Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753368AbaATVY7 (ORCPT ); Mon, 20 Jan 2014 16:24:59 -0500 Received: from smtp02.citrix.com ([66.165.176.63]:45710 "EHLO SMTP02.CITRIX.COM" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752864AbaATVYx (ORCPT ); Mon, 20 Jan 2014 16:24:53 -0500 X-IronPort-AV: E=Sophos;i="4.95,692,1384300800"; d="scan'208";a="92595820" From: Zoltan Kiss To: , , , , , CC: Zoltan Kiss Subject: [PATCH net-next v5 6/9] xen-netback: Handle guests with too many frags Date: Mon, 20 Jan 2014 21:24:26 +0000 Message-ID: <1390253069-25507-7-git-send-email-zoltan.kiss@citrix.com> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1390253069-25507-1-git-send-email-zoltan.kiss@citrix.com> References: <1390253069-25507-1-git-send-email-zoltan.kiss@citrix.com> MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.80.2.133] X-DLP: MIA1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Xen network protocol had implicit dependency on MAX_SKB_FRAGS. Netback has to handle guests sending up to XEN_NETBK_LEGACY_SLOTS_MAX slots. To achieve that: - create a new skb - map the leftover slots to its frags (no linear buffer here!) - chain it to the previous through skb_shinfo(skb)->frag_list - map them - copy the whole stuff into a brand new skb and send it to the stack - unmap the 2 old skb's pages v3: - adding extra check for frag number - consolidate alloc_skb's into xenvif_alloc_skb() - BUG_ON(frag_overflow > MAX_SKB_FRAGS) v4: - handle error of skb_copy_expand() v5: - ratelimit error messages - remove a tx_flags setting from xenvif_tx_submit Signed-off-by: Zoltan Kiss --- drivers/net/xen-netback/netback.c | 124 ++++++++++++++++++++++++++++++++++--- 1 file changed, 114 insertions(+), 10 deletions(-) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 22d05de..031258c 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -803,6 +803,20 @@ static inline void xenvif_tx_create_gop(struct xenvif *vif, sizeof(*txp)); } +static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) +{ + struct sk_buff *skb = + alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(skb == NULL)) + return NULL; + + /* Packets passed to netif_rx() must have some headroom. */ + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); + + return skb; +} + static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, struct sk_buff *skb, struct xen_netif_tx_request *txp, @@ -813,11 +827,16 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, u16 pending_idx = *((u16 *)skb->data); int start; pending_ring_idx_t index; - unsigned int nr_slots; + unsigned int nr_slots, frag_overflow = 0; /* At this point shinfo->nr_frags is in fact the number of * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX. */ + if (shinfo->nr_frags > MAX_SKB_FRAGS) { + frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS; + BUG_ON(frag_overflow > MAX_SKB_FRAGS); + shinfo->nr_frags = MAX_SKB_FRAGS; + } nr_slots = shinfo->nr_frags; /* Skip first skb fragment if it is on same page as header fragment. */ @@ -833,6 +852,30 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, BUG_ON(shinfo->nr_frags > MAX_SKB_FRAGS); + if (frag_overflow) { + struct sk_buff *nskb = xenvif_alloc_skb(0); + if (unlikely(nskb == NULL)) { + if (net_ratelimit()) + netdev_err(vif->dev, + "Can't allocate the frag_list skb.\n"); + return NULL; + } + + shinfo = skb_shinfo(nskb); + frags = shinfo->frags; + + for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow; + shinfo->nr_frags++, txp++, gop++) { + index = pending_index(vif->pending_cons++); + pending_idx = vif->pending_ring[index]; + xenvif_tx_create_gop(vif, pending_idx, txp, gop); + frag_set_pending_idx(&frags[shinfo->nr_frags], + pending_idx); + } + + skb_shinfo(skb)->frag_list = nskb; + } + return gop; } @@ -846,6 +889,7 @@ static int xenvif_tx_check_gop(struct xenvif *vif, struct pending_tx_info *tx_info; int nr_frags = shinfo->nr_frags; int i, err, start; + struct sk_buff *first_skb = NULL; /* Check status of header. */ err = gop->status; @@ -866,6 +910,7 @@ static int xenvif_tx_check_gop(struct xenvif *vif, /* Skip first skb fragment if it is on same page as header fragment. */ start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); +check_frags: for (i = start; i < nr_frags; i++) { int j, newerr; @@ -900,11 +945,20 @@ static int xenvif_tx_check_gop(struct xenvif *vif, /* Not the first error? Preceding frags already invalidated. */ if (err) continue; - /* First error: invalidate header and preceding fragments. */ - pending_idx = *((u16 *)skb->data); - xenvif_idx_unmap(vif, pending_idx); - xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); + if (!first_skb) { + pending_idx = *((u16 *)skb->data); + xenvif_idx_unmap(vif, pending_idx); + xenvif_idx_release(vif, + pending_idx, + XEN_NETIF_RSP_OKAY); + } else { + pending_idx = *((u16 *)first_skb->data); + xenvif_idx_unmap(vif, pending_idx); + xenvif_idx_release(vif, + pending_idx, + XEN_NETIF_RSP_OKAY); + } for (j = start; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); xenvif_idx_unmap(vif, pending_idx); @@ -916,6 +970,32 @@ static int xenvif_tx_check_gop(struct xenvif *vif, err = newerr; } + if (shinfo->frag_list) { + first_skb = skb; + skb = shinfo->frag_list; + shinfo = skb_shinfo(skb); + nr_frags = shinfo->nr_frags; + start = 0; + + goto check_frags; + } + + /* There was a mapping error in the frag_list skb. We have to unmap + * the first skb's frags + */ + if (first_skb && err) { + int j; + shinfo = skb_shinfo(first_skb); + pending_idx = *((u16 *)first_skb->data); + start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); + for (j = start; j < shinfo->nr_frags; j++) { + pending_idx = frag_get_pending_idx(&shinfo->frags[j]); + xenvif_idx_unmap(vif, pending_idx); + xenvif_idx_release(vif, pending_idx, + XEN_NETIF_RSP_OKAY); + } + } + *gopp = gop + 1; return err; } @@ -1419,8 +1499,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) ret < XEN_NETBK_LEGACY_SLOTS_MAX) ? PKT_PROT_LEN : txreq.size; - skb = alloc_skb(data_len + NET_SKB_PAD + NET_IP_ALIGN, - GFP_ATOMIC | __GFP_NOWARN); + skb = xenvif_alloc_skb(data_len); if (unlikely(skb == NULL)) { netdev_dbg(vif->dev, "Can't allocate a skb in start_xmit.\n"); @@ -1428,9 +1507,6 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) break; } - /* Packets passed to netif_rx() must have some headroom. */ - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) { struct xen_netif_extra_info *gso; gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; @@ -1492,6 +1568,7 @@ static int xenvif_tx_submit(struct xenvif *vif) struct xen_netif_tx_request *txp; u16 pending_idx; unsigned data_len; + struct sk_buff *nskb = NULL; pending_idx = *((u16 *)skb->data); txp = &vif->pending_tx_info[pending_idx].req; @@ -1534,6 +1611,30 @@ static int xenvif_tx_submit(struct xenvif *vif) pending_idx : INVALID_PENDING_IDX); + if (skb_shinfo(skb)->frag_list) { + nskb = skb_shinfo(skb)->frag_list; + xenvif_fill_frags(vif, nskb, INVALID_PENDING_IDX); + skb->len += nskb->len; + skb->data_len += nskb->len; + skb->truesize += nskb->truesize; + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + skb_shinfo(nskb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + vif->tx_zerocopy_sent += 2; + nskb = skb; + + skb = skb_copy_expand(skb, + 0, + 0, + GFP_ATOMIC | __GFP_NOWARN); + if (!skb) { + if (net_ratelimit()) + netdev_dbg(vif->dev, + "Can't consolidate skb with too many fragments\n"); + kfree_skb(nskb); + continue; + } + skb_shinfo(skb)->destructor_arg = NULL; + } if (skb_is_nonlinear(skb) && skb_headlen(skb) < PKT_PROT_LEN) { int target = min_t(int, skb->len, PKT_PROT_LEN); __pskb_pull_tail(skb, target - skb_headlen(skb)); @@ -1587,6 +1688,9 @@ static int xenvif_tx_submit(struct xenvif *vif) } netif_receive_skb(skb); + + if (nskb) + kfree_skb(nskb); } return work_done; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/