[PATCH AUTOSEL 5.17 020/149] net/mlx5e: TC, Hold sample_attr on stack instead of pointer

[PATCH AUTOSEL 5.17 020/149] net/mlx5e: TC, Hold sample_attr on stack instead of pointer

[Sasha Levin]

From: Roi Dayan <roid@nvidia.com>

[ Upstream commit eeed226ed110ed40598e60e29b66643012277be7 ]

In later commit we are going to instantiate multiple attr instances
for flow instead of single attr.
Parsing TC sample allocates a new memory but there is no symmetric
cleanup in the infrastructure.
To avoid asymmetric alloc/free use sample_attr as part of the flow attr
and not allocated and held as a pointer.
This will avoid a cleanup leak when sample action is not on the first
attr.

Signed-off-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Oz Shlomo <ozsh@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c |  7 +------
 drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c | 10 +++++-----
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c        |  1 -
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h        |  2 +-
 .../net/ethernet/mellanox/mlx5/core/eswitch_offloads.c |  6 +++---
 5 files changed, 10 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c
index 6699bdf5cf01..b895c378cfaf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c
@@ -27,11 +27,7 @@ tc_act_parse_sample(struct mlx5e_tc_act_parse_state *parse_state,
 		    struct mlx5e_priv *priv,
 		    struct mlx5_flow_attr *attr)
 {
-	struct mlx5e_sample_attr *sample_attr;
-
-	sample_attr = kzalloc(sizeof(*attr->sample_attr), GFP_KERNEL);
-	if (!sample_attr)
-		return -ENOMEM;
+	struct mlx5e_sample_attr *sample_attr = &attr->sample_attr;
 
 	sample_attr->rate = act->sample.rate;
 	sample_attr->group_num = act->sample.psample_group->group_num;
@@ -39,7 +35,6 @@ tc_act_parse_sample(struct mlx5e_tc_act_parse_state *parse_state,
 	if (act->sample.truncate)
 		sample_attr->trunc_size = act->sample.trunc_size;
 
-	attr->sample_attr = sample_attr;
 	flow_flag_set(parse_state->flow, SAMPLE);
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
index ff4b4f8a5a9d..0faaf9a4b531 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
@@ -513,7 +513,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
 	sample_flow = kzalloc(sizeof(*sample_flow), GFP_KERNEL);
 	if (!sample_flow)
 		return ERR_PTR(-ENOMEM);
-	sample_attr = attr->sample_attr;
+	sample_attr = &attr->sample_attr;
 	sample_attr->sample_flow = sample_flow;
 
 	/* For NICs with reg_c_preserve support or decap action, use
@@ -546,6 +546,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
 		err = PTR_ERR(sample_flow->sampler);
 		goto err_sampler;
 	}
+	sample_attr->sampler_id = sample_flow->sampler->sampler_id;
 
 	/* Create an id mapping reg_c0 value to sample object. */
 	restore_obj.type = MLX5_MAPPED_OBJ_SAMPLE;
@@ -585,8 +586,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
 	pre_attr->outer_match_level = attr->outer_match_level;
 	pre_attr->chain = attr->chain;
 	pre_attr->prio = attr->prio;
-	pre_attr->sample_attr = attr->sample_attr;
-	sample_attr->sampler_id = sample_flow->sampler->sampler_id;
+	pre_attr->sample_attr = *sample_attr;
 	pre_esw_attr = pre_attr->esw_attr;
 	pre_esw_attr->in_mdev = esw_attr->in_mdev;
 	pre_esw_attr->in_rep = esw_attr->in_rep;
@@ -633,11 +633,11 @@ mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample,
 	 * will hit fw syndromes.
 	 */
 	esw = tc_psample->esw;
-	sample_flow = attr->sample_attr->sample_flow;
+	sample_flow = attr->sample_attr.sample_flow;
 	mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, sample_flow->pre_attr);
 
 	sample_restore_put(tc_psample, sample_flow->restore);
-	mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr->restore_obj_id);
+	mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr.restore_obj_id);
 	sampler_put(tc_psample, sample_flow->sampler);
 	if (sample_flow->post_act_handle)
 		mlx5e_tc_post_act_del(tc_psample->post_act, sample_flow->post_act_handle);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b27532a9301e..7e5c00349ccf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1634,7 +1634,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	if (flow_flag_test(flow, L3_TO_L2_DECAP))
 		mlx5e_detach_decap(priv, flow);
 
-	kfree(attr->sample_attr);
 	kvfree(attr->esw_attr->rx_tun_attr);
 	kvfree(attr->parse_attr);
 	kfree(flow->attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 5ffae9b13066..2f09e34db9ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -71,7 +71,7 @@ struct mlx5_flow_attr {
 	struct mlx5_fc *counter;
 	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5_ct_attr ct_attr;
-	struct mlx5e_sample_attr *sample_attr;
+	struct mlx5e_sample_attr sample_attr;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	u32 chain;
 	u16 prio;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index cfcd72bad9af..e7e7b4b0dcdb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -201,12 +201,12 @@ esw_cleanup_decap_indir(struct mlx5_eswitch *esw,
 static int
 esw_setup_sampler_dest(struct mlx5_flow_destination *dest,
 		       struct mlx5_flow_act *flow_act,
-		       struct mlx5_flow_attr *attr,
+		       u32 sampler_id,
 		       int i)
 {
 	flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
-	dest[i].sampler_id = attr->sample_attr->sampler_id;
+	dest[i].sampler_id = sampler_id;
 
 	return 0;
 }
@@ -466,7 +466,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 		attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE;
 
 	if (attr->flags & MLX5_ESW_ATTR_FLAG_SAMPLE) {
-		esw_setup_sampler_dest(dest, flow_act, attr, *i);
+		esw_setup_sampler_dest(dest, flow_act, attr->sample_attr.sampler_id, *i);
 		(*i)++;
 	} else if (attr->dest_ft) {
 		esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i);
-- 
2.34.1

[PATCH AUTOSEL 5.17 026/149] RDMA/rtrs-clt: Do stop and failover outside reconnect work.

[Sasha Levin]

From: Jack Wang <jinpu.wang@ionos.com>

[ Upstream commit c1289d5d8502d62e5bc50ff066c9d6daabfc3264 ]

We can't do instant reconnect, not to DDoS server, but we should stop and
failover earlier, so there is less service interruption.

To avoid deadlock, as error_recovery is called from different callback
like rdma event or hb error handler, add a new err recovery_work.

Link: https://lore.kernel.org/r/20220114154753.983568-6-haris.iqbal@ionos.com
Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
Reviewed-by: Aleksei Marov <aleksei.marov@ionos.com>
Reviewed-by: Md Haris Iqbal <haris.iqbal@ionos.com>
Signed-off-by: Md Haris Iqbal <haris.iqbal@ionos.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/ulp/rtrs/rtrs-clt.c | 40 ++++++++++++++------------
 drivers/infiniband/ulp/rtrs/rtrs-clt.h |  1 +
 2 files changed, 23 insertions(+), 18 deletions(-)

diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 759b85f03331..df4d06d4d183 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -297,6 +297,7 @@ static bool rtrs_clt_change_state_from_to(struct rtrs_clt_path *clt_path,
 	return changed;
 }
 
+static void rtrs_clt_stop_and_destroy_conns(struct rtrs_clt_path *clt_path);
 static void rtrs_rdma_error_recovery(struct rtrs_clt_con *con)
 {
 	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
@@ -304,16 +305,7 @@ static void rtrs_rdma_error_recovery(struct rtrs_clt_con *con)
 	if (rtrs_clt_change_state_from_to(clt_path,
 					   RTRS_CLT_CONNECTED,
 					   RTRS_CLT_RECONNECTING)) {
-		struct rtrs_clt_sess *clt = clt_path->clt;
-		unsigned int delay_ms;
-
-		/*
-		 * Normal scenario, reconnect if we were successfully connected
-		 */
-		delay_ms = clt->reconnect_delay_sec * 1000;
-		queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
-				   msecs_to_jiffies(delay_ms +
-						    prandom_u32() % RTRS_RECONNECT_SEED));
+		queue_work(rtrs_wq, &clt_path->err_recovery_work);
 	} else {
 		/*
 		 * Error can happen just on establishing new connection,
@@ -1511,6 +1503,22 @@ static void rtrs_clt_init_hb(struct rtrs_clt_path *clt_path)
 static void rtrs_clt_reconnect_work(struct work_struct *work);
 static void rtrs_clt_close_work(struct work_struct *work);
 
+static void rtrs_clt_err_recovery_work(struct work_struct *work)
+{
+	struct rtrs_clt_path *clt_path;
+	struct rtrs_clt_sess *clt;
+	int delay_ms;
+
+	clt_path = container_of(work, struct rtrs_clt_path, err_recovery_work);
+	clt = clt_path->clt;
+	delay_ms = clt->reconnect_delay_sec * 1000;
+	rtrs_clt_stop_and_destroy_conns(clt_path);
+	queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
+			   msecs_to_jiffies(delay_ms +
+					    prandom_u32() %
+					    RTRS_RECONNECT_SEED));
+}
+
 static struct rtrs_clt_path *alloc_path(struct rtrs_clt_sess *clt,
 					const struct rtrs_addr *path,
 					size_t con_num, u32 nr_poll_queues)
@@ -1562,6 +1570,7 @@ static struct rtrs_clt_path *alloc_path(struct rtrs_clt_sess *clt,
 	clt_path->state = RTRS_CLT_CONNECTING;
 	atomic_set(&clt_path->connected_cnt, 0);
 	INIT_WORK(&clt_path->close_work, rtrs_clt_close_work);
+	INIT_WORK(&clt_path->err_recovery_work, rtrs_clt_err_recovery_work);
 	INIT_DELAYED_WORK(&clt_path->reconnect_dwork, rtrs_clt_reconnect_work);
 	rtrs_clt_init_hb(clt_path);
 
@@ -2326,6 +2335,7 @@ static void rtrs_clt_close_work(struct work_struct *work)
 
 	clt_path = container_of(work, struct rtrs_clt_path, close_work);
 
+	cancel_work_sync(&clt_path->err_recovery_work);
 	cancel_delayed_work_sync(&clt_path->reconnect_dwork);
 	rtrs_clt_stop_and_destroy_conns(clt_path);
 	rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CLOSED, NULL);
@@ -2638,7 +2648,6 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
 {
 	struct rtrs_clt_path *clt_path;
 	struct rtrs_clt_sess *clt;
-	unsigned int delay_ms;
 	int err;
 
 	clt_path = container_of(to_delayed_work(work), struct rtrs_clt_path,
@@ -2655,8 +2664,6 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
 	}
 	clt_path->reconnect_attempts++;
 
-	/* Stop everything */
-	rtrs_clt_stop_and_destroy_conns(clt_path);
 	msleep(RTRS_RECONNECT_BACKOFF);
 	if (rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CONNECTING, NULL)) {
 		err = init_path(clt_path);
@@ -2669,11 +2676,7 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
 reconnect_again:
 	if (rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_RECONNECTING, NULL)) {
 		clt_path->stats->reconnects.fail_cnt++;
-		delay_ms = clt->reconnect_delay_sec * 1000;
-		queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
-				   msecs_to_jiffies(delay_ms +
-						    prandom_u32() %
-						    RTRS_RECONNECT_SEED));
+		queue_work(rtrs_wq, &clt_path->err_recovery_work);
 	}
 }
 
@@ -2908,6 +2911,7 @@ int rtrs_clt_reconnect_from_sysfs(struct rtrs_clt_path *clt_path)
 						 &old_state);
 	if (changed) {
 		clt_path->reconnect_attempts = 0;
+		rtrs_clt_stop_and_destroy_conns(clt_path);
 		queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork, 0);
 	}
 	if (changed || old_state == RTRS_CLT_RECONNECTING) {
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
index d1b18a154ae0..f848c0392d98 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
@@ -134,6 +134,7 @@ struct rtrs_clt_path {
 	struct rtrs_clt_io_req	*reqs;
 	struct delayed_work	reconnect_dwork;
 	struct work_struct	close_work;
+	struct work_struct	err_recovery_work;
 	unsigned int		reconnect_attempts;
 	bool			established;
 	struct rtrs_rbuf	*rbufs;
-- 
2.34.1

[PATCH AUTOSEL 5.17 074/149] net/mlx5e: Disable TX queues before registering the netdev

[Sasha Levin]

From: Maxim Mikityanskiy <maximmi@nvidia.com>

[ Upstream commit d08c6e2a4d0308a7922d7ef3b1b3af45d4096aad ]

Normally, the queues are disabled when the channels are deactivated, and
enabled when the channels are activated. However, on register, the
channels are not active, but the queues are enabled by default. This
change fixes it, preventing mlx5e_xmit from running when the channels
are deactivated in the beginning.

Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3667f5ef5990..169e3524bb1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5345,6 +5345,7 @@ mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *prof
 	}
 
 	netif_carrier_off(netdev);
+	netif_tx_disable(netdev);
 	dev_net_set(netdev, mlx5_core_net(mdev));
 
 	return netdev;
-- 
2.34.1

[PATCH AUTOSEL 5.17 132/149] net/mlx5e: Remove overzealous validations in netlink EEPROM query

[Sasha Levin]

From: Gal Pressman <gal@nvidia.com>

[ Upstream commit 970adfb76095fa719778d70a6b86030d2feb88dd ]

Unlike the legacy EEPROM callbacks, when using the netlink EEPROM query
(get_module_eeprom_by_page) the driver should not try to validate the
query parameters, but just perform the read requested by the userspace.

Recent discussion in the mailing list:
https://lore.kernel.org/netdev/20220120093051.70845141@kicinski-fedora-PC1C0HJN.hsd1.ca.comcast.net/

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/port.c    | 23 -------------------
 1 file changed, 23 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 7b16a1188aab..fd79860de723 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -433,35 +433,12 @@ int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
 				     struct mlx5_module_eeprom_query_params *params,
 				     u8 *data)
 {
-	u8 module_id;
 	int err;
 
 	err = mlx5_query_module_num(dev, &params->module_number);
 	if (err)
 		return err;
 
-	err = mlx5_query_module_id(dev, params->module_number, &module_id);
-	if (err)
-		return err;
-
-	switch (module_id) {
-	case MLX5_MODULE_ID_SFP:
-		if (params->page > 0)
-			return -EINVAL;
-		break;
-	case MLX5_MODULE_ID_QSFP:
-	case MLX5_MODULE_ID_QSFP28:
-	case MLX5_MODULE_ID_QSFP_PLUS:
-		if (params->page > 3)
-			return -EINVAL;
-		break;
-	case MLX5_MODULE_ID_DSFP:
-		break;
-	default:
-		mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id);
-		return -EINVAL;
-	}
-
 	if (params->i2c_address != MLX5_I2C_ADDR_HIGH &&
 	    params->i2c_address != MLX5_I2C_ADDR_LOW) {
 		mlx5_core_err(dev, "I2C address not recognized: 0x%x\n", params->i2c_address);
-- 
2.34.1