[PATCH net-next 00/11] bnxt_en: Updates.

[PATCH net-next 00/11] bnxt_en: Updates.

[Michael Chan]

Various changes including updated firmware interface, improved TX ring
allocation scheme, improved out-of-memory logic in NAPI loop, reduced
default rings on multi-port devices, new PCI IDs. Of particular note,

CPU affinity hints from Vasundhara Volam.

TC Flower eswitch support from Sathya Perla.

Michael Chan (4):
  bnxt_en: Update firmware interface spec. to 1.8.1.4.
  bnxt_en: Improve tx ring reservation logic.
  bnxt_en: Improve -ENOMEM logic in NAPI poll loop.
  bnxt_en: Reduce default rings on multi-port cards.

Ray Jui (1):
  bnxt: Add PCIe device IDs for bcm58802/bcm58808

Sathya Perla (4):
  bnxt_en: fix clearing devlink ptr from bnxt struct
  bnxt_en: bnxt: add TC flower filter offload support
  bnxt_en: add TC flower offload flow_alloc/free FW cmds
  bnxt_en: add code to query TC flower offload stats

Scott Branden (1):
  bnxt: initialize board_info values with proper enums

Vasundhara Volam (1):
  bnxt_en: assign CPU affinity hints to bnxt_en IRQs

 drivers/net/ethernet/broadcom/Kconfig             |   9 +
 drivers/net/ethernet/broadcom/bnxt/Makefile       |   2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 198 +++--
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |  41 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c |   3 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h     | 186 ++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c      | 834 ++++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h      | 158 ++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c     |  22 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h     |  22 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c     |   4 +-
 11 files changed, 1407 insertions(+), 72 deletions(-)
 create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
 create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h

-- 
1.8.3.1

[PATCH net-next 01/11] bnxt_en: Update firmware interface spec. to 1.8.1.4.

[Michael Chan]

Flow APIs are added in this firmware interface.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 186 +++++++++++++++++++++++++-
 1 file changed, 181 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 3ba22e8..cb04cc7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -11,14 +11,14 @@
 #ifndef BNXT_HSI_H
 #define BNXT_HSI_H
 
-/* HSI and HWRM Specification 1.8.0 */
+/* HSI and HWRM Specification 1.8.1 */
 #define HWRM_VERSION_MAJOR	1
 #define HWRM_VERSION_MINOR	8
-#define HWRM_VERSION_UPDATE	0
+#define HWRM_VERSION_UPDATE	1
 
-#define HWRM_VERSION_RSVD	0 /* non-zero means beta version */
+#define HWRM_VERSION_RSVD	4 /* non-zero means beta version */
 
-#define HWRM_VERSION_STR	"1.8.0.0"
+#define HWRM_VERSION_STR	"1.8.1.4"
 /*
  * Following is the signature for HWRM message field that indicates not
  * applicable (All F's). Need to cast it the size of the field if needed.
@@ -946,6 +946,7 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE	    0x400UL
 	#define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST		    0x800UL
 	#define FUNC_CFG_REQ_FLAGS_NO_AUTOCLEAR_STATISTIC	    0x1000UL
+	#define FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST		    0x2000UL
 	__le32 enables;
 	#define FUNC_CFG_REQ_ENABLES_MTU			    0x1UL
 	#define FUNC_CFG_REQ_ENABLES_MRU			    0x2UL
@@ -1972,7 +1973,12 @@ struct hwrm_port_phy_qcaps_output {
 	#define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED	    0x1UL
 	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK		    0xfeUL
 	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT		    1
-	u8 unused_0;
+	u8 port_cnt;
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN		   0x0UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_1			   0x1UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_2			   0x2UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_3			   0x3UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_4			   0x4UL
 	__le16 supported_speeds_force_mode;
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MBHD 0x1UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MB 0x2UL
@@ -4407,6 +4413,164 @@ struct hwrm_cfa_ntuple_filter_cfg_output {
 	u8 valid;
 };
 
+/* hwrm_cfa_flow_alloc */
+/* Input (128 bytes) */
+struct hwrm_cfa_flow_alloc_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 flags;
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_TUNNEL		    0x1UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_MASK		    0x6UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_SFT		    1
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_NONE		   (0x0UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_ONE		   (0x1UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO		   (0x2UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_LAST    CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_MASK		    0x38UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_SFT		    3
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2		   (0x0UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV4		   (0x1UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6		   (0x2UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_LAST    CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6
+	__le16 src_fid;
+	__le32 tunnel_handle;
+	__le16 action_flags;
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD		    0x1UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE	    0x2UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP		    0x4UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER		    0x8UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL		    0x10UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC	    0x20UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST	    0x40UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS   0x80UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE  0x100UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT      0x200UL
+	__le16 dst_fid;
+	__be16 l2_rewrite_vlan_tpid;
+	__be16 l2_rewrite_vlan_tci;
+	__le16 act_meter_id;
+	__le16 ref_flow_handle;
+	__be16 ethertype;
+	__be16 outer_vlan_tci;
+	__be16 dmac[3];
+	__be16 inner_vlan_tci;
+	__be16 smac[3];
+	u8 ip_dst_mask_len;
+	u8 ip_src_mask_len;
+	__be32 ip_dst[4];
+	__be32 ip_src[4];
+	__be16 l4_src_port;
+	__be16 l4_src_port_mask;
+	__be16 l4_dst_port;
+	__be16 l4_dst_port_mask;
+	__be32 nat_ip_address[4];
+	__be16 l2_rewrite_dmac[3];
+	__be16 nat_port;
+	__be16 l2_rewrite_smac[3];
+	u8 ip_proto;
+	u8 unused_0;
+};
+
+/* Output (16 bytes) */
+struct hwrm_cfa_flow_alloc_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 flow_handle;
+	u8 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 unused_4;
+	u8 valid;
+};
+
+/* hwrm_cfa_flow_free */
+/* Input (24 bytes) */
+struct hwrm_cfa_flow_free_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 flow_handle;
+	__le16 unused_0[3];
+};
+
+/* Output (32 bytes) */
+struct hwrm_cfa_flow_free_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le64 packet;
+	__le64 byte;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
+/* hwrm_cfa_flow_stats */
+/* Input (40 bytes) */
+struct hwrm_cfa_flow_stats_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le16 num_flows;
+	__le16 flow_handle_0;
+	__le16 flow_handle_1;
+	__le16 flow_handle_2;
+	__le16 flow_handle_3;
+	__le16 flow_handle_4;
+	__le16 flow_handle_5;
+	__le16 flow_handle_6;
+	__le16 flow_handle_7;
+	__le16 flow_handle_8;
+	__le16 flow_handle_9;
+	__le16 unused_0;
+};
+
+/* Output (176 bytes) */
+struct hwrm_cfa_flow_stats_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le64 packet_0;
+	__le64 packet_1;
+	__le64 packet_2;
+	__le64 packet_3;
+	__le64 packet_4;
+	__le64 packet_5;
+	__le64 packet_6;
+	__le64 packet_7;
+	__le64 packet_8;
+	__le64 packet_9;
+	__le64 byte_0;
+	__le64 byte_1;
+	__le64 byte_2;
+	__le64 byte_3;
+	__le64 byte_4;
+	__le64 byte_5;
+	__le64 byte_6;
+	__le64 byte_7;
+	__le64 byte_8;
+	__le64 byte_9;
+	__le32 unused_0;
+	u8 unused_1;
+	u8 unused_2;
+	u8 unused_3;
+	u8 valid;
+};
+
 /* hwrm_cfa_vfr_alloc */
 /* Input (32 bytes) */
 struct hwrm_cfa_vfr_alloc_input {
@@ -5534,11 +5698,15 @@ struct hwrm_selftest_qlist_output {
 	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST      0x2UL
 	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST  0x4UL
 	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST    0x8UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_PCIE_EYE_TEST  0x10UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_ETHERNET_EYE_TEST 0x20UL
 	u8 offline_tests;
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST	    0x1UL
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST	    0x2UL
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST    0x4UL
 	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST      0x8UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_PCIE_EYE_TEST    0x10UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_ETHERNET_EYE_TEST 0x20UL
 	u8 unused_0;
 	__le16 test_timeout;
 	u8 unused_1;
@@ -5566,6 +5734,8 @@ struct hwrm_selftest_exec_input {
 	#define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST		    0x2UL
 	#define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST		    0x4UL
 	#define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST		    0x8UL
+	#define SELFTEST_EXEC_REQ_FLAGS_PCIE_EYE_TEST		    0x10UL
+	#define SELFTEST_EXEC_REQ_FLAGS_ETHERNET_EYE_TEST	    0x20UL
 	u8 unused_0[7];
 };
 
@@ -5580,11 +5750,15 @@ struct hwrm_selftest_exec_output {
 	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST       0x2UL
 	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST   0x4UL
 	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST     0x8UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_PCIE_EYE_TEST   0x10UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_ETHERNET_EYE_TEST 0x20UL
 	u8 test_success;
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST	    0x1UL
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST	    0x2UL
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST      0x4UL
 	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST	    0x8UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_PCIE_EYE_TEST      0x10UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_ETHERNET_EYE_TEST  0x20UL
 	__le16 unused_0[3];
 };
 
@@ -5767,6 +5941,7 @@ struct cmd_nums {
 	#define HWRM_SELFTEST_QLIST				   (0x200UL)
 	#define HWRM_SELFTEST_EXEC				   (0x201UL)
 	#define HWRM_SELFTEST_IRQ				   (0x202UL)
+	#define HWRM_SELFTEST_RETREIVE_EYE_DATA		   (0x203UL)
 	#define HWRM_DBG_READ_DIRECT				   (0xff10UL)
 	#define HWRM_DBG_READ_INDIRECT				   (0xff11UL)
 	#define HWRM_DBG_WRITE_DIRECT				   (0xff12UL)
@@ -5984,6 +6159,7 @@ struct hwrm_struct_hdr {
 	#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE		   0x426UL
 	#define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE		   0x1UL
 	#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION		   0xaUL
+	#define STRUCT_HDR_STRUCT_ID_RSS_V2			   0x64UL
 	__le16 len;
 	u8 version;
 	u8 count;
-- 
1.8.3.1

[PATCH net-next 02/11] bnxt_en: Improve tx ring reservation logic.

[Michael Chan]

When the number of TX rings is changed (e.g. ethtool -L, enabling XDP TX
rings, etc), the current code tries to reserve the new number of TX rings
before closing and re-opening the NIC.  If we are unable to reserve the
new TX rings, we abort the operation and keep the current TX rings.

The problem is that the firmware will disable the current TX rings even
when it cannot reserve the new set of TX rings.  We fix it as follows:

1. Instead of reserving the new set of TX rings, just ask the firmware
to check if the new set of TX rings is available.  There is a flag in
the firmware message to do that.  If not available, abort and the
current TX rings will not be disabled.

2. Do the actual TX ring reservation in the path that opens the NIC.
We keep the number of TX rings currently successfully reserved.  If the
number of TX rings is different than the reserved TX rings, we call
firmware and reserve again.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 46 +++++++++++++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |  5 ++-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c |  3 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c     |  4 +-
 4 files changed, 44 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6e14fc4..4b0a807 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4461,9 +4461,33 @@ static int bnxt_hwrm_reserve_tx_rings(struct bnxt *bp, int *tx_rings)
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = __bnxt_hwrm_get_tx_rings(bp, 0xffff, tx_rings);
 	mutex_unlock(&bp->hwrm_cmd_lock);
+	if (!rc)
+		bp->tx_reserved_rings = *tx_rings;
 	return rc;
 }
 
+static int bnxt_hwrm_check_tx_rings(struct bnxt *bp, int tx_rings)
+{
+	struct hwrm_func_cfg_input req = {0};
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10801)
+		return 0;
+
+	if (BNXT_VF(bp))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
+	req.fid = cpu_to_le16(0xffff);
+	req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST);
+	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS);
+	req.num_tx_rings = cpu_to_le16(tx_rings);
+	rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		return -ENOMEM;
+	return 0;
+}
+
 static void bnxt_hwrm_set_coal_params(struct bnxt *bp, u32 max_bufs,
 	u32 buf_tmrs, u16 flags,
 	struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req)
@@ -5115,6 +5139,15 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 				   rc);
 			goto err_out;
 		}
+		if (bp->tx_reserved_rings != bp->tx_nr_rings) {
+			int tx = bp->tx_nr_rings;
+
+			if (bnxt_hwrm_reserve_tx_rings(bp, &tx) ||
+			    tx < bp->tx_nr_rings) {
+				rc = -ENOMEM;
+				goto err_out;
+			}
+		}
 	}
 
 	rc = bnxt_hwrm_ring_alloc(bp);
@@ -6998,8 +7031,8 @@ static void bnxt_sp_task(struct work_struct *work)
 }
 
 /* Under rtnl_lock */
-int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
-		       int tx_xdp)
+int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
+		     int tx_xdp)
 {
 	int max_rx, max_tx, tx_sets = 1;
 	int tx_rings_needed;
@@ -7019,10 +7052,7 @@ int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 	if (max_tx < tx_rings_needed)
 		return -ENOMEM;
 
-	if (bnxt_hwrm_reserve_tx_rings(bp, &tx_rings_needed) ||
-	    tx_rings_needed < (tx * tx_sets + tx_xdp))
-		return -ENOMEM;
-	return 0;
+	return bnxt_hwrm_check_tx_rings(bp, tx_rings_needed);
 }
 
 static void bnxt_unmap_bars(struct bnxt *bp, struct pci_dev *pdev)
@@ -7211,8 +7241,8 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
 		sh = true;
 
-	rc = bnxt_reserve_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
-				sh, tc, bp->tx_nr_rings_xdp);
+	rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
+			      sh, tc, bp->tx_nr_rings_xdp);
 	if (rc)
 		return rc;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 2d84d57..568516f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1118,6 +1118,7 @@ struct bnxt {
 	int			tx_nr_rings;
 	int			tx_nr_rings_per_tc;
 	int			tx_nr_rings_xdp;
+	int			tx_reserved_rings;
 
 	int			tx_wake_thresh;
 	int			tx_push_thresh;
@@ -1346,8 +1347,8 @@ int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
 int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
 int bnxt_close_nic(struct bnxt *, bool, bool);
-int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
-		       int tx_xdp);
+int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
+		     int tx_xdp);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
 int bnxt_get_max_rings(struct bnxt *, int *, int *, bool);
 void bnxt_restore_pf_fw_resources(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 08b870d..8eff05a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -435,8 +435,7 @@ static int bnxt_set_channels(struct net_device *dev,
 		}
 		tx_xdp = req_rx_rings;
 	}
-	rc = bnxt_reserve_rings(bp, req_tx_rings, req_rx_rings, sh, tcs,
-				tx_xdp);
+	rc = bnxt_check_rings(bp, req_tx_rings, req_rx_rings, sh, tcs, tx_xdp);
 	if (rc) {
 		netdev_warn(dev, "Unable to allocate the requested rings\n");
 		return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 3961a68..d8f0c83 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -169,8 +169,8 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	tc = netdev_get_num_tc(dev);
 	if (!tc)
 		tc = 1;
-	rc = bnxt_reserve_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
-				true, tc, tx_xdp);
+	rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings,
+			      true, tc, tx_xdp);
 	if (rc) {
 		netdev_warn(dev, "Unable to reserve enough TX rings to support XDP.\n");
 		return rc;
-- 
1.8.3.1

[PATCH net-next 03/11] bnxt_en: assign CPU affinity hints to bnxt_en IRQs

[Michael Chan]

From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>

This patch provides hints to irqbalance to map bnxt_en device IRQs
to specific CPU cores. cpumask_local_spread() is used, which first
maps IRQs to near NUMA cores; when those cores are exhausted, IRQs
are mapped to far NUMA cores.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 25 ++++++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  4 +++-
 2 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4b0a807..9657bfb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -49,6 +49,7 @@
 #include <linux/aer.h>
 #include <linux/bitmap.h>
 #include <linux/cpu_rmap.h>
+#include <linux/cpumask.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -5554,8 +5555,15 @@ static void bnxt_free_irq(struct bnxt *bp)
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		irq = &bp->irq_tbl[i];
-		if (irq->requested)
+		if (irq->requested) {
+			if (irq->have_cpumask) {
+				irq_set_affinity_hint(irq->vector, NULL);
+				free_cpumask_var(irq->cpu_mask);
+				irq->have_cpumask = 0;
+			}
 			free_irq(irq->vector, bp->bnapi[i]);
+		}
+
 		irq->requested = 0;
 	}
 }
@@ -5588,6 +5596,21 @@ static int bnxt_request_irq(struct bnxt *bp)
 			break;
 
 		irq->requested = 1;
+
+		if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
+			int numa_node = dev_to_node(&bp->pdev->dev);
+
+			irq->have_cpumask = 1;
+			cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+					irq->cpu_mask);
+			rc = irq_set_affinity_hint(irq->vector, irq->cpu_mask);
+			if (rc) {
+				netdev_warn(bp->dev,
+					    "Set affinity failed, IRQ = %d\n",
+					    irq->vector);
+				break;
+			}
+		}
 	}
 	return rc;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 568516f..801c0f7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -701,8 +701,10 @@ struct bnxt_napi {
 struct bnxt_irq {
 	irq_handler_t	handler;
 	unsigned int	vector;
-	u8		requested;
+	u8		requested:1;
+	u8		have_cpumask:1;
 	char		name[IFNAMSIZ + 2];
+	cpumask_var_t	cpu_mask;
 };
 
 #define HWRM_RING_ALLOC_TX	0x1
-- 
1.8.3.1

[PATCH net-next 04/11] bnxt: Add PCIe device IDs for bcm58802/bcm58808

[Michael Chan]

From: Ray Jui <ray.jui@broadcom.com>

Add PCIe device ID for bcm58802 and bcm58808. Also add chip number
update to declare bcm588xx as chip class phase 4 and later

Signed-off-by: Ray Jui <ray.jui@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 +++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 8 ++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9657bfb..500681d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -104,6 +104,8 @@ enum board_idx {
 	BCM57416_NPAR,
 	BCM57452,
 	BCM57454,
+	BCM58802,
+	BCM58808,
 	NETXTREME_E_VF,
 	NETXTREME_C_VF,
 };
@@ -140,11 +142,14 @@ enum board_idx {
 	{ "Broadcom BCM57416 NetXtreme-E Ethernet Partition" },
 	{ "Broadcom BCM57452 NetXtreme-E 10Gb/25Gb/40Gb/50Gb Ethernet" },
 	{ "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
+	{ "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	{ "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
 	{ "Broadcom NetXtreme-E Ethernet Virtual Function" },
 	{ "Broadcom NetXtreme-C Ethernet Virtual Function" },
 };
 
 static const struct pci_device_id bnxt_pci_tbl[] = {
+	{ PCI_VDEVICE(BROADCOM, 0x1614), .driver_data = BCM57454 },
 	{ PCI_VDEVICE(BROADCOM, 0x16c0), .driver_data = BCM57417_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x16c8), .driver_data = BCM57301 },
 	{ PCI_VDEVICE(BROADCOM, 0x16c9), .driver_data = BCM57302 },
@@ -175,8 +180,9 @@ enum board_idx {
 	{ PCI_VDEVICE(BROADCOM, 0x16ed), .driver_data = BCM57414_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x16ee), .driver_data = BCM57416_NPAR },
 	{ PCI_VDEVICE(BROADCOM, 0x16ef), .driver_data = BCM57416_NPAR },
+	{ PCI_VDEVICE(BROADCOM, 0x16f0), .driver_data = BCM58808 },
 	{ PCI_VDEVICE(BROADCOM, 0x16f1), .driver_data = BCM57452 },
-	{ PCI_VDEVICE(BROADCOM, 0x1614), .driver_data = BCM57454 },
+	{ PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 },
 #ifdef CONFIG_BNXT_SRIOV
 	{ PCI_VDEVICE(BROADCOM, 0x1606), .driver_data = NETXTREME_E_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x1609), .driver_data = NETXTREME_E_VF },
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 801c0f7..3521e46 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -990,6 +990,9 @@ struct bnxt {
 
 #define CHIP_NUM_5745X		0xd730
 
+#define CHIP_NUM_58802		0xd802
+#define CHIP_NUM_58808		0xd808
+
 #define BNXT_CHIP_NUM_5730X(chip_num)		\
 	((chip_num) >= CHIP_NUM_57301 &&	\
 	 (chip_num) <= CHIP_NUM_57304)
@@ -1021,6 +1024,10 @@ struct bnxt {
 #define BNXT_CHIP_NUM_57X1X(chip_num)		\
 	(BNXT_CHIP_NUM_5731X(chip_num) || BNXT_CHIP_NUM_5741X(chip_num))
 
+#define BNXT_CHIP_NUM_588XX(chip_num)		\
+	((chip_num) == CHIP_NUM_58802 ||	\
+	 (chip_num) == CHIP_NUM_58808)
+
 	struct net_device	*dev;
 	struct pci_dev		*pdev;
 
@@ -1079,6 +1086,7 @@ struct bnxt {
 #define BNXT_CHIP_P4_PLUS(bp)			\
 	(BNXT_CHIP_NUM_57X1X((bp)->chip_num) ||	\
 	 BNXT_CHIP_NUM_5745X((bp)->chip_num) ||	\
+	 BNXT_CHIP_NUM_588XX((bp)->chip_num) ||	\
 	 (BNXT_CHIP_NUM_58700((bp)->chip_num) &&	\
 	  !BNXT_CHIP_TYPE_NITRO_A0(bp)))
 
-- 
1.8.3.1

[PATCH net-next 05/11] bnxt: initialize board_info values with proper enums

[Michael Chan]

From: Scott Branden <scott.branden@broadcom.com>

initialize board_info values with proper enums for defensive programming
purposes.  This will avoid any errors of the enums being declared not
lining up with the board_info array.

Signed-off-by: Scott Branden <scott.branden@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 64 +++++++++++++++----------------
 1 file changed, 32 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 500681d..1afb408 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -114,38 +114,38 @@ enum board_idx {
 static const struct {
 	char *name;
 } board_info[] = {
-	{ "Broadcom BCM57301 NetXtreme-C 10Gb Ethernet" },
-	{ "Broadcom BCM57302 NetXtreme-C 10Gb/25Gb Ethernet" },
-	{ "Broadcom BCM57304 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" },
-	{ "Broadcom BCM57417 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM58700 Nitro 1Gb/2.5Gb/10Gb Ethernet" },
-	{ "Broadcom BCM57311 NetXtreme-C 10Gb Ethernet" },
-	{ "Broadcom BCM57312 NetXtreme-C 10Gb/25Gb Ethernet" },
-	{ "Broadcom BCM57402 NetXtreme-E 10Gb Ethernet" },
-	{ "Broadcom BCM57404 NetXtreme-E 10Gb/25Gb Ethernet" },
-	{ "Broadcom BCM57406 NetXtreme-E 10GBase-T Ethernet" },
-	{ "Broadcom BCM57402 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57407 NetXtreme-E 10GBase-T Ethernet" },
-	{ "Broadcom BCM57412 NetXtreme-E 10Gb Ethernet" },
-	{ "Broadcom BCM57414 NetXtreme-E 10Gb/25Gb Ethernet" },
-	{ "Broadcom BCM57416 NetXtreme-E 10GBase-T Ethernet" },
-	{ "Broadcom BCM57417 NetXtreme-E 10GBase-T Ethernet" },
-	{ "Broadcom BCM57412 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57314 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" },
-	{ "Broadcom BCM57417 NetXtreme-E 10Gb/25Gb Ethernet" },
-	{ "Broadcom BCM57416 NetXtreme-E 10Gb Ethernet" },
-	{ "Broadcom BCM57404 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57406 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57407 NetXtreme-E 25Gb Ethernet" },
-	{ "Broadcom BCM57407 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57414 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57416 NetXtreme-E Ethernet Partition" },
-	{ "Broadcom BCM57452 NetXtreme-E 10Gb/25Gb/40Gb/50Gb Ethernet" },
-	{ "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
-	{ "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" },
-	{ "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
-	{ "Broadcom NetXtreme-E Ethernet Virtual Function" },
-	{ "Broadcom NetXtreme-C Ethernet Virtual Function" },
+	[BCM57301] = { "Broadcom BCM57301 NetXtreme-C 10Gb Ethernet" },
+	[BCM57302] = { "Broadcom BCM57302 NetXtreme-C 10Gb/25Gb Ethernet" },
+	[BCM57304] = { "Broadcom BCM57304 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	[BCM57417_NPAR] = { "Broadcom BCM57417 NetXtreme-E Ethernet Partition" },
+	[BCM58700] = { "Broadcom BCM58700 Nitro 1Gb/2.5Gb/10Gb Ethernet" },
+	[BCM57311] = { "Broadcom BCM57311 NetXtreme-C 10Gb Ethernet" },
+	[BCM57312] = { "Broadcom BCM57312 NetXtreme-C 10Gb/25Gb Ethernet" },
+	[BCM57402] = { "Broadcom BCM57402 NetXtreme-E 10Gb Ethernet" },
+	[BCM57404] = { "Broadcom BCM57404 NetXtreme-E 10Gb/25Gb Ethernet" },
+	[BCM57406] = { "Broadcom BCM57406 NetXtreme-E 10GBase-T Ethernet" },
+	[BCM57402_NPAR] = { "Broadcom BCM57402 NetXtreme-E Ethernet Partition" },
+	[BCM57407] = { "Broadcom BCM57407 NetXtreme-E 10GBase-T Ethernet" },
+	[BCM57412] = { "Broadcom BCM57412 NetXtreme-E 10Gb Ethernet" },
+	[BCM57414] = { "Broadcom BCM57414 NetXtreme-E 10Gb/25Gb Ethernet" },
+	[BCM57416] = { "Broadcom BCM57416 NetXtreme-E 10GBase-T Ethernet" },
+	[BCM57417] = { "Broadcom BCM57417 NetXtreme-E 10GBase-T Ethernet" },
+	[BCM57412_NPAR] = { "Broadcom BCM57412 NetXtreme-E Ethernet Partition" },
+	[BCM57314] = { "Broadcom BCM57314 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	[BCM57417_SFP] = { "Broadcom BCM57417 NetXtreme-E 10Gb/25Gb Ethernet" },
+	[BCM57416_SFP] = { "Broadcom BCM57416 NetXtreme-E 10Gb Ethernet" },
+	[BCM57404_NPAR] = { "Broadcom BCM57404 NetXtreme-E Ethernet Partition" },
+	[BCM57406_NPAR] = { "Broadcom BCM57406 NetXtreme-E Ethernet Partition" },
+	[BCM57407_SFP] = { "Broadcom BCM57407 NetXtreme-E 25Gb Ethernet" },
+	[BCM57407_NPAR] = { "Broadcom BCM57407 NetXtreme-E Ethernet Partition" },
+	[BCM57414_NPAR] = { "Broadcom BCM57414 NetXtreme-E Ethernet Partition" },
+	[BCM57416_NPAR] = { "Broadcom BCM57416 NetXtreme-E Ethernet Partition" },
+	[BCM57452] = { "Broadcom BCM57452 NetXtreme-E 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	[BCM57454] = { "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
+	[BCM58802] = { "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" },
+	[BCM58808] = { "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
+	[NETXTREME_E_VF] = { "Broadcom NetXtreme-E Ethernet Virtual Function" },
+	[NETXTREME_C_VF] = { "Broadcom NetXtreme-C Ethernet Virtual Function" },
 };
 
 static const struct pci_device_id bnxt_pci_tbl[] = {
-- 
1.8.3.1

[PATCH net-next 06/11] bnxt_en: Improve -ENOMEM logic in NAPI poll loop.

[Michael Chan]

If we cannot allocate RX buffers in the NAPI poll loop when processing
an RX event, the current code does not count that event towards the NAPI
budget.  This can cause us to potentially loop forever in NAPI if we
consistently cannot allocate new buffers.  Improve it by counting
-ENOMEM event as 1 towards the NAPI budget.

Cc: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1afb408..a34fcdd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1850,6 +1850,13 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 							   &event);
 			if (likely(rc >= 0))
 				rx_pkts += rc;
+			/* Increment rx_pkts when rc is -ENOMEM to count towards
+			 * the NAPI budget.  Otherwise, we may potentially loop
+			 * here forever if we consistently cannot allocate
+			 * buffers.
+			 */
+			else if (rc == -ENOMEM)
+				rx_pkts++;
 			else if (rc == -EBUSY)	/* partial completion */
 				break;
 		} else if (unlikely((TX_CMP_TYPE(txcmp) ==
-- 
1.8.3.1

[PATCH net-next 07/11] bnxt_en: Reduce default rings on multi-port cards.

[Michael Chan]

Reduce default rings from 8 to 4 on multi-port cards to reduce memory
usage.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 13 +++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a34fcdd..4406f91 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5795,6 +5795,8 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 		link_info->support_auto_speeds =
 			le16_to_cpu(resp->supported_speeds_auto_mode);
 
+	bp->port_count = resp->port_cnt;
+
 hwrm_phy_qcaps_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -7877,6 +7879,9 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 	if (sh)
 		bp->flags |= BNXT_FLAG_SHARED_RINGS;
 	dflt_rings = netif_get_num_default_rss_queues();
+	/* Reduce default rings to reduce memory usage on multi-port cards */
+	if (bp->port_count > 1)
+		dflt_rings = min_t(int, dflt_rings, 4);
 	rc = bnxt_get_dflt_rings(bp, &max_rx_rings, &max_tx_rings, sh);
 	if (rc)
 		return rc;
@@ -8049,6 +8054,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bnxt_ethtool_init(bp);
 	bnxt_dcb_init(bp);
 
+	rc = bnxt_probe_phy(bp);
+	if (rc)
+		goto init_err_pci_clean;
+
 	bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
@@ -8083,10 +8092,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (dev->hw_features & NETIF_F_HW_VLAN_CTAG_RX)
 		bp->flags |= BNXT_FLAG_STRIP_VLAN;
 
-	rc = bnxt_probe_phy(bp);
-	if (rc)
-		goto init_err_pci_clean;
-
 	rc = bnxt_init_int_mode(bp);
 	if (rc)
 		goto init_err_pci_clean;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 3521e46..86af8ea 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1207,6 +1207,7 @@ struct bnxt {
 	u8			nge_port_cnt;
 	__le16			nge_fw_dst_port_id;
 	u8			port_partition_type;
+	u8			port_count;
 	u16			br_mode;
 
 	u16			rx_coal_ticks;
-- 
1.8.3.1

[PATCH net-next 08/11] bnxt_en: fix clearing devlink ptr from bnxt struct

[Michael Chan]

From: Sathya Perla <sathya.perla@broadcom.com>

The routine bnxt_link_bp_to_dl() is used to set the devlink ptr
in bnxt struct (bp) and also to set the bnxt back ptr in
the devlink struct.  If devlink_register() fails, bp->dl must
be cleared which is not happening currently. This patch fixes
bnxt_link_bp_to_dl() to clear bp->dl by passing  a NULL dl ptr.

Fixes: 4ab0c6a8ffd7 ("bnxt_en: add support to enable VF-representors")
Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c |  4 ++--
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h | 14 +++++++++-----
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index 86cce6f..c365d3c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -468,11 +468,11 @@ int bnxt_dl_register(struct bnxt *bp)
 		return -ENOMEM;
 	}
 
-	bnxt_link_bp_to_dl(dl, bp);
+	bnxt_link_bp_to_dl(bp, dl);
 	bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
 	rc = devlink_register(dl, &bp->pdev->dev);
 	if (rc) {
-		bnxt_link_bp_to_dl(dl, NULL);
+		bnxt_link_bp_to_dl(bp, NULL);
 		devlink_free(dl);
 		netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc);
 		return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
index e55a3b6..3e997c9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
@@ -24,13 +24,17 @@ static inline struct bnxt *bnxt_get_bp_from_dl(struct devlink *dl)
 	return ((struct bnxt_dl *)devlink_priv(dl))->bp;
 }
 
-static inline void bnxt_link_bp_to_dl(struct devlink *dl, struct bnxt *bp)
+/* To clear devlink pointer from bp, pass NULL dl */
+static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
 {
-	struct bnxt_dl *bp_dl = devlink_priv(dl);
+	bp->dl = dl;
 
-	bp_dl->bp = bp;
-	if (bp)
-		bp->dl = dl;
+	/* add a back pointer in dl to bp */
+	if (dl) {
+		struct bnxt_dl *bp_dl = devlink_priv(dl);
+
+		bp_dl->bp = bp;
+	}
 }
 
 int bnxt_dl_register(struct bnxt *bp);
-- 
1.8.3.1

[PATCH net-next 09/11] bnxt_en: bnxt: add TC flower filter offload support

[Michael Chan]

From: Sathya Perla <sathya.perla@broadcom.com>

This patch adds support for offloading TC based flow
rules and actions for the 'flower' classifier in the bnxt_en driver.
It includes logic to parse flow rules and actions received from the
TC subsystem, store them and issue the corresponding
hwrm_cfa_flow_alloc/free FW cmds. L2/IPv4/IPv6 flows and drop,
redir, vlan push/pop actions are supported in this patch.

In this patch the hwrm_cfa_flow_xxx routines are just stubs.
The code for these routines is introduced in the next patch for easier
review. Also, the code to query the TC/flower action stats will
be introduced in a subsequent patch.

Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/Kconfig         |   9 +
 drivers/net/ethernet/broadcom/bnxt/Makefile   |   2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     |  39 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  23 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c  | 602 ++++++++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h  | 158 +++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c |  18 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h |   8 +
 8 files changed, 850 insertions(+), 9 deletions(-)
 create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
 create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 1456cb1..67134ec 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -212,6 +212,15 @@ config BNXT_SRIOV
 	  Virtualization support in the NetXtreme-C/E products. This
 	  allows for virtual function acceleration in virtual environments.
 
+config BNXT_FLOWER_OFFLOAD
+	bool "TC Flower offload support for NetXtreme-C/E"
+	depends on BNXT
+	default y
+	---help---
+	  This configuration parameter enables TC Flower packet classifier
+	  offload for eswitch.  This option enables SR-IOV switchdev eswitch
+	  offload.
+
 config BNXT_DCB
 	bool "Data Center Bridging (DCB) Support"
 	default n
diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile
index d141a22..4f0cb8e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/Makefile
+++ b/drivers/net/ethernet/broadcom/bnxt/Makefile
@@ -1,3 +1,3 @@
 obj-$(CONFIG_BNXT) += bnxt_en.o
 
-bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o
+bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_tc.o
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4406f91..d6367c1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -50,6 +50,7 @@
 #include <linux/bitmap.h>
 #include <linux/cpu_rmap.h>
 #include <linux/cpumask.h>
+#include <net/pkt_cls.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -59,6 +60,7 @@
 #include "bnxt_dcb.h"
 #include "bnxt_xdp.h"
 #include "bnxt_vfr.h"
+#include "bnxt_tc.h"
 
 #define BNXT_TX_TIMEOUT		(5 * HZ)
 
@@ -7305,17 +7307,33 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	return 0;
 }
 
-static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
-			 void *type_data)
+static int bnxt_setup_flower(struct net_device *dev,
+			     struct tc_cls_flower_offload *cls_flower)
 {
-	struct tc_mqprio_qopt *mqprio = type_data;
+	struct bnxt *bp = netdev_priv(dev);
 
-	if (type != TC_SETUP_MQPRIO)
+	if (BNXT_VF(bp))
 		return -EOPNOTSUPP;
 
-	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	return bnxt_tc_setup_flower(bp, bp->pf.fw_fid, cls_flower);
+}
+
+static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			 void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return bnxt_setup_flower(dev, type_data);
+	case TC_SETUP_MQPRIO: {
+		struct tc_mqprio_qopt *mqprio = type_data;
+
+		mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
 
-	return bnxt_setup_mq_tc(dev, mqprio->num_tc);
+		return bnxt_setup_mq_tc(dev, mqprio->num_tc);
+	}
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 #ifdef CONFIG_RFS_ACCEL
@@ -7711,6 +7729,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
+	bnxt_shutdown_tc(bp);
 	cancel_work_sync(&bp->sp_task);
 	bp->sp_event = 0;
 
@@ -8102,9 +8121,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	else
 		device_set_wakeup_capable(&pdev->dev, false);
 
+	if (BNXT_PF(bp))
+		bnxt_init_tc(bp);
+
 	rc = register_netdev(dev);
 	if (rc)
-		goto init_err_clr_int;
+		goto init_err_cleanup_tc;
 
 	if (BNXT_PF(bp))
 		bnxt_dl_register(bp);
@@ -8117,7 +8139,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 
-init_err_clr_int:
+init_err_cleanup_tc:
+	bnxt_shutdown_tc(bp);
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 86af8ea..7b888d4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -19,6 +19,7 @@
 #define DRV_VER_UPD	0
 
 #include <linux/interrupt.h>
+#include <linux/rhashtable.h>
 #include <net/devlink.h>
 #include <net/dst_metadata.h>
 #include <net/switchdev.h>
@@ -943,6 +944,27 @@ struct bnxt_test_info {
 #define BNXT_CAG_REG_LEGACY_INT_STATUS	0x4014
 #define BNXT_CAG_REG_BASE		0x300000
 
+struct bnxt_tc_info {
+	bool				enabled;
+
+	/* hash table to store TC offloaded flows */
+	struct rhashtable		flow_table;
+	struct rhashtable_params	flow_ht_params;
+
+	/* hash table to store L2 keys of TC flows */
+	struct rhashtable		l2_table;
+	struct rhashtable_params	l2_ht_params;
+
+	/* lock to atomically add/del an l2 node when a flow is
+	 * added or deleted.
+	 */
+	struct mutex			lock;
+
+	/* Stat counter mask (width) */
+	u64				bytes_mask;
+	u64				packets_mask;
+};
+
 struct bnxt_vf_rep_stats {
 	u64			packets;
 	u64			bytes;
@@ -1289,6 +1311,7 @@ struct bnxt {
 	enum devlink_eswitch_mode eswitch_mode;
 	struct bnxt_vf_rep	**vf_reps; /* array of vf-rep ptrs */
 	u16			*cfa_code_map; /* cfa_code -> vf_idx map */
+	struct bnxt_tc_info	tc_info;
 };
 
 #define BNXT_RX_STATS_OFFSET(counter)			\
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
new file mode 100644
index 0000000..a10df27
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -0,0 +1,602 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/if_vlan.h>
+#include <net/flow_dissector.h>
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gact.h>
+#include <net/tc_act/tc_skbedit.h>
+#include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_vlan.h>
+
+#include "bnxt_hsi.h"
+#include "bnxt.h"
+#include "bnxt_sriov.h"
+#include "bnxt_tc.h"
+#include "bnxt_vfr.h"
+
+#ifdef CONFIG_BNXT_FLOWER_OFFLOAD
+
+#define BNXT_FID_INVALID			0xffff
+#define VLAN_TCI(vid, prio)	((vid) | ((prio) << VLAN_PRIO_SHIFT))
+
+/* Return the dst fid of the func for flow forwarding
+ * For PFs: src_fid is the fid of the PF
+ * For VF-reps: src_fid the fid of the VF
+ */
+static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev)
+{
+	struct bnxt *bp;
+
+	/* check if dev belongs to the same switch */
+	if (!switchdev_port_same_parent_id(pf_bp->dev, dev)) {
+		netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch",
+			    dev->ifindex);
+		return BNXT_FID_INVALID;
+	}
+
+	/* Is dev a VF-rep? */
+	if (dev != pf_bp->dev)
+		return bnxt_vf_rep_get_fid(dev);
+
+	bp = netdev_priv(dev);
+	return bp->pf.fw_fid;
+}
+
+static int bnxt_tc_parse_redir(struct bnxt *bp,
+			       struct bnxt_tc_actions *actions,
+			       const struct tc_action *tc_act)
+{
+	int ifindex = tcf_mirred_ifindex(tc_act);
+	struct net_device *dev;
+	u16 dst_fid;
+
+	dev = __dev_get_by_index(dev_net(bp->dev), ifindex);
+	if (!dev) {
+		netdev_info(bp->dev, "no dev for ifindex=%d", ifindex);
+		return -EINVAL;
+	}
+
+	/* find the FID from dev */
+	dst_fid = bnxt_flow_get_dst_fid(bp, dev);
+	if (dst_fid == BNXT_FID_INVALID) {
+		netdev_info(bp->dev, "can't get fid for ifindex=%d", ifindex);
+		return -EINVAL;
+	}
+
+	actions->flags |= BNXT_TC_ACTION_FLAG_FWD;
+	actions->dst_fid = dst_fid;
+	actions->dst_dev = dev;
+	return 0;
+}
+
+static void bnxt_tc_parse_vlan(struct bnxt *bp,
+			       struct bnxt_tc_actions *actions,
+			       const struct tc_action *tc_act)
+{
+	if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_POP) {
+		actions->flags |= BNXT_TC_ACTION_FLAG_POP_VLAN;
+	} else if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_PUSH) {
+		actions->flags |= BNXT_TC_ACTION_FLAG_PUSH_VLAN;
+		actions->push_vlan_tci = htons(tcf_vlan_push_vid(tc_act));
+		actions->push_vlan_tpid = tcf_vlan_push_proto(tc_act);
+	}
+}
+
+static int bnxt_tc_parse_actions(struct bnxt *bp,
+				 struct bnxt_tc_actions *actions,
+				 struct tcf_exts *tc_exts)
+{
+	const struct tc_action *tc_act;
+	LIST_HEAD(tc_actions);
+	int rc;
+
+	if (!tcf_exts_has_actions(tc_exts)) {
+		netdev_info(bp->dev, "no actions");
+		return -EINVAL;
+	}
+
+	tcf_exts_to_list(tc_exts, &tc_actions);
+	list_for_each_entry(tc_act, &tc_actions, list) {
+		/* Drop action */
+		if (is_tcf_gact_shot(tc_act)) {
+			actions->flags |= BNXT_TC_ACTION_FLAG_DROP;
+			return 0; /* don't bother with other actions */
+		}
+
+		/* Redirect action */
+		if (is_tcf_mirred_egress_redirect(tc_act)) {
+			rc = bnxt_tc_parse_redir(bp, actions, tc_act);
+			if (rc)
+				return rc;
+			continue;
+		}
+
+		/* Push/pop VLAN */
+		if (is_tcf_vlan(tc_act)) {
+			bnxt_tc_parse_vlan(bp, actions, tc_act);
+			continue;
+		}
+	}
+
+	return 0;
+}
+
+#define GET_KEY(flow_cmd, key_type)					\
+		skb_flow_dissector_target((flow_cmd)->dissector, key_type,\
+					  (flow_cmd)->key)
+#define GET_MASK(flow_cmd, key_type)					\
+		skb_flow_dissector_target((flow_cmd)->dissector, key_type,\
+					  (flow_cmd)->mask)
+
+static int bnxt_tc_parse_flow(struct bnxt *bp,
+			      struct tc_cls_flower_offload *tc_flow_cmd,
+			      struct bnxt_tc_flow *flow)
+{
+	struct flow_dissector *dissector = tc_flow_cmd->dissector;
+	u16 addr_type = 0;
+
+	/* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */
+	if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 ||
+	    (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) == 0) {
+		netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x",
+			    dissector->used_keys);
+		return -EOPNOTSUPP;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_dissector_key_control *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_CONTROL);
+
+		addr_type = key->addr_type;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC);
+		struct flow_dissector_key_basic *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC);
+
+		flow->l2_key.ether_type = key->n_proto;
+		flow->l2_mask.ether_type = mask->n_proto;
+
+		if (key->n_proto == htons(ETH_P_IP) ||
+		    key->n_proto == htons(ETH_P_IPV6)) {
+			flow->l4_key.ip_proto = key->ip_proto;
+			flow->l4_mask.ip_proto = mask->ip_proto;
+		}
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_dissector_key_eth_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS);
+		struct flow_dissector_key_eth_addrs *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_ETH_ADDRS;
+		ether_addr_copy(flow->l2_key.dmac, key->dst);
+		ether_addr_copy(flow->l2_mask.dmac, mask->dst);
+		ether_addr_copy(flow->l2_key.smac, key->src);
+		ether_addr_copy(flow->l2_mask.smac, mask->src);
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_dissector_key_vlan *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN);
+		struct flow_dissector_key_vlan *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN);
+
+		flow->l2_key.inner_vlan_tci =
+		   cpu_to_be16(VLAN_TCI(key->vlan_id, key->vlan_priority));
+		flow->l2_mask.inner_vlan_tci =
+		   cpu_to_be16((VLAN_TCI(mask->vlan_id, mask->vlan_priority)));
+		flow->l2_key.inner_vlan_tpid = htons(ETH_P_8021Q);
+		flow->l2_mask.inner_vlan_tpid = htons(0xffff);
+		flow->l2_key.num_vlans = 1;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_dissector_key_ipv4_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+		struct flow_dissector_key_ipv4_addrs *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_IPV4_ADDRS;
+		flow->l3_key.ipv4.daddr.s_addr = key->dst;
+		flow->l3_mask.ipv4.daddr.s_addr = mask->dst;
+		flow->l3_key.ipv4.saddr.s_addr = key->src;
+		flow->l3_mask.ipv4.saddr.s_addr = mask->src;
+	} else if (dissector_uses_key(dissector,
+				      FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_dissector_key_ipv6_addrs *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
+		struct flow_dissector_key_ipv6_addrs *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_IPV6_ADDRS;
+		flow->l3_key.ipv6.daddr = key->dst;
+		flow->l3_mask.ipv6.daddr = mask->dst;
+		flow->l3_key.ipv6.saddr = key->src;
+		flow->l3_mask.ipv6.saddr = mask->src;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_dissector_key_ports *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS);
+		struct flow_dissector_key_ports *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_PORTS;
+		flow->l4_key.ports.dport = key->dst;
+		flow->l4_mask.ports.dport = mask->dst;
+		flow->l4_key.ports.sport = key->src;
+		flow->l4_mask.ports.sport = mask->src;
+	}
+
+	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ICMP)) {
+		struct flow_dissector_key_icmp *key =
+			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP);
+		struct flow_dissector_key_icmp *mask =
+			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP);
+
+		flow->flags |= BNXT_TC_FLOW_FLAGS_ICMP;
+		flow->l4_key.icmp.type = key->type;
+		flow->l4_key.icmp.code = key->code;
+		flow->l4_mask.icmp.type = mask->type;
+		flow->l4_mask.icmp.code = mask->code;
+	}
+
+	return bnxt_tc_parse_actions(bp, &flow->actions, tc_flow_cmd->exts);
+}
+
+static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, __le16 flow_handle)
+{
+	return 0;
+}
+
+static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
+				    __le16 ref_flow_handle, __le16 *flow_handle)
+{
+	return 0;
+}
+
+static int bnxt_tc_put_l2_node(struct bnxt *bp,
+			       struct bnxt_tc_flow_node *flow_node)
+{
+	struct bnxt_tc_l2_node *l2_node = flow_node->l2_node;
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	int rc;
+
+	/* remove flow_node from the L2 shared flow list */
+	list_del(&flow_node->l2_list_node);
+	if (--l2_node->refcount == 0) {
+		rc =  rhashtable_remove_fast(&tc_info->l2_table, &l2_node->node,
+					     tc_info->l2_ht_params);
+		if (rc)
+			netdev_err(bp->dev,
+				   "Error: %s: rhashtable_remove_fast: %d",
+				   __func__, rc);
+		kfree_rcu(l2_node, rcu);
+	}
+	return 0;
+}
+
+static struct bnxt_tc_l2_node *
+bnxt_tc_get_l2_node(struct bnxt *bp, struct rhashtable *l2_table,
+		    struct rhashtable_params ht_params,
+		    struct bnxt_tc_l2_key *l2_key)
+{
+	struct bnxt_tc_l2_node *l2_node;
+	int rc;
+
+	l2_node = rhashtable_lookup_fast(l2_table, l2_key, ht_params);
+	if (!l2_node) {
+		l2_node = kzalloc(sizeof(*l2_node), GFP_KERNEL);
+		if (!l2_node) {
+			rc = -ENOMEM;
+			return NULL;
+		}
+
+		l2_node->key = *l2_key;
+		rc = rhashtable_insert_fast(l2_table, &l2_node->node,
+					    ht_params);
+		if (rc) {
+			kfree(l2_node);
+			netdev_err(bp->dev,
+				   "Error: %s: rhashtable_insert_fast: %d",
+				   __func__, rc);
+			return NULL;
+		}
+		INIT_LIST_HEAD(&l2_node->common_l2_flows);
+	}
+	return l2_node;
+}
+
+/* Get the ref_flow_handle for a flow by checking if there are any other
+ * flows that share the same L2 key as this flow.
+ */
+static int
+bnxt_tc_get_ref_flow_handle(struct bnxt *bp, struct bnxt_tc_flow *flow,
+			    struct bnxt_tc_flow_node *flow_node,
+			    __le16 *ref_flow_handle)
+{
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_flow_node *ref_flow_node;
+	struct bnxt_tc_l2_node *l2_node;
+
+	l2_node = bnxt_tc_get_l2_node(bp, &tc_info->l2_table,
+				      tc_info->l2_ht_params,
+				      &flow->l2_key);
+	if (!l2_node)
+		return -1;
+
+	/* If any other flow is using this l2_node, use it's flow_handle
+	 * as the ref_flow_handle
+	 */
+	if (l2_node->refcount > 0) {
+		ref_flow_node = list_first_entry(&l2_node->common_l2_flows,
+						 struct bnxt_tc_flow_node,
+						 l2_list_node);
+		*ref_flow_handle = ref_flow_node->flow_handle;
+	} else {
+		*ref_flow_handle = cpu_to_le16(0xffff);
+	}
+
+	/* Insert the l2_node into the flow_node so that subsequent flows
+	 * with a matching l2 key can use the flow_handle of this flow
+	 * as their ref_flow_handle
+	 */
+	flow_node->l2_node = l2_node;
+	list_add(&flow_node->l2_list_node, &l2_node->common_l2_flows);
+	l2_node->refcount++;
+	return 0;
+}
+
+/* After the flow parsing is done, this routine is used for checking
+ * if there are any aspects of the flow that prevent it from being
+ * offloaded.
+ */
+static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow)
+{
+	/* If L4 ports are specified then ip_proto must be TCP or UDP */
+	if ((flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) &&
+	    (flow->l4_key.ip_proto != IPPROTO_TCP &&
+	     flow->l4_key.ip_proto != IPPROTO_UDP)) {
+		netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports",
+			    flow->l4_key.ip_proto);
+		return false;
+	}
+
+	return true;
+}
+
+static int __bnxt_tc_del_flow(struct bnxt *bp,
+			      struct bnxt_tc_flow_node *flow_node)
+{
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	int rc;
+
+	/* send HWRM cmd to free the flow-id */
+	bnxt_hwrm_cfa_flow_free(bp, flow_node->flow_handle);
+
+	mutex_lock(&tc_info->lock);
+
+	/* release reference to l2 node */
+	bnxt_tc_put_l2_node(bp, flow_node);
+
+	mutex_unlock(&tc_info->lock);
+
+	rc = rhashtable_remove_fast(&tc_info->flow_table, &flow_node->node,
+				    tc_info->flow_ht_params);
+	if (rc)
+		netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d",
+			   __func__, rc);
+
+	kfree_rcu(flow_node, rcu);
+	return 0;
+}
+
+/* Add a new flow or replace an existing flow.
+ * Notes on locking:
+ * There are essentially two critical sections here.
+ * 1. while adding a new flow
+ *    a) lookup l2-key
+ *    b) issue HWRM cmd and get flow_handle
+ *    c) link l2-key with flow
+ * 2. while deleting a flow
+ *    a) unlinking l2-key from flow
+ * A lock is needed to protect these two critical sections.
+ *
+ * The hash-tables are already protected by the rhashtable API.
+ */
+static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
+			    struct tc_cls_flower_offload *tc_flow_cmd)
+{
+	struct bnxt_tc_flow_node *new_node, *old_node;
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_flow *flow;
+	__le16 ref_flow_handle;
+	int rc;
+
+	/* allocate memory for the new flow and it's node */
+	new_node = kzalloc(sizeof(*new_node), GFP_KERNEL);
+	if (!new_node) {
+		rc = -ENOMEM;
+		goto done;
+	}
+	new_node->cookie = tc_flow_cmd->cookie;
+	flow = &new_node->flow;
+
+	rc = bnxt_tc_parse_flow(bp, tc_flow_cmd, flow);
+	if (rc)
+		goto free_node;
+	flow->src_fid = src_fid;
+
+	if (!bnxt_tc_can_offload(bp, flow)) {
+		rc = -ENOSPC;
+		goto free_node;
+	}
+
+	/* If a flow exists with the same cookie, delete it */
+	old_node = rhashtable_lookup_fast(&tc_info->flow_table,
+					  &tc_flow_cmd->cookie,
+					  tc_info->flow_ht_params);
+	if (old_node)
+		__bnxt_tc_del_flow(bp, old_node);
+
+	/* Check if the L2 part of the flow has been offloaded already.
+	 * If so, bump up it's refcnt and get it's reference handle.
+	 */
+	mutex_lock(&tc_info->lock);
+	rc = bnxt_tc_get_ref_flow_handle(bp, flow, new_node, &ref_flow_handle);
+	if (rc)
+		goto unlock;
+
+	/* send HWRM cmd to alloc the flow */
+	rc = bnxt_hwrm_cfa_flow_alloc(bp, flow, ref_flow_handle,
+				      &new_node->flow_handle);
+	if (rc)
+		goto put_l2;
+
+	/* add new flow to flow-table */
+	rc = rhashtable_insert_fast(&tc_info->flow_table, &new_node->node,
+				    tc_info->flow_ht_params);
+	if (rc)
+		goto hwrm_flow_free;
+
+	mutex_unlock(&tc_info->lock);
+	return 0;
+
+hwrm_flow_free:
+	bnxt_hwrm_cfa_flow_free(bp, new_node->flow_handle);
+put_l2:
+	bnxt_tc_put_l2_node(bp, new_node);
+unlock:
+	mutex_unlock(&tc_info->lock);
+free_node:
+	kfree(new_node);
+done:
+	netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d",
+		   __func__, tc_flow_cmd->cookie, rc);
+	return rc;
+}
+
+static int bnxt_tc_del_flow(struct bnxt *bp,
+			    struct tc_cls_flower_offload *tc_flow_cmd)
+{
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_flow_node *flow_node;
+
+	flow_node = rhashtable_lookup_fast(&tc_info->flow_table,
+					   &tc_flow_cmd->cookie,
+					   tc_info->flow_ht_params);
+	if (!flow_node) {
+		netdev_info(bp->dev, "ERROR: no flow_node for cookie %lx",
+			    tc_flow_cmd->cookie);
+		return -EINVAL;
+	}
+
+	return __bnxt_tc_del_flow(bp, flow_node);
+}
+
+static int bnxt_tc_get_flow_stats(struct bnxt *bp,
+				  struct tc_cls_flower_offload *tc_flow_cmd)
+{
+	return 0;
+}
+
+int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
+			 struct tc_cls_flower_offload *cls_flower)
+{
+	int rc = 0;
+
+	switch (cls_flower->command) {
+	case TC_CLSFLOWER_REPLACE:
+		rc = bnxt_tc_add_flow(bp, src_fid, cls_flower);
+		break;
+
+	case TC_CLSFLOWER_DESTROY:
+		rc = bnxt_tc_del_flow(bp, cls_flower);
+		break;
+
+	case TC_CLSFLOWER_STATS:
+		rc = bnxt_tc_get_flow_stats(bp, cls_flower);
+		break;
+	}
+	return rc;
+}
+
+static const struct rhashtable_params bnxt_tc_flow_ht_params = {
+	.head_offset = offsetof(struct bnxt_tc_flow_node, node),
+	.key_offset = offsetof(struct bnxt_tc_flow_node, cookie),
+	.key_len = sizeof(((struct bnxt_tc_flow_node *)0)->cookie),
+	.automatic_shrinking = true
+};
+
+static const struct rhashtable_params bnxt_tc_l2_ht_params = {
+	.head_offset = offsetof(struct bnxt_tc_l2_node, node),
+	.key_offset = offsetof(struct bnxt_tc_l2_node, key),
+	.key_len = BNXT_TC_L2_KEY_LEN,
+	.automatic_shrinking = true
+};
+
+/* convert counter width in bits to a mask */
+#define mask(width)		((u64)~0 >> (64 - (width)))
+
+int bnxt_init_tc(struct bnxt *bp)
+{
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10800) {
+		netdev_warn(bp->dev,
+			    "Firmware does not support TC flower offload.\n");
+		return -ENOTSUPP;
+	}
+	mutex_init(&tc_info->lock);
+
+	/* Counter widths are programmed by FW */
+	tc_info->bytes_mask = mask(36);
+	tc_info->packets_mask = mask(28);
+
+	tc_info->flow_ht_params = bnxt_tc_flow_ht_params;
+	rc = rhashtable_init(&tc_info->flow_table, &tc_info->flow_ht_params);
+	if (rc)
+		return rc;
+
+	tc_info->l2_ht_params = bnxt_tc_l2_ht_params;
+	rc = rhashtable_init(&tc_info->l2_table, &tc_info->l2_ht_params);
+	if (rc)
+		goto destroy_flow_table;
+
+	tc_info->enabled = true;
+	bp->dev->hw_features |= NETIF_F_HW_TC;
+	bp->dev->features |= NETIF_F_HW_TC;
+	return 0;
+
+destroy_flow_table:
+	rhashtable_destroy(&tc_info->flow_table);
+	return rc;
+}
+
+void bnxt_shutdown_tc(struct bnxt *bp)
+{
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+
+	if (!tc_info->enabled)
+		return;
+
+	rhashtable_destroy(&tc_info->flow_table);
+	rhashtable_destroy(&tc_info->l2_table);
+}
+
+#else
+#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
new file mode 100644
index 0000000..6c4c1ed
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
@@ -0,0 +1,158 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2017 Broadcom Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_TC_H
+#define BNXT_TC_H
+
+#ifdef CONFIG_BNXT_FLOWER_OFFLOAD
+
+/* Structs used for storing the filter/actions of the TC cmd.
+ */
+struct bnxt_tc_l2_key {
+	u8		dmac[ETH_ALEN];
+	u8		smac[ETH_ALEN];
+	__be16		inner_vlan_tpid;
+	__be16		inner_vlan_tci;
+	__be16		ether_type;
+	u8		num_vlans;
+};
+
+struct bnxt_tc_l3_key {
+	union {
+		struct {
+			struct in_addr daddr;
+			struct in_addr saddr;
+		} ipv4;
+		struct {
+			struct in6_addr daddr;
+			struct in6_addr saddr;
+		} ipv6;
+	};
+};
+
+struct bnxt_tc_l4_key {
+	u8  ip_proto;
+	union {
+		struct {
+			__be16 sport;
+			__be16 dport;
+		} ports;
+		struct {
+			u8 type;
+			u8 code;
+		} icmp;
+	};
+};
+
+struct bnxt_tc_actions {
+	u32				flags;
+#define BNXT_TC_ACTION_FLAG_FWD			BIT(0)
+#define BNXT_TC_ACTION_FLAG_FWD_VXLAN		BIT(1)
+#define BNXT_TC_ACTION_FLAG_PUSH_VLAN		BIT(3)
+#define BNXT_TC_ACTION_FLAG_POP_VLAN		BIT(4)
+#define BNXT_TC_ACTION_FLAG_DROP		BIT(5)
+
+	u16				dst_fid;
+	struct net_device		*dst_dev;
+	__be16				push_vlan_tpid;
+	__be16				push_vlan_tci;
+};
+
+struct bnxt_tc_flow_stats {
+	u64		packets;
+	u64		bytes;
+};
+
+struct bnxt_tc_flow {
+	u32				flags;
+#define BNXT_TC_FLOW_FLAGS_ETH_ADDRS		BIT(1)
+#define BNXT_TC_FLOW_FLAGS_IPV4_ADDRS		BIT(2)
+#define BNXT_TC_FLOW_FLAGS_IPV6_ADDRS		BIT(3)
+#define BNXT_TC_FLOW_FLAGS_PORTS		BIT(4)
+#define BNXT_TC_FLOW_FLAGS_ICMP			BIT(5)
+
+	/* flow applicable to pkts ingressing on this fid */
+	u16				src_fid;
+	struct bnxt_tc_l2_key		l2_key;
+	struct bnxt_tc_l2_key		l2_mask;
+	struct bnxt_tc_l3_key		l3_key;
+	struct bnxt_tc_l3_key		l3_mask;
+	struct bnxt_tc_l4_key		l4_key;
+	struct bnxt_tc_l4_key		l4_mask;
+
+	struct bnxt_tc_actions		actions;
+
+	/* updated stats accounting for hw-counter wrap-around */
+	struct bnxt_tc_flow_stats	stats;
+	/* previous snap-shot of stats */
+	struct bnxt_tc_flow_stats	prev_stats;
+	unsigned long			lastused; /* jiffies */
+};
+
+/* L2 hash table
+ * This data-struct is used for L2-flow table.
+ * The L2 part of a flow is stored in a hash table.
+ * A flow that shares the same L2 key/mask with an
+ * already existing flow must refer to it's flow handle.
+ */
+struct bnxt_tc_l2_node {
+	/* hash key: first 16b of key */
+#define BNXT_TC_L2_KEY_LEN			16
+	struct bnxt_tc_l2_key	key;
+	struct rhash_head	node;
+
+	/* a linked list of flows that share the same l2 key */
+	struct list_head	common_l2_flows;
+
+	/* number of flows sharing the l2 key */
+	u16			refcount;
+
+	struct rcu_head		rcu;
+};
+
+struct bnxt_tc_flow_node {
+	/* hash key: provided by TC */
+	unsigned long			cookie;
+	struct rhash_head		node;
+
+	struct bnxt_tc_flow		flow;
+
+	__le16				flow_handle;
+
+	/* L2 node in l2 hashtable that shares flow's l2 key */
+	struct bnxt_tc_l2_node		*l2_node;
+	/* for the shared_flows list maintained in l2_node */
+	struct list_head		l2_list_node;
+
+	struct rcu_head			rcu;
+};
+
+int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
+			 struct tc_cls_flower_offload *cls_flower);
+int bnxt_init_tc(struct bnxt *bp);
+void bnxt_shutdown_tc(struct bnxt *bp);
+
+#else /* CONFIG_BNXT_FLOWER_OFFLOAD */
+
+static inline int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
+				       struct tc_cls_flower_offload *cls_flower)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int bnxt_init_tc(struct bnxt *bp)
+{
+	return 0;
+}
+
+static inline void bnxt_shutdown_tc(struct bnxt *bp)
+{
+}
+#endif /* CONFIG_BNXT_FLOWER_OFFLOAD */
+#endif /* BNXT_TC_H */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index c365d3c..e75db04 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -11,10 +11,12 @@
 #include <linux/etherdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/jhash.h>
+#include <net/pkt_cls.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_vfr.h"
+#include "bnxt_tc.h"
 
 #ifdef CONFIG_BNXT_SRIOV
 
@@ -113,6 +115,21 @@ static netdev_tx_t bnxt_vf_rep_xmit(struct sk_buff *skb,
 	stats->tx_bytes = vf_rep->tx_stats.bytes;
 }
 
+static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
+				void *type_data)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+	struct bnxt *bp = vf_rep->bp;
+	int vf_fid = bp->pf.vf[vf_rep->vf_idx].fw_fid;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return bnxt_tc_setup_flower(bp, vf_fid, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code)
 {
 	u16 vf_idx;
@@ -182,6 +199,7 @@ static int bnxt_vf_rep_port_attr_get(struct net_device *dev,
 	.ndo_stop		= bnxt_vf_rep_close,
 	.ndo_start_xmit		= bnxt_vf_rep_xmit,
 	.ndo_get_stats64	= bnxt_vf_rep_get_stats64,
+	.ndo_setup_tc		= bnxt_vf_rep_setup_tc,
 	.ndo_get_phys_port_name = bnxt_vf_rep_get_phys_port_name
 };
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
index 3e997c9..d8b5f89 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h
@@ -45,6 +45,14 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
 void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb);
 struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code);
 
+static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev)
+{
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+	struct bnxt *bp = vf_rep->bp;
+
+	return bp->pf.vf[vf_rep->vf_idx].fw_fid;
+}
+
 #else
 
 static inline int bnxt_dl_register(struct bnxt *bp)
-- 
1.8.3.1

[PATCH net-next 10/11] bnxt_en: add TC flower offload flow_alloc/free FW cmds

[Michael Chan]

From: Sathya Perla <sathya.perla@broadcom.com>

This patch adds the hwrm_cfa_flow_alloc/free() routines
that are needed to issue the FW cmds needed for TC flower offload.

Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 141 ++++++++++++++++++++++++++-
 1 file changed, 139 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index a10df27..5fa0835 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -259,13 +259,150 @@ static int bnxt_tc_parse_flow(struct bnxt *bp,
 
 static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, __le16 flow_handle)
 {
-	return 0;
+	struct hwrm_cfa_flow_free_input req = { 0 };
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_FREE, -1, -1);
+	req.flow_handle = flow_handle;
+
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		netdev_info(bp->dev, "Error: %s: flow_handle=0x%x rc=%d",
+			    __func__, flow_handle, rc);
+	return rc;
+}
+
+static int ipv6_mask_len(struct in6_addr *mask)
+{
+	int mask_len = 0, i;
+
+	for (i = 0; i < 4; i++)
+		mask_len += inet_mask_len(mask->s6_addr32[i]);
+
+	return mask_len;
+}
+
+static bool is_wildcard(void *mask, int len)
+{
+	const u8 *p = mask;
+	int i;
+
+	for (i = 0; i < len; i++) {
+		if (p[i] != 0)
+			return false;
+	}
+	return true;
 }
 
 static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 				    __le16 ref_flow_handle, __le16 *flow_handle)
 {
-	return 0;
+	struct hwrm_cfa_flow_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	struct bnxt_tc_actions *actions = &flow->actions;
+	struct bnxt_tc_l3_key *l3_mask = &flow->l3_mask;
+	struct bnxt_tc_l3_key *l3_key = &flow->l3_key;
+	struct hwrm_cfa_flow_alloc_input req = { 0 };
+	u16 flow_flags = 0, action_flags = 0;
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_ALLOC, -1, -1);
+
+	req.src_fid = cpu_to_le16(flow->src_fid);
+	req.ref_flow_handle = ref_flow_handle;
+	req.ethertype = flow->l2_key.ether_type;
+	req.ip_proto = flow->l4_key.ip_proto;
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_ETH_ADDRS) {
+		memcpy(req.dmac, flow->l2_key.dmac, ETH_ALEN);
+		memcpy(req.smac, flow->l2_key.smac, ETH_ALEN);
+	}
+
+	if (flow->l2_key.num_vlans > 0) {
+		flow_flags |= CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_ONE;
+		/* FW expects the inner_vlan_tci value to be set
+		 * in outer_vlan_tci when num_vlans is 1 (which is
+		 * always the case in TC.)
+		 */
+		req.outer_vlan_tci = flow->l2_key.inner_vlan_tci;
+	}
+
+	/* If all IP and L4 fields are wildcarded then this is an L2 flow */
+	if (is_wildcard(&l3_mask, sizeof(l3_mask)) &&
+	    is_wildcard(&flow->l4_mask, sizeof(flow->l4_mask))) {
+		flow_flags |= CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2;
+	} else {
+		flow_flags |= flow->l2_key.ether_type == htons(ETH_P_IP) ?
+				CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV4 :
+				CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6;
+
+		if (flow->flags & BNXT_TC_FLOW_FLAGS_IPV4_ADDRS) {
+			req.ip_dst[0] = l3_key->ipv4.daddr.s_addr;
+			req.ip_dst_mask_len =
+				inet_mask_len(l3_mask->ipv4.daddr.s_addr);
+			req.ip_src[0] = l3_key->ipv4.saddr.s_addr;
+			req.ip_src_mask_len =
+				inet_mask_len(l3_mask->ipv4.saddr.s_addr);
+		} else if (flow->flags & BNXT_TC_FLOW_FLAGS_IPV6_ADDRS) {
+			memcpy(req.ip_dst, l3_key->ipv6.daddr.s6_addr32,
+			       sizeof(req.ip_dst));
+			req.ip_dst_mask_len =
+					ipv6_mask_len(&l3_mask->ipv6.daddr);
+			memcpy(req.ip_src, l3_key->ipv6.saddr.s6_addr32,
+			       sizeof(req.ip_src));
+			req.ip_src_mask_len =
+					ipv6_mask_len(&l3_mask->ipv6.saddr);
+		}
+	}
+
+	if (flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) {
+		req.l4_src_port = flow->l4_key.ports.sport;
+		req.l4_src_port_mask = flow->l4_mask.ports.sport;
+		req.l4_dst_port = flow->l4_key.ports.dport;
+		req.l4_dst_port_mask = flow->l4_mask.ports.dport;
+	} else if (flow->flags & BNXT_TC_FLOW_FLAGS_ICMP) {
+		/* l4 ports serve as type/code when ip_proto is ICMP */
+		req.l4_src_port = htons(flow->l4_key.icmp.type);
+		req.l4_src_port_mask = htons(flow->l4_mask.icmp.type);
+		req.l4_dst_port = htons(flow->l4_key.icmp.code);
+		req.l4_dst_port_mask = htons(flow->l4_mask.icmp.code);
+	}
+	req.flags = cpu_to_le16(flow_flags);
+
+	if (actions->flags & BNXT_TC_ACTION_FLAG_DROP) {
+		action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP;
+	} else {
+		if (actions->flags & BNXT_TC_ACTION_FLAG_FWD) {
+			action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD;
+			req.dst_fid = cpu_to_le16(actions->dst_fid);
+		}
+		if (actions->flags & BNXT_TC_ACTION_FLAG_PUSH_VLAN) {
+			action_flags |=
+			    CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE;
+			req.l2_rewrite_vlan_tpid = actions->push_vlan_tpid;
+			req.l2_rewrite_vlan_tci = actions->push_vlan_tci;
+			memcpy(&req.l2_rewrite_dmac, &req.dmac, ETH_ALEN);
+			memcpy(&req.l2_rewrite_smac, &req.smac, ETH_ALEN);
+		}
+		if (actions->flags & BNXT_TC_ACTION_FLAG_POP_VLAN) {
+			action_flags |=
+			    CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE;
+			/* Rewrite config with tpid = 0 implies vlan pop */
+			req.l2_rewrite_vlan_tpid = 0;
+			memcpy(&req.l2_rewrite_dmac, &req.dmac, ETH_ALEN);
+			memcpy(&req.l2_rewrite_smac, &req.smac, ETH_ALEN);
+		}
+	}
+	req.action_flags = cpu_to_le16(action_flags);
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*flow_handle = resp->flow_handle;
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+
+	return rc;
 }
 
 static int bnxt_tc_put_l2_node(struct bnxt *bp,
-- 
1.8.3.1

[PATCH net-next 11/11] bnxt_en: add code to query TC flower offload stats

[Michael Chan]

From: Sathya Perla <sathya.perla@broadcom.com>

This patch adds code to implement TC_CLSFLOWER_STATS TC-cmd and the
required FW code to query the stats from the HW.

Signed-off-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 95 ++++++++++++++++++++++++++++
 1 file changed, 95 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 5fa0835..ccd699f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -405,6 +405,81 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 	return rc;
 }
 
+/* Add val to accum while handling a possible wraparound
+ * of val. Eventhough val is of type u64, its actual width
+ * is denoted by mask and will wrap-around beyond that width.
+ */
+static void accumulate_val(u64 *accum, u64 val, u64 mask)
+{
+#define low_bits(x, mask)		((x) & (mask))
+#define high_bits(x, mask)		((x) & ~(mask))
+	bool wrapped = val < low_bits(*accum, mask);
+
+	*accum = high_bits(*accum, mask) + val;
+	if (wrapped)
+		*accum += (mask + 1);
+}
+
+/* The HW counters' width is much less than 64bits.
+ * Handle possible wrap-around while updating the stat counters
+ */
+static void bnxt_flow_stats_fix_wraparound(struct bnxt_tc_info *tc_info,
+					   struct bnxt_tc_flow_stats *stats,
+					   struct bnxt_tc_flow_stats *hw_stats)
+{
+	accumulate_val(&stats->bytes, hw_stats->bytes, tc_info->bytes_mask);
+	accumulate_val(&stats->packets, hw_stats->packets,
+		       tc_info->packets_mask);
+}
+
+/* Fix possible wraparound of the stats queried from HW, calculate
+ * the delta from prev_stats, and also update the prev_stats.
+ * The HW flow stats are fetched under the hwrm_cmd_lock mutex.
+ * This routine is best called while under the mutex so that the
+ * stats processing happens atomically.
+ */
+static void bnxt_flow_stats_calc(struct bnxt_tc_info *tc_info,
+				 struct bnxt_tc_flow *flow,
+				 struct bnxt_tc_flow_stats *stats)
+{
+	struct bnxt_tc_flow_stats *acc_stats, *prev_stats;
+
+	acc_stats = &flow->stats;
+	bnxt_flow_stats_fix_wraparound(tc_info, acc_stats, stats);
+
+	prev_stats = &flow->prev_stats;
+	stats->bytes = acc_stats->bytes - prev_stats->bytes;
+	stats->packets = acc_stats->packets - prev_stats->packets;
+	*prev_stats = *acc_stats;
+}
+
+static int bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp,
+					__le16 flow_handle,
+					struct bnxt_tc_flow *flow,
+					struct bnxt_tc_flow_stats *stats)
+{
+	struct hwrm_cfa_flow_stats_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_flow_stats_input req = { 0 };
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_STATS, -1, -1);
+	req.num_flows = cpu_to_le16(1);
+	req.flow_handle_0 = flow_handle;
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		stats->packets = le64_to_cpu(resp->packet_0);
+		stats->bytes = le64_to_cpu(resp->byte_0);
+		bnxt_flow_stats_calc(&bp->tc_info, flow, stats);
+	} else {
+		netdev_info(bp->dev, "error rc=%d", rc);
+	}
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
 static int bnxt_tc_put_l2_node(struct bnxt *bp,
 			       struct bnxt_tc_flow_node *flow_node)
 {
@@ -647,6 +722,26 @@ static int bnxt_tc_del_flow(struct bnxt *bp,
 static int bnxt_tc_get_flow_stats(struct bnxt *bp,
 				  struct tc_cls_flower_offload *tc_flow_cmd)
 {
+	struct bnxt_tc_info *tc_info = &bp->tc_info;
+	struct bnxt_tc_flow_node *flow_node;
+	struct bnxt_tc_flow_stats stats;
+	int rc;
+
+	flow_node = rhashtable_lookup_fast(&tc_info->flow_table,
+					   &tc_flow_cmd->cookie,
+					   tc_info->flow_ht_params);
+	if (!flow_node) {
+		netdev_info(bp->dev, "Error: no flow_node for cookie %lx",
+			    tc_flow_cmd->cookie);
+		return -1;
+	}
+
+	rc = bnxt_hwrm_cfa_flow_stats_get(bp, flow_node->flow_handle,
+					  &flow_node->flow, &stats);
+	if (rc)
+		return rc;
+
+	tcf_exts_stats_update(tc_flow_cmd->exts, stats.bytes, stats.packets, 0);
 	return 0;
 }
 
-- 
1.8.3.1

Re: [PATCH net-next 06/11] bnxt_en: Improve -ENOMEM logic in NAPI poll loop.

[Martin KaFai Lau]

On Mon, Aug 28, 2017 at 01:40:30PM -0400, Michael Chan wrote:
> If we cannot allocate RX buffers in the NAPI poll loop when processing
> an RX event, the current code does not count that event towards the NAPI
> budget.  This can cause us to potentially loop forever in NAPI if we
> consistently cannot allocate new buffers.  Improve it by counting
> -ENOMEM event as 1 towards the NAPI budget.
>
> Cc: Martin KaFai Lau <kafai@fb.com>
> Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Thanks for fixing it.

Reported-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>

> ---
>  drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 +++++++
>  1 file changed, 7 insertions(+)
>
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> index 1afb408..a34fcdd 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> @@ -1850,6 +1850,13 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
>  							   &event);
>  			if (likely(rc >= 0))
>  				rx_pkts += rc;
> +			/* Increment rx_pkts when rc is -ENOMEM to count towards
> +			 * the NAPI budget.  Otherwise, we may potentially loop
> +			 * here forever if we consistently cannot allocate
> +			 * buffers.
> +			 */
> +			else if (rc == -ENOMEM)
> +				rx_pkts++;
>  			else if (rc == -EBUSY)	/* partial completion */
>  				break;
>  		} else if (unlikely((TX_CMP_TYPE(txcmp) ==
> --
> 1.8.3.1
>

Re: [PATCH net-next 00/11] bnxt_en: Updates.

[David Miller]

From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 28 Aug 2017 13:40:24 -0400

> Various changes including updated firmware interface, improved TX ring
> allocation scheme, improved out-of-memory logic in NAPI loop, reduced
> default rings on multi-port devices, new PCI IDs. Of particular note,
> 
> CPU affinity hints from Vasundhara Volam.
> 
> TC Flower eswitch support from Sathya Perla.

Looks good, series applied, thanks!

Re: [PATCH net-next 09/11] bnxt_en: bnxt: add TC flower filter offload support

[Jiri Pirko]

Mon, Aug 28, 2017 at 07:40:33PM CEST, michael.chan@broadcom.com wrote:
>From: Sathya Perla <sathya.perla@broadcom.com>
>
>This patch adds support for offloading TC based flow
>rules and actions for the 'flower' classifier in the bnxt_en driver.
>It includes logic to parse flow rules and actions received from the
>TC subsystem, store them and issue the corresponding
>hwrm_cfa_flow_alloc/free FW cmds. L2/IPv4/IPv6 flows and drop,
>redir, vlan push/pop actions are supported in this patch.
>
>In this patch the hwrm_cfa_flow_xxx routines are just stubs.
>The code for these routines is introduced in the next patch for easier
>review. Also, the code to query the TC/flower action stats will
>be introduced in a subsequent patch.

Hi.

You are missing checks for the offload. Please see nfp as an example:
Function nfp_flower_setup_tc:

            !is_classid_clsact_ingress(cls_flower->common.classid) ||
            cls_flower->common.chain_index)

Do you support both ingress and egress or ingress only?

You certainly don't support multichain.

Re: [PATCH net-next 09/11] bnxt_en: bnxt: add TC flower filter offload support

[Jiri Pirko]

Mon, Sep 18, 2017 at 11:43:22AM CEST, sathya.perla@broadcom.com wrote:
>On Mon, Sep 11, 2017 at 7:06 PM, Jiri Pirko <jiri@resnulli.us> wrote:
>> Mon, Aug 28, 2017 at 07:40:33PM CEST, michael.chan@broadcom.com wrote:
>>>From: Sathya Perla <sathya.perla@broadcom.com>
>>>
>>>This patch adds support for offloading TC based flow
>>>rules and actions for the 'flower' classifier in the bnxt_en driver.
>>>It includes logic to parse flow rules and actions received from the
>>>TC subsystem, store them and issue the corresponding
>>>hwrm_cfa_flow_alloc/free FW cmds. L2/IPv4/IPv6 flows and drop,
>>>redir, vlan push/pop actions are supported in this patch.
>>>
>>>In this patch the hwrm_cfa_flow_xxx routines are just stubs.
>>>The code for these routines is introduced in the next patch for easier
>>>review. Also, the code to query the TC/flower action stats will
>>>be introduced in a subsequent patch.
>>
>> Hi.
>>
>> You are missing checks for the offload. Please see nfp as an example:
>> Function nfp_flower_setup_tc:
>>
>>             !is_classid_clsact_ingress(cls_flower->common.classid) ||
>>             cls_flower->common.chain_index)
>
>Thanks for catching this...will send a patch.
>
>>
>> Do you support both ingress and egress or ingress only?
>
>Ingress only for flower offload.

Cool, the check would resolve it. Thanks!