xen-netback: fix guest-receive-side array sizes

The sizes chosen for the metadata and grant_copy_op arrays on the guest
receive size are wrong;

- The meta array is needlessly twice the ring size, when we only ever
  consume a single array element per RX ring slot
- The grant_copy_op array is way too small. It's sized based on a bogus
  assumption: that at most two copy ops will be used per ring slot. This
  may have been true at some point in the past but it's clear from looking
  at start_new_rx_buffer() that a new ring slot is only consumed if a frag
  would overflow the current slot (plus some other conditions) so the actual
  limit is MAX_SKB_FRAGS grant_copy_ops per ring slot.

This patch fixes those two sizing issues and, because grant_copy_ops grows
so much, it pulls it out into a separate chunk of vmalloc()ed memory.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 24 insertions, 7 deletions

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 08ae01b41c83..c47794b9d42f 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -101,6 +101,13 @@ struct xenvif_rx_meta {
 
 #define MAX_PENDING_REQS 256
 
+/* It's possible for an skb to have a maximal number of frags
+ * but still be less than MAX_BUFFER_OFFSET in size. Thus the
+ * worst-case number of copy operations is MAX_SKB_FRAGS per
+ * ring slot.
+ */
+#define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE)
+
 struct xenvif {
         /* Unique identifier for this interface. */
         domid_t          domid;
@@ -143,13 +150,13 @@ struct xenvif {
          */
         RING_IDX rx_req_cons_peek;
 
-        /* Given MAX_BUFFER_OFFSET of 4096 the worst case is that each
-         * head/fragment page uses 2 copy operations because it
-         * straddles two buffers in the frontend.
-         */
-        struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE];
-        struct xenvif_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE];
+        /* This array is allocated seperately as it is large */
+        struct gnttab_copy *grant_copy_op;
 
+        /* We create one meta structure per ring request we consume, so
+         * the maximum number is the same as the ring size.
+         */
+        struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE];
 
         u8               fe_dev_addr[6];
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 870f1fa58370..34ca4e58a43d 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -307,6 +307,15 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
         SET_NETDEV_DEV(dev, parent);
 
         vif = netdev_priv(dev);
+
+        vif->grant_copy_op = vmalloc(sizeof(struct gnttab_copy) *
+                                     MAX_GRANT_COPY_OPS);
+        if (vif->grant_copy_op == NULL) {
+                pr_warn("Could not allocate grant copy space for %s\n", name);
+                free_netdev(dev);
+                return ERR_PTR(-ENOMEM);
+        }
+
         vif->domid  = domid;
         vif->handle = handle;
         vif->can_sg = 1;
@@ -487,6 +496,7 @@ void xenvif_free(struct xenvif *vif)
 
         unregister_netdev(vif->dev);
 
+        vfree(vif->grant_copy_op);
         free_netdev(vif->dev);
 
         module_put(THIS_MODULE);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 7b4fd93be76d..78425554a537 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -608,7 +608,7 @@ void xenvif_rx_action(struct xenvif *vif)
         if (!npo.copy_prod)
                 return;
 
-        BUG_ON(npo.copy_prod > ARRAY_SIZE(vif->grant_copy_op));
+        BUG_ON(npo.copy_prod > MAX_GRANT_COPY_OPS);
         gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod);
 
         while ((skb = __skb_dequeue(&rxq)) != NULL) {