From 2266bb1e122a4f7cdf3427defcfb48e5c6a8f205 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Mon, 13 Sep 2021 15:48:11 +0300 Subject: [PATCH 1/6] net/mlx5: Fix cleanup of bridge delayed work Currently, bridge cleanup is calling to cancel_delayed_work(). When this function is finished, there is a chance that the delayed work is still running. Also, the delayed work is queueing itself. As a result, we might execute the delayed work after the bridge cleanup have finished and hit a null-ptr oops[1]. Fix it by using cancel_delayed_work_sync(), which is waiting until the work is done and will cancel the queue work. [1] [ 8202.143043 ] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 8202.144438 ] #PF: supervisor write access in kernel mode [ 8202.145476 ] #PF: error_code(0x0002) - not-present page [ 8202.146520 ] PGD 0 P4D 0 [ 8202.147126 ] Oops: 0002 [#1] SMP NOPTI [ 8202.147899 ] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.14.0-rc6_for_upstream_min_debug_2021_08_25_16_06 #1 [ 8202.149741 ] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 8202.151908 ] RIP: 0010:_raw_spin_lock+0xc/0x20 [ 8202.156234 ] RSP: 0018:ffff88846f885ea0 EFLAGS: 00010046 [ 8202.157289 ] RAX: 0000000000000000 RBX: ffff88846f880000 RCX: 0000000000000000 [ 8202.158731 ] RDX: 0000000000000001 RSI: ffff8881004000c8 RDI: 0000000000000000 [ 8202.160177 ] RBP: ffff8881fe684978 R08: ffff888100140000 R09: ffffffff824455b8 [ 8202.161569 ] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001 [ 8202.163004 ] R13: 0000000000000012 R14: 0000000000000200 R15: ffff88812992d000 [ 8202.164018 ] FS: 0000000000000000(0000) GS:ffff88846f880000(0000) knlGS:0000000000000000 [ 8202.164960 ] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8202.165634 ] CR2: 0000000000000000 CR3: 0000000108cac004 CR4: 0000000000370ea0 [ 8202.166450 ] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 8202.167807 ] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 8202.168852 ] Call Trace: [ 8202.169421 ] [ 8202.169792 ] __queue_work+0xf2/0x3d0 [ 8202.170481 ] ? queue_work_node+0x40/0x40 [ 8202.171270 ] call_timer_fn+0x2b/0x100 [ 8202.171932 ] __run_timers.part.0+0x152/0x220 [ 8202.172717 ] ? __hrtimer_run_queues+0x171/0x290 [ 8202.173526 ] ? kvm_clock_get_cycles+0xd/0x10 [ 8202.174232 ] ? ktime_get+0x35/0x90 [ 8202.174943 ] run_timer_softirq+0x26/0x50 [ 8202.175745 ] __do_softirq+0xc7/0x271 [ 8202.176373 ] irq_exit_rcu+0x93/0xb0 [ 8202.176983 ] sysvec_apic_timer_interrupt+0x72/0x90 [ 8202.177755 ] [ 8202.178245 ] asm_sysvec_apic_timer_interrupt+0x12/0x20 Fixes: c636a0f0f3f0 ("net/mlx5: Bridge, dynamic entry ageing") Signed-off-by: Shay Drory Reviewed-by: Vlad Buslov Reviewed-by: Leon Romanovsky Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index b5ddaa82755f..c6d2f8c78db7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -475,9 +475,6 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) esw_warn(mdev, "Failed to allocate bridge offloads workqueue\n"); goto err_alloc_wq; } - INIT_DELAYED_WORK(&br_offloads->update_work, mlx5_esw_bridge_update_work); - queue_delayed_work(br_offloads->wq, &br_offloads->update_work, - msecs_to_jiffies(MLX5_ESW_BRIDGE_UPDATE_INTERVAL)); br_offloads->nb.notifier_call = mlx5_esw_bridge_switchdev_event; err = register_switchdev_notifier(&br_offloads->nb); @@ -500,6 +497,9 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) err); goto err_register_netdev; } + INIT_DELAYED_WORK(&br_offloads->update_work, mlx5_esw_bridge_update_work); + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + msecs_to_jiffies(MLX5_ESW_BRIDGE_UPDATE_INTERVAL)); return; err_register_netdev: @@ -523,10 +523,10 @@ void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) if (!br_offloads) return; + cancel_delayed_work_sync(&br_offloads->update_work); unregister_netdevice_notifier(&br_offloads->netdev_nb); unregister_switchdev_blocking_notifier(&br_offloads->nb_blk); unregister_switchdev_notifier(&br_offloads->nb); - cancel_delayed_work(&br_offloads->update_work); destroy_workqueue(br_offloads->wq); rtnl_lock(); mlx5_esw_bridge_cleanup(esw); From ca20dfda05ae0531c8f5117b6ac989816f6cf658 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 4 Oct 2021 15:04:25 +0300 Subject: [PATCH 2/6] net/mlx5e: Allow only complete TXQs partition in MQPRIO channel mode Do not allow configurations of MQPRIO channel mode that do not fully define and utilize the channels txqs. Fixes: ec60c4581bd9 ("net/mlx5e: Support MQPRIO channel mode") Signed-off-by: Tariq Toukan Reviewed-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 0c5197f9cea3..336aa07313da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2981,8 +2981,8 @@ static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv, agg_count += mqprio->qopt.count[i]; } - if (priv->channels.params.num_channels < agg_count) { - netdev_err(netdev, "Num of queues (%d) exceeds available (%d)\n", + if (priv->channels.params.num_channels != agg_count) { + netdev_err(netdev, "Num of queues (%d) does not match available (%d)\n", agg_count, priv->channels.params.num_channels); return -EINVAL; } From 94b960b9deffc02fc0747afc01f72cc62ab099e3 Mon Sep 17 00:00:00 2001 From: Valentine Fatiev Date: Sun, 15 Aug 2021 17:43:19 +0300 Subject: [PATCH 3/6] net/mlx5e: Fix memory leak in mlx5_core_destroy_cq() error path Prior to this patch in case mlx5_core_destroy_cq() failed it returns without completing all destroy operations and that leads to memory leak. Instead, complete the destroy flow before return error. Also move mlx5_debug_cq_remove() to the beginning of mlx5_core_destroy_cq() to be symmetrical with mlx5_core_create_cq(). kmemleak complains on: unreferenced object 0xc000000038625100 (size 64): comm "ethtool", pid 28301, jiffies 4298062946 (age 785.380s) hex dump (first 32 bytes): 60 01 48 94 00 00 00 c0 b8 05 34 c3 00 00 00 c0 `.H.......4..... 02 00 00 00 00 00 00 00 00 db 7d c1 00 00 00 c0 ..........}..... backtrace: [<000000009e8643cb>] add_res_tree+0xd0/0x270 [mlx5_core] [<00000000e7cb8e6c>] mlx5_debug_cq_add+0x5c/0xc0 [mlx5_core] [<000000002a12918f>] mlx5_core_create_cq+0x1d0/0x2d0 [mlx5_core] [<00000000cef0a696>] mlx5e_create_cq+0x210/0x3f0 [mlx5_core] [<000000009c642c26>] mlx5e_open_cq+0xb4/0x130 [mlx5_core] [<0000000058dfa578>] mlx5e_ptp_open+0x7f4/0xe10 [mlx5_core] [<0000000081839561>] mlx5e_open_channels+0x9cc/0x13e0 [mlx5_core] [<0000000009cf05d4>] mlx5e_switch_priv_channels+0xa4/0x230 [mlx5_core] [<0000000042bbedd8>] mlx5e_safe_switch_params+0x14c/0x300 [mlx5_core] [<0000000004bc9db8>] set_pflag_tx_port_ts+0x9c/0x160 [mlx5_core] [<00000000a0553443>] mlx5e_set_priv_flags+0xd0/0x1b0 [mlx5_core] [<00000000a8f3d84b>] ethnl_set_privflags+0x234/0x2d0 [<00000000fd27f27c>] genl_family_rcv_msg_doit+0x108/0x1d0 [<00000000f495e2bb>] genl_family_rcv_msg+0xe4/0x1f0 [<00000000646c5c2c>] genl_rcv_msg+0x78/0x120 [<00000000d53e384e>] netlink_rcv_skb+0x74/0x1a0 Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Valentine Fatiev Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/cq.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index cf97985628ab..02e77ffe5c3e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -155,6 +155,8 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {}; int err; + mlx5_debug_cq_remove(dev, cq); + mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq); mlx5_eq_del_cq(&cq->eq->core, cq); @@ -162,16 +164,13 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) MLX5_SET(destroy_cq_in, in, cqn, cq->cqn); MLX5_SET(destroy_cq_in, in, uid, cq->uid); err = mlx5_cmd_exec_in(dev, destroy_cq, in); - if (err) - return err; synchronize_irq(cq->irqn); - mlx5_debug_cq_remove(dev, cq); mlx5_cq_put(cq); wait_for_completion(&cq->free); - return 0; + return err; } EXPORT_SYMBOL(mlx5_core_destroy_cq); From b2107cdc43d8601f2cadfba990ae844cc1f44e68 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 4 Oct 2021 21:20:25 -0700 Subject: [PATCH 4/6] net/mlx5e: Switchdev representors are not vlan challenged Before this patch, mlx5 representors advertised the NETIF_F_VLAN_CHALLENGED bit, this could lead to missing features when using reps with vxlan/bridge and maybe other virtual interfaces, when such interfaces inherit this bit and block vlan usage in their topology. Example: $ip link add dev bridge type bridge # add representor interface to the bridge $ip link set dev pf0hpf master $ip link add link bridge name vlan10 type vlan id 10 protocol 802.1q Error: 8021q: VLANs not supported on device. Reps are perfectly capable of handling vlan traffic, although they don't implement vlan_{add,kill}_vid ndos, hence, remove NETIF_F_VLAN_CHALLENGED advertisement. Fixes: cb67b832921c ("net/mlx5e: Introduce SRIOV VF representors") Reported-by: Roopa Prabhu Signed-off-by: Saeed Mahameed Reviewed-by: Roi Dayan --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 1 - 1 file changed, 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 3dd1101cc693..0439203fc7d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -643,7 +643,6 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev, netdev->hw_features |= NETIF_F_RXCSUM; netdev->features |= netdev->hw_features; - netdev->features |= NETIF_F_VLAN_CHALLENGED; netdev->features |= NETIF_F_NETNS_LOCAL; } From 0bc73ad46a76ed6ece4dcacb28858e7b38561e1c Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Sun, 26 Sep 2021 17:55:41 +0300 Subject: [PATCH 5/6] net/mlx5e: Mutually exclude RX-FCS and RX-port-timestamp Due to current HW arch limitations, RX-FCS (scattering FCS frame field to software) and RX-port-timestamp (improved timestamp accuracy on the receive side) can't work together. RX-port-timestamp is not controlled by the user and it is enabled by default when supported by the HW/FW. This patch sets RX-port-timestamp opposite to RX-FCS configuration. Fixes: 102722fc6832 ("net/mlx5e: Add support for RXFCS feature flag") Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 57 +++++++++++++++++-- include/linux/mlx5/mlx5_ifc.h | 10 +++- 2 files changed, 60 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 336aa07313da..09c8b71b186c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3325,20 +3325,67 @@ static int set_feature_rx_all(struct net_device *netdev, bool enable) return mlx5_set_port_fcs(mdev, !enable); } +static int mlx5e_set_rx_port_ts(struct mlx5_core_dev *mdev, bool enable) +{ + u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {}; + bool supported, curr_state; + int err; + + if (!MLX5_CAP_GEN(mdev, ports_check)) + return 0; + + err = mlx5_query_ports_check(mdev, in, sizeof(in)); + if (err) + return err; + + supported = MLX5_GET(pcmr_reg, in, rx_ts_over_crc_cap); + curr_state = MLX5_GET(pcmr_reg, in, rx_ts_over_crc); + + if (!supported || enable == curr_state) + return 0; + + MLX5_SET(pcmr_reg, in, local_port, 1); + MLX5_SET(pcmr_reg, in, rx_ts_over_crc, enable); + + return mlx5_set_ports_check(mdev, in, sizeof(in)); +} + static int set_feature_rx_fcs(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_channels *chs = &priv->channels; + struct mlx5_core_dev *mdev = priv->mdev; int err; mutex_lock(&priv->state_lock); - priv->channels.params.scatter_fcs_en = enable; - err = mlx5e_modify_channels_scatter_fcs(&priv->channels, enable); - if (err) - priv->channels.params.scatter_fcs_en = !enable; + if (enable) { + err = mlx5e_set_rx_port_ts(mdev, false); + if (err) + goto out; + chs->params.scatter_fcs_en = true; + err = mlx5e_modify_channels_scatter_fcs(chs, true); + if (err) { + chs->params.scatter_fcs_en = false; + mlx5e_set_rx_port_ts(mdev, true); + } + } else { + chs->params.scatter_fcs_en = false; + err = mlx5e_modify_channels_scatter_fcs(chs, false); + if (err) { + chs->params.scatter_fcs_en = true; + goto out; + } + err = mlx5e_set_rx_port_ts(mdev, true); + if (err) { + mlx5_core_warn(mdev, "Failed to set RX port timestamp %d\n", err); + err = 0; + } + } + +out: mutex_unlock(&priv->state_lock); - return err; } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f3638d09ba77..993204a6c1a1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9475,16 +9475,22 @@ struct mlx5_ifc_pcmr_reg_bits { u8 reserved_at_0[0x8]; u8 local_port[0x8]; u8 reserved_at_10[0x10]; + u8 entropy_force_cap[0x1]; u8 entropy_calc_cap[0x1]; u8 entropy_gre_calc_cap[0x1]; - u8 reserved_at_23[0x1b]; + u8 reserved_at_23[0xf]; + u8 rx_ts_over_crc_cap[0x1]; + u8 reserved_at_33[0xb]; u8 fcs_cap[0x1]; u8 reserved_at_3f[0x1]; + u8 entropy_force[0x1]; u8 entropy_calc[0x1]; u8 entropy_gre_calc[0x1]; - u8 reserved_at_43[0x1b]; + u8 reserved_at_43[0xf]; + u8 rx_ts_over_crc[0x1]; + u8 reserved_at_53[0xb]; u8 fcs_chk[0x1]; u8 reserved_at_5f[0x1]; }; From 84c8a87402cf073ba7948dd62d4815a3f4a224c8 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Mon, 11 Oct 2021 18:39:35 +0300 Subject: [PATCH 6/6] net/mlx5e: Fix division by 0 in mlx5e_select_queue for representors Commit 846d6da1fcdb ("net/mlx5e: Fix division by 0 in mlx5e_select_queue") makes mlx5e_build_nic_params assign a non-zero initial value to priv->num_tc_x_num_ch, so that mlx5e_select_queue doesn't fail with division by 0 if called before the first activation of channels. However, the initialization flow of representors doesn't call mlx5e_build_nic_params, so this bug can still happen with representors. This commit fixes the bug by adding the missing assignment to mlx5e_build_rep_params. Fixes: 846d6da1fcdb ("net/mlx5e: Fix division by 0 in mlx5e_select_queue") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 0439203fc7d9..0684ac6699b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -618,6 +618,11 @@ static void mlx5e_build_rep_params(struct net_device *netdev) params->mqprio.num_tc = 1; params->tunneled_offload_en = false; + /* Set an initial non-zero value, so that mlx5e_select_queue won't + * divide by zero if called before first activating channels. + */ + priv->num_tc_x_num_ch = params->num_channels * params->mqprio.num_tc; + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); }