From 9f34519a82356f6cf0ccb8480ee0ed99b3d0af75 Mon Sep 17 00:00:00 2001
From: Steve Wise <swise@opengridcomputing.com>
Date: Fri, 31 Aug 2018 11:52:00 -0700
Subject: cxgb4: fix abort_req_rss6 struct

Remove the incorrect WR_HDR field which can cause a misinterpretation
of ABORT CPL by ULDs, such as iw_cxgb4.

Fixes: a3cdaa69e4ae ("cxgb4: Adds CPL support for Shared Receive Queues")
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_msg.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index b8f75a22fb6c..f152da1ce046 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -753,7 +753,6 @@ struct cpl_abort_req_rss {
 };
 
 struct cpl_abort_req_rss6 {
-	WR_HDR;
 	union opcode_tid ot;
 	__be32 srqidx_status;
 };
-- 
cgit v1.2.3


From 250ae0d46d857ed61f3e0abf584901e46bd2c638 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Sun, 2 Sep 2018 12:01:53 +0300
Subject: net/mlx5: Fix read from coherent memory

Use accessor function READ_ONCE to read from coherent memory modified
by the device and read by the driver. This becomes most important in
preemptive kernels where cond_resched implementation does not have the
side effect which guaranteed the updated value.

Fixes: 269d26f47f6f ("net/mlx5: Reduce command polling interval")
Change-Id: Ie6deeb565ffaf76777b07448c7fbcce3510bbb8a
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 3ce14d42ddc8..a53736c26c0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -206,7 +206,7 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent)
 	u8 own;
 
 	do {
-		own = ent->lay->status_own;
+		own = READ_ONCE(ent->lay->status_own);
 		if (!(own & CMD_OWNER_HW)) {
 			ent->ret = 0;
 			return;
-- 
cgit v1.2.3


From 6b359d5550a1ae7a1269c9dc1dd73dfdc4d6fe58 Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <alaa@mellanox.com>
Date: Mon, 3 Sep 2018 10:38:14 +0300
Subject: net/mlx5: Check for SQ and not RQ state when modifying hairpin SQ

When modifying hairpin SQ, instead of checking if the next state equals
to MLX5_SQC_STATE_RDY, we compare it against the MLX5_RQC_STATE_RDY enum
value.

The code worked since both of MLX5_RQC_STATE_RDY and MLX5_SQC_STATE_RDY
have the same value today.

This patch fixes this issue.

Fixes: 18e568c390c6 ("net/mlx5: Hairpin pair core object setup")
Change-Id: I6758aa7b4bd137966ae28206b70648c5bc223b46
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index dae1c5c5d27c..d2f76070ea7c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -509,7 +509,7 @@ static int mlx5_hairpin_modify_sq(struct mlx5_core_dev *peer_mdev, u32 sqn,
 
 	sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx);
 
-	if (next_state == MLX5_RQC_STATE_RDY) {
+	if (next_state == MLX5_SQC_STATE_RDY) {
 		MLX5_SET(sqc, sqc, hairpin_peer_rq, peer_rq);
 		MLX5_SET(sqc, sqc, hairpin_peer_vhca, peer_vhca);
 	}
-- 
cgit v1.2.3


From 8f92e35aff9692028279d3c03e88547df6d15020 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Sat, 15 Sep 2018 00:50:02 -0700
Subject: net/mlx5e: TLS, Read capabilities only when it is safe

Read TLS caps from the core driver only when TLS is supported, i.e
mlx5_accel_is_tls_device returns true.

Fixes: 790af90c00d2 ("net/mlx5e: TLS, build TLS netdev from capabilities")
Change-Id: I5f21ff4d684901af487e366a7e0cf032b54ee9cf
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index eddd7702680b..e88340e196f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -183,12 +183,13 @@ static const struct tlsdev_ops mlx5e_tls_ops = {
 
 void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
 {
-	u32 caps = mlx5_accel_tls_device_caps(priv->mdev);
 	struct net_device *netdev = priv->netdev;
+	u32 caps;
 
 	if (!mlx5_accel_is_tls_device(priv->mdev))
 		return;
 
+	caps = mlx5_accel_tls_device_caps(priv->mdev);
 	if (caps & MLX5_ACCEL_TLS_TX) {
 		netdev->features          |= NETIF_F_HW_TLS_TX;
 		netdev->hw_features       |= NETIF_F_HW_TLS_TX;
-- 
cgit v1.2.3


From 8fce3331702316d4bcfeb0771c09ac75d2192bbc Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 17 Sep 2018 09:22:56 +0100
Subject: net: stmmac: Rework coalesce timer and fix multi-queue races

This follows David Miller advice and tries to fix coalesce timer in
multi-queue scenarios.

We are now using per-queue coalesce values and per-queue TX timer.

Coalesce timer default values was changed to 1ms and the coalesce frames
to 25.

Tested in B2B setup between XGMAC2 and GMAC5.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Fixes: 	ce736788e8a ("net: stmmac: adding multiple buffers for TX")
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Neil Armstrong <narmstrong@baylibre.com>
Cc: Jerome Brunet <jbrunet@baylibre.com>
Cc: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h      |   4 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac.h      |  14 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 233 ++++++++++++----------
 include/linux/stmmac.h                            |   1 +
 4 files changed, 146 insertions(+), 106 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 1854f270ad66..b1b305f8f414 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -258,10 +258,10 @@ struct stmmac_safety_stats {
 #define MAX_DMA_RIWT		0xff
 #define MIN_DMA_RIWT		0x20
 /* Tx coalesce parameters */
-#define STMMAC_COAL_TX_TIMER	40000
+#define STMMAC_COAL_TX_TIMER	1000
 #define STMMAC_MAX_COAL_TX_TICK	100000
 #define STMMAC_TX_MAX_FRAMES	256
-#define STMMAC_TX_FRAMES	64
+#define STMMAC_TX_FRAMES	25
 
 /* Packets types */
 enum packets_types {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index c0a855b7ab3b..63e1064b27a2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -48,6 +48,8 @@ struct stmmac_tx_info {
 
 /* Frequently used values are kept adjacent for cache effect */
 struct stmmac_tx_queue {
+	u32 tx_count_frames;
+	struct timer_list txtimer;
 	u32 queue_index;
 	struct stmmac_priv *priv_data;
 	struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp;
@@ -73,7 +75,14 @@ struct stmmac_rx_queue {
 	u32 rx_zeroc_thresh;
 	dma_addr_t dma_rx_phy;
 	u32 rx_tail_addr;
+};
+
+struct stmmac_channel {
 	struct napi_struct napi ____cacheline_aligned_in_smp;
+	struct stmmac_priv *priv_data;
+	u32 index;
+	int has_rx;
+	int has_tx;
 };
 
 struct stmmac_tc_entry {
@@ -109,14 +118,12 @@ struct stmmac_pps_cfg {
 
 struct stmmac_priv {
 	/* Frequently used values are kept adjacent for cache effect */
-	u32 tx_count_frames;
 	u32 tx_coal_frames;
 	u32 tx_coal_timer;
 
 	int tx_coalesce;
 	int hwts_tx_en;
 	bool tx_path_in_lpi_mode;
-	struct timer_list txtimer;
 	bool tso;
 
 	unsigned int dma_buf_sz;
@@ -137,6 +144,9 @@ struct stmmac_priv {
 	/* TX Queue */
 	struct stmmac_tx_queue tx_queue[MTL_MAX_TX_QUEUES];
 
+	/* Generic channel for NAPI */
+	struct stmmac_channel channel[STMMAC_CH_MAX];
+
 	bool oldlink;
 	int speed;
 	int oldduplex;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9f458bb16f2a..ab9cc0143ff2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -148,12 +148,14 @@ static void stmmac_verify_args(void)
 static void stmmac_disable_all_queues(struct stmmac_priv *priv)
 {
 	u32 rx_queues_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_queues_cnt = priv->plat->tx_queues_to_use;
+	u32 maxq = max(rx_queues_cnt, tx_queues_cnt);
 	u32 queue;
 
-	for (queue = 0; queue < rx_queues_cnt; queue++) {
-		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	for (queue = 0; queue < maxq; queue++) {
+		struct stmmac_channel *ch = &priv->channel[queue];
 
-		napi_disable(&rx_q->napi);
+		napi_disable(&ch->napi);
 	}
 }
 
@@ -164,12 +166,14 @@ static void stmmac_disable_all_queues(struct stmmac_priv *priv)
 static void stmmac_enable_all_queues(struct stmmac_priv *priv)
 {
 	u32 rx_queues_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_queues_cnt = priv->plat->tx_queues_to_use;
+	u32 maxq = max(rx_queues_cnt, tx_queues_cnt);
 	u32 queue;
 
-	for (queue = 0; queue < rx_queues_cnt; queue++) {
-		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	for (queue = 0; queue < maxq; queue++) {
+		struct stmmac_channel *ch = &priv->channel[queue];
 
-		napi_enable(&rx_q->napi);
+		napi_enable(&ch->napi);
 	}
 }
 
@@ -1843,18 +1847,18 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
  * @queue: TX queue index
  * Description: it reclaims the transmit resources after transmission completes.
  */
-static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue)
+static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
 {
 	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
 	unsigned int bytes_compl = 0, pkts_compl = 0;
-	unsigned int entry;
+	unsigned int entry, count = 0;
 
-	netif_tx_lock(priv->dev);
+	__netif_tx_lock_bh(netdev_get_tx_queue(priv->dev, queue));
 
 	priv->xstats.tx_clean++;
 
 	entry = tx_q->dirty_tx;
-	while (entry != tx_q->cur_tx) {
+	while ((entry != tx_q->cur_tx) && (count < budget)) {
 		struct sk_buff *skb = tx_q->tx_skbuff[entry];
 		struct dma_desc *p;
 		int status;
@@ -1870,6 +1874,8 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue)
 		if (unlikely(status & tx_dma_own))
 			break;
 
+		count++;
+
 		/* Make sure descriptor fields are read after reading
 		 * the own bit.
 		 */
@@ -1937,7 +1943,10 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue)
 		stmmac_enable_eee_mode(priv);
 		mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer));
 	}
-	netif_tx_unlock(priv->dev);
+
+	__netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue));
+
+	return count;
 }
 
 /**
@@ -2020,6 +2029,33 @@ static bool stmmac_safety_feat_interrupt(struct stmmac_priv *priv)
 	return false;
 }
 
+static int stmmac_napi_check(struct stmmac_priv *priv, u32 chan)
+{
+	int status = stmmac_dma_interrupt_status(priv, priv->ioaddr,
+						 &priv->xstats, chan);
+	struct stmmac_channel *ch = &priv->channel[chan];
+	bool needs_work = false;
+
+	if ((status & handle_rx) && ch->has_rx) {
+		needs_work = true;
+	} else {
+		status &= ~handle_rx;
+	}
+
+	if ((status & handle_tx) && ch->has_tx) {
+		needs_work = true;
+	} else {
+		status &= ~handle_tx;
+	}
+
+	if (needs_work && napi_schedule_prep(&ch->napi)) {
+		stmmac_disable_dma_irq(priv, priv->ioaddr, chan);
+		__napi_schedule(&ch->napi);
+	}
+
+	return status;
+}
+
 /**
  * stmmac_dma_interrupt - DMA ISR
  * @priv: driver private structure
@@ -2034,57 +2070,14 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv)
 	u32 channels_to_check = tx_channel_count > rx_channel_count ?
 				tx_channel_count : rx_channel_count;
 	u32 chan;
-	bool poll_scheduled = false;
 	int status[max_t(u32, MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES)];
 
 	/* Make sure we never check beyond our status buffer. */
 	if (WARN_ON_ONCE(channels_to_check > ARRAY_SIZE(status)))
 		channels_to_check = ARRAY_SIZE(status);
 
-	/* Each DMA channel can be used for rx and tx simultaneously, yet
-	 * napi_struct is embedded in struct stmmac_rx_queue rather than in a
-	 * stmmac_channel struct.
-	 * Because of this, stmmac_poll currently checks (and possibly wakes)
-	 * all tx queues rather than just a single tx queue.
-	 */
 	for (chan = 0; chan < channels_to_check; chan++)
-		status[chan] = stmmac_dma_interrupt_status(priv, priv->ioaddr,
-				&priv->xstats, chan);
-
-	for (chan = 0; chan < rx_channel_count; chan++) {
-		if (likely(status[chan] & handle_rx)) {
-			struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan];
-
-			if (likely(napi_schedule_prep(&rx_q->napi))) {
-				stmmac_disable_dma_irq(priv, priv->ioaddr, chan);
-				__napi_schedule(&rx_q->napi);
-				poll_scheduled = true;
-			}
-		}
-	}
-
-	/* If we scheduled poll, we already know that tx queues will be checked.
-	 * If we didn't schedule poll, see if any DMA channel (used by tx) has a
-	 * completed transmission, if so, call stmmac_poll (once).
-	 */
-	if (!poll_scheduled) {
-		for (chan = 0; chan < tx_channel_count; chan++) {
-			if (status[chan] & handle_tx) {
-				/* It doesn't matter what rx queue we choose
-				 * here. We use 0 since it always exists.
-				 */
-				struct stmmac_rx_queue *rx_q =
-					&priv->rx_queue[0];
-
-				if (likely(napi_schedule_prep(&rx_q->napi))) {
-					stmmac_disable_dma_irq(priv,
-							priv->ioaddr, chan);
-					__napi_schedule(&rx_q->napi);
-				}
-				break;
-			}
-		}
-	}
+		status[chan] = stmmac_napi_check(priv, chan);
 
 	for (chan = 0; chan < tx_channel_count; chan++) {
 		if (unlikely(status[chan] & tx_hard_error_bump_tc)) {
@@ -2233,6 +2226,13 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 	return ret;
 }
 
+static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue)
+{
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+	mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer));
+}
+
 /**
  * stmmac_tx_timer - mitigation sw timer for tx.
  * @data: data pointer
@@ -2241,13 +2241,14 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
  */
 static void stmmac_tx_timer(struct timer_list *t)
 {
-	struct stmmac_priv *priv = from_timer(priv, t, txtimer);
-	u32 tx_queues_count = priv->plat->tx_queues_to_use;
-	u32 queue;
+	struct stmmac_tx_queue *tx_q = from_timer(tx_q, t, txtimer);
+	struct stmmac_priv *priv = tx_q->priv_data;
+	struct stmmac_channel *ch;
+
+	ch = &priv->channel[tx_q->queue_index];
 
-	/* let's scan all the tx queues */
-	for (queue = 0; queue < tx_queues_count; queue++)
-		stmmac_tx_clean(priv, queue);
+	if (likely(napi_schedule_prep(&ch->napi)))
+		__napi_schedule(&ch->napi);
 }
 
 /**
@@ -2260,11 +2261,17 @@ static void stmmac_tx_timer(struct timer_list *t)
  */
 static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
 {
+	u32 tx_channel_count = priv->plat->tx_queues_to_use;
+	u32 chan;
+
 	priv->tx_coal_frames = STMMAC_TX_FRAMES;
 	priv->tx_coal_timer = STMMAC_COAL_TX_TIMER;
-	timer_setup(&priv->txtimer, stmmac_tx_timer, 0);
-	priv->txtimer.expires = STMMAC_COAL_TIMER(priv->tx_coal_timer);
-	add_timer(&priv->txtimer);
+
+	for (chan = 0; chan < tx_channel_count; chan++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
+
+		timer_setup(&tx_q->txtimer, stmmac_tx_timer, 0);
+	}
 }
 
 static void stmmac_set_rings_length(struct stmmac_priv *priv)
@@ -2592,6 +2599,7 @@ static void stmmac_hw_teardown(struct net_device *dev)
 static int stmmac_open(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 chan;
 	int ret;
 
 	stmmac_check_ether_addr(priv);
@@ -2688,7 +2696,9 @@ irq_error:
 	if (dev->phydev)
 		phy_stop(dev->phydev);
 
-	del_timer_sync(&priv->txtimer);
+	for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
+		del_timer_sync(&priv->tx_queue[chan].txtimer);
+
 	stmmac_hw_teardown(dev);
 init_error:
 	free_dma_desc_resources(priv);
@@ -2708,6 +2718,7 @@ dma_desc_error:
 static int stmmac_release(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 chan;
 
 	if (priv->eee_enabled)
 		del_timer_sync(&priv->eee_ctrl_timer);
@@ -2722,7 +2733,8 @@ static int stmmac_release(struct net_device *dev)
 
 	stmmac_disable_all_queues(priv);
 
-	del_timer_sync(&priv->txtimer);
+	for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
+		del_timer_sync(&priv->tx_queue[chan].txtimer);
 
 	/* Free the IRQ lines */
 	free_irq(dev->irq, dev);
@@ -2936,14 +2948,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	priv->xstats.tx_tso_nfrags += nfrags;
 
 	/* Manage tx mitigation */
-	priv->tx_count_frames += nfrags + 1;
-	if (likely(priv->tx_coal_frames > priv->tx_count_frames)) {
-		mod_timer(&priv->txtimer,
-			  STMMAC_COAL_TIMER(priv->tx_coal_timer));
-	} else {
-		priv->tx_count_frames = 0;
+	tx_q->tx_count_frames += nfrags + 1;
+	if (priv->tx_coal_frames <= tx_q->tx_count_frames) {
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
+		tx_q->tx_count_frames = 0;
+	} else {
+		stmmac_tx_timer_arm(priv, queue);
 	}
 
 	skb_tx_timestamp(skb);
@@ -3146,14 +3157,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * This approach takes care about the fragments: desc is the first
 	 * element in case of no SG.
 	 */
-	priv->tx_count_frames += nfrags + 1;
-	if (likely(priv->tx_coal_frames > priv->tx_count_frames)) {
-		mod_timer(&priv->txtimer,
-			  STMMAC_COAL_TIMER(priv->tx_coal_timer));
-	} else {
-		priv->tx_count_frames = 0;
+	tx_q->tx_count_frames += nfrags + 1;
+	if (priv->tx_coal_frames <= tx_q->tx_count_frames) {
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
+		tx_q->tx_count_frames = 0;
+	} else {
+		stmmac_tx_timer_arm(priv, queue);
 	}
 
 	skb_tx_timestamp(skb);
@@ -3199,6 +3209,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr);
+
 	stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue);
 
 	return NETDEV_TX_OK;
@@ -3319,6 +3330,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 {
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	struct stmmac_channel *ch = &priv->channel[queue];
 	unsigned int entry = rx_q->cur_rx;
 	int coe = priv->hw->rx_csum;
 	unsigned int next_entry;
@@ -3491,7 +3503,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			else
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-			napi_gro_receive(&rx_q->napi, skb);
+			napi_gro_receive(&ch->napi, skb);
 
 			priv->dev->stats.rx_packets++;
 			priv->dev->stats.rx_bytes += frame_len;
@@ -3514,27 +3526,33 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
  *  Description :
  *  To look at the incoming frames and clear the tx resources.
  */
-static int stmmac_poll(struct napi_struct *napi, int budget)
+static int stmmac_napi_poll(struct napi_struct *napi, int budget)
 {
-	struct stmmac_rx_queue *rx_q =
-		container_of(napi, struct stmmac_rx_queue, napi);
-	struct stmmac_priv *priv = rx_q->priv_data;
-	u32 tx_count = priv->plat->tx_queues_to_use;
-	u32 chan = rx_q->queue_index;
-	int work_done = 0;
-	u32 queue;
+	struct stmmac_channel *ch =
+		container_of(napi, struct stmmac_channel, napi);
+	struct stmmac_priv *priv = ch->priv_data;
+	int work_done = 0, work_rem = budget;
+	u32 chan = ch->index;
 
 	priv->xstats.napi_poll++;
 
-	/* check all the queues */
-	for (queue = 0; queue < tx_count; queue++)
-		stmmac_tx_clean(priv, queue);
+	if (ch->has_tx) {
+		int done = stmmac_tx_clean(priv, work_rem, chan);
 
-	work_done = stmmac_rx(priv, budget, rx_q->queue_index);
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
-		stmmac_enable_dma_irq(priv, priv->ioaddr, chan);
+		work_done += done;
+		work_rem -= done;
+	}
+
+	if (ch->has_rx) {
+		int done = stmmac_rx(priv, work_rem, chan);
+
+		work_done += done;
+		work_rem -= done;
 	}
+
+	if (work_done < budget && napi_complete_done(napi, work_done))
+		stmmac_enable_dma_irq(priv, priv->ioaddr, chan);
+
 	return work_done;
 }
 
@@ -4198,8 +4216,8 @@ int stmmac_dvr_probe(struct device *device,
 {
 	struct net_device *ndev = NULL;
 	struct stmmac_priv *priv;
+	u32 queue, maxq;
 	int ret = 0;
-	u32 queue;
 
 	ndev = alloc_etherdev_mqs(sizeof(struct stmmac_priv),
 				  MTL_MAX_TX_QUEUES,
@@ -4322,11 +4340,22 @@ int stmmac_dvr_probe(struct device *device,
 			 "Enable RX Mitigation via HW Watchdog Timer\n");
 	}
 
-	for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) {
-		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	/* Setup channels NAPI */
+	maxq = max(priv->plat->rx_queues_to_use, priv->plat->tx_queues_to_use);
 
-		netif_napi_add(ndev, &rx_q->napi, stmmac_poll,
-			       (8 * priv->plat->rx_queues_to_use));
+	for (queue = 0; queue < maxq; queue++) {
+		struct stmmac_channel *ch = &priv->channel[queue];
+
+		ch->priv_data = priv;
+		ch->index = queue;
+
+		if (queue < priv->plat->rx_queues_to_use)
+			ch->has_rx = true;
+		if (queue < priv->plat->tx_queues_to_use)
+			ch->has_tx = true;
+
+		netif_napi_add(ndev, &ch->napi, stmmac_napi_poll,
+			       NAPI_POLL_WEIGHT);
 	}
 
 	mutex_init(&priv->lock);
@@ -4372,10 +4401,10 @@ error_netdev_register:
 	    priv->hw->pcs != STMMAC_PCS_RTBI)
 		stmmac_mdio_unregister(ndev);
 error_mdio_register:
-	for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) {
-		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	for (queue = 0; queue < maxq; queue++) {
+		struct stmmac_channel *ch = &priv->channel[queue];
 
-		netif_napi_del(&rx_q->napi);
+		netif_napi_del(&ch->napi);
 	}
 error_hw_init:
 	destroy_workqueue(priv->wq);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index c43e9a01b892..7ddfc65586b0 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -30,6 +30,7 @@
 
 #define MTL_MAX_RX_QUEUES	8
 #define MTL_MAX_TX_QUEUES	8
+#define STMMAC_CH_MAX		8
 
 #define STMMAC_RX_COE_NONE	0
 #define STMMAC_RX_COE_TYPE1	1
-- 
cgit v1.2.3


From 0431100b3d82c509729ece1ab22ada2484e209c1 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 17 Sep 2018 09:22:57 +0100
Subject: net: stmmac: Fixup the tail addr setting in xmit path

Currently we are always setting the tail address of descriptor list to
the end of the pre-allocated list.

According to databook this is not correct. Tail address should point to
the last available descriptor + 1, which means we have to update the
tail address everytime we call the xmit function.

This should make no impact in older versions of MAC but in newer
versions there are some DMA features which allows the IP to fetch
descriptors in advance and in a non sequential order so its critical
that we set the tail address correctly.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Fixes: f748be531d70 ("stmmac: support new GMAC4")
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ab9cc0143ff2..75896d6ba6e2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2213,8 +2213,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 		stmmac_init_tx_chan(priv, priv->ioaddr, priv->plat->dma_cfg,
 				    tx_q->dma_tx_phy, chan);
 
-		tx_q->tx_tail_addr = tx_q->dma_tx_phy +
-			    (DMA_TX_SIZE * sizeof(struct dma_desc));
+		tx_q->tx_tail_addr = tx_q->dma_tx_phy;
 		stmmac_set_tx_tail_ptr(priv, priv->ioaddr,
 				       tx_q->tx_tail_addr, chan);
 	}
@@ -3003,6 +3002,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
+	tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc));
 	stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue);
 
 	return NETDEV_TX_OK;
@@ -3210,6 +3210,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr);
 
+	tx_q->tx_tail_addr = tx_q->dma_tx_phy + (tx_q->cur_tx * sizeof(*desc));
 	stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue);
 
 	return NETDEV_TX_OK;
-- 
cgit v1.2.3


From 08e39982ef64f800fd1f9b9b92968d14d5fafa82 Mon Sep 17 00:00:00 2001
From: Christian Lamparter <chunkeey@gmail.com>
Date: Mon, 17 Sep 2018 17:22:40 +0200
Subject: net: emac: fix fixed-link setup for the RTL8363SB switch

On the Netgear WNDAP620, the emac ethernet isn't receiving nor
xmitting any frames from/to the RTL8363SB (identifies itself
as a RTL8367RB).

This is caused by the emac hardware not knowing the forced link
parameters for speed, duplex, pause, etc.

This begs the question, how this was working on the original
driver code, when it was necessary to set the phy_address and
phy_map to 0xffffffff. But I guess without access to the old
PPC405/440/460 hardware, it's not possible to know.

Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/emac/core.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 372664686309..129f4e9f38da 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2677,12 +2677,17 @@ static int emac_init_phy(struct emac_instance *dev)
 		if (of_phy_is_fixed_link(np)) {
 			int res = emac_dt_mdio_probe(dev);
 
-			if (!res) {
-				res = of_phy_register_fixed_link(np);
-				if (res)
-					mdiobus_unregister(dev->mii_bus);
+			if (res)
+				return res;
+
+			res = of_phy_register_fixed_link(np);
+			dev->phy_dev = of_phy_find_device(np);
+			if (res || !dev->phy_dev) {
+				mdiobus_unregister(dev->mii_bus);
+				return res ? res : -EINVAL;
 			}
-			return res;
+			emac_adjust_link(dev->ndev);
+			put_device(&dev->phy_dev->mdio.dev);
 		}
 		return 0;
 	}
-- 
cgit v1.2.3


From 65fac4fe9080714df80d430888834ce87c6716ba Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Tue, 18 Sep 2018 15:15:44 +0800
Subject: net: bnxt: Fix a uninitialized variable warning.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following compile warning:

drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c:49:5: warning: ‘nvm_param.dir_type’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  if (nvm_param.dir_type == BNXT_NVM_PORT_CFG)

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

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index f3b9fbcc705b..790c684f08ab 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -46,6 +46,9 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 		}
 	}
 
+	if (i == ARRAY_SIZE(nvm_params))
+		return -EOPNOTSUPP;
+
 	if (nvm_param.dir_type == BNXT_NVM_PORT_CFG)
 		idx = bp->pf.port_id;
 	else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG)
-- 
cgit v1.2.3


From 2fe397a3959de8a472f165e6d152f64cb77fa2cc Mon Sep 17 00:00:00 2001
From: Kazuya Mizuguchi <kazuya.mizuguchi.ks@renesas.com>
Date: Tue, 18 Sep 2018 12:22:26 +0200
Subject: ravb: do not write 1 to reserved bits

EtherAVB hardware requires 0 to be written to status register bits in
order to clear them, however, care must be taken not to:

1. Clear other bits, by writing zero to them
2. Write one to reserved bits

This patch corrects the ravb driver with respect to the second point above.
This is done by defining reserved bit masks for the affected registers and,
after auditing the code, ensure all sites that may write a one to a
reserved bit use are suitably masked.

Signed-off-by: Kazuya Mizuguchi <kazuya.mizuguchi.ks@renesas.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Reviewed-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb.h      |  5 +++++
 drivers/net/ethernet/renesas/ravb_main.c | 11 ++++++-----
 drivers/net/ethernet/renesas/ravb_ptp.c  |  2 +-
 3 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h
index 1470fc12282b..9b6bf557a2f5 100644
--- a/drivers/net/ethernet/renesas/ravb.h
+++ b/drivers/net/ethernet/renesas/ravb.h
@@ -428,6 +428,7 @@ enum EIS_BIT {
 	EIS_CULF1	= 0x00000080,
 	EIS_TFFF	= 0x00000100,
 	EIS_QFS		= 0x00010000,
+	EIS_RESERVED	= (GENMASK(31, 17) | GENMASK(15, 11)),
 };
 
 /* RIC0 */
@@ -472,6 +473,7 @@ enum RIS0_BIT {
 	RIS0_FRF15	= 0x00008000,
 	RIS0_FRF16	= 0x00010000,
 	RIS0_FRF17	= 0x00020000,
+	RIS0_RESERVED	= GENMASK(31, 18),
 };
 
 /* RIC1 */
@@ -528,6 +530,7 @@ enum RIS2_BIT {
 	RIS2_QFF16	= 0x00010000,
 	RIS2_QFF17	= 0x00020000,
 	RIS2_RFFF	= 0x80000000,
+	RIS2_RESERVED	= GENMASK(30, 18),
 };
 
 /* TIC */
@@ -544,6 +547,7 @@ enum TIS_BIT {
 	TIS_FTF1	= 0x00000002,	/* Undocumented? */
 	TIS_TFUF	= 0x00000100,
 	TIS_TFWF	= 0x00000200,
+	TIS_RESERVED	= (GENMASK(31, 20) | GENMASK(15, 12) | GENMASK(7, 4))
 };
 
 /* ISS */
@@ -617,6 +621,7 @@ enum GIC_BIT {
 enum GIS_BIT {
 	GIS_PTCF	= 0x00000001,	/* Undocumented? */
 	GIS_PTMF	= 0x00000004,
+	GIS_RESERVED	= GENMASK(15, 10),
 };
 
 /* GIE (R-Car Gen3 only) */
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index aff5516b781e..d6f753925352 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -739,10 +739,11 @@ static void ravb_error_interrupt(struct net_device *ndev)
 	u32 eis, ris2;
 
 	eis = ravb_read(ndev, EIS);
-	ravb_write(ndev, ~EIS_QFS, EIS);
+	ravb_write(ndev, ~(EIS_QFS | EIS_RESERVED), EIS);
 	if (eis & EIS_QFS) {
 		ris2 = ravb_read(ndev, RIS2);
-		ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF), RIS2);
+		ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF | RIS2_RESERVED),
+			   RIS2);
 
 		/* Receive Descriptor Empty int */
 		if (ris2 & RIS2_QFF0)
@@ -795,7 +796,7 @@ static bool ravb_timestamp_interrupt(struct net_device *ndev)
 	u32 tis = ravb_read(ndev, TIS);
 
 	if (tis & TIS_TFUF) {
-		ravb_write(ndev, ~TIS_TFUF, TIS);
+		ravb_write(ndev, ~(TIS_TFUF | TIS_RESERVED), TIS);
 		ravb_get_tx_tstamp(ndev);
 		return true;
 	}
@@ -930,7 +931,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 		/* Processing RX Descriptor Ring */
 		if (ris0 & mask) {
 			/* Clear RX interrupt */
-			ravb_write(ndev, ~mask, RIS0);
+			ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0);
 			if (ravb_rx(ndev, &quota, q))
 				goto out;
 		}
@@ -938,7 +939,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 		if (tis & mask) {
 			spin_lock_irqsave(&priv->lock, flags);
 			/* Clear TX interrupt */
-			ravb_write(ndev, ~mask, TIS);
+			ravb_write(ndev, ~(mask | TIS_RESERVED), TIS);
 			ravb_tx_free(ndev, q, true);
 			netif_wake_subqueue(ndev, q);
 			mmiowb();
diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
index 0721b5c35d91..dce2a40a31e3 100644
--- a/drivers/net/ethernet/renesas/ravb_ptp.c
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -315,7 +315,7 @@ void ravb_ptp_interrupt(struct net_device *ndev)
 		}
 	}
 
-	ravb_write(ndev, ~gis, GIS);
+	ravb_write(ndev, ~(gis | GIS_RESERVED), GIS);
 }
 
 void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev)
-- 
cgit v1.2.3


From 774268f3e51b53ed432a1ec516574fd5ba469398 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 18 Sep 2018 16:58:47 +0200
Subject: net: mvpp2: fix a txq_done race condition

When no Tx IRQ is available, the txq_done() routine (called from
tx_done()) shouldn't be called from the polling function, as in such
case it is already called in the Tx path thanks to an hrtimer. This
mostly occurred when using PPv2.1, as the engine then do not have Tx
IRQs.

Fixes: edc660fa09e2 ("net: mvpp2: replace TX coalescing interrupts with hrtimer")
Reported-by: Stefan Chulski <stefanc@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 702fec82d806..38cc01beea79 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3055,10 +3055,12 @@ static int mvpp2_poll(struct napi_struct *napi, int budget)
 				   cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK);
 	}
 
-	cause_tx = cause_rx_tx & MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK;
-	if (cause_tx) {
-		cause_tx >>= MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_OFFSET;
-		mvpp2_tx_done(port, cause_tx, qv->sw_thread_id);
+	if (port->has_tx_irqs) {
+		cause_tx = cause_rx_tx & MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK;
+		if (cause_tx) {
+			cause_tx >>= MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_OFFSET;
+			mvpp2_tx_done(port, cause_tx, qv->sw_thread_id);
+		}
 	}
 
 	/* Process RX packets */
-- 
cgit v1.2.3


From 126d6848ef13958e1cb959e96c21d19bc498ade9 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Tue, 18 Sep 2018 16:48:53 +0100
Subject: sfp: fix oops with ethtool -m

If a network interface is created prior to the SFP socket being
available, ethtool can request module information.  This unfortunately
leads to an oops:

Unable to handle kernel NULL pointer dereference at virtual address 00000008
pgd = (ptrval)
[00000008] *pgd=7c400831, *pte=00000000, *ppte=00000000
Internal error: Oops: 17 [#1] SMP ARM
Modules linked in:
CPU: 0 PID: 1480 Comm: ethtool Not tainted 4.19.0-rc3 #138
Hardware name: Broadcom Northstar Plus SoC
PC is at sfp_get_module_info+0x8/0x10
LR is at dev_ethtool+0x218c/0x2afc

Fix this by not filling in the network device's SFP bus pointer until
SFP is fully bound, thereby avoiding the core calling into the SFP bus
code.

Fixes: ce0aa27ff3f6 ("sfp: add sfp-bus to bridge between network devices and sfp cages")
Reported-by: Florian Fainelli <f.fainelli@gmail.com>
Tested-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp-bus.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 740655261e5b..83060fb349f4 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -349,6 +349,7 @@ static int sfp_register_bus(struct sfp_bus *bus)
 	}
 	if (bus->started)
 		bus->socket_ops->start(bus->sfp);
+	bus->netdev->sfp_bus = bus;
 	bus->registered = true;
 	return 0;
 }
@@ -357,6 +358,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 {
 	const struct sfp_upstream_ops *ops = bus->upstream_ops;
 
+	bus->netdev->sfp_bus = NULL;
 	if (bus->registered) {
 		if (bus->started)
 			bus->socket_ops->stop(bus->sfp);
@@ -438,7 +440,6 @@ static void sfp_upstream_clear(struct sfp_bus *bus)
 {
 	bus->upstream_ops = NULL;
 	bus->upstream = NULL;
-	bus->netdev->sfp_bus = NULL;
 	bus->netdev = NULL;
 }
 
@@ -467,7 +468,6 @@ struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode,
 		bus->upstream_ops = ops;
 		bus->upstream = upstream;
 		bus->netdev = ndev;
-		ndev->sfp_bus = bus;
 
 		if (bus->sfp) {
 			ret = sfp_register_bus(bus);
-- 
cgit v1.2.3


From cf5cca6e4cc4dea604d8c83e7676f10459d6809c Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Wed, 19 Sep 2018 15:29:06 +0200
Subject: net: mvneta: fix the Rx desc buffer DMA unmapping

With CONFIG_DMA_API_DEBUG enabled we now get a warning when using the
mvneta driver:

  mvneta d0030000.ethernet: DMA-API: device driver frees DMA memory with
  wrong function [device address=0x000000001165b000] [size=4096 bytes]
  [mapped as page] [unmapped as single]

This is because when using the s/w buffer management, the Rx descriptor
buffer is mapped with dma_map_page but unmapped with dma_unmap_single.
This patch fixes this by using the right unmapping function.

Fixes: 562e2f467e71 ("net: mvneta: Improve the buffer allocation method for SWBM")
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index bc80a678abc3..2db9708f2e24 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2008,8 +2008,8 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 				skb_add_rx_frag(rxq->skb, frag_num, page,
 						frag_offset, frag_size,
 						PAGE_SIZE);
-				dma_unmap_single(dev->dev.parent, phys_addr,
-						 PAGE_SIZE, DMA_FROM_DEVICE);
+				dma_unmap_page(dev->dev.parent, phys_addr,
+					       PAGE_SIZE, DMA_FROM_DEVICE);
 				rxq->left_size -= frag_size;
 			}
 		} else {
-- 
cgit v1.2.3


From 50fdf60181b01b7383b85d4b9acbb842263d96a2 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Wed, 19 Sep 2018 21:59:10 -0700
Subject: qed: Fix populating the invalid stag value in multi function mode.

In multi-function mode, driver receives the stag value (outer vlan)
for a PF from management FW (MFW). If the stag value is negotiated prior to
the driver load, then the stag is not notified to the driver and hence
driver will have the invalid stag value.
The fix is to request the MFW for STAG value during the driver load time.

Fixes: cac6f691 ("qed: Add support for Unified Fabric Port")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dev.c | 15 ++++++++++++++-
 drivers/net/ethernet/qlogic/qed/qed_hsi.h |  4 ++++
 2 files changed, 18 insertions(+), 1 deletion(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 016ca8a7ec8a..97f073fd3725 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -1706,7 +1706,7 @@ static int qed_vf_start(struct qed_hwfn *p_hwfn,
 int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 {
 	struct qed_load_req_params load_req_params;
-	u32 load_code, param, drv_mb_param;
+	u32 load_code, resp, param, drv_mb_param;
 	bool b_default_mtu = true;
 	struct qed_hwfn *p_hwfn;
 	int rc = 0, mfw_rc, i;
@@ -1852,6 +1852,19 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 
 	if (IS_PF(cdev)) {
 		p_hwfn = QED_LEADING_HWFN(cdev);
+
+		/* Get pre-negotiated values for stag, bandwidth etc. */
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_SPQ,
+			   "Sending GET_OEM_UPDATES command to trigger stag/bandwidth attention handling\n");
+		drv_mb_param = 1 << DRV_MB_PARAM_DUMMY_OEM_UPDATES_OFFSET;
+		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
+				 DRV_MSG_CODE_GET_OEM_UPDATES,
+				 drv_mb_param, &resp, &param);
+		if (rc)
+			DP_NOTICE(p_hwfn,
+				  "Failed to send GET_OEM_UPDATES attention request\n");
+
 		drv_mb_param = STORM_FW_VERSION;
 		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
 				 DRV_MSG_CODE_OV_UPDATE_STORM_FW_VER,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 8faceb691657..9b3ef00e5782 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -12414,6 +12414,7 @@ struct public_drv_mb {
 #define DRV_MSG_SET_RESOURCE_VALUE_MSG		0x35000000
 #define DRV_MSG_CODE_OV_UPDATE_WOL              0x38000000
 #define DRV_MSG_CODE_OV_UPDATE_ESWITCH_MODE     0x39000000
+#define DRV_MSG_CODE_GET_OEM_UPDATES            0x41000000
 
 #define DRV_MSG_CODE_BW_UPDATE_ACK		0x32000000
 #define DRV_MSG_CODE_NIG_DRAIN			0x30000000
@@ -12541,6 +12542,9 @@ struct public_drv_mb {
 #define DRV_MB_PARAM_ESWITCH_MODE_VEB	0x1
 #define DRV_MB_PARAM_ESWITCH_MODE_VEPA	0x2
 
+#define DRV_MB_PARAM_DUMMY_OEM_UPDATES_MASK	0x1
+#define DRV_MB_PARAM_DUMMY_OEM_UPDATES_OFFSET	0
+
 #define DRV_MB_PARAM_SET_LED_MODE_OPER		0x0
 #define DRV_MB_PARAM_SET_LED_MODE_ON		0x1
 #define DRV_MB_PARAM_SET_LED_MODE_OFF		0x2
-- 
cgit v1.2.3


From 0216da9413afa546627a1b0d319dfd17fef34050 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Wed, 19 Sep 2018 21:59:11 -0700
Subject: qed: Do not add VLAN 0 tag to untagged frames in multi-function mode.

In certain multi-function switch dependent modes, firmware adds vlan tag 0
to the untagged frames. This leads to double tagging for the traffic
if the dcbx is enabled, which is not the desired behavior. To avoid this,
driver needs to set "dcb_dont_add_vlan0" flag.

Fixes: cac6f691 ("qed: Add support for Unified Fabric Port")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 9 ++++++++-
 drivers/net/ethernet/qlogic/qed/qed_dcbx.h | 1 +
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 6bb76e6d3c14..d53f33c6b1fc 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -190,6 +190,7 @@ qed_dcbx_dp_protocol(struct qed_hwfn *p_hwfn, struct qed_dcbx_results *p_data)
 
 static void
 qed_dcbx_set_params(struct qed_dcbx_results *p_data,
+		    struct qed_hwfn *p_hwfn,
 		    struct qed_hw_info *p_info,
 		    bool enable,
 		    u8 prio,
@@ -206,6 +207,11 @@ qed_dcbx_set_params(struct qed_dcbx_results *p_data,
 	else
 		p_data->arr[type].update = DONT_UPDATE_DCB_DSCP;
 
+	/* Do not add vlan tag 0 when DCB is enabled and port in UFP/OV mode */
+	if ((test_bit(QED_MF_8021Q_TAGGING, &p_hwfn->cdev->mf_bits) ||
+	     test_bit(QED_MF_8021AD_TAGGING, &p_hwfn->cdev->mf_bits)))
+		p_data->arr[type].dont_add_vlan0 = true;
+
 	/* QM reconf data */
 	if (p_info->personality == personality)
 		qed_hw_info_set_offload_tc(p_info, tc);
@@ -231,7 +237,7 @@ qed_dcbx_update_app_info(struct qed_dcbx_results *p_data,
 
 		personality = qed_dcbx_app_update[i].personality;
 
-		qed_dcbx_set_params(p_data, p_info, enable,
+		qed_dcbx_set_params(p_data, p_hwfn, p_info, enable,
 				    prio, tc, type, personality);
 	}
 }
@@ -954,6 +960,7 @@ static void qed_dcbx_update_protocol_data(struct protocol_dcb_data *p_data,
 	p_data->dcb_enable_flag = p_src->arr[type].enable;
 	p_data->dcb_priority = p_src->arr[type].priority;
 	p_data->dcb_tc = p_src->arr[type].tc;
+	p_data->dcb_dont_add_vlan0 = p_src->arr[type].dont_add_vlan0;
 }
 
 /* Set pf update ramrod command params */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
index a4d688c04e18..01f253ea4b22 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
@@ -55,6 +55,7 @@ struct qed_dcbx_app_data {
 	u8 update;		/* Update indication */
 	u8 priority;		/* Priority */
 	u8 tc;			/* Traffic Class */
+	bool dont_add_vlan0;	/* Do not insert a vlan tag with id 0 */
 };
 
 #define QED_DCBX_VERSION_DISABLED       0
-- 
cgit v1.2.3


From 7e3e375ceede8fba5218362d14db7de25fa83f12 Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Wed, 19 Sep 2018 21:59:12 -0700
Subject: qed: Add missing device config for RoCE EDPM in UFP mode.

This patch adds support to configure the DORQ to use vlan-id/priority for
roce EDPM.

Fixes: cac6f691 ("qed: Add support for Unified Fabric Port")
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Tomer Tayar <Tomer.Tayar@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c     | 40 ++++++++++++++------------
 drivers/net/ethernet/qlogic/qed/qed_mcp.c      | 24 +++++++++++++---
 drivers/net/ethernet/qlogic/qed/qed_reg_addr.h |  6 ++++
 3 files changed, 48 insertions(+), 22 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index d53f33c6b1fc..f5459de6d60a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -190,11 +190,8 @@ qed_dcbx_dp_protocol(struct qed_hwfn *p_hwfn, struct qed_dcbx_results *p_data)
 
 static void
 qed_dcbx_set_params(struct qed_dcbx_results *p_data,
-		    struct qed_hwfn *p_hwfn,
-		    struct qed_hw_info *p_info,
-		    bool enable,
-		    u8 prio,
-		    u8 tc,
+		    struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+		    bool enable, u8 prio, u8 tc,
 		    enum dcbx_protocol_type type,
 		    enum qed_pci_personality personality)
 {
@@ -213,18 +210,24 @@ qed_dcbx_set_params(struct qed_dcbx_results *p_data,
 		p_data->arr[type].dont_add_vlan0 = true;
 
 	/* QM reconf data */
-	if (p_info->personality == personality)
-		qed_hw_info_set_offload_tc(p_info, tc);
+	if (p_hwfn->hw_info.personality == personality)
+		qed_hw_info_set_offload_tc(&p_hwfn->hw_info, tc);
+
+	/* Configure dcbx vlan priority in doorbell block for roce EDPM */
+	if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits) &&
+	    type == DCBX_PROTOCOL_ROCE) {
+		qed_wr(p_hwfn, p_ptt, DORQ_REG_TAG1_OVRD_MODE, 1);
+		qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_PCP_BB_K2, prio << 1);
+	}
 }
 
 /* Update app protocol data and hw_info fields with the TLV info */
 static void
 qed_dcbx_update_app_info(struct qed_dcbx_results *p_data,
-			 struct qed_hwfn *p_hwfn,
-			 bool enable,
-			 u8 prio, u8 tc, enum dcbx_protocol_type type)
+			 struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			 bool enable, u8 prio, u8 tc,
+			 enum dcbx_protocol_type type)
 {
-	struct qed_hw_info *p_info = &p_hwfn->hw_info;
 	enum qed_pci_personality personality;
 	enum dcbx_protocol_type id;
 	int i;
@@ -237,7 +240,7 @@ qed_dcbx_update_app_info(struct qed_dcbx_results *p_data,
 
 		personality = qed_dcbx_app_update[i].personality;
 
-		qed_dcbx_set_params(p_data, p_hwfn, p_info, enable,
+		qed_dcbx_set_params(p_data, p_hwfn, p_ptt, enable,
 				    prio, tc, type, personality);
 	}
 }
@@ -271,7 +274,7 @@ qed_dcbx_get_app_protocol_type(struct qed_hwfn *p_hwfn,
  * reconfiguring QM. Get protocol specific data for PF update ramrod command.
  */
 static int
-qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn,
+qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 		     struct qed_dcbx_results *p_data,
 		     struct dcbx_app_priority_entry *p_tbl,
 		     u32 pri_tc_tbl, int count, u8 dcbx_version)
@@ -315,7 +318,7 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn,
 				enable = true;
 			}
 
-			qed_dcbx_update_app_info(p_data, p_hwfn, enable,
+			qed_dcbx_update_app_info(p_data, p_hwfn, p_ptt, enable,
 						 priority, tc, type);
 		}
 	}
@@ -337,7 +340,7 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn,
 			continue;
 
 		enable = (type == DCBX_PROTOCOL_ETH) ? false : !!dcbx_version;
-		qed_dcbx_update_app_info(p_data, p_hwfn, enable,
+		qed_dcbx_update_app_info(p_data, p_hwfn, p_ptt, enable,
 					 priority, tc, type);
 	}
 
@@ -347,7 +350,8 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn,
 /* Parse app TLV's to update TC information in hw_info structure for
  * reconfiguring QM. Get protocol specific data for PF update ramrod command.
  */
-static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn)
+static int
+qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct dcbx_app_priority_feature *p_app;
 	struct dcbx_app_priority_entry *p_tbl;
@@ -371,7 +375,7 @@ static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn)
 	p_info = &p_hwfn->hw_info;
 	num_entries = QED_MFW_GET_FIELD(p_app->flags, DCBX_APP_NUM_ENTRIES);
 
-	rc = qed_dcbx_process_tlv(p_hwfn, &data, p_tbl, pri_tc_tbl,
+	rc = qed_dcbx_process_tlv(p_hwfn, p_ptt, &data, p_tbl, pri_tc_tbl,
 				  num_entries, dcbx_version);
 	if (rc)
 		return rc;
@@ -897,7 +901,7 @@ qed_dcbx_mib_update_event(struct qed_hwfn *p_hwfn,
 		return rc;
 
 	if (type == QED_DCBX_OPERATIONAL_MIB) {
-		rc = qed_dcbx_process_mib_info(p_hwfn);
+		rc = qed_dcbx_process_mib_info(p_hwfn, p_ptt);
 		if (!rc) {
 			/* reconfigure tcs of QM queues according
 			 * to negotiation results
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 5d37ec7e9b0b..58c7eb9d8e1b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1581,13 +1581,29 @@ static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	p_hwfn->mcp_info->func_info.ovlan = (u16)shmem_info.ovlan_stag &
 						 FUNC_MF_CFG_OV_STAG_MASK;
 	p_hwfn->hw_info.ovlan = p_hwfn->mcp_info->func_info.ovlan;
-	if ((p_hwfn->hw_info.hw_mode & BIT(MODE_MF_SD)) &&
-	    (p_hwfn->hw_info.ovlan != QED_MCP_VLAN_UNSET)) {
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_TAG_VALUE, p_hwfn->hw_info.ovlan);
+	if (test_bit(QED_MF_OVLAN_CLSS, &p_hwfn->cdev->mf_bits)) {
+		if (p_hwfn->hw_info.ovlan != QED_MCP_VLAN_UNSET) {
+			qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_FUNC_TAG_VALUE,
+			       p_hwfn->hw_info.ovlan);
+			qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_FUNC_TAG_EN, 1);
+
+			/* Configure DB to add external vlan to EDPM packets */
+			qed_wr(p_hwfn, p_ptt, DORQ_REG_TAG1_OVRD_MODE, 1);
+			qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_EXT_VID_BB_K2,
+			       p_hwfn->hw_info.ovlan);
+		} else {
+			qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_FUNC_TAG_EN, 0);
+			qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_FUNC_TAG_VALUE, 0);
+			qed_wr(p_hwfn, p_ptt, DORQ_REG_TAG1_OVRD_MODE, 0);
+			qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_EXT_VID_BB_K2, 0);
+		}
+
 		qed_sp_pf_update_stag(p_hwfn);
 	}
 
+	DP_VERBOSE(p_hwfn, QED_MSG_SP, "ovlan  = %d hw_mode = 0x%x\n",
+		   p_hwfn->mcp_info->func_info.ovlan, p_hwfn->hw_info.hw_mode);
+
 	/* Acknowledge the MFW */
 	qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_S_TAG_UPDATE_ACK, 0,
 		    &resp, &param);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index f736f70956fd..2440970882c4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -216,6 +216,12 @@
 	0x00c000UL
 #define  DORQ_REG_IFEN \
 	0x100040UL
+#define DORQ_REG_TAG1_OVRD_MODE \
+	0x1008b4UL
+#define DORQ_REG_PF_PCP_BB_K2 \
+	0x1008c4UL
+#define DORQ_REG_PF_EXT_VID_BB_K2 \
+	0x1008c8UL
 #define DORQ_REG_DB_DROP_REASON \
 	0x100a2cUL
 #define DORQ_REG_DB_DROP_DETAILS \
-- 
cgit v1.2.3


From f9d5b1d50840320fb6c66fafd1a532a995fc3758 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 20 Sep 2018 09:31:45 +0300
Subject: mlxsw: spectrum: Bump required firmware version

MC-aware mode was introduced to mlxsw in commit 7b8195306694 ("mlxsw: spectrum:
Configure MC-aware mode on mlxsw ports") and fixed up later in commit
3a3539cd3632 ("mlxsw: spectrum_buffers: Set up a dedicated pool for BUM
traffic"). As the final piece of puzzle, a firmware issue whereby a wrong
priority was assigned to BUM traffic was corrected in FW version 13.1703.4.
Therefore require this FW version in the driver.

Fixes: 7b8195306694 ("mlxsw: spectrum: Configure MC-aware mode on mlxsw ports")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 930700413b1d..b492152c8881 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -44,8 +44,8 @@
 #define MLXSW_SP_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
 
 #define MLXSW_SP1_FWREV_MAJOR 13
-#define MLXSW_SP1_FWREV_MINOR 1702
-#define MLXSW_SP1_FWREV_SUBMINOR 6
+#define MLXSW_SP1_FWREV_MINOR 1703
+#define MLXSW_SP1_FWREV_SUBMINOR 4
 #define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702
 
 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
-- 
cgit v1.2.3


From 8c6ec3613e7b0aade20a3196169c0bab32ed3e3f Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 19 Sep 2018 19:01:37 +0200
Subject: bnxt_en: don't try to offload VLAN 'modify' action

bnxt offload code currently supports only 'push' and 'pop' operation: let
.ndo_setup_tc() return -EOPNOTSUPP if VLAN 'modify' action is configured.

Fixes: 2ae7408fedfe ("bnxt_en: bnxt: add TC flower filter offload support")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Acked-by: Sathya Perla <sathya.perla@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 092c817f8f11..e1594c9df4c6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -75,17 +75,23 @@ static int bnxt_tc_parse_redir(struct bnxt *bp,
 	return 0;
 }
 
-static void bnxt_tc_parse_vlan(struct bnxt *bp,
-			       struct bnxt_tc_actions *actions,
-			       const struct tc_action *tc_act)
+static int 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) {
+	switch (tcf_vlan_action(tc_act)) {
+	case TCA_VLAN_ACT_POP:
 		actions->flags |= BNXT_TC_ACTION_FLAG_POP_VLAN;
-	} else if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_PUSH) {
+		break;
+	case 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);
+		break;
+	default:
+		return -EOPNOTSUPP;
 	}
+	return 0;
 }
 
 static int bnxt_tc_parse_tunnel_set(struct bnxt *bp,
@@ -134,7 +140,9 @@ static int bnxt_tc_parse_actions(struct bnxt *bp,
 
 		/* Push/pop VLAN */
 		if (is_tcf_vlan(tc_act)) {
-			bnxt_tc_parse_vlan(bp, actions, tc_act);
+			rc = bnxt_tc_parse_vlan(bp, actions, tc_act);
+			if (rc)
+				return rc;
 			continue;
 		}
 
-- 
cgit v1.2.3


From 10bc6a6042c900934a097988b5d50e3cf3f91781 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 20 Sep 2018 22:47:09 +0200
Subject: r8169: fix autoneg issue on resume with RTL8168E

It was reported that chip version 33 (RTL8168E) ends up with
10MBit/Half on a 1GBit link after resuming from S3 (with different
link partners). For whatever reason the PHY on this chip doesn't
properly start a renegotiation when soft-reset.
Explicitly requesting a renegotiation fixes this.

Fixes: a2965f12fde6 ("r8169: remove rtl8169_set_speed_xmii")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reported-by: Neil MacLeod <neil@nmacleod.com>
Tested-by: Neil MacLeod <neil@nmacleod.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index bb529ff2ca81..ab30aaeac6d3 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4071,6 +4071,15 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 	phy_speed_up(dev->phydev);
 
 	genphy_soft_reset(dev->phydev);
+
+	/* It was reported that chip version 33 ends up with 10MBit/Half on a
+	 * 1GBit link after resuming from S3. For whatever reason the PHY on
+	 * this chip doesn't properly start a renegotiation when soft-reset.
+	 * Explicitly requesting a renegotiation fixes this.
+	 */
+	if (tp->mac_version == RTL_GIGA_MAC_VER_33 &&
+	    dev->phydev->autoneg == AUTONEG_ENABLE)
+		phy_restart_aneg(dev->phydev);
 }
 
 static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr)
-- 
cgit v1.2.3


From 652ef42c134da1bbb03bd4c9b4291dfaf8d7febb Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 20 Sep 2018 12:08:54 +0200
Subject: net: mscc: fix the frame extraction into the skb

When extracting frames from the Ocelot switch, the frame check sequence
(FCS) is present at the end of the data extracted. The FCS was put into
the sk buffer which introduced some issues (as length related ones), as
the FCS shouldn't be part of an Rx sk buffer.

This patch fixes the Ocelot switch extraction behaviour by discarding
the FCS.

Fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support")
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_board.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index 26bb3b18f3be..3cdf63e35b53 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -91,7 +91,7 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
 		struct sk_buff *skb;
 		struct net_device *dev;
 		u32 *buf;
-		int sz, len;
+		int sz, len, buf_len;
 		u32 ifh[4];
 		u32 val;
 		struct frame_info info;
@@ -116,14 +116,20 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
 			err = -ENOMEM;
 			break;
 		}
-		buf = (u32 *)skb_put(skb, info.len);
+		buf_len = info.len - ETH_FCS_LEN;
+		buf = (u32 *)skb_put(skb, buf_len);
 
 		len = 0;
 		do {
 			sz = ocelot_rx_frame_word(ocelot, grp, false, &val);
 			*buf++ = val;
 			len += sz;
-		} while ((sz == 4) && (len < info.len));
+		} while (len < buf_len);
+
+		/* Read the FCS and discard it */
+		sz = ocelot_rx_frame_word(ocelot, grp, false, &val);
+		/* Update the statistics if part of the FCS was read before */
+		len -= ETH_FCS_LEN - sz;
 
 		if (sz < 0) {
 			err = sz;
-- 
cgit v1.2.3


From 72b462798c2a258725dd741d1c6c139446e20d12 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 21 Sep 2018 10:53:47 +0800
Subject: net: seeq: fix return type of ndo_start_xmit function

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.

Found by coccinelle.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/seeq/ether3.c  | 5 +++--
 drivers/net/ethernet/seeq/sgiseeq.c | 3 ++-
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c
index c5bc124b41a9..d1bb73bf9914 100644
--- a/drivers/net/ethernet/seeq/ether3.c
+++ b/drivers/net/ethernet/seeq/ether3.c
@@ -77,7 +77,8 @@ static void	ether3_setmulticastlist(struct net_device *dev);
 static int	ether3_rx(struct net_device *dev, unsigned int maxcnt);
 static void	ether3_tx(struct net_device *dev);
 static int	ether3_open (struct net_device *dev);
-static int	ether3_sendpacket (struct sk_buff *skb, struct net_device *dev);
+static netdev_tx_t	ether3_sendpacket(struct sk_buff *skb,
+					  struct net_device *dev);
 static irqreturn_t ether3_interrupt (int irq, void *dev_id);
 static int	ether3_close (struct net_device *dev);
 static void	ether3_setmulticastlist (struct net_device *dev);
@@ -481,7 +482,7 @@ static void ether3_timeout(struct net_device *dev)
 /*
  * Transmit a packet
  */
-static int
+static netdev_tx_t
 ether3_sendpacket(struct sk_buff *skb, struct net_device *dev)
 {
 	unsigned long flags;
diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c
index 573691bc3b71..70cce63a6081 100644
--- a/drivers/net/ethernet/seeq/sgiseeq.c
+++ b/drivers/net/ethernet/seeq/sgiseeq.c
@@ -578,7 +578,8 @@ static inline int sgiseeq_reset(struct net_device *dev)
 	return 0;
 }
 
-static int sgiseeq_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t
+sgiseeq_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct sgiseeq_private *sp = netdev_priv(dev);
 	struct hpc3_ethregs *hregs = sp->hregs;
-- 
cgit v1.2.3


From f3bf939f3d4552becb115d76e17b3e5957bab4a2 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 21 Sep 2018 11:02:37 +0800
Subject: net: cirrus: fix return type of ndo_start_xmit function

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.

Found by coccinelle.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cirrus/ep93xx_eth.c | 2 +-
 drivers/net/ethernet/cirrus/mac89x0.c    | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c
index e2a702996db4..13dfdfca49fc 100644
--- a/drivers/net/ethernet/cirrus/ep93xx_eth.c
+++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c
@@ -332,7 +332,7 @@ static int ep93xx_poll(struct napi_struct *napi, int budget)
 	return rx;
 }
 
-static int ep93xx_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t ep93xx_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ep93xx_priv *ep = netdev_priv(dev);
 	struct ep93xx_tdesc *txd;
diff --git a/drivers/net/ethernet/cirrus/mac89x0.c b/drivers/net/ethernet/cirrus/mac89x0.c
index 3f8fe8fd79cc..6324e80960c3 100644
--- a/drivers/net/ethernet/cirrus/mac89x0.c
+++ b/drivers/net/ethernet/cirrus/mac89x0.c
@@ -113,7 +113,7 @@ struct net_local {
 
 /* Index to functions, as function prototypes. */
 static int net_open(struct net_device *dev);
-static int net_send_packet(struct sk_buff *skb, struct net_device *dev);
+static netdev_tx_t net_send_packet(struct sk_buff *skb, struct net_device *dev);
 static irqreturn_t net_interrupt(int irq, void *dev_id);
 static void set_multicast_list(struct net_device *dev);
 static void net_rx(struct net_device *dev);
@@ -324,7 +324,7 @@ net_open(struct net_device *dev)
 	return 0;
 }
 
-static int
+static netdev_tx_t
 net_send_packet(struct sk_buff *skb, struct net_device *dev)
 {
 	struct net_local *lp = netdev_priv(dev);
-- 
cgit v1.2.3


From 28d304efb88f18aadfe9219f0e4b2b0ef9558a3b Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 21 Sep 2018 11:05:50 +0800
Subject: net: sgi: fix return type of ndo_start_xmit function

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.

Found by coccinelle.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sgi/ioc3-eth.c | 4 ++--
 drivers/net/ethernet/sgi/meth.c     | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 18d533fdf14c..3140999642ba 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -99,7 +99,7 @@ struct ioc3_private {
 
 static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
 static void ioc3_set_multicast_list(struct net_device *dev);
-static int ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev);
+static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev);
 static void ioc3_timeout(struct net_device *dev);
 static inline unsigned int ioc3_hash(const unsigned char *addr);
 static inline void ioc3_stop(struct ioc3_private *ip);
@@ -1390,7 +1390,7 @@ static struct pci_driver ioc3_driver = {
 	.remove		= ioc3_remove_one,
 };
 
-static int ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	unsigned long data;
 	struct ioc3_private *ip = netdev_priv(dev);
diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c
index ea55abd62ec7..703fbbefea44 100644
--- a/drivers/net/ethernet/sgi/meth.c
+++ b/drivers/net/ethernet/sgi/meth.c
@@ -697,7 +697,7 @@ static void meth_add_to_tx_ring(struct meth_private *priv, struct sk_buff *skb)
 /*
  * Transmit a packet (called by the kernel)
  */
-static int meth_tx(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t meth_tx(struct sk_buff *skb, struct net_device *dev)
 {
 	struct meth_private *priv = netdev_priv(dev);
 	unsigned long flags;
-- 
cgit v1.2.3


From f0f25516e3b9efff2a34059347d13361d26e314a Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 21 Sep 2018 11:35:11 +0800
Subject: net: wiznet: fix return type of ndo_start_xmit function

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.

Found by coccinelle.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/wiznet/w5100.c | 2 +-
 drivers/net/ethernet/wiznet/w5300.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index 2bdfb39215e9..d8ba512f166a 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -835,7 +835,7 @@ static void w5100_tx_work(struct work_struct *work)
 	w5100_tx_skb(priv->ndev, skb);
 }
 
-static int w5100_start_tx(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t w5100_start_tx(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct w5100_priv *priv = netdev_priv(ndev);
 
diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
index 56ae573001e8..80fdbff67d82 100644
--- a/drivers/net/ethernet/wiznet/w5300.c
+++ b/drivers/net/ethernet/wiznet/w5300.c
@@ -365,7 +365,7 @@ static void w5300_tx_timeout(struct net_device *ndev)
 	netif_wake_queue(ndev);
 }
 
-static int w5300_start_tx(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t w5300_start_tx(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct w5300_priv *priv = netdev_priv(ndev);
 
-- 
cgit v1.2.3


From 648c361a568dcd098a3496c6c66bca4c8473e52b Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 21 Sep 2018 11:44:05 +0800
Subject: net: i825xx: fix return type of ndo_start_xmit function

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.

Found by coccinelle.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/i825xx/ether1.c     | 5 +++--
 drivers/net/ethernet/i825xx/lib82596.c   | 4 ++--
 drivers/net/ethernet/i825xx/sun3_82586.c | 6 ++++--
 3 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/i825xx/ether1.c b/drivers/net/ethernet/i825xx/ether1.c
index dc983450354b..35f6291a3672 100644
--- a/drivers/net/ethernet/i825xx/ether1.c
+++ b/drivers/net/ethernet/i825xx/ether1.c
@@ -64,7 +64,8 @@ static unsigned int net_debug = NET_DEBUG;
 #define RX_AREA_END	0x0fc00
 
 static int ether1_open(struct net_device *dev);
-static int ether1_sendpacket(struct sk_buff *skb, struct net_device *dev);
+static netdev_tx_t ether1_sendpacket(struct sk_buff *skb,
+				     struct net_device *dev);
 static irqreturn_t ether1_interrupt(int irq, void *dev_id);
 static int ether1_close(struct net_device *dev);
 static void ether1_setmulticastlist(struct net_device *dev);
@@ -667,7 +668,7 @@ ether1_timeout(struct net_device *dev)
 	netif_wake_queue(dev);
 }
 
-static int
+static netdev_tx_t
 ether1_sendpacket (struct sk_buff *skb, struct net_device *dev)
 {
 	int tmp, tst, nopaddr, txaddr, tbdaddr, dataddr;
diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c
index f00a1dc2128c..2f7ae118217f 100644
--- a/drivers/net/ethernet/i825xx/lib82596.c
+++ b/drivers/net/ethernet/i825xx/lib82596.c
@@ -347,7 +347,7 @@ static const char init_setup[] =
 	0x7f /*  *multi IA */ };
 
 static int i596_open(struct net_device *dev);
-static int i596_start_xmit(struct sk_buff *skb, struct net_device *dev);
+static netdev_tx_t i596_start_xmit(struct sk_buff *skb, struct net_device *dev);
 static irqreturn_t i596_interrupt(int irq, void *dev_id);
 static int i596_close(struct net_device *dev);
 static void i596_add_cmd(struct net_device *dev, struct i596_cmd *cmd);
@@ -966,7 +966,7 @@ static void i596_tx_timeout (struct net_device *dev)
 }
 
 
-static int i596_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t i596_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct i596_private *lp = netdev_priv(dev);
 	struct tx_cmd *tx_cmd;
diff --git a/drivers/net/ethernet/i825xx/sun3_82586.c b/drivers/net/ethernet/i825xx/sun3_82586.c
index 8bb15a8c2a40..1a86184d44c0 100644
--- a/drivers/net/ethernet/i825xx/sun3_82586.c
+++ b/drivers/net/ethernet/i825xx/sun3_82586.c
@@ -121,7 +121,8 @@ static int     sun3_82586_probe1(struct net_device *dev,int ioaddr);
 static irqreturn_t sun3_82586_interrupt(int irq,void *dev_id);
 static int     sun3_82586_open(struct net_device *dev);
 static int     sun3_82586_close(struct net_device *dev);
-static int     sun3_82586_send_packet(struct sk_buff *,struct net_device *);
+static netdev_tx_t     sun3_82586_send_packet(struct sk_buff *,
+					      struct net_device *);
 static struct  net_device_stats *sun3_82586_get_stats(struct net_device *dev);
 static void    set_multicast_list(struct net_device *dev);
 static void    sun3_82586_timeout(struct net_device *dev);
@@ -1002,7 +1003,8 @@ static void sun3_82586_timeout(struct net_device *dev)
  * send frame
  */
 
-static int sun3_82586_send_packet(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t
+sun3_82586_send_packet(struct sk_buff *skb, struct net_device *dev)
 {
 	int len,i;
 #ifndef NO_NOPCOMMANDS
-- 
cgit v1.2.3


From e6ce3822a9f264b3f24c1acdc624131fb014f2f0 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 21 Sep 2018 11:46:37 +0800
Subject: net: apple: fix return type of ndo_start_xmit function

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, so make sure the implementation in
this driver has returns 'netdev_tx_t' value, and change the function
return type to netdev_tx_t.

Found by coccinelle.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/apple/bmac.c    | 4 ++--
 drivers/net/ethernet/apple/mace.c    | 4 ++--
 drivers/net/ethernet/apple/macmace.c | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 024998d6d8c6..6a8e2567f2bd 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -154,7 +154,7 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id);
 static irqreturn_t bmac_rxdma_intr(int irq, void *dev_id);
 static void bmac_set_timeout(struct net_device *dev);
 static void bmac_tx_timeout(struct timer_list *t);
-static int bmac_output(struct sk_buff *skb, struct net_device *dev);
+static netdev_tx_t bmac_output(struct sk_buff *skb, struct net_device *dev);
 static void bmac_start(struct net_device *dev);
 
 #define	DBDMA_SET(x)	( ((x) | (x) << 16) )
@@ -1456,7 +1456,7 @@ bmac_start(struct net_device *dev)
 	spin_unlock_irqrestore(&bp->lock, flags);
 }
 
-static int
+static netdev_tx_t
 bmac_output(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bmac_data *bp = netdev_priv(dev);
diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c
index 0b5429d76bcf..68b9ee489489 100644
--- a/drivers/net/ethernet/apple/mace.c
+++ b/drivers/net/ethernet/apple/mace.c
@@ -78,7 +78,7 @@ struct mace_data {
 
 static int mace_open(struct net_device *dev);
 static int mace_close(struct net_device *dev);
-static int mace_xmit_start(struct sk_buff *skb, struct net_device *dev);
+static netdev_tx_t mace_xmit_start(struct sk_buff *skb, struct net_device *dev);
 static void mace_set_multicast(struct net_device *dev);
 static void mace_reset(struct net_device *dev);
 static int mace_set_address(struct net_device *dev, void *addr);
@@ -525,7 +525,7 @@ static inline void mace_set_timeout(struct net_device *dev)
     mp->timeout_active = 1;
 }
 
-static int mace_xmit_start(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t mace_xmit_start(struct sk_buff *skb, struct net_device *dev)
 {
     struct mace_data *mp = netdev_priv(dev);
     volatile struct dbdma_regs __iomem *td = mp->tx_dma;
diff --git a/drivers/net/ethernet/apple/macmace.c b/drivers/net/ethernet/apple/macmace.c
index 137cbb470af2..376f2c2613e7 100644
--- a/drivers/net/ethernet/apple/macmace.c
+++ b/drivers/net/ethernet/apple/macmace.c
@@ -89,7 +89,7 @@ struct mace_frame {
 
 static int mace_open(struct net_device *dev);
 static int mace_close(struct net_device *dev);
-static int mace_xmit_start(struct sk_buff *skb, struct net_device *dev);
+static netdev_tx_t mace_xmit_start(struct sk_buff *skb, struct net_device *dev);
 static void mace_set_multicast(struct net_device *dev);
 static int mace_set_address(struct net_device *dev, void *addr);
 static void mace_reset(struct net_device *dev);
@@ -444,7 +444,7 @@ static int mace_close(struct net_device *dev)
  * Transmit a frame
  */
 
-static int mace_xmit_start(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t mace_xmit_start(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mace_data *mp = netdev_priv(dev);
 	unsigned long flags;
-- 
cgit v1.2.3


From 8ac1ee6f4d62e781e3b3fd8b9c42b70371427669 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Fri, 21 Sep 2018 02:44:12 -0700
Subject: net/mlx4: Use cpumask_available for eq->affinity_mask

Clang warns that the address of a pointer will always evaluated as true
in a boolean context:

drivers/net/ethernet/mellanox/mlx4/eq.c:243:11: warning: address of
array 'eq->affinity_mask' will always evaluate to 'true'
[-Wpointer-bool-conversion]
        if (!eq->affinity_mask || cpumask_empty(eq->affinity_mask))
            ~~~~~^~~~~~~~~~~~~
1 warning generated.

Use cpumask_available, introduced in commit f7e30f01a9e2 ("cpumask: Add
helper cpumask_available()"), which does the proper checking and avoids
this warning.

Link: https://github.com/ClangBuiltLinux/linux/issues/86
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/eq.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 1f3372c1802e..2df92dbd38e1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -240,7 +240,8 @@ static void mlx4_set_eq_affinity_hint(struct mlx4_priv *priv, int vec)
 	struct mlx4_dev *dev = &priv->dev;
 	struct mlx4_eq *eq = &priv->eq_table.eq[vec];
 
-	if (!eq->affinity_mask || cpumask_empty(eq->affinity_mask))
+	if (!cpumask_available(eq->affinity_mask) ||
+	    cpumask_empty(eq->affinity_mask))
 		return;
 
 	hint_err = irq_set_affinity_hint(eq->irq, eq->affinity_mask);
-- 
cgit v1.2.3


From 93f62ad5e83a13e0c224dfca5ef40f90c09aad51 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:39 -0700
Subject: bonding: use netpoll_poll_dev() helper

We want to allow NAPI drivers to no longer provide
ndo_poll_controller() method, as it has been proven problematic.

team driver must not look at its presence, but instead call
netpoll_poll_dev() which factorize the needed actions.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index a764a83f99da..0d87e11e7f1d 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -971,16 +971,13 @@ static void bond_poll_controller(struct net_device *bond_dev)
 	struct slave *slave = NULL;
 	struct list_head *iter;
 	struct ad_info ad_info;
-	struct netpoll_info *ni;
-	const struct net_device_ops *ops;
 
 	if (BOND_MODE(bond) == BOND_MODE_8023AD)
 		if (bond_3ad_get_active_agg_info(bond, &ad_info))
 			return;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		ops = slave->dev->netdev_ops;
-		if (!bond_slave_is_up(slave) || !ops->ndo_poll_controller)
+		if (!bond_slave_is_up(slave))
 			continue;
 
 		if (BOND_MODE(bond) == BOND_MODE_8023AD) {
@@ -992,11 +989,7 @@ static void bond_poll_controller(struct net_device *bond_dev)
 				continue;
 		}
 
-		ni = rcu_dereference_bh(slave->dev->npinfo);
-		if (down_trylock(&ni->dev_lock))
-			continue;
-		ops->ndo_poll_controller(slave->dev);
-		up(&ni->dev_lock);
+		netpoll_poll_dev(slave->dev);
 	}
 }
 
-- 
cgit v1.2.3


From b80e71a986c2ab5677dc6b84923cd7030b690800 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:40 -0700
Subject: ixgbe: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

ixgbe uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Reported-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Song Liu <songliubraving@fb.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 25 -------------------------
 1 file changed, 25 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 9a23d33a47ed..f27d73a7bf16 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8768,28 +8768,6 @@ static int ixgbe_del_sanmac_netdev(struct net_device *dev)
 	return err;
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/*
- * Polling 'interrupt' - used by things like netconsole to send skbs
- * without having to re-enable interrupts. It's not called while
- * the interrupt routine is executing.
- */
-static void ixgbe_netpoll(struct net_device *netdev)
-{
-	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	int i;
-
-	/* if interface is down do nothing */
-	if (test_bit(__IXGBE_DOWN, &adapter->state))
-		return;
-
-	/* loop through and schedule all active queues */
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		ixgbe_msix_clean_rings(0, adapter->q_vector[i]);
-}
-
-#endif
-
 static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats,
 				   struct ixgbe_ring *ring)
 {
@@ -10251,9 +10229,6 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_get_vf_config	= ixgbe_ndo_get_vf_config,
 	.ndo_get_stats64	= ixgbe_get_stats64,
 	.ndo_setup_tc		= __ixgbe_setup_tc,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= ixgbe_netpoll,
-#endif
 #ifdef IXGBE_FCOE
 	.ndo_select_queue	= ixgbe_select_queue,
 	.ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get,
-- 
cgit v1.2.3


From 6f5d941ebadeb1150530f205af0eb5cf5bfeb219 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:41 -0700
Subject: ixgbevf: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

ixgbevf uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 21 ---------------------
 1 file changed, 21 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index d86446d202d5..5a228582423b 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4233,24 +4233,6 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
 	return 0;
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/* Polling 'interrupt' - used by things like netconsole to send skbs
- * without having to re-enable interrupts. It's not called while
- * the interrupt routine is executing.
- */
-static void ixgbevf_netpoll(struct net_device *netdev)
-{
-	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
-	int i;
-
-	/* if interface is down do nothing */
-	if (test_bit(__IXGBEVF_DOWN, &adapter->state))
-		return;
-	for (i = 0; i < adapter->num_rx_queues; i++)
-		ixgbevf_msix_clean_rings(0, adapter->q_vector[i]);
-}
-#endif /* CONFIG_NET_POLL_CONTROLLER */
-
 static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -4482,9 +4464,6 @@ static const struct net_device_ops ixgbevf_netdev_ops = {
 	.ndo_tx_timeout		= ixgbevf_tx_timeout,
 	.ndo_vlan_rx_add_vid	= ixgbevf_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= ixgbevf_vlan_rx_kill_vid,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= ixgbevf_netpoll,
-#endif
 	.ndo_features_check	= ixgbevf_features_check,
 	.ndo_bpf		= ixgbevf_xdp,
 };
-- 
cgit v1.2.3


From dda9d57e2d4245c0d8e309ee7399bf2ebfca64ae Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:42 -0700
Subject: fm10k: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
lasts for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

fm10k uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/fm10k/fm10k.h        |  3 ---
 drivers/net/ethernet/intel/fm10k/fm10k_netdev.c |  3 ---
 drivers/net/ethernet/intel/fm10k/fm10k_pci.c    | 22 ----------------------
 3 files changed, 28 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h
index a903a0ba45e1..7d42582ed48d 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k.h
@@ -504,9 +504,6 @@ void fm10k_update_stats(struct fm10k_intfc *interface);
 void fm10k_service_event_schedule(struct fm10k_intfc *interface);
 void fm10k_macvlan_schedule(struct fm10k_intfc *interface);
 void fm10k_update_rx_drop_en(struct fm10k_intfc *interface);
-#ifdef CONFIG_NET_POLL_CONTROLLER
-void fm10k_netpoll(struct net_device *netdev);
-#endif
 
 /* Netdev */
 struct net_device *fm10k_alloc_netdev(const struct fm10k_info *info);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 929f538d28bc..538a8467f434 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -1648,9 +1648,6 @@ static const struct net_device_ops fm10k_netdev_ops = {
 	.ndo_udp_tunnel_del	= fm10k_udp_tunnel_del,
 	.ndo_dfwd_add_station	= fm10k_dfwd_add_station,
 	.ndo_dfwd_del_station	= fm10k_dfwd_del_station,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= fm10k_netpoll,
-#endif
 	.ndo_features_check	= fm10k_features_check,
 };
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index 15071e4adb98..c859ababeed5 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -1210,28 +1210,6 @@ static irqreturn_t fm10k_msix_mbx_vf(int __always_unused irq, void *data)
 	return IRQ_HANDLED;
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/**
- *  fm10k_netpoll - A Polling 'interrupt' handler
- *  @netdev: network interface device structure
- *
- *  This is used by netconsole to send skbs without having to re-enable
- *  interrupts. It's not called while the normal interrupt routine is executing.
- **/
-void fm10k_netpoll(struct net_device *netdev)
-{
-	struct fm10k_intfc *interface = netdev_priv(netdev);
-	int i;
-
-	/* if interface is down do nothing */
-	if (test_bit(__FM10K_DOWN, interface->state))
-		return;
-
-	for (i = 0; i < interface->num_q_vectors; i++)
-		fm10k_msix_clean_rings(0, interface->q_vector[i]);
-}
-
-#endif
 #define FM10K_ERR_MSG(type) case (type): error = #type; break
 static void fm10k_handle_fault(struct fm10k_intfc *interface, int type,
 			       struct fm10k_fault *fault)
-- 
cgit v1.2.3


From 2753166e4be9df4677745a7f7d9d8daa94938a08 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:43 -0700
Subject: ixgb: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

ixgb uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

This also removes a problematic use of disable_irq() in
a context it is forbidden, as explained in commit
af3e0fcf7887 ("8139too: Use disable_irq_nosync() in
rtl8139_poll_controller()")

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgb/ixgb_main.c | 25 -------------------------
 1 file changed, 25 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index d3e72d0f66ef..7722153c4ac2 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -81,11 +81,6 @@ static int ixgb_vlan_rx_kill_vid(struct net_device *netdev,
 				 __be16 proto, u16 vid);
 static void ixgb_restore_vlan(struct ixgb_adapter *adapter);
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/* for netdump / net console */
-static void ixgb_netpoll(struct net_device *dev);
-#endif
-
 static pci_ers_result_t ixgb_io_error_detected (struct pci_dev *pdev,
                              enum pci_channel_state state);
 static pci_ers_result_t ixgb_io_slot_reset (struct pci_dev *pdev);
@@ -348,9 +343,6 @@ static const struct net_device_ops ixgb_netdev_ops = {
 	.ndo_tx_timeout		= ixgb_tx_timeout,
 	.ndo_vlan_rx_add_vid	= ixgb_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= ixgb_vlan_rx_kill_vid,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= ixgb_netpoll,
-#endif
 	.ndo_fix_features       = ixgb_fix_features,
 	.ndo_set_features       = ixgb_set_features,
 };
@@ -2195,23 +2187,6 @@ ixgb_restore_vlan(struct ixgb_adapter *adapter)
 		ixgb_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), vid);
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/*
- * Polling 'interrupt' - used by things like netconsole to send skbs
- * without having to re-enable interrupts. It's not called while
- * the interrupt routine is executing.
- */
-
-static void ixgb_netpoll(struct net_device *dev)
-{
-	struct ixgb_adapter *adapter = netdev_priv(dev);
-
-	disable_irq(adapter->pdev->irq);
-	ixgb_intr(adapter->pdev->irq, dev);
-	enable_irq(adapter->pdev->irq);
-}
-#endif
-
 /**
  * ixgb_io_error_detected - called when PCI error is detected
  * @pdev:    pointer to pci device with error
-- 
cgit v1.2.3


From 0542997edece2d75e0bf3e173dfddf1b2b3ef756 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:44 -0700
Subject: igb: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

igb uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 30 ------------------------------
 1 file changed, 30 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index a32c576c1e65..0796cef96fa3 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -205,10 +205,6 @@ static struct notifier_block dca_notifier = {
 	.priority	= 0
 };
 #endif
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/* for netdump / net console */
-static void igb_netpoll(struct net_device *);
-#endif
 #ifdef CONFIG_PCI_IOV
 static unsigned int max_vfs;
 module_param(max_vfs, uint, 0);
@@ -2881,9 +2877,6 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_set_vf_spoofchk	= igb_ndo_set_vf_spoofchk,
 	.ndo_set_vf_trust	= igb_ndo_set_vf_trust,
 	.ndo_get_vf_config	= igb_ndo_get_vf_config,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= igb_netpoll,
-#endif
 	.ndo_fix_features	= igb_fix_features,
 	.ndo_set_features	= igb_set_features,
 	.ndo_fdb_add		= igb_ndo_fdb_add,
@@ -9053,29 +9046,6 @@ static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs)
 	return 0;
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/* Polling 'interrupt' - used by things like netconsole to send skbs
- * without having to re-enable interrupts. It's not called while
- * the interrupt routine is executing.
- */
-static void igb_netpoll(struct net_device *netdev)
-{
-	struct igb_adapter *adapter = netdev_priv(netdev);
-	struct e1000_hw *hw = &adapter->hw;
-	struct igb_q_vector *q_vector;
-	int i;
-
-	for (i = 0; i < adapter->num_q_vectors; i++) {
-		q_vector = adapter->q_vector[i];
-		if (adapter->flags & IGB_FLAG_HAS_MSIX)
-			wr32(E1000_EIMC, q_vector->eims_value);
-		else
-			igb_irq_disable(adapter);
-		napi_schedule(&q_vector->napi);
-	}
-}
-#endif /* CONFIG_NET_POLL_CONTROLLER */
-
 /**
  *  igb_io_error_detected - called when PCI error is detected
  *  @pdev: Pointer to PCI device
-- 
cgit v1.2.3


From 158a08a694c4ecf9574fe452db24a6b4943853aa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:45 -0700
Subject: ice: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

ice uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 27 ---------------------------
 1 file changed, 27 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index f1e80eed2fd6..3f047bb43348 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4806,30 +4806,6 @@ void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
 	stats->rx_length_errors = vsi_stats->rx_length_errors;
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/**
- * ice_netpoll - polling "interrupt" handler
- * @netdev: network interface device structure
- *
- * Used by netconsole to send skbs without having to re-enable interrupts.
- * This is not called in the normal interrupt path.
- */
-static void ice_netpoll(struct net_device *netdev)
-{
-	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi *vsi = np->vsi;
-	struct ice_pf *pf = vsi->back;
-	int i;
-
-	if (test_bit(__ICE_DOWN, vsi->state) ||
-	    !test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-		return;
-
-	for (i = 0; i < vsi->num_q_vectors; i++)
-		ice_msix_clean_rings(0, vsi->q_vectors[i]);
-}
-#endif /* CONFIG_NET_POLL_CONTROLLER */
-
 /**
  * ice_napi_disable_all - Disable NAPI for all q_vectors in the VSI
  * @vsi: VSI having NAPI disabled
@@ -5497,9 +5473,6 @@ static const struct net_device_ops ice_netdev_ops = {
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_change_mtu = ice_change_mtu,
 	.ndo_get_stats64 = ice_get_stats64,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller = ice_netpoll,
-#endif /* CONFIG_NET_POLL_CONTROLLER */
 	.ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid,
 	.ndo_set_features = ice_set_features,
-- 
cgit v1.2.3


From 1aa28fb98368078bcaf527bf46c0e001db934414 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:46 -0700
Subject: i40evf: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

i40evf uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 26 -------------------------
 1 file changed, 26 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 5906c1c1d19d..fef6d892ed4c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -396,29 +396,6 @@ static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter)
 	adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS;
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/**
- * i40evf_netpoll - A Polling 'interrupt' handler
- * @netdev: network interface device structure
- *
- * This is used by netconsole to send skbs without having to re-enable
- * interrupts.  It's not called while the normal interrupt routine is executing.
- **/
-static void i40evf_netpoll(struct net_device *netdev)
-{
-	struct i40evf_adapter *adapter = netdev_priv(netdev);
-	int q_vectors = adapter->num_msix_vectors - NONQ_VECS;
-	int i;
-
-	/* if interface is down do nothing */
-	if (test_bit(__I40E_VSI_DOWN, adapter->vsi.state))
-		return;
-
-	for (i = 0; i < q_vectors; i++)
-		i40evf_msix_clean_rings(0, &adapter->q_vectors[i]);
-}
-
-#endif
 /**
  * i40evf_irq_affinity_notify - Callback for affinity changes
  * @notify: context as to what irq was changed
@@ -3229,9 +3206,6 @@ static const struct net_device_ops i40evf_netdev_ops = {
 	.ndo_features_check	= i40evf_features_check,
 	.ndo_fix_features	= i40evf_fix_features,
 	.ndo_set_features	= i40evf_set_features,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= i40evf_netpoll,
-#endif
 	.ndo_setup_tc		= i40evf_setup_tc,
 };
 
-- 
cgit v1.2.3


From a24b66c249f71dde11da5ba3b4c397a42ece3fc9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:47 -0700
Subject: mlx4: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

mlx4 uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 20 --------------------
 1 file changed, 20 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 6785661d1a72..fe49384eba48 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1286,20 +1286,6 @@ out:
 	mutex_unlock(&mdev->state_lock);
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void mlx4_en_netpoll(struct net_device *dev)
-{
-	struct mlx4_en_priv *priv = netdev_priv(dev);
-	struct mlx4_en_cq *cq;
-	int i;
-
-	for (i = 0; i < priv->tx_ring_num[TX]; i++) {
-		cq = priv->tx_cq[TX][i];
-		napi_schedule(&cq->napi);
-	}
-}
-#endif
-
 static int mlx4_en_set_rss_steer_rules(struct mlx4_en_priv *priv)
 {
 	u64 reg_id;
@@ -2946,9 +2932,6 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_tx_timeout		= mlx4_en_tx_timeout,
 	.ndo_vlan_rx_add_vid	= mlx4_en_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= mlx4_en_vlan_rx_kill_vid,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= mlx4_en_netpoll,
-#endif
 	.ndo_set_features	= mlx4_en_set_features,
 	.ndo_fix_features	= mlx4_en_fix_features,
 	.ndo_setup_tc		= __mlx4_en_setup_tc,
@@ -2983,9 +2966,6 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 	.ndo_set_vf_link_state	= mlx4_en_set_vf_link_state,
 	.ndo_get_vf_stats       = mlx4_en_get_vf_stats,
 	.ndo_get_vf_config	= mlx4_en_get_vf_config,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= mlx4_en_netpoll,
-#endif
 	.ndo_set_features	= mlx4_en_set_features,
 	.ndo_fix_features	= mlx4_en_fix_features,
 	.ndo_setup_tc		= __mlx4_en_setup_tc,
-- 
cgit v1.2.3


From 9c29bcd189f4ab1644b7125713602532d0aefdb7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:48 -0700
Subject: mlx5: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

mlx5 uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 19 -------------------
 1 file changed, 19 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5a7939e70190..54118b77dc1f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4315,22 +4315,6 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-/* Fake "interrupt" called by netpoll (eg netconsole) to send skbs without
- * reenabling interrupts.
- */
-static void mlx5e_netpoll(struct net_device *dev)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_channels *chs = &priv->channels;
-
-	int i;
-
-	for (i = 0; i < chs->num; i++)
-		napi_schedule(&chs->c[i]->napi);
-}
-#endif
-
 static const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_open                = mlx5e_open,
 	.ndo_stop                = mlx5e_close,
@@ -4356,9 +4340,6 @@ static const struct net_device_ops mlx5e_netdev_ops = {
 #ifdef CONFIG_MLX5_EN_ARFS
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller     = mlx5e_netpoll,
-#endif
 #ifdef CONFIG_MLX5_ESWITCH
 	/* SRIOV E-Switch NDOs */
 	.ndo_set_vf_mac          = mlx5e_set_vf_mac,
-- 
cgit v1.2.3


From d8ea6a91ad70ae0881d76446df27d3f58fd478c3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:49 -0700
Subject: bnx2x: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

bnx2x uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 16 ----------------
 1 file changed, 16 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 71362b7f6040..fcc2328bb0d9 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12894,19 +12894,6 @@ static int bnx2x_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	}
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void poll_bnx2x(struct net_device *dev)
-{
-	struct bnx2x *bp = netdev_priv(dev);
-	int i;
-
-	for_each_eth_queue(bp, i) {
-		struct bnx2x_fastpath *fp = &bp->fp[i];
-		napi_schedule(&bnx2x_fp(bp, fp->index, napi));
-	}
-}
-#endif
-
 static int bnx2x_validate_addr(struct net_device *dev)
 {
 	struct bnx2x *bp = netdev_priv(dev);
@@ -13113,9 +13100,6 @@ static const struct net_device_ops bnx2x_netdev_ops = {
 	.ndo_tx_timeout		= bnx2x_tx_timeout,
 	.ndo_vlan_rx_add_vid	= bnx2x_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= bnx2x_vlan_rx_kill_vid,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= poll_bnx2x,
-#endif
 	.ndo_setup_tc		= __bnx2x_setup_tc,
 #ifdef CONFIG_BNX2X_SRIOV
 	.ndo_set_vf_mac		= bnx2x_set_vf_mac,
-- 
cgit v1.2.3


From 58e0e22bff638055278ea73e34d0d07a95260790 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:50 -0700
Subject: bnxt: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

bnxt uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 18 ------------------
 1 file changed, 18 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 177587f9c3f1..61957b0bbd8c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7672,21 +7672,6 @@ static void bnxt_tx_timeout(struct net_device *dev)
 	bnxt_queue_sp_work(bp);
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void bnxt_poll_controller(struct net_device *dev)
-{
-	struct bnxt *bp = netdev_priv(dev);
-	int i;
-
-	/* Only process tx rings/combined rings in netpoll mode. */
-	for (i = 0; i < bp->tx_nr_rings; i++) {
-		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
-
-		napi_schedule(&txr->bnapi->napi);
-	}
-}
-#endif
-
 static void bnxt_timer(struct timer_list *t)
 {
 	struct bnxt *bp = from_timer(bp, t, timer);
@@ -8519,9 +8504,6 @@ static const struct net_device_ops bnxt_netdev_ops = {
 	.ndo_set_vf_link_state	= bnxt_set_vf_link_state,
 	.ndo_set_vf_spoofchk	= bnxt_set_vf_spoofchk,
 	.ndo_set_vf_trust	= bnxt_set_vf_trust,
-#endif
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= bnxt_poll_controller,
 #endif
 	.ndo_setup_tc           = bnxt_setup_tc,
 #ifdef CONFIG_RFS_ACCEL
-- 
cgit v1.2.3


From 0825ce70318e9c576acbdd5ceb4a8d563263cf8f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:51 -0700
Subject: nfp: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

nfp uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Tested-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 18 ------------------
 1 file changed, 18 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 253bdaef1505..8ed38fd5a852 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3146,21 +3146,6 @@ nfp_net_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	return nfp_net_reconfig_mbox(nn, NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL);
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void nfp_net_netpoll(struct net_device *netdev)
-{
-	struct nfp_net *nn = netdev_priv(netdev);
-	int i;
-
-	/* nfp_net's NAPIs are statically allocated so even if there is a race
-	 * with reconfig path this will simply try to schedule some disabled
-	 * NAPI instances.
-	 */
-	for (i = 0; i < nn->dp.num_stack_tx_rings; i++)
-		napi_schedule_irqoff(&nn->r_vecs[i].napi);
-}
-#endif
-
 static void nfp_net_stat64(struct net_device *netdev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3519,9 +3504,6 @@ const struct net_device_ops nfp_net_netdev_ops = {
 	.ndo_get_stats64	= nfp_net_stat64,
 	.ndo_vlan_rx_add_vid	= nfp_net_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= nfp_net_vlan_rx_kill_vid,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= nfp_net_netpoll,
-#endif
 	.ndo_set_vf_mac         = nfp_app_set_vf_mac,
 	.ndo_set_vf_vlan        = nfp_app_set_vf_vlan,
 	.ndo_set_vf_spoofchk    = nfp_app_set_vf_spoofchk,
-- 
cgit v1.2.3


From 765cdc209cb89fb81215310a066cd0a3018ffef7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Sep 2018 15:27:52 -0700
Subject: tun: remove ndo_poll_controller

As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

tun uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 43 -------------------------------------------
 1 file changed, 43 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ebd07ad82431..e2648b5a3861 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1153,43 +1153,6 @@ static netdev_features_t tun_net_fix_features(struct net_device *dev,
 
 	return (features & tun->set_features) | (features & ~TUN_USER_FEATURES);
 }
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void tun_poll_controller(struct net_device *dev)
-{
-	/*
-	 * Tun only receives frames when:
-	 * 1) the char device endpoint gets data from user space
-	 * 2) the tun socket gets a sendmsg call from user space
-	 * If NAPI is not enabled, since both of those are synchronous
-	 * operations, we are guaranteed never to have pending data when we poll
-	 * for it so there is nothing to do here but return.
-	 * We need this though so netpoll recognizes us as an interface that
-	 * supports polling, which enables bridge devices in virt setups to
-	 * still use netconsole
-	 * If NAPI is enabled, however, we need to schedule polling for all
-	 * queues unless we are using napi_gro_frags(), which we call in
-	 * process context and not in NAPI context.
-	 */
-	struct tun_struct *tun = netdev_priv(dev);
-
-	if (tun->flags & IFF_NAPI) {
-		struct tun_file *tfile;
-		int i;
-
-		if (tun_napi_frags_enabled(tun))
-			return;
-
-		rcu_read_lock();
-		for (i = 0; i < tun->numqueues; i++) {
-			tfile = rcu_dereference(tun->tfiles[i]);
-			if (tfile->napi_enabled)
-				napi_schedule(&tfile->napi);
-		}
-		rcu_read_unlock();
-	}
-	return;
-}
-#endif
 
 static void tun_set_headroom(struct net_device *dev, int new_hr)
 {
@@ -1283,9 +1246,6 @@ static const struct net_device_ops tun_netdev_ops = {
 	.ndo_start_xmit		= tun_net_xmit,
 	.ndo_fix_features	= tun_net_fix_features,
 	.ndo_select_queue	= tun_select_queue,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= tun_poll_controller,
-#endif
 	.ndo_set_rx_headroom	= tun_set_headroom,
 	.ndo_get_stats64	= tun_net_get_stats64,
 };
@@ -1365,9 +1325,6 @@ static const struct net_device_ops tap_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_select_queue	= tun_select_queue,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= tun_poll_controller,
-#endif
 	.ndo_features_check	= passthru_features_check,
 	.ndo_set_rx_headroom	= tun_set_headroom,
 	.ndo_get_stats64	= tun_net_get_stats64,
-- 
cgit v1.2.3


From d26ed6b0e5e23190d43ab34bc69cbecdc464a2cf Mon Sep 17 00:00:00 2001
From: Friedemann Gerold <f.gerold@b-c-s.de>
Date: Sat, 15 Sep 2018 18:03:39 +0300
Subject: net: aquantia: memory corruption on jumbo frames

This patch fixes skb_shared area, which will be corrupted
upon reception of 4K jumbo packets.

Originally build_skb usage purpose was to reuse page for skb to eliminate
needs of extra fragments. But that logic does not take into account that
skb_shared_info should be reserved at the end of skb data area.

In case packet data consumes all the page (4K), skb_shinfo location
overflows the page. As a consequence, __build_skb zeroed shinfo data above
the allocated page, corrupting next page.

The issue is rarely seen in real life because jumbo are normally larger
than 4K and that causes another code path to trigger.
But it 100% reproducible with simple scapy packet, like:

    sendp(IP(dst="192.168.100.3") / TCP(dport=443) \
          / Raw(RandString(size=(4096-40))), iface="enp1s0")

Fixes: 018423e90bee ("net: ethernet: aquantia: Add ring support code")

Reported-by: Friedemann Gerold <f.gerold@b-c-s.de>
Reported-by: Michael Rauch <michael@rauch.be>
Signed-off-by: Friedemann Gerold <f.gerold@b-c-s.de>
Tested-by: Nikita Danilov <nikita.danilov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 32 +++++++++++++-----------
 1 file changed, 18 insertions(+), 14 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index b5f1f62e8e25..d1e1a0ba8615 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -225,9 +225,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 		}
 
 		/* for single fragment packets use build_skb() */
-		if (buff->is_eop) {
+		if (buff->is_eop &&
+		    buff->len <= AQ_CFG_RX_FRAME_MAX - AQ_SKB_ALIGN) {
 			skb = build_skb(page_address(buff->page),
-					buff->len + AQ_SKB_ALIGN);
+					AQ_CFG_RX_FRAME_MAX);
 			if (unlikely(!skb)) {
 				err = -ENOMEM;
 				goto err_exit;
@@ -247,18 +248,21 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 					buff->len - ETH_HLEN,
 					SKB_TRUESIZE(buff->len - ETH_HLEN));
 
-			for (i = 1U, next_ = buff->next,
-			     buff_ = &self->buff_ring[next_]; true;
-			     next_ = buff_->next,
-			     buff_ = &self->buff_ring[next_], ++i) {
-				skb_add_rx_frag(skb, i, buff_->page, 0,
-						buff_->len,
-						SKB_TRUESIZE(buff->len -
-						ETH_HLEN));
-				buff_->is_cleaned = 1;
-
-				if (buff_->is_eop)
-					break;
+			if (!buff->is_eop) {
+				for (i = 1U, next_ = buff->next,
+				     buff_ = &self->buff_ring[next_];
+				     true; next_ = buff_->next,
+				     buff_ = &self->buff_ring[next_], ++i) {
+					skb_add_rx_frag(skb, i,
+							buff_->page, 0,
+							buff_->len,
+							SKB_TRUESIZE(buff->len -
+							ETH_HLEN));
+					buff_->is_cleaned = 1;
+
+					if (buff_->is_eop)
+						break;
+				}
 			}
 		}
 
-- 
cgit v1.2.3


From f4a518797b40e956b6e6220b42657e045dc24470 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Mon, 24 Sep 2018 16:56:13 +0200
Subject: net: mvneta: fix the remaining Rx descriptor unmapping issues

With CONFIG_DMA_API_DEBUG enabled we get DMA unmapping warning in
various places of the mvneta driver, for example when putting down an
interface while traffic is passing through.

The issue is when using s/w buffer management, the Rx buffers are mapped
using dma_map_page but unmapped with dma_unmap_single. This patch fixes
this by using the right unmapping function.

Fixes: 562e2f467e71 ("net: mvneta: Improve the buffer allocation method for SWBM")
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Reviewed-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'drivers/net')

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 2db9708f2e24..b4ed7d394d07 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1890,8 +1890,8 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 		if (!data || !(rx_desc->buf_phys_addr))
 			continue;
 
-		dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
-				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
+		dma_unmap_page(pp->dev->dev.parent, rx_desc->buf_phys_addr,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
 		__free_page(data);
 	}
 }
@@ -2039,9 +2039,8 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 						frag_offset, frag_size,
 						PAGE_SIZE);
 
-				dma_unmap_single(dev->dev.parent, phys_addr,
-						 PAGE_SIZE,
-						 DMA_FROM_DEVICE);
+				dma_unmap_page(dev->dev.parent, phys_addr,
+					       PAGE_SIZE, DMA_FROM_DEVICE);
 
 				rxq->left_size -= frag_size;
 			}
-- 
cgit v1.2.3