From 4bc0d63a23957262b01b5848bd5e1739e98bbf36 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 28 Feb 2024 17:30:09 +0800 Subject: page_frag: unify gfp bits for order 3 page allocation Currently there seems to be three page frag implementations which all try to allocate order 3 page, if that fails, it then fail back to allocate order 0 page, and each of them all allow order 3 page allocation to fail under certain condition by using specific gfp bits. The gfp bits for order 3 page allocation are different between different implementation, __GFP_NOMEMALLOC is or'd to forbid access to emergency reserves memory for __page_frag_cache_refill(), but it is not or'd in other implementions, __GFP_DIRECT_RECLAIM is masked off to avoid direct reclaim in vhost_net_page_frag_refill(), but it is not masked off in __page_frag_cache_refill(). This patch unifies the gfp bits used between different implementions by or'ing __GFP_NOMEMALLOC and masking off __GFP_DIRECT_RECLAIM for order 3 page allocation to avoid possible pressure for mm. Leave the gfp unifying for page frag implementation in sock.c for now as suggested by Paolo Abeni. Signed-off-by: Yunsheng Lin Reviewed-by: Alexander Duyck CC: Alexander Duyck Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni --- drivers/vhost/net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/vhost/net.c') diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index f2ed7167c848..e574e21cc0ca 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -670,7 +670,7 @@ static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz, /* Avoid direct reclaim but allow kswapd to wake */ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | - __GFP_NORETRY, + __GFP_NORETRY | __GFP_NOMEMALLOC, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; -- cgit v1.2.3 From 4051bd8129ac6c1faf447264aa7a8f91feb778b8 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 28 Feb 2024 17:30:11 +0800 Subject: vhost/net: remove vhost_net_page_frag_refill() The page frag in vhost_net_page_frag_refill() uses the 'struct page_frag' from skb_page_frag_refill(), but it's implementation is similar to page_frag_alloc_align() now. This patch removes vhost_net_page_frag_refill() by using 'struct page_frag_cache' instead of 'struct page_frag', and allocating frag using page_frag_alloc_align(). The added benefit is that not only unifying the page frag implementation a little, but also having about 0.5% performance boost testing by using the vhost_net_test introduced in the last patch. Signed-off-by: Yunsheng Lin Acked-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni --- drivers/vhost/net.c | 91 ++++++++++++++++------------------------------------- 1 file changed, 27 insertions(+), 64 deletions(-) (limited to 'drivers/vhost/net.c') diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index e574e21cc0ca..4b2fcb228a0a 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -141,10 +141,8 @@ struct vhost_net { unsigned tx_zcopy_err; /* Flush in progress. Protected by tx vq lock. */ bool tx_flush; - /* Private page frag */ - struct page_frag page_frag; - /* Refcount bias of page frag */ - int refcnt_bias; + /* Private page frag cache */ + struct page_frag_cache pf_cache; }; static unsigned vhost_net_zcopy_mask __read_mostly; @@ -655,41 +653,6 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len) !vhost_vq_avail_empty(vq->dev, vq); } -static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz, - struct page_frag *pfrag, gfp_t gfp) -{ - if (pfrag->page) { - if (pfrag->offset + sz <= pfrag->size) - return true; - __page_frag_cache_drain(pfrag->page, net->refcnt_bias); - } - - pfrag->offset = 0; - net->refcnt_bias = 0; - if (SKB_FRAG_PAGE_ORDER) { - /* Avoid direct reclaim but allow kswapd to wake */ - pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | - __GFP_COMP | __GFP_NOWARN | - __GFP_NORETRY | __GFP_NOMEMALLOC, - SKB_FRAG_PAGE_ORDER); - if (likely(pfrag->page)) { - pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; - goto done; - } - } - pfrag->page = alloc_page(gfp); - if (likely(pfrag->page)) { - pfrag->size = PAGE_SIZE; - goto done; - } - return false; - -done: - net->refcnt_bias = USHRT_MAX; - page_ref_add(pfrag->page, USHRT_MAX - 1); - return true; -} - #define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, @@ -699,7 +662,6 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); struct socket *sock = vhost_vq_get_backend(vq); - struct page_frag *alloc_frag = &net->page_frag; struct virtio_net_hdr *gso; struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; struct tun_xdp_hdr *hdr; @@ -710,6 +672,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, int sock_hlen = nvq->sock_hlen; void *buf; int copied; + int ret; if (unlikely(len < nvq->sock_hlen)) return -EFAULT; @@ -719,18 +682,17 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, return -ENOSPC; buflen += SKB_DATA_ALIGN(len + pad); - alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); - if (unlikely(!vhost_net_page_frag_refill(net, buflen, - alloc_frag, GFP_KERNEL))) + buf = page_frag_alloc_align(&net->pf_cache, buflen, GFP_KERNEL, + SMP_CACHE_BYTES); + if (unlikely(!buf)) return -ENOMEM; - buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; - copied = copy_page_from_iter(alloc_frag->page, - alloc_frag->offset + - offsetof(struct tun_xdp_hdr, gso), - sock_hlen, from); - if (copied != sock_hlen) - return -EFAULT; + copied = copy_from_iter(buf + offsetof(struct tun_xdp_hdr, gso), + sock_hlen, from); + if (copied != sock_hlen) { + ret = -EFAULT; + goto err; + } hdr = buf; gso = &hdr->gso; @@ -743,27 +705,30 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, vhost16_to_cpu(vq, gso->csum_start) + vhost16_to_cpu(vq, gso->csum_offset) + 2); - if (vhost16_to_cpu(vq, gso->hdr_len) > len) - return -EINVAL; + if (vhost16_to_cpu(vq, gso->hdr_len) > len) { + ret = -EINVAL; + goto err; + } } len -= sock_hlen; - copied = copy_page_from_iter(alloc_frag->page, - alloc_frag->offset + pad, - len, from); - if (copied != len) - return -EFAULT; + copied = copy_from_iter(buf + pad, len, from); + if (copied != len) { + ret = -EFAULT; + goto err; + } xdp_init_buff(xdp, buflen, NULL); xdp_prepare_buff(xdp, buf, pad, len, true); hdr->buflen = buflen; - --net->refcnt_bias; - alloc_frag->offset += buflen; - ++nvq->batched_xdp; return 0; + +err: + page_frag_free(buf); + return ret; } static void handle_tx_copy(struct vhost_net *net, struct socket *sock) @@ -1353,8 +1318,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) vqs[VHOST_NET_VQ_RX]); f->private_data = n; - n->page_frag.page = NULL; - n->refcnt_bias = 0; + n->pf_cache.va = NULL; return 0; } @@ -1422,8 +1386,7 @@ static int vhost_net_release(struct inode *inode, struct file *f) kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue); kfree(n->vqs[VHOST_NET_VQ_TX].xdp); kfree(n->dev.vqs); - if (n->page_frag.page) - __page_frag_cache_drain(n->page_frag.page, n->refcnt_bias); + page_frag_cache_drain(&n->pf_cache); kvfree(n); return 0; } -- cgit v1.2.3 From f6baca2d32ead51b10e15f1eef812d7c6a7b9a40 Mon Sep 17 00:00:00 2001 From: Andrew Melnychenko Date: Mon, 15 Jan 2024 21:48:40 +0200 Subject: vhost: Added pad cleanup if vnet_hdr is not present. When the Qemu launched with vhost but without tap vnet_hdr, vhost tries to copy vnet_hdr from socket iter with size 0 to the page that may contain some trash. That trash can be interpreted as unpredictable values for vnet_hdr. That leads to dropping some packets and in some cases to stalling vhost routine when the vhost_net tries to process packets and fails in a loop. Qemu options: -netdev tap,vhost=on,vnet_hdr=off,... Signed-off-by: Andrew Melnychenko Message-Id: <20240115194840.1183077-1-andrew@daynix.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/net.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/vhost/net.c') diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index f2ed7167c848..57411ac2d08b 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -735,6 +735,9 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, hdr = buf; gso = &hdr->gso; + if (!sock_hlen) + memset(buf, 0, pad); + if ((gso->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && vhost16_to_cpu(vq, gso->csum_start) + vhost16_to_cpu(vq, gso->csum_offset) + 2 > -- cgit v1.2.3