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

Pull networking changes from David Miller:

 1) GRE now works over ipv6, from Dmitry Kozlov.

 2) Make SCTP more network namespace aware, from Eric Biederman.

 3) TEAM driver now works with non-ethernet devices, from Jiri Pirko.

 4) Make openvswitch network namespace aware, from Pravin B Shelar.

 5) IPV6 NAT implementation, from Patrick McHardy.

 6) Server side support for TCP Fast Open, from Jerry Chu and others.

 7) Packet BPF filter supports MOD and XOR, from Eric Dumazet and Daniel
    Borkmann.

 8) Increate the loopback default MTU to 64K, from Eric Dumazet.

 9) Use a per-task rather than per-socket page fragment allocator for
    outgoing networking traffic.  This benefits processes that have very
    many mostly idle sockets, which is quite common.

    From Eric Dumazet.

10) Use up to 32K for page fragment allocations, with fallbacks to
    smaller sizes when higher order page allocations fail.  Benefits are
    a) less segments for driver to process b) less calls to page
    allocator c) less waste of space.

    From Eric Dumazet.

11) Allow GRO to be used on GRE tunnels, from Eric Dumazet.

12) VXLAN device driver, one way to handle VLAN issues such as the
    limitation of 4096 VLAN IDs yet still have some level of isolation.
    From Stephen Hemminger.

13) As usual there is a large boatload of driver changes, with the scale
    perhaps tilted towards the wireless side this time around.

Fix up various fairly trivial conflicts, mostly caused by the user
namespace changes.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1012 commits)
  hyperv: Add buffer for extended info after the RNDIS response message.
  hyperv: Report actual status in receive completion packet
  hyperv: Remove extra allocated space for recv_pkt_list elements
  hyperv: Fix page buffer handling in rndis_filter_send_request()
  hyperv: Fix the missing return value in rndis_filter_set_packet_filter()
  hyperv: Fix the max_xfer_size in RNDIS initialization
  vxlan: put UDP socket in correct namespace
  vxlan: Depend on CONFIG_INET
  sfc: Fix the reported priorities of different filter types
  sfc: Remove EFX_FILTER_FLAG_RX_OVERRIDE_IP
  sfc: Fix loopback self-test with separate_tx_channels=1
  sfc: Fix MCDI structure field lookup
  sfc: Add parentheses around use of bitfield macro arguments
  sfc: Fix null function pointer in efx_sriov_channel_type
  vxlan: virtual extensible lan
  igmp: export symbol ip_mc_leave_group
  netlink: add attributes to fdb interface
  tg3: unconditionally select HWMON support when tg3 is enabled.
  Revert "net: ti cpsw ethernet: allow reading phy interface mode from DT"
  gre: fix sparse warning
  ...

1 files changed, 52 insertions, 26 deletions

diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index cd9c0a989692..c1a010cda89b 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -37,7 +37,7 @@
  *
  **************************************************************************/
 
-#define EFX_DRIVER_VERSION	"3.1"
+#define EFX_DRIVER_VERSION	"3.2"
 
 #ifdef DEBUG
 #define EFX_BUG_ON_PARANOID(x) BUG_ON(x)
@@ -56,7 +56,8 @@
 #define EFX_MAX_CHANNELS 32U
 #define EFX_MAX_RX_QUEUES EFX_MAX_CHANNELS
 #define EFX_EXTRA_CHANNEL_IOV	0
-#define EFX_MAX_EXTRA_CHANNELS	1U
+#define EFX_EXTRA_CHANNEL_PTP	1
+#define EFX_MAX_EXTRA_CHANNELS	2U
 
 /* Checksum generation is a per-queue option in hardware, so each
  * queue visible to the networking core is backed by two hardware TX
@@ -68,6 +69,9 @@
 #define EFX_TXQ_TYPES		4
 #define EFX_MAX_TX_QUEUES	(EFX_TXQ_TYPES * EFX_MAX_CHANNELS)
 
+/* Forward declare Precision Time Protocol (PTP) support structure. */
+struct efx_ptp_data;
+
 struct efx_self_tests;
 
 /**
@@ -91,29 +95,31 @@ struct efx_special_buffer {
 };
 
 /**
- * struct efx_tx_buffer - An Efx TX buffer
- * @skb: The associated socket buffer.
- *	Set only on the final fragment of a packet; %NULL for all other
- *	fragments.  When this fragment completes, then we can free this
- *	skb.
- * @tsoh: The associated TSO header structure, or %NULL if this
- *	buffer is not a TSO header.
+ * struct efx_tx_buffer - buffer state for a TX descriptor
+ * @skb: When @flags & %EFX_TX_BUF_SKB, the associated socket buffer to be
+ *	freed when descriptor completes
+ * @heap_buf: When @flags & %EFX_TX_BUF_HEAP, the associated heap buffer to be
+ *	freed when descriptor completes.
  * @dma_addr: DMA address of the fragment.
+ * @flags: Flags for allocation and DMA mapping type
  * @len: Length of this fragment.
  *	This field is zero when the queue slot is empty.
- * @continuation: True if this fragment is not the end of a packet.
- * @unmap_single: True if dma_unmap_single should be used.
  * @unmap_len: Length of this fragment to unmap
  */
 struct efx_tx_buffer {
-	const struct sk_buff *skb;
-	struct efx_tso_header *tsoh;
+	union {
+		const struct sk_buff *skb;
+		void *heap_buf;
+	};
 	dma_addr_t dma_addr;
+	unsigned short flags;
 	unsigned short len;
-	bool continuation;
-	bool unmap_single;
 	unsigned short unmap_len;
 };
+#define EFX_TX_BUF_CONT		1	/* not last descriptor of packet */
+#define EFX_TX_BUF_SKB		2	/* buffer is last part of skb */
+#define EFX_TX_BUF_HEAP		4	/* buffer was allocated with kmalloc() */
+#define EFX_TX_BUF_MAP_SINGLE	8	/* buffer was mapped with dma_map_single() */
 
 /**
  * struct efx_tx_queue - An Efx TX queue
@@ -133,6 +139,7 @@ struct efx_tx_buffer {
  * @channel: The associated channel
  * @core_txq: The networking core TX queue structure
  * @buffer: The software buffer ring
+ * @tsoh_page: Array of pages of TSO header buffers
  * @txd: The hardware descriptor ring
  * @ptr_mask: The size of the ring minus 1.
  * @initialised: Has hardware queue been initialised?
@@ -156,9 +163,6 @@ struct efx_tx_buffer {
  *	variable indicates that the queue is full.  This is to
  *	avoid cache-line ping-pong between the xmit path and the
  *	completion path.
- * @tso_headers_free: A list of TSO headers allocated for this TX queue
- *	that are not in use, and so available for new TSO sends. The list
- *	is protected by the TX queue lock.
  * @tso_bursts: Number of times TSO xmit invoked by kernel
  * @tso_long_headers: Number of packets with headers too long for standard
  *	blocks
@@ -175,6 +179,7 @@ struct efx_tx_queue {
 	struct efx_channel *channel;
 	struct netdev_queue *core_txq;
 	struct efx_tx_buffer *buffer;
+	struct efx_buffer *tsoh_page;
 	struct efx_special_buffer txd;
 	unsigned int ptr_mask;
 	bool initialised;
@@ -187,7 +192,6 @@ struct efx_tx_queue {
 	unsigned int insert_count ____cacheline_aligned_in_smp;
 	unsigned int write_count;
 	unsigned int old_read_count;
-	struct efx_tso_header *tso_headers_free;
 	unsigned int tso_bursts;
 	unsigned int tso_long_headers;
 	unsigned int tso_packets;
@@ -242,6 +246,8 @@ struct efx_rx_page_state {
 /**
  * struct efx_rx_queue - An Efx RX queue
  * @efx: The associated Efx NIC
+ * @core_index:  Index of network core RX queue.  Will be >= 0 iff this
+ *	is associated with a real RX queue.
  * @buffer: The software buffer ring
  * @rxd: The hardware descriptor ring
  * @ptr_mask: The size of the ring minus 1.
@@ -263,6 +269,7 @@ struct efx_rx_page_state {
  */
 struct efx_rx_queue {
 	struct efx_nic *efx;
+	int core_index;
 	struct efx_rx_buffer *buffer;
 	struct efx_special_buffer rxd;
 	unsigned int ptr_mask;
@@ -390,14 +397,17 @@ struct efx_channel {
  * @get_name: Generate the channel's name (used for its IRQ handler)
  * @copy: Copy the channel state prior to reallocation.  May be %NULL if
  *	reallocation is not supported.
+ * @receive_skb: Handle an skb ready to be passed to netif_receive_skb()
  * @keep_eventq: Flag for whether event queue should be kept initialised
  *	while the device is stopped
  */
 struct efx_channel_type {
 	void (*handle_no_channel)(struct efx_nic *);
 	int (*pre_probe)(struct efx_channel *);
+	void (*post_remove)(struct efx_channel *);
 	void (*get_name)(struct efx_channel *, char *buf, size_t len);
 	struct efx_channel *(*copy)(const struct efx_channel *);
+	void (*receive_skb)(struct efx_channel *, struct sk_buff *);
 	bool keep_eventq;
 };
 
@@ -430,11 +440,9 @@ enum efx_int_mode {
 #define EFX_INT_MODE_USE_MSI(x) (((x)->interrupt_mode) <= EFX_INT_MODE_MSI)
 
 enum nic_state {
-	STATE_INIT = 0,
-	STATE_RUNNING = 1,
-	STATE_FINI = 2,
-	STATE_DISABLED = 3,
-	STATE_MAX,
+	STATE_UNINIT = 0,	/* device being probed/removed or is frozen */
+	STATE_READY = 1,	/* hardware ready and netdev registered */
+	STATE_DISABLED = 2,	/* device disabled due to hardware errors */
 };
 
 /*
@@ -654,7 +662,7 @@ struct vfdi_status;
  * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues
  * @irq_rx_moderation: IRQ moderation time for RX event queues
  * @msg_enable: Log message enable flags
- * @state: Device state flag. Serialised by the rtnl_lock.
+ * @state: Device state number (%STATE_*). Serialised by the rtnl_lock.
  * @reset_pending: Bitmask for pending resets
  * @tx_queue: TX DMA queues
  * @rx_queue: RX DMA queues
@@ -664,6 +672,8 @@ struct vfdi_status;
  *	should be allocated for this NIC
  * @rxq_entries: Size of receive queues requested by user.
  * @txq_entries: Size of transmit queues requested by user.
+ * @txq_stop_thresh: TX queue fill level at or above which we stop it.
+ * @txq_wake_thresh: TX queue fill level at or below which we wake it.
  * @tx_dc_base: Base qword address in SRAM of TX queue descriptor caches
  * @rx_dc_base: Base qword address in SRAM of RX queue descriptor caches
  * @sram_lim_qw: Qword address limit of SRAM
@@ -730,6 +740,7 @@ struct vfdi_status;
  *	%local_addr_list. Protected by %local_lock.
  * @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
  * @monitor_work: Hardware monitor workitem
  * @biu_lock: BIU (bus interface unit) lock
  * @last_irq_cpu: Last CPU to handle a possible test interrupt.  This
@@ -774,6 +785,9 @@ struct efx_nic {
 
 	unsigned rxq_entries;
 	unsigned txq_entries;
+	unsigned int txq_stop_thresh;
+	unsigned int txq_wake_thresh;
+
 	unsigned tx_dc_base;
 	unsigned rx_dc_base;
 	unsigned sram_lim_qw;
@@ -854,6 +868,10 @@ struct efx_nic {
 	struct work_struct peer_work;
 #endif
 
+#ifdef CONFIG_SFC_PTP
+	struct efx_ptp_data *ptp_data;
+#endif
+
 	/* The following fields may be written more often */
 
 	struct delayed_work monitor_work ____cacheline_aligned_in_smp;
@@ -1044,7 +1062,7 @@ static inline bool efx_tx_queue_used(struct efx_tx_queue *tx_queue)
 
 static inline bool efx_channel_has_rx_queue(struct efx_channel *channel)
 {
-	return channel->channel < channel->efx->n_rx_channels;
+	return channel->rx_queue.core_index >= 0;
 }
 
 static inline struct efx_rx_queue *
@@ -1116,5 +1134,13 @@ static inline void clear_bit_le(unsigned nr, unsigned char *addr)
 #define EFX_MAX_FRAME_LEN(mtu) \
 	((((mtu) + ETH_HLEN + VLAN_HLEN + 4/* FCS */ + 7) & ~7) + 16)
 
+static inline bool efx_xmit_with_hwtstamp(struct sk_buff *skb)
+{
+	return skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP;
+}
+static inline void efx_xmit_hwtstamp_pending(struct sk_buff *skb)
+{
+	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+}
 
 #endif /* EFX_NET_DRIVER_H */