/0x320 [ 157.760328] ? security_capable+0x37/0x60 [ 157.761209] ? security_capable+0x37/0x60 [ 157.762072] rtnetlink_rcv_msg+0x145/0x3d0 [ 157.762929] ? ___slab_alloc+0x327/0x610 [ 157.763754] ? __alloc_skb+0x141/0x170 [ 157.764533] ? __pfx_rtnetlink_rcv_msg+0x10/0x10 [ 157.765422] netlink_rcv_skb+0x58/0x110 [ 157.766229] netlink_unicast+0x21f/0x330 [ 157.766951] netlink_sendmsg+0x240/0x4a0 [ 157.767654] sock_sendmsg+0x93/0xa0 [ 157.768434] ? sockfd_lookup_light+0x12/0x70 [ 157.769245] __sys_sendto+0xfe/0x170 [ 157.770079] ? handle_mm_fault+0xe9/0x2d0 [ 157.770859] ? preempt_count_add+0x51/0xa0 [ 157.771645] ? up_read+0x3c/0x80 [ 157.772340] ? do_user_addr_fault+0x1e9/0x710 [ 157.773166] ? kvm_read_and_reset_apf_flags+0x49/0x60 [ 157.774087] __x64_sys_sendto+0x29/0x30 [ 157.774856] do_syscall_64+0x3c/0x90 [ 157.775518] entry_SYSCALL_64_after_hwframe+0x72/0xdc [ 157.776382] RIP: 0033:0x7f06122def70 Fixes: 18117a842ab0 ("virtio-net: remove xdp related info from page_to_skb()") Signed-off-by: Xuan Zhuo Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 1a309cfb4976a..8ecf7a341d543 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -446,7 +446,8 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx) static struct sk_buff *page_to_skb(struct virtnet_info *vi, struct receive_queue *rq, struct page *page, unsigned int offset, - unsigned int len, unsigned int truesize) + unsigned int len, unsigned int truesize, + unsigned int headroom) { struct sk_buff *skb; struct virtio_net_hdr_mrg_rxbuf *hdr; @@ -464,11 +465,11 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, else hdr_padded_len = sizeof(struct padded_vnet_hdr); - buf = p; + buf = p - headroom; len -= hdr_len; offset += hdr_padded_len; p += hdr_padded_len; - tailroom = truesize - hdr_padded_len - len; + tailroom = truesize - headroom - hdr_padded_len - len; shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -1009,7 +1010,7 @@ static struct sk_buff *receive_big(struct net_device *dev, { struct page *page = buf; struct sk_buff *skb = - page_to_skb(vi, rq, page, 0, len, PAGE_SIZE); + page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, 0); stats->bytes += len - vi->hdr_len; if (unlikely(!skb)) @@ -1332,7 +1333,7 @@ err_xdp_frags: rcu_read_unlock(); skip_xdp: - head_skb = page_to_skb(vi, rq, page, offset, len, truesize); + head_skb = page_to_skb(vi, rq, page, offset, len, truesize, headroom); curr_skb = head_skb; if (unlikely(!curr_skb)) -- cgit v1.2.3 From 1a3bd6eabae35afc5c6dbe2651f21467cf8ad3fd Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Wed, 15 Mar 2023 09:52:23 +0800 Subject: virtio_net: free xdp shinfo frags when build_skb_from_xdp_buff() fails build_skb_from_xdp_buff() may return NULL, in this case we need to free the frags of xdp shinfo. Fixes: fab89bafa95b ("virtio-net: support multi-buffer xdp") Signed-off-by: Xuan Zhuo Acked-by: Michael S. Tsirkin Reviewed-by: Yunsheng Lin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 8ecf7a341d543..2396c28c01221 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1273,9 +1273,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, switch (act) { case XDP_PASS: + head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz); + if (unlikely(!head_skb)) + goto err_xdp_frags; + if (unlikely(xdp_page != page)) put_page(page); - head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz); rcu_read_unlock(); return head_skb; case XDP_TX: -- cgit v1.2.3 From 853618d5886bf94812f31228091cd37d308230f7 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Fri, 14 Apr 2023 14:08:35 +0800 Subject: virtio_net: bugfix overflow inside xdp_linearize_page() Here we copy the data from the original buf to the new page. But we not check that it may be overflow. As long as the size received(including vnethdr) is greater than 3840 (PAGE_SIZE -VIRTIO_XDP_HEADROOM). Then the memcpy will overflow. And this is completely possible, as long as the MTU is large, such as 4096. In our test environment, this will cause crash. Since crash is caused by the written memory, it is meaningless, so I do not include it. Fixes: 72979a6c3590 ("virtio_net: xdp, add slowpath case for non contiguous buffers") Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 2396c28c01221..ea1bd4bb326d1 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -814,8 +814,13 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, int page_off, unsigned int *len) { - struct page *page = alloc_page(GFP_ATOMIC); + int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + struct page *page; + + if (page_off + *len + tailroom > PAGE_SIZE) + return NULL; + page = alloc_page(GFP_ATOMIC); if (!page) return NULL; @@ -823,7 +828,6 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, page_off += *len; while (--*num_buf) { - int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); unsigned int buflen; void *buf; int off; -- cgit v1.2.3 From f8bb5104394560e29017c25bcade4c6b7aabd108 Mon Sep 17 00:00:00 2001 From: Wenliang Wang Date: Thu, 4 May 2023 10:27:06 +0800 Subject: virtio_net: suppress cpu stall when free_unused_bufs For multi-queue and large ring-size use case, the following error occurred when free_unused_bufs: rcu: INFO: rcu_sched self-detected stall on CPU. Fixes: 986a4f4d452d ("virtio_net: multiqueue support") Signed-off-by: Wenliang Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 8d8038538fc47..a12ae26db0e22 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi) struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_sq_free_unused_buf(vq, buf); + cond_resched(); } for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->rq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_rq_free_unused_buf(vq, buf); + cond_resched(); } } -- cgit v1.2.3 From 5306623a9826aa7d63b32c6a3803c798a765474d Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Fri, 12 May 2023 11:18:12 -0400 Subject: virtio_net: Fix error unwinding of XDP initialization When initializing XDP in virtnet_open(), some rq xdp initialization may hit an error causing net device open failed. However, previous rqs have already initialized XDP and enabled NAPI, which is not the expected behavior. Need to roll back the previous rq initialization to avoid leaks in error unwinding of init code. Also extract helper functions of disable and enable queue pairs. Use newly introduced disable helper function in error unwinding and virtnet_close. Use enable helper function in virtnet_open. Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info") Signed-off-by: Feng Liu Reviewed-by: Jiri Pirko Reviewed-by: William Tu Acked-by: Michael S. Tsirkin Acked-by: Jason Wang Reviewed-by: Xuan Zhuo Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 61 ++++++++++++++++++++++++++++++++++-------------- 1 file changed, 44 insertions(+), 17 deletions(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index a12ae26db0e22..56ca1d2703042 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1868,6 +1868,38 @@ static int virtnet_poll(struct napi_struct *napi, int budget) return received; } +static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) +{ + virtnet_napi_tx_disable(&vi->sq[qp_index].napi); + napi_disable(&vi->rq[qp_index].napi); + xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); +} + +static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) +{ + struct net_device *dev = vi->dev; + int err; + + err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index, + vi->rq[qp_index].napi.napi_id); + if (err < 0) + return err; + + err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL); + if (err < 0) + goto err_xdp_reg_mem_model; + + virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); + virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); + + return 0; + +err_xdp_reg_mem_model: + xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); + return err; +} + static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -1881,22 +1913,20 @@ static int virtnet_open(struct net_device *dev) if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); - err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id); + err = virtnet_enable_queue_pair(vi, i); if (err < 0) - return err; - - err = xdp_rxq_info_reg_mem_model(&vi->rq[i].xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL); - if (err < 0) { - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - return err; - } - - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); - virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi); + goto err_enable_qp; } return 0; + +err_enable_qp: + disable_delayed_refill(vi); + cancel_delayed_work_sync(&vi->refill); + + for (i--; i >= 0; i--) + virtnet_disable_queue_pair(vi, i); + return err; } static int virtnet_poll_tx(struct napi_struct *napi, int budget) @@ -2305,11 +2335,8 @@ static int virtnet_close(struct net_device *dev) /* Make sure refill_work doesn't re-enable napi! */ cancel_delayed_work_sync(&vi->refill); - for (i = 0; i < vi->max_queue_pairs; i++) { - virtnet_napi_tx_disable(&vi->sq[i].napi); - napi_disable(&vi->rq[i].napi); - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - } + for (i = 0; i < vi->max_queue_pairs; i++) + virtnet_disable_queue_pair(vi, i); return 0; } -- cgit v1.2.3 From accc1bf23068c1cdc4c2b015320ba856e210dd98 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Mon, 5 Jun 2023 12:59:25 -0700 Subject: virtio_net: use control_buf for coalesce params Commit 699b045a8e43 ("net: virtio_net: notifications coalescing support") added coalescing command support for virtio_net. However, the coalesce commands are using buffers on the stack, which is causing the device to see DMA errors. There should also be a complaint from check_for_stack() in debug_dma_map_xyz(). Fix this by adding and using coalesce params from the control_buf struct, which aligns with other commands. Cc: stable@vger.kernel.org Fixes: 699b045a8e43 ("net: virtio_net: notifications coalescing support") Reviewed-by: Shannon Nelson Signed-off-by: Allen Hubbe Signed-off-by: Brett Creeley Acked-by: Jason Wang Reviewed-by: Xuan Zhuo Acked-by: Michael S. Tsirkin Link: https://lore.kernel.org/r/20230605195925.51625-1-brett.creeley@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'drivers/net/virtio_net.c') diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 56ca1d2703042..486b5849033dc 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -205,6 +205,8 @@ struct control_buf { __virtio16 vid; __virtio64 offloads; struct virtio_net_ctrl_rss rss; + struct virtio_net_ctrl_coal_tx coal_tx; + struct virtio_net_ctrl_coal_rx coal_rx; }; struct virtnet_info { @@ -2934,12 +2936,10 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec) { struct scatterlist sgs_tx, sgs_rx; - struct virtio_net_ctrl_coal_tx coal_tx; - struct virtio_net_ctrl_coal_rx coal_rx; - coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs); - coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames); - sg_init_one(&sgs_tx, &coal_tx, sizeof(coal_tx)); + vi->ctrl->coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs); + vi->ctrl->coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames); + sg_init_one(&sgs_tx, &vi->ctrl->coal_tx, sizeof(vi->ctrl->coal_tx)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_TX_SET, @@ -2950,9 +2950,9 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, vi->tx_usecs = ec->tx_coalesce_usecs; vi->tx_max_packets = ec->tx_max_coalesced_frames; - coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs); - coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames); - sg_init_one(&sgs_rx, &coal_rx, sizeof(coal_rx)); + vi->ctrl->coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs); + vi->ctrl->coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames); + sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_RX_SET, -- cgit v1.2.3