Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Here is my initial pull request for the networking subsystem during
  this merge window:

   1) Support for ESN in AH (RFC 4302) from Fan Du.

   2) Add full kernel doc for ethtool command structures, from Ben
      Hutchings.

   3) Add BCM7xxx PHY driver, from Florian Fainelli.

   4) Export computed TCP rate information in netlink socket dumps, from
      Eric Dumazet.

   5) Allow IPSEC SA to be dumped partially using a filter, from Nicolas
      Dichtel.

   6) Convert many drivers to pci_enable_msix_range(), from Alexander
      Gordeev.

   7) Record SKB timestamps more efficiently, from Eric Dumazet.

   8) Switch to microsecond resolution for TCP round trip times, also
      from Eric Dumazet.

   9) Clean up and fix 6lowpan fragmentation handling by making use of
      the existing inet_frag api for it's implementation.

  10) Add TX grant mapping to xen-netback driver, from Zoltan Kiss.

  11) Auto size SKB lengths when composing netlink messages based upon
      past message sizes used, from Eric Dumazet.

  12) qdisc dumps can take a long time, add a cond_resched(), From Eric
      Dumazet.

  13) Sanitize netpoll core and drivers wrt.  SKB handling semantics.
      Get rid of never-used-in-tree netpoll RX handling.  From Eric W
      Biederman.

  14) Support inter-address-family and namespace changing in VTI tunnel
      driver(s).  From Steffen Klassert.

  15) Add Altera TSE driver, from Vince Bridgers.

  16) Optimizing csum_replace2() so that it doesn't adjust the checksum
      by checksumming the entire header, from Eric Dumazet.

  17) Expand BPF internal implementation for faster interpreting, more
      direct translations into JIT'd code, and much cleaner uses of BPF
      filtering in non-socket ocntexts.  From Daniel Borkmann and Alexei
      Starovoitov"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1976 commits)
  netpoll: Use skb_irq_freeable to make zap_completion_queue safe.
  net: Add a test to see if a skb is freeable in irq context
  qlcnic: Fix build failure due to undefined reference to `vxlan_get_rx_port'
  net: ptp: move PTP classifier in its own file
  net: sxgbe: make "core_ops" static
  net: sxgbe: fix logical vs bitwise operation
  net: sxgbe: sxgbe_mdio_register() frees the bus
  Call efx_set_channels() before efx->type->dimension_resources()
  xen-netback: disable rogue vif in kthread context
  net/mlx4: Set proper build dependancy with vxlan
  be2net: fix build dependency on VxLAN
  mac802154: make csma/cca parameters per-wpan
  mac802154: allow only one WPAN to be up at any given time
  net: filter: minor: fix kdoc in __sk_run_filter
  netlink: don't compare the nul-termination in nla_strcmp
  can: c_can: Avoid led toggling for every packet.
  can: c_can: Simplify TX interrupt cleanup
  can: c_can: Store dlc private
  can: c_can: Reduce register access
  can: c_can: Make the code readable
  ...

1 files changed, 74 insertions, 38 deletions

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index ae413a2cbee7..89d1d0556b6e 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -48,37 +48,19 @@
 typedef unsigned int pending_ring_idx_t;
 #define INVALID_PENDING_RING_IDX (~0U)
 
-/* For the head field in pending_tx_info: it is used to indicate
- * whether this tx info is the head of one or more coalesced requests.
- *
- * When head != INVALID_PENDING_RING_IDX, it means the start of a new
- * tx requests queue and the end of previous queue.
- *
- * An example sequence of head fields (I = INVALID_PENDING_RING_IDX):
- *
- * ...|0 I I I|5 I|9 I I I|...
- * -->|<-INUSE----------------
- *
- * After consuming the first slot(s) we have:
- *
- * ...|V V V V|5 I|9 I I I|...
- * -----FREE->|<-INUSE--------
- *
- * where V stands for "valid pending ring index". Any number other
- * than INVALID_PENDING_RING_IDX is OK. These entries are considered
- * free and can contain any number other than
- * INVALID_PENDING_RING_IDX. In practice we use 0.
- *
- * The in use non-INVALID_PENDING_RING_IDX (say 0, 5 and 9 in the
- * above example) number is the index into pending_tx_info and
- * mmap_pages arrays.
- */
 struct pending_tx_info {
-	struct xen_netif_tx_request req; /* coalesced tx request */
-	pending_ring_idx_t head; /* head != INVALID_PENDING_RING_IDX
-				  * if it is head of one or more tx
-				  * reqs
-				  */
+	struct xen_netif_tx_request req; /* tx request */
+	/* Callback data for released SKBs. The callback is always
+	 * xenvif_zerocopy_callback, desc contains the pending_idx, which is
+	 * also an index in pending_tx_info array. It is initialized in
+	 * xenvif_alloc and it never changes.
+	 * skb_shinfo(skb)->destructor_arg points to the first mapped slot's
+	 * callback_struct in this array of struct pending_tx_info's, then ctx
+	 * to the next, or NULL if there is no more slot for this skb.
+	 * ubuf_to_vif is a helper which finds the struct xenvif from a pointer
+	 * to this field.
+	 */
+	struct ubuf_info callback_struct;
 };
 
 #define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
@@ -99,7 +81,7 @@ struct xenvif_rx_meta {
 
 #define MAX_BUFFER_OFFSET PAGE_SIZE
 
-#define MAX_PENDING_REQS 256
+#define MAX_PENDING_REQS XEN_NETIF_TX_RING_SIZE
 
 /* 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
@@ -108,11 +90,25 @@ struct xenvif_rx_meta {
  */
 #define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE)
 
+#define NETBACK_INVALID_HANDLE -1
+
+/* To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating
+ * the maximum slots a valid packet can use. Now this value is defined
+ * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by
+ * all backend.
+ */
+#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN
+
 struct xenvif {
 	/* Unique identifier for this interface. */
 	domid_t          domid;
 	unsigned int     handle;
 
+	/* Is this interface disabled? True when backend discovers
+	 * frontend is rogue.
+	 */
+	bool disabled;
+
 	/* Use NAPI for guest TX */
 	struct napi_struct napi;
 	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
@@ -126,13 +122,26 @@ struct xenvif {
 	pending_ring_idx_t pending_cons;
 	u16 pending_ring[MAX_PENDING_REQS];
 	struct pending_tx_info pending_tx_info[MAX_PENDING_REQS];
-
-	/* Coalescing tx requests before copying makes number of grant
-	 * copy ops greater or equal to number of slots required. In
-	 * worst case a tx request consumes 2 gnttab_copy.
+	grant_handle_t grant_tx_handle[MAX_PENDING_REQS];
+
+	struct gnttab_map_grant_ref tx_map_ops[MAX_PENDING_REQS];
+	struct gnttab_unmap_grant_ref tx_unmap_ops[MAX_PENDING_REQS];
+	/* passed to gnttab_[un]map_refs with pages under (un)mapping */
+	struct page *pages_to_map[MAX_PENDING_REQS];
+	struct page *pages_to_unmap[MAX_PENDING_REQS];
+
+	/* This prevents zerocopy callbacks  to race over dealloc_ring */
+	spinlock_t callback_lock;
+	/* This prevents dealloc thread and NAPI instance to race over response
+	 * creation and pending_ring in xenvif_idx_release. In xenvif_tx_err
+	 * it only protect response creation
 	 */
-	struct gnttab_copy tx_copy_ops[2*MAX_PENDING_REQS];
-
+	spinlock_t response_lock;
+	pending_ring_idx_t dealloc_prod;
+	pending_ring_idx_t dealloc_cons;
+	u16 dealloc_ring[MAX_PENDING_REQS];
+	struct task_struct *dealloc_task;
+	wait_queue_head_t dealloc_wq;
 
 	/* Use kthread for guest RX */
 	struct task_struct *task;
@@ -144,6 +153,9 @@ struct xenvif {
 	struct xen_netif_rx_back_ring rx;
 	struct sk_buff_head rx_queue;
 	RING_IDX rx_last_skb_slots;
+	bool rx_queue_purge;
+
+	struct timer_list wake_queue;
 
 	/* This array is allocated seperately as it is large */
 	struct gnttab_copy *grant_copy_op;
@@ -175,6 +187,10 @@ struct xenvif {
 
 	/* Statistics */
 	unsigned long rx_gso_checksum_fixup;
+	unsigned long tx_zerocopy_sent;
+	unsigned long tx_zerocopy_success;
+	unsigned long tx_zerocopy_fail;
+	unsigned long tx_frag_overflow;
 
 	/* Miscellaneous private stuff. */
 	struct net_device *dev;
@@ -216,9 +232,11 @@ void xenvif_carrier_off(struct xenvif *vif);
 
 int xenvif_tx_action(struct xenvif *vif, int budget);
 
-int xenvif_kthread(void *data);
+int xenvif_kthread_guest_rx(void *data);
 void xenvif_kick_thread(struct xenvif *vif);
 
+int xenvif_dealloc_kthread(void *data);
+
 /* Determine whether the needed number of slots (req) are available,
  * and set req_event if not.
  */
@@ -226,6 +244,24 @@ bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed);
 
 void xenvif_stop_queue(struct xenvif *vif);
 
+/* Callback from stack when TX packet can be released */
+void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);
+
+/* Unmap a pending page and release it back to the guest */
+void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx);
+
+static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif)
+{
+	return MAX_PENDING_REQS -
+		vif->pending_prod + vif->pending_cons;
+}
+
+/* Callback from stack when TX packet can be released */
+void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);
+
 extern bool separate_tx_rx_irq;
 
+extern unsigned int rx_drain_timeout_msecs;
+extern unsigned int rx_drain_timeout_jiffies;
+
 #endif /* __XEN_NETBACK__COMMON_H__ */