From: Carolina Jubran When changing a node's parent, its scheduling element is destroyed and re-created with bw_share 0. However, the node's bw_share field was not updated accordingly. Set the node's bw_share to 0 after re-creation to keep the software state in sync with the firmware configuration. Fixes: 9c7bbf4c3304 ("net/mlx5: Add support for setting parent of nodes") Signed-off-by: Carolina Jubran Reviewed-by: Cosmin Ratiu Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan --- drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index b6ae384396b3..ad9f6fca9b6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -1076,6 +1076,7 @@ static int esw_qos_vports_node_update_parent(struct mlx5_esw_sched_node *node, return err; } esw_qos_node_set_parent(node, parent); + node->bw_share = 0; return 0; } -- 2.31.1 From: Carolina Jubran There's a race between disabling DIM and NAPI callbacks using the dim pointer on the RQ or SQ. If NAPI checks the DIM state bit and sees it still set, it assumes `rq->dim` or `sq->dim` is valid. But if DIM gets disabled right after that check, the pointer might already be set to NULL, leading to a NULL pointer dereference in net_dim(). Fix this by calling `synchronize_net()` before freeing the DIM context. This ensures all in-progress NAPI callbacks are finished before the pointer is cleared. Kernel log: BUG: kernel NULL pointer dereference, address: 0000000000000000 ... RIP: 0010:net_dim+0x23/0x190 ... Call Trace: ? __die+0x20/0x60 ? page_fault_oops+0x150/0x3e0 ? common_interrupt+0xf/0xa0 ? sysvec_call_function_single+0xb/0x90 ? exc_page_fault+0x74/0x130 ? asm_exc_page_fault+0x22/0x30 ? net_dim+0x23/0x190 ? mlx5e_poll_ico_cq+0x41/0x6f0 [mlx5_core] ? sysvec_apic_timer_interrupt+0xb/0x90 mlx5e_handle_rx_dim+0x92/0xd0 [mlx5_core] mlx5e_napi_poll+0x2cd/0xac0 [mlx5_core] ? mlx5e_poll_ico_cq+0xe5/0x6f0 [mlx5_core] busy_poll_stop+0xa2/0x200 ? mlx5e_napi_poll+0x1d9/0xac0 [mlx5_core] ? mlx5e_trigger_irq+0x130/0x130 [mlx5_core] __napi_busy_loop+0x345/0x3b0 ? sysvec_call_function_single+0xb/0x90 ? asm_sysvec_call_function_single+0x16/0x20 ? sysvec_apic_timer_interrupt+0xb/0x90 ? pcpu_free_area+0x1e4/0x2e0 napi_busy_loop+0x11/0x20 xsk_recvmsg+0x10c/0x130 sock_recvmsg+0x44/0x70 __sys_recvfrom+0xbc/0x130 ? __schedule+0x398/0x890 __x64_sys_recvfrom+0x20/0x30 do_syscall_64+0x4c/0x100 entry_SYSCALL_64_after_hwframe+0x4b/0x53 ... ---[ end trace 0000000000000000 ]--- ... ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- Fixes: 445a25f6e1a2 ("net/mlx5e: Support updating coalescing configuration without resetting channels") Signed-off-by: Carolina Jubran Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan --- drivers/net/ethernet/mellanox/mlx5/core/en_dim.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c index 298bb74ec5e9..d1d629697e28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c @@ -113,7 +113,7 @@ int mlx5e_dim_rx_change(struct mlx5e_rq *rq, bool enable) __set_bit(MLX5E_RQ_STATE_DIM, &rq->state); } else { __clear_bit(MLX5E_RQ_STATE_DIM, &rq->state); - + synchronize_net(); mlx5e_dim_disable(rq->dim); rq->dim = NULL; } @@ -140,7 +140,7 @@ int mlx5e_dim_tx_change(struct mlx5e_txqsq *sq, bool enable) __set_bit(MLX5E_SQ_STATE_DIM, &sq->state); } else { __clear_bit(MLX5E_SQ_STATE_DIM, &sq->state); - + synchronize_net(); mlx5e_dim_disable(sq->dim); sq->dim = NULL; } -- 2.31.1 From: Jianbo Liu An optimization for promiscuous mode adds a high-priority steering table with a single catch-all rule to steer all traffic directly to the TTC table. However, a gap exists between the creation of this table and the insertion of the catch-all rule. Packets arriving in this brief window would miss as no rule was inserted yet, unnecessarily incrementing the 'rx_steer_missed_packets' counter and dropped. This patch resolves the issue by introducing a new prio for this table, placing it between MLX5E_TC_PRIO and MLX5E_NIC_PRIO. By doing so, packets arriving during the window now fall through to the next prio (at MLX5E_NIC_PRIO) instead of being dropped. Fixes: 1c46d7409f30 ("net/mlx5e: Optimize promiscuous mode") Signed-off-by: Jianbo Liu Reviewed-by: Mark Bloch Signed-off-by: Tariq Toukan --- drivers/net/ethernet/mellanox/mlx5/core/en/fs.h | 9 +++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 13 +++++++++---- 3 files changed, 17 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index b5c3a2a9d2a5..9560fcba643f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -18,7 +18,8 @@ enum { enum { MLX5E_TC_PRIO = 0, - MLX5E_NIC_PRIO + MLX5E_PROMISC_PRIO, + MLX5E_NIC_PRIO, }; struct mlx5e_flow_table { @@ -68,9 +69,13 @@ struct mlx5e_l2_table { MLX5_HASH_FIELD_SEL_DST_IP |\ MLX5_HASH_FIELD_SEL_IPSEC_SPI) -/* NIC prio FTS */ +/* NIC promisc FT level */ enum { MLX5E_PROMISC_FT_LEVEL, +}; + +/* NIC prio FTS */ +enum { MLX5E_VLAN_FT_LEVEL, MLX5E_L2_FT_LEVEL, MLX5E_TTC_FT_LEVEL, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 04a969128161..265c4ca85f7d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -780,7 +780,7 @@ static int mlx5e_create_promisc_table(struct mlx5e_flow_steering *fs) ft_attr.max_fte = MLX5E_PROMISC_TABLE_SIZE; ft_attr.autogroup.max_num_groups = 1; ft_attr.level = MLX5E_PROMISC_FT_LEVEL; - ft_attr.prio = MLX5E_NIC_PRIO; + ft_attr.prio = MLX5E_PROMISC_PRIO; ft->t = mlx5_create_auto_grouped_flow_table(fs->ns, &ft_attr); if (IS_ERR(ft->t)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index a8046200d376..3dd9a6f40709 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -113,13 +113,16 @@ #define ETHTOOL_PRIO_NUM_LEVELS 1 #define ETHTOOL_NUM_PRIOS 11 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS) -/* Promiscuous, Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy, +/* Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy, * {IPsec RoCE MPV,Alias table},IPsec RoCE policy */ -#define KERNEL_NIC_PRIO_NUM_LEVELS 11 +#define KERNEL_NIC_PRIO_NUM_LEVELS 10 #define KERNEL_NIC_NUM_PRIOS 1 -/* One more level for tc */ -#define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 1) +/* One more level for tc, and one more for promisc */ +#define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 2) + +#define KERNEL_NIC_PROMISC_NUM_PRIOS 1 +#define KERNEL_NIC_PROMISC_NUM_LEVELS 1 #define KERNEL_NIC_TC_NUM_PRIOS 1 #define KERNEL_NIC_TC_NUM_LEVELS 3 @@ -187,6 +190,8 @@ static struct init_tree_node { ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, ADD_MULTIPLE_PRIO(KERNEL_NIC_TC_NUM_PRIOS, KERNEL_NIC_TC_NUM_LEVELS), + ADD_MULTIPLE_PRIO(KERNEL_NIC_PROMISC_NUM_PRIOS, + KERNEL_NIC_PROMISC_NUM_LEVELS), ADD_MULTIPLE_PRIO(KERNEL_NIC_NUM_PRIOS, KERNEL_NIC_PRIO_NUM_LEVELS))), ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, FS_CHAINING_CAPS, -- 2.31.1