1 files changed, 37 insertions, 127 deletions

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 6563f0713fc0..7dc2d64db3cb 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -60,14 +60,12 @@ module_param(separate_tx_rx_irq, bool, 0644);
  */
 unsigned int rx_drain_timeout_msecs = 10000;
 module_param(rx_drain_timeout_msecs, uint, 0444);
-unsigned int rx_drain_timeout_jiffies;
 
 /* The length of time before the frontend is considered unresponsive
  * because it isn't providing Rx slots.
  */
-static unsigned int rx_stall_timeout_msecs = 60000;
+unsigned int rx_stall_timeout_msecs = 60000;
 module_param(rx_stall_timeout_msecs, uint, 0444);
-static unsigned int rx_stall_timeout_jiffies;
 
 unsigned int xenvif_max_queues;
 module_param_named(max_queues, xenvif_max_queues, uint, 0644);
@@ -82,6 +80,16 @@ MODULE_PARM_DESC(max_queues,
 static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT;
 module_param(fatal_skb_slots, uint, 0444);
 
+/* The amount to copy out of the first guest Tx slot into the skb's
+ * linear area.  If the first slot has more data, it will be mapped
+ * and put into the first frag.
+ *
+ * This is sized to avoid pulling headers from the frags for most
+ * TCP/IP packets.
+ */
+#define XEN_NETBACK_TX_COPY_LEN 128
+
+
 static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 			       u8 status);
 
@@ -125,13 +133,6 @@ static inline struct xenvif_queue *ubuf_to_queue(const struct ubuf_info *ubuf)
 			    pending_tx_info[0]);
 }
 
-/* This is a miniumum size for the linear area to avoid lots of
- * calls to __pskb_pull_tail() as we set up checksum offsets. The
- * value 128 was chosen as it covers all IPv4 and most likely
- * IPv6 headers.
- */
-#define PKT_PROT_LEN 128
-
 static u16 frag_get_pending_idx(skb_frag_t *frag)
 {
 	return (u16)frag->page_offset;
@@ -313,9 +314,7 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue,
 static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb,
 				 struct netrx_pending_operations *npo,
 				 struct page *page, unsigned long size,
-				 unsigned long offset, int *head,
-				 struct xenvif_queue *foreign_queue,
-				 grant_ref_t foreign_gref)
+				 unsigned long offset, int *head)
 {
 	struct gnttab_copy *copy_gop;
 	struct xenvif_rx_meta *meta;
@@ -332,6 +331,8 @@ static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb
 	offset &= ~PAGE_MASK;
 
 	while (size > 0) {
+		struct xen_page_foreign *foreign;
+
 		BUG_ON(offset >= PAGE_SIZE);
 		BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET);
 
@@ -360,9 +361,10 @@ static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb
 		copy_gop->flags = GNTCOPY_dest_gref;
 		copy_gop->len = bytes;
 
-		if (foreign_queue) {
-			copy_gop->source.domid = foreign_queue->vif->domid;
-			copy_gop->source.u.ref = foreign_gref;
+		foreign = xen_page_foreign(page);
+		if (foreign) {
+			copy_gop->source.domid = foreign->domid;
+			copy_gop->source.u.ref = foreign->gref;
 			copy_gop->flags |= GNTCOPY_source_gref;
 		} else {
 			copy_gop->source.domid = DOMID_SELF;
@@ -405,35 +407,6 @@ static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb
 }
 
 /*
- * Find the grant ref for a given frag in a chain of struct ubuf_info's
- * skb: the skb itself
- * i: the frag's number
- * ubuf: a pointer to an element in the chain. It should not be NULL
- *
- * Returns a pointer to the element in the chain where the page were found. If
- * not found, returns NULL.
- * See the definition of callback_struct in common.h for more details about
- * the chain.
- */
-static const struct ubuf_info *xenvif_find_gref(const struct sk_buff *const skb,
-						const int i,
-						const struct ubuf_info *ubuf)
-{
-	struct xenvif_queue *foreign_queue = ubuf_to_queue(ubuf);
-
-	do {
-		u16 pending_idx = ubuf->desc;
-
-		if (skb_shinfo(skb)->frags[i].page.p ==
-		    foreign_queue->mmap_pages[pending_idx])
-			break;
-		ubuf = (struct ubuf_info *) ubuf->ctx;
-	} while (ubuf);
-
-	return ubuf;
-}
-
-/*
  * Prepare an SKB to be transmitted to the frontend.
  *
  * This function is responsible for allocating grant operations, meta
@@ -458,8 +431,6 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 	int head = 1;
 	int old_meta_prod;
 	int gso_type;
-	const struct ubuf_info *ubuf = skb_shinfo(skb)->destructor_arg;
-	const struct ubuf_info *const head_ubuf = ubuf;
 
 	old_meta_prod = npo->meta_prod;
 
@@ -506,68 +477,16 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 			len = skb_tail_pointer(skb) - data;
 
 		xenvif_gop_frag_copy(queue, skb, npo,
-				     virt_to_page(data), len, offset, &head,
-				     NULL,
-				     0);
+				     virt_to_page(data), len, offset, &head);
 		data += len;
 	}
 
 	for (i = 0; i < nr_frags; i++) {
-		/* This variable also signals whether foreign_gref has a real
-		 * value or not.
-		 */
-		struct xenvif_queue *foreign_queue = NULL;
-		grant_ref_t foreign_gref;
-
-		if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) &&
-			(ubuf->callback == &xenvif_zerocopy_callback)) {
-			const struct ubuf_info *const startpoint = ubuf;
-
-			/* Ideally ubuf points to the chain element which
-			 * belongs to this frag. Or if frags were removed from
-			 * the beginning, then shortly before it.
-			 */
-			ubuf = xenvif_find_gref(skb, i, ubuf);
-
-			/* Try again from the beginning of the list, if we
-			 * haven't tried from there. This only makes sense in
-			 * the unlikely event of reordering the original frags.
-			 * For injected local pages it's an unnecessary second
-			 * run.
-			 */
-			if (unlikely(!ubuf) && startpoint != head_ubuf)
-				ubuf = xenvif_find_gref(skb, i, head_ubuf);
-
-			if (likely(ubuf)) {
-				u16 pending_idx = ubuf->desc;
-
-				foreign_queue = ubuf_to_queue(ubuf);
-				foreign_gref =
-					foreign_queue->pending_tx_info[pending_idx].req.gref;
-				/* Just a safety measure. If this was the last
-				 * element on the list, the for loop will
-				 * iterate again if a local page were added to
-				 * the end. Using head_ubuf here prevents the
-				 * second search on the chain. Or the original
-				 * frags changed order, but that's less likely.
-				 * In any way, ubuf shouldn't be NULL.
-				 */
-				ubuf = ubuf->ctx ?
-					(struct ubuf_info *) ubuf->ctx :
-					head_ubuf;
-			} else
-				/* This frag was a local page, added to the
-				 * array after the skb left netback.
-				 */
-				ubuf = head_ubuf;
-		}
 		xenvif_gop_frag_copy(queue, skb, npo,
 				     skb_frag_page(&skb_shinfo(skb)->frags[i]),
 				     skb_frag_size(&skb_shinfo(skb)->frags[i]),
 				     skb_shinfo(skb)->frags[i].page_offset,
-				     &head,
-				     foreign_queue,
-				     foreign_queue ? foreign_gref : UINT_MAX);
+				     &head);
 	}
 
 	return npo->meta_prod - old_meta_prod;
@@ -1240,12 +1159,6 @@ static void xenvif_fill_frags(struct xenvif_queue *queue, struct sk_buff *skb)
 		/* Take an extra reference to offset network stack's put_page */
 		get_page(queue->mmap_pages[pending_idx]);
 	}
-	/* FIXME: __skb_fill_page_desc set this to true because page->pfmemalloc
-	 * overlaps with "index", and "mapping" is not set. I think mapping
-	 * should be set. If delivered to local stack, it would drop this
-	 * skb in sk_filter unless the socket has the right to use it.
-	 */
-	skb->pfmemalloc	= false;
 }
 
 static int xenvif_get_extras(struct xenvif_queue *queue,
@@ -1446,9 +1359,9 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 		index = pending_index(queue->pending_cons);
 		pending_idx = queue->pending_ring[index];
 
-		data_len = (txreq.size > PKT_PROT_LEN &&
+		data_len = (txreq.size > XEN_NETBACK_TX_COPY_LEN &&
 			    ret < XEN_NETBK_LEGACY_SLOTS_MAX) ?
-			PKT_PROT_LEN : txreq.size;
+			XEN_NETBACK_TX_COPY_LEN : txreq.size;
 
 		skb = xenvif_alloc_skb(data_len);
 		if (unlikely(skb == NULL)) {
@@ -1550,7 +1463,7 @@ static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *s
 		unsigned int len;
 
 		BUG_ON(i >= MAX_SKB_FRAGS);
-		page = alloc_page(GFP_ATOMIC|__GFP_COLD);
+		page = alloc_page(GFP_ATOMIC);
 		if (!page) {
 			int j;
 			skb->truesize += skb->data_len;
@@ -1653,11 +1566,6 @@ static int xenvif_tx_submit(struct xenvif_queue *queue)
 			}
 		}
 
-		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));
-		}
-
 		skb->dev      = queue->vif->dev;
 		skb->protocol = eth_type_trans(skb, skb->dev);
 		skb_reset_network_header(skb);
@@ -2022,7 +1930,7 @@ static bool xenvif_rx_queue_stalled(struct xenvif_queue *queue)
 	return !queue->stalled
 		&& prod - cons < XEN_NETBK_RX_SLOTS_MAX
 		&& time_after(jiffies,
-			      queue->last_rx_time + rx_stall_timeout_jiffies);
+			      queue->last_rx_time + queue->vif->stall_timeout);
 }
 
 static bool xenvif_rx_queue_ready(struct xenvif_queue *queue)
@@ -2040,8 +1948,9 @@ static bool xenvif_have_rx_work(struct xenvif_queue *queue)
 {
 	return (!skb_queue_empty(&queue->rx_queue)
 		&& xenvif_rx_ring_slots_available(queue, XEN_NETBK_RX_SLOTS_MAX))
-		|| xenvif_rx_queue_stalled(queue)
-		|| xenvif_rx_queue_ready(queue)
+		|| (queue->vif->stall_timeout &&
+		    (xenvif_rx_queue_stalled(queue)
+		     || xenvif_rx_queue_ready(queue)))
 		|| kthread_should_stop()
 		|| queue->vif->disabled;
 }
@@ -2094,6 +2003,9 @@ int xenvif_kthread_guest_rx(void *data)
 	struct xenvif_queue *queue = data;
 	struct xenvif *vif = queue->vif;
 
+	if (!vif->stall_timeout)
+		xenvif_queue_carrier_on(queue);
+
 	for (;;) {
 		xenvif_wait_for_rx_work(queue);
 
@@ -2109,8 +2021,7 @@ int xenvif_kthread_guest_rx(void *data)
 		 */
 		if (unlikely(vif->disabled && queue->id == 0)) {
 			xenvif_carrier_off(vif);
-			xenvif_rx_queue_purge(queue);
-			continue;
+			break;
 		}
 
 		if (!skb_queue_empty(&queue->rx_queue))
@@ -2120,10 +2031,12 @@ int xenvif_kthread_guest_rx(void *data)
 		 * while it's probably not responsive, drop the
 		 * carrier so packets are dropped earlier.
 		 */
-		if (xenvif_rx_queue_stalled(queue))
-			xenvif_queue_carrier_off(queue);
-		else if (xenvif_rx_queue_ready(queue))
-			xenvif_queue_carrier_on(queue);
+		if (vif->stall_timeout) {
+			if (xenvif_rx_queue_stalled(queue))
+				xenvif_queue_carrier_off(queue);
+			else if (xenvif_rx_queue_ready(queue))
+				xenvif_queue_carrier_on(queue);
+		}
 
 		/* Queued packets may have foreign pages from other
 		 * domains.  These cannot be queued indefinitely as
@@ -2194,9 +2107,6 @@ static int __init netback_init(void)
 	if (rc)
 		goto failed_init;
 
-	rx_drain_timeout_jiffies = msecs_to_jiffies(rx_drain_timeout_msecs);
-	rx_stall_timeout_jiffies = msecs_to_jiffies(rx_stall_timeout_msecs);
-
 #ifdef CONFIG_DEBUG_FS
 	xen_netback_dbg_root = debugfs_create_dir("xen-netback", NULL);
 	if (IS_ERR_OR_NULL(xen_netback_dbg_root))