From b356a2e729cec145a648d22ba5686357c009da25 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:31 -0500
Subject: bnxt_en: Remove busy poll logic in the driver.

Use native NAPI polling instead.  The next patch will complete the work
by switching to use napi_complete_done()

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 53 +----------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 99 -------------------------------
 2 files changed, 3 insertions(+), 149 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9608cb49a11c..b53f958ffcb8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -39,9 +39,6 @@
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
 #include <net/udp_tunnel.h>
-#ifdef CONFIG_NET_RX_BUSY_POLL
-#include <net/busy_poll.h>
-#endif
 #include <linux/workqueue.h>
 #include <linux/prefetch.h>
 #include <linux/cache.h>
@@ -1356,11 +1353,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 		rc = -ENOMEM;
 		if (likely(skb)) {
 			skb_record_rx_queue(skb, bnapi->index);
-			skb_mark_napi_id(skb, &bnapi->napi);
-			if (bnxt_busy_polling(bnapi))
-				netif_receive_skb(skb);
-			else
-				napi_gro_receive(&bnapi->napi, skb);
+			napi_gro_receive(&bnapi->napi, skb);
 			rc = 1;
 		}
 		goto next_rx_no_prod;
@@ -1460,11 +1453,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons,
 	}
 
 	skb_record_rx_queue(skb, bnapi->index);
-	skb_mark_napi_id(skb, &bnapi->napi);
-	if (bnxt_busy_polling(bnapi))
-		netif_receive_skb(skb);
-	else
-		napi_gro_receive(&bnapi->napi, skb);
+	napi_gro_receive(&bnapi->napi, skb);
 	rc = 1;
 
 next_rx:
@@ -1782,9 +1771,6 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
 	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 	int work_done = 0;
 
-	if (!bnxt_lock_napi(bnapi))
-		return budget;
-
 	while (1) {
 		work_done += bnxt_poll_work(bp, bnapi, budget - work_done);
 
@@ -1798,36 +1784,9 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
 		}
 	}
 	mmiowb();
-	bnxt_unlock_napi(bnapi);
 	return work_done;
 }
 
-#ifdef CONFIG_NET_RX_BUSY_POLL
-static int bnxt_busy_poll(struct napi_struct *napi)
-{
-	struct bnxt_napi *bnapi = container_of(napi, struct bnxt_napi, napi);
-	struct bnxt *bp = bnapi->bp;
-	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
-	int rx_work, budget = 4;
-
-	if (atomic_read(&bp->intr_sem) != 0)
-		return LL_FLUSH_FAILED;
-
-	if (!bp->link_info.link_up)
-		return LL_FLUSH_FAILED;
-
-	if (!bnxt_lock_poll(bnapi))
-		return LL_FLUSH_BUSY;
-
-	rx_work = bnxt_poll_work(bp, bnapi, budget);
-
-	BNXT_CP_DB_REARM(cpr->cp_doorbell, cpr->cp_raw_cons);
-
-	bnxt_unlock_poll(bnapi);
-	return rx_work;
-}
-#endif
-
 static void bnxt_free_tx_skbs(struct bnxt *bp)
 {
 	int i, max_idx;
@@ -5094,10 +5053,8 @@ static void bnxt_disable_napi(struct bnxt *bp)
 	if (!bp->bnapi)
 		return;
 
-	for (i = 0; i < bp->cp_nr_rings; i++) {
+	for (i = 0; i < bp->cp_nr_rings; i++)
 		napi_disable(&bp->bnapi[i]->napi);
-		bnxt_disable_poll(bp->bnapi[i]);
-	}
 }
 
 static void bnxt_enable_napi(struct bnxt *bp)
@@ -5106,7 +5063,6 @@ static void bnxt_enable_napi(struct bnxt *bp)
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		bp->bnapi[i]->in_reset = false;
-		bnxt_enable_poll(bp->bnapi[i]);
 		napi_enable(&bp->bnapi[i]->napi);
 	}
 }
@@ -6765,9 +6721,6 @@ static const struct net_device_ops bnxt_netdev_ops = {
 #endif
 	.ndo_udp_tunnel_add	= bnxt_udp_tunnel_add,
 	.ndo_udp_tunnel_del	= bnxt_udp_tunnel_del,
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	.ndo_busy_poll		= bnxt_busy_poll,
-#endif
 };
 
 static void bnxt_remove_one(struct pci_dev *pdev)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 16defe9ececc..fddc316170b2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -654,21 +654,9 @@ struct bnxt_napi {
 	struct bnxt_rx_ring_info	*rx_ring;
 	struct bnxt_tx_ring_info	*tx_ring;
 
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	atomic_t		poll_state;
-#endif
 	bool			in_reset;
 };
 
-#ifdef CONFIG_NET_RX_BUSY_POLL
-enum bnxt_poll_state_t {
-	BNXT_STATE_IDLE = 0,
-	BNXT_STATE_NAPI,
-	BNXT_STATE_POLL,
-	BNXT_STATE_DISABLE,
-};
-#endif
-
 struct bnxt_irq {
 	irq_handler_t	handler;
 	unsigned int	vector;
@@ -1141,93 +1129,6 @@ struct bnxt {
 	((offsetof(struct tx_port_stats, counter) +	\
 	  sizeof(struct rx_port_stats) + 512) / 8)
 
-#ifdef CONFIG_NET_RX_BUSY_POLL
-static inline void bnxt_enable_poll(struct bnxt_napi *bnapi)
-{
-	atomic_set(&bnapi->poll_state, BNXT_STATE_IDLE);
-}
-
-/* called from the NAPI poll routine to get ownership of a bnapi */
-static inline bool bnxt_lock_napi(struct bnxt_napi *bnapi)
-{
-	int rc = atomic_cmpxchg(&bnapi->poll_state, BNXT_STATE_IDLE,
-				BNXT_STATE_NAPI);
-
-	return rc == BNXT_STATE_IDLE;
-}
-
-static inline void bnxt_unlock_napi(struct bnxt_napi *bnapi)
-{
-	atomic_set(&bnapi->poll_state, BNXT_STATE_IDLE);
-}
-
-/* called from the busy poll routine to get ownership of a bnapi */
-static inline bool bnxt_lock_poll(struct bnxt_napi *bnapi)
-{
-	int rc = atomic_cmpxchg(&bnapi->poll_state, BNXT_STATE_IDLE,
-				BNXT_STATE_POLL);
-
-	return rc == BNXT_STATE_IDLE;
-}
-
-static inline void bnxt_unlock_poll(struct bnxt_napi *bnapi)
-{
-	atomic_set(&bnapi->poll_state, BNXT_STATE_IDLE);
-}
-
-static inline bool bnxt_busy_polling(struct bnxt_napi *bnapi)
-{
-	return atomic_read(&bnapi->poll_state) == BNXT_STATE_POLL;
-}
-
-static inline void bnxt_disable_poll(struct bnxt_napi *bnapi)
-{
-	int old;
-
-	while (1) {
-		old = atomic_cmpxchg(&bnapi->poll_state, BNXT_STATE_IDLE,
-				     BNXT_STATE_DISABLE);
-		if (old == BNXT_STATE_IDLE)
-			break;
-		usleep_range(500, 5000);
-	}
-}
-
-#else
-
-static inline void bnxt_enable_poll(struct bnxt_napi *bnapi)
-{
-}
-
-static inline bool bnxt_lock_napi(struct bnxt_napi *bnapi)
-{
-	return true;
-}
-
-static inline void bnxt_unlock_napi(struct bnxt_napi *bnapi)
-{
-}
-
-static inline bool bnxt_lock_poll(struct bnxt_napi *bnapi)
-{
-	return false;
-}
-
-static inline void bnxt_unlock_poll(struct bnxt_napi *bnapi)
-{
-}
-
-static inline bool bnxt_busy_polling(struct bnxt_napi *bnapi)
-{
-	return false;
-}
-
-static inline void bnxt_disable_poll(struct bnxt_napi *bnapi)
-{
-}
-
-#endif
-
 #define I2C_DEV_ADDR_A0				0xa0
 #define I2C_DEV_ADDR_A2				0xa2
 #define SFP_EEPROM_SFF_8472_COMP_ADDR		0x5e
-- 
cgit v1.2.3


From e7b9569102995ebc26821789628eef45bd9840d8 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:32 -0500
Subject: bnxt_en: Use napi_complete_done()

For better busy polling and GRO support.  Do not re-arm IRQ if
napi_complete_done() returns false.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b53f958ffcb8..3fbc8427be2e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1778,8 +1778,9 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
 			break;
 
 		if (!bnxt_has_work(bp, cpr)) {
-			napi_complete(napi);
-			BNXT_CP_DB_REARM(cpr->cp_doorbell, cpr->cp_raw_cons);
+			if (napi_complete_done(napi, work_done))
+				BNXT_CP_DB_REARM(cpr->cp_doorbell,
+						 cpr->cp_raw_cons);
 			break;
 		}
 	}
-- 
cgit v1.2.3


From 9d8bc09766f1a229b2d204c713a1cfc6c7fa1bb1 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:33 -0500
Subject: bnxt_en: Improve the IRQ disable sequence during shutdown.

The IRQ is disabled by writing to the completion ring doorbell.  This
should be done before the hardware completion ring is freed for correctness.
The current code disables IRQs after all the completion rings are freed.

Fix it by calling bnxt_disable_int_sync() before freeing the completion
rings.  Rearrange the code to avoid forward declaration.

Signed-off-by: Michael Chan <michael.chan@broadocm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 89 ++++++++++++++++---------------
 1 file changed, 46 insertions(+), 43 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 3fbc8427be2e..277573b3d261 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2953,6 +2953,45 @@ alloc_mem_err:
 	return rc;
 }
 
+static void bnxt_disable_int(struct bnxt *bp)
+{
+	int i;
+
+	if (!bp->bnapi)
+		return;
+
+	for (i = 0; i < bp->cp_nr_rings; i++) {
+		struct bnxt_napi *bnapi = bp->bnapi[i];
+		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
+
+		BNXT_CP_DB(cpr->cp_doorbell, cpr->cp_raw_cons);
+	}
+}
+
+static void bnxt_disable_int_sync(struct bnxt *bp)
+{
+	int i;
+
+	atomic_inc(&bp->intr_sem);
+
+	bnxt_disable_int(bp);
+	for (i = 0; i < bp->cp_nr_rings; i++)
+		synchronize_irq(bp->irq_tbl[i].vector);
+}
+
+static void bnxt_enable_int(struct bnxt *bp)
+{
+	int i;
+
+	atomic_set(&bp->intr_sem, 0);
+	for (i = 0; i < bp->cp_nr_rings; i++) {
+		struct bnxt_napi *bnapi = bp->bnapi[i];
+		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
+
+		BNXT_CP_DB_REARM(cpr->cp_doorbell, cpr->cp_raw_cons);
+	}
+}
+
 void bnxt_hwrm_cmd_hdr_init(struct bnxt *bp, void *request, u16 req_type,
 			    u16 cmpl_ring, u16 target_id)
 {
@@ -3937,6 +3976,12 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		}
 	}
 
+	/* The completion rings are about to be freed.  After that the
+	 * IRQ doorbell will not work anymore.  So we need to disable
+	 * IRQ here.
+	 */
+	bnxt_disable_int_sync(bp);
+
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
@@ -4658,34 +4703,6 @@ static int bnxt_init_nic(struct bnxt *bp, bool irq_re_init)
 	return bnxt_init_chip(bp, irq_re_init);
 }
 
-static void bnxt_disable_int(struct bnxt *bp)
-{
-	int i;
-
-	if (!bp->bnapi)
-		return;
-
-	for (i = 0; i < bp->cp_nr_rings; i++) {
-		struct bnxt_napi *bnapi = bp->bnapi[i];
-		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
-
-		BNXT_CP_DB(cpr->cp_doorbell, cpr->cp_raw_cons);
-	}
-}
-
-static void bnxt_enable_int(struct bnxt *bp)
-{
-	int i;
-
-	atomic_set(&bp->intr_sem, 0);
-	for (i = 0; i < bp->cp_nr_rings; i++) {
-		struct bnxt_napi *bnapi = bp->bnapi[i];
-		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
-
-		BNXT_CP_DB_REARM(cpr->cp_doorbell, cpr->cp_raw_cons);
-	}
-}
-
 static int bnxt_set_real_num_queues(struct bnxt *bp)
 {
 	int rc;
@@ -5640,19 +5657,6 @@ static int bnxt_open(struct net_device *dev)
 	return __bnxt_open_nic(bp, true, true);
 }
 
-static void bnxt_disable_int_sync(struct bnxt *bp)
-{
-	int i;
-
-	atomic_inc(&bp->intr_sem);
-	if (!netif_running(bp->dev))
-		return;
-
-	bnxt_disable_int(bp);
-	for (i = 0; i < bp->cp_nr_rings; i++)
-		synchronize_irq(bp->irq_tbl[i].vector);
-}
-
 int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
@@ -5674,13 +5678,12 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	while (test_bit(BNXT_STATE_IN_SP_TASK, &bp->state))
 		msleep(20);
 
-	/* Flush rings before disabling interrupts */
+	/* Flush rings and and disable interrupts */
 	bnxt_shutdown_nic(bp, irq_re_init);
 
 	/* TODO CHIMP_FW: Link/PHY related cleanup if (link_re_init) */
 
 	bnxt_disable_napi(bp);
-	bnxt_disable_int_sync(bp);
 	del_timer_sync(&bp->timer);
 	bnxt_free_skbs(bp);
 
-- 
cgit v1.2.3


From 68515a186cf8a8f97956eaea5829277752399f58 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:34 -0500
Subject: bnxt_en: Fix and clarify link_info->advertising.

The advertising field is closely related to the auto_link_speeds field.
The former is the user setting while the latter is the firmware setting.
Both should be u16.  We should use the advertising field in
bnxt_get_link_ksettings because the auto_link_speeds field may not
be updated with the latest from the firmware yet.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         | 4 ++--
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 5 +++--
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 277573b3d261..4a8059fcc858 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5363,7 +5363,7 @@ static void bnxt_hwrm_set_link_common(struct bnxt *bp,
 {
 	u8 autoneg = bp->link_info.autoneg;
 	u16 fw_link_speed = bp->link_info.req_link_speed;
-	u32 advertising = bp->link_info.advertising;
+	u16 advertising = bp->link_info.advertising;
 
 	if (autoneg & BNXT_AUTONEG_SPEED) {
 		req->auto_mode |=
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index fddc316170b2..0eb64013fa5e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -828,7 +828,7 @@ struct bnxt_link_info {
 #define BNXT_LINK_SPEED_40GB	PORT_PHY_QCFG_RESP_LINK_SPEED_40GB
 #define BNXT_LINK_SPEED_50GB	PORT_PHY_QCFG_RESP_LINK_SPEED_50GB
 	u16			support_speeds;
-	u16			auto_link_speeds;
+	u16			auto_link_speeds;	/* fw adv setting */
 #define BNXT_LINK_SPEED_MSK_100MB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MB
 #define BNXT_LINK_SPEED_MSK_1GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GB
 #define BNXT_LINK_SPEED_MSK_2GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_2GB
@@ -851,7 +851,7 @@ struct bnxt_link_info {
 	u8			req_duplex;
 	u8			req_flow_ctrl;
 	u16			req_link_speed;
-	u32			advertising;
+	u16			advertising;	/* user adv setting */
 	bool			force_link_chng;
 
 	/* a copy of phy_qcfg output used to report link
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 784aa77610bc..1cfa7a67cadb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -893,7 +893,7 @@ u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause)
 static void bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info,
 				struct ethtool_link_ksettings *lk_ksettings)
 {
-	u16 fw_speeds = link_info->auto_link_speeds;
+	u16 fw_speeds = link_info->advertising;
 	u8 fw_pause = 0;
 
 	if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL)
@@ -1090,8 +1090,9 @@ static int bnxt_set_link_ksettings(struct net_device *dev,
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_link_info *link_info = &bp->link_info;
 	const struct ethtool_link_settings *base = &lk_ksettings->base;
-	u32 speed, fw_advertising = 0;
 	bool set_pause = false;
+	u16 fw_advertising = 0;
+	u32 speed;
 	int rc = 0;
 
 	if (!BNXT_SINGLE_PF(bp))
-- 
cgit v1.2.3


From 5910906ca9ee32943f67db24917f78a9ad1087db Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:35 -0500
Subject: bnxt_en: Refactor TPA code path.

Call tcp_gro_complete() in the common code path instead of the chip-
specific method.  The newer 5731x method is missing the call.

Signed-off-by: Michael Chan <michael.chan@broadcmo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4a8059fcc858..0654c3f32cea 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1127,7 +1127,6 @@ static struct sk_buff *bnxt_gro_func_5730x(struct bnxt_tpa_info *tpa_info,
 		dev_kfree_skb_any(skb);
 		return NULL;
 	}
-	tcp_gro_complete(skb);
 
 	if (nw_off) { /* tunnel */
 		struct udphdr *uh = NULL;
@@ -1177,6 +1176,8 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,
 		       RX_TPA_END_CMP_PAYLOAD_OFFSET) >>
 		      RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT;
 	skb = bp->gro_func(tpa_info, payload_off, TPA_END_GRO_TS(tpa_end), skb);
+	if (likely(skb))
+		tcp_gro_complete(skb);
 #endif
 	return skb;
 }
-- 
cgit v1.2.3


From 8fdefd63c203d9b2955d679704f4ed92bf40752c Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:36 -0500
Subject: bnxt_en: Add function to get vnic capability.

The new vnic RSS capability will enhance NTUPLE support, to be added
in subsequent patches.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 22 +++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 34 +++++++++++++++++++++++++++
 3 files changed, 57 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0654c3f32cea..916832684ad5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3665,6 +3665,27 @@ static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id,
 	return rc;
 }
 
+static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
+{
+	struct hwrm_vnic_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_vnic_qcaps_input req = {0};
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10600)
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_QCAPS, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		if (resp->flags &
+		    cpu_to_le32(VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP))
+			bp->flags |= BNXT_FLAG_NEW_RSS_CAP;
+	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
 static int bnxt_hwrm_ring_grp_alloc(struct bnxt *bp)
 {
 	u16 i;
@@ -7070,6 +7091,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 				    VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6;
 	}
 
+	bnxt_hwrm_vnic_qcaps(bp);
 	if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		dev->hw_features |= NETIF_F_NTUPLE;
 		if (bnxt_rfs_capable(bp)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 0eb64013fa5e..80bf1ab7df8c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -944,6 +944,7 @@ struct bnxt {
 	#define BNXT_FLAG_PORT_STATS	0x400
 	#define BNXT_FLAG_UDP_RSS_CAP	0x800
 	#define BNXT_FLAG_EEE_CAP	0x1000
+	#define BNXT_FLAG_NEW_RSS_CAP	0x2000
 	#define BNXT_FLAG_ROCEV1_CAP	0x8000
 	#define BNXT_FLAG_ROCEV2_CAP	0x10000
 	#define BNXT_FLAG_ROCE_CAP	(BNXT_FLAG_ROCEV1_CAP |	\
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 2ddfa51519a1..d0d49ed71ce4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -2797,6 +2797,40 @@ struct hwrm_vnic_cfg_output {
 	u8 valid;
 };
 
+/* hwrm_vnic_qcaps */
+/* Input (24 bytes) */
+struct hwrm_vnic_qcaps_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le32 enables;
+	__le32 unused_0;
+};
+
+/* Output (24 bytes) */
+struct hwrm_vnic_qcaps_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	__le16 mru;
+	u8 unused_0;
+	u8 unused_1;
+	__le32 flags;
+	#define VNIC_QCAPS_RESP_FLAGS_VLAN_STRIP_CAP		    0x2UL
+	#define VNIC_QCAPS_RESP_FLAGS_BD_STALL_CAP		    0x4UL
+	#define VNIC_QCAPS_RESP_FLAGS_ROCE_DUAL_VNIC_CAP	    0x8UL
+	#define VNIC_QCAPS_RESP_FLAGS_ROCE_ONLY_VNIC_CAP	    0x10UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP		    0x20UL
+	__le32 unused_2;
+	u8 unused_3;
+	u8 unused_4;
+	u8 unused_5;
+	u8 valid;
+};
+
 /* hwrm_vnic_tpa_cfg */
 /* Input (40 bytes) */
 struct hwrm_vnic_tpa_cfg_input {
-- 
cgit v1.2.3


From 8079e8f107bf02e1e5ece89239dd2fb475a4735f Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:37 -0500
Subject: bnxt_en: Refactor code that determines RFS capability.

Add function bnxt_rfs_supported() that determines if the chip supports
RFS.  Refactor the existing function bnxt_rfs_capable() that determines
if run-time conditions support RFS.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 38 +++++++++++++++++++++++++++----
 1 file changed, 33 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 916832684ad5..f7ea99ff6fa3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4835,6 +4835,24 @@ static int bnxt_setup_int_mode(struct bnxt *bp)
 	return rc;
 }
 
+static unsigned int bnxt_get_max_func_rss_ctxs(struct bnxt *bp)
+{
+#if defined(CONFIG_BNXT_SRIOV)
+	if (BNXT_VF(bp))
+		return bp->vf.max_rsscos_ctxs;
+#endif
+	return bp->pf.max_rsscos_ctxs;
+}
+
+static unsigned int bnxt_get_max_func_vnics(struct bnxt *bp)
+{
+#if defined(CONFIG_BNXT_SRIOV)
+	if (BNXT_VF(bp))
+		return bp->vf.max_vnics;
+#endif
+	return bp->pf.max_vnics;
+}
+
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp)
 {
 #if defined(CONFIG_BNXT_SRIOV)
@@ -5962,20 +5980,30 @@ skip_uc:
 	return rc;
 }
 
+/* If the chip and firmware supports RFS */
+static bool bnxt_rfs_supported(struct bnxt *bp)
+{
+	if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp))
+		return true;
+	return false;
+}
+
+/* If runtime conditions support RFS */
 static bool bnxt_rfs_capable(struct bnxt *bp)
 {
 #ifdef CONFIG_RFS_ACCEL
-	struct bnxt_pf_info *pf = &bp->pf;
-	int vnics;
+	int vnics, max_vnics, max_rss_ctxs;
 
 	if (BNXT_VF(bp) || !(bp->flags & BNXT_FLAG_MSIX_CAP))
 		return false;
 
 	vnics = 1 + bp->rx_nr_rings;
-	if (vnics > pf->max_rsscos_ctxs || vnics > pf->max_vnics) {
+	max_vnics = bnxt_get_max_func_vnics(bp);
+	max_rss_ctxs = bnxt_get_max_func_rss_ctxs(bp);
+	if (vnics > max_vnics || vnics > max_rss_ctxs) {
 		netdev_warn(bp->dev,
 			    "Not enough resources to support NTUPLE filters, enough resources for up to %d rx rings\n",
-			    min(pf->max_rsscos_ctxs - 1, pf->max_vnics - 1));
+			    min(max_rss_ctxs - 1, max_vnics - 1));
 		return false;
 	}
 
@@ -7092,7 +7120,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	bnxt_hwrm_vnic_qcaps(bp);
-	if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp)) {
+	if (bnxt_rfs_supported(bp)) {
 		dev->hw_features |= NETIF_F_NTUPLE;
 		if (bnxt_rfs_capable(bp)) {
 			bp->flags |= BNXT_FLAG_RFS;
-- 
cgit v1.2.3


From ae10ae740ad2befd92b6f5b2ab39220bce6e5da2 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:38 -0500
Subject: bnxt_en: Add new hardware RFS mode.

The existing hardware RFS mode uses one hardware RSS context block
per ring just to calculate the RSS hash.  This is very wasteful and
prevents VF functions from using it.  The new hardware mode shares
the same hardware RSS context for RSS placement and RFS steering.
This allows VFs to enable RFS.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 27 ++++++++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index f7ea99ff6fa3..0ca530e9f73e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2630,6 +2630,10 @@ static int bnxt_alloc_vnic_attributes(struct bnxt *bp)
 			goto out;
 		}
 
+		if ((bp->flags & BNXT_FLAG_NEW_RSS_CAP) &&
+		    !(vnic->flags & BNXT_VNIC_RSS_FLAG))
+			continue;
+
 		/* Allocate rss table and hash key */
 		vnic->rss_table = dma_alloc_coherent(&pdev->dev, PAGE_SIZE,
 						     &vnic->rss_table_dma_addr,
@@ -3562,6 +3566,12 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 		req.rss_rule = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]);
 		req.enables |= cpu_to_le32(VNIC_CFG_REQ_ENABLES_RSS_RULE |
 					   VNIC_CFG_REQ_ENABLES_MRU);
+	} else if (vnic->flags & BNXT_VNIC_RFS_NEW_RSS_FLAG) {
+		req.rss_rule =
+			cpu_to_le16(bp->vnic_info[0].fw_rss_cos_lb_ctx[0]);
+		req.enables |= cpu_to_le32(VNIC_CFG_REQ_ENABLES_RSS_RULE |
+					   VNIC_CFG_REQ_ENABLES_MRU);
+		req.flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE);
 	} else {
 		req.rss_rule = cpu_to_le16(0xffff);
 	}
@@ -4490,8 +4500,12 @@ static void bnxt_hwrm_resource_free(struct bnxt *bp, bool close_path,
 
 static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
 {
+	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	int rc;
 
+	if (vnic->flags & BNXT_VNIC_RFS_NEW_RSS_FLAG)
+		goto skip_rss_ctx;
+
 	/* allocate context for vnic */
 	rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id, 0);
 	if (rc) {
@@ -4511,6 +4525,7 @@ static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
 		bp->rsscos_nr_ctxs++;
 	}
 
+skip_rss_ctx:
 	/* configure default vnic, ring grp */
 	rc = bnxt_hwrm_vnic_cfg(bp, vnic_id);
 	if (rc) {
@@ -4545,13 +4560,17 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 	int i, rc = 0;
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
+		struct bnxt_vnic_info *vnic;
 		u16 vnic_id = i + 1;
 		u16 ring_id = i;
 
 		if (vnic_id >= bp->nr_vnics)
 			break;
 
-		bp->vnic_info[vnic_id].flags |= BNXT_VNIC_RFS_FLAG;
+		vnic = &bp->vnic_info[vnic_id];
+		vnic->flags |= BNXT_VNIC_RFS_FLAG;
+		if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
+			vnic->flags |= BNXT_VNIC_RFS_NEW_RSS_FLAG;
 		rc = bnxt_hwrm_vnic_alloc(bp, vnic_id, ring_id, 1);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic %d alloc failure rc: %x\n",
@@ -5985,6 +6004,8 @@ static bool bnxt_rfs_supported(struct bnxt *bp)
 {
 	if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return true;
+	if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
+		return true;
 	return false;
 }
 
@@ -6000,6 +6021,10 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 	vnics = 1 + bp->rx_nr_rings;
 	max_vnics = bnxt_get_max_func_vnics(bp);
 	max_rss_ctxs = bnxt_get_max_func_rss_ctxs(bp);
+
+	/* RSS contexts not a limiting factor */
+	if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
+		max_rss_ctxs = max_vnics;
 	if (vnics > max_vnics || vnics > max_rss_ctxs) {
 		netdev_warn(bp->dev,
 			    "Not enough resources to support NTUPLE filters, enough resources for up to %d rx rings\n",
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 80bf1ab7df8c..75803e5f3bf5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -708,6 +708,7 @@ struct bnxt_vnic_info {
 #define BNXT_VNIC_RFS_FLAG	2
 #define BNXT_VNIC_MCAST_FLAG	4
 #define BNXT_VNIC_UCAST_FLAG	8
+#define BNXT_VNIC_RFS_NEW_RSS_FLAG	0x10
 };
 
 #if defined(CONFIG_BNXT_SRIOV)
-- 
cgit v1.2.3


From 8427af811a2fcbbf0c71a4b1f904f2442abdcf39 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:39 -0500
Subject: bnxt_en: Assign additional vnics to VFs.

Assign additional vnics to VFs whenever possible so that NTUPLE can be
supported on the VFs.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index c69602508666..0c9f6c1db546 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -429,6 +429,8 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 		vf_rx_rings = (pf->max_rx_rings - bp->rx_nr_rings) / num_vfs;
 	vf_ring_grps = (bp->pf.max_hw_ring_grps - bp->rx_nr_rings) / num_vfs;
 	vf_tx_rings = (pf->max_tx_rings - bp->tx_nr_rings) / num_vfs;
+	vf_vnics = (pf->max_vnics - bp->nr_vnics) / num_vfs;
+	vf_vnics = min_t(u16, vf_vnics, vf_rx_rings);
 
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MTU |
 				  FUNC_CFG_REQ_ENABLES_MRU |
@@ -451,7 +453,6 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 	req.num_rx_rings = cpu_to_le16(vf_rx_rings);
 	req.num_hw_ring_grps = cpu_to_le16(vf_ring_grps);
 	req.num_l2_ctxs = cpu_to_le16(4);
-	vf_vnics = 1;
 
 	req.num_vnics = cpu_to_le16(vf_vnics);
 	/* FIXME spec currently uses 1 bit for stats ctx */
@@ -506,6 +507,8 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 			    min_rx_rings)
 				rx_ok = 1;
 		}
+		if (bp->pf.max_vnics - bp->nr_vnics < min_rx_rings)
+			rx_ok = 0;
 
 		if (bp->pf.max_tx_rings - bp->tx_nr_rings >= min_tx_rings)
 			tx_ok = 1;
-- 
cgit v1.2.3


From dda0e7465f040ed814d4a5c98c6bf042e59cba69 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:40 -0500
Subject: bnxt_en: Add IPV6 hardware RFS support.

Accept ipv6 flows in .ndo_rx_flow_steer() and support ETHTOOL_GRXCLSRULE
ipv6 flows.

Signed-off-by: Michael Chan <michael.chan@broadocm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 32 +++++++++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 53 +++++++++++++++++------
 2 files changed, 66 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0ca530e9f73e..4d478e79d424 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3316,10 +3316,26 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 	req.ip_addr_type = CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4;
 	req.ip_protocol = keys->basic.ip_proto;
 
-	req.src_ipaddr[0] = keys->addrs.v4addrs.src;
-	req.src_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
-	req.dst_ipaddr[0] = keys->addrs.v4addrs.dst;
-	req.dst_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+	if (keys->basic.n_proto == htons(ETH_P_IPV6)) {
+		int i;
+
+		req.ethertype = htons(ETH_P_IPV6);
+		req.ip_addr_type =
+			CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6;
+		*(struct in6_addr *)&req.src_ipaddr[0] =
+			keys->addrs.v6addrs.src;
+		*(struct in6_addr *)&req.dst_ipaddr[0] =
+			keys->addrs.v6addrs.dst;
+		for (i = 0; i < 4; i++) {
+			req.src_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
+			req.dst_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
+		}
+	} else {
+		req.src_ipaddr[0] = keys->addrs.v4addrs.src;
+		req.src_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+		req.dst_ipaddr[0] = keys->addrs.v4addrs.dst;
+		req.dst_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+	}
 
 	req.src_port = keys->ports.src;
 	req.src_port_mask = cpu_to_be16(0xffff);
@@ -6588,12 +6604,18 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 		goto err_free;
 	}
 
-	if ((fkeys->basic.n_proto != htons(ETH_P_IP)) ||
+	if ((fkeys->basic.n_proto != htons(ETH_P_IP) &&
+	     fkeys->basic.n_proto != htons(ETH_P_IPV6)) ||
 	    ((fkeys->basic.ip_proto != IPPROTO_TCP) &&
 	     (fkeys->basic.ip_proto != IPPROTO_UDP))) {
 		rc = -EPROTONOSUPPORT;
 		goto err_free;
 	}
+	if (fkeys->basic.n_proto == htons(ETH_P_IPV6) &&
+	    bp->hwrm_spec_code < 0x10601) {
+		rc = -EPROTONOSUPPORT;
+		goto err_free;
+	}
 
 	memcpy(new_fltr->dst_mac_addr, eth->h_dest, ETH_ALEN);
 	memcpy(new_fltr->src_mac_addr, eth->h_source, ETH_ALEN);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 1cfa7a67cadb..e6b11969c9a0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -524,24 +524,49 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 
 fltr_found:
 	fkeys = &fltr->fkeys;
-	if (fkeys->basic.ip_proto == IPPROTO_TCP)
-		fs->flow_type = TCP_V4_FLOW;
-	else if (fkeys->basic.ip_proto == IPPROTO_UDP)
-		fs->flow_type = UDP_V4_FLOW;
-	else
-		goto fltr_err;
+	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
+		if (fkeys->basic.ip_proto == IPPROTO_TCP)
+			fs->flow_type = TCP_V4_FLOW;
+		else if (fkeys->basic.ip_proto == IPPROTO_UDP)
+			fs->flow_type = UDP_V4_FLOW;
+		else
+			goto fltr_err;
+
+		fs->h_u.tcp_ip4_spec.ip4src = fkeys->addrs.v4addrs.src;
+		fs->m_u.tcp_ip4_spec.ip4src = cpu_to_be32(~0);
+
+		fs->h_u.tcp_ip4_spec.ip4dst = fkeys->addrs.v4addrs.dst;
+		fs->m_u.tcp_ip4_spec.ip4dst = cpu_to_be32(~0);
 
-	fs->h_u.tcp_ip4_spec.ip4src = fkeys->addrs.v4addrs.src;
-	fs->m_u.tcp_ip4_spec.ip4src = cpu_to_be32(~0);
+		fs->h_u.tcp_ip4_spec.psrc = fkeys->ports.src;
+		fs->m_u.tcp_ip4_spec.psrc = cpu_to_be16(~0);
 
-	fs->h_u.tcp_ip4_spec.ip4dst = fkeys->addrs.v4addrs.dst;
-	fs->m_u.tcp_ip4_spec.ip4dst = cpu_to_be32(~0);
+		fs->h_u.tcp_ip4_spec.pdst = fkeys->ports.dst;
+		fs->m_u.tcp_ip4_spec.pdst = cpu_to_be16(~0);
+	} else {
+		int i;
 
-	fs->h_u.tcp_ip4_spec.psrc = fkeys->ports.src;
-	fs->m_u.tcp_ip4_spec.psrc = cpu_to_be16(~0);
+		if (fkeys->basic.ip_proto == IPPROTO_TCP)
+			fs->flow_type = TCP_V6_FLOW;
+		else if (fkeys->basic.ip_proto == IPPROTO_UDP)
+			fs->flow_type = UDP_V6_FLOW;
+		else
+			goto fltr_err;
+
+		*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6src[0] =
+			fkeys->addrs.v6addrs.src;
+		*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6dst[0] =
+			fkeys->addrs.v6addrs.dst;
+		for (i = 0; i < 4; i++) {
+			fs->m_u.tcp_ip6_spec.ip6src[i] = cpu_to_be32(~0);
+			fs->m_u.tcp_ip6_spec.ip6dst[i] = cpu_to_be32(~0);
+		}
+		fs->h_u.tcp_ip6_spec.psrc = fkeys->ports.src;
+		fs->m_u.tcp_ip6_spec.psrc = cpu_to_be16(~0);
 
-	fs->h_u.tcp_ip4_spec.pdst = fkeys->ports.dst;
-	fs->m_u.tcp_ip4_spec.pdst = cpu_to_be16(~0);
+		fs->h_u.tcp_ip6_spec.pdst = fkeys->ports.dst;
+		fs->m_u.tcp_ip6_spec.pdst = cpu_to_be16(~0);
+	}
 
 	fs->ring_cookie = fltr->rxq;
 	rc = 0;
-- 
cgit v1.2.3


From 391be5c2736456f032fe0265031ecfe17aee84a0 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:41 -0500
Subject: bnxt_en: Implement new scheme to reserve tx rings.

In order to properly support TX rate limiting in SRIOV VF functions or
NPAR functions, firmware needs better control over tx ring allocations.
The new scheme requires the driver to reserve the number of tx rings
and to query to see if the requested number of tx rings is reserved.
The driver will use the new scheme when the firmware interface spec is
1.6.1 or newer.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 59 ++++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |  2 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 15 ++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c   | 10 +++-
 4 files changed, 83 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4d478e79d424..338dbd03ff58 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4045,6 +4045,50 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	}
 }
 
+/* Caller must hold bp->hwrm_cmd_lock */
+int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings)
+{
+	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_func_qcfg_input req = {0};
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10601)
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
+	req.fid = cpu_to_le16(fid);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*tx_rings = le16_to_cpu(resp->alloc_tx_rings);
+
+	return rc;
+}
+
+int bnxt_hwrm_reserve_tx_rings(struct bnxt *bp, int *tx_rings)
+{
+	struct hwrm_func_cfg_input req = {0};
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10601)
+		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.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS);
+	req.num_tx_rings = cpu_to_le16(*tx_rings);
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		return rc;
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = __bnxt_hwrm_get_tx_rings(bp, 0xffff, tx_rings);
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
 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)
@@ -6509,10 +6553,16 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 		sh = true;
 
 	if (tc) {
-		int max_rx_rings, max_tx_rings, rc;
+		int max_rx_rings, max_tx_rings, req_tx_rings, rsv_tx_rings, rc;
 
+		req_tx_rings = bp->tx_nr_rings_per_tc * tc;
 		rc = bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings, sh);
-		if (rc || bp->tx_nr_rings_per_tc * tc > max_tx_rings)
+		if (rc || req_tx_rings > max_tx_rings)
+			return -ENOMEM;
+
+		rsv_tx_rings = req_tx_rings;
+		if (bnxt_hwrm_reserve_tx_rings(bp, &rsv_tx_rings) ||
+		    rsv_tx_rings < req_tx_rings)
 			return -ENOMEM;
 	}
 
@@ -7000,6 +7050,11 @@ static int bnxt_set_dflt_rings(struct bnxt *bp)
 		return rc;
 	bp->rx_nr_rings = min_t(int, dflt_rings, max_rx_rings);
 	bp->tx_nr_rings_per_tc = min_t(int, dflt_rings, max_tx_rings);
+
+	rc = bnxt_hwrm_reserve_tx_rings(bp, &bp->tx_nr_rings_per_tc);
+	if (rc)
+		netdev_warn(bp->dev, "Unable to reserve tx rings\n");
+
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
 	bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
 			       bp->tx_nr_rings + bp->rx_nr_rings;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 75803e5f3bf5..d174729de761 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1149,6 +1149,8 @@ int hwrm_send_message_silent(struct bnxt *, void *, u32, int);
 int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
 				     int bmap_size);
 int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id);
+int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings);
+int bnxt_hwrm_reserve_tx_rings(struct bnxt *bp, int *tx_rings);
 int bnxt_hwrm_set_coal(struct bnxt *);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
 void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index e6b11969c9a0..dd21be4a5fdd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -388,6 +388,7 @@ static int bnxt_set_channels(struct net_device *dev,
 {
 	struct bnxt *bp = netdev_priv(dev);
 	int max_rx_rings, max_tx_rings, tcs;
+	int req_tx_rings, rsv_tx_rings;
 	u32 rc = 0;
 	bool sh = false;
 
@@ -423,6 +424,20 @@ static int bnxt_set_channels(struct net_device *dev,
 		    channel->tx_count > max_tx_rings))
 		return -ENOMEM;
 
+	req_tx_rings = sh ? channel->combined_count : channel->tx_count;
+	req_tx_rings = min_t(int, req_tx_rings, max_tx_rings);
+	if (tcs > 1)
+		req_tx_rings *= tcs;
+
+	rsv_tx_rings = req_tx_rings;
+	if (bnxt_hwrm_reserve_tx_rings(bp, &rsv_tx_rings))
+		return -ENOMEM;
+
+	if (rsv_tx_rings < req_tx_rings) {
+		netdev_warn(dev, "Unable to allocate the requested tx rings\n");
+		return -ENOMEM;
+	}
+
 	if (netif_running(dev)) {
 		if (BNXT_PF(bp)) {
 			/* TODO CHIMP_FW: Send message to all VF's
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 0c9f6c1db546..64ef0e5dad8c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -416,6 +416,7 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 	u16 vf_ring_grps;
 	struct hwrm_func_cfg_input req = {0};
 	struct bnxt_pf_info *pf = &bp->pf;
+	int total_vf_tx_rings = 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 
@@ -460,6 +461,8 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	for (i = 0; i < num_vfs; i++) {
+		int vf_tx_rsvd = vf_tx_rings;
+
 		req.fid = cpu_to_le16(pf->first_vf_id + i);
 		rc = _hwrm_send_message(bp, &req, sizeof(req),
 					HWRM_CMD_TIMEOUT);
@@ -467,10 +470,15 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 			break;
 		pf->active_vfs = i + 1;
 		pf->vf[i].fw_fid = le16_to_cpu(req.fid);
+		rc = __bnxt_hwrm_get_tx_rings(bp, pf->vf[i].fw_fid,
+					      &vf_tx_rsvd);
+		if (rc)
+			break;
+		total_vf_tx_rings += vf_tx_rsvd;
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	if (!rc) {
-		pf->max_tx_rings -= vf_tx_rings * num_vfs;
+		pf->max_tx_rings -= total_vf_tx_rings;
 		pf->max_rx_rings -= vf_rx_rings * num_vfs;
 		pf->max_hw_ring_grps -= vf_ring_grps * num_vfs;
 		pf->max_cp_rings -= vf_cp_rings * num_vfs;
-- 
cgit v1.2.3


From 486b5c22ea1d35e00e90dd79a32a9ee530b18915 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:42 -0500
Subject: bnxt_en: Set default completion ring for async events.

With the added support for the bnxt_re RDMA driver, both drivers can be
allocating completion rings in any order.  The firmware does not know
which completion ring should be receiving async events.  Add an
extra step to tell firmware the completion ring number for receiving
async events after bnxt_en allocates the completion rings.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 338dbd03ff58..1f54a7acc3f7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3858,6 +3858,30 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 	return rc;
 }
 
+static int bnxt_hwrm_set_async_event_cr(struct bnxt *bp, int idx)
+{
+	int rc;
+
+	if (BNXT_PF(bp)) {
+		struct hwrm_func_cfg_input req = {0};
+
+		bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
+		req.fid = cpu_to_le16(0xffff);
+		req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_ASYNC_EVENT_CR);
+		req.async_event_cr = cpu_to_le16(idx);
+		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	} else {
+		struct hwrm_func_vf_cfg_input req = {0};
+
+		bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_CFG, -1, -1);
+		req.enables =
+			cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_ASYNC_EVENT_CR);
+		req.async_event_cr = cpu_to_le16(idx);
+		rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	}
+	return rc;
+}
+
 static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 {
 	int i, rc = 0;
@@ -3874,6 +3898,12 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 			goto err_out;
 		BNXT_CP_DB(cpr->cp_doorbell, cpr->cp_raw_cons);
 		bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id;
+
+		if (!i) {
+			rc = bnxt_hwrm_set_async_event_cr(bp, ring->fw_ring_id);
+			if (rc)
+				netdev_warn(bp->dev, "Failed to set async event completion ring.\n");
+		}
 	}
 
 	for (i = 0; i < bp->tx_nr_rings; i++) {
-- 
cgit v1.2.3


From bdbd1eb59c565c56a74d21076e2ae8706de00ecd Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:43 -0500
Subject: bnxt_en: Handle no aggregation ring gracefully.

The current code assumes that we will always have at least 2 rx rings, 1
will be used as an aggregation ring for TPA and jumbo page placements.
However, it is possible, especially on a VF, that there is only 1 rx
ring available.  In this scenario, the current code will fail to initialize.
To handle it, we need to properly set up only 1 ring without aggregation.
Set a new flag BNXT_FLAG_NO_AGG_RINGS for this condition and add logic to
set up the chip to place RX data linearly into a single buffer per packet.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 25 +++++++++++++++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1f54a7acc3f7..98e948489700 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2496,7 +2496,7 @@ void bnxt_set_ring_params(struct bnxt *bp)
 		agg_factor = min_t(u32, 4, 65536 / BNXT_RX_PAGE_SIZE);
 
 	bp->flags &= ~BNXT_FLAG_JUMBO;
-	if (rx_space > PAGE_SIZE) {
+	if (rx_space > PAGE_SIZE && !(bp->flags & BNXT_FLAG_NO_AGG_RINGS)) {
 		u32 jumbo_factor;
 
 		bp->flags |= BNXT_FLAG_JUMBO;
@@ -6174,6 +6174,9 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features)
 	if (features & NETIF_F_LRO)
 		flags |= BNXT_FLAG_LRO;
 
+	if (bp->flags & BNXT_FLAG_NO_AGG_RINGS)
+		flags &= ~BNXT_FLAG_TPA;
+
 	if (features & NETIF_F_HW_VLAN_CTAG_RX)
 		flags |= BNXT_FLAG_STRIP_VLAN;
 
@@ -7040,8 +7043,17 @@ static int bnxt_get_dflt_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 	int rc;
 
 	rc = bnxt_get_max_rings(bp, max_rx, max_tx, shared);
-	if (rc)
-		return rc;
+	if (rc && (bp->flags & BNXT_FLAG_AGG_RINGS)) {
+		/* Not enough rings, try disabling agg rings. */
+		bp->flags &= ~BNXT_FLAG_AGG_RINGS;
+		rc = bnxt_get_max_rings(bp, max_rx, max_tx, shared);
+		if (rc)
+			return rc;
+		bp->flags |= BNXT_FLAG_NO_AGG_RINGS;
+		bp->dev->hw_features &= ~NETIF_F_LRO;
+		bp->dev->features &= ~NETIF_F_LRO;
+		bnxt_set_ring_params(bp);
+	}
 
 	if (bp->flags & BNXT_FLAG_ROCE_CAP) {
 		int max_cp, max_stat, max_irq;
@@ -7236,7 +7248,12 @@ 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);
-	bnxt_set_dflt_rings(bp);
+	rc = bnxt_set_dflt_rings(bp);
+	if (rc) {
+		netdev_err(bp->dev, "Not enough rings available.\n");
+		rc = -ENOMEM;
+		goto init_err;
+	}
 
 	/* Default RSS hash cfg. */
 	bp->rss_hash_cfg = VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 |
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index d174729de761..f6b9b1c530fe 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -950,6 +950,7 @@ struct bnxt {
 	#define BNXT_FLAG_ROCEV2_CAP	0x10000
 	#define BNXT_FLAG_ROCE_CAP	(BNXT_FLAG_ROCEV1_CAP |	\
 					 BNXT_FLAG_ROCEV2_CAP)
+	#define BNXT_FLAG_NO_AGG_RINGS	0x20000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
-- 
cgit v1.2.3


From 3f0d80b6d228f11117244a16d2e17ea684b540f5 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 29 Dec 2016 12:13:44 -0500
Subject: MAINTAINERS: Add bnxt_en maintainer info.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index cfff2c9e3d94..11904a95672a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2605,6 +2605,12 @@ L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2x/
 
+BROADCOM BNXT_EN 50 GIGABIT ETHERNET DRIVER
+M:	Michael Chan <michael.chan@broadcom.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/ethernet/broadcom/bnxt/
+
 BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE
 M:	Florian Fainelli <f.fainelli@gmail.com>
 M:	Ray Jui <rjui@broadcom.com>
-- 
cgit v1.2.3