From 1f8b977ab32dc5d148f103326e80d9097f1cefb5 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 3 Aug 2017 16:29:41 -0400 Subject: [PATCH] sock: enable MSG_ZEROCOPY Prepare the datapath for refcounted ubuf_info. Clone ubuf_info with skb_zerocopy_clone() wherever needed due to skb split, merge, resize or clone. Split skb_orphan_frags into two variants. The split, merge, .. paths support reference counted zerocopy buffers, so do not do a deep copy. Add skb_orphan_frags_rx for paths that may loop packets to receive sockets. That is not allowed, as it may cause unbounded latency. Deep copy all zerocopy copy buffers, ref-counted or not, in this path. The exact locations to modify were chosen by exhaustively searching through all code that might modify skb_frag references and/or the the SKBTX_DEV_ZEROCOPY tx_flags bit. The changes err on the safe side, in two ways. (1) legacy ubuf_info paths virtio and tap are not modified. They keep a 1:1 ubuf_info to sk_buff relationship. Calls to skb_orphan_frags still call skb_copy_ubufs and thus copy frags in this case. (2) not all copies deep in the stack are addressed yet. skb_shift, skb_split and skb_try_coalesce can be refined to avoid copying. These are not in the hot path and this patch is hairy enough as is, so that is left for future refinement. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- drivers/net/tun.c | 2 +- drivers/vhost/net.c | 1 + include/linux/skbuff.h | 14 +++++++++++- net/core/dev.c | 4 ++-- net/core/skbuff.c | 48 +++++++++++++++++------------------------- 5 files changed, 36 insertions(+), 33 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 68add55f8460..d21510d47aa2 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -892,7 +892,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) sk_filter(tfile->socket.sk, skb)) goto drop; - if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; skb_tx_timestamp(skb); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 06d044862e58..ba08b78ed630 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -533,6 +533,7 @@ static void handle_tx(struct vhost_net *net) ubuf->callback = vhost_zerocopy_callback; ubuf->ctx = nvq->ubufs; ubuf->desc = nvq->upend_idx; + atomic_set(&ubuf->refcnt, 1); msg.msg_control = ubuf; msg.msg_controllen = sizeof(ubuf); ubufs = nvq->ubufs; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 59cff7aa494e..e5387932c266 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2512,7 +2512,17 @@ static inline void skb_orphan(struct sk_buff *skb) */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { - if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY))) + if (likely(!skb_zcopy(skb))) + return 0; + if (skb_uarg(skb)->callback == sock_zerocopy_callback) + return 0; + return skb_copy_ubufs(skb, gfp_mask); +} + +/* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ +static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) +{ + if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } @@ -2944,6 +2954,8 @@ static inline int skb_add_data(struct sk_buff *skb, static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { + if (skb_zcopy(skb)) + return false; if (i) { const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; diff --git a/net/core/dev.c b/net/core/dev.c index 8ea6b4b42611..1d75499add72 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1853,7 +1853,7 @@ static inline int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) { - if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) return -ENOMEM; refcount_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); @@ -4412,7 +4412,7 @@ skip_classify: } if (pt_prev) { - if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; else ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 29e34bc6a17c..74d3c36f8419 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -567,21 +567,10 @@ static void skb_release_data(struct sk_buff *skb) for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i]); - /* - * If skb buf is from userspace, we need to notify the caller - * the lower device DMA has done; - */ - if (shinfo->tx_flags & SKBTX_DEV_ZEROCOPY) { - struct ubuf_info *uarg; - - uarg = shinfo->destructor_arg; - if (uarg->callback) - uarg->callback(uarg, true); - } - if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); + skb_zcopy_clear(skb, true); skb_free_head(skb); } @@ -695,14 +684,7 @@ EXPORT_SYMBOL(kfree_skb_list); */ void skb_tx_error(struct sk_buff *skb) { - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - struct ubuf_info *uarg; - - uarg = skb_shinfo(skb)->destructor_arg; - if (uarg->callback) - uarg->callback(uarg, false); - skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; - } + skb_zcopy_clear(skb, true); } EXPORT_SYMBOL(skb_tx_error); @@ -1029,9 +1011,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); -/* unused only until next patch in the series; will remove attribute */ -static int __attribute__((unused)) - skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, +static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, gfp_t gfp_mask) { if (skb_zcopy(orig)) { @@ -1068,7 +1048,6 @@ static int __attribute__((unused)) */ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) { - struct ubuf_info *uarg = skb_shinfo(skb)->destructor_arg; int num_frags = skb_shinfo(skb)->nr_frags; struct page *page, *head = NULL; int i, new_frags; @@ -1127,8 +1106,6 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) for (i = 0; i < num_frags; i++) skb_frag_unref(skb, i); - uarg->callback(uarg, false); - /* skb frags point to kernel buffers */ for (i = 0; i < new_frags - 1; i++) { __skb_fill_page_desc(skb, i, head, 0, PAGE_SIZE); @@ -1137,7 +1114,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) __skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off); skb_shinfo(skb)->nr_frags = new_frags; - skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; + skb_zcopy_clear(skb, false); return 0; } EXPORT_SYMBOL_GPL(skb_copy_ubufs); @@ -1298,7 +1275,8 @@ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, if (skb_shinfo(skb)->nr_frags) { int i; - if (skb_orphan_frags(skb, gfp_mask)) { + if (skb_orphan_frags(skb, gfp_mask) || + skb_zerocopy_clone(n, skb, gfp_mask)) { kfree_skb(n); n = NULL; goto out; @@ -1375,9 +1353,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, * be since all we did is relocate the values */ if (skb_cloned(skb)) { - /* copy this zero copy skb frags */ if (skb_orphan_frags(skb, gfp_mask)) goto nofrags; + if (skb_zcopy(skb)) + atomic_inc(&skb_uarg(skb)->refcnt); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); @@ -1872,6 +1851,9 @@ end: skb->tail += delta; skb->data_len -= delta; + if (!skb->data_len) + skb_zcopy_clear(skb, false); + return skb_tail_pointer(skb); } EXPORT_SYMBOL(__pskb_pull_tail); @@ -2627,6 +2609,7 @@ skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) skb_tx_error(from); return -ENOMEM; } + skb_zerocopy_clone(to, from, GFP_ATOMIC); for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { if (!len) @@ -2924,6 +2907,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) skb_shinfo(skb1)->tx_flags |= skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; + skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ @@ -2967,6 +2951,8 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) if (skb_headlen(skb)) return 0; + if (skb_zcopy(tgt) || skb_zcopy(skb)) + return 0; todo = shiftlen; from = 0; @@ -3540,6 +3526,8 @@ normal: skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags & SKBTX_SHARED_FRAG; + if (skb_zerocopy_clone(nskb, head_skb, GFP_ATOMIC)) + goto err; while (pos < offset + len) { if (i >= nfrags) { @@ -4663,6 +4651,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_has_frag_list(to) || skb_has_frag_list(from)) return false; + if (skb_zcopy(to) || skb_zcopy(from)) + return false; if (skb_headlen(from) != 0) { struct page *page;