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

Pull networking updates from David Miller:

 1) BPF debugger and asm tool by Daniel Borkmann.

 2) Speed up create/bind in AF_PACKET, also from Daniel Borkmann.

 3) Correct reciprocal_divide and update users, from Hannes Frederic
    Sowa and Daniel Borkmann.

 4) Currently we only have a "set" operation for the hw timestamp socket
    ioctl, add a "get" operation to match.  From Ben Hutchings.

 5) Add better trace events for debugging driver datapath problems, also
    from Ben Hutchings.

 6) Implement auto corking in TCP, from Eric Dumazet.  Basically, if we
    have a small send and a previous packet is already in the qdisc or
    device queue, defer until TX completion or we get more data.

 7) Allow userspace to manage ipv6 temporary addresses, from Jiri Pirko.

 8) Add a qdisc bypass option for AF_PACKET sockets, from Daniel
    Borkmann.

 9) Share IP header compression code between Bluetooth and IEEE802154
    layers, from Jukka Rissanen.

10) Fix ipv6 router reachability probing, from Jiri Benc.

11) Allow packets to be captured on macvtap devices, from Vlad Yasevich.

12) Support tunneling in GRO layer, from Jerry Chu.

13) Allow bonding to be configured fully using netlink, from Scott
    Feldman.

14) Allow AF_PACKET users to obtain the VLAN TPID, just like they can
    already get the TCI.  From Atzm Watanabe.

15) New "Heavy Hitter" qdisc, from Terry Lam.

16) Significantly improve the IPSEC support in pktgen, from Fan Du.

17) Allow ipv4 tunnels to cache routes, just like sockets.  From Tom
    Herbert.

18) Add Proportional Integral Enhanced packet scheduler, from Vijay
    Subramanian.

19) Allow openvswitch to mmap'd netlink, from Thomas Graf.

20) Key TCP metrics blobs also by source address, not just destination
    address.  From Christoph Paasch.

21) Support 10G in generic phylib.  From Andy Fleming.

22) Try to short-circuit GRO flow compares using device provided RX
    hash, if provided.  From Tom Herbert.

The wireless and netfilter folks have been busy little bees too.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2064 commits)
  net/cxgb4: Fix referencing freed adapter
  ipv6: reallocate addrconf router for ipv6 address when lo device up
  fib_frontend: fix possible NULL pointer dereference
  rtnetlink: remove IFLA_BOND_SLAVE definition
  rtnetlink: remove check for fill_slave_info in rtnl_have_link_slave_info
  qlcnic: update version to 5.3.55
  qlcnic: Enhance logic to calculate msix vectors.
  qlcnic: Refactor interrupt coalescing code for all adapters.
  qlcnic: Update poll controller code path
  qlcnic: Interrupt code cleanup
  qlcnic: Enhance Tx timeout debugging.
  qlcnic: Use bool for rx_mac_learn.
  bonding: fix u64 division
  rtnetlink: add missing IFLA_BOND_AD_INFO_UNSPEC
  sfc: Use the correct maximum TX DMA ring size for SFC9100
  Add Shradha Shah as the sfc driver maintainer.
  net/vxlan: Share RX skb de-marking and checksum checks with ovs
  tulip: cleanup by using ARRAY_SIZE()
  ip_tunnel: clear IPCB in ip_tunnel_xmit() in case dst_link_failure() is called
  net/cxgb4: Don't retrieve stats during recovery
  ...

1 files changed, 54 insertions, 21 deletions

diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 542a0d252ae0..af2b8c59a903 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -91,6 +91,7 @@
 
 /* Forward declare Precision Time Protocol (PTP) support structure. */
 struct efx_ptp_data;
+struct hwtstamp_config;
 
 struct efx_self_tests;
 
@@ -287,12 +288,9 @@ struct efx_rx_buffer {
  * Used to facilitate sharing dma mappings between recycled rx buffers
  * and those passed up to the kernel.
  *
- * @refcnt: Number of struct efx_rx_buffer's referencing this page.
- *	When refcnt falls to zero, the page is unmapped for dma
  * @dma_addr: The dma address of this page.
  */
 struct efx_rx_page_state {
-	unsigned refcnt;
 	dma_addr_t dma_addr;
 
 	unsigned int __pad[0] ____cacheline_aligned;
@@ -362,10 +360,11 @@ struct efx_rx_queue {
 	unsigned int slow_fill_count;
 };
 
-enum efx_rx_alloc_method {
-	RX_ALLOC_METHOD_AUTO = 0,
-	RX_ALLOC_METHOD_SKB = 1,
-	RX_ALLOC_METHOD_PAGE = 2,
+enum efx_sync_events_state {
+	SYNC_EVENTS_DISABLED = 0,
+	SYNC_EVENTS_QUIESCENT,
+	SYNC_EVENTS_REQUESTED,
+	SYNC_EVENTS_VALID,
 };
 
 /**
@@ -407,6 +406,9 @@ enum efx_rx_alloc_method {
  *	by __efx_rx_packet(), if @rx_pkt_n_frags != 0
  * @rx_queue: RX queue for this channel
  * @tx_queue: TX queues for this channel
+ * @sync_events_state: Current state of sync events on this channel
+ * @sync_timestamp_major: Major part of the last ptp sync event
+ * @sync_timestamp_minor: Minor part of the last ptp sync event
  */
 struct efx_channel {
 	struct efx_nic *efx;
@@ -445,6 +447,10 @@ struct efx_channel {
 
 	struct efx_rx_queue rx_queue;
 	struct efx_tx_queue tx_queue[EFX_TXQ_TYPES];
+
+	enum efx_sync_events_state sync_events_state;
+	u32 sync_timestamp_major;
+	u32 sync_timestamp_minor;
 };
 
 /**
@@ -520,15 +526,6 @@ enum nic_state {
 	STATE_RECOVERY = 3,	/* device recovering from PCI error */
 };
 
-/*
- * Alignment of the skb->head which wraps a page-allocated RX buffer
- *
- * The skb allocated to wrap an rx_buffer can have this alignment. Since
- * the data is memcpy'd from the rx_buf, it does not need to be equal to
- * NET_IP_ALIGN.
- */
-#define EFX_PAGE_SKB_ALIGN 2
-
 /* Forward declaration */
 struct efx_nic;
 
@@ -651,6 +648,13 @@ struct vfdi_status;
  * struct efx_nic - an Efx NIC
  * @name: Device name (net device name or bus id before net device registered)
  * @pci_dev: The PCI device
+ * @node: List node for maintaning primary/secondary function lists
+ * @primary: &struct efx_nic instance for the primary function of this
+ *	controller.  May be the same structure, and may be %NULL if no
+ *	primary function is bound.  Serialised by rtnl_lock.
+ * @secondary_list: List of &struct efx_nic instances for the secondary PCI
+ *	functions of the controller, if this is for the primary function.
+ *	Serialised by rtnl_lock.
  * @type: Controller type attributes
  * @legacy_irq: IRQ number
  * @workqueue: Workqueue for port reconfigures and the HW monitor.
@@ -694,6 +698,8 @@ struct vfdi_status;
  *	(valid only if @rx_prefix_size != 0; always negative)
  * @rx_packet_len_offset: Offset of RX packet length from start of packet data
  *	(valid only for NICs that set %EFX_RX_PKT_PREFIX_LEN; always negative)
+ * @rx_packet_ts_offset: Offset of timestamp from start of packet data
+ *	(valid only if channel->sync_timestamps_enabled; always negative)
  * @rx_hash_key: Toeplitz hash key for RSS
  * @rx_indir_table: Indirection table for RSS
  * @rx_scatter: Scatter mode enabled for receives
@@ -763,6 +769,7 @@ struct vfdi_status;
  * @local_lock: Mutex protecting %local_addr_list and %local_page_list.
  * @peer_work: Work item to broadcast peer addresses to VMs.
  * @ptp_data: PTP state data
+ * @vpd_sn: Serial number read from VPD
  * @monitor_work: Hardware monitor workitem
  * @biu_lock: BIU (bus interface unit) lock
  * @last_irq_cpu: Last CPU to handle a possible test interrupt.  This
@@ -777,6 +784,9 @@ struct efx_nic {
 	/* The following fields should be written very rarely */
 
 	char name[IFNAMSIZ];
+	struct list_head node;
+	struct efx_nic *primary;
+	struct list_head secondary_list;
 	struct pci_dev *pci_dev;
 	unsigned int port_num;
 	const struct efx_nic_type *type;
@@ -828,6 +838,7 @@ struct efx_nic {
 	unsigned int rx_prefix_size;
 	int rx_packet_hash_offset;
 	int rx_packet_len_offset;
+	int rx_packet_ts_offset;
 	u8 rx_hash_key[40];
 	u32 rx_indir_table[128];
 	bool rx_scatter;
@@ -852,10 +863,14 @@ struct efx_nic {
 	struct work_struct mac_work;
 	bool port_enabled;
 
+	bool mc_bist_for_other_fn;
 	bool port_initialized;
 	struct net_device *net_dev;
 
 	struct efx_buffer stats_buffer;
+	u64 rx_nodesc_drops_total;
+	u64 rx_nodesc_drops_while_down;
+	bool rx_nodesc_drops_prev_state;
 
 	unsigned int phy_type;
 	const struct efx_phy_operations *phy_op;
@@ -907,6 +922,8 @@ struct efx_nic {
 
 	struct efx_ptp_data *ptp_data;
 
+	char *vpd_sn;
+
 	/* The following fields may be written more often */
 
 	struct delayed_work monitor_work ____cacheline_aligned_in_smp;
@@ -959,6 +976,7 @@ struct efx_mtd_partition {
  * @update_stats: Update statistics not provided by event handling.
  *	Either argument may be %NULL.
  * @start_stats: Start the regular fetching of statistics
+ * @pull_stats: Pull stats from the NIC and wait until they arrive.
  * @stop_stats: Stop the regular fetching of statistics
  * @set_id_led: Set state of identifying LED or revert to automatic function
  * @push_irq_moderation: Apply interrupt moderation value
@@ -997,7 +1015,7 @@ struct efx_mtd_partition {
  * @tx_init: Initialise TX queue on the NIC
  * @tx_remove: Free resources for TX queue
  * @tx_write: Write TX descriptors and doorbell
- * @rx_push_indir_table: Write RSS indirection table to the NIC
+ * @rx_push_rss_config: Write RSS hash key and indirection table to the NIC
  * @rx_probe: Allocate resources for RX queue
  * @rx_init: Initialise RX queue on the NIC
  * @rx_remove: Free resources for RX queue
@@ -1017,7 +1035,8 @@ struct efx_mtd_partition {
  * @filter_insert: add or replace a filter
  * @filter_remove_safe: remove a filter by ID, carefully
  * @filter_get_safe: retrieve a filter by ID, carefully
- * @filter_clear_rx: remove RX filters by priority
+ * @filter_clear_rx: Remove all RX filters whose priority is less than or
+ *	equal to the given priority and is not %EFX_FILTER_PRI_AUTO
  * @filter_count_rx_used: Get the number of filters in use at a given priority
  * @filter_get_rx_id_limit: Get maximum value of a filter id, plus 1
  * @filter_get_rx_ids: Get list of RX filters at a given priority
@@ -1037,6 +1056,12 @@ struct efx_mtd_partition {
  * @mtd_sync: Wait for write-back to complete on MTD partition.  This
  *	also notifies the driver that a writer has finished using this
  *	partition.
+ * @ptp_write_host_time: Send host time to MC as part of sync protocol
+ * @ptp_set_ts_sync_events: Enable or disable sync events for inline RX
+ *	timestamping, possibly only temporarily for the purposes of a reset.
+ * @ptp_set_ts_config: Set hardware timestamp configuration.  The flags
+ *	and tx_type will already have been validated but this operation
+ *	must validate and update rx_filter.
  * @revision: Hardware architecture revision
  * @txd_ptr_tbl_base: TX descriptor ring base address
  * @rxd_ptr_tbl_base: RX descriptor ring base address
@@ -1046,6 +1071,7 @@ struct efx_mtd_partition {
  * @max_dma_mask: Maximum possible DMA mask
  * @rx_prefix_size: Size of RX prefix before packet data
  * @rx_hash_offset: Offset of RX flow hash within prefix
+ * @rx_ts_offset: Offset of timestamp within prefix
  * @rx_buffer_padding: Size of padding at end of RX packet
  * @can_rx_scatter: NIC is able to scatter packets to multiple buffers
  * @always_rx_scatter: NIC will always scatter packets to multiple buffers
@@ -1055,6 +1081,7 @@ struct efx_mtd_partition {
  * @offload_features: net_device feature flags for protocol offload
  *	features implemented in hardware
  * @mcdi_max_ver: Maximum MCDI version supported
+ * @hwtstamp_filters: Mask of hardware timestamp filter types supported
  */
 struct efx_nic_type {
 	unsigned int (*mem_map_size)(struct efx_nic *efx);
@@ -1077,6 +1104,7 @@ struct efx_nic_type {
 	size_t (*update_stats)(struct efx_nic *efx, u64 *full_stats,
 			       struct rtnl_link_stats64 *core_stats);
 	void (*start_stats)(struct efx_nic *efx);
+	void (*pull_stats)(struct efx_nic *efx);
 	void (*stop_stats)(struct efx_nic *efx);
 	void (*set_id_led)(struct efx_nic *efx, enum efx_led_mode mode);
 	void (*push_irq_moderation)(struct efx_channel *channel);
@@ -1105,7 +1133,7 @@ struct efx_nic_type {
 	void (*tx_init)(struct efx_tx_queue *tx_queue);
 	void (*tx_remove)(struct efx_tx_queue *tx_queue);
 	void (*tx_write)(struct efx_tx_queue *tx_queue);
-	void (*rx_push_indir_table)(struct efx_nic *efx);
+	void (*rx_push_rss_config)(struct efx_nic *efx);
 	int (*rx_probe)(struct efx_rx_queue *rx_queue);
 	void (*rx_init)(struct efx_rx_queue *rx_queue);
 	void (*rx_remove)(struct efx_rx_queue *rx_queue);
@@ -1130,8 +1158,8 @@ struct efx_nic_type {
 	int (*filter_get_safe)(struct efx_nic *efx,
 			       enum efx_filter_priority priority,
 			       u32 filter_id, struct efx_filter_spec *);
-	void (*filter_clear_rx)(struct efx_nic *efx,
-				enum efx_filter_priority priority);
+	int (*filter_clear_rx)(struct efx_nic *efx,
+			       enum efx_filter_priority priority);
 	u32 (*filter_count_rx_used)(struct efx_nic *efx,
 				    enum efx_filter_priority priority);
 	u32 (*filter_get_rx_id_limit)(struct efx_nic *efx);
@@ -1155,6 +1183,9 @@ struct efx_nic_type {
 	int (*mtd_sync)(struct mtd_info *mtd);
 #endif
 	void (*ptp_write_host_time)(struct efx_nic *efx, u32 host_time);
+	int (*ptp_set_ts_sync_events)(struct efx_nic *efx, bool en, bool temp);
+	int (*ptp_set_ts_config)(struct efx_nic *efx,
+				 struct hwtstamp_config *init);
 
 	int revision;
 	unsigned int txd_ptr_tbl_base;
@@ -1165,6 +1196,7 @@ struct efx_nic_type {
 	u64 max_dma_mask;
 	unsigned int rx_prefix_size;
 	unsigned int rx_hash_offset;
+	unsigned int rx_ts_offset;
 	unsigned int rx_buffer_padding;
 	bool can_rx_scatter;
 	bool always_rx_scatter;
@@ -1173,6 +1205,7 @@ struct efx_nic_type {
 	netdev_features_t offload_features;
 	int mcdi_max_ver;
 	unsigned int max_rx_ip_filters;
+	u32 hwtstamp_filters;
 };
 
 /**************************************************************************