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

Pull networking updates from David Miller:
 "Reasonably busy this cycle, but perhaps not as busy as in the 4.12
  merge window:

   1) Several optimizations for UDP processing under high load from
      Paolo Abeni.

   2) Support pacing internally in TCP when using the sch_fq packet
      scheduler for this is not practical. From Eric Dumazet.

   3) Support mutliple filter chains per qdisc, from Jiri Pirko.

   4) Move to 1ms TCP timestamp clock, from Eric Dumazet.

   5) Add batch dequeueing to vhost_net, from Jason Wang.

   6) Flesh out more completely SCTP checksum offload support, from
      Davide Caratti.

   7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
      Neira Ayuso, and Matthias Schiffer.

   8) Add devlink support to nfp driver, from Simon Horman.

   9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
      Prabhu.

  10) Add stack depth tracking to BPF verifier and use this information
      in the various eBPF JITs. From Alexei Starovoitov.

  11) Support XDP on qed device VFs, from Yuval Mintz.

  12) Introduce BPF PROG ID for better introspection of installed BPF
      programs. From Martin KaFai Lau.

  13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.

  14) For loads, allow narrower accesses in bpf verifier checking, from
      Yonghong Song.

  15) Support MIPS in the BPF selftests and samples infrastructure, the
      MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
      Daney.

  16) Support kernel based TLS, from Dave Watson and others.

  17) Remove completely DST garbage collection, from Wei Wang.

  18) Allow installing TCP MD5 rules using prefixes, from Ivan
      Delalande.

  19) Add XDP support to Intel i40e driver, from Björn Töpel

  20) Add support for TC flower offload in nfp driver, from Simon
      Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
      Kicinski, and Bert van Leeuwen.

  21) IPSEC offloading support in mlx5, from Ilan Tayari.

  22) Add HW PTP support to macb driver, from Rafal Ozieblo.

  23) Networking refcount_t conversions, From Elena Reshetova.

  24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
      for tuning the TCP sockopt settings of a group of applications,
      currently via CGROUPs"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
  net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
  dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
  cxgb4: Support for get_ts_info ethtool method
  cxgb4: Add PTP Hardware Clock (PHC) support
  cxgb4: time stamping interface for PTP
  nfp: default to chained metadata prepend format
  nfp: remove legacy MAC address lookup
  nfp: improve order of interfaces in breakout mode
  net: macb: remove extraneous return when MACB_EXT_DESC is defined
  bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
  bpf: fix return in load_bpf_file
  mpls: fix rtm policy in mpls_getroute
  net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
  net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
  net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
  net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
  ...

1 files changed, 124 insertions, 50 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 74e8e21..a19f68f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -175,6 +175,8 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16f1), .driver_data = BCM57452 },
 	{ PCI_VDEVICE(BROADCOM, 0x1614), .driver_data = BCM57454 },
 #ifdef CONFIG_BNXT_SRIOV
+	{ PCI_VDEVICE(BROADCOM, 0x1606), .driver_data = NETXTREME_E_VF },
+	{ PCI_VDEVICE(BROADCOM, 0x1609), .driver_data = NETXTREME_E_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16c1), .driver_data = NETXTREME_E_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16cb), .driver_data = NETXTREME_C_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16d3), .driver_data = NETXTREME_E_VF },
@@ -461,14 +463,17 @@ normal_tx:
 	prod = NEXT_TX(prod);
 	txr->tx_prod = prod;
 
-	writel(DB_KEY_TX | prod, txr->tx_doorbell);
-	writel(DB_KEY_TX | prod, txr->tx_doorbell);
+	if (!skb->xmit_more || netif_xmit_stopped(txq))
+		bnxt_db_write(bp, txr->tx_doorbell, DB_KEY_TX | prod);
 
 tx_done:
 
 	mmiowb();
 
 	if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
+		if (skb->xmit_more && !tx_buf->is_push)
+			bnxt_db_write(bp, txr->tx_doorbell, DB_KEY_TX | prod);
+
 		netif_tx_stop_queue(txq);
 
 		/* netif_tx_stop_queue() must be done before checking
@@ -582,7 +587,8 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 	if (!page)
 		return NULL;
 
-	*mapping = dma_map_page(dev, page, 0, PAGE_SIZE, bp->rx_dir);
+	*mapping = dma_map_page_attrs(dev, page, 0, PAGE_SIZE, bp->rx_dir,
+				      DMA_ATTR_WEAK_ORDERING);
 	if (dma_mapping_error(dev, *mapping)) {
 		__free_page(page);
 		return NULL;
@@ -601,8 +607,9 @@ static inline u8 *__bnxt_alloc_rx_data(struct bnxt *bp, dma_addr_t *mapping,
 	if (!data)
 		return NULL;
 
-	*mapping = dma_map_single(&pdev->dev, data + bp->rx_dma_offset,
-				  bp->rx_buf_use_size, bp->rx_dir);
+	*mapping = dma_map_single_attrs(&pdev->dev, data + bp->rx_dma_offset,
+					bp->rx_buf_use_size, bp->rx_dir,
+					DMA_ATTR_WEAK_ORDERING);
 
 	if (dma_mapping_error(&pdev->dev, *mapping)) {
 		kfree(data);
@@ -705,8 +712,9 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
 			return -ENOMEM;
 	}
 
-	mapping = dma_map_page(&pdev->dev, page, offset, BNXT_RX_PAGE_SIZE,
-			       PCI_DMA_FROMDEVICE);
+	mapping = dma_map_page_attrs(&pdev->dev, page, offset,
+				     BNXT_RX_PAGE_SIZE, PCI_DMA_FROMDEVICE,
+				     DMA_ATTR_WEAK_ORDERING);
 	if (dma_mapping_error(&pdev->dev, mapping)) {
 		__free_page(page);
 		return -EIO;
@@ -799,7 +807,8 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 		return NULL;
 	}
 	dma_addr -= bp->rx_dma_offset;
-	dma_unmap_page(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir);
+	dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir,
+			     DMA_ATTR_WEAK_ORDERING);
 
 	if (unlikely(!payload))
 		payload = eth_get_headlen(data_ptr, len);
@@ -841,8 +850,8 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
 	}
 
 	skb = build_skb(data, 0);
-	dma_unmap_single(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size,
-			 bp->rx_dir);
+	dma_unmap_single_attrs(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size,
+			       bp->rx_dir, DMA_ATTR_WEAK_ORDERING);
 	if (!skb) {
 		kfree(data);
 		return NULL;
@@ -909,8 +918,9 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, struct bnxt_napi *bnapi,
 			return NULL;
 		}
 
-		dma_unmap_page(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
-			       PCI_DMA_FROMDEVICE);
+		dma_unmap_page_attrs(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
+				     PCI_DMA_FROMDEVICE,
+				     DMA_ATTR_WEAK_ORDERING);
 
 		skb->data_len += frag_len;
 		skb->len += frag_len;
@@ -1330,8 +1340,9 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
 		tpa_info->mapping = new_mapping;
 
 		skb = build_skb(data, 0);
-		dma_unmap_single(&bp->pdev->dev, mapping, bp->rx_buf_use_size,
-				 bp->rx_dir);
+		dma_unmap_single_attrs(&bp->pdev->dev, mapping,
+				       bp->rx_buf_use_size, bp->rx_dir,
+				       DMA_ATTR_WEAK_ORDERING);
 
 		if (!skb) {
 			kfree(data);
@@ -1815,8 +1826,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 		/* Sync BD data before updating doorbell */
 		wmb();
 
-		writel(DB_KEY_TX | prod, db);
-		writel(DB_KEY_TX | prod, db);
+		bnxt_db_write(bp, db, DB_KEY_TX | prod);
 	}
 
 	cpr->cp_raw_cons = raw_cons;
@@ -1832,14 +1842,10 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 	if (event & BNXT_RX_EVENT) {
 		struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
 
-		writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell);
-		writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell);
-		if (event & BNXT_AGG_EVENT) {
-			writel(DB_KEY_RX | rxr->rx_agg_prod,
-			       rxr->rx_agg_doorbell);
-			writel(DB_KEY_RX | rxr->rx_agg_prod,
-			       rxr->rx_agg_doorbell);
-		}
+		bnxt_db_write(bp, rxr->rx_doorbell, DB_KEY_RX | rxr->rx_prod);
+		if (event & BNXT_AGG_EVENT)
+			bnxt_db_write(bp, rxr->rx_agg_doorbell,
+				      DB_KEY_RX | rxr->rx_agg_prod);
 	}
 	return rx_pkts;
 }
@@ -1899,13 +1905,11 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget)
 
 	cpr->cp_raw_cons = raw_cons;
 	BNXT_CP_DB(cpr->cp_doorbell, cpr->cp_raw_cons);
-	writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell);
-	writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell);
+	bnxt_db_write(bp, rxr->rx_doorbell, DB_KEY_RX | rxr->rx_prod);
 
-	if (event & BNXT_AGG_EVENT) {
-		writel(DB_KEY_RX | rxr->rx_agg_prod, rxr->rx_agg_doorbell);
-		writel(DB_KEY_RX | rxr->rx_agg_prod, rxr->rx_agg_doorbell);
-	}
+	if (event & BNXT_AGG_EVENT)
+		bnxt_db_write(bp, rxr->rx_agg_doorbell,
+			      DB_KEY_RX | rxr->rx_agg_prod);
 
 	if (!bnxt_has_work(bp, cpr) && rx_pkts < budget) {
 		napi_complete_done(napi, rx_pkts);
@@ -2015,9 +2019,11 @@ static void bnxt_free_rx_skbs(struct bnxt *bp)
 				if (!data)
 					continue;
 
-				dma_unmap_single(&pdev->dev, tpa_info->mapping,
-						 bp->rx_buf_use_size,
-						 bp->rx_dir);
+				dma_unmap_single_attrs(&pdev->dev,
+						       tpa_info->mapping,
+						       bp->rx_buf_use_size,
+						       bp->rx_dir,
+						       DMA_ATTR_WEAK_ORDERING);
 
 				tpa_info->data = NULL;
 
@@ -2037,13 +2043,15 @@ static void bnxt_free_rx_skbs(struct bnxt *bp)
 
 			if (BNXT_RX_PAGE_MODE(bp)) {
 				mapping -= bp->rx_dma_offset;
-				dma_unmap_page(&pdev->dev, mapping,
-					       PAGE_SIZE, bp->rx_dir);
+				dma_unmap_page_attrs(&pdev->dev, mapping,
+						     PAGE_SIZE, bp->rx_dir,
+						     DMA_ATTR_WEAK_ORDERING);
 				__free_page(data);
 			} else {
-				dma_unmap_single(&pdev->dev, mapping,
-						 bp->rx_buf_use_size,
-						 bp->rx_dir);
+				dma_unmap_single_attrs(&pdev->dev, mapping,
+						       bp->rx_buf_use_size,
+						       bp->rx_dir,
+						       DMA_ATTR_WEAK_ORDERING);
 				kfree(data);
 			}
 		}
@@ -2056,8 +2064,10 @@ static void bnxt_free_rx_skbs(struct bnxt *bp)
 			if (!page)
 				continue;
 
-			dma_unmap_page(&pdev->dev, rx_agg_buf->mapping,
-				       BNXT_RX_PAGE_SIZE, PCI_DMA_FROMDEVICE);
+			dma_unmap_page_attrs(&pdev->dev, rx_agg_buf->mapping,
+					     BNXT_RX_PAGE_SIZE,
+					     PCI_DMA_FROMDEVICE,
+					     DMA_ATTR_WEAK_ORDERING);
 
 			rx_agg_buf->page = NULL;
 			__clear_bit(j, rxr->rx_agg_bmap);
@@ -2900,6 +2910,32 @@ static int bnxt_alloc_hwrm_resources(struct bnxt *bp)
 	return 0;
 }
 
+static void bnxt_free_hwrm_short_cmd_req(struct bnxt *bp)
+{
+	if (bp->hwrm_short_cmd_req_addr) {
+		struct pci_dev *pdev = bp->pdev;
+
+		dma_free_coherent(&pdev->dev, BNXT_HWRM_MAX_REQ_LEN,
+				  bp->hwrm_short_cmd_req_addr,
+				  bp->hwrm_short_cmd_req_dma_addr);
+		bp->hwrm_short_cmd_req_addr = NULL;
+	}
+}
+
+static int bnxt_alloc_hwrm_short_cmd_req(struct bnxt *bp)
+{
+	struct pci_dev *pdev = bp->pdev;
+
+	bp->hwrm_short_cmd_req_addr =
+		dma_alloc_coherent(&pdev->dev, BNXT_HWRM_MAX_REQ_LEN,
+				   &bp->hwrm_short_cmd_req_dma_addr,
+				   GFP_KERNEL);
+	if (!bp->hwrm_short_cmd_req_addr)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static void bnxt_free_stats(struct bnxt *bp)
 {
 	u32 size, i;
@@ -3247,16 +3283,41 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	__le32 *resp_len, *valid;
 	u16 cp_ring_id, len = 0;
 	struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr;
+	u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN;
 
 	req->seq_id = cpu_to_le16(bp->hwrm_cmd_seq++);
 	memset(resp, 0, PAGE_SIZE);
 	cp_ring_id = le16_to_cpu(req->cmpl_ring);
 	intr_process = (cp_ring_id == INVALID_HW_RING_ID) ? 0 : 1;
 
+	if (bp->flags & BNXT_FLAG_SHORT_CMD) {
+		void *short_cmd_req = bp->hwrm_short_cmd_req_addr;
+		struct hwrm_short_input short_input = {0};
+
+		memcpy(short_cmd_req, req, msg_len);
+		memset(short_cmd_req + msg_len, 0, BNXT_HWRM_MAX_REQ_LEN -
+						   msg_len);
+
+		short_input.req_type = req->req_type;
+		short_input.signature =
+				cpu_to_le16(SHORT_REQ_SIGNATURE_SHORT_CMD);
+		short_input.size = cpu_to_le16(msg_len);
+		short_input.req_addr =
+			cpu_to_le64(bp->hwrm_short_cmd_req_dma_addr);
+
+		data = (u32 *)&short_input;
+		msg_len = sizeof(short_input);
+
+		/* Sync memory write before updating doorbell */
+		wmb();
+
+		max_req_len = BNXT_HWRM_SHORT_REQ_LEN;
+	}
+
 	/* Write request msg to hwrm channel */
 	__iowrite32_copy(bp->bar0, data, msg_len / 4);
 
-	for (i = msg_len; i < BNXT_HWRM_MAX_REQ_LEN; i += 4)
+	for (i = msg_len; i < max_req_len; i += 4)
 		writel(0, bp->bar0 + i);
 
 	/* currently supports only one outstanding message */
@@ -4694,6 +4755,7 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	int rc;
 	struct hwrm_ver_get_input req = {0};
 	struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr;
+	u32 dev_caps_cfg;
 
 	bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN;
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VER_GET, -1, -1);
@@ -4731,6 +4793,11 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	    !resp->chip_metal)
 		bp->flags |= BNXT_FLAG_CHIP_NITRO_A0;
 
+	dev_caps_cfg = le32_to_cpu(resp->dev_caps_cfg);
+	if ((dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_SUPPORTED) &&
+	    (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED))
+		bp->flags |= BNXT_FLAG_SHORT_CMD;
+
 hwrm_ver_get_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -7079,8 +7146,8 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	return 0;
 }
 
-static int bnxt_setup_tc(struct net_device *dev, u32 handle, __be16 proto,
-			 struct tc_to_netdev *ntc)
+static int bnxt_setup_tc(struct net_device *dev, u32 handle, u32 chain_index,
+			 __be16 proto, struct tc_to_netdev *ntc)
 {
 	if (ntc->type != TC_SETUP_MQPRIO)
 		return -EINVAL;
@@ -7388,6 +7455,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	bnxt_free_hwrm_resources(bp);
+	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_ethtool_free(bp);
 	bnxt_dcb_free(bp);
 	kfree(bp->edev);
@@ -7542,10 +7610,9 @@ static int bnxt_get_dflt_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 	return rc;
 }
 
-static int bnxt_set_dflt_rings(struct bnxt *bp)
+static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 {
 	int dflt_rings, max_rx_rings, max_tx_rings, rc;
-	bool sh = true;
 
 	if (sh)
 		bp->flags |= BNXT_FLAG_SHARED_RINGS;
@@ -7638,6 +7705,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
+	if (bp->flags & BNXT_FLAG_SHORT_CMD) {
+		rc = bnxt_alloc_hwrm_short_cmd_req(bp);
+		if (rc)
+			goto init_err_pci_clean;
+	}
+
 	rc = bnxt_hwrm_func_reset(bp);
 	if (rc)
 		goto init_err_pci_clean;
@@ -7677,8 +7750,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	init_waitqueue_head(&bp->sriov_cfg_wait);
 #endif
 	bp->gro_func = bnxt_gro_func_5730x;
-	if (BNXT_CHIP_NUM_57X1X(bp->chip_num))
+	if (BNXT_CHIP_P4_PLUS(bp))
 		bp->gro_func = bnxt_gro_func_5731x;
+	else
+		bp->flags |= BNXT_FLAG_DOUBLE_DB;
 
 	rc = bnxt_hwrm_func_drv_rgtr(bp);
 	if (rc)
@@ -7716,7 +7791,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 	bnxt_set_max_func_irqs(bp, max_irqs);
-	rc = bnxt_set_dflt_rings(bp);
+	rc = bnxt_set_dflt_rings(bp, true);
 	if (rc) {
 		netdev_err(bp->dev, "Not enough rings available.\n");
 		rc = -ENOMEM;
@@ -7728,9 +7803,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 |
 			   VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 |
 			   VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6;
-	if (!BNXT_CHIP_NUM_57X0X(bp->chip_num) &&
-	    !BNXT_CHIP_TYPE_NITRO_A0(bp) &&
-	    bp->hwrm_spec_code >= 0x10501) {
+	if (BNXT_CHIP_P4_PLUS(bp) && bp->hwrm_spec_code >= 0x10501) {
 		bp->flags |= BNXT_FLAG_UDP_RSS_CAP;
 		bp->rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 |
 				    VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
@@ -7802,6 +7875,7 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 		dev_close(dev);
 
 	if (system_state == SYSTEM_POWER_OFF) {
+		bnxt_ulp_shutdown(bp);
 		bnxt_clear_int_mode(bp);
 		pci_wake_from_d3(pdev, bp->wol);
 		pci_set_power_state(pdev, PCI_D3hot);