From cefc23554fc259114e78a7b0908aac4610ee18eb Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Mon, 31 Aug 2020 20:50:42 +0300
Subject: [PATCH 01/15] net/mlx5: Fix FTE cleanup

Currently, when an FTE is allocated, its refcount is decreased to 0
with the purpose it will not be a stand alone steering object and every
rule (destination) of the FTE would increase the refcount.
When mlx5_cleanup_fs is called while not all rules were deleted by the
steering users, it hit refcount underflow on the FTE once clean_tree
calls to tree_remove_node after the deleted rules already decreased
the refcount to 0.

FTE is no longer destroyed implicitly when the last rule (destination)
is deleted. mlx5_del_flow_rules avoids it by increasing the refcount on
the FTE and destroy it explicitly after all rules were deleted. So we
can avoid the refcount underflow by making FTE as stand alone object.
In addition need to set del_hw_func to FTE so the HW object will be
destroyed when the FTE is deleted from the cleanup_tree flow.

refcount_t: underflow; use-after-free.
WARNING: CPU: 2 PID: 15715 at lib/refcount.c:28 refcount_warn_saturate+0xd9/0xe0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
Call Trace:
 tree_put_node+0xf2/0x140 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x5f/0xf0 [mlx5_core]
 clean_tree+0x4e/0xf0 [mlx5_core]
 clean_tree+0x5f/0xf0 [mlx5_core]
 mlx5_cleanup_fs+0x26/0x270 [mlx5_core]
 mlx5_unload+0x2e/0xa0 [mlx5_core]
 mlx5_unload_one+0x51/0x120 [mlx5_core]
 mlx5_devlink_reload_down+0x51/0x90 [mlx5_core]
 devlink_reload+0x39/0x120
 ? devlink_nl_cmd_reload+0x43/0x220
 genl_rcv_msg+0x1e4/0x420
 ? genl_family_rcv_msg_attrs_parse+0x100/0x100
 netlink_rcv_skb+0x47/0x110
 genl_rcv+0x24/0x40
 netlink_unicast+0x217/0x2f0
 netlink_sendmsg+0x30f/0x430
 sock_sendmsg+0x30/0x40
 __sys_sendto+0x10e/0x140
 ? handle_mm_fault+0xc4/0x1f0
 ? do_page_fault+0x33f/0x630
 __x64_sys_sendto+0x24/0x30
 do_syscall_64+0x48/0x130
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 718ce4d601db ("net/mlx5: Consolidate update FTE for all removal changes")
Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 9ccec5f8b92a..75fa44eee434 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -654,7 +654,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
 	fte->action = *flow_act;
 	fte->flow_context = spec->flow_context;
 
-	tree_init_node(&fte->node, NULL, del_sw_fte);
+	tree_init_node(&fte->node, del_hw_fte, del_sw_fte);
 
 	return fte;
 }
@@ -1792,7 +1792,6 @@ skip_search:
 		up_write_ref_node(&g->node, false);
 		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 		up_write_ref_node(&fte->node, false);
-		tree_put_node(&fte->node, false);
 		return rule;
 	}
 	rule = ERR_PTR(-ENOENT);
@@ -1891,7 +1890,6 @@ search_again_locked:
 	up_write_ref_node(&g->node, false);
 	rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 	up_write_ref_node(&fte->node, false);
-	tree_put_node(&fte->node, false);
 	tree_put_node(&g->node, false);
 	return rule;
 
@@ -2001,7 +1999,9 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
 		up_write_ref_node(&fte->node, false);
 	} else {
 		del_hw_fte(&fte->node);
-		up_write(&fte->node.lock);
+		/* Avoid double call to del_hw_fte */
+		fte->node.del_hw_func = NULL;
+		up_write_ref_node(&fte->node, false);
 		tree_put_node(&fte->node, false);
 	}
 	kfree(handle);

From fe45386a208277cae4648106133c08246eecd012 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Thu, 11 Jun 2020 13:55:19 +0300
Subject: [PATCH 02/15] net/mlx5e: Use RCU to protect rq->xdp_prog

Currently, the RQs are temporarily deactivated while hot-replacing the
XDP program, and napi_synchronize is used to make sure rq->xdp_prog is
not in use. However, napi_synchronize is not ideal: instead of waiting
till the end of a NAPI cycle, it polls and waits until NAPI is not
running, sleeping for 1ms between the periodic checks. Under heavy
workloads, this loop will never end, which may even lead to a kernel
panic if the kernel detects the hangup. Such workloads include XSK TX
and possibly also heavy RX (XSK or normal).

The fix is inspired by commit 326fe02d1ed6 ("net/mlx4_en: protect
ring->xdp_prog with rcu_read_lock"). As mlx5e_xdp_handle is already
protected by rcu_read_lock, and bpf_prog_put uses call_rcu to free the
program, there is no need for additional synchronization if proper RCU
functions are used to access the pointer. This patch converts all
accesses to rq->xdp_prog to use RCU functions.

Fixes: 86994156c736 ("net/mlx5e: XDP fast RX drop bpf programs support")
Fixes: db05815b36cb ("net/mlx5e: Add XSK zero-copy support")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c  |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 53 +++++++++----------
 3 files changed, 27 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0cc2080fd847..5d7b79518449 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -600,7 +600,7 @@ struct mlx5e_rq {
 	struct dim         dim; /* Dynamic Interrupt Moderation */
 
 	/* XDP */
-	struct bpf_prog       *xdp_prog;
+	struct bpf_prog __rcu *xdp_prog;
 	struct mlx5e_xdpsq    *xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 0e6946fc121f..b28df21981a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -122,7 +122,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      u32 *len, struct xdp_buff *xdp)
 {
-	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
+	struct bpf_prog *prog = rcu_dereference(rq->xdp_prog);
 	u32 act;
 	int err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index aebcf73f8546..bde97b108db5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -399,7 +399,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	if (params->xdp_prog)
 		bpf_prog_inc(params->xdp_prog);
-	rq->xdp_prog = params->xdp_prog;
+	RCU_INIT_POINTER(rq->xdp_prog, params->xdp_prog);
 
 	rq_xdp_ix = rq->ix;
 	if (xsk)
@@ -408,7 +408,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	if (err < 0)
 		goto err_rq_wq_destroy;
 
-	rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+	rq->buff.map_dir = params->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
 	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk);
 	pool_size = 1 << params->log_rq_mtu_frames;
 
@@ -564,8 +564,8 @@ err_free:
 	}
 
 err_rq_wq_destroy:
-	if (rq->xdp_prog)
-		bpf_prog_put(rq->xdp_prog);
+	if (params->xdp_prog)
+		bpf_prog_put(params->xdp_prog);
 	xdp_rxq_info_unreg(&rq->xdp_rxq);
 	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
@@ -575,10 +575,16 @@ err_rq_wq_destroy:
 
 static void mlx5e_free_rq(struct mlx5e_rq *rq)
 {
+	struct mlx5e_channel *c = rq->channel;
+	struct bpf_prog *old_prog = NULL;
 	int i;
 
-	if (rq->xdp_prog)
-		bpf_prog_put(rq->xdp_prog);
+	/* drop_rq has neither channel nor xdp_prog. */
+	if (c)
+		old_prog = rcu_dereference_protected(rq->xdp_prog,
+						     lockdep_is_held(&c->priv->state_lock));
+	if (old_prog)
+		bpf_prog_put(old_prog);
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
@@ -4330,6 +4336,16 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 	return 0;
 }
 
+static void mlx5e_rq_replace_xdp_prog(struct mlx5e_rq *rq, struct bpf_prog *prog)
+{
+	struct bpf_prog *old_prog;
+
+	old_prog = rcu_replace_pointer(rq->xdp_prog, prog,
+				       lockdep_is_held(&rq->channel->priv->state_lock));
+	if (old_prog)
+		bpf_prog_put(old_prog);
+}
+
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -4388,29 +4404,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	 */
 	for (i = 0; i < priv->channels.num; i++) {
 		struct mlx5e_channel *c = priv->channels.c[i];
-		bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
 
-		clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
-		if (xsk_open)
-			clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
-		napi_synchronize(&c->napi);
-		/* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */
-
-		old_prog = xchg(&c->rq.xdp_prog, prog);
-		if (old_prog)
-			bpf_prog_put(old_prog);
-
-		if (xsk_open) {
-			old_prog = xchg(&c->xskrq.xdp_prog, prog);
-			if (old_prog)
-				bpf_prog_put(old_prog);
-		}
-
-		set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
-		if (xsk_open)
-			set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
-		/* napi_schedule in case we have missed anything */
-		napi_schedule(&c->napi);
+		mlx5e_rq_replace_xdp_prog(&c->rq, prog);
+		if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+			mlx5e_rq_replace_xdp_prog(&c->xskrq, prog);
 	}
 
 unlock:

From 9c25a22dfb00270372224721fed646965420323a Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Thu, 11 Jun 2020 14:25:19 +0300
Subject: [PATCH 03/15] net/mlx5e: Use synchronize_rcu to sync with NAPI

As described in the previous commit, napi_synchronize doesn't quite fit
the purpose when we just need to wait until the currently running NAPI
quits. Its implementation waits until NAPI is not running by polling and
waiting for 1ms in between. In cases where we need to deactivate one
queue (e.g., recovery flows) or where we deactivate them one-by-one
(deactivate channel flow), we may get stuck in napi_synchronize forever
if other queues keep NAPI active, causing a soft lockup. Depending on
kernel configuration (CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC), it may result
in a kernel panic.

To fix the issue, use synchronize_rcu to wait for NAPI to quit, and wrap
the whole NAPI in rcu_read_lock.

Fixes: acc6c5953af1 ("net/mlx5e: Split open/close channels to stages")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/xsk/rx.c | 14 ++------------
 .../ethernet/mellanox/mlx5/core/en/xsk/setup.c  |  3 +--
 .../net/ethernet/mellanox/mlx5/core/en_main.c   | 12 ++++--------
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 12 ++----------
 .../net/ethernet/mellanox/mlx5/core/en_txrx.c   | 17 +++++++++++++----
 5 files changed, 22 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index a33a1f762c70..40db27bf790b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -31,7 +31,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 {
 	struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk;
 	u32 cqe_bcnt32 = cqe_bcnt;
-	bool consumed;
 
 	/* Check packet size. Note LRO doesn't use linear SKB */
 	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
@@ -51,10 +50,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	xsk_buff_dma_sync_for_cpu(xdp);
 	prefetch(xdp->data);
 
-	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp);
-	rcu_read_unlock();
-
 	/* Possible flows:
 	 * - XDP_REDIRECT to XSKMAP:
 	 *   The page is owned by the userspace from now.
@@ -70,7 +65,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
 	 * allocated first from the Reuse Ring, so it has enough space.
 	 */
 
-	if (likely(consumed)) {
+	if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp))) {
 		if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)))
 			__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
 		return NULL; /* page/packet was consumed by XDP */
@@ -88,7 +83,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 					      u32 cqe_bcnt)
 {
 	struct xdp_buff *xdp = wi->di->xsk;
-	bool consumed;
 
 	/* wi->offset is not used in this function, because xdp->data and the
 	 * DMA address point directly to the necessary place. Furthermore, the
@@ -107,11 +101,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
 		return NULL;
 	}
 
-	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp);
-	rcu_read_unlock();
-
-	if (likely(consumed))
+	if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp)))
 		return NULL; /* page/packet was consumed by XDP */
 
 	/* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index dd9df519d383..55e65a438de7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -106,8 +106,7 @@ err_free_cparam:
 void mlx5e_close_xsk(struct mlx5e_channel *c)
 {
 	clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
-	napi_synchronize(&c->napi);
-	synchronize_rcu(); /* Sync with the XSK wakeup. */
+	synchronize_rcu(); /* Sync with the XSK wakeup and with NAPI. */
 
 	mlx5e_close_rq(&c->xskrq);
 	mlx5e_close_cq(&c->xskrq.cq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index bde97b108db5..917c28e7f29e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -873,7 +873,7 @@ void mlx5e_activate_rq(struct mlx5e_rq *rq)
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 {
 	clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
+	synchronize_rcu(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */
 }
 
 void mlx5e_close_rq(struct mlx5e_rq *rq)
@@ -1318,12 +1318,10 @@ void mlx5e_tx_disable_queue(struct netdev_queue *txq)
 
 static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 {
-	struct mlx5e_channel *c = sq->channel;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	/* prevent netif_tx_wake_queue */
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI to prevent netif_tx_wake_queue. */
 
 	mlx5e_tx_disable_queue(sq->txq);
 
@@ -1398,10 +1396,8 @@ void mlx5e_activate_icosq(struct mlx5e_icosq *icosq)
 
 void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
 {
-	struct mlx5e_channel *c = icosq->channel;
-
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state);
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI. */
 }
 
 void mlx5e_close_icosq(struct mlx5e_icosq *sq)
@@ -1480,7 +1476,7 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
 	struct mlx5e_channel *c = sq->channel;
 
 	clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-	napi_synchronize(&c->napi);
+	synchronize_rcu(); /* Sync with NAPI. */
 
 	mlx5e_destroy_sq(c->mdev, sq->sqn);
 	mlx5e_free_xdpsq_descs(sq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 65828af120b7..99d102c035b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1132,7 +1132,6 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	struct xdp_buff xdp;
 	struct sk_buff *skb;
 	void *va, *data;
-	bool consumed;
 	u32 frag_size;
 
 	va             = page_address(di->page) + wi->offset;
@@ -1144,11 +1143,8 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
 
-	rcu_read_lock();
 	mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp);
-	consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp);
-	rcu_read_unlock();
-	if (consumed)
+	if (mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp))
 		return NULL; /* page/packet was consumed by XDP */
 
 	rx_headroom = xdp.data - xdp.data_hard_start;
@@ -1438,7 +1434,6 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	struct sk_buff *skb;
 	void *va, *data;
 	u32 frag_size;
-	bool consumed;
 
 	/* Check packet size. Note LRO doesn't use linear SKB */
 	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
@@ -1455,11 +1450,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
 
-	rcu_read_lock();
 	mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp);
-	consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp);
-	rcu_read_unlock();
-	if (consumed) {
+	if (mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp)) {
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
 			__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
 		return NULL; /* page/packet was consumed by XDP */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index de10b06bade5..d5868670f8a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -121,13 +121,17 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	struct mlx5e_xdpsq *xsksq = &c->xsksq;
 	struct mlx5e_rq *xskrq = &c->xskrq;
 	struct mlx5e_rq *rq = &c->rq;
-	bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
 	bool aff_change = false;
 	bool busy_xsk = false;
 	bool busy = false;
 	int work_done = 0;
+	bool xsk_open;
 	int i;
 
+	rcu_read_lock();
+
+	xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
+
 	ch_stats->poll++;
 
 	for (i = 0; i < c->num_tc; i++)
@@ -167,8 +171,10 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	busy |= busy_xsk;
 
 	if (busy) {
-		if (likely(mlx5e_channel_no_affinity_change(c)))
-			return budget;
+		if (likely(mlx5e_channel_no_affinity_change(c))) {
+			work_done = budget;
+			goto out;
+		}
 		ch_stats->aff_change++;
 		aff_change = true;
 		if (budget && work_done == budget)
@@ -176,7 +182,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	}
 
 	if (unlikely(!napi_complete_done(napi, work_done)))
-		return work_done;
+		goto out;
 
 	ch_stats->arm++;
 
@@ -203,6 +209,9 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 		ch_stats->force_irq++;
 	}
 
+out:
+	rcu_read_unlock();
+
 	return work_done;
 }
 

From 12a240a41427d37b5e70570700704e84c827452f Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Tue, 7 Jul 2020 06:16:24 +0000
Subject: [PATCH 04/15] net/mlx5e: Fix memory leak of tunnel info when rule
 under multipath not ready

When deleting vxlan flow rule under multipath, tun_info in parse_attr is
not freed when the rule is not ready.

Fixes: ef06c9ee8933 ("net/mlx5e: Allow one failure when offloading tc encap rules under multipath")
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index fd53d101d8fd..7be282d2ddde 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1290,11 +1290,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 
 	mlx5e_put_flow_tunnel_id(flow);
 
-	if (flow_flag_test(flow, NOT_READY)) {
+	if (flow_flag_test(flow, NOT_READY))
 		remove_unready_flow(flow);
-		kvfree(attr->parse_attr);
-		return;
-	}
 
 	if (mlx5e_is_offloaded_flow(flow)) {
 		if (flow_flag_test(flow, SLOW))

From 4c8594adb9d9250120cffc57a7175a1a09f2b084 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Sun, 26 Jul 2020 16:37:47 +0300
Subject: [PATCH 05/15] net/mlx5e: CT: Fix freeing ct_label mapping

Add missing mapping remove call when removing ct rule,
as the mapping was allocated when ct rule was adding with ct_label.
Also there is a missing mapping remove call in error flow.

Fixes: 54b154ecfb8c ("net/mlx5e: CT: Map 128 bits labels to 32 bit map ID")
Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en/tc_ct.c    | 21 +++++++++++----
 .../ethernet/mellanox/mlx5/core/en/tc_ct.h    | 26 ++++++++++++-------
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   |  6 +++--
 3 files changed, 36 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index c6bc9224c3b1..bc5f72ec3623 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -699,6 +699,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 err_rule:
 	mlx5e_mod_hdr_detach(ct_priv->esw->dev,
 			     &esw->offloads.mod_hdr, zone_rule->mh);
+	mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id);
 err_mod_hdr:
 	kfree(spec);
 	return err;
@@ -958,12 +959,22 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv,
 	return 0;
 }
 
+void mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr)
+{
+	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
+
+	if (!ct_priv || !ct_attr->ct_labels_id)
+		return;
+
+	mapping_remove(ct_priv->labels_mapping, ct_attr->ct_labels_id);
+}
+
 int
-mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct flow_cls_offload *f,
-		       struct mlx5_ct_attr *ct_attr,
-		       struct netlink_ext_ack *extack)
+mlx5_tc_ct_match_add(struct mlx5e_priv *priv,
+		     struct mlx5_flow_spec *spec,
+		     struct flow_cls_offload *f,
+		     struct mlx5_ct_attr *ct_attr,
+		     struct netlink_ext_ack *extack)
 {
 	struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv);
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
index 3baef917a677..708c216325d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
@@ -87,12 +87,15 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv);
 void
 mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv);
 
+void
+mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr);
+
 int
-mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct flow_cls_offload *f,
-		       struct mlx5_ct_attr *ct_attr,
-		       struct netlink_ext_ack *extack);
+mlx5_tc_ct_match_add(struct mlx5e_priv *priv,
+		     struct mlx5_flow_spec *spec,
+		     struct flow_cls_offload *f,
+		     struct mlx5_ct_attr *ct_attr,
+		     struct netlink_ext_ack *extack);
 int
 mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv,
 			    struct mlx5_flow_spec *spec);
@@ -130,12 +133,15 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv)
 {
 }
 
+static inline void
+mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr) {}
+
 static inline int
-mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct flow_cls_offload *f,
-		       struct mlx5_ct_attr *ct_attr,
-		       struct netlink_ext_ack *extack)
+mlx5_tc_ct_match_add(struct mlx5e_priv *priv,
+		     struct mlx5_flow_spec *spec,
+		     struct flow_cls_offload *f,
+		     struct mlx5_ct_attr *ct_attr,
+		     struct netlink_ext_ack *extack)
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 7be282d2ddde..bf0c6f063941 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1312,6 +1312,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 		}
 	kvfree(attr->parse_attr);
 
+	mlx5_tc_ct_match_del(priv, &flow->esw_attr->ct_attr);
+
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		mlx5e_detach_mod_hdr(priv, flow);
 
@@ -4399,8 +4401,8 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 		goto err_free;
 
 	/* actions validation depends on parsing the ct matches first */
-	err = mlx5_tc_ct_parse_match(priv, &parse_attr->spec, f,
-				     &flow->esw_attr->ct_attr, extack);
+	err = mlx5_tc_ct_match_add(priv, &parse_attr->spec, f,
+				   &flow->esw_attr->ct_attr, extack);
 	if (err)
 		goto err_free;
 

From 6cec0229ab1959259e71e9a5bbe47c04577950b1 Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@mellanox.com>
Date: Wed, 5 Aug 2020 17:56:04 +0300
Subject: [PATCH 06/15] net/mlx5e: Enable adding peer miss rules only if merged
 eswitch is supported

The cited commit creates peer miss group during switchdev mode
initialization in order to handle miss packets correctly while in VF
LAG mode. This is done regardless of FW support of such groups which
could cause rules setups failure later on.

Fix by adding FW capability check before creating peer groups/rule.

Fixes: ac004b832128 ("net/mlx5e: E-Switch, Add peer miss rules")
Signed-off-by: Maor Dickman <maord@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 56 ++++++++++---------
 1 file changed, 30 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index d2516922d867..1bcf2609dca8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1219,36 +1219,38 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	}
 	esw->fdb_table.offloads.send_to_vport_grp = g;
 
-	/* create peer esw miss group */
-	memset(flow_group_in, 0, inlen);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
+		/* create peer esw miss group */
+		memset(flow_group_in, 0, inlen);
 
-	esw_set_flow_group_source_port(esw, flow_group_in);
+		esw_set_flow_group_source_port(esw, flow_group_in);
 
-	if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
-		match_criteria = MLX5_ADDR_OF(create_flow_group_in,
-					      flow_group_in,
-					      match_criteria);
+		if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+			match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+						      flow_group_in,
+						      match_criteria);
 
-		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
-				 misc_parameters.source_eswitch_owner_vhca_id);
+			MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+					 misc_parameters.source_eswitch_owner_vhca_id);
 
-		MLX5_SET(create_flow_group_in, flow_group_in,
-			 source_eswitch_owner_vhca_id_valid, 1);
+			MLX5_SET(create_flow_group_in, flow_group_in,
+				 source_eswitch_owner_vhca_id_valid, 1);
+		}
+
+		MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
+		MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+			 ix + esw->total_vports - 1);
+		ix += esw->total_vports;
+
+		g = mlx5_create_flow_group(fdb, flow_group_in);
+		if (IS_ERR(g)) {
+			err = PTR_ERR(g);
+			esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
+			goto peer_miss_err;
+		}
+		esw->fdb_table.offloads.peer_miss_grp = g;
 	}
 
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
-		 ix + esw->total_vports - 1);
-	ix += esw->total_vports;
-
-	g = mlx5_create_flow_group(fdb, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
-		goto peer_miss_err;
-	}
-	esw->fdb_table.offloads.peer_miss_grp = g;
-
 	/* create miss group */
 	memset(flow_group_in, 0, inlen);
 	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
@@ -1281,7 +1283,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 miss_rule_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 miss_err:
-	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 peer_miss_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
 send_vport_err:
@@ -1305,7 +1308,8 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi);
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
-	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 
 	mlx5_esw_chains_destroy(esw);

From 82198d8bcdeff01d19215d712aa55031e21bccbc Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@nvidia.com>
Date: Wed, 2 Sep 2020 16:49:52 +0300
Subject: [PATCH 07/15] net/mlx5e: Fix endianness when calculating pedit mask
 first bit

The field mask value is provided in network byte order and has to
be converted to host byte order before calculating pedit mask
first bit.

Fixes: 88f30bbcbaaa ("net/mlx5e: Bit sized fields rewrite support")
Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_tc.c   | 34 ++++++++++++-------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index bf0c6f063941..1c93f92d9210 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2624,6 +2624,22 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest,   0, udp_dport),
 };
 
+static unsigned long mask_to_le(unsigned long mask, int size)
+{
+	__be32 mask_be32;
+	__be16 mask_be16;
+
+	if (size == 32) {
+		mask_be32 = (__force __be32)(mask);
+		mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
+	} else if (size == 16) {
+		mask_be32 = (__force __be32)(mask);
+		mask_be16 = *(__be16 *)&mask_be32;
+		mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
+	}
+
+	return mask;
+}
 static int offload_pedit_fields(struct mlx5e_priv *priv,
 				int namespace,
 				struct pedit_headers_action *hdrs,
@@ -2637,9 +2653,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 	u32 *s_masks_p, *a_masks_p, s_mask, a_mask;
 	struct mlx5e_tc_mod_hdr_acts *mod_acts;
 	struct mlx5_fields *f;
-	unsigned long mask;
-	__be32 mask_be32;
-	__be16 mask_be16;
+	unsigned long mask, field_mask;
 	int err;
 	u8 cmd;
 
@@ -2705,14 +2719,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		if (skip)
 			continue;
 
-		if (f->field_bsize == 32) {
-			mask_be32 = (__force __be32)(mask);
-			mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
-		} else if (f->field_bsize == 16) {
-			mask_be32 = (__force __be32)(mask);
-			mask_be16 = *(__be16 *)&mask_be32;
-			mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
-		}
+		mask = mask_to_le(mask, f->field_bsize);
 
 		first = find_first_bit(&mask, f->field_bsize);
 		next_z = find_next_zero_bit(&mask, f->field_bsize, first);
@@ -2743,9 +2750,10 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		if (cmd == MLX5_ACTION_TYPE_SET) {
 			int start;
 
+			field_mask = mask_to_le(f->field_mask, f->field_bsize);
+
 			/* if field is bit sized it can start not from first bit */
-			start = find_first_bit((unsigned long *)&f->field_mask,
-					       f->field_bsize);
+			start = find_first_bit(&field_mask, f->field_bsize);
 
 			MLX5_SET(set_action_in, action, offset, first - start);
 			/* length is num of bits to be written, zero means length of 32 */

From 47c97e6b10a1e3680cad539929da092bfa535446 Mon Sep 17 00:00:00 2001
From: Ron Diskin <rondi@mellanox.com>
Date: Sun, 10 May 2020 14:39:51 +0300
Subject: [PATCH 08/15] net/mlx5e: Fix multicast counter not up-to-date in "ip
 -s"

Currently the FW does not generate events for counters other than error
counters. Unlike ".get_ethtool_stats", ".ndo_get_stats64" (which ip -s
uses) might run in atomic context, while the FW interface is non atomic.
Thus, 'ip' is not allowed to issue FW commands, so it will only display
cached counters in the driver.

Add a SW counter (mcast_packets) in the driver to count rx multicast
packets. The counter also counts broadcast packets, as we consider it a
special case of multicast.
Use the counter value when calling "ip -s"/"ifconfig".

Fixes: f62b8bb8f2d3 ("net/mlx5: Extend mlx5_core to support ConnectX-4 Ethernet functionality")
Signed-off-by: Ron Diskin <rondi@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h  | 5 +++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 8 +-------
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    | 4 ++++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 2 ++
 4 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 9334c9c3e208..24336c60123a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -20,6 +20,11 @@ enum mlx5e_icosq_wqe_type {
 };
 
 /* General */
+static inline bool mlx5e_skb_is_multicast(struct sk_buff *skb)
+{
+	return skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST;
+}
+
 void mlx5e_trigger_irq(struct mlx5e_icosq *sq);
 void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe);
 void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 917c28e7f29e..d46047235568 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3569,6 +3569,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
 
 		s->rx_packets   += rq_stats->packets + xskrq_stats->packets;
 		s->rx_bytes     += rq_stats->bytes + xskrq_stats->bytes;
+		s->multicast    += rq_stats->mcast_packets + xskrq_stats->mcast_packets;
 
 		for (j = 0; j < priv->max_opened_tc; j++) {
 			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
@@ -3584,7 +3585,6 @@ void
 mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
 	/* In switchdev mode, monitor counters doesn't monitor
@@ -3619,12 +3619,6 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors +
 			   stats->rx_frame_errors;
 	stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors;
-
-	/* vport multicast also counts packets that are dropped due to steering
-	 * or rx out of buffer
-	 */
-	stats->multicast =
-		VPORT_COUNTER_GET(vstats, received_eth_multicast.packets);
 }
 
 static void mlx5e_set_rx_mode(struct net_device *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 99d102c035b0..64c8ac5eabf6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -53,6 +53,7 @@
 #include "en/xsk/rx.h"
 #include "en/health.h"
 #include "en/params.h"
+#include "en/txrx.h"
 
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
@@ -1080,6 +1081,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 		mlx5e_enable_ecn(rq, skb);
 
 	skb->protocol = eth_type_trans(skb, netdev);
+
+	if (unlikely(mlx5e_skb_is_multicast(skb)))
+		stats->mcast_packets++;
 }
 
 static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 2e1cca1923b9..be7cda283781 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -119,6 +119,7 @@ struct mlx5e_sw_stats {
 	u64 tx_nop;
 	u64 rx_lro_packets;
 	u64 rx_lro_bytes;
+	u64 rx_mcast_packets;
 	u64 rx_ecn_mark;
 	u64 rx_removed_vlan_packets;
 	u64 rx_csum_unnecessary;
@@ -298,6 +299,7 @@ struct mlx5e_rq_stats {
 	u64 csum_none;
 	u64 lro_packets;
 	u64 lro_bytes;
+	u64 mcast_packets;
 	u64 ecn_mark;
 	u64 removed_vlan_packets;
 	u64 xdp_drop;

From b521105b68a2e3334d69202fb354d7b711b01aa3 Mon Sep 17 00:00:00 2001
From: Alaa Hleihel <alaa@nvidia.com>
Date: Tue, 25 Aug 2020 10:41:50 +0300
Subject: [PATCH 09/15] net/mlx5e: Fix using wrong stats_grps in
 mlx5e_update_ndo_stats()

The cited commit started to reuse function mlx5e_update_ndo_stats() for
the representors as well.
However, the function is hard-coded to work on mlx5e_nic_stats_grps only.
Due to this issue, the representors statistics were not updated in the
output of "ip -s".

Fix it to work with the correct group by extracting it from the caller's
profile.

Also, while at it and since this function became generic, move it to
en_stats.c and rename it accordingly.

Fixes: 8a236b15144b ("net/mlx5e: Convert rep stats to mlx5e_stats_grp-based infra")
Signed-off-by: Alaa Hleihel <alaa@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h         |  1 -
 .../ethernet/mellanox/mlx5/core/en/monitor_stats.c   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c    | 12 +-----------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c     |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c   | 12 ++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h   |  1 +
 6 files changed, 17 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 5d7b79518449..90d5caabd6af 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1005,7 +1005,6 @@ int mlx5e_update_nic_rx(struct mlx5e_priv *priv);
 void mlx5e_update_carrier(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
-void mlx5e_update_ndo_stats(struct mlx5e_priv *priv);
 
 void mlx5e_queue_update_stats(struct mlx5e_priv *priv);
 int mlx5e_bits_invert(unsigned long a, int size);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
index 8fe8b4d6ad1c..254c84739046 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
@@ -51,7 +51,7 @@ static void mlx5e_monitor_counters_work(struct work_struct *work)
 					       monitor_counters_work);
 
 	mutex_lock(&priv->state_lock);
-	mlx5e_update_ndo_stats(priv);
+	mlx5e_stats_update_ndo_stats(priv);
 	mutex_unlock(&priv->state_lock);
 	mlx5e_monitor_counter_arm(priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d46047235568..b3cda7b6e5e1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -158,16 +158,6 @@ static void mlx5e_update_carrier_work(struct work_struct *work)
 	mutex_unlock(&priv->state_lock);
 }
 
-void mlx5e_update_ndo_stats(struct mlx5e_priv *priv)
-{
-	int i;
-
-	for (i = mlx5e_nic_stats_grps_num(priv) - 1; i >= 0; i--)
-		if (mlx5e_nic_stats_grps[i]->update_stats_mask &
-		    MLX5E_NDO_UPDATE_STATS)
-			mlx5e_nic_stats_grps[i]->update_stats(priv);
-}
-
 static void mlx5e_update_stats_work(struct work_struct *work)
 {
 	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
@@ -5187,7 +5177,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.enable		   = mlx5e_nic_enable,
 	.disable	   = mlx5e_nic_disable,
 	.update_rx	   = mlx5e_update_nic_rx,
-	.update_stats	   = mlx5e_update_ndo_stats,
+	.update_stats	   = mlx5e_stats_update_ndo_stats,
 	.update_carrier	   = mlx5e_update_carrier,
 	.rx_handlers       = &mlx5e_rx_handlers_nic,
 	.max_tc		   = MLX5E_MAX_NUM_TC,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index e13e5d1b3eae..e979bff64c49 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1171,7 +1171,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
 	.cleanup_tx		= mlx5e_cleanup_rep_tx,
 	.enable		        = mlx5e_rep_enable,
 	.update_rx		= mlx5e_update_rep_rx,
-	.update_stats           = mlx5e_update_ndo_stats,
+	.update_stats           = mlx5e_stats_update_ndo_stats,
 	.rx_handlers            = &mlx5e_rx_handlers_rep,
 	.max_tc			= 1,
 	.rq_groups		= MLX5E_NUM_RQ_GROUPS(REGULAR),
@@ -1189,7 +1189,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 	.enable		        = mlx5e_uplink_rep_enable,
 	.disable	        = mlx5e_uplink_rep_disable,
 	.update_rx		= mlx5e_update_rep_rx,
-	.update_stats           = mlx5e_update_ndo_stats,
+	.update_stats           = mlx5e_stats_update_ndo_stats,
 	.update_carrier	        = mlx5e_update_carrier,
 	.rx_handlers            = &mlx5e_rx_handlers_rep,
 	.max_tc			= MLX5E_MAX_NUM_TC,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index e3b2f59408e6..f6383bc2bc3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -54,6 +54,18 @@ unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv)
 	return total;
 }
 
+void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv)
+{
+	mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps;
+	const unsigned int num_stats_grps = stats_grps_num(priv);
+	int i;
+
+	for (i = num_stats_grps - 1; i >= 0; i--)
+		if (stats_grps[i]->update_stats &&
+		    stats_grps[i]->update_stats_mask & MLX5E_NDO_UPDATE_STATS)
+			stats_grps[i]->update_stats(priv);
+}
+
 void mlx5e_stats_update(struct mlx5e_priv *priv)
 {
 	mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index be7cda283781..562263d62141 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -103,6 +103,7 @@ unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv);
 void mlx5e_stats_update(struct mlx5e_priv *priv);
 void mlx5e_stats_fill(struct mlx5e_priv *priv, u64 *data, int idx);
 void mlx5e_stats_fill_strings(struct mlx5e_priv *priv, u8 *data);
+void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv);
 
 /* Concrete NIC Stats */
 

From 8f0bcd19b1da3f264223abea985b9462e85a3718 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 28 Jun 2020 13:06:06 +0300
Subject: [PATCH 10/15] net/mlx5e: TLS, Do not expose FPGA TLS counter if not
 supported

The set of TLS TX global SW counters in mlx5e_tls_sw_stats_desc
is updated from all rings by using atomic ops.
This set of stats is used only in the FPGA TLS use case, not in
the Connect-X TLS one, where regular per-ring counters are used.

Do not expose them in the Connect-X use case, as this would cause
counter duplication. For example, tx_tls_drop_no_sync_data would
appear twice in the ethtool stats.

Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/tls_stats.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
index 01468ec27446..b949b9a7538b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c
@@ -35,7 +35,6 @@
 #include <net/sock.h>
 
 #include "en.h"
-#include "accel/tls.h"
 #include "fpga/sdk.h"
 #include "en_accel/tls.h"
 
@@ -51,9 +50,14 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = {
 
 #define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc)
 
+static bool is_tls_atomic_stats(struct mlx5e_priv *priv)
+{
+	return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev);
+}
+
 int mlx5e_tls_get_count(struct mlx5e_priv *priv)
 {
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	return NUM_TLS_SW_COUNTERS;
@@ -63,7 +67,7 @@ int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
 {
 	unsigned int i, idx = 0;
 
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
@@ -77,7 +81,7 @@ int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data)
 {
 	int i, idx = 0;
 
-	if (!priv->tls)
+	if (!is_tls_atomic_stats(priv))
 		return 0;
 
 	for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)

From 6e8de0b6b4690ba7a685db33801bf7536bac674f Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 10 Aug 2020 15:59:41 +0300
Subject: [PATCH 11/15] net/mlx5e: kTLS, Fix napi sync and possible
 use-after-free

Using synchronize_rcu() is sufficient to wait until running NAPI quits.

See similar upstream fix with detailed explanation:
("net/mlx5e: Use synchronize_rcu to sync with NAPI")

This change also fixes a possible use-after-free as the NAPI
might be already released at this stage.

Fixes: 0419d8c9d8f8 ("net/mlx5e: kTLS, Add kTLS RX resync support")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index acf6d80a6bb7..f95aa50ab51a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -659,7 +659,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx)
 	priv_rx = mlx5e_get_ktls_rx_priv_ctx(tls_ctx);
 	set_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags);
 	mlx5e_set_ktls_rx_priv_ctx(tls_ctx, NULL);
-	napi_synchronize(&priv->channels.c[priv_rx->rxq]->napi);
+	synchronize_rcu(); /* Sync with NAPI */
 	if (!cancel_work_sync(&priv_rx->rule.work))
 		/* completion is needed, as the priv_rx in the add flow
 		 * is maintained on the wqe info (wi), not on the socket.

From 66ce5fc05713e6b90f74c01439f2aaa137ffd9f4 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@nvidia.com>
Date: Mon, 7 Sep 2020 22:58:50 -0700
Subject: [PATCH 12/15] net/mlx5e: kTLS, Add missing dma_unmap in RX resync

Progress params dma address is never unmapped, unmap it when completion
handling is over.

Fixes: 0419d8c9d8f8 ("net/mlx5e: kTLS, Add kTLS RX resync support")
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c    | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index f95aa50ab51a..fb4e4f2ebe02 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -386,16 +386,17 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 	struct mlx5e_ktls_offload_context_rx *priv_rx;
 	struct mlx5e_ktls_rx_resync_ctx *resync;
 	u8 tracker_state, auth_state, *ctx;
+	struct device *dev;
 	u32 hw_seq;
 
 	priv_rx = buf->priv_rx;
 	resync = &priv_rx->resync;
-
+	dev = resync->priv->mdev->device;
 	if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags)))
 		goto out;
 
-	dma_sync_single_for_cpu(resync->priv->mdev->device, buf->dma_addr,
-				PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
+	dma_sync_single_for_cpu(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE,
+				DMA_FROM_DEVICE);
 
 	ctx = buf->progress.ctx;
 	tracker_state = MLX5_GET(tls_progress_params, ctx, record_tracker_state);
@@ -411,6 +412,7 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 	priv_rx->stats->tls_resync_req_end++;
 out:
 	refcount_dec(&resync->refcnt);
+	dma_unmap_single(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
 	kfree(buf);
 }
 

From 581642f32f33017619355b7d91704c152df1fc2d Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@nvidia.com>
Date: Thu, 10 Sep 2020 21:16:04 -0700
Subject: [PATCH 13/15] net/mlx5e: kTLS, Fix leak on resync error flow

Resync progress params buffer and dma weren't released on error,
Add missing error unwinding for resync_post_get_progress_params().

Fixes: 0419d8c9d8f8 ("net/mlx5e: kTLS, Add kTLS RX resync support")
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c    | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index fb4e4f2ebe02..e85411bd1fed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -258,7 +258,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 				       PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(pdev, buf->dma_addr))) {
 		err = -ENOMEM;
-		goto err_out;
+		goto err_free;
 	}
 
 	buf->priv_rx = priv_rx;
@@ -266,7 +266,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 	BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1);
 	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
 		err = -ENOSPC;
-		goto err_out;
+		goto err_dma_unmap;
 	}
 
 	pi = mlx5e_icosq_get_next_pi(sq, 1);
@@ -297,6 +297,10 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 
 	return cseg;
 
+err_dma_unmap:
+	dma_unmap_single(pdev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
+err_free:
+	kfree(buf);
 err_out:
 	priv_rx->stats->tls_resync_req_skip++;
 	return ERR_PTR(err);

From 94c4fed710c372313157f20b5eced39d04a96f88 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@nvidia.com>
Date: Mon, 7 Sep 2020 22:54:43 -0700
Subject: [PATCH 14/15] net/mlx5e: kTLS, Avoid kzalloc(GFP_KERNEL) under
 spinlock

The spinlock only needed when accessing the channel's icosq, grab the lock
after the buf allocation in resync_post_get_progress_params() to avoid
kzalloc(GFP_KERNEL) in atomic context.

Fixes: 0419d8c9d8f8 ("net/mlx5e: kTLS, Add kTLS RX resync support")
Reported-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ktls_rx.c     | 25 ++++++++-----------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index e85411bd1fed..6bbfcf18107d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -234,7 +234,7 @@ mlx5e_get_ktls_rx_priv_ctx(struct tls_context *tls_ctx)
 
 /* Re-sync */
 /* Runs in work context */
-static struct mlx5_wqe_ctrl_seg *
+static int
 resync_post_get_progress_params(struct mlx5e_icosq *sq,
 				struct mlx5e_ktls_offload_context_rx *priv_rx)
 {
@@ -264,7 +264,11 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 	buf->priv_rx = priv_rx;
 
 	BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1);
+
+	spin_lock(&sq->channel->async_icosq_lock);
+
 	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
+		spin_unlock(&sq->channel->async_icosq_lock);
 		err = -ENOSPC;
 		goto err_dma_unmap;
 	}
@@ -294,8 +298,10 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq,
 	};
 	icosq_fill_wi(sq, pi, &wi);
 	sq->pc++;
+	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
+	spin_unlock(&sq->channel->async_icosq_lock);
 
-	return cseg;
+	return 0;
 
 err_dma_unmap:
 	dma_unmap_single(pdev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
@@ -303,7 +309,7 @@ err_free:
 	kfree(buf);
 err_out:
 	priv_rx->stats->tls_resync_req_skip++;
-	return ERR_PTR(err);
+	return err;
 }
 
 /* Function is called with elevated refcount.
@@ -313,10 +319,8 @@ static void resync_handle_work(struct work_struct *work)
 {
 	struct mlx5e_ktls_offload_context_rx *priv_rx;
 	struct mlx5e_ktls_rx_resync_ctx *resync;
-	struct mlx5_wqe_ctrl_seg *cseg;
 	struct mlx5e_channel *c;
 	struct mlx5e_icosq *sq;
-	struct mlx5_wq_cyc *wq;
 
 	resync = container_of(work, struct mlx5e_ktls_rx_resync_ctx, work);
 	priv_rx = container_of(resync, struct mlx5e_ktls_offload_context_rx, resync);
@@ -328,18 +332,9 @@ static void resync_handle_work(struct work_struct *work)
 
 	c = resync->priv->channels.c[priv_rx->rxq];
 	sq = &c->async_icosq;
-	wq = &sq->wq;
 
-	spin_lock(&c->async_icosq_lock);
-
-	cseg = resync_post_get_progress_params(sq, priv_rx);
-	if (IS_ERR(cseg)) {
+	if (resync_post_get_progress_params(sq, priv_rx))
 		refcount_dec(&resync->refcnt);
-		goto unlock;
-	}
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
-unlock:
-	spin_unlock(&c->async_icosq_lock);
 }
 
 static void resync_init(struct mlx5e_ktls_rx_resync_ctx *resync,

From cb39ccc5cbe1011d8d21886b75e2468070ac672c Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@nvidia.com>
Date: Fri, 11 Sep 2020 11:00:06 -0700
Subject: [PATCH 15/15] net/mlx5e: mlx5e_fec_in_caps() returns a boolean

Returning errno is a bug, fix that.

Also fixes smatch warnings:
drivers/net/ethernet/mellanox/mlx5/core/en/port.c:453
mlx5e_fec_in_caps() warn: signedness bug returning '(-95)'

Fixes: 2132b71f78d2 ("net/mlx5e: Advertise globaly supported FEC modes")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Aya Levin <ayal@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/port.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 5de1cb9f5330..96608dbb9314 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -490,11 +490,8 @@ bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy)
 	int err;
 	int i;
 
-	if (!MLX5_CAP_GEN(dev, pcam_reg))
-		return -EOPNOTSUPP;
-
-	if (!MLX5_CAP_PCAM_REG(dev, pplm))
-		return -EOPNOTSUPP;
+	if (!MLX5_CAP_GEN(dev, pcam_reg) || !MLX5_CAP_PCAM_REG(dev, pplm))
+		return false;
 
 	MLX5_SET(pplm_reg, in, local_port, 1);
 	err =  mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0);