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

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

1 files changed, 180 insertions, 48 deletions

diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index d37928f01949..81640f8bb811 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/moduleparam.h>
 #include <asm/cmpxchg.h>
 #include "net_driver.h"
 #include "nic.h"
@@ -54,18 +55,32 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 static bool efx_mcdi_poll_once(struct efx_nic *efx);
 static void efx_mcdi_abandon(struct efx_nic *efx);
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+static bool mcdi_logging_default;
+module_param(mcdi_logging_default, bool, 0644);
+MODULE_PARM_DESC(mcdi_logging_default,
+		 "Enable MCDI logging on newly-probed functions");
+#endif
+
 int efx_mcdi_init(struct efx_nic *efx)
 {
 	struct efx_mcdi_iface *mcdi;
 	bool already_attached;
-	int rc;
+	int rc = -ENOMEM;
 
 	efx->mcdi = kzalloc(sizeof(*efx->mcdi), GFP_KERNEL);
 	if (!efx->mcdi)
-		return -ENOMEM;
+		goto fail;
 
 	mcdi = efx_mcdi(efx);
 	mcdi->efx = efx;
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	/* consuming code assumes buffer is page-sized */
+	mcdi->logging_buffer = (char *)__get_free_page(GFP_KERNEL);
+	if (!mcdi->logging_buffer)
+		goto fail1;
+	mcdi->logging_enabled = mcdi_logging_default;
+#endif
 	init_waitqueue_head(&mcdi->wq);
 	spin_lock_init(&mcdi->iface_lock);
 	mcdi->state = MCDI_STATE_QUIESCENT;
@@ -81,7 +96,7 @@ int efx_mcdi_init(struct efx_nic *efx)
 	/* Recover from a failed assertion before probing */
 	rc = efx_mcdi_handle_assertion(efx);
 	if (rc)
-		return rc;
+		goto fail2;
 
 	/* Let the MC (and BMC, if this is a LOM) know that the driver
 	 * is loaded. We should do this before we reset the NIC.
@@ -90,7 +105,7 @@ int efx_mcdi_init(struct efx_nic *efx)
 	if (rc) {
 		netif_err(efx, probe, efx->net_dev,
 			  "Unable to register driver with MCPU\n");
-		return rc;
+		goto fail2;
 	}
 	if (already_attached)
 		/* Not a fatal error */
@@ -102,6 +117,15 @@ int efx_mcdi_init(struct efx_nic *efx)
 		efx->primary = efx;
 
 	return 0;
+fail2:
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	free_page((unsigned long)mcdi->logging_buffer);
+fail1:
+#endif
+	kfree(efx->mcdi);
+	efx->mcdi = NULL;
+fail:
+	return rc;
 }
 
 void efx_mcdi_fini(struct efx_nic *efx)
@@ -114,6 +138,10 @@ void efx_mcdi_fini(struct efx_nic *efx)
 	/* Relinquish the device (back to the BMC, if this is a LOM) */
 	efx_mcdi_drv_attach(efx, false, NULL);
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	free_page((unsigned long)efx->mcdi->iface.logging_buffer);
+#endif
+
 	kfree(efx->mcdi);
 }
 
@@ -121,6 +149,9 @@ static void efx_mcdi_send_request(struct efx_nic *efx, unsigned cmd,
 				  const efx_dword_t *inbuf, size_t inlen)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	char *buf = mcdi->logging_buffer; /* page-sized */
+#endif
 	efx_dword_t hdr[2];
 	size_t hdr_len;
 	u32 xflags, seqno;
@@ -165,6 +196,31 @@ static void efx_mcdi_send_request(struct efx_nic *efx, unsigned cmd,
 		hdr_len = 8;
 	}
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	if (mcdi->logging_enabled && !WARN_ON_ONCE(!buf)) {
+		int bytes = 0;
+		int i;
+		/* Lengths should always be a whole number of dwords, so scream
+		 * if they're not.
+		 */
+		WARN_ON_ONCE(hdr_len % 4);
+		WARN_ON_ONCE(inlen % 4);
+
+		/* We own the logging buffer, as only one MCDI can be in
+		 * progress on a NIC at any one time.  So no need for locking.
+		 */
+		for (i = 0; i < hdr_len / 4 && bytes < PAGE_SIZE; i++)
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(hdr[i].u32[0]));
+
+		for (i = 0; i < inlen / 4 && bytes < PAGE_SIZE; i++)
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(inbuf[i].u32[0]));
+
+		netif_info(efx, hw, efx->net_dev, "MCDI RPC REQ:%s\n", buf);
+	}
+#endif
+
 	efx->type->mcdi_request(efx, hdr, hdr_len, inbuf, inlen);
 
 	mcdi->new_epoch = false;
@@ -206,6 +262,9 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
 	unsigned int respseq, respcmd, error;
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	char *buf = mcdi->logging_buffer; /* page-sized */
+#endif
 	efx_dword_t hdr;
 
 	efx->type->mcdi_read_response(efx, &hdr, 0, 4);
@@ -223,6 +282,39 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx)
 			EFX_DWORD_FIELD(hdr, MC_CMD_V2_EXTN_IN_ACTUAL_LEN);
 	}
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	if (mcdi->logging_enabled && !WARN_ON_ONCE(!buf)) {
+		size_t hdr_len, data_len;
+		int bytes = 0;
+		int i;
+
+		WARN_ON_ONCE(mcdi->resp_hdr_len % 4);
+		hdr_len = mcdi->resp_hdr_len / 4;
+		/* MCDI_DECLARE_BUF ensures that underlying buffer is padded
+		 * to dword size, and the MCDI buffer is always dword size
+		 */
+		data_len = DIV_ROUND_UP(mcdi->resp_data_len, 4);
+
+		/* We own the logging buffer, as only one MCDI can be in
+		 * progress on a NIC at any one time.  So no need for locking.
+		 */
+		for (i = 0; i < hdr_len && bytes < PAGE_SIZE; i++) {
+			efx->type->mcdi_read_response(efx, &hdr, (i * 4), 4);
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(hdr.u32[0]));
+		}
+
+		for (i = 0; i < data_len && bytes < PAGE_SIZE; i++) {
+			efx->type->mcdi_read_response(efx, &hdr,
+					mcdi->resp_hdr_len + (i * 4), 4);
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(hdr.u32[0]));
+		}
+
+		netif_info(efx, hw, efx->net_dev, "MCDI RPC RESP:%s\n", buf);
+	}
+#endif
+
 	if (error && mcdi->resp_data_len == 0) {
 		netif_err(efx, hw, efx->net_dev, "MC rebooted\n");
 		mcdi->resprc = -EIO;
@@ -406,7 +498,7 @@ static bool efx_mcdi_complete_async(struct efx_mcdi_iface *mcdi, bool timeout)
 	struct efx_mcdi_async_param *async;
 	size_t hdr_len, data_len, err_len;
 	efx_dword_t *outbuf;
-	MCDI_DECLARE_BUF_OUT_OR_ERR(errbuf, 0);
+	MCDI_DECLARE_BUF_ERR(errbuf);
 	int rc;
 
 	if (cmpxchg(&mcdi->state,
@@ -534,7 +626,7 @@ static int _efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
 				size_t *outlen_actual, bool quiet)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
-	MCDI_DECLARE_BUF_OUT_OR_ERR(errbuf, 0);
+	MCDI_DECLARE_BUF_ERR(errbuf);
 	int rc;
 
 	if (mcdi->mode == MCDI_MODE_POLL)
@@ -1035,7 +1127,9 @@ void efx_mcdi_process_event(struct efx_channel *channel,
 		/* MAC stats are gather lazily.  We can ignore this. */
 		break;
 	case MCDI_EVENT_CODE_FLR:
-		efx_siena_sriov_flr(efx, MCDI_EVENT_FIELD(*event, FLR_VF));
+		if (efx->type->sriov_flr)
+			efx->type->sriov_flr(efx,
+					     MCDI_EVENT_FIELD(*event, FLR_VF));
 		break;
 	case MCDI_EVENT_CODE_PTP_RX:
 	case MCDI_EVENT_CODE_PTP_FAULT:
@@ -1081,9 +1175,7 @@ void efx_mcdi_process_event(struct efx_channel *channel,
 
 void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len)
 {
-	MCDI_DECLARE_BUF(outbuf,
-			 max(MC_CMD_GET_VERSION_OUT_LEN,
-			     MC_CMD_GET_CAPABILITIES_OUT_LEN));
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_VERSION_OUT_LEN);
 	size_t outlength;
 	const __le16 *ver_words;
 	size_t offset;
@@ -1108,19 +1200,11 @@ void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len)
 	 * single version.  Report which variants are running.
 	 */
 	if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0) {
-		BUILD_BUG_ON(MC_CMD_GET_CAPABILITIES_IN_LEN != 0);
-		rc = efx_mcdi_rpc(efx, MC_CMD_GET_CAPABILITIES, NULL, 0,
-				  outbuf, sizeof(outbuf), &outlength);
-		if (rc || outlength < MC_CMD_GET_CAPABILITIES_OUT_LEN)
-			offset += snprintf(
-				buf + offset, len - offset, " rx? tx?");
-		else
-			offset += snprintf(
-				buf + offset, len - offset, " rx%x tx%x",
-				MCDI_WORD(outbuf,
-					  GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID),
-				MCDI_WORD(outbuf,
-					  GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID));
+		struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+		offset += snprintf(buf + offset, len - offset, " rx%x tx%x",
+				   nic_data->rx_dpcpu_fw_id,
+				   nic_data->tx_dpcpu_fw_id);
 
 		/* It's theoretically possible for the string to exceed 31
 		 * characters, though in practice the first three version
@@ -1150,10 +1234,26 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 	MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_UPDATE, 1);
 	MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_FIRMWARE_ID, MC_CMD_FW_LOW_LATENCY);
 
-	rc = efx_mcdi_rpc(efx, MC_CMD_DRV_ATTACH, inbuf, sizeof(inbuf),
-			  outbuf, sizeof(outbuf), &outlen);
-	if (rc)
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_DRV_ATTACH, inbuf, sizeof(inbuf),
+				outbuf, sizeof(outbuf), &outlen);
+	/* If we're not the primary PF, trying to ATTACH with a FIRMWARE_ID
+	 * specified will fail with EPERM, and we have to tell the MC we don't
+	 * care what firmware we get.
+	 */
+	if (rc == -EPERM) {
+		netif_dbg(efx, probe, efx->net_dev,
+			  "efx_mcdi_drv_attach with fw-variant setting failed EPERM, trying without it\n");
+		MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_FIRMWARE_ID,
+			       MC_CMD_FW_DONT_CARE);
+		rc = efx_mcdi_rpc_quiet(efx, MC_CMD_DRV_ATTACH, inbuf,
+					sizeof(inbuf), outbuf, sizeof(outbuf),
+					&outlen);
+	}
+	if (rc) {
+		efx_mcdi_display_error(efx, MC_CMD_DRV_ATTACH, sizeof(inbuf),
+				       outbuf, outlen, rc);
 		goto fail;
+	}
 	if (outlen < MC_CMD_DRV_ATTACH_OUT_LEN) {
 		rc = -EIO;
 		goto fail;
@@ -1178,16 +1278,6 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 	 * and are completely trusted by firmware.  Abort probing
 	 * if that's not true for this function.
 	 */
-	if (driver_operating &&
-	    (efx->mcdi->fn_flags &
-	     (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL |
-	      1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) !=
-	    (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL |
-	     1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) {
-		netif_err(efx, probe, efx->net_dev,
-			  "This driver version only supports one function per port\n");
-		return -ENODEV;
-	}
 
 	if (was_attached != NULL)
 		*was_attached = MCDI_DWORD(outbuf, DRV_ATTACH_OUT_OLD_STATE);
@@ -1385,10 +1475,13 @@ fail1:
 	return rc;
 }
 
+/* Returns 1 if an assertion was read, 0 if no assertion had fired,
+ * negative on error.
+ */
 static int efx_mcdi_read_assertion(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_ASSERTS_IN_LEN);
-	MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, MC_CMD_GET_ASSERTS_OUT_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_ASSERTS_OUT_LEN);
 	unsigned int flags, index;
 	const char *reason;
 	size_t outlen;
@@ -1406,6 +1499,8 @@ static int efx_mcdi_read_assertion(struct efx_nic *efx)
 		rc = efx_mcdi_rpc_quiet(efx, MC_CMD_GET_ASSERTS,
 					inbuf, MC_CMD_GET_ASSERTS_IN_LEN,
 					outbuf, sizeof(outbuf), &outlen);
+		if (rc == -EPERM)
+			return 0;
 	} while ((rc == -EINTR || rc == -EIO) && retry-- > 0);
 
 	if (rc) {
@@ -1443,24 +1538,31 @@ static int efx_mcdi_read_assertion(struct efx_nic *efx)
 			  MCDI_ARRAY_DWORD(outbuf, GET_ASSERTS_OUT_GP_REGS_OFFS,
 					   index));
 
-	return 0;
+	return 1;
 }
 
-static void efx_mcdi_exit_assertion(struct efx_nic *efx)
+static int efx_mcdi_exit_assertion(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_REBOOT_IN_LEN);
+	int rc;
 
 	/* If the MC is running debug firmware, it might now be
 	 * waiting for a debugger to attach, but we just want it to
 	 * reboot.  We set a flag that makes the command a no-op if it
-	 * has already done so.  We don't know what return code to
-	 * expect (0 or -EIO), so ignore it.
+	 * has already done so.
+	 * The MCDI will thus return either 0 or -EIO.
 	 */
 	BUILD_BUG_ON(MC_CMD_REBOOT_OUT_LEN != 0);
 	MCDI_SET_DWORD(inbuf, REBOOT_IN_FLAGS,
 		       MC_CMD_REBOOT_FLAGS_AFTER_ASSERTION);
-	(void) efx_mcdi_rpc(efx, MC_CMD_REBOOT, inbuf, MC_CMD_REBOOT_IN_LEN,
-			    NULL, 0, NULL);
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_REBOOT, inbuf, MC_CMD_REBOOT_IN_LEN,
+				NULL, 0, NULL);
+	if (rc == -EIO)
+		rc = 0;
+	if (rc)
+		efx_mcdi_display_error(efx, MC_CMD_REBOOT, MC_CMD_REBOOT_IN_LEN,
+				       NULL, 0, rc);
+	return rc;
 }
 
 int efx_mcdi_handle_assertion(struct efx_nic *efx)
@@ -1468,12 +1570,10 @@ int efx_mcdi_handle_assertion(struct efx_nic *efx)
 	int rc;
 
 	rc = efx_mcdi_read_assertion(efx);
-	if (rc)
+	if (rc <= 0)
 		return rc;
 
-	efx_mcdi_exit_assertion(efx);
-
-	return 0;
+	return efx_mcdi_exit_assertion(efx);
 }
 
 void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode)
@@ -1550,7 +1650,9 @@ int efx_mcdi_reset(struct efx_nic *efx, enum reset_type method)
 	if (rc)
 		return rc;
 
-	if (method == RESET_TYPE_WORLD)
+	if (method == RESET_TYPE_DATAPATH)
+		return 0;
+	else if (method == RESET_TYPE_WORLD)
 		return efx_mcdi_reset_mc(efx);
 	else
 		return efx_mcdi_reset_func(efx);
@@ -1688,6 +1790,36 @@ int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled)
 			    NULL, 0, NULL);
 }
 
+int efx_mcdi_get_workarounds(struct efx_nic *efx, unsigned int *impl_out,
+			     unsigned int *enabled_out)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_WORKAROUNDS_OUT_LEN);
+	size_t outlen;
+	int rc;
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_GET_WORKAROUNDS, NULL, 0,
+			  outbuf, sizeof(outbuf), &outlen);
+	if (rc)
+		goto fail;
+
+	if (outlen < MC_CMD_GET_WORKAROUNDS_OUT_LEN) {
+		rc = -EIO;
+		goto fail;
+	}
+
+	if (impl_out)
+		*impl_out = MCDI_DWORD(outbuf, GET_WORKAROUNDS_OUT_IMPLEMENTED);
+
+	if (enabled_out)
+		*enabled_out = MCDI_DWORD(outbuf, GET_WORKAROUNDS_OUT_ENABLED);
+
+	return 0;
+
+fail:
+	netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
+	return rc;
+}
+
 #ifdef CONFIG_SFC_MTD
 
 #define EFX_MCDI_NVRAM_LEN_MAX 128