From a5e400a985df8041ed4659ed1462aa9134318130 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Sun, 20 Aug 2023 20:58:56 +0300
Subject: net/mlx5e: Honor user choice of IPsec replay window size

Users can configure IPsec replay window size, but mlx5 driver didn't
honor their choice and set always 32bits. Fix assignment logic to
configure right size from the beginning.

Fixes: 7db21ef4566e ("net/mlx5e: Set IPsec replay sequence numbers")
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c    | 21 +++++++++++++++++++++
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c     |  2 +-
 include/linux/mlx5/mlx5_ifc.h                       |  7 +++++++
 3 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 655496598c68..4028932d93ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -335,6 +335,27 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 		attrs->replay_esn.esn = sa_entry->esn_state.esn;
 		attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb;
 		attrs->replay_esn.overlap = sa_entry->esn_state.overlap;
+		switch (x->replay_esn->replay_window) {
+		case 32:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_32BIT;
+			break;
+		case 64:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_64BIT;
+			break;
+		case 128:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_128BIT;
+			break;
+		case 256:
+			attrs->replay_esn.replay_window =
+				MLX5_IPSEC_ASO_REPLAY_WIN_256BIT;
+			break;
+		default:
+			WARN_ON(true);
+			return;
+		}
 	}
 
 	attrs->dir = x->xso.dir;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index a91f772dc981..4e018fba2d5f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -95,7 +95,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
 
 		if (attrs->dir == XFRM_DEV_OFFLOAD_IN) {
 			MLX5_SET(ipsec_aso, aso_ctx, window_sz,
-				 attrs->replay_esn.replay_window / 64);
+				 attrs->replay_esn.replay_window);
 			MLX5_SET(ipsec_aso, aso_ctx, mode,
 				 MLX5_IPSEC_ASO_REPLAY_PROTECTION);
 		}
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6f3631425f38..90ca63f4bf63 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -12001,6 +12001,13 @@ enum {
 	MLX5_IPSEC_ASO_INC_SN            = 0x2,
 };
 
+enum {
+	MLX5_IPSEC_ASO_REPLAY_WIN_32BIT  = 0x0,
+	MLX5_IPSEC_ASO_REPLAY_WIN_64BIT  = 0x1,
+	MLX5_IPSEC_ASO_REPLAY_WIN_128BIT = 0x2,
+	MLX5_IPSEC_ASO_REPLAY_WIN_256BIT = 0x3,
+};
+
 struct mlx5_ifc_ipsec_aso_bits {
 	u8         valid[0x1];
 	u8         reserved_at_201[0x1];
-- 
cgit v1.2.3


From 3d42c8cc67a8fcbff0181f9ed6d03d353edcee07 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Wed, 20 Sep 2023 10:07:13 +0300
Subject: net/mlx5e: Ensure that IPsec sequence packet number starts from 1

According to RFC4303, section "3.3.3. Sequence Number Generation",
the first packet sent using a given SA will contain a sequence
number of 1.

However if user didn't set seq/oseq, the HW used zero as first sequence
packet number. Such misconfiguration causes to drop of first packet
if replay window protection was enabled in SA.

To fix it, set sequence number to be at least 1.

Fixes: 7db21ef4566e ("net/mlx5e: Set IPsec replay sequence numbers")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 4028932d93ce..914b9e6eb7db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -121,7 +121,14 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
 	if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO)
 		esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom));
 
-	sa_entry->esn_state.esn = esn;
+	if (sa_entry->esn_state.esn_msb)
+		sa_entry->esn_state.esn = esn;
+	else
+		/* According to RFC4303, section "3.3.3. Sequence Number Generation",
+		 * the first packet sent using a given SA will contain a sequence
+		 * number of 1.
+		 */
+		sa_entry->esn_state.esn = max_t(u32, esn, 1);
 	sa_entry->esn_state.esn_msb = esn_msb;
 
 	if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) {
-- 
cgit v1.2.3


From 94af50c0a9bb961fe93cf0fdd14eb0883da86721 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 21 Sep 2023 14:06:18 +0300
Subject: net/mlx5e: Unify esw and normal IPsec status table
 creation/destruction

Change normal IPsec flow to use the same creation/destruction functions
for status flow table as that of ESW, which first of all refines the
code to have less code duplication.

And more importantly, the ESW status table handles IPsec syndrome
checks at steering by HW, which is more efficient than the previous
behaviour we had where it was copied to WQE meta data and checked
by the driver.

Fixes: 1762f132d542 ("net/mlx5e: Support IPsec packet offload for RX in switchdev mode")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         | 187 ++++++++++++++++-----
 .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c | 152 -----------------
 .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h |  15 --
 3 files changed, 141 insertions(+), 213 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index f41c976dc33f..85ed5171e835 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -128,63 +128,166 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns,
 	return mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
 }
 
-static int ipsec_status_rule(struct mlx5_core_dev *mdev,
-			     struct mlx5e_ipsec_rx *rx,
-			     struct mlx5_flow_destination *dest)
+static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
+					 struct mlx5e_ipsec_rx *rx)
 {
-	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	mlx5_del_flow_rules(rx->status_drop.rule);
+	mlx5_destroy_flow_group(rx->status_drop.group);
+	mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt);
+}
+
+static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	mlx5_del_flow_rules(rx->status.rule);
+
+	if (rx != ipsec->rx_esw)
+		return;
+
+#ifdef CONFIG_MLX5_ESWITCH
+	mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
+#endif
+}
+
+static int ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_act flow_act = {};
-	struct mlx5_modify_hdr *modify_hdr;
-	struct mlx5_flow_handle *fte;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *flow_counter;
 	struct mlx5_flow_spec *spec;
-	int err;
+	struct mlx5_flow_group *g;
+	u32 *flow_group_in;
+	int err = 0;
 
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec)
-		return -ENOMEM;
+	if (!flow_group_in || !spec) {
+		err = -ENOMEM;
+		goto err_out;
+	}
 
-	/* Action to copy 7 bit ipsec_syndrome to regB[24:30] */
-	MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY);
-	MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME);
-	MLX5_SET(copy_action_in, action, src_offset, 0);
-	MLX5_SET(copy_action_in, action, length, 7);
-	MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
-	MLX5_SET(copy_action_in, action, dst_offset, 24);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
+	g = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop flow group, err=%d\n", err);
+		goto err_out;
+	}
 
-	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL,
-					      1, action);
+	flow_counter = mlx5_fc_create(mdev, false);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt;
+	}
 
-	if (IS_ERR(modify_hdr)) {
-		err = PTR_ERR(modify_hdr);
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
 		mlx5_core_err(mdev,
-			      "fail to alloc ipsec copy modify_header_id err=%d\n", err);
-		goto out_spec;
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule;
 	}
 
-	/* create fte */
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
-			  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+	rx->status_drop.group = g;
+	rx->status_drop.rule = rule;
+	rx->status_drop_cnt = flow_counter;
+
+	kvfree(flow_group_in);
+	kvfree(spec);
+	return 0;
+
+err_rule:
+	mlx5_fc_destroy(mdev, flow_counter);
+err_cnt:
+	mlx5_destroy_flow_group(g);
+err_out:
+	kvfree(flow_group_in);
+	kvfree(spec);
+	return err;
+}
+
+static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.ipsec_syndrome, 0);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	flow_act.flags = FLOW_ACT_NO_APPEND;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	flow_act.modify_hdr = modify_hdr;
-	fte = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
-	if (IS_ERR(fte)) {
-		err = PTR_ERR(fte);
-		mlx5_core_err(mdev, "fail to add ipsec rx err copy rule err=%d\n", err);
-		goto out;
+	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_warn(ipsec->mdev,
+			       "Failed to add ipsec rx status pass rule, err=%d\n", err);
+		goto err_rule;
 	}
 
+	rx->status.rule = rule;
 	kvfree(spec);
-	rx->status.rule = fte;
-	rx->status.modify_hdr = modify_hdr;
 	return 0;
 
-out:
-	mlx5_modify_header_dealloc(mdev, modify_hdr);
-out_spec:
+err_rule:
 	kvfree(spec);
 	return err;
 }
 
+static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	ipsec_rx_status_pass_destroy(ipsec, rx);
+	ipsec_rx_status_drop_destroy(ipsec, rx);
+}
+
+static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5_flow_destination *dest)
+{
+	int err;
+
+	err = ipsec_rx_status_drop_create(ipsec, rx);
+	if (err)
+		return err;
+
+	err = ipsec_rx_status_pass_create(ipsec, rx, dest);
+	if (err)
+		goto err_pass_create;
+
+	return 0;
+
+err_pass_create:
+	ipsec_rx_status_drop_destroy(ipsec, rx);
+	return err;
+}
+
 static int ipsec_miss_create(struct mlx5_core_dev *mdev,
 			     struct mlx5_flow_table *ft,
 			     struct mlx5e_ipsec_miss *miss,
@@ -333,12 +436,7 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_destroy_flow_table(rx->ft.sa);
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-	if (rx == ipsec->rx_esw) {
-		mlx5_esw_ipsec_rx_status_destroy(ipsec, rx);
-	} else {
-		mlx5_del_flow_rules(rx->status.rule);
-		mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
-	}
+	mlx5_ipsec_rx_status_destroy(ipsec, rx);
 	mlx5_destroy_flow_table(rx->ft.status);
 
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
@@ -428,10 +526,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 	dest[1].counter_id = mlx5_fc_id(rx->fc->cnt);
-	if (rx == ipsec->rx_esw)
-		err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest);
-	else
-		err = ipsec_status_rule(mdev, rx, dest);
+	err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
 	if (err)
 		goto err_add;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 095f31f380fa..13b5916b64e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -21,158 +21,6 @@ enum {
 	MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL,
 };
 
-static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
-					     struct mlx5e_ipsec_rx *rx)
-{
-	mlx5_del_flow_rules(rx->status_drop.rule);
-	mlx5_destroy_flow_group(rx->status_drop.group);
-	mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt);
-}
-
-static void esw_ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
-					     struct mlx5e_ipsec_rx *rx)
-{
-	mlx5_del_flow_rules(rx->status.rule);
-	mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
-}
-
-static int esw_ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec,
-					   struct mlx5e_ipsec_rx *rx)
-{
-	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
-	struct mlx5_flow_table *ft = rx->ft.status;
-	struct mlx5_core_dev *mdev = ipsec->mdev;
-	struct mlx5_flow_destination dest = {};
-	struct mlx5_flow_act flow_act = {};
-	struct mlx5_flow_handle *rule;
-	struct mlx5_fc *flow_counter;
-	struct mlx5_flow_spec *spec;
-	struct mlx5_flow_group *g;
-	u32 *flow_group_in;
-	int err = 0;
-
-	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!flow_group_in || !spec) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-
-	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1);
-	g = mlx5_create_flow_group(ft, flow_group_in);
-	if (IS_ERR(g)) {
-		err = PTR_ERR(g);
-		mlx5_core_err(mdev,
-			      "Failed to add ipsec rx status drop flow group, err=%d\n", err);
-		goto err_out;
-	}
-
-	flow_counter = mlx5_fc_create(mdev, false);
-	if (IS_ERR(flow_counter)) {
-		err = PTR_ERR(flow_counter);
-		mlx5_core_err(mdev,
-			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
-		goto err_cnt;
-	}
-
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest.counter_id = mlx5_fc_id(flow_counter);
-	spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
-	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
-	if (IS_ERR(rule)) {
-		err = PTR_ERR(rule);
-		mlx5_core_err(mdev,
-			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
-		goto err_rule;
-	}
-
-	rx->status_drop.group = g;
-	rx->status_drop.rule = rule;
-	rx->status_drop_cnt = flow_counter;
-
-	kvfree(flow_group_in);
-	kvfree(spec);
-	return 0;
-
-err_rule:
-	mlx5_fc_destroy(mdev, flow_counter);
-err_cnt:
-	mlx5_destroy_flow_group(g);
-err_out:
-	kvfree(flow_group_in);
-	kvfree(spec);
-	return err;
-}
-
-static int esw_ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
-					   struct mlx5e_ipsec_rx *rx,
-					   struct mlx5_flow_destination *dest)
-{
-	struct mlx5_flow_act flow_act = {};
-	struct mlx5_flow_handle *rule;
-	struct mlx5_flow_spec *spec;
-	int err;
-
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec)
-		return -ENOMEM;
-
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
-			 misc_parameters_2.ipsec_syndrome);
-	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.ipsec_syndrome, 0);
-	spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
-	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
-	flow_act.flags = FLOW_ACT_NO_APPEND;
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
-			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
-	if (IS_ERR(rule)) {
-		err = PTR_ERR(rule);
-		mlx5_core_warn(ipsec->mdev,
-			       "Failed to add ipsec rx status pass rule, err=%d\n", err);
-		goto err_rule;
-	}
-
-	rx->status.rule = rule;
-	kvfree(spec);
-	return 0;
-
-err_rule:
-	kvfree(spec);
-	return err;
-}
-
-void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
-				      struct mlx5e_ipsec_rx *rx)
-{
-	esw_ipsec_rx_status_pass_destroy(ipsec, rx);
-	esw_ipsec_rx_status_drop_destroy(ipsec, rx);
-}
-
-int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
-				    struct mlx5e_ipsec_rx *rx,
-				    struct mlx5_flow_destination *dest)
-{
-	int err;
-
-	err = esw_ipsec_rx_status_drop_create(ipsec, rx);
-	if (err)
-		return err;
-
-	err = esw_ipsec_rx_status_pass_create(ipsec, rx, dest);
-	if (err)
-		goto err_pass_create;
-
-	return 0;
-
-err_pass_create:
-	esw_ipsec_rx_status_drop_destroy(ipsec, rx);
-	return err;
-}
-
 void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx_create_attr *attr)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index 0c90f7a8b0d3..ac9c65b89166 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -8,11 +8,6 @@ struct mlx5e_ipsec;
 struct mlx5e_ipsec_sa_entry;
 
 #ifdef CONFIG_MLX5_ESWITCH
-void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
-				      struct mlx5e_ipsec_rx *rx);
-int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
-				    struct mlx5e_ipsec_rx *rx,
-				    struct mlx5_flow_destination *dest);
 void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx_create_attr *attr);
 int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
@@ -26,16 +21,6 @@ void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_tx_create_attr *attr);
 void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev);
 #else
-static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
-						    struct mlx5e_ipsec_rx *rx) {}
-
-static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
-						  struct mlx5e_ipsec_rx *rx,
-						  struct mlx5_flow_destination *dest)
-{
-	return  -EINVAL;
-}
-
 static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_rx_create_attr *attr) {}
 
-- 
cgit v1.2.3


From 5ad00dee43b98129b86930d457b983d4d04dc553 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 3 Oct 2023 16:44:19 +0300
Subject: net/mlx5e: Remove exposure of IPsec RX flow steering struct

After previous commit, which unified various IPsec creation modes,
there is no need to have struct mlx5e_ipsec_rx exposed in global
IPsec header. Move it to ipsec_fs.c to be placed together with
already existing struct mlx5e_ipsec_tx.

Fixes: 1762f132d542 ("net/mlx5e: Support IPsec packet offload for RX in switchdev mode")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h | 14 +-------------
 .../net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c  | 16 ++++++++++++++--
 drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c   |  8 ++++----
 3 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 8f4a37bceaf4..c3a40bf11952 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -201,19 +201,6 @@ struct mlx5e_ipsec_miss {
 	struct mlx5_flow_handle *rule;
 };
 
-struct mlx5e_ipsec_rx {
-	struct mlx5e_ipsec_ft ft;
-	struct mlx5e_ipsec_miss pol;
-	struct mlx5e_ipsec_miss sa;
-	struct mlx5e_ipsec_rule status;
-	struct mlx5e_ipsec_miss status_drop;
-	struct mlx5_fc *status_drop_cnt;
-	struct mlx5e_ipsec_fc *fc;
-	struct mlx5_fs_chains *chains;
-	u8 allow_tunnel_mode : 1;
-	struct xarray ipsec_obj_id_map;
-};
-
 struct mlx5e_ipsec_tx_create_attr {
 	int prio;
 	int pol_level;
@@ -248,6 +235,7 @@ struct mlx5e_ipsec {
 	struct mlx5_ipsec_fs *roce;
 	u8 is_uplink_rep: 1;
 	struct mlx5e_ipsec_mpv_work mpv_work;
+	struct xarray ipsec_obj_id_map;
 };
 
 struct mlx5e_ipsec_esn_state {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 85ed5171e835..aa74a2422869 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -32,6 +32,18 @@ struct mlx5e_ipsec_tx {
 	u8 allow_tunnel_mode : 1;
 };
 
+struct mlx5e_ipsec_rx {
+	struct mlx5e_ipsec_ft ft;
+	struct mlx5e_ipsec_miss pol;
+	struct mlx5e_ipsec_miss sa;
+	struct mlx5e_ipsec_rule status;
+	struct mlx5e_ipsec_miss status_drop;
+	struct mlx5_fc *status_drop_cnt;
+	struct mlx5e_ipsec_fc *fc;
+	struct mlx5_fs_chains *chains;
+	u8 allow_tunnel_mode : 1;
+};
+
 /* IPsec RX flow steering */
 static enum mlx5_traffic_types family2tt(u32 family)
 {
@@ -2052,7 +2064,7 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
 	kfree(ipsec->rx_ipv6);
 
 	if (ipsec->is_uplink_rep) {
-		xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map);
+		xa_destroy(&ipsec->ipsec_obj_id_map);
 
 		mutex_destroy(&ipsec->tx_esw->ft.mutex);
 		WARN_ON(ipsec->tx_esw->ft.refcnt);
@@ -2115,7 +2127,7 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec,
 		mutex_init(&ipsec->tx_esw->ft.mutex);
 		mutex_init(&ipsec->rx_esw->ft.mutex);
 		ipsec->tx_esw->ns = ns_esw;
-		xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
+		xa_init_flags(&ipsec->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
 	} else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) {
 		ipsec->roce = mlx5_ipsec_fs_roce_init(mdev, devcom);
 	} else {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 13b5916b64e2..5a0047bdcb51 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -50,7 +50,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
 	u32 mapped_id;
 	int err;
 
-	err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id,
+	err = xa_alloc_bh(&ipsec->ipsec_obj_id_map, &mapped_id,
 			  xa_mk_value(sa_entry->ipsec_obj_id),
 			  XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0);
 	if (err)
@@ -81,7 +81,7 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
 	return 0;
 
 err_header_alloc:
-	xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id);
+	xa_erase_bh(&ipsec->ipsec_obj_id_map, mapped_id);
 	return err;
 }
 
@@ -90,7 +90,7 @@ void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
 
 	if (sa_entry->rx_mapped_id)
-		xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map,
+		xa_erase_bh(&ipsec->ipsec_obj_id_map,
 			    sa_entry->rx_mapped_id);
 }
 
@@ -100,7 +100,7 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 	struct mlx5e_ipsec *ipsec = priv->ipsec;
 	void *val;
 
-	val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id);
+	val = xa_load(&ipsec->ipsec_obj_id_map, id);
 	if (!val)
 		return -ENOENT;
 
-- 
cgit v1.2.3


From dddb49b63d8683be81cff220b94a0196c1367b74 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Sun, 24 Sep 2023 11:50:31 +0300
Subject: net/mlx5e: Add IPsec and ASO syndromes check in HW

After IPsec decryption it isn't enough to only check the IPsec syndrome
but need to also check the ASO syndrome in order to verify that the
operation was actually successful.

Verify that both syndromes are actually zero and in case not drop the
packet and increment the appropriate flow counter for the drop reason.

Fixes: 6b5c45e16e43 ("net/mlx5e: Configure IPsec packet offload flow steering")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.h   |   8 +
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         | 235 +++++++++++++++++++--
 2 files changed, 223 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index c3a40bf11952..adaea3493193 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -189,11 +189,19 @@ struct mlx5e_ipsec_ft {
 	u32 refcnt;
 };
 
+struct mlx5e_ipsec_drop {
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *fc;
+};
+
 struct mlx5e_ipsec_rule {
 	struct mlx5_flow_handle *rule;
 	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5_pkt_reformat *pkt_reformat;
 	struct mlx5_fc *fc;
+	struct mlx5e_ipsec_drop replay;
+	struct mlx5e_ipsec_drop auth;
+	struct mlx5e_ipsec_drop trailer;
 };
 
 struct mlx5e_ipsec_miss {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index aa74a2422869..aeb399d8dae5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -32,13 +32,17 @@ struct mlx5e_ipsec_tx {
 	u8 allow_tunnel_mode : 1;
 };
 
+struct mlx5e_ipsec_status_checks {
+	struct mlx5_flow_group *drop_all_group;
+	struct mlx5e_ipsec_drop all;
+};
+
 struct mlx5e_ipsec_rx {
 	struct mlx5e_ipsec_ft ft;
 	struct mlx5e_ipsec_miss pol;
 	struct mlx5e_ipsec_miss sa;
 	struct mlx5e_ipsec_rule status;
-	struct mlx5e_ipsec_miss status_drop;
-	struct mlx5_fc *status_drop_cnt;
+	struct mlx5e_ipsec_status_checks status_drops;
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fs_chains *chains;
 	u8 allow_tunnel_mode : 1;
@@ -143,9 +147,9 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns,
 static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
-	mlx5_del_flow_rules(rx->status_drop.rule);
-	mlx5_destroy_flow_group(rx->status_drop.group);
-	mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt);
+	mlx5_del_flow_rules(rx->status_drops.all.rule);
+	mlx5_fc_destroy(ipsec->mdev, rx->status_drops.all.fc);
+	mlx5_destroy_flow_group(rx->status_drops.drop_all_group);
 }
 
 static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
@@ -161,8 +165,149 @@ static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
 #endif
 }
 
-static int ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec,
-				       struct mlx5e_ipsec_rx *rx)
+static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *flow_counter;
+	struct mlx5_flow_spec *spec;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	flow_counter = mlx5_fc_create(mdev, true);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt;
+	}
+	sa_entry->ipsec_rule.auth.fc = flow_counter;
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = FLOW_ACT_NO_APPEND;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_2,
+		 sa_entry->ipsec_obj_id | BIT(31));
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule;
+	}
+	sa_entry->ipsec_rule.auth.rule = rule;
+
+	flow_counter = mlx5_fc_create(mdev, true);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt_2;
+	}
+	sa_entry->ipsec_rule.trailer.fc = flow_counter;
+
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 2);
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule_2;
+	}
+	sa_entry->ipsec_rule.trailer.rule = rule;
+
+	kvfree(spec);
+	return 0;
+
+err_rule_2:
+	mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.trailer.fc);
+err_cnt_2:
+	mlx5_del_flow_rules(sa_entry->ipsec_rule.auth.rule);
+err_rule:
+	mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.auth.fc);
+err_cnt:
+	kvfree(spec);
+	return err;
+}
+
+static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct mlx5e_ipsec_rx *rx)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *flow_counter;
+	struct mlx5_flow_spec *spec;
+	int err;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	flow_counter = mlx5_fc_create(mdev, true);
+	if (IS_ERR(flow_counter)) {
+		err = PTR_ERR(flow_counter);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule counter, err=%d\n", err);
+		goto err_cnt;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = FLOW_ACT_NO_APPEND;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter_id = mlx5_fc_id(flow_counter);
+	if (rx == ipsec->rx_esw)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4);
+	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
+	MLX5_SET(fte_match_param, spec->match_value,  misc_parameters_2.metadata_reg_c_2,
+		 sa_entry->ipsec_obj_id | BIT(31));
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx status drop rule, err=%d\n", err);
+		goto err_rule;
+	}
+
+	sa_entry->ipsec_rule.replay.rule = rule;
+	sa_entry->ipsec_rule.replay.fc = flow_counter;
+
+	kvfree(spec);
+	return 0;
+
+err_rule:
+	mlx5_fc_destroy(mdev, flow_counter);
+err_cnt:
+	kvfree(spec);
+	return err;
+}
+
+static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec,
+					   struct mlx5e_ipsec_rx *rx)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_table *ft = rx->ft.status;
@@ -214,9 +359,9 @@ static int ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec,
 		goto err_rule;
 	}
 
-	rx->status_drop.group = g;
-	rx->status_drop.rule = rule;
-	rx->status_drop_cnt = flow_counter;
+	rx->status_drops.drop_all_group = g;
+	rx->status_drops.all.rule = rule;
+	rx->status_drops.all.fc = flow_counter;
 
 	kvfree(flow_group_in);
 	kvfree(spec);
@@ -247,8 +392,12 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
 	MLX5_SET(fte_match_param, spec->match_value,
 		 misc_parameters_2.ipsec_syndrome, 0);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_4, 0);
 	if (rx == ipsec->rx_esw)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
@@ -285,7 +434,7 @@ static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
 {
 	int err;
 
-	err = ipsec_rx_status_drop_create(ipsec, rx);
+	err = ipsec_rx_status_drop_all_create(ipsec, rx);
 	if (err)
 		return err;
 
@@ -529,7 +678,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
-	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 1, 0);
+	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft_status;
@@ -1159,29 +1308,48 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8
 			       struct mlx5_flow_act *flow_act)
 {
 	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, type, dir);
-	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	u8 action[3][MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
 	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_modify_hdr *modify_hdr;
+	u8 num_of_actions = 1;
 
-	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action[0], action_type, MLX5_ACTION_TYPE_SET);
 	switch (dir) {
 	case XFRM_DEV_OFFLOAD_IN:
-		MLX5_SET(set_action_in, action, field,
+		MLX5_SET(set_action_in, action[0], field,
 			 MLX5_ACTION_IN_FIELD_METADATA_REG_B);
+
+		num_of_actions++;
+		MLX5_SET(set_action_in, action[1], action_type, MLX5_ACTION_TYPE_SET);
+		MLX5_SET(set_action_in, action[1], field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_2);
+		MLX5_SET(set_action_in, action[1], data, val);
+		MLX5_SET(set_action_in, action[1], offset, 0);
+		MLX5_SET(set_action_in, action[1], length, 32);
+
+		if (type == XFRM_DEV_OFFLOAD_CRYPTO) {
+			num_of_actions++;
+			MLX5_SET(set_action_in, action[2], action_type,
+				 MLX5_ACTION_TYPE_SET);
+			MLX5_SET(set_action_in, action[2], field,
+				 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
+			MLX5_SET(set_action_in, action[2], data, 0);
+			MLX5_SET(set_action_in, action[2], offset, 0);
+			MLX5_SET(set_action_in, action[2], length, 32);
+		}
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
-		MLX5_SET(set_action_in, action, field,
+		MLX5_SET(set_action_in, action[0], field,
 			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	MLX5_SET(set_action_in, action, data, val);
-	MLX5_SET(set_action_in, action, offset, 0);
-	MLX5_SET(set_action_in, action, length, 32);
+	MLX5_SET(set_action_in, action[0], data, val);
+	MLX5_SET(set_action_in, action[0], offset, 0);
+	MLX5_SET(set_action_in, action[0], length, 32);
 
-	modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, 1, action);
+	modify_hdr = mlx5_modify_header_alloc(mdev, ns_type, num_of_actions, action);
 	if (IS_ERR(modify_hdr)) {
 		mlx5_core_err(mdev, "Failed to allocate modify_header %ld\n",
 			      PTR_ERR(modify_hdr));
@@ -1479,6 +1647,15 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err);
 		goto err_add_flow;
 	}
+	if (attrs->type == XFRM_DEV_OFFLOAD_PACKET)
+		err = rx_add_rule_drop_replay(sa_entry, rx);
+	if (err)
+		goto err_add_replay;
+
+	err = rx_add_rule_drop_auth_trailer(sa_entry, rx);
+	if (err)
+		goto err_drop_reason;
+
 	kvfree(spec);
 
 	sa_entry->ipsec_rule.rule = rule;
@@ -1487,6 +1664,13 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	sa_entry->ipsec_rule.pkt_reformat = flow_act.pkt_reformat;
 	return 0;
 
+err_drop_reason:
+	if (sa_entry->ipsec_rule.replay.rule) {
+		mlx5_del_flow_rules(sa_entry->ipsec_rule.replay.rule);
+		mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.replay.fc);
+	}
+err_add_replay:
+	mlx5_del_flow_rules(rule);
 err_add_flow:
 	mlx5_fc_destroy(mdev, counter);
 err_add_cnt:
@@ -1994,6 +2178,17 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	if (ipsec_rule->modify_hdr)
 		mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr);
+
+	mlx5_del_flow_rules(ipsec_rule->trailer.rule);
+	mlx5_fc_destroy(mdev, ipsec_rule->trailer.fc);
+
+	mlx5_del_flow_rules(ipsec_rule->auth.rule);
+	mlx5_fc_destroy(mdev, ipsec_rule->auth.fc);
+
+	if (ipsec_rule->replay.rule) {
+		mlx5_del_flow_rules(ipsec_rule->replay.rule);
+		mlx5_fc_destroy(mdev, ipsec_rule->replay.fc);
+	}
 	mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry);
 	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
 }
-- 
cgit v1.2.3


From c2bf84f1d1a1595dcc45fe867f0e02b331993fee Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Sun, 12 Nov 2023 13:50:00 +0200
Subject: net/mlx5e: Tidy up IPsec NAT-T SA discovery

IPsec NAT-T packets are UDP encapsulated packets over ESP normal ones.
In case they arrive to RX, the SPI and ESP are located in inner header,
while the check was performed on outer header instead.

That wrong check caused to the situation where received rekeying request
was missed and caused to rekey timeout, which "compensated" this failure
by completing rekeying.

Fixes: d65954934937 ("net/mlx5e: Support IPsec NAT-T functionality")
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         | 22 ++++++++++++++++------
 include/linux/mlx5/mlx5_ifc.h                      |  2 +-
 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index aeb399d8dae5..7a789061c998 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -1212,13 +1212,22 @@ static void setup_fte_esp(struct mlx5_flow_spec *spec)
 	MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_ESP);
 }
 
-static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi)
+static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi, bool encap)
 {
 	/* SPI number */
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
 
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters.outer_esp_spi);
-	MLX5_SET(fte_match_param, spec->match_value, misc_parameters.outer_esp_spi, spi);
+	if (encap) {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters.inner_esp_spi);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters.inner_esp_spi, spi);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters.outer_esp_spi);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters.outer_esp_spi, spi);
+	}
 }
 
 static void setup_fte_no_frags(struct mlx5_flow_spec *spec)
@@ -1596,8 +1605,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	else
 		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
 
-	setup_fte_spi(spec, attrs->spi);
-	setup_fte_esp(spec);
+	setup_fte_spi(spec, attrs->spi, attrs->encap);
+	if (!attrs->encap)
+		setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
@@ -1719,7 +1729,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	switch (attrs->type) {
 	case XFRM_DEV_OFFLOAD_CRYPTO:
-		setup_fte_spi(spec, attrs->spi);
+		setup_fte_spi(spec, attrs->spi, false);
 		setup_fte_esp(spec);
 		setup_fte_reg_a(spec);
 		break;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 90ca63f4bf63..3f7b664d625b 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -621,7 +621,7 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 
 	u8         reserved_at_140[0x8];
 	u8         bth_dst_qp[0x18];
-	u8	   reserved_at_160[0x20];
+	u8	   inner_esp_spi[0x20];
 	u8	   outer_esp_spi[0x20];
 	u8         reserved_at_1a0[0x60];
 };
-- 
cgit v1.2.3


From baac8351f74c543896b8fd40138b7ad9365587a3 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Wed, 11 Oct 2023 03:38:29 +0000
Subject: net/mlx5e: Reduce eswitch mode_lock protection context

Currently eswitch mode_lock is so heavy, for example, it's locked
during the whole process of the mode change, which may need to hold
other locks. As the mode_lock is also used by IPSec to block mode and
encap change now, it is easy to cause lock dependency.

Since some of protections are also done by devlink lock, the eswitch
mode_lock is not needed at those places, and thus the possibility of
lockdep issue is reduced.

Fixes: c8e350e62fc5 ("net/mlx5e: Make TC and IPsec offloads mutually exclusive on a netdev")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         |  9 +++--
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  | 35 ++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  2 ++
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 38 +++++++++++++---------
 4 files changed, 52 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 7a789061c998..c1e89dc77db9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -2110,8 +2110,11 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 	int err = 0;
 
-	if (esw)
-		down_write(&esw->mode_lock);
+	if (esw) {
+		err = mlx5_esw_lock(esw);
+		if (err)
+			return err;
+	}
 
 	if (mdev->num_block_ipsec) {
 		err = -EBUSY;
@@ -2122,7 +2125,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
 
 unlock:
 	if (esw)
-		up_write(&esw->mode_lock);
+		mlx5_esw_unlock(esw);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 8d0b915a3121..3047d7015c52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1463,7 +1463,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs)
 {
 	int err;
 
-	lockdep_assert_held(&esw->mode_lock);
+	devl_assert_locked(priv_to_devlink(esw->dev));
 
 	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
 		esw_warn(esw->dev, "FDB is not supported, aborting ...\n");
@@ -1531,7 +1531,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 	if (toggle_lag)
 		mlx5_lag_disable_change(esw->dev);
 
-	down_write(&esw->mode_lock);
 	if (!mlx5_esw_is_fdb_created(esw)) {
 		ret = mlx5_eswitch_enable_locked(esw, num_vfs);
 	} else {
@@ -1554,8 +1553,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 		}
 	}
 
-	up_write(&esw->mode_lock);
-
 	if (toggle_lag)
 		mlx5_lag_enable_change(esw->dev);
 
@@ -1569,12 +1566,11 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 		return;
 
 	devl_assert_locked(priv_to_devlink(esw->dev));
-	down_write(&esw->mode_lock);
 	/* If driver is unloaded, this function is called twice by remove_one()
 	 * and mlx5_unload(). Prevent the second call.
 	 */
 	if (!esw->esw_funcs.num_vfs && !esw->esw_funcs.num_ec_vfs && !clear_vf)
-		goto unlock;
+		return;
 
 	esw_info(esw->dev, "Unload vfs: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n",
 		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
@@ -1603,9 +1599,6 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
 		esw->esw_funcs.num_vfs = 0;
 	else
 		esw->esw_funcs.num_ec_vfs = 0;
-
-unlock:
-	up_write(&esw->mode_lock);
 }
 
 /* Free resources for corresponding eswitch mode. It is called by devlink
@@ -1647,10 +1640,8 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
 
 	devl_assert_locked(priv_to_devlink(esw->dev));
 	mlx5_lag_disable_change(esw->dev);
-	down_write(&esw->mode_lock);
 	mlx5_eswitch_disable_locked(esw);
 	esw->mode = MLX5_ESWITCH_LEGACY;
-	up_write(&esw->mode_lock);
 	mlx5_lag_enable_change(esw->dev);
 }
 
@@ -2254,8 +2245,13 @@ bool mlx5_esw_hold(struct mlx5_core_dev *mdev)
 	if (!mlx5_esw_allowed(esw))
 		return true;
 
-	if (down_read_trylock(&esw->mode_lock) != 0)
+	if (down_read_trylock(&esw->mode_lock) != 0) {
+		if (esw->eswitch_operation_in_progress) {
+			up_read(&esw->mode_lock);
+			return false;
+		}
 		return true;
+	}
 
 	return false;
 }
@@ -2312,7 +2308,8 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw)
 	if (down_write_trylock(&esw->mode_lock) == 0)
 		return -EINVAL;
 
-	if (atomic64_read(&esw->user_count) > 0) {
+	if (esw->eswitch_operation_in_progress ||
+	    atomic64_read(&esw->user_count) > 0) {
 		up_write(&esw->mode_lock);
 		return -EBUSY;
 	}
@@ -2320,6 +2317,18 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw)
 	return esw->mode;
 }
 
+int mlx5_esw_lock(struct mlx5_eswitch *esw)
+{
+	down_write(&esw->mode_lock);
+
+	if (esw->eswitch_operation_in_progress) {
+		up_write(&esw->mode_lock);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
 /**
  * mlx5_esw_unlock() - Release write lock on esw mode lock
  * @esw: eswitch device.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 37ab66e7b403..b674b57d05aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -383,6 +383,7 @@ struct mlx5_eswitch {
 	struct xarray paired;
 	struct mlx5_devcom_comp_dev *devcom;
 	u16 enabled_ipsec_vf_count;
+	bool eswitch_operation_in_progress;
 };
 
 void esw_offloads_disable(struct mlx5_eswitch *esw);
@@ -827,6 +828,7 @@ void mlx5_esw_release(struct mlx5_core_dev *dev);
 void mlx5_esw_get(struct mlx5_core_dev *dev);
 void mlx5_esw_put(struct mlx5_core_dev *dev);
 int mlx5_esw_try_lock(struct mlx5_eswitch *esw);
+int mlx5_esw_lock(struct mlx5_eswitch *esw);
 void mlx5_esw_unlock(struct mlx5_eswitch *esw);
 
 void esw_vport_change_handle_locked(struct mlx5_vport *vport);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 88236e75fd90..bf78eeca401b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3733,13 +3733,16 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 		goto unlock;
 	}
 
+	esw->eswitch_operation_in_progress = true;
+	up_write(&esw->mode_lock);
+
 	mlx5_eswitch_disable_locked(esw);
 	if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) {
 		if (mlx5_devlink_trap_get_num_active(esw->dev)) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Can't change mode while devlink traps are active");
 			err = -EOPNOTSUPP;
-			goto unlock;
+			goto skip;
 		}
 		err = esw_offloads_start(esw, extack);
 	} else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) {
@@ -3749,6 +3752,9 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 		err = -EINVAL;
 	}
 
+skip:
+	down_write(&esw->mode_lock);
+	esw->eswitch_operation_in_progress = false;
 unlock:
 	mlx5_esw_unlock(esw);
 enable_lag:
@@ -3759,16 +3765,12 @@ enable_lag:
 int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
 {
 	struct mlx5_eswitch *esw;
-	int err;
 
 	esw = mlx5_devlink_eswitch_get(devlink);
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_read(&esw->mode_lock);
-	err = esw_mode_to_devlink(esw->mode, mode);
-	up_read(&esw->mode_lock);
-	return err;
+	return esw_mode_to_devlink(esw->mode, mode);
 }
 
 static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode,
@@ -3862,11 +3864,15 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 	if (err)
 		goto out;
 
+	esw->eswitch_operation_in_progress = true;
+	up_write(&esw->mode_lock);
+
 	err = mlx5_esw_vports_inline_set(esw, mlx5_mode, extack);
-	if (err)
-		goto out;
+	if (!err)
+		esw->offloads.inline_mode = mlx5_mode;
 
-	esw->offloads.inline_mode = mlx5_mode;
+	down_write(&esw->mode_lock);
+	esw->eswitch_operation_in_progress = false;
 	up_write(&esw->mode_lock);
 	return 0;
 
@@ -3878,16 +3884,12 @@ out:
 int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 {
 	struct mlx5_eswitch *esw;
-	int err;
 
 	esw = mlx5_devlink_eswitch_get(devlink);
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_read(&esw->mode_lock);
-	err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
-	up_read(&esw->mode_lock);
-	return err;
+	return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
 }
 
 bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev)
@@ -3969,6 +3971,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
 		goto unlock;
 	}
 
+	esw->eswitch_operation_in_progress = true;
+	up_write(&esw->mode_lock);
+
 	esw_destroy_offloads_fdb_tables(esw);
 
 	esw->offloads.encap = encap;
@@ -3982,6 +3987,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
 		(void)esw_create_offloads_fdb_tables(esw);
 	}
 
+	down_write(&esw->mode_lock);
+	esw->eswitch_operation_in_progress = false;
+
 unlock:
 	up_write(&esw->mode_lock);
 	return err;
@@ -3996,9 +4004,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
 	if (IS_ERR(esw))
 		return PTR_ERR(esw);
 
-	down_read(&esw->mode_lock);
 	*encap = esw->offloads.encap;
-	up_read(&esw->mode_lock);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 4e25b661f484df54b6751b65f9ea2434a3b67539 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 12 Oct 2023 02:00:44 +0000
Subject: net/mlx5e: Check the number of elements before walk TC rhashtable

After IPSec TX tables are destroyed, the flow rules in TC rhashtable,
which have the destination to IPSec, are restored to the original
one, the uplink.

However, when the device is in switchdev mode and unload driver with
IPSec rules configured, TC rhashtable cleanup is done before IPSec
cleanup, which means tc_ht->tbl is already freed when walking TC
rhashtable, in order to restore the destination. So add the checking
before walking to avoid unexpected behavior.

Fixes: d1569537a837 ("net/mlx5e: Modify and restore TC rules for IPSec TX rules")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 5a0047bdcb51..190f10aba170 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -152,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev)
 
 	xa_for_each(&esw->offloads.vport_reps, i, rep) {
 		rpriv = rep->rep_data[REP_ETH].priv;
-		if (!rpriv || !rpriv->netdev)
+		if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems))
 			continue;
 
 		rhashtable_walk_enter(&rpriv->tc_ht, &iter);
-- 
cgit v1.2.3


From 762a55a54eec4217e4cec9265ab6e5d4c11b61bd Mon Sep 17 00:00:00 2001
From: Chris Mi <cmi@nvidia.com>
Date: Mon, 30 Oct 2023 15:44:47 +0200
Subject: net/mlx5e: Disable IPsec offload support if not FW steering

IPsec FDB offload can only work with FW steering as of now,
disable the cap upon non FW steering.

And since the IPSec cap is dynamic now based on steering mode.
Cleanup the resources if they exist instead of checking the
IPsec cap again.

Fixes: edd8b295f9e2 ("Merge branch 'mlx5-ipsec-packet-offload-support-in-eswitch-mode'")
Signed-off-by: Chris Mi <cmi@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.c   | 26 +++++++++-------------
 .../mellanox/mlx5/core/en_accel/ipsec_offload.c    |  8 ++++++-
 2 files changed, 18 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 914b9e6eb7db..161c5190c236 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -935,9 +935,11 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv)
 		return;
 
 	mlx5e_accel_ipsec_fs_cleanup(ipsec);
-	if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_TUNNEL)
+	if (ipsec->netevent_nb.notifier_call) {
 		unregister_netevent_notifier(&ipsec->netevent_nb);
-	if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)
+		ipsec->netevent_nb.notifier_call = NULL;
+	}
+	if (ipsec->aso)
 		mlx5e_ipsec_aso_cleanup(ipsec);
 	destroy_workqueue(ipsec->wq);
 	kfree(ipsec);
@@ -1046,6 +1048,12 @@ static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev,
 		}
 	}
 
+	if (x->xdo.type == XFRM_DEV_OFFLOAD_PACKET &&
+	    !(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)) {
+		NL_SET_ERR_MSG_MOD(extack, "Packet offload is not supported");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -1141,14 +1149,6 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = {
 	.xdo_dev_state_free	= mlx5e_xfrm_free_state,
 	.xdo_dev_offload_ok	= mlx5e_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
-};
-
-static const struct xfrmdev_ops mlx5e_ipsec_packet_xfrmdev_ops = {
-	.xdo_dev_state_add	= mlx5e_xfrm_add_state,
-	.xdo_dev_state_delete	= mlx5e_xfrm_del_state,
-	.xdo_dev_state_free	= mlx5e_xfrm_free_state,
-	.xdo_dev_offload_ok	= mlx5e_ipsec_offload_ok,
-	.xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
 
 	.xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft,
 	.xdo_dev_policy_add = mlx5e_xfrm_add_policy,
@@ -1166,11 +1166,7 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv)
 
 	mlx5_core_info(mdev, "mlx5e: IPSec ESP acceleration enabled\n");
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)
-		netdev->xfrmdev_ops = &mlx5e_ipsec_packet_xfrmdev_ops;
-	else
-		netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops;
-
+	netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops;
 	netdev->features |= NETIF_F_HW_ESP;
 	netdev->hw_enc_features |= NETIF_F_HW_ESP;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 4e018fba2d5f..6e00afe4671b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -6,6 +6,8 @@
 #include "ipsec.h"
 #include "lib/crypto.h"
 #include "lib/ipsec_fs_roce.h"
+#include "fs_core.h"
+#include "eswitch.h"
 
 enum {
 	MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET,
@@ -38,7 +40,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 	    MLX5_CAP_ETH(mdev, insert_trailer) && MLX5_CAP_ETH(mdev, swp))
 		caps |= MLX5_IPSEC_CAP_CRYPTO;
 
-	if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload)) {
+	if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) &&
+	    (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS ||
+	     (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS &&
+	     is_mdev_legacy_mode(mdev)))) {
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,
 					      reformat_add_esp_trasport) &&
 		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev,
@@ -559,6 +564,7 @@ void mlx5e_ipsec_aso_cleanup(struct mlx5e_ipsec *ipsec)
 	dma_unmap_single(pdev, aso->dma_addr, sizeof(aso->ctx),
 			 DMA_BIDIRECTIONAL);
 	kfree(aso);
+	ipsec->aso = NULL;
 }
 
 static void mlx5e_ipsec_aso_copy(struct mlx5_wqe_aso_ctrl_seg *ctrl,
-- 
cgit v1.2.3


From eab0da38912ebdad922ed0388209f7eb0a5163cd Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Wed, 21 Sep 2022 18:45:11 +0300
Subject: net/mlx5e: Fix possible deadlock on mlx5e_tx_timeout_work

Due to the cited patch, devlink health commands take devlink lock and
this may result in deadlock for mlx5e_tx_reporter as it takes local
state_lock before calling devlink health report and on the other hand
devlink health commands such as diagnose for same reporter take local
state_lock after taking devlink lock (see kernel log below).

To fix it, remove local state_lock from mlx5e_tx_timeout_work() before
calling devlink_health_report() and take care to cancel the work before
any call to close channels, which may free the SQs that should be
handled by the work. Before cancel_work_sync(), use current_work() to
check we are not calling it from within the work, as
mlx5e_tx_timeout_work() itself may close the channels and reopen as part
of recovery flow.

While removing state_lock from mlx5e_tx_timeout_work() keep rtnl_lock to
ensure no change in netdev->real_num_tx_queues, but use rtnl_trylock()
and a flag to avoid deadlock by calling cancel_work_sync() before
closing the channels while holding rtnl_lock too.

Kernel log:
======================================================
WARNING: possible circular locking dependency detected
6.0.0-rc3_for_upstream_debug_2022_08_30_13_10 #1 Not tainted
------------------------------------------------------
kworker/u16:2/65 is trying to acquire lock:
ffff888122f6c2f8 (&devlink->lock_key#2){+.+.}-{3:3}, at: devlink_health_report+0x2f1/0x7e0

but task is already holding lock:
ffff888121d20be0 (&priv->state_lock){+.+.}-{3:3}, at: mlx5e_tx_timeout_work+0x70/0x280 [mlx5_core]

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&priv->state_lock){+.+.}-{3:3}:
       __mutex_lock+0x12c/0x14b0
       mlx5e_rx_reporter_diagnose+0x71/0x700 [mlx5_core]
       devlink_nl_cmd_health_reporter_diagnose_doit+0x212/0xa50
       genl_family_rcv_msg_doit+0x1e9/0x2f0
       genl_rcv_msg+0x2e9/0x530
       netlink_rcv_skb+0x11d/0x340
       genl_rcv+0x24/0x40
       netlink_unicast+0x438/0x710
       netlink_sendmsg+0x788/0xc40
       sock_sendmsg+0xb0/0xe0
       __sys_sendto+0x1c1/0x290
       __x64_sys_sendto+0xdd/0x1b0
       do_syscall_64+0x3d/0x90
       entry_SYSCALL_64_after_hwframe+0x46/0xb0

-> #0 (&devlink->lock_key#2){+.+.}-{3:3}:
       __lock_acquire+0x2c8a/0x6200
       lock_acquire+0x1c1/0x550
       __mutex_lock+0x12c/0x14b0
       devlink_health_report+0x2f1/0x7e0
       mlx5e_health_report+0xc9/0xd7 [mlx5_core]
       mlx5e_reporter_tx_timeout+0x2ab/0x3d0 [mlx5_core]
       mlx5e_tx_timeout_work+0x1c1/0x280 [mlx5_core]
       process_one_work+0x7c2/0x1340
       worker_thread+0x59d/0xec0
       kthread+0x28f/0x330
       ret_from_fork+0x1f/0x30

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&priv->state_lock);
                               lock(&devlink->lock_key#2);
                               lock(&priv->state_lock);
  lock(&devlink->lock_key#2);

 *** DEADLOCK ***

4 locks held by kworker/u16:2/65:
 #0: ffff88811a55b138 ((wq_completion)mlx5e#2){+.+.}-{0:0}, at: process_one_work+0x6e2/0x1340
 #1: ffff888101de7db8 ((work_completion)(&priv->tx_timeout_work)){+.+.}-{0:0}, at: process_one_work+0x70f/0x1340
 #2: ffffffff84ce8328 (rtnl_mutex){+.+.}-{3:3}, at: mlx5e_tx_timeout_work+0x53/0x280 [mlx5_core]
 #3: ffff888121d20be0 (&priv->state_lock){+.+.}-{3:3}, at: mlx5e_tx_timeout_work+0x70/0x280 [mlx5_core]

stack backtrace:
CPU: 1 PID: 65 Comm: kworker/u16:2 Not tainted 6.0.0-rc3_for_upstream_debug_2022_08_30_13_10 #1
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
Workqueue: mlx5e mlx5e_tx_timeout_work [mlx5_core]
Call Trace:
 <TASK>
 dump_stack_lvl+0x57/0x7d
 check_noncircular+0x278/0x300
 ? print_circular_bug+0x460/0x460
 ? find_held_lock+0x2d/0x110
 ? __stack_depot_save+0x24c/0x520
 ? alloc_chain_hlocks+0x228/0x700
 __lock_acquire+0x2c8a/0x6200
 ? register_lock_class+0x1860/0x1860
 ? kasan_save_stack+0x1e/0x40
 ? kasan_set_free_info+0x20/0x30
 ? ____kasan_slab_free+0x11d/0x1b0
 ? kfree+0x1ba/0x520
 ? devlink_health_do_dump.part.0+0x171/0x3a0
 ? devlink_health_report+0x3d5/0x7e0
 lock_acquire+0x1c1/0x550
 ? devlink_health_report+0x2f1/0x7e0
 ? lockdep_hardirqs_on_prepare+0x400/0x400
 ? find_held_lock+0x2d/0x110
 __mutex_lock+0x12c/0x14b0
 ? devlink_health_report+0x2f1/0x7e0
 ? devlink_health_report+0x2f1/0x7e0
 ? mutex_lock_io_nested+0x1320/0x1320
 ? trace_hardirqs_on+0x2d/0x100
 ? bit_wait_io_timeout+0x170/0x170
 ? devlink_health_do_dump.part.0+0x171/0x3a0
 ? kfree+0x1ba/0x520
 ? devlink_health_do_dump.part.0+0x171/0x3a0
 devlink_health_report+0x2f1/0x7e0
 mlx5e_health_report+0xc9/0xd7 [mlx5_core]
 mlx5e_reporter_tx_timeout+0x2ab/0x3d0 [mlx5_core]
 ? lockdep_hardirqs_on_prepare+0x400/0x400
 ? mlx5e_reporter_tx_err_cqe+0x1b0/0x1b0 [mlx5_core]
 ? mlx5e_tx_reporter_timeout_dump+0x70/0x70 [mlx5_core]
 ? mlx5e_tx_reporter_dump_sq+0x320/0x320 [mlx5_core]
 ? mlx5e_tx_timeout_work+0x70/0x280 [mlx5_core]
 ? mutex_lock_io_nested+0x1320/0x1320
 ? process_one_work+0x70f/0x1340
 ? lockdep_hardirqs_on_prepare+0x400/0x400
 ? lock_downgrade+0x6e0/0x6e0
 mlx5e_tx_timeout_work+0x1c1/0x280 [mlx5_core]
 process_one_work+0x7c2/0x1340
 ? lockdep_hardirqs_on_prepare+0x400/0x400
 ? pwq_dec_nr_in_flight+0x230/0x230
 ? rwlock_bug.part.0+0x90/0x90
 worker_thread+0x59d/0xec0
 ? process_one_work+0x1340/0x1340
 kthread+0x28f/0x330
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x1f/0x30
 </TASK>

Fixes: c90005b5f75c ("devlink: Hold the instance lock in health callbacks")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 27 ++++++++++++++++++++---
 2 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index b2a5da9739d2..729a11b5fb25 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -826,6 +826,7 @@ enum {
 	MLX5E_STATE_DESTROYING,
 	MLX5E_STATE_XDP_TX_ENABLED,
 	MLX5E_STATE_XDP_ACTIVE,
+	MLX5E_STATE_CHANNELS_ACTIVE,
 };
 
 struct mlx5e_modify_sq_param {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ea58c6917433..0c87ddb8a7a2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2731,6 +2731,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs)
 {
 	int i;
 
+	ASSERT_RTNL();
 	if (chs->ptp) {
 		mlx5e_ptp_close(chs->ptp);
 		chs->ptp = NULL;
@@ -3012,17 +3013,29 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	if (mlx5e_is_vport_rep(priv))
 		mlx5e_rep_activate_channels(priv);
 
+	set_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state);
+
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
 
 	if (priv->rx_res)
 		mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels);
 }
 
+static void mlx5e_cancel_tx_timeout_work(struct mlx5e_priv *priv)
+{
+	WARN_ON_ONCE(test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state));
+	if (current_work() != &priv->tx_timeout_work)
+		cancel_work_sync(&priv->tx_timeout_work);
+}
+
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
 	if (priv->rx_res)
 		mlx5e_rx_res_channels_deactivate(priv->rx_res);
 
+	clear_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state);
+	mlx5e_cancel_tx_timeout_work(priv);
+
 	if (mlx5e_is_vport_rep(priv))
 		mlx5e_rep_deactivate_channels(priv);
 
@@ -4801,8 +4814,17 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	struct net_device *netdev = priv->netdev;
 	int i;
 
-	rtnl_lock();
-	mutex_lock(&priv->state_lock);
+	/* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues
+	 * through this flow. However, channel closing flows have to wait for
+	 * this work to finish while holding rtnl lock too. So either get the
+	 * lock or find that channels are being closed for other reason and
+	 * this work is not relevant anymore.
+	 */
+	while (!rtnl_trylock()) {
+		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state))
+			return;
+		msleep(20);
+	}
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		goto unlock;
@@ -4821,7 +4843,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	}
 
 unlock:
-	mutex_unlock(&priv->state_lock);
 	rtnl_unlock();
 }
 
-- 
cgit v1.2.3


From ccbe33003b109f14c4dde2a4fca9c2a50c423601 Mon Sep 17 00:00:00 2001
From: Chris Mi <cmi@nvidia.com>
Date: Mon, 11 Sep 2023 13:28:10 +0300
Subject: net/mlx5e: TC, Don't offload post action rule if not supported

If post action is not supported, eg. ignore_flow_level is not
supported, don't offload post action rule. Otherwise, will hit
panic [1].

Fix it by checking if post action table is valid or not.

[1]
[445537.863880] BUG: unable to handle page fault for address: ffffffffffffffb1
[445537.864617] #PF: supervisor read access in kernel mode
[445537.865244] #PF: error_code(0x0000) - not-present page
[445537.865860] PGD 70683a067 P4D 70683a067 PUD 70683c067 PMD 0
[445537.866497] Oops: 0000 [#1] PREEMPT SMP NOPTI
[445537.867077] CPU: 19 PID: 248742 Comm: tc Kdump: loaded Tainted: G           O       6.5.0+ #1
[445537.867888] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[445537.868834] RIP: 0010:mlx5e_tc_post_act_add+0x51/0x130 [mlx5_core]
[445537.869635] Code: c0 0d 00 00 e8 20 96 c6 d3 48 85 c0 0f 84 e5 00 00 00 c7 83 b0 01 00 00 00 00 00 00 49 89 c5 31 c0 31 d2 66 89 83 b4 01 00 00 <49> 8b 44 24 10 83 23 df 83 8b d8 01 00 00 04 48 89 83 c0 01 00 00
[445537.871318] RSP: 0018:ffffb98741cef428 EFLAGS: 00010246
[445537.871962] RAX: 0000000000000000 RBX: ffff8df341167000 RCX: 0000000000000001
[445537.872704] RDX: 0000000000000000 RSI: ffffffff954844e1 RDI: ffffffff9546e9cb
[445537.873430] RBP: ffffb98741cef448 R08: 0000000000000020 R09: 0000000000000246
[445537.874160] R10: 0000000000000000 R11: ffffffff943f73ff R12: ffffffffffffffa1
[445537.874893] R13: ffff8df36d336c20 R14: ffffffffffffffa1 R15: ffff8df341167000
[445537.875628] FS:  00007fcd6564f800(0000) GS:ffff8dfa9ea00000(0000) knlGS:0000000000000000
[445537.876425] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[445537.877090] CR2: ffffffffffffffb1 CR3: 00000003b5884001 CR4: 0000000000770ee0
[445537.877832] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[445537.878564] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[445537.879300] PKRU: 55555554
[445537.879797] Call Trace:
[445537.880263]  <TASK>
[445537.880713]  ? show_regs+0x6e/0x80
[445537.881232]  ? __die+0x29/0x70
[445537.881731]  ? page_fault_oops+0x85/0x160
[445537.882276]  ? search_exception_tables+0x65/0x70
[445537.882852]  ? kernelmode_fixup_or_oops+0xa2/0x120
[445537.883432]  ? __bad_area_nosemaphore+0x18b/0x250
[445537.884019]  ? bad_area_nosemaphore+0x16/0x20
[445537.884566]  ? do_kern_addr_fault+0x8b/0xa0
[445537.885105]  ? exc_page_fault+0xf5/0x1c0
[445537.885623]  ? asm_exc_page_fault+0x2b/0x30
[445537.886149]  ? __kmem_cache_alloc_node+0x1df/0x2a0
[445537.886717]  ? mlx5e_tc_post_act_add+0x51/0x130 [mlx5_core]
[445537.887431]  ? mlx5e_tc_post_act_add+0x30/0x130 [mlx5_core]
[445537.888172]  alloc_flow_post_acts+0xfb/0x1c0 [mlx5_core]
[445537.888849]  parse_tc_actions+0x582/0x5c0 [mlx5_core]
[445537.889505]  parse_tc_fdb_actions+0xd7/0x1f0 [mlx5_core]
[445537.890175]  __mlx5e_add_fdb_flow+0x1ab/0x2b0 [mlx5_core]
[445537.890843]  mlx5e_add_fdb_flow+0x56/0x120 [mlx5_core]
[445537.891491]  ? debug_smp_processor_id+0x1b/0x30
[445537.892037]  mlx5e_tc_add_flow+0x79/0x90 [mlx5_core]
[445537.892676]  mlx5e_configure_flower+0x305/0x450 [mlx5_core]
[445537.893341]  mlx5e_rep_setup_tc_cls_flower+0x3d/0x80 [mlx5_core]
[445537.894037]  mlx5e_rep_setup_tc_cb+0x5c/0xa0 [mlx5_core]
[445537.894693]  tc_setup_cb_add+0xdc/0x220
[445537.895177]  fl_hw_replace_filter+0x15f/0x220 [cls_flower]
[445537.895767]  fl_change+0xe87/0x1190 [cls_flower]
[445537.896302]  tc_new_tfilter+0x484/0xa50

Fixes: f0da4daa3413 ("net/mlx5e: Refactor ct to use post action infrastructure")
Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Automatic Verification <verifier@nvidia.com>
Reviewed-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shachar Kagan <skagan@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en/tc/post_act.c   |  6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 25 ++++++++++++++++++----
 2 files changed, 27 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
index 4e923a2874ae..86bf007fd05b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c
@@ -83,6 +83,9 @@ mlx5e_tc_post_act_offload(struct mlx5e_post_act *post_act,
 	struct mlx5_flow_spec *spec;
 	int err;
 
+	if (IS_ERR(post_act))
+		return PTR_ERR(post_act);
+
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
 		return -ENOMEM;
@@ -111,6 +114,9 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *po
 	struct mlx5e_post_act_handle *handle;
 	int err;
 
+	if (IS_ERR(post_act))
+		return ERR_CAST(post_act);
+
 	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
 	if (!handle)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 7ca9e5b86778..4809a66f3491 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -444,6 +444,9 @@ mlx5e_tc_add_flow_meter(struct mlx5e_priv *priv,
 	struct mlx5e_flow_meter_handle *meter;
 	enum mlx5e_post_meter_type type;
 
+	if (IS_ERR(post_act))
+		return PTR_ERR(post_act);
+
 	meter = mlx5e_tc_meter_replace(priv->mdev, &attr->meter_attr.params);
 	if (IS_ERR(meter)) {
 		mlx5_core_err(priv->mdev, "Failed to get flow meter\n");
@@ -3738,6 +3741,20 @@ out_free:
 	return err;
 }
 
+static int
+set_branch_dest_ft(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr)
+{
+	struct mlx5e_post_act *post_act = get_post_action(priv);
+
+	if (IS_ERR(post_act))
+		return PTR_ERR(post_act);
+
+	attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	attr->dest_ft = mlx5e_tc_post_act_get_ft(post_act);
+
+	return 0;
+}
+
 static int
 alloc_branch_attr(struct mlx5e_tc_flow *flow,
 		  struct mlx5e_tc_act_branch_ctrl *cond,
@@ -3761,8 +3778,8 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow,
 		break;
 	case FLOW_ACTION_ACCEPT:
 	case FLOW_ACTION_PIPE:
-		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-		attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv));
+		if (set_branch_dest_ft(flow->priv, attr))
+			goto out_err;
 		break;
 	case FLOW_ACTION_JUMP:
 		if (*jump_count) {
@@ -3771,8 +3788,8 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow,
 			goto out_err;
 		}
 		*jump_count = cond->extval;
-		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-		attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv));
+		if (set_branch_dest_ft(flow->priv, attr))
+			goto out_err;
 		break;
 	default:
 		err = -EOPNOTSUPP;
-- 
cgit v1.2.3


From 3d7a3f2612d75de5f371a681038b089ded6667eb Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Mon, 7 Aug 2023 13:11:32 +0300
Subject: net/mlx5: Nack sync reset request when HotPlug is enabled

Current sync reset flow is not supported when PCIe bridge connected
directly to mlx5 device has HotPlug interrupt enabled and can be
triggered on link state change event. Return nack on reset request in
such case.

Fixes: 92501fa6e421 ("net/mlx5: Ack on sync_reset_request only if PF can do reset_now")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 29 ++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index b568988e92e3..c4e19d627da2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -325,6 +325,29 @@ static void mlx5_fw_live_patch_event(struct work_struct *work)
 		mlx5_core_err(dev, "Failed to reload FW tracer\n");
 }
 
+#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
+static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev)
+{
+	struct pci_dev *bridge = dev->pdev->bus->self;
+	u16 reg16;
+	int err;
+
+	if (!bridge)
+		return -EOPNOTSUPP;
+
+	err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, &reg16);
+	if (err)
+		return err;
+
+	if ((reg16 & PCI_EXP_SLTCTL_HPIE) && (reg16 & PCI_EXP_SLTCTL_DLLSCE)) {
+		mlx5_core_warn(dev, "FW reset is not supported as HotPlug is enabled\n");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+#endif
+
 static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id)
 {
 	struct pci_bus *bridge_bus = dev->pdev->bus;
@@ -357,6 +380,12 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev)
 		return false;
 	}
 
+#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
+	err = mlx5_check_hotplug_interrupt(dev);
+	if (err)
+		return false;
+#endif
+
 	err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id);
 	if (err)
 		return false;
-- 
cgit v1.2.3


From 7aaf975238c47b710fcc4eca0da1e7902a53abe2 Mon Sep 17 00:00:00 2001
From: Gavin Li <gavinl@nvidia.com>
Date: Thu, 31 Aug 2023 05:47:09 +0300
Subject: net/mlx5e: Check netdev pointer before checking its net ns

Previously, when comparing the net namespaces, the case where the netdev
doesn't exist wasn't taken into account, and therefore can cause a crash.
In such a case, the comparing function should return false, as there is no
netdev->net to compare the devlink->net to.

Furthermore, this will result in an attempt to enter switchdev mode
without a netdev to fail, and which is the desired result as there is no
meaning in switchdev mode without a net device.

Fixes: 662404b24a4c ("net/mlx5e: Block entering switchdev mode with ns inconsistency")
Signed-off-by: Gavin Li <gavinl@nvidia.com>
Reviewed-by: Gavi Teitz <gavi@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch_offloads.c   | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index bf78eeca401b..bb8bcb448ae9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -3653,14 +3653,18 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode)
 
 static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink)
 {
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct net *devl_net, *netdev_net;
-	struct mlx5_eswitch *esw;
-
-	esw = mlx5_devlink_eswitch_nocheck_get(devlink);
-	netdev_net = dev_net(esw->dev->mlx5e_res.uplink_netdev);
-	devl_net = devlink_net(devlink);
+	bool ret = false;
 
-	return net_eq(devl_net, netdev_net);
+	mutex_lock(&dev->mlx5e_res.uplink_netdev_lock);
+	if (dev->mlx5e_res.uplink_netdev) {
+		netdev_net = dev_net(dev->mlx5e_res.uplink_netdev);
+		devl_net = devlink_net(devlink);
+		ret = net_eq(devl_net, netdev_net);
+	}
+	mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock);
+	return ret;
 }
 
 int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev)
-- 
cgit v1.2.3


From ca4ef28d0ad831d2521fa2b16952f37fd9324ca3 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 3 Nov 2023 09:36:20 +0300
Subject: net/mlx5: Fix a NULL vs IS_ERR() check

The mlx5_esw_offloads_devlink_port() function returns error pointers, not
NULL.

Fixes: 7bef147a6ab6 ("net/mlx5: Don't skip vport check")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3ab682bbcf86..1bf7540a65ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1497,7 +1497,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 
 	dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch,
 						 rpriv->rep->vport);
-	if (dl_port) {
+	if (!IS_ERR(dl_port)) {
 		SET_NETDEV_DEVLINK_PORT(netdev, dl_port);
 		mlx5e_rep_vnic_reporter_create(priv, dl_port);
 	}
-- 
cgit v1.2.3


From e5dc5afff62f3e97e86c3643ec9fcad23de4f2d3 Mon Sep 17 00:00:00 2001
From: Judy Hsiao <judyhsiao@chromium.org>
Date: Wed, 6 Dec 2023 03:38:33 +0000
Subject: neighbour: Don't let neigh_forced_gc() disable preemption for long

We are seeing cases where neigh_cleanup_and_release() is called by
neigh_forced_gc() many times in a row with preemption turned off.
When running on a low powered CPU at a low CPU frequency, this has
been measured to keep preemption off for ~10 ms. That's not great on a
system with HZ=1000 which expects tasks to be able to schedule in
with ~1ms latency.

Suggested-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Judy Hsiao <judyhsiao@chromium.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index df81c1f0a570..552719c3bbc3 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -253,9 +253,11 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 {
 	int max_clean = atomic_read(&tbl->gc_entries) -
 			READ_ONCE(tbl->gc_thresh2);
+	u64 tmax = ktime_get_ns() + NSEC_PER_MSEC;
 	unsigned long tref = jiffies - 5 * HZ;
 	struct neighbour *n, *tmp;
 	int shrunk = 0;
+	int loop = 0;
 
 	NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs);
 
@@ -278,11 +280,16 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 				shrunk++;
 			if (shrunk >= max_clean)
 				break;
+			if (++loop == 16) {
+				if (ktime_get_ns() > tmax)
+					goto unlock;
+				loop = 0;
+			}
 		}
 	}
 
 	WRITE_ONCE(tbl->last_flush, jiffies);
-
+unlock:
 	write_unlock_bh(&tbl->lock);
 
 	return shrunk;
-- 
cgit v1.2.3


From bd4a816752bab609dd6d65ae021387beb9e2ddbd Mon Sep 17 00:00:00 2001
From: Maciej Żenczykowski <maze@google.com>
Date: Wed, 6 Dec 2023 09:36:12 -0800
Subject: net: ipv6: support reporting otherwise unknown prefix flags in
 RTM_NEWPREFIX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Lorenzo points out that we effectively clear all unknown
flags from PIO when copying them to userspace in the netlink
RTM_NEWPREFIX notification.

We could fix this one at a time as new flags are defined,
or in one fell swoop - I choose the latter.

We could either define 6 new reserved flags (reserved1..6) and handle
them individually (and rename them as new flags are defined), or we
could simply copy the entire unmodified byte over - I choose the latter.

This unfortunately requires some anonymous union/struct magic,
so we add a static assert on the struct size for a little extra safety.

Cc: David Ahern <dsahern@kernel.org>
Cc: Lorenzo Colitti <lorenzo@google.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h | 12 ++++++++++--
 include/net/if_inet6.h |  4 ----
 net/ipv6/addrconf.c    |  6 +-----
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 82da55101b5a..61ebe723ee4d 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -31,17 +31,22 @@ struct prefix_info {
 	__u8			length;
 	__u8			prefix_len;
 
+	union __packed {
+		__u8		flags;
+		struct __packed {
 #if defined(__BIG_ENDIAN_BITFIELD)
-	__u8			onlink : 1,
+			__u8	onlink : 1,
 			 	autoconf : 1,
 				reserved : 6;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-	__u8			reserved : 6,
+			__u8	reserved : 6,
 				autoconf : 1,
 				onlink : 1;
 #else
 #error "Please fix <asm/byteorder.h>"
 #endif
+		};
+	};
 	__be32			valid;
 	__be32			prefered;
 	__be32			reserved2;
@@ -49,6 +54,9 @@ struct prefix_info {
 	struct in6_addr		prefix;
 };
 
+/* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */
+static_assert(sizeof(struct prefix_info) == 32);
+
 #include <linux/ipv6.h>
 #include <linux/netdevice.h>
 #include <net/if_inet6.h>
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 3e454c4d7ba6..f07642264c1e 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -22,10 +22,6 @@
 #define IF_RS_SENT	0x10
 #define IF_READY	0x80000000
 
-/* prefix flags */
-#define IF_PREFIX_ONLINK	0x01
-#define IF_PREFIX_AUTOCONF	0x02
-
 enum {
 	INET6_IFADDR_STATE_PREDAD,
 	INET6_IFADDR_STATE_DAD,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 3aaea56b5166..2692a7b24c40 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6149,11 +6149,7 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
 	pmsg->prefix_len = pinfo->prefix_len;
 	pmsg->prefix_type = pinfo->type;
 	pmsg->prefix_pad3 = 0;
-	pmsg->prefix_flags = 0;
-	if (pinfo->onlink)
-		pmsg->prefix_flags |= IF_PREFIX_ONLINK;
-	if (pinfo->autoconf)
-		pmsg->prefix_flags |= IF_PREFIX_AUTOCONF;
+	pmsg->prefix_flags = pinfo->flags;
 
 	if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix))
 		goto nla_put_failure;
-- 
cgit v1.2.3


From c12296bbecc488623b7d1932080e394d08f3226b Mon Sep 17 00:00:00 2001
From: Florent Revest <revest@chromium.org>
Date: Wed, 6 Dec 2023 13:37:18 +0100
Subject: team: Fix use-after-free when an option instance allocation fails

In __team_options_register, team_options are allocated and appended to
the team's option_list.
If one option instance allocation fails, the "inst_rollback" cleanup
path frees the previously allocated options but doesn't remove them from
the team's option_list.
This leaves dangling pointers that can be dereferenced later by other
parts of the team driver that iterate over options.

This patch fixes the cleanup path to remove the dangling pointers from
the list.

As far as I can tell, this uaf doesn't have much security implications
since it would be fairly hard to exploit (an attacker would need to make
the allocation of that specific small object fail) but it's still nice
to fix.

Cc: stable@vger.kernel.org
Fixes: 80f7c6683fe0 ("team: add support for per-port options")
Signed-off-by: Florent Revest <revest@chromium.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://lore.kernel.org/r/20231206123719.1963153-1-revest@chromium.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/team/team.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 508d9a392ab1..f575f225d417 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -281,8 +281,10 @@ static int __team_options_register(struct team *team,
 	return 0;
 
 inst_rollback:
-	for (i--; i >= 0; i--)
+	for (i--; i >= 0; i--) {
 		__team_option_inst_del_option(team, dst_opts[i]);
+		list_del(&dst_opts[i]->list);
+	}
 
 	i = option_count;
 alloc_rollback:
-- 
cgit v1.2.3


From a1664b991ac12b872be859ca03529c68c72795a2 Mon Sep 17 00:00:00 2001
From: Shinas Rasheed <srasheed@marvell.com>
Date: Wed, 6 Dec 2023 05:52:27 -0800
Subject: octeon_ep: initialise control mbox tasks before using APIs

Initialise various workqueue tasks and queue interrupt poll task
before the first invocation of any control net APIs. Since
octep_ctrl_net_get_info was called before the control net receive
work task was initialised or even the interrupt poll task was
queued, the function call wasn't returning actual firmware
info queried from Octeon.

Fixes: 8d6198a14e2b ("octeon_ep: support to fetch firmware info")
Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
Reviewed-by: Michal Schmidt <mschmidt@redhat.com>
Link: https://lore.kernel.org/r/20231206135228.2591659-1-srasheed@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/marvell/octeon_ep/octep_main.c    | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index 552970c7dec0..a2b5a3f8df93 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -1193,6 +1193,13 @@ int octep_device_setup(struct octep_device *oct)
 	if (ret)
 		return ret;
 
+	INIT_WORK(&oct->tx_timeout_task, octep_tx_timeout_task);
+	INIT_WORK(&oct->ctrl_mbox_task, octep_ctrl_mbox_task);
+	INIT_DELAYED_WORK(&oct->intr_poll_task, octep_intr_poll_task);
+	oct->poll_non_ioq_intr = true;
+	queue_delayed_work(octep_wq, &oct->intr_poll_task,
+			   msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS));
+
 	atomic_set(&oct->hb_miss_cnt, 0);
 	INIT_DELAYED_WORK(&oct->hb_task, octep_hb_timeout_task);
 
@@ -1325,21 +1332,18 @@ static int octep_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_octep_config;
 	}
 
-	octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID,
-				&octep_dev->conf->fw_info);
+	err = octep_ctrl_net_get_info(octep_dev, OCTEP_CTRL_NET_INVALID_VFID,
+				      &octep_dev->conf->fw_info);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to get firmware info\n");
+		goto register_dev_err;
+	}
 	dev_info(&octep_dev->pdev->dev, "Heartbeat interval %u msecs Heartbeat miss count %u\n",
 		 octep_dev->conf->fw_info.hb_interval,
 		 octep_dev->conf->fw_info.hb_miss_count);
 	queue_delayed_work(octep_wq, &octep_dev->hb_task,
 			   msecs_to_jiffies(octep_dev->conf->fw_info.hb_interval));
 
-	INIT_WORK(&octep_dev->tx_timeout_task, octep_tx_timeout_task);
-	INIT_WORK(&octep_dev->ctrl_mbox_task, octep_ctrl_mbox_task);
-	INIT_DELAYED_WORK(&octep_dev->intr_poll_task, octep_intr_poll_task);
-	octep_dev->poll_non_ioq_intr = true;
-	queue_delayed_work(octep_wq, &octep_dev->intr_poll_task,
-			   msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS));
-
 	netdev->netdev_ops = &octep_netdev_ops;
 	octep_set_ethtool_ops(netdev);
 	netif_carrier_off(netdev);
-- 
cgit v1.2.3


From f4e6064c97c050bd9904925ff7d53d0c9954fc7b Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Wed, 6 Dec 2023 15:12:20 +0100
Subject: qca_debug: Prevent crash on TX ring changes

The qca_spi driver stop and restart the SPI kernel thread
(via ndo_stop & ndo_open) in case of TX ring changes. This is
a big issue because it allows userspace to prevent restart of
the SPI kernel thread (via signals). A subsequent change of
TX ring wrongly assume a valid spi_thread pointer which result
in a crash.

So prevent this by stopping the network traffic handling and
temporary park the SPI thread.

Fixes: 291ab06ecf67 ("net: qualcomm: new Ethernet over SPI driver for QCA7000")
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Link: https://lore.kernel.org/r/20231206141222.52029-2-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qualcomm/qca_debug.c |  9 ++++-----
 drivers/net/ethernet/qualcomm/qca_spi.c   | 12 ++++++++++++
 2 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c
index 6f2fa2a42770..a5445252b0c4 100644
--- a/drivers/net/ethernet/qualcomm/qca_debug.c
+++ b/drivers/net/ethernet/qualcomm/qca_debug.c
@@ -263,7 +263,6 @@ qcaspi_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring,
 		     struct kernel_ethtool_ringparam *kernel_ring,
 		     struct netlink_ext_ack *extack)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
 	struct qcaspi *qca = netdev_priv(dev);
 
 	if ((ring->rx_pending) ||
@@ -271,14 +270,14 @@ qcaspi_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring,
 	    (ring->rx_jumbo_pending))
 		return -EINVAL;
 
-	if (netif_running(dev))
-		ops->ndo_stop(dev);
+	if (qca->spi_thread)
+		kthread_park(qca->spi_thread);
 
 	qca->txr.count = max_t(u32, ring->tx_pending, TX_RING_MIN_LEN);
 	qca->txr.count = min_t(u16, qca->txr.count, TX_RING_MAX_LEN);
 
-	if (netif_running(dev))
-		ops->ndo_open(dev);
+	if (qca->spi_thread)
+		kthread_unpark(qca->spi_thread);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index bec723028e96..b0fad69bb755 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -580,6 +580,18 @@ qcaspi_spi_thread(void *data)
 	netdev_info(qca->net_dev, "SPI thread created\n");
 	while (!kthread_should_stop()) {
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_park()) {
+			netif_tx_disable(qca->net_dev);
+			netif_carrier_off(qca->net_dev);
+			qcaspi_flush_tx_ring(qca);
+			kthread_parkme();
+			if (qca->sync == QCASPI_SYNC_READY) {
+				netif_carrier_on(qca->net_dev);
+				netif_wake_queue(qca->net_dev);
+			}
+			continue;
+		}
+
 		if ((qca->intr_req == qca->intr_svc) &&
 		    !qca->txr.skb[qca->txr.head])
 			schedule();
-- 
cgit v1.2.3


From 96a7e861d9e04d07febd3011c30cd84cd141d81f Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Wed, 6 Dec 2023 15:12:21 +0100
Subject: qca_debug: Fix ethtool -G iface tx behavior

After calling ethtool -g it was not possible to adjust the TX ring
size again:

  # ethtool -g eth1
  Ring parameters for eth1:
  Pre-set maximums:
  RX:		4
  RX Mini:	n/a
  RX Jumbo:	n/a
  TX:		10
  Current hardware settings:
  RX:		4
  RX Mini:	n/a
  RX Jumbo:	n/a
  TX:		10
  # ethtool -G eth1 tx 8
  netlink error: Invalid argument

The reason for this is that the readonly setting rx_pending get
initialized and after that the range check in qcaspi_set_ringparam()
fails regardless of the provided parameter. So fix this by accepting
the exposed RX defaults. Instead of adding another magic number
better use a new define here.

Fixes: 291ab06ecf67 ("net: qualcomm: new Ethernet over SPI driver for QCA7000")
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Link: https://lore.kernel.org/r/20231206141222.52029-3-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qualcomm/qca_debug.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c
index a5445252b0c4..1822f2ad8f0d 100644
--- a/drivers/net/ethernet/qualcomm/qca_debug.c
+++ b/drivers/net/ethernet/qualcomm/qca_debug.c
@@ -30,6 +30,8 @@
 
 #define QCASPI_MAX_REGS 0x20
 
+#define QCASPI_RX_MAX_FRAMES 4
+
 static const u16 qcaspi_spi_regs[] = {
 	SPI_REG_BFR_SIZE,
 	SPI_REG_WRBUF_SPC_AVA,
@@ -252,9 +254,9 @@ qcaspi_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring,
 {
 	struct qcaspi *qca = netdev_priv(dev);
 
-	ring->rx_max_pending = 4;
+	ring->rx_max_pending = QCASPI_RX_MAX_FRAMES;
 	ring->tx_max_pending = TX_RING_MAX_LEN;
-	ring->rx_pending = 4;
+	ring->rx_pending = QCASPI_RX_MAX_FRAMES;
 	ring->tx_pending = qca->txr.count;
 }
 
@@ -265,7 +267,7 @@ qcaspi_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring,
 {
 	struct qcaspi *qca = netdev_priv(dev);
 
-	if ((ring->rx_pending) ||
+	if (ring->rx_pending != QCASPI_RX_MAX_FRAMES ||
 	    (ring->rx_mini_pending) ||
 	    (ring->rx_jumbo_pending))
 		return -EINVAL;
-- 
cgit v1.2.3


From 1057812d146dd658c9a9a96d869c2551150207b5 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Wed, 6 Dec 2023 15:12:22 +0100
Subject: qca_spi: Fix reset behavior

In case of a reset triggered by the QCA7000 itself, the behavior of the
qca_spi driver was not quite correct:
- in case of a pending RX frame decoding the drop counter must be
  incremented and decoding state machine reseted
- also the reset counter must always be incremented regardless of sync
  state

Fixes: 291ab06ecf67 ("net: qualcomm: new Ethernet over SPI driver for QCA7000")
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Link: https://lore.kernel.org/r/20231206141222.52029-4-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qualcomm/qca_spi.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index b0fad69bb755..5f3c11fb3fa2 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -620,11 +620,17 @@ qcaspi_spi_thread(void *data)
 			if (intr_cause & SPI_INT_CPU_ON) {
 				qcaspi_qca7k_sync(qca, QCASPI_EVENT_CPUON);
 
+				/* Frame decoding in progress */
+				if (qca->frm_handle.state != qca->frm_handle.init)
+					qca->net_dev->stats.rx_dropped++;
+
+				qcafrm_fsm_init_spi(&qca->frm_handle);
+				qca->stats.device_reset++;
+
 				/* not synced. */
 				if (qca->sync != QCASPI_SYNC_READY)
 					continue;
 
-				qca->stats.device_reset++;
 				netif_wake_queue(qca->net_dev);
 				netif_carrier_on(qca->net_dev);
 			}
-- 
cgit v1.2.3


From a45f1e46274256852990c479fbb1198a7d84529b Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Thu, 7 Dec 2023 21:23:58 +0100
Subject: MAINTAINERS: remove myself as maintainer of SMC

I changed responsibilities some time ago, its time
to remove myself as maintainer of the SMC component.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Wenjia Zhang <wenjia@linux.ibm.com>
Link: https://lore.kernel.org/r/20231207202358.53502-1-wenjia@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index a0fb0df07b43..c17c66810598 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19638,7 +19638,6 @@ S:	Maintained
 F:	drivers/misc/sgi-xp/
 
 SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
-M:	Karsten Graul <kgraul@linux.ibm.com>
 M:	Wenjia Zhang <wenjia@linux.ibm.com>
 M:	Jan Karcher <jaka@linux.ibm.com>
 R:	D. Wythe <alibuda@linux.alibaba.com>
-- 
cgit v1.2.3


From 9c25aae0132b8babbe71ebb2160186d69231d9b3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 7 Dec 2023 18:13:42 +0000
Subject: tcp: fix tcp_disordered_ack() vs usec TS resolution

After commit 939463016b7a ("tcp: change data receiver flowlabel after one dup")
we noticed an increase of TCPACKSkippedPAWS events.

Neal Cardwell tracked the issue to tcp_disordered_ack() assumption
about remote peer TS clock.

RFC 1323 & 7323 are suggesting the following:
  "timestamp clock frequency in the range 1 ms to 1 sec per tick
   between 1ms and 1sec."

This has to be adjusted for 1 MHz clock frequency.

This hints at reorders of SACK packets on send side,
this might deserve a future patch.
(skb->ooo_okay is always set for pure ACK packets)

Fixes: 614e8316aa4c ("tcp: add support for usec resolution in TCP TS values")
Co-developed-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Morley <morleyd@google.com>
Link: https://lore.kernel.org/r/20231207181342.525181-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_input.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 90de838a2745..701cb87043f2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4368,6 +4368,23 @@ EXPORT_SYMBOL(tcp_do_parse_auth_options);
  * up to bandwidth of 18Gigabit/sec. 8) ]
  */
 
+/* Estimates max number of increments of remote peer TSval in
+ * a replay window (based on our current RTO estimation).
+ */
+static u32 tcp_tsval_replay(const struct sock *sk)
+{
+	/* If we use usec TS resolution,
+	 * then expect the remote peer to use the same resolution.
+	 */
+	if (tcp_sk(sk)->tcp_usec_ts)
+		return inet_csk(sk)->icsk_rto * (USEC_PER_SEC / HZ);
+
+	/* RFC 7323 recommends a TSval clock between 1ms and 1sec.
+	 * We know that some OS (including old linux) can use 1200 Hz.
+	 */
+	return inet_csk(sk)->icsk_rto * 1200 / HZ;
+}
+
 static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -4375,7 +4392,7 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
 	u32 seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 
-	return (/* 1. Pure ACK with correct sequence number. */
+	return	/* 1. Pure ACK with correct sequence number. */
 		(th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) &&
 
 		/* 2. ... and duplicate ACK. */
@@ -4385,7 +4402,8 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
 		!tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) &&
 
 		/* 4. ... and sits in replay window. */
-		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ);
+		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <=
+		tcp_tsval_replay(sk);
 }
 
 static inline bool tcp_paws_discard(const struct sock *sk,
-- 
cgit v1.2.3


From 9ef7c58f5abe41e6d91f37f28fe2d851ffedd92a Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Thu, 7 Dec 2023 16:16:55 -0800
Subject: bnxt_en: Clear resource reservation during resume

We are issuing HWRM_FUNC_RESET cmd to reset the device including
all reserved resources, but not clearing the reservations
within the driver struct. As a result, when the driver re-initializes
as part of resume, it believes that there is no need to do any
resource reservation and goes ahead and tries to allocate rings
which will eventually fail beyond a certain number pre-reserved by
the firmware.

Fixes: 674f50a5b026 ("bnxt_en: Implement new method to reserve rings.")
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20231208001658.14230-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d0359b569afe..72f2fc983940 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -13940,6 +13940,8 @@ static int bnxt_resume(struct device *device)
 	if (rc)
 		goto resume_exit;
 
+	bnxt_clear_reservations(bp, true);
+
 	if (bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, false)) {
 		rc = -ENODEV;
 		goto resume_exit;
-- 
cgit v1.2.3


From aded5d1feb08e48d544845d3594d70c4d5fe6e54 Mon Sep 17 00:00:00 2001
From: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Date: Thu, 7 Dec 2023 16:16:56 -0800
Subject: bnxt_en: Fix skb recycling logic in bnxt_deliver_skb()

Receive SKBs can go through the VF-rep path or the normal path.
skb_mark_for_recycle() is only called for the normal path.  Fix it
to do it for both paths to fix possible stalled page pool shutdown
errors.

Fixes: 86b05508f775 ("bnxt_en: Use the unified RX page pool buffers for XDP and non-XDP")
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Vikas Gupta <vikas.gupta@broadcom.com>
Signed-off-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20231208001658.14230-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 72f2fc983940..b4a5311bdeb5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1748,13 +1748,14 @@ static void bnxt_tpa_agg(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi,
 			     struct sk_buff *skb)
 {
+	skb_mark_for_recycle(skb);
+
 	if (skb->dev != bp->dev) {
 		/* this packet belongs to a vf-rep */
 		bnxt_vf_rep_rx(bp, skb);
 		return;
 	}
 	skb_record_rx_queue(skb, bnapi->index);
-	skb_mark_for_recycle(skb);
 	napi_gro_receive(&bnapi->napi, skb);
 }
 
-- 
cgit v1.2.3


From bd6781c18cb5b5e5d8c5873fa9a51668e89ec76e Mon Sep 17 00:00:00 2001
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date: Thu, 7 Dec 2023 16:16:57 -0800
Subject: bnxt_en: Fix wrong return value check in bnxt_close_nic()

The wait_event_interruptible_timeout() function returns 0
if the timeout elapsed, -ERESTARTSYS if it was interrupted
by a signal, and the remaining jiffies otherwise if the
condition evaluated to true before the timeout elapsed.

Driver should have checked for zero return value instead of
a positive value.

MChan: Print a warning for -ERESTARTSYS.  The close operation
will proceed anyway when wait_event_interruptible_timeout()
returns for any reason.  Since we do the close no matter what,
we should not return this error code to the caller.  Change
bnxt_close_nic() to a void function and remove all error
handling from some of the callers.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Vikas Gupta <vikas.gupta@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20231208001658.14230-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 13 +++++++------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 11 ++---------
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 19 ++++---------------
 drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c     |  5 ++---
 5 files changed, 16 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b4a5311bdeb5..aa1f5b776b5a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10732,10 +10732,8 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_free_mem(bp, irq_re_init);
 }
 
-int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
+void bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
-	int rc = 0;
-
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		/* If we get here, it means firmware reset is in progress
 		 * while we are trying to close.  We can safely proceed with
@@ -10750,15 +10748,18 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 
 #ifdef CONFIG_BNXT_SRIOV
 	if (bp->sriov_cfg) {
+		int rc;
+
 		rc = wait_event_interruptible_timeout(bp->sriov_cfg_wait,
 						      !bp->sriov_cfg,
 						      BNXT_SRIOV_CFG_WAIT_TMO);
-		if (rc)
-			netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete!\n");
+		if (!rc)
+			netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete, proceeding to close!\n");
+		else if (rc < 0)
+			netdev_warn(bp->dev, "SRIOV config operation interrupted, proceeding to close!\n");
 	}
 #endif
 	__bnxt_close_nic(bp, irq_re_init, link_re_init);
-	return rc;
 }
 
 static int bnxt_close(struct net_device *dev)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index e702dbc3e6b1..0488b0466015 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2375,7 +2375,7 @@ int bnxt_open_nic(struct bnxt *, bool, bool);
 int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
 void bnxt_reenable_sriov(struct bnxt *bp);
-int bnxt_close_nic(struct bnxt *, bool, bool);
+void bnxt_close_nic(struct bnxt *, bool, bool);
 void bnxt_get_ring_err_stats(struct bnxt *bp,
 			     struct bnxt_total_ring_err_stats *stats);
 int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index f302dac56599..89809f1b129c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -449,15 +449,8 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 			return -ENODEV;
 		}
 		bnxt_ulp_stop(bp);
-		if (netif_running(bp->dev)) {
-			rc = bnxt_close_nic(bp, true, true);
-			if (rc) {
-				NL_SET_ERR_MSG_MOD(extack, "Failed to close");
-				dev_close(bp->dev);
-				rtnl_unlock();
-				break;
-			}
-		}
+		if (netif_running(bp->dev))
+			bnxt_close_nic(bp, true, true);
 		bnxt_vf_reps_free(bp);
 		rc = bnxt_hwrm_func_drv_unrgtr(bp);
 		if (rc) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index f3f384773ac0..5f67a7f94e7d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -165,9 +165,8 @@ static int bnxt_set_coalesce(struct net_device *dev,
 reset_coalesce:
 	if (test_bit(BNXT_STATE_OPEN, &bp->state)) {
 		if (update_stats) {
-			rc = bnxt_close_nic(bp, true, false);
-			if (!rc)
-				rc = bnxt_open_nic(bp, true, false);
+			bnxt_close_nic(bp, true, false);
+			rc = bnxt_open_nic(bp, true, false);
 		} else {
 			rc = bnxt_hwrm_set_coal(bp);
 		}
@@ -972,12 +971,7 @@ static int bnxt_set_channels(struct net_device *dev,
 			 * before PF unload
 			 */
 		}
-		rc = bnxt_close_nic(bp, true, false);
-		if (rc) {
-			netdev_err(bp->dev, "Set channel failure rc :%x\n",
-				   rc);
-			return rc;
-		}
+		bnxt_close_nic(bp, true, false);
 	}
 
 	if (sh) {
@@ -4042,12 +4036,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		bnxt_run_fw_tests(bp, test_mask, &test_results);
 	} else {
 		bnxt_ulp_stop(bp);
-		rc = bnxt_close_nic(bp, true, false);
-		if (rc) {
-			etest->flags |= ETH_TEST_FL_FAILED;
-			bnxt_ulp_start(bp, rc);
-			return;
-		}
+		bnxt_close_nic(bp, true, false);
 		bnxt_run_fw_tests(bp, test_mask, &test_results);
 
 		buf[BNXT_MACLPBK_TEST_IDX] = 1;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index f3886710e778..6e3da3362bd6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -521,9 +521,8 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp)
 
 	if (netif_running(bp->dev)) {
 		if (ptp->rx_filter == HWTSTAMP_FILTER_ALL) {
-			rc = bnxt_close_nic(bp, false, false);
-			if (!rc)
-				rc = bnxt_open_nic(bp, false, false);
+			bnxt_close_nic(bp, false, false);
+			rc = bnxt_open_nic(bp, false, false);
 		} else {
 			bnxt_ptp_cfg_tstamp_filters(bp);
 		}
-- 
cgit v1.2.3


From c13e268c0768659cdaae4bfe2fb24860bcc8ddb4 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Thu, 7 Dec 2023 16:16:58 -0800
Subject: bnxt_en: Fix HWTSTAMP_FILTER_ALL packet timestamp logic

When the chip is configured to timestamp all receive packets, the
timestamp in the RX completion is only valid if the metadata
present flag is not set for packets received on the wire.  In
addition, internal loopback packets will never have a valid timestamp
and the timestamp field will always be zero.  We must exclude
any 0 value in the timestamp field because there is no way to
determine if it is a loopback packet or not.

Add a new function bnxt_rx_ts_valid() to check for all timestamp
valid conditions.

Fixes: 66ed81dcedc6 ("bnxt_en: Enable packet timestamping for all RX packets")
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://lore.kernel.org/r/20231208001658.14230-5-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 20 +++++++++++++++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  8 +++++++-
 2 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index aa1f5b776b5a..579eebb6fc56 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1759,6 +1759,21 @@ static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi,
 	napi_gro_receive(&bnapi->napi, skb);
 }
 
+static bool bnxt_rx_ts_valid(struct bnxt *bp, u32 flags,
+			     struct rx_cmp_ext *rxcmp1, u32 *cmpl_ts)
+{
+	u32 ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp);
+
+	if (BNXT_PTP_RX_TS_VALID(flags))
+		goto ts_valid;
+	if (!bp->ptp_all_rx_tstamp || !ts || !BNXT_ALL_RX_TS_VALID(flags))
+		return false;
+
+ts_valid:
+	*cmpl_ts = ts;
+	return true;
+}
+
 /* returns the following:
  * 1       - 1 packet successfully received
  * 0       - successful TPA_START, packet not completed yet
@@ -1784,6 +1799,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct sk_buff *skb;
 	struct xdp_buff xdp;
 	u32 flags, misc;
+	u32 cmpl_ts;
 	void *data;
 	int rc = 0;
 
@@ -2006,10 +2022,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		}
 	}
 
-	if (unlikely((flags & RX_CMP_FLAGS_ITYPES_MASK) ==
-		     RX_CMP_FLAGS_ITYPE_PTP_W_TS) || bp->ptp_all_rx_tstamp) {
+	if (bnxt_rx_ts_valid(bp, flags, rxcmp1, &cmpl_ts)) {
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
-			u32 cmpl_ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp);
 			u64 ns, ts;
 
 			if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 0488b0466015..a7d7b09ea162 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -161,7 +161,7 @@ struct rx_cmp {
 	#define RX_CMP_FLAGS_ERROR				(1 << 6)
 	#define RX_CMP_FLAGS_PLACEMENT				(7 << 7)
 	#define RX_CMP_FLAGS_RSS_VALID				(1 << 10)
-	#define RX_CMP_FLAGS_UNUSED				(1 << 11)
+	#define RX_CMP_FLAGS_PKT_METADATA_PRESENT		(1 << 11)
 	 #define RX_CMP_FLAGS_ITYPES_SHIFT			 12
 	 #define RX_CMP_FLAGS_ITYPES_MASK			 0xf000
 	 #define RX_CMP_FLAGS_ITYPE_UNKNOWN			 (0 << 12)
@@ -188,6 +188,12 @@ struct rx_cmp {
 	__le32 rx_cmp_rss_hash;
 };
 
+#define BNXT_PTP_RX_TS_VALID(flags)				\
+	(((flags) & RX_CMP_FLAGS_ITYPES_MASK) == RX_CMP_FLAGS_ITYPE_PTP_W_TS)
+
+#define BNXT_ALL_RX_TS_VALID(flags)				\
+	!((flags) & RX_CMP_FLAGS_PKT_METADATA_PRESENT)
+
 #define RX_CMP_HASH_VALID(rxcmp)				\
 	((rxcmp)->rx_cmp_len_flags_type & cpu_to_le32(RX_CMP_FLAGS_RSS_VALID))
 
-- 
cgit v1.2.3


From d5dba32b8f6cb39be708b726044ba30dbc088b30 Mon Sep 17 00:00:00 2001
From: Chengfeng Ye <dg573847474@gmail.com>
Date: Thu, 7 Dec 2023 12:34:37 +0000
Subject: atm: solos-pci: Fix potential deadlock on &cli_queue_lock

As &card->cli_queue_lock is acquired under softirq context along the
following call chain from solos_bh(), other acquisition of the same
lock inside process context should disable at least bh to avoid double
lock.

<deadlock #1>
console_show()
--> spin_lock(&card->cli_queue_lock)
<interrupt>
   --> solos_bh()
   --> spin_lock(&card->cli_queue_lock)

This flaw was found by an experimental static analysis tool I am
developing for irq-related deadlock.

To prevent the potential deadlock, the patch uses spin_lock_bh()
on the card->cli_queue_lock under process context code consistently
to prevent the possible deadlock scenario.

Fixes: 9c54004ea717 ("atm: Driver for Solos PCI ADSL2+ card.")
Signed-off-by: Chengfeng Ye <dg573847474@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/solos-pci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index 94fbc3abe60e..95f768b28a5e 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -449,9 +449,9 @@ static ssize_t console_show(struct device *dev, struct device_attribute *attr,
 	struct sk_buff *skb;
 	unsigned int len;
 
-	spin_lock(&card->cli_queue_lock);
+	spin_lock_bh(&card->cli_queue_lock);
 	skb = skb_dequeue(&card->cli_queue[SOLOS_CHAN(atmdev)]);
-	spin_unlock(&card->cli_queue_lock);
+	spin_unlock_bh(&card->cli_queue_lock);
 	if(skb == NULL)
 		return sprintf(buf, "No data.\n");
 
-- 
cgit v1.2.3


From 15319a4e8ee4b098118591c6ccbd17237f841613 Mon Sep 17 00:00:00 2001
From: Chengfeng Ye <dg573847474@gmail.com>
Date: Thu, 7 Dec 2023 12:34:53 +0000
Subject: atm: solos-pci: Fix potential deadlock on &tx_queue_lock

As &card->tx_queue_lock is acquired under softirq context along the
following call chain from solos_bh(), other acquisition of the same
lock inside process context should disable at least bh to avoid double
lock.

<deadlock #2>
pclose()
--> spin_lock(&card->tx_queue_lock)
<interrupt>
   --> solos_bh()
   --> fpga_tx()
   --> spin_lock(&card->tx_queue_lock)

This flaw was found by an experimental static analysis tool I am
developing for irq-related deadlock.

To prevent the potential deadlock, the patch uses spin_lock_bh()
on &card->tx_queue_lock under process context code consistently to
prevent the possible deadlock scenario.

Fixes: 213e85d38912 ("solos-pci: clean up pclose() function")
Signed-off-by: Chengfeng Ye <dg573847474@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/solos-pci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index 95f768b28a5e..d3c30a28c410 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -956,14 +956,14 @@ static void pclose(struct atm_vcc *vcc)
 	struct pkt_hdr *header;
 
 	/* Remove any yet-to-be-transmitted packets from the pending queue */
-	spin_lock(&card->tx_queue_lock);
+	spin_lock_bh(&card->tx_queue_lock);
 	skb_queue_walk_safe(&card->tx_queue[port], skb, tmpskb) {
 		if (SKB_CB(skb)->vcc == vcc) {
 			skb_unlink(skb, &card->tx_queue[port]);
 			solos_pop(vcc, skb);
 		}
 	}
-	spin_unlock(&card->tx_queue_lock);
+	spin_unlock_bh(&card->tx_queue_lock);
 
 	skb = alloc_skb(sizeof(*header), GFP_KERNEL);
 	if (!skb) {
-- 
cgit v1.2.3


From 69db702c83874fbaa2a51af761e35a8e5a593b95 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 6 Dec 2023 13:55:19 +0000
Subject: io_uring/af_unix: disable sending io_uring over sockets

File reference cycles have caused lots of problems for io_uring
in the past, and it still doesn't work exactly right and races with
unix_stream_read_generic(). The safest fix would be to completely
disallow sending io_uring files via sockets via SCM_RIGHT, so there
are no possible cycles invloving registered files and thus rendering
SCM accounting on the io_uring side unnecessary.

Cc: stable@vger.kernel.org
Fixes: 0091bfc81741b ("io_uring/af_unix: defer registered files gc to io_uring release")
Reported-and-suggested-by: Jann Horn <jannh@google.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 io_uring/rsrc.h | 7 -------
 net/core/scm.c  | 6 ++++++
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 8625181fb87a..08ac0d8e07ef 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -77,17 +77,10 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 
 int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file);
 
-#if defined(CONFIG_UNIX)
-static inline bool io_file_need_scm(struct file *filp)
-{
-	return !!unix_get_socket(filp);
-}
-#else
 static inline bool io_file_need_scm(struct file *filp)
 {
 	return false;
 }
-#endif
 
 static inline int io_scm_file_account(struct io_ring_ctx *ctx,
 				      struct file *file)
diff --git a/net/core/scm.c b/net/core/scm.c
index 880027ecf516..7dc47c17d863 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -26,6 +26,7 @@
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/errqueue.h>
+#include <linux/io_uring.h>
 
 #include <linux/uaccess.h>
 
@@ -103,6 +104,11 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
 
 		if (fd < 0 || !(file = fget_raw(fd)))
 			return -EBADF;
+		/* don't allow io_uring files */
+		if (io_uring_get_socket(file)) {
+			fput(file);
+			return -EINVAL;
+		}
 		*fpp++ = file;
 		fpl->count++;
 	}
-- 
cgit v1.2.3


From 9fc95fe95c3e2a63ced8eeca4b256518ab204b63 Mon Sep 17 00:00:00 2001
From: Radu Bulie <radu-andrei.bulie@nxp.com>
Date: Thu, 7 Dec 2023 16:38:01 +0800
Subject: net: fec: correct queue selection

The old implementation extracted VLAN TCI info from the payload
before the VLAN tag has been pushed in the payload.

Another problem was that the VLAN TCI was extracted even if the
packet did not have VLAN protocol header.

This resulted in invalid VLAN TCI and as a consequence a random
queue was computed.

This patch fixes the above issues and use the VLAN TCI from the
skb if it is present or VLAN TCI from payload if present. If no
VLAN header is present queue 0 is selected.

Fixes: 52c4a1a85f4b ("net: fec: add ndo_select_queue to fix TX bandwidth fluctuations")
Signed-off-by: Radu Bulie <radu-andrei.bulie@nxp.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c3b7694a7485..e08c7b572497 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3731,31 +3731,26 @@ static int fec_set_features(struct net_device *netdev,
 	return 0;
 }
 
-static u16 fec_enet_get_raw_vlan_tci(struct sk_buff *skb)
-{
-	struct vlan_ethhdr *vhdr;
-	unsigned short vlan_TCI = 0;
-
-	if (skb->protocol == htons(ETH_P_ALL)) {
-		vhdr = (struct vlan_ethhdr *)(skb->data);
-		vlan_TCI = ntohs(vhdr->h_vlan_TCI);
-	}
-
-	return vlan_TCI;
-}
-
 static u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb,
 				 struct net_device *sb_dev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	u16 vlan_tag;
+	u16 vlan_tag = 0;
 
 	if (!(fep->quirks & FEC_QUIRK_HAS_AVB))
 		return netdev_pick_tx(ndev, skb, NULL);
 
-	vlan_tag = fec_enet_get_raw_vlan_tci(skb);
-	if (!vlan_tag)
+	/* VLAN is present in the payload.*/
+	if (eth_type_vlan(skb->protocol)) {
+		struct vlan_ethhdr *vhdr = skb_vlan_eth_hdr(skb);
+
+		vlan_tag = ntohs(vhdr->h_vlan_TCI);
+	/*  VLAN is present in the skb but not yet pushed in the payload.*/
+	} else if (skb_vlan_tag_present(skb)) {
+		vlan_tag = skb->vlan_tci;
+	} else {
 		return vlan_tag;
+	}
 
 	return fec_enet_vlan_pri_to_queue[vlan_tag >> 13];
 }
-- 
cgit v1.2.3


From 28a7cb045ab700de5554193a1642917602787784 Mon Sep 17 00:00:00 2001
From: Zhipeng Lu <alexious@zju.edu.cn>
Date: Thu, 7 Dec 2023 17:49:16 +0800
Subject: octeontx2-af: fix a use-after-free in rvu_nix_register_reporters

The rvu_dl will be freed in rvu_nix_health_reporters_destroy(rvu_dl)
after the create_workqueue fails, and after that free, the rvu_dl will
be translate back through the following call chain:

rvu_nix_health_reporters_destroy
  |-> rvu_nix_health_reporters_create
       |-> rvu_health_reporters_create
             |-> rvu_register_dl (label err_dl_health)

Finally. in the err_dl_health label, rvu_dl being freed again in
rvu_health_reporters_destroy(rvu) by rvu_nix_health_reporters_destroy.
In the second calls of rvu_nix_health_reporters_destroy, however,
it uses rvu_dl->rvu_nix_health_reporter, which is already freed at
the end of rvu_nix_health_reporters_destroy in the first call.

So this patch prevents the first destroy by instantly returning -ENONMEN
when create_workqueue fails. In addition, since the failure of
create_workqueue is the only entrence of label err, it has been
integrated into the error-handling path of create_workqueue.

Fixes: 5ed66306eab6 ("octeontx2-af: Add devlink health reporters for NIX")
Signed-off-by: Zhipeng Lu <alexious@zju.edu.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index 62780d8b4f9a..21b5d71c1e37 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -538,7 +538,7 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl)
 
 	rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq");
 	if (!rvu_dl->devlink_wq)
-		goto err;
+		return -ENOMEM;
 
 	INIT_WORK(&rvu_reporters->intr_work, rvu_nix_intr_work);
 	INIT_WORK(&rvu_reporters->gen_work, rvu_nix_gen_work);
@@ -546,9 +546,6 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl)
 	INIT_WORK(&rvu_reporters->ras_work, rvu_nix_ras_work);
 
 	return 0;
-err:
-	rvu_nix_health_reporters_destroy(rvu_dl);
-	return -ENOMEM;
 }
 
 static int rvu_nix_health_reporters_create(struct rvu_devlink *rvu_dl)
-- 
cgit v1.2.3


From 125f1c7f26ffcdbf96177abe75b70c1a6ceb17bc Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Tue, 5 Dec 2023 18:25:54 +0100
Subject: net/sched: act_ct: Take per-cb reference to tcf_ct_flow_table

The referenced change added custom cleanup code to act_ct to delete any
callbacks registered on the parent block when deleting the
tcf_ct_flow_table instance. However, the underlying issue is that the
drivers don't obtain the reference to the tcf_ct_flow_table instance when
registering callbacks which means that not only driver callbacks may still
be on the table when deleting it but also that the driver can still have
pointers to its internal nf_flowtable and can use it concurrently which
results either warning in netfilter[0] or use-after-free.

Fix the issue by taking a reference to the underlying struct
tcf_ct_flow_table instance when registering the callback and release the
reference when unregistering. Expose new API required for such reference
counting by adding two new callbacks to nf_flowtable_type and implementing
them for act_ct flowtable_ct type. This fixes the issue by extending the
lifetime of nf_flowtable until all users have unregistered.

[0]:
[106170.938634] ------------[ cut here ]------------
[106170.939111] WARNING: CPU: 21 PID: 3688 at include/net/netfilter/nf_flow_table.h:262 mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.940108] Modules linked in: act_ct nf_flow_table act_mirred act_skbedit act_tunnel_key vxlan cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress mlx5_vdpa vringh vhost_iotlb vdpa bonding openvswitch nsh rpcrdma rdma_ucm
ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core xt_MASQUERADE nf_conntrack_netlink nfnetlink iptable_nat xt_addrtype xt_conntrack nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_regis
try overlay mlx5_core
[106170.943496] CPU: 21 PID: 3688 Comm: kworker/u48:0 Not tainted 6.6.0-rc7_for_upstream_min_debug_2023_11_01_13_02 #1
[106170.944361] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[106170.945292] Workqueue: mlx5e mlx5e_rep_neigh_update [mlx5_core]
[106170.945846] RIP: 0010:mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.946413] Code: 89 ef 48 83 05 71 a4 14 00 01 e8 f4 06 04 e1 48 83 05 6c a4 14 00 01 48 83 c4 28 5b 5d 41 5c 41 5d c3 48 83 05 d1 8b 14 00 01 <0f> 0b 48 83 05 d7 8b 14 00 01 e9 96 fe ff ff 48 83 05 a2 90 14 00
[106170.947924] RSP: 0018:ffff88813ff0fcb8 EFLAGS: 00010202
[106170.948397] RAX: 0000000000000000 RBX: ffff88811eabac40 RCX: ffff88811eabad48
[106170.949040] RDX: ffff88811eab8000 RSI: ffffffffa02cd560 RDI: 0000000000000000
[106170.949679] RBP: ffff88811eab8000 R08: 0000000000000001 R09: ffffffffa0229700
[106170.950317] R10: ffff888103538fc0 R11: 0000000000000001 R12: ffff88811eabad58
[106170.950969] R13: ffff888110c01c00 R14: ffff888106b40000 R15: 0000000000000000
[106170.951616] FS:  0000000000000000(0000) GS:ffff88885fd40000(0000) knlGS:0000000000000000
[106170.952329] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[106170.952834] CR2: 00007f1cefd28cb0 CR3: 000000012181b006 CR4: 0000000000370ea0
[106170.953482] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[106170.954121] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[106170.954766] Call Trace:
[106170.955057]  <TASK>
[106170.955315]  ? __warn+0x79/0x120
[106170.955648]  ? mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.956172]  ? report_bug+0x17c/0x190
[106170.956537]  ? handle_bug+0x3c/0x60
[106170.956891]  ? exc_invalid_op+0x14/0x70
[106170.957264]  ? asm_exc_invalid_op+0x16/0x20
[106170.957666]  ? mlx5_del_flow_rules+0x10/0x310 [mlx5_core]
[106170.958172]  ? mlx5_tc_ct_block_flow_offload_add+0x1240/0x1240 [mlx5_core]
[106170.958788]  ? mlx5_tc_ct_del_ft_cb+0x267/0x2b0 [mlx5_core]
[106170.959339]  ? mlx5_tc_ct_del_ft_cb+0xc6/0x2b0 [mlx5_core]
[106170.959854]  ? mapping_remove+0x154/0x1d0 [mlx5_core]
[106170.960342]  ? mlx5e_tc_action_miss_mapping_put+0x4f/0x80 [mlx5_core]
[106170.960927]  mlx5_tc_ct_delete_flow+0x76/0xc0 [mlx5_core]
[106170.961441]  mlx5_free_flow_attr_actions+0x13b/0x220 [mlx5_core]
[106170.962001]  mlx5e_tc_del_fdb_flow+0x22c/0x3b0 [mlx5_core]
[106170.962524]  mlx5e_tc_del_flow+0x95/0x3c0 [mlx5_core]
[106170.963034]  mlx5e_flow_put+0x73/0xe0 [mlx5_core]
[106170.963506]  mlx5e_put_flow_list+0x38/0x70 [mlx5_core]
[106170.964002]  mlx5e_rep_update_flows+0xec/0x290 [mlx5_core]
[106170.964525]  mlx5e_rep_neigh_update+0x1da/0x310 [mlx5_core]
[106170.965056]  process_one_work+0x13a/0x2c0
[106170.965443]  worker_thread+0x2e5/0x3f0
[106170.965808]  ? rescuer_thread+0x410/0x410
[106170.966192]  kthread+0xc6/0xf0
[106170.966515]  ? kthread_complete_and_exit+0x20/0x20
[106170.966970]  ret_from_fork+0x2d/0x50
[106170.967332]  ? kthread_complete_and_exit+0x20/0x20
[106170.967774]  ret_from_fork_asm+0x11/0x20
[106170.970466]  </TASK>
[106170.970726] ---[ end trace 0000000000000000 ]---

Fixes: 77ac5e40c44e ("net/sched: act_ct: remove and free nf_table callbacks")
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Paul Blakey <paulb@nvidia.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netfilter/nf_flow_table.h | 10 ++++++++++
 net/sched/act_ct.c                    | 34 ++++++++++++++++++++++++++++------
 2 files changed, 38 insertions(+), 6 deletions(-)

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index fe1507c1db82..692d5955911c 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -62,6 +62,8 @@ struct nf_flowtable_type {
 						  enum flow_offload_tuple_dir dir,
 						  struct nf_flow_rule *flow_rule);
 	void				(*free)(struct nf_flowtable *ft);
+	void				(*get)(struct nf_flowtable *ft);
+	void				(*put)(struct nf_flowtable *ft);
 	nf_hookfn			*hook;
 	struct module			*owner;
 };
@@ -240,6 +242,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
 	}
 
 	list_add_tail(&block_cb->list, &block->cb_list);
+	up_write(&flow_table->flow_block_lock);
+
+	if (flow_table->type->get)
+		flow_table->type->get(flow_table);
+	return 0;
 
 unlock:
 	up_write(&flow_table->flow_block_lock);
@@ -262,6 +269,9 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
 		WARN_ON(true);
 	}
 	up_write(&flow_table->flow_block_lock);
+
+	if (flow_table->type->put)
+		flow_table->type->put(flow_table);
 }
 
 void flow_offload_route_init(struct flow_offload *flow,
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index b3f4a503ee2b..f69c47945175 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -286,9 +286,31 @@ static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow)
 	       !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags);
 }
 
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_get(struct nf_flowtable *ft)
+{
+	struct tcf_ct_flow_table *ct_ft =
+		container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+	tcf_ct_flow_table_get_ref(ct_ft);
+}
+
+static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft);
+
+static void tcf_ct_nf_put(struct nf_flowtable *ft)
+{
+	struct tcf_ct_flow_table *ct_ft =
+		container_of(ft, struct tcf_ct_flow_table, nf_ft);
+
+	tcf_ct_flow_table_put(ct_ft);
+}
+
 static struct nf_flowtable_type flowtable_ct = {
 	.gc		= tcf_ct_flow_is_outdated,
 	.action		= tcf_ct_flow_table_fill_actions,
+	.get		= tcf_ct_nf_get,
+	.put		= tcf_ct_nf_put,
 	.owner		= THIS_MODULE,
 };
 
@@ -337,9 +359,13 @@ err_alloc:
 	return err;
 }
 
+static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft)
+{
+	refcount_inc(&ct_ft->ref);
+}
+
 static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 {
-	struct flow_block_cb *block_cb, *tmp_cb;
 	struct tcf_ct_flow_table *ct_ft;
 	struct flow_block *block;
 
@@ -347,13 +373,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
 			     rwork);
 	nf_flow_table_free(&ct_ft->nf_ft);
 
-	/* Remove any remaining callbacks before cleanup */
 	block = &ct_ft->nf_ft.flow_block;
 	down_write(&ct_ft->nf_ft.flow_block_lock);
-	list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
-		list_del(&block_cb->list);
-		flow_block_cb_free(block_cb);
-	}
+	WARN_ON(!list_empty(&block->cb_list));
 	up_write(&ct_ft->nf_ft.flow_block_lock);
 	kfree(ct_ft);
 
-- 
cgit v1.2.3


From 284f717622417cb267e344a9174f8e5698d1e3c1 Mon Sep 17 00:00:00 2001
From: Shinas Rasheed <srasheed@marvell.com>
Date: Thu, 7 Dec 2023 21:56:46 -0800
Subject: octeon_ep: explicitly test for firmware ready value

The firmware ready value is 1, and get firmware ready status
function should explicitly test for that value. The firmware
ready value read will be 2 after driver load, and on unbind
till firmware rewrites the firmware ready back to 0, the value
seen by driver will be 2, which should be regarded as not ready.

Fixes: 10c073e40469 ("octeon_ep: defer probe if firmware not ready")
Signed-off-by: Shinas Rasheed <srasheed@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeon_ep/octep_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index a2b5a3f8df93..a9bdf3283a85 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -1265,7 +1265,8 @@ static bool get_fw_ready_status(struct pci_dev *pdev)
 
 		pci_read_config_byte(pdev, (pos + 8), &status);
 		dev_info(&pdev->dev, "Firmware ready status = %u\n", status);
-		return status;
+#define FW_STATUS_READY 1ULL
+		return status == FW_STATUS_READY;
 	}
 	return false;
 }
-- 
cgit v1.2.3


From dbda436824ded8ef6a05bb82cd9baa8d42377a49 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 8 Dec 2023 12:26:09 +0530
Subject: octeontx2-pf: Fix promisc mcam entry action

Current implementation is such that, promisc mcam entry action
is set as multicast even when there are no trusted VFs. multicast
action causes the hardware to copy packet data, which reduces
the performance.

This patch fixes this issue by setting the promisc mcam entry action to
unicast instead of multicast when there are no trusted VFs. The same
change is made for the 'allmulti' mcam entry action.

Fixes: ffd2f89ad05c ("octeontx2-pf: Enable promisc/allmulti match MCAM entries.")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/octeontx2/nic/otx2_pf.c   | 25 +++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 0c17ebdda148..a57455aebff6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1650,6 +1650,21 @@ static void otx2_free_hw_resources(struct otx2_nic *pf)
 	mutex_unlock(&mbox->lock);
 }
 
+static bool otx2_promisc_use_mce_list(struct otx2_nic *pfvf)
+{
+	int vf;
+
+	/* The AF driver will determine whether to allow the VF netdev or not */
+	if (is_otx2_vf(pfvf->pcifunc))
+		return true;
+
+	/* check if there are any trusted VFs associated with the PF netdev */
+	for (vf = 0; vf < pci_num_vf(pfvf->pdev); vf++)
+		if (pfvf->vf_configs[vf].trusted)
+			return true;
+	return false;
+}
+
 static void otx2_do_set_rx_mode(struct otx2_nic *pf)
 {
 	struct net_device *netdev = pf->netdev;
@@ -1682,7 +1697,8 @@ static void otx2_do_set_rx_mode(struct otx2_nic *pf)
 	if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST))
 		req->mode |= NIX_RX_MODE_ALLMULTI;
 
-	req->mode |= NIX_RX_MODE_USE_MCE;
+	if (otx2_promisc_use_mce_list(pf))
+		req->mode |= NIX_RX_MODE_USE_MCE;
 
 	otx2_sync_mbox_msg(&pf->mbox);
 	mutex_unlock(&pf->mbox.lock);
@@ -2691,11 +2707,14 @@ static int otx2_ndo_set_vf_trust(struct net_device *netdev, int vf,
 	pf->vf_configs[vf].trusted = enable;
 	rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF);
 
-	if (rc)
+	if (rc) {
 		pf->vf_configs[vf].trusted = !enable;
-	else
+	} else {
 		netdev_info(pf->netdev, "VF %d is %strusted\n",
 			    vf, enable ? "" : "not ");
+		otx2_set_rx_mode(netdev);
+	}
+
 	return rc;
 }
 
-- 
cgit v1.2.3


From 570ba37898ecd9069beb58bf0b6cf84daba6e0fe Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 8 Dec 2023 12:26:10 +0530
Subject: octeontx2-af: Update RSS algorithm index

The RSS flow algorithm is not set up correctly for promiscuous or all
multi MCAM entries. This has an impact on flow distribution.

This patch fixes the issue by updating flow algorithm index in above
mentioned MCAM entries.

Fixes: 967db3529eca ("octeontx2-af: add support for multicast/promisc packet replication feature")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    | 55 +++++++++++++++++-----
 1 file changed, 44 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index f65805860c8d..0bcf3e559280 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -671,6 +671,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	int blkaddr, ucast_idx, index;
 	struct nix_rx_action action = { 0 };
 	u64 relaxed_mask;
+	u8 flow_key_alg;
 
 	if (!hw->cap.nix_rx_multicast && is_cgx_vf(rvu, pcifunc))
 		return;
@@ -701,6 +702,8 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 		action.op = NIX_RX_ACTIONOP_UCAST;
 	}
 
+	flow_key_alg = action.flow_key_alg;
+
 	/* RX_ACTION set to MCAST for CGX PF's */
 	if (hw->cap.nix_rx_multicast && pfvf->use_mce_list &&
 	    is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
@@ -740,7 +743,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	req.vf = pcifunc;
 	req.index = action.index;
 	req.match_id = action.match_id;
-	req.flow_key_alg = action.flow_key_alg;
+	req.flow_key_alg = flow_key_alg;
 
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
@@ -854,6 +857,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 	u8 mac_addr[ETH_ALEN] = { 0 };
 	struct nix_rx_action action = { 0 };
 	struct rvu_pfvf *pfvf;
+	u8 flow_key_alg;
 	u16 vf_func;
 
 	/* Only CGX PF/VF can add allmulticast entry */
@@ -888,6 +892,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 		*(u64 *)&action = npc_get_mcam_action(rvu, mcam,
 							blkaddr, ucast_idx);
 
+	flow_key_alg = action.flow_key_alg;
 	if (action.op != NIX_RX_ACTIONOP_RSS) {
 		*(u64 *)&action = 0;
 		action.op = NIX_RX_ACTIONOP_UCAST;
@@ -924,7 +929,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 	req.vf = pcifunc | vf_func;
 	req.index = action.index;
 	req.match_id = action.match_id;
-	req.flow_key_alg = action.flow_key_alg;
+	req.flow_key_alg = flow_key_alg;
 
 	rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
 }
@@ -990,11 +995,38 @@ static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam,
 	mutex_unlock(&mcam->lock);
 }
 
+static void npc_update_rx_action_with_alg_idx(struct rvu *rvu, struct nix_rx_action action,
+					      struct rvu_pfvf *pfvf, int mcam_index, int blkaddr,
+					      int alg_idx)
+
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	struct rvu_hwinfo *hw = rvu->hw;
+	int bank, op_rss;
+
+	if (!is_mcam_entry_enabled(rvu, mcam, blkaddr, mcam_index))
+		return;
+
+	op_rss = (!hw->cap.nix_rx_multicast || !pfvf->use_mce_list);
+
+	bank = npc_get_bank(mcam, mcam_index);
+	mcam_index &= (mcam->banksize - 1);
+
+	/* If Rx action is MCAST update only RSS algorithm index */
+	if (!op_rss) {
+		*(u64 *)&action = rvu_read64(rvu, blkaddr,
+				NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank));
+
+		action.flow_key_alg = alg_idx;
+	}
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank), *(u64 *)&action);
+}
+
 void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    int group, int alg_idx, int mcam_index)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
-	struct rvu_hwinfo *hw = rvu->hw;
 	struct nix_rx_action action;
 	int blkaddr, index, bank;
 	struct rvu_pfvf *pfvf;
@@ -1050,15 +1082,16 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 	/* If PF's promiscuous entry is enabled,
 	 * Set RSS action for that entry as well
 	 */
-	if ((!hw->cap.nix_rx_multicast || !pfvf->use_mce_list) &&
-	    is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) {
-		bank = npc_get_bank(mcam, index);
-		index &= (mcam->banksize - 1);
+	npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr,
+					  alg_idx);
 
-		rvu_write64(rvu, blkaddr,
-			    NPC_AF_MCAMEX_BANKX_ACTION(index, bank),
-			    *(u64 *)&action);
-	}
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					 nixlf, NIXLF_ALLMULTI_ENTRY);
+	/* If PF's allmulti  entry is enabled,
+	 * Set RSS action for that entry as well
+	 */
+	npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr,
+					  alg_idx);
 }
 
 void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc,
-- 
cgit v1.2.3


From e307b5a845c5951dabafc48d00b6424ee64716c4 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 8 Dec 2023 14:57:54 +0530
Subject: octeontx2-af: Fix pause frame configuration

The current implementation's default Pause Forward setting is causing
unnecessary network traffic. This patch disables Pause Forward to
address this issue.

Fixes: 1121f6b02e7a ("octeontx2-af: Priority flow control configuration support")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rpm.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
index af21e2030cff..4728ba34b0e3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c
@@ -373,6 +373,11 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable)
 	cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE;
 	rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
 
+	/* Disable forward pause to driver */
+	cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG);
+	cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD;
+	rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg);
+
 	/* Enable channel mask for all LMACS */
 	if (is_dev_rpm2(rpm))
 		rpm_write(rpm, lmac_id, RPM2_CMR_CHAN_MSK_OR, 0xffff);
@@ -616,12 +621,10 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p
 
 	if (rx_pause) {
 		cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD);
+			 RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE);
 	} else {
 		cfg |= (RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE |
-				RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD);
+			RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE);
 	}
 
 	if (tx_pause) {
-- 
cgit v1.2.3


From 24e90b9e34f9e039f56b5f25f6e6eb92cdd8f4b3 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <v4bel@theori.io>
Date: Sat, 9 Dec 2023 04:42:10 -0500
Subject: atm: Fix Use-After-Free in do_vcc_ioctl

Because do_vcc_ioctl() accesses sk->sk_receive_queue
without holding a sk->sk_receive_queue.lock, it can
cause a race with vcc_recvmsg().
A use-after-free for skb occurs with the following flow.
```
do_vcc_ioctl() -> skb_peek()
vcc_recvmsg() -> skb_recv_datagram() -> skb_free_datagram()
```
Add sk->sk_receive_queue.lock to do_vcc_ioctl() to fix this issue.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Hyunwoo Kim <v4bel@theori.io>
Link: https://lore.kernel.org/r/20231209094210.GA403126@v4bel-B760M-AORUS-ELITE-AX
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/atm/ioctl.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c
index 838ebf0cabbf..f81f8d56f5c0 100644
--- a/net/atm/ioctl.c
+++ b/net/atm/ioctl.c
@@ -73,14 +73,17 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd,
 	case SIOCINQ:
 	{
 		struct sk_buff *skb;
+		int amount;
 
 		if (sock->state != SS_CONNECTED) {
 			error = -EINVAL;
 			goto done;
 		}
+		spin_lock_irq(&sk->sk_receive_queue.lock);
 		skb = skb_peek(&sk->sk_receive_queue);
-		error = put_user(skb ? skb->len : 0,
-				 (int __user *)argp) ? -EFAULT : 0;
+		amount = skb ? skb->len : 0;
+		spin_unlock_irq(&sk->sk_receive_queue.lock);
+		error = put_user(amount, (int __user *)argp) ? -EFAULT : 0;
 		goto done;
 	}
 	case ATM_SETSC:
-- 
cgit v1.2.3


From 810c38a369a0a0ce625b5c12169abce1dd9ccd53 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <v4bel@theori.io>
Date: Sat, 9 Dec 2023 05:05:38 -0500
Subject: net/rose: Fix Use-After-Free in rose_ioctl

Because rose_ioctl() accesses sk->sk_receive_queue
without holding a sk->sk_receive_queue.lock, it can
cause a race with rose_accept().
A use-after-free for skb occurs with the following flow.
```
rose_ioctl() -> skb_peek()
rose_accept() -> skb_dequeue() -> kfree_skb()
```
Add sk->sk_receive_queue.lock to rose_ioctl() to fix this issue.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Hyunwoo Kim <v4bel@theori.io>
Link: https://lore.kernel.org/r/20231209100538.GA407321@v4bel-B760M-AORUS-ELITE-AX
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/rose/af_rose.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 0cc5a4e19900..ecb91ad4ce63 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1315,9 +1315,11 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case TIOCINQ: {
 		struct sk_buff *skb;
 		long amount = 0L;
-		/* These two are safe on a single CPU system as only user tasks fiddle here */
+
+		spin_lock_irq(&sk->sk_receive_queue.lock);
 		if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL)
 			amount = skb->len;
+		spin_unlock_irq(&sk->sk_receive_queue.lock);
 		return put_user(amount, (unsigned int __user *) argp);
 	}
 
-- 
cgit v1.2.3


From 3a0b5a2929fdeda63fc921c2dbed237059acf732 Mon Sep 17 00:00:00 2001
From: Piotr Gardocki <piotrx.gardocki@intel.com>
Date: Tue, 21 Nov 2023 22:47:15 -0500
Subject: iavf: Introduce new state machines for flow director

New states introduced:

 IAVF_FDIR_FLTR_DIS_REQUEST
 IAVF_FDIR_FLTR_DIS_PENDING
 IAVF_FDIR_FLTR_INACTIVE

Current FDIR state machines (SM) are not adequate to handle a few
scenarios in the link DOWN/UP event, reset event and ntuple-feature.

For example, when VF link goes DOWN and comes back UP administratively,
the expectation is that previously installed filters should also be
restored. But with current SM, filters are not restored.
So with new SM, during link DOWN filters are marked as INACTIVE in
the iavf list but removed from PF. After link UP, SM will transition
from INACTIVE to ADD_REQUEST to restore the filter.

Similarly, with VF reset, filters will be removed from the PF, but
marked as INACTIVE in the iavf list. Filters will be restored after
reset completion.

Steps to reproduce:
-------------------

1. Create a VF. Here VF is enp8s0.

2. Assign IP addresses to VF and link partner and ping continuously
from remote. Here remote IP is 1.1.1.1.

3. Check default RX Queue of traffic.

ethtool -S enp8s0 | grep -E "rx-[[:digit:]]+\.packets"

4. Add filter - change default RX Queue (to 15 here)

ethtool -U ens8s0 flow-type ip4 src-ip 1.1.1.1 action 15 loc 5

5. Ensure filter gets added and traffic is received on RX queue 15 now.

Link event testing:
-------------------
6. Bring VF link down and up. If traffic flows to configured queue 15,
test is success, otherwise it is a failure.

Reset event testing:
--------------------
7. Reset the VF. If traffic flows to configured queue 15, test is success,
otherwise it is a failure.

Fixes: 0dbfbabb840d ("iavf: Add framework to enable ethtool ntuple filters")
Signed-off-by: Piotr Gardocki <piotrx.gardocki@intel.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Signed-off-by: Ranganatha Rao <ranganatha.rao@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf.h          |  1 +
 drivers/net/ethernet/intel/iavf/iavf_ethtool.c  | 27 ++++++----
 drivers/net/ethernet/intel/iavf/iavf_fdir.h     | 15 +++++-
 drivers/net/ethernet/intel/iavf/iavf_main.c     | 48 +++++++++++++----
 drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 71 +++++++++++++++++++++++--
 5 files changed, 139 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index e7ab89dc883a..63b45c61cc4a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -292,6 +292,7 @@ struct iavf_adapter {
 #define IAVF_FLAG_QUEUES_DISABLED		BIT(17)
 #define IAVF_FLAG_SETUP_NETDEV_FEATURES		BIT(18)
 #define IAVF_FLAG_REINIT_MSIX_NEEDED		BIT(20)
+#define IAVF_FLAG_FDIR_ENABLED			BIT(21)
 /* duplicates for common code */
 #define IAVF_FLAG_DCB_ENABLED			0
 	/* flags for admin queue service task */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 19cbfe554689..dc499fe7734e 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -1061,7 +1061,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter,
 	struct iavf_fdir_fltr *rule = NULL;
 	int ret = 0;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
@@ -1203,7 +1203,7 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd,
 	unsigned int cnt = 0;
 	int val = 0;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	cmd->data = IAVF_MAX_FDIR_FILTERS;
@@ -1395,7 +1395,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	int count = 50;
 	int err;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	if (fsp->flow_type & FLOW_MAC_EXT)
@@ -1436,12 +1436,16 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	spin_lock_bh(&adapter->fdir_fltr_lock);
 	iavf_fdir_list_add_fltr(adapter, fltr);
 	adapter->fdir_active_fltr++;
-	fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
-	adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+	if (adapter->link_up) {
+		fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+		adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+	} else {
+		fltr->state = IAVF_FDIR_FLTR_INACTIVE;
+	}
 	spin_unlock_bh(&adapter->fdir_fltr_lock);
 
-	mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
-
+	if (adapter->link_up)
+		mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
 ret:
 	if (err && fltr)
 		kfree(fltr);
@@ -1463,7 +1467,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	struct iavf_fdir_fltr *fltr = NULL;
 	int err = 0;
 
-	if (!FDIR_FLTR_SUPPORT(adapter))
+	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
@@ -1472,6 +1476,11 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 		if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) {
 			fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST;
 			adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER;
+		} else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) {
+			list_del(&fltr->list);
+			kfree(fltr);
+			adapter->fdir_active_fltr--;
+			fltr = NULL;
 		} else {
 			err = -EBUSY;
 		}
@@ -1780,7 +1789,7 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 		ret = 0;
 		break;
 	case ETHTOOL_GRXCLSRLCNT:
-		if (!FDIR_FLTR_SUPPORT(adapter))
+		if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 			break;
 		spin_lock_bh(&adapter->fdir_fltr_lock);
 		cmd->rule_cnt = adapter->fdir_active_fltr;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h
index 9eb9f73f6adf..d31bd923ba8c 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h
@@ -6,12 +6,25 @@
 
 struct iavf_adapter;
 
-/* State of Flow Director filter */
+/* State of Flow Director filter
+ *
+ * *_REQUEST states are used to mark filter to be sent to PF driver to perform
+ * an action (either add or delete filter). *_PENDING states are an indication
+ * that request was sent to PF and the driver is waiting for response.
+ *
+ * Both DELETE and DISABLE states are being used to delete a filter in PF.
+ * The difference is that after a successful response filter in DEL_PENDING
+ * state is being deleted from VF driver as well and filter in DIS_PENDING state
+ * is being changed to INACTIVE state.
+ */
 enum iavf_fdir_fltr_state_t {
 	IAVF_FDIR_FLTR_ADD_REQUEST,	/* User requests to add filter */
 	IAVF_FDIR_FLTR_ADD_PENDING,	/* Filter pending add by the PF */
 	IAVF_FDIR_FLTR_DEL_REQUEST,	/* User requests to delete filter */
 	IAVF_FDIR_FLTR_DEL_PENDING,	/* Filter pending delete by the PF */
+	IAVF_FDIR_FLTR_DIS_REQUEST,	/* Filter scheduled to be disabled */
+	IAVF_FDIR_FLTR_DIS_PENDING,	/* Filter pending disable by the PF */
+	IAVF_FDIR_FLTR_INACTIVE,	/* Filter inactive on link down */
 	IAVF_FDIR_FLTR_ACTIVE,		/* Filter is active */
 };
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index c862ebcd2e39..567435e23936 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1353,18 +1353,20 @@ static void iavf_clear_cloud_filters(struct iavf_adapter *adapter)
  **/
 static void iavf_clear_fdir_filters(struct iavf_adapter *adapter)
 {
-	struct iavf_fdir_fltr *fdir, *fdirtmp;
+	struct iavf_fdir_fltr *fdir;
 
 	/* remove all Flow Director filters */
 	spin_lock_bh(&adapter->fdir_fltr_lock);
-	list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head,
-				 list) {
+	list_for_each_entry(fdir, &adapter->fdir_list_head, list) {
 		if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST) {
-			list_del(&fdir->list);
-			kfree(fdir);
-			adapter->fdir_active_fltr--;
-		} else {
-			fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST;
+			/* Cancel a request, keep filter as inactive */
+			fdir->state = IAVF_FDIR_FLTR_INACTIVE;
+		} else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+			 fdir->state == IAVF_FDIR_FLTR_ACTIVE) {
+			/* Disable filters which are active or have a pending
+			 * request to PF to be added
+			 */
+			fdir->state = IAVF_FDIR_FLTR_DIS_REQUEST;
 		}
 	}
 	spin_unlock_bh(&adapter->fdir_fltr_lock);
@@ -4112,6 +4114,33 @@ static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 	}
 }
 
+/**
+ * iavf_restore_fdir_filters
+ * @adapter: board private structure
+ *
+ * Restore existing FDIR filters when VF netdev comes back up.
+ **/
+static void iavf_restore_fdir_filters(struct iavf_adapter *adapter)
+{
+	struct iavf_fdir_fltr *f;
+
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	list_for_each_entry(f, &adapter->fdir_list_head, list) {
+		if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST) {
+			/* Cancel a request, keep filter as active */
+			f->state = IAVF_FDIR_FLTR_ACTIVE;
+		} else if (f->state == IAVF_FDIR_FLTR_DIS_PENDING ||
+			   f->state == IAVF_FDIR_FLTR_INACTIVE) {
+			/* Add filters which are inactive or have a pending
+			 * request to PF to be deleted
+			 */
+			f->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+			adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+		}
+	}
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+}
+
 /**
  * iavf_open - Called when a network interface is made active
  * @netdev: network interface device structure
@@ -4179,8 +4208,9 @@ static int iavf_open(struct net_device *netdev)
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
-	/* Restore VLAN filters that were removed with IFF_DOWN */
+	/* Restore filters that were removed with IFF_DOWN */
 	iavf_restore_filters(adapter);
+	iavf_restore_fdir_filters(adapter);
 
 	iavf_configure(adapter);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 64c4443dbef9..2d9366be0ec5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1735,8 +1735,8 @@ void iavf_add_fdir_filter(struct iavf_adapter *adapter)
  **/
 void iavf_del_fdir_filter(struct iavf_adapter *adapter)
 {
+	struct virtchnl_fdir_del f = {};
 	struct iavf_fdir_fltr *fdir;
-	struct virtchnl_fdir_del f;
 	bool process_fltr = false;
 	int len;
 
@@ -1753,11 +1753,16 @@ void iavf_del_fdir_filter(struct iavf_adapter *adapter)
 	list_for_each_entry(fdir, &adapter->fdir_list_head, list) {
 		if (fdir->state == IAVF_FDIR_FLTR_DEL_REQUEST) {
 			process_fltr = true;
-			memset(&f, 0, len);
 			f.vsi_id = fdir->vc_add_msg.vsi_id;
 			f.flow_id = fdir->flow_id;
 			fdir->state = IAVF_FDIR_FLTR_DEL_PENDING;
 			break;
+		} else if (fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST) {
+			process_fltr = true;
+			f.vsi_id = fdir->vc_add_msg.vsi_id;
+			f.flow_id = fdir->flow_id;
+			fdir->state = IAVF_FDIR_FLTR_DIS_PENDING;
+			break;
 		}
 	}
 	spin_unlock_bh(&adapter->fdir_fltr_lock);
@@ -1901,6 +1906,48 @@ static void iavf_netdev_features_vlan_strip_set(struct net_device *netdev,
 		netdev->features &= ~NETIF_F_HW_VLAN_CTAG_RX;
 }
 
+/**
+ * iavf_activate_fdir_filters - Reactivate all FDIR filters after a reset
+ * @adapter: private adapter structure
+ *
+ * Called after a reset to re-add all FDIR filters and delete some of them
+ * if they were pending to be deleted.
+ */
+static void iavf_activate_fdir_filters(struct iavf_adapter *adapter)
+{
+	struct iavf_fdir_fltr *f, *ftmp;
+	bool add_filters = false;
+
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	list_for_each_entry_safe(f, ftmp, &adapter->fdir_list_head, list) {
+		if (f->state == IAVF_FDIR_FLTR_ADD_REQUEST ||
+		    f->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+		    f->state == IAVF_FDIR_FLTR_ACTIVE) {
+			/* All filters and requests have been removed in PF,
+			 * restore them
+			 */
+			f->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+			add_filters = true;
+		} else if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST ||
+			   f->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+			/* Link down state, leave filters as inactive */
+			f->state = IAVF_FDIR_FLTR_INACTIVE;
+		} else if (f->state == IAVF_FDIR_FLTR_DEL_REQUEST ||
+			   f->state == IAVF_FDIR_FLTR_DEL_PENDING) {
+			/* Delete filters that were pending to be deleted, the
+			 * list on PF is already cleared after a reset
+			 */
+			list_del(&f->list);
+			kfree(f);
+			adapter->fdir_active_fltr--;
+		}
+	}
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+
+	if (add_filters)
+		adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
+}
+
 /**
  * iavf_virtchnl_completion
  * @adapter: adapter structure
@@ -2078,7 +2125,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			spin_lock_bh(&adapter->fdir_fltr_lock);
 			list_for_each_entry(fdir, &adapter->fdir_list_head,
 					    list) {
-				if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) {
+				if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING ||
+				    fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
 					fdir->state = IAVF_FDIR_FLTR_ACTIVE;
 					dev_info(&adapter->pdev->dev, "Failed to del Flow Director filter, error %s\n",
 						 iavf_stat_str(&adapter->hw,
@@ -2214,6 +2262,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 
 		spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
+		iavf_activate_fdir_filters(adapter);
+
 		iavf_parse_vf_resource_msg(adapter);
 
 		/* negotiated VIRTCHNL_VF_OFFLOAD_VLAN_V2, so wait for the
@@ -2390,7 +2440,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		list_for_each_entry_safe(fdir, fdir_tmp, &adapter->fdir_list_head,
 					 list) {
 			if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) {
-				if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS) {
+				if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS ||
+				    del_fltr->status ==
+				    VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) {
 					dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n",
 						 fdir->loc);
 					list_del(&fdir->list);
@@ -2402,6 +2454,17 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 						 del_fltr->status);
 					iavf_print_fdir_fltr(adapter, fdir);
 				}
+			} else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+				if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS ||
+				    del_fltr->status ==
+				    VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) {
+					fdir->state = IAVF_FDIR_FLTR_INACTIVE;
+				} else {
+					fdir->state = IAVF_FDIR_FLTR_ACTIVE;
+					dev_info(&adapter->pdev->dev, "Failed to disable Flow Director filter with status: %d\n",
+						 del_fltr->status);
+					iavf_print_fdir_fltr(adapter, fdir);
+				}
 			}
 		}
 		spin_unlock_bh(&adapter->fdir_fltr_lock);
-- 
cgit v1.2.3


From 09d23b8918f9ab0f8114f6b94f2faf8bde3fb52a Mon Sep 17 00:00:00 2001
From: Piotr Gardocki <piotrx.gardocki@intel.com>
Date: Tue, 21 Nov 2023 22:47:16 -0500
Subject: iavf: Handle ntuple on/off based on new state machines for flow
 director

ntuple-filter feature on/off:
Default is on. If turned off, the filters will be removed from both
PF and iavf list. The removal is irrespective of current filter state.

Steps to reproduce:
-------------------

1. Ensure ntuple is on.

ethtool -K enp8s0 ntuple-filters on

2. Create a filter to receive the traffic into non-default rx-queue like 15
and ensure traffic is flowing into queue into 15.
Now, turn off ntuple. Traffic should not flow to configured queue 15.
It should flow to default RX queue.

Fixes: 0dbfbabb840d ("iavf: Add framework to enable ethtool ntuple filters")
Signed-off-by: Piotr Gardocki <piotrx.gardocki@intel.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Signed-off-by: Ranganatha Rao <ranganatha.rao@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 59 +++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 567435e23936..98116872f6bd 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -4341,6 +4341,49 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
 	return ret;
 }
 
+/**
+ * iavf_disable_fdir - disable Flow Director and clear existing filters
+ * @adapter: board private structure
+ **/
+static void iavf_disable_fdir(struct iavf_adapter *adapter)
+{
+	struct iavf_fdir_fltr *fdir, *fdirtmp;
+	bool del_filters = false;
+
+	adapter->flags &= ~IAVF_FLAG_FDIR_ENABLED;
+
+	/* remove all Flow Director filters */
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head,
+				 list) {
+		if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST ||
+		    fdir->state == IAVF_FDIR_FLTR_INACTIVE) {
+			/* Delete filters not registered in PF */
+			list_del(&fdir->list);
+			kfree(fdir);
+			adapter->fdir_active_fltr--;
+		} else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING ||
+			   fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST ||
+			   fdir->state == IAVF_FDIR_FLTR_ACTIVE) {
+			/* Filters registered in PF, schedule their deletion */
+			fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST;
+			del_filters = true;
+		} else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) {
+			/* Request to delete filter already sent to PF, change
+			 * state to DEL_PENDING to delete filter after PF's
+			 * response, not set as INACTIVE
+			 */
+			fdir->state = IAVF_FDIR_FLTR_DEL_PENDING;
+		}
+	}
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+
+	if (del_filters) {
+		adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER;
+		mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+	}
+}
+
 #define NETIF_VLAN_OFFLOAD_FEATURES	(NETIF_F_HW_VLAN_CTAG_RX | \
 					 NETIF_F_HW_VLAN_CTAG_TX | \
 					 NETIF_F_HW_VLAN_STAG_RX | \
@@ -4366,6 +4409,13 @@ static int iavf_set_features(struct net_device *netdev,
 	    ((netdev->features & NETIF_F_RXFCS) ^ (features & NETIF_F_RXFCS)))
 		iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED);
 
+	if ((netdev->features & NETIF_F_NTUPLE) ^ (features & NETIF_F_NTUPLE)) {
+		if (features & NETIF_F_NTUPLE)
+			adapter->flags |= IAVF_FLAG_FDIR_ENABLED;
+		else
+			iavf_disable_fdir(adapter);
+	}
+
 	return 0;
 }
 
@@ -4715,6 +4765,9 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev,
 
 	features = iavf_fix_netdev_vlan_features(adapter, features);
 
+	if (!FDIR_FLTR_SUPPORT(adapter))
+		features &= ~NETIF_F_NTUPLE;
+
 	return iavf_fix_strip_features(adapter, features);
 }
 
@@ -4832,6 +4885,12 @@ int iavf_process_config(struct iavf_adapter *adapter)
 	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)
 		netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
+	if (FDIR_FLTR_SUPPORT(adapter)) {
+		netdev->hw_features |= NETIF_F_NTUPLE;
+		netdev->features |= NETIF_F_NTUPLE;
+		adapter->flags |= IAVF_FLAG_FDIR_ENABLED;
+	}
+
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
 	/* Do not turn on offloads when they are requested to be turned off.
-- 
cgit v1.2.3


From 7ae42ef308ed0f6250b36f43e4eeb182ebbe6215 Mon Sep 17 00:00:00 2001
From: Slawomir Laba <slawomirx.laba@intel.com>
Date: Wed, 29 Nov 2023 10:35:26 -0500
Subject: iavf: Fix iavf_shutdown to call iavf_remove instead iavf_close

Make the flow for pci shutdown be the same to the pci remove.

iavf_shutdown was implementing an incomplete version
of iavf_remove. It misses several calls to the kernel like
iavf_free_misc_irq, iavf_reset_interrupt_capability, iounmap
that might break the system on reboot or hibernation.

Implement the call of iavf_remove directly in iavf_shutdown to
close this gap.

Fixes below error messages (dmesg) during shutdown stress tests -
[685814.900917] ice 0000:88:00.0: MAC 02:d0:5f:82:43:5d does not exist for
 VF 0
[685814.900928] ice 0000:88:00.0: MAC 33:33:00:00:00:01 does not exist for
VF 0

Reproduction:

1. Create one VF interface:
echo 1 > /sys/class/net/<interface_name>/device/sriov_numvfs

2. Run live dmesg on the host:
dmesg -wH

3. On SUT, script below steps into vf_namespace_assignment.sh

<#!/bin/sh> // Remove <>. Git removes # line
if=<VF name> (edit this per VF name)
loop=0

while true; do

echo test round $loop
let loop++

ip netns add ns$loop
ip link set dev $if up
ip link set dev $if netns ns$loop
ip netns exec ns$loop ip link set dev $if up
ip netns exec ns$loop ip link set dev $if netns 1
ip netns delete ns$loop

done

4. Run the script for at least 1000 iterations on SUT:
./vf_namespace_assignment.sh

Expected result:
No errors in dmesg.

Fixes: 129cf89e5856 ("iavf: rename functions and structs to new name")
Signed-off-by: Slawomir Laba <slawomirx.laba@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Co-developed-by: Ranganatha Rao <ranganatha.rao@intel.com>
Signed-off-by: Ranganatha Rao <ranganatha.rao@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 72 +++++++++--------------------
 1 file changed, 21 insertions(+), 51 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 98116872f6bd..e8d5b889addc 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -276,27 +276,6 @@ void iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem)
 	kfree(mem->va);
 }
 
-/**
- * iavf_lock_timeout - try to lock mutex but give up after timeout
- * @lock: mutex that should be locked
- * @msecs: timeout in msecs
- *
- * Returns 0 on success, negative on failure
- **/
-static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs)
-{
-	unsigned int wait, delay = 10;
-
-	for (wait = 0; wait < msecs; wait += delay) {
-		if (mutex_trylock(lock))
-			return 0;
-
-		msleep(delay);
-	}
-
-	return -1;
-}
-
 /**
  * iavf_schedule_reset - Set the flags and schedule a reset event
  * @adapter: board private structure
@@ -4914,34 +4893,6 @@ int iavf_process_config(struct iavf_adapter *adapter)
 	return 0;
 }
 
-/**
- * iavf_shutdown - Shutdown the device in preparation for a reboot
- * @pdev: pci device structure
- **/
-static void iavf_shutdown(struct pci_dev *pdev)
-{
-	struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev);
-	struct net_device *netdev = adapter->netdev;
-
-	netif_device_detach(netdev);
-
-	if (netif_running(netdev))
-		iavf_close(netdev);
-
-	if (iavf_lock_timeout(&adapter->crit_lock, 5000))
-		dev_warn(&adapter->pdev->dev, "%s: failed to acquire crit_lock\n", __func__);
-	/* Prevent the watchdog from running. */
-	iavf_change_state(adapter, __IAVF_REMOVE);
-	adapter->aq_required = 0;
-	mutex_unlock(&adapter->crit_lock);
-
-#ifdef CONFIG_PM
-	pci_save_state(pdev);
-
-#endif
-	pci_disable_device(pdev);
-}
-
 /**
  * iavf_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -5152,16 +5103,21 @@ static int __maybe_unused iavf_resume(struct device *dev_d)
  **/
 static void iavf_remove(struct pci_dev *pdev)
 {
-	struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev);
 	struct iavf_fdir_fltr *fdir, *fdirtmp;
 	struct iavf_vlan_filter *vlf, *vlftmp;
 	struct iavf_cloud_filter *cf, *cftmp;
 	struct iavf_adv_rss *rss, *rsstmp;
 	struct iavf_mac_filter *f, *ftmp;
+	struct iavf_adapter *adapter;
 	struct net_device *netdev;
 	struct iavf_hw *hw;
 
-	netdev = adapter->netdev;
+	/* Don't proceed with remove if netdev is already freed */
+	netdev = pci_get_drvdata(pdev);
+	if (!netdev)
+		return;
+
+	adapter = iavf_pdev_to_adapter(pdev);
 	hw = &adapter->hw;
 
 	if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
@@ -5273,11 +5229,25 @@ static void iavf_remove(struct pci_dev *pdev)
 
 	destroy_workqueue(adapter->wq);
 
+	pci_set_drvdata(pdev, NULL);
+
 	free_netdev(netdev);
 
 	pci_disable_device(pdev);
 }
 
+/**
+ * iavf_shutdown - Shutdown the device in preparation for a reboot
+ * @pdev: pci device structure
+ **/
+static void iavf_shutdown(struct pci_dev *pdev)
+{
+	iavf_remove(pdev);
+
+	if (system_state == SYSTEM_POWER_OFF)
+		pci_set_power_state(pdev, PCI_D3hot);
+}
+
 static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume);
 
 static struct pci_driver iavf_driver = {
-- 
cgit v1.2.3


From b65d52ac9c085c0c52dee012a210d4e2f352611b Mon Sep 17 00:00:00 2001
From: Dinghao Liu <dinghao.liu@zju.edu.cn>
Date: Sun, 10 Dec 2023 12:52:55 +0800
Subject: qed: Fix a potential use-after-free in qed_cxt_tables_alloc

qed_ilt_shadow_alloc() will call qed_ilt_shadow_free() to
free p_hwfn->p_cxt_mngr->ilt_shadow on error. However,
qed_cxt_tables_alloc() accesses the freed pointer on failure
of qed_ilt_shadow_alloc() through calling qed_cxt_mngr_free(),
which may lead to use-after-free. Fix this issue by setting
p_mngr->ilt_shadow to NULL in qed_ilt_shadow_free().

Fixes: fe56b9e6a8d9 ("qed: Add module with basic common support")
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Dinghao Liu <dinghao.liu@zju.edu.cn>
Link: https://lore.kernel.org/r/20231210045255.21383-1-dinghao.liu@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qlogic/qed/qed_cxt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index 65e20693c549..33f4f58ee51c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -933,6 +933,7 @@ static void qed_ilt_shadow_free(struct qed_hwfn *p_hwfn)
 		p_dma->virt_addr = NULL;
 	}
 	kfree(p_mngr->ilt_shadow);
+	p_mngr->ilt_shadow = NULL;
 }
 
 static int qed_ilt_blk_alloc(struct qed_hwfn *p_hwfn,
-- 
cgit v1.2.3


From f99cd56230f56c8b6b33713c5be4da5d6766be1f Mon Sep 17 00:00:00 2001
From: Dong Chenchen <dongchenchen2@huawei.com>
Date: Sun, 10 Dec 2023 10:02:00 +0800
Subject: net: Remove acked SYN flag from packet in the transmit queue
 correctly

syzkaller report:

 kernel BUG at net/core/skbuff.c:3452!
 invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI
 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.7.0-rc4-00009-gbee0e7762ad2-dirty #135
 RIP: 0010:skb_copy_and_csum_bits (net/core/skbuff.c:3452)
 Call Trace:
 icmp_glue_bits (net/ipv4/icmp.c:357)
 __ip_append_data.isra.0 (net/ipv4/ip_output.c:1165)
 ip_append_data (net/ipv4/ip_output.c:1362 net/ipv4/ip_output.c:1341)
 icmp_push_reply (net/ipv4/icmp.c:370)
 __icmp_send (./include/net/route.h:252 net/ipv4/icmp.c:772)
 ip_fragment.constprop.0 (./include/linux/skbuff.h:1234 net/ipv4/ip_output.c:592 net/ipv4/ip_output.c:577)
 __ip_finish_output (net/ipv4/ip_output.c:311 net/ipv4/ip_output.c:295)
 ip_output (net/ipv4/ip_output.c:427)
 __ip_queue_xmit (net/ipv4/ip_output.c:535)
 __tcp_transmit_skb (net/ipv4/tcp_output.c:1462)
 __tcp_retransmit_skb (net/ipv4/tcp_output.c:3387)
 tcp_retransmit_skb (net/ipv4/tcp_output.c:3404)
 tcp_retransmit_timer (net/ipv4/tcp_timer.c:604)
 tcp_write_timer (./include/linux/spinlock.h:391 net/ipv4/tcp_timer.c:716)

The panic issue was trigered by tcp simultaneous initiation.
The initiation process is as follows:

      TCP A                                            TCP B

  1.  CLOSED                                           CLOSED

  2.  SYN-SENT     --> <SEQ=100><CTL=SYN>              ...

  3.  SYN-RECEIVED <-- <SEQ=300><CTL=SYN>              <-- SYN-SENT

  4.               ... <SEQ=100><CTL=SYN>              --> SYN-RECEIVED

  5.  SYN-RECEIVED --> <SEQ=100><ACK=301><CTL=SYN,ACK> ...

  // TCP B: not send challenge ack for ack limit or packet loss
  // TCP A: close
	tcp_close
	   tcp_send_fin
              if (!tskb && tcp_under_memory_pressure(sk))
                  tskb = skb_rb_last(&sk->tcp_rtx_queue); //pick SYN_ACK packet
           TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;  // set FIN flag

  6.  FIN_WAIT_1  --> <SEQ=100><ACK=301><END_SEQ=102><CTL=SYN,FIN,ACK> ...

  // TCP B: send challenge ack to SYN_FIN_ACK

  7.               ... <SEQ=301><ACK=101><CTL=ACK>   <-- SYN-RECEIVED //challenge ack

  // TCP A:  <SND.UNA=101>

  8.  FIN_WAIT_1 --> <SEQ=101><ACK=301><END_SEQ=102><CTL=SYN,FIN,ACK> ... // retransmit panic

	__tcp_retransmit_skb  //skb->len=0
	    tcp_trim_head
		len = tp->snd_una - TCP_SKB_CB(skb)->seq // len=101-100
		    __pskb_trim_head
			skb->data_len -= len // skb->len=-1, wrap around
	    ... ...
	    ip_fragment
		icmp_glue_bits //BUG_ON

If we use tcp_trim_head() to remove acked SYN from packet that contains data
or other flags, skb->len will be incorrectly decremented. We can remove SYN
flag that has been acked from rtx_queue earlier than tcp_trim_head(), which
can fix the problem mentioned above.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Co-developed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Dong Chenchen <dongchenchen2@huawei.com>
Link: https://lore.kernel.org/r/20231210020200.1539875-1-dongchenchen2@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_output.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f5ef15e1d9ac..e3167ad96567 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3293,7 +3293,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	if (skb_still_in_host_queue(sk, skb))
 		return -EBUSY;
 
+start:
 	if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
+		if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+			TCP_SKB_CB(skb)->seq++;
+			goto start;
+		}
 		if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
 			WARN_ON_ONCE(1);
 			return -EINVAL;
-- 
cgit v1.2.3


From 41db6f99b5489a0d2ef26afe816ef0c6118d1d47 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Mon, 11 Dec 2023 06:27:58 +0000
Subject: net: ena: Destroy correct number of xdp queues upon failure

The ena_setup_and_create_all_xdp_queues() function freed all the
resources upon failure, after creating only xdp_num_queues queues,
instead of freeing just the created ones.

In this patch, the only resources that are freed, are the ones
allocated right before the failure occurs.

Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Shahar Itzko <itzko@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Link: https://lore.kernel.org/r/20231211062801.27891-2-darinzon@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index b5bca4814830..9884ef38f18a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -74,6 +74,8 @@ static void ena_unmap_tx_buff(struct ena_ring *tx_ring,
 			      struct ena_tx_buffer *tx_info);
 static int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter,
 					    int first_index, int count);
+static void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter,
+						  int first_index, int count);
 
 /* Increase a stat by cnt while holding syncp seqlock on 32bit machines */
 static void ena_increase_stat(u64 *statp, u64 cnt,
@@ -457,23 +459,22 @@ static void ena_init_all_xdp_queues(struct ena_adapter *adapter)
 
 static int ena_setup_and_create_all_xdp_queues(struct ena_adapter *adapter)
 {
+	u32 xdp_first_ring = adapter->xdp_first_ring;
+	u32 xdp_num_queues = adapter->xdp_num_queues;
 	int rc = 0;
 
-	rc = ena_setup_tx_resources_in_range(adapter, adapter->xdp_first_ring,
-					     adapter->xdp_num_queues);
+	rc = ena_setup_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues);
 	if (rc)
 		goto setup_err;
 
-	rc = ena_create_io_tx_queues_in_range(adapter,
-					      adapter->xdp_first_ring,
-					      adapter->xdp_num_queues);
+	rc = ena_create_io_tx_queues_in_range(adapter, xdp_first_ring, xdp_num_queues);
 	if (rc)
 		goto create_err;
 
 	return 0;
 
 create_err:
-	ena_free_all_io_tx_resources(adapter);
+	ena_free_all_io_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues);
 setup_err:
 	return rc;
 }
-- 
cgit v1.2.3


From 505b1a88d311ff6f8c44a34f94e3be21745cce6f Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Mon, 11 Dec 2023 06:27:59 +0000
Subject: net: ena: Fix xdp drops handling due to multibuf packets

Current xdp code drops packets larger than ENA_XDP_MAX_MTU.
This is an incorrect condition since the problem is not the
size of the packet, rather the number of buffers it contains.

This commit:

1. Identifies and drops XDP multi-buffer packets at the
   beginning of the function.
2. Increases the xdp drop statistic when this drop occurs.
3. Adds a one-time print that such drops are happening to
   give better indication to the user.

Fixes: 838c93dc5449 ("net: ena: implement XDP drop support")
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Link: https://lore.kernel.org/r/20231211062801.27891-3-darinzon@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 9884ef38f18a..c7bc5720d16d 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1672,20 +1672,23 @@ static void ena_set_rx_hash(struct ena_ring *rx_ring,
 	}
 }
 
-static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp)
+static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp, u16 num_descs)
 {
 	struct ena_rx_buffer *rx_info;
 	int ret;
 
+	/* XDP multi-buffer packets not supported */
+	if (unlikely(num_descs > 1)) {
+		netdev_err_once(rx_ring->adapter->netdev,
+				"xdp: dropped unsupported multi-buffer packets\n");
+		ena_increase_stat(&rx_ring->rx_stats.xdp_drop, 1, &rx_ring->syncp);
+		return ENA_XDP_DROP;
+	}
+
 	rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
 	xdp_prepare_buff(xdp, page_address(rx_info->page),
 			 rx_info->buf_offset,
 			 rx_ring->ena_bufs[0].len, false);
-	/* If for some reason we received a bigger packet than
-	 * we expect, then we simply drop it
-	 */
-	if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU))
-		return ENA_XDP_DROP;
 
 	ret = ena_xdp_execute(rx_ring, xdp);
 
@@ -1754,7 +1757,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 			  ena_rx_ctx.l4_proto, ena_rx_ctx.hash);
 
 		if (ena_xdp_present_ring(rx_ring))
-			xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp);
+			xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp, ena_rx_ctx.descs);
 
 		/* allocate skb and fill it */
 		if (xdp_verdict == ENA_XDP_PASS)
-- 
cgit v1.2.3


From d760117060cf2e90b5c59c5492cab179a4dbce01 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Mon, 11 Dec 2023 06:28:00 +0000
Subject: net: ena: Fix DMA syncing in XDP path when SWIOTLB is on

This patch fixes two issues:

Issue 1
-------
Description
```````````
Current code does not call dma_sync_single_for_cpu() to sync data from
the device side memory to the CPU side memory before the XDP code path
uses the CPU side data.
This causes the XDP code path to read the unset garbage data in the CPU
side memory, resulting in incorrect handling of the packet by XDP.

Solution
````````
1. Add a call to dma_sync_single_for_cpu() before the XDP code starts to
   use the data in the CPU side memory.
2. The XDP code verdict can be XDP_PASS, in which case there is a
   fallback to the non-XDP code, which also calls
   dma_sync_single_for_cpu().
   To avoid calling dma_sync_single_for_cpu() twice:
2.1. Put the dma_sync_single_for_cpu() in the code in such a place where
     it happens before XDP and non-XDP code.
2.2. Remove the calls to dma_sync_single_for_cpu() in the non-XDP code
     for the first buffer only (rx_copybreak and non-rx_copybreak
     cases), since the new call that was added covers these cases.
     The call to dma_sync_single_for_cpu() for the second buffer and on
     stays because only the first buffer is handled by the newly added
     dma_sync_single_for_cpu(). And there is no need for special
     handling of the second buffer and on for the XDP path since
     currently the driver supports only single buffer packets.

Issue 2
-------
Description
```````````
In case the XDP code forwarded the packet (ENA_XDP_FORWARDED),
ena_unmap_rx_buff_attrs() is called with attrs set to 0.
This means that before unmapping the buffer, the internal function
dma_unmap_page_attrs() will also call dma_sync_single_for_cpu() on
the whole buffer (not only on the data part of it).
This sync is both wasteful (since a sync was already explicitly
called before) and also causes a bug, which will be explained
using the below diagram.

The following diagram shows the flow of events causing the bug.
The order of events is (1)-(4) as shown in the diagram.

CPU side memory area

     (3)convert_to_xdp_frame() initializes the
        headroom with xdpf metadata
                      ||
                      \/
          ___________________________________
         |                                   |
 0       |                                   V                       4K
 ---------------------------------------------------------------------
 | xdpf->data      | other xdpf       |   < data >   | tailroom ||...|
 |                 | fields           |              | GARBAGE  ||   |
 ---------------------------------------------------------------------

                   /\                        /\
                   ||                        ||
   (4)ena_unmap_rx_buff_attrs() calls     (2)dma_sync_single_for_cpu()
      dma_sync_single_for_cpu() on the       copies data from device
      whole buffer page, overwriting         side to CPU side memory
      the xdpf->data with GARBAGE.           ||
 0                                                                   4K
 ---------------------------------------------------------------------
 | headroom                           |   < data >   | tailroom ||...|
 | GARBAGE                            |              | GARBAGE  ||   |
 ---------------------------------------------------------------------

Device side memory area                      /\
                                             ||
                               (1) device writes RX packet data

After the call to ena_unmap_rx_buff_attrs() in (4), the xdpf->data
becomes corrupted, and so when it is later accessed in
ena_clean_xdp_irq()->xdp_return_frame(), it causes a page fault,
crashing the kernel.

Solution
````````
Explicitly tell ena_unmap_rx_buff_attrs() not to call
dma_sync_single_for_cpu() by passing it the ENA_DMA_ATTR_SKIP_CPU_SYNC
flag.

Fixes: f7d625adeb7b ("net: ena: Add dynamic recycling mechanism for rx buffers")
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Link: https://lore.kernel.org/r/20231211062801.27891-4-darinzon@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 23 +++++++++--------------
 1 file changed, 9 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c7bc5720d16d..c44c44e26ddf 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1493,11 +1493,6 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 		if (unlikely(!skb))
 			return NULL;
 
-		/* sync this buffer for CPU use */
-		dma_sync_single_for_cpu(rx_ring->dev,
-					dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
-					len,
-					DMA_FROM_DEVICE);
 		skb_copy_to_linear_data(skb, buf_addr + buf_offset, len);
 		dma_sync_single_for_device(rx_ring->dev,
 					   dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
@@ -1516,17 +1511,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 
 	buf_len = SKB_DATA_ALIGN(len + buf_offset + tailroom);
 
-	pre_reuse_paddr = dma_unmap_addr(&rx_info->ena_buf, paddr);
-
 	/* If XDP isn't loaded try to reuse part of the RX buffer */
 	reuse_rx_buf_page = !is_xdp_loaded &&
 			    ena_try_rx_buf_page_reuse(rx_info, buf_len, len, pkt_offset);
 
-	dma_sync_single_for_cpu(rx_ring->dev,
-				pre_reuse_paddr + pkt_offset,
-				len,
-				DMA_FROM_DEVICE);
-
 	if (!reuse_rx_buf_page)
 		ena_unmap_rx_buff_attrs(rx_ring, rx_info, DMA_ATTR_SKIP_CPU_SYNC);
 
@@ -1723,6 +1711,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 	int xdp_flags = 0;
 	int total_len = 0;
 	int xdp_verdict;
+	u8 pkt_offset;
 	int rc = 0;
 	int i;
 
@@ -1749,13 +1738,19 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 
 		/* First descriptor might have an offset set by the device */
 		rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
-		rx_info->buf_offset += ena_rx_ctx.pkt_offset;
+		pkt_offset = ena_rx_ctx.pkt_offset;
+		rx_info->buf_offset += pkt_offset;
 
 		netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
 			  "rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n",
 			  rx_ring->qid, ena_rx_ctx.descs, ena_rx_ctx.l3_proto,
 			  ena_rx_ctx.l4_proto, ena_rx_ctx.hash);
 
+		dma_sync_single_for_cpu(rx_ring->dev,
+					dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset,
+					rx_ring->ena_bufs[0].len,
+					DMA_FROM_DEVICE);
+
 		if (ena_xdp_present_ring(rx_ring))
 			xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp, ena_rx_ctx.descs);
 
@@ -1781,7 +1776,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 				if (xdp_verdict & ENA_XDP_FORWARDED) {
 					ena_unmap_rx_buff_attrs(rx_ring,
 								&rx_ring->rx_buffer_info[req_id],
-								0);
+								DMA_ATTR_SKIP_CPU_SYNC);
 					rx_ring->rx_buffer_info[req_id].page = NULL;
 				}
 			}
-- 
cgit v1.2.3


From 4ab138ca0a340e6d6e7a6a9bd5004bd8f83127ca Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Mon, 11 Dec 2023 06:28:01 +0000
Subject: net: ena: Fix XDP redirection error

When sending TX packets, the meta descriptor can be all zeroes
as no meta information is required (as in XDP).

This patch removes the validity check, as when
`disable_meta_caching` is enabled, such TX packets will be
dropped otherwise.

Fixes: 0e3a3f6dacf0 ("net: ena: support new LLQ acceleration mode")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Link: https://lore.kernel.org/r/20231211062801.27891-5-darinzon@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amazon/ena/ena_eth_com.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index 3d6f0a466a9e..f9f886289b97 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -328,9 +328,6 @@ static int ena_com_create_and_store_tx_meta_desc(struct ena_com_io_sq *io_sq,
 	 * compare it to the stored version, just create the meta
 	 */
 	if (io_sq->disable_meta_caching) {
-		if (unlikely(!ena_tx_ctx->meta_valid))
-			return -EINVAL;
-
 		*have_meta = true;
 		return ena_com_create_meta(io_sq, ena_meta);
 	}
-- 
cgit v1.2.3


From 65c95f78917ea6fa7ff189a2c19879c4fe161873 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Mon, 11 Dec 2023 09:37:58 +0100
Subject: dpll: sanitize possible null pointer dereference in
 dpll_pin_parent_pin_set()

User may not pass DPLL_A_PIN_STATE attribute in the pin set operation
message. Sanitize that by checking if the attr pointer is not null
and process the passed state attribute value only in that case.

Reported-by: Xingyuan Mo <hdthky0@gmail.com>
Fixes: 9d71b54b65b1 ("dpll: netlink: Add DPLL framework base functions")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://lore.kernel.org/r/20231211083758.1082853-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/dpll/dpll_netlink.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 442a0ebeb953..ce7cf736f020 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -925,7 +925,6 @@ dpll_pin_parent_pin_set(struct dpll_pin *pin, struct nlattr *parent_nest,
 			struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[DPLL_A_PIN_MAX + 1];
-	enum dpll_pin_state state;
 	u32 ppin_idx;
 	int ret;
 
@@ -936,10 +935,14 @@ dpll_pin_parent_pin_set(struct dpll_pin *pin, struct nlattr *parent_nest,
 		return -EINVAL;
 	}
 	ppin_idx = nla_get_u32(tb[DPLL_A_PIN_PARENT_ID]);
-	state = nla_get_u32(tb[DPLL_A_PIN_STATE]);
-	ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack);
-	if (ret)
-		return ret;
+
+	if (tb[DPLL_A_PIN_STATE]) {
+		enum dpll_pin_state state = nla_get_u32(tb[DPLL_A_PIN_STATE]);
+
+		ret = dpll_pin_on_pin_state_set(pin, ppin_idx, state, extack);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From f3f32a356c0d2379d4431364e74f101f8f075ce3 Mon Sep 17 00:00:00 2001
From: Salvatore Dipietro <dipiets@amazon.com>
Date: Fri, 8 Dec 2023 10:20:49 -0800
Subject: tcp: disable tcp_autocorking for socket when TCP_NODELAY flag is set

Based on the tcp man page, if TCP_NODELAY is set, it disables Nagle's algorithm
and packets are sent as soon as possible. However in the `tcp_push` function
where autocorking is evaluated the `nonagle` value set by TCP_NODELAY is not
considered which can trigger unexpected corking of packets and induce delays.

For example, if two packets are generated as part of a server's reply, if the
first one is not transmitted on the wire quickly enough, the second packet can
trigger the autocorking in `tcp_push` and be delayed instead of sent as soon as
possible. It will either wait for additional packets to be coalesced or an ACK
from the client before transmitting the corked packet. This can interact badly
if the receiver has tcp delayed acks enabled, introducing 40ms extra delay in
completion times. It is not always possible to control who has delayed acks
set, but it is possible to adjust when and how autocorking is triggered.
Patch prevents autocorking if the TCP_NODELAY flag is set on the socket.

Patch has been tested using an AWS c7g.2xlarge instance with Ubuntu 22.04 and
Apache Tomcat 9.0.83 running the basic servlet below:

import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import javax.servlet.ServletException;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;

public class HelloWorldServlet extends HttpServlet {
    @Override
    protected void doGet(HttpServletRequest request, HttpServletResponse response)
      throws ServletException, IOException {
        response.setContentType("text/html;charset=utf-8");
        OutputStreamWriter osw = new OutputStreamWriter(response.getOutputStream(),"UTF-8");
        String s = "a".repeat(3096);
        osw.write(s,0,s.length());
        osw.flush();
    }
}

Load was applied using  wrk2 (https://github.com/kinvolk/wrk2) from an AWS
c6i.8xlarge instance.  With the current auto-corking behavior and TCP_NODELAY
set an additional 40ms latency from P99.99+ values are observed.  With the
patch applied we see no occurrences of 40ms latencies. The patch has also been
tested with iperf and uperf benchmarks and no regression was observed.

# No patch with tcp_autocorking=1 and TCP_NODELAY set on all sockets
./wrk -t32 -c128 -d40s --latency -R10000  http://172.31.49.177:8080/hello/hello'
  ...
 50.000%    0.91ms
 75.000%    1.12ms
 90.000%    1.46ms
 99.000%    1.73ms
 99.900%    1.96ms
 99.990%   43.62ms   <<< 40+ ms extra latency
 99.999%   48.32ms
100.000%   49.34ms

# With patch
./wrk -t32 -c128 -d40s --latency -R10000  http://172.31.49.177:8080/hello/hello'
  ...
 50.000%    0.89ms
 75.000%    1.13ms
 90.000%    1.44ms
 99.000%    1.67ms
 99.900%    1.78ms
 99.990%    2.27ms   <<< no 40+ ms extra latency
 99.999%    3.71ms
100.000%    4.57ms

Fixes: f54b311142a9 ("tcp: auto corking")
Signed-off-by: Salvatore Dipietro <dipiets@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ff6838ca2e58..96fc89ccec33 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -716,7 +716,7 @@ void tcp_push(struct sock *sk, int flags, int mss_now,
 
 	tcp_mark_urg(tp, flags);
 
-	if (tcp_should_autocork(sk, skb, size_goal)) {
+	if (!nonagle && tcp_should_autocork(sk, skb, size_goal)) {
 
 		/* avoid atomic op if TSQ_THROTTLED bit is already set */
 		if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
-- 
cgit v1.2.3


From e87d3a1370ce9f04770d789bcf7cce44865d2e8d Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Mon, 11 Dec 2023 18:33:11 +0800
Subject: stmmac: dwmac-loongson: Make sure MDIO is initialized before use

Generic code will use mdio. If it is not initialized before use,
the kernel will Oops.

Fixes: 30bba69d7db4 ("stmmac: pci: Add dwmac support for Loongson")
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 2cd6fce5c993..e7701326adc6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -68,17 +68,15 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	if (!plat)
 		return -ENOMEM;
 
+	plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
+					   sizeof(*plat->mdio_bus_data),
+					   GFP_KERNEL);
+	if (!plat->mdio_bus_data)
+		return -ENOMEM;
+
 	plat->mdio_node = of_get_child_by_name(np, "mdio");
 	if (plat->mdio_node) {
 		dev_info(&pdev->dev, "Found MDIO subnode\n");
-
-		plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
-						   sizeof(*plat->mdio_bus_data),
-						   GFP_KERNEL);
-		if (!plat->mdio_bus_data) {
-			ret = -ENOMEM;
-			goto err_put_node;
-		}
 		plat->mdio_bus_data->needs_reset = true;
 	}
 
-- 
cgit v1.2.3


From 31fea092c6f9f8fb2c40a08137907f5fbeae55dd Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 11 Dec 2023 18:33:53 +0800
Subject: stmmac: dwmac-loongson: drop useless check for compatible fallback

Device binds to proper PCI ID (LOONGSON, 0x7a03), already listed in DTS,
so checking for some other compatible does not make sense.  It cannot be
bound to unsupported platform.

Drop useless, incorrect (space in between) and undocumented compatible.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index e7701326adc6..9e40c28d453a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -59,11 +59,6 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 		return -ENODEV;
 	}
 
-	if (!of_device_is_compatible(np, "loongson, pci-gmac")) {
-		pr_info("dwmac_loongson_pci: Incompatible OF node\n");
-		return -ENODEV;
-	}
-
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
 	if (!plat)
 		return -ENOMEM;
-- 
cgit v1.2.3


From 4907a3f54b12b8209864572a312cf967befcae80 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 11 Dec 2023 18:33:54 +0800
Subject: MIPS: dts: loongson: drop incorrect dwmac fallback compatible

Device binds to proper PCI ID (LOONGSON, 0x7a03), already listed in DTS,
so checking for some other compatible does not make sense.  It cannot be
bound to unsupported platform.

Drop useless, incorrect (space in between) and undocumented compatible.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi | 3 +--
 arch/mips/boot/dts/loongson/ls7a-pch.dtsi          | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
index f878f47e4501..ee3e2153dd13 100644
--- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
+++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
@@ -130,8 +130,7 @@
 				compatible = "pci0014,7a03.0",
 						   "pci0014,7a03",
 						   "pciclass0c0320",
-						   "pciclass0c03",
-						   "loongson, pci-gmac";
+						   "pciclass0c03";
 
 				reg = <0x1800 0x0 0x0 0x0 0x0>;
 				interrupts = <12 IRQ_TYPE_LEVEL_LOW>,
diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
index 7c69e8245c2f..cce9428afc41 100644
--- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
+++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
@@ -193,8 +193,7 @@
 				compatible = "pci0014,7a03.0",
 						   "pci0014,7a03",
 						   "pciclass020000",
-						   "pciclass0200",
-						   "loongson, pci-gmac";
+						   "pciclass0200";
 
 				reg = <0x1800 0x0 0x0 0x0 0x0>;
 				interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
-- 
cgit v1.2.3


From 9702817384aa4a3700643d0b26e71deac0172cfd Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 13 Dec 2023 10:56:29 -0800
Subject: Revert "tcp: disable tcp_autocorking for socket when TCP_NODELAY flag
 is set"

This reverts commit f3f32a356c0d2379d4431364e74f101f8f075ce3.

Paolo reports that the change disables autocorking even after
the userspace sets TCP_CORK.

Fixes: f3f32a356c0d ("tcp: disable tcp_autocorking for socket when TCP_NODELAY flag is set")
Link: https://lore.kernel.org/r/0d30d5a41d3ac990573016308aaeacb40a9dc79f.camel@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 96fc89ccec33..ff6838ca2e58 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -716,7 +716,7 @@ void tcp_push(struct sock *sk, int flags, int mss_now,
 
 	tcp_mark_urg(tp, flags);
 
-	if (!nonagle && tcp_should_autocork(sk, skb, size_goal)) {
+	if (tcp_should_autocork(sk, skb, size_goal)) {
 
 		/* avoid atomic op if TSQ_THROTTLED bit is already set */
 		if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
-- 
cgit v1.2.3


From 60316d7f10b17a7ebb1ead0642fee8710e1560e0 Mon Sep 17 00:00:00 2001
From: Nikolay Kuratov <kniv@yandex-team.ru>
Date: Mon, 11 Dec 2023 19:23:17 +0300
Subject: vsock/virtio: Fix unsigned integer wrap around in
 virtio_transport_has_space()

We need to do signed arithmetic if we expect condition
`if (bytes < 0)` to be possible

Found by Linux Verification Center (linuxtesting.org) with SVACE

Fixes: 06a8fc78367d ("VSOCK: Introduce virtio_vsock_common.ko")
Signed-off-by: Nikolay Kuratov <kniv@yandex-team.ru>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://lore.kernel.org/r/20231211162317.4116625-1-kniv@yandex-team.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/virtio_transport_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index c8e162c9d1df..6df246b53260 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -843,7 +843,7 @@ static s64 virtio_transport_has_space(struct vsock_sock *vsk)
 	struct virtio_vsock_sock *vvs = vsk->trans;
 	s64 bytes;
 
-	bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
+	bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
 	if (bytes < 0)
 		bytes = 0;
 
-- 
cgit v1.2.3


From 23d05d563b7e7b0314e65c8e882bc27eac2da8e7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 12 Dec 2023 16:46:21 +0000
Subject: net: prevent mss overflow in skb_segment()

Once again syzbot is able to crash the kernel in skb_segment() [1]

GSO_BY_FRAGS is a forbidden value, but unfortunately the following
computation in skb_segment() can reach it quite easily :

	mss = mss * partial_segs;

65535 = 3 * 5 * 17 * 257, so many initial values of mss can lead to
a bad final result.

Make sure to limit segmentation so that the new mss value is smaller
than GSO_BY_FRAGS.

[1]

general protection fault, probably for non-canonical address 0xdffffc000000000e: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077]
CPU: 1 PID: 5079 Comm: syz-executor993 Not tainted 6.7.0-rc4-syzkaller-00141-g1ae4cd3cbdd0 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/10/2023
RIP: 0010:skb_segment+0x181d/0x3f30 net/core/skbuff.c:4551
Code: 83 e3 02 e9 fb ed ff ff e8 90 68 1c f9 48 8b 84 24 f8 00 00 00 48 8d 78 70 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 8a 21 00 00 48 8b 84 24 f8 00
RSP: 0018:ffffc900043473d0 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: 0000000000010046 RCX: ffffffff886b1597
RDX: 000000000000000e RSI: ffffffff886b2520 RDI: 0000000000000070
RBP: ffffc90004347578 R08: 0000000000000005 R09: 000000000000ffff
R10: 000000000000ffff R11: 0000000000000002 R12: ffff888063202ac0
R13: 0000000000010000 R14: 000000000000ffff R15: 0000000000000046
FS: 0000555556e7e380(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020010000 CR3: 0000000027ee2000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
udp6_ufo_fragment+0xa0e/0xd00 net/ipv6/udp_offload.c:109
ipv6_gso_segment+0x534/0x17e0 net/ipv6/ip6_offload.c:120
skb_mac_gso_segment+0x290/0x610 net/core/gso.c:53
__skb_gso_segment+0x339/0x710 net/core/gso.c:124
skb_gso_segment include/net/gso.h:83 [inline]
validate_xmit_skb+0x36c/0xeb0 net/core/dev.c:3626
__dev_queue_xmit+0x6f3/0x3d60 net/core/dev.c:4338
dev_queue_xmit include/linux/netdevice.h:3134 [inline]
packet_xmit+0x257/0x380 net/packet/af_packet.c:276
packet_snd net/packet/af_packet.c:3087 [inline]
packet_sendmsg+0x24c6/0x5220 net/packet/af_packet.c:3119
sock_sendmsg_nosec net/socket.c:730 [inline]
__sock_sendmsg+0xd5/0x180 net/socket.c:745
__sys_sendto+0x255/0x340 net/socket.c:2190
__do_sys_sendto net/socket.c:2202 [inline]
__se_sys_sendto net/socket.c:2198 [inline]
__x64_sys_sendto+0xe0/0x1b0 net/socket.c:2198
do_syscall_x64 arch/x86/entry/common.c:52 [inline]
do_syscall_64+0x40/0x110 arch/x86/entry/common.c:83
entry_SYSCALL_64_after_hwframe+0x63/0x6b
RIP: 0033:0x7f8692032aa9
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 d1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fff8d685418 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f8692032aa9
RDX: 0000000000010048 RSI: 00000000200000c0 RDI: 0000000000000003
RBP: 00000000000f4240 R08: 0000000020000540 R09: 0000000000000014
R10: 0000000000000000 R11: 0000000000000246 R12: 00007fff8d685480
R13: 0000000000000001 R14: 00007fff8d685480 R15: 0000000000000003
</TASK>
Modules linked in:
---[ end trace 0000000000000000 ]---
RIP: 0010:skb_segment+0x181d/0x3f30 net/core/skbuff.c:4551
Code: 83 e3 02 e9 fb ed ff ff e8 90 68 1c f9 48 8b 84 24 f8 00 00 00 48 8d 78 70 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 8a 21 00 00 48 8b 84 24 f8 00
RSP: 0018:ffffc900043473d0 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: 0000000000010046 RCX: ffffffff886b1597
RDX: 000000000000000e RSI: ffffffff886b2520 RDI: 0000000000000070
RBP: ffffc90004347578 R08: 0000000000000005 R09: 000000000000ffff
R10: 000000000000ffff R11: 0000000000000002 R12: ffff888063202ac0
R13: 0000000000010000 R14: 000000000000ffff R15: 0000000000000046
FS: 0000555556e7e380(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020010000 CR3: 0000000027ee2000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fixes: 3953c46c3ac7 ("sk_buff: allow segmenting based on frag sizes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20231212164621.4131800-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skbuff.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b157efea5dea..83af8aaeb893 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4522,8 +4522,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 		/* GSO partial only requires that we trim off any excess that
 		 * doesn't fit into an MSS sized block, so take care of that
 		 * now.
+		 * Cap len to not accidentally hit GSO_BY_FRAGS.
 		 */
-		partial_segs = len / mss;
+		partial_segs = min(len, GSO_BY_FRAGS - 1) / mss;
 		if (partial_segs > 1)
 			mss *= partial_segs;
 		else
-- 
cgit v1.2.3


From 2aad7d4189a923b24efa8ea6ad09059882b1bfe4 Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Tue, 12 Dec 2023 18:43:25 +0200
Subject: dpaa2-switch: fix size of the dma_unmap

The size of the DMA unmap was wrongly put as a sizeof of a pointer.
Change the value of the DMA unmap to be the actual macro used for the
allocation and the DMA map.

Fixes: 1110318d83e8 ("dpaa2-switch: add tc flower hardware offload on ingress traffic")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://lore.kernel.org/r/20231212164326.2753457-2-ioana.ciornei@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
index 4798fb7fe35d..b6a534a3e0b1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c
@@ -139,7 +139,8 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block,
 	err = dpsw_acl_add_entry(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				 filter_block->acl_id, acl_entry_cfg);
 
-	dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff),
+	dma_unmap_single(dev, acl_entry_cfg->key_iova,
+			 DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE,
 			 DMA_TO_DEVICE);
 	if (err) {
 		dev_err(dev, "dpsw_acl_add_entry() failed %d\n", err);
@@ -181,8 +182,8 @@ dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block,
 	err = dpsw_acl_remove_entry(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				    block->acl_id, acl_entry_cfg);
 
-	dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff),
-			 DMA_TO_DEVICE);
+	dma_unmap_single(dev, acl_entry_cfg->key_iova,
+			 DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE, DMA_TO_DEVICE);
 	if (err) {
 		dev_err(dev, "dpsw_acl_remove_entry() failed %d\n", err);
 		kfree(cmd_buff);
-- 
cgit v1.2.3


From f24a49a375f65e8e75ee1b19d806f46dbaae57fd Mon Sep 17 00:00:00 2001
From: Ioana Ciornei <ioana.ciornei@nxp.com>
Date: Tue, 12 Dec 2023 18:43:26 +0200
Subject: dpaa2-switch: do not ask for MDB, VLAN and FDB replay

Starting with commit 4e51bf44a03a ("net: bridge: move the switchdev
object replay helpers to "push" mode") the switchdev_bridge_port_offload()
helper was extended with the intention to provide switchdev drivers easy
access to object addition and deletion replays. This works by calling
the replay helpers with non-NULL notifier blocks.

In the same commit, the dpaa2-switch driver was updated so that it
passes valid notifier blocks to the helper. At that moment, no
regression was identified through testing.

In the meantime, the blamed commit changed the behavior in terms of
which ports get hit by the replay. Before this commit, only the initial
port which identified itself as offloaded through
switchdev_bridge_port_offload() got a replay of all port objects and
FDBs. After this, the newly joining port will trigger a replay of
objects on all bridge ports and on the bridge itself.

This behavior leads to errors in dpaa2_switch_port_vlans_add() when a
VLAN gets installed on the same interface multiple times.

The intended mechanism to address this is to pass a non-NULL ctx to the
switchdev_bridge_port_offload() helper and then check it against the
port's private structure. But since the driver does not have any use for
the replayed port objects and FDBs until it gains support for LAG
offload, it's better to fix the issue by reverting the dpaa2-switch
driver to not ask for replay. The pointers will be added back when we
are prepared to ignore replays on unrelated ports.

Fixes: b28d580e2939 ("net: bridge: switchdev: replay all VLAN groups")
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://lore.kernel.org/r/20231212164326.2753457-3-ioana.ciornei@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index 97d3151076d5..e01a246124ac 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -1998,9 +1998,6 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev,
 	return notifier_from_errno(err);
 }
 
-static struct notifier_block dpaa2_switch_port_switchdev_nb;
-static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb;
-
 static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 					 struct net_device *upper_dev,
 					 struct netlink_ext_ack *extack)
@@ -2043,9 +2040,7 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 		goto err_egress_flood;
 
 	err = switchdev_bridge_port_offload(netdev, netdev, NULL,
-					    &dpaa2_switch_port_switchdev_nb,
-					    &dpaa2_switch_port_switchdev_blocking_nb,
-					    false, extack);
+					    NULL, NULL, false, extack);
 	if (err)
 		goto err_switchdev_offload;
 
@@ -2079,9 +2074,7 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo
 
 static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev)
 {
-	switchdev_bridge_port_unoffload(netdev, NULL,
-					&dpaa2_switch_port_switchdev_nb,
-					&dpaa2_switch_port_switchdev_blocking_nb);
+	switchdev_bridge_port_unoffload(netdev, NULL, NULL, NULL);
 }
 
 static int dpaa2_switch_port_bridge_leave(struct net_device *netdev)
-- 
cgit v1.2.3


From 981d947bcd382c3950a593690e0e13d194d65b1c Mon Sep 17 00:00:00 2001
From: Sneh Shah <quic_snehshah@quicinc.com>
Date: Tue, 12 Dec 2023 14:52:08 +0530
Subject: net: stmmac: dwmac-qcom-ethqos: Fix drops in 10M SGMII RX

In 10M SGMII mode all the packets are being dropped due to wrong Rx clock.
SGMII 10MBPS mode needs RX clock divider programmed to avoid drops in Rx.
Update configure SGMII function with Rx clk divider programming.

Fixes: 463120c31c58 ("net: stmmac: dwmac-qcom-ethqos: add support for SGMII")
Tested-by: Andrew Halaney <ahalaney@redhat.com>
Signed-off-by: Sneh Shah <quic_snehshah@quicinc.com>
Reviewed-by: Bjorn Andersson <quic_bjorande@quicinc.com>
Link: https://lore.kernel.org/r/20231212092208.22393-1-quic_snehshah@quicinc.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index d3bf42d0fceb..31631e3f89d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -34,6 +34,7 @@
 #define RGMII_CONFIG_LOOPBACK_EN		BIT(2)
 #define RGMII_CONFIG_PROG_SWAP			BIT(1)
 #define RGMII_CONFIG_DDR_MODE			BIT(0)
+#define RGMII_CONFIG_SGMII_CLK_DVDR		GENMASK(18, 10)
 
 /* SDCC_HC_REG_DLL_CONFIG fields */
 #define SDCC_DLL_CONFIG_DLL_RST			BIT(30)
@@ -78,6 +79,8 @@
 #define ETHQOS_MAC_CTRL_SPEED_MODE		BIT(14)
 #define ETHQOS_MAC_CTRL_PORT_SEL		BIT(15)
 
+#define SGMII_10M_RX_CLK_DVDR			0x31
+
 struct ethqos_emac_por {
 	unsigned int offset;
 	unsigned int value;
@@ -598,6 +601,9 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos)
 	return 0;
 }
 
+/* On interface toggle MAC registers gets reset.
+ * Configure MAC block for SGMII on ethernet phy link up
+ */
 static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 {
 	int val;
@@ -617,6 +623,10 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos)
 	case SPEED_10:
 		val |= ETHQOS_MAC_CTRL_PORT_SEL;
 		val &= ~ETHQOS_MAC_CTRL_SPEED_MODE;
+		rgmii_updatel(ethqos, RGMII_CONFIG_SGMII_CLK_DVDR,
+			      FIELD_PREP(RGMII_CONFIG_SGMII_CLK_DVDR,
+					 SGMII_10M_RX_CLK_DVDR),
+			      RGMII_IO_MACRO_CONFIG);
 		break;
 	}
 
-- 
cgit v1.2.3


From e23c0d21ce9234fbc31ece35663ababbb83f9347 Mon Sep 17 00:00:00 2001
From: Andrew Halaney <ahalaney@redhat.com>
Date: Tue, 12 Dec 2023 16:18:33 -0600
Subject: net: stmmac: Handle disabled MDIO busses from devicetree

Many hardware configurations have the MDIO bus disabled, and are instead
using some other MDIO bus to talk to the MAC's phy.

of_mdiobus_register() returns -ENODEV in this case. Let's handle it
gracefully instead of failing to probe the MAC.

Fixes: 47dd7a540b8a ("net: add support for STMicroelectronics Ethernet controllers.")
Signed-off-by: Andrew Halaney <ahalaney@redhat.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://lore.kernel.org/r/20231212-b4-stmmac-handle-mdio-enodev-v2-1-600171acf79f@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index fa9e7e7040b9..0542cfd1817e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -591,7 +591,11 @@ int stmmac_mdio_register(struct net_device *ndev)
 	new_bus->parent = priv->device;
 
 	err = of_mdiobus_register(new_bus, mdio_node);
-	if (err != 0) {
+	if (err == -ENODEV) {
+		err = 0;
+		dev_info(dev, "MDIO bus is disabled\n");
+		goto bus_register_fail;
+	} else if (err) {
 		dev_err_probe(dev, err, "Cannot register the MDIO bus\n");
 		goto bus_register_fail;
 	}
-- 
cgit v1.2.3


From 189ff16722ee36ced4d2a2469d4ab65a8fee4198 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <v4bel@theori.io>
Date: Tue, 12 Dec 2023 23:10:56 -0500
Subject: appletalk: Fix Use-After-Free in atalk_ioctl

Because atalk_ioctl() accesses sk->sk_receive_queue
without holding a sk->sk_receive_queue.lock, it can
cause a race with atalk_recvmsg().
A use-after-free for skb occurs with the following flow.
```
atalk_ioctl() -> skb_peek()
atalk_recvmsg() -> skb_recv_datagram() -> skb_free_datagram()
```
Add sk->sk_receive_queue.lock to atalk_ioctl() to fix this issue.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Hyunwoo Kim <v4bel@theori.io>
Link: https://lore.kernel.org/r/20231213041056.GA519680@v4bel-B760M-AORUS-ELITE-AX
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/appletalk/ddp.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 9ba04a69ec2a..a852ec093fa8 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1775,15 +1775,14 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		break;
 	}
 	case TIOCINQ: {
-		/*
-		 * These two are safe on a single CPU system as only
-		 * user tasks fiddle here
-		 */
-		struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+		struct sk_buff *skb;
 		long amount = 0;
 
+		spin_lock_irq(&sk->sk_receive_queue.lock);
+		skb = skb_peek(&sk->sk_receive_queue);
 		if (skb)
 			amount = skb->len - sizeof(struct ddpehdr);
+		spin_unlock_irq(&sk->sk_receive_queue.lock);
 		rc = put_user(amount, (int __user *)argp);
 		break;
 	}
-- 
cgit v1.2.3


From 7bb26ea74aa86fdf894b7dbd8c5712c5b4187da7 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <irusskikh@marvell.com>
Date: Wed, 13 Dec 2023 10:40:44 +0100
Subject: net: atlantic: fix double free in ring reinit logic

Driver has a logic leak in ring data allocation/free,
where double free may happen in aq_ring_free if system is under
stress and driver init/deinit is happening.

The probability is higher to get this during suspend/resume cycle.

Verification was done simulating same conditions with

    stress -m 2000 --vm-bytes 20M --vm-hang 10 --backoff 1000
    while true; do sudo ifconfig enp1s0 down; sudo ifconfig enp1s0 up; done

Fixed by explicitly clearing pointers to NULL on deallocation

Fixes: 018423e90bee ("net: ethernet: aquantia: Add ring support code")
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Closes: https://lore.kernel.org/netdev/CAHk-=wiZZi7FcvqVSUirHBjx0bBUZ4dFrMDVLc3+3HCrtq0rBA@mail.gmail.com/
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Link: https://lore.kernel.org/r/20231213094044.22988-1-irusskikh@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 694daeaf3e61..e1885c1eb100 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -938,11 +938,14 @@ void aq_ring_free(struct aq_ring_s *self)
 		return;
 
 	kfree(self->buff_ring);
+	self->buff_ring = NULL;
 
-	if (self->dx_ring)
+	if (self->dx_ring) {
 		dma_free_coherent(aq_nic_get_dev(self->aq_nic),
 				  self->size * self->dx_size, self->dx_ring,
 				  self->dx_ring_pa);
+		self->dx_ring = NULL;
+	}
 }
 
 unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data)
-- 
cgit v1.2.3