From a019b36123aec9700b21ae0724710f62928a8bc1 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Thu, 9 Apr 2020 09:46:20 +0200 Subject: [PATCH 1/5] net/mlx5: Fix failing fw tracer allocation on s390 On s390 FORCE_MAX_ZONEORDER is 9 instead of 11, thus a larger kzalloc() allocation as done for the firmware tracer will always fail. Looking at mlx5_fw_tracer_save_trace(), it is actually the driver itself that copies the debug data into the trace array and there is no need for the allocation to be contiguous in physical memory. We can therefor use kvzalloc() instead of kzalloc() and get rid of the large contiguous allcoation. Fixes: f53aaa31cce7 ("net/mlx5: FW tracer, implement tracer logic") Signed-off-by: Niklas Schnelle Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index c9c9b479bda5..5ce6ebbc7f10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -935,7 +935,7 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) return NULL; } - tracer = kzalloc(sizeof(*tracer), GFP_KERNEL); + tracer = kvzalloc(sizeof(*tracer), GFP_KERNEL); if (!tracer) return ERR_PTR(-ENOMEM); @@ -982,7 +982,7 @@ destroy_workqueue: tracer->dev = NULL; destroy_workqueue(tracer->work_queue); free_tracer: - kfree(tracer); + kvfree(tracer); return ERR_PTR(err); } @@ -1061,7 +1061,7 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) mlx5_fw_tracer_destroy_log_buf(tracer); flush_workqueue(tracer->work_queue); destroy_workqueue(tracer->work_queue); - kfree(tracer); + kvfree(tracer); } static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data) From 70840b66da4d3b9a8962905d9111a53ee628beb3 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Mon, 6 Apr 2020 15:47:52 +0300 Subject: [PATCH 2/5] net/mlx5: CT: Change idr to xarray to protect parallel tuple id allocation After allowing parallel tuple insertion, we get the following trace: [ 5505.142249] ------------[ cut here ]------------ [ 5505.148155] WARNING: CPU: 21 PID: 13313 at lib/radix-tree.c:581 delete_node+0x16c/0x180 [ 5505.295553] CPU: 21 PID: 13313 Comm: kworker/u50:22 Tainted: G OE 5.6.0+ #78 [ 5505.304824] Hardware name: Supermicro Super Server/X10DRT-P, BIOS 2.0b 03/30/2017 [ 5505.313740] Workqueue: nf_flow_table_offload flow_offload_work_handler [nf_flow_table] [ 5505.323257] RIP: 0010:delete_node+0x16c/0x180 [ 5505.349862] RSP: 0018:ffffb19184eb7b30 EFLAGS: 00010282 [ 5505.356785] RAX: 0000000000000000 RBX: ffff904ac95b86d8 RCX: ffff904b6f938838 [ 5505.365190] RDX: 0000000000000000 RSI: ffff904ac954b908 RDI: ffff904ac954b920 [ 5505.373628] RBP: ffff904b4ac13060 R08: 0000000000000001 R09: 0000000000000000 [ 5505.382155] R10: 0000000000000000 R11: 0000000000000040 R12: 0000000000000000 [ 5505.390527] R13: ffffb19184eb7bfc R14: ffff904b6bef5800 R15: ffff90482c1203c0 [ 5505.399246] FS: 0000000000000000(0000) GS:ffff904c2fc80000(0000) knlGS:0000000000000000 [ 5505.408621] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 5505.415739] CR2: 00007f5d27006010 CR3: 0000000058c10006 CR4: 00000000001626e0 [ 5505.424547] Call Trace: [ 5505.428429] idr_alloc_u32+0x7b/0xc0 [ 5505.433803] mlx5_tc_ct_entry_add_rule+0xbf/0x950 [mlx5_core] [ 5505.441354] ? mlx5_fc_create+0x23c/0x370 [mlx5_core] [ 5505.448225] mlx5_tc_ct_block_flow_offload+0x874/0x10b0 [mlx5_core] [ 5505.456278] ? mlx5_tc_ct_block_flow_offload+0x63d/0x10b0 [mlx5_core] [ 5505.464532] nf_flow_offload_tuple.isra.21+0xc5/0x140 [nf_flow_table] [ 5505.472286] ? __kmalloc+0x217/0x2f0 [ 5505.477093] ? flow_rule_alloc+0x1c/0x30 [ 5505.482117] flow_offload_work_handler+0x1d0/0x290 [nf_flow_table] [ 5505.489674] ? process_one_work+0x17c/0x580 [ 5505.494922] process_one_work+0x202/0x580 [ 5505.500082] ? process_one_work+0x17c/0x580 [ 5505.505696] worker_thread+0x4c/0x3f0 [ 5505.510458] kthread+0x103/0x140 [ 5505.514989] ? process_one_work+0x580/0x580 [ 5505.520616] ? kthread_bind+0x10/0x10 [ 5505.525837] ret_from_fork+0x3a/0x50 [ 5505.570841] ---[ end trace 07995de9c56d6831 ]--- This happens from parallel deletes/adds to idr, as idr isn't protected. Fix that by using xarray as the tuple_ids allocator instead of idr. Fixes: 7da182a998d6 ("netfilter: flowtable: Use work entry per offload command") Reviewed-by: Roi Dayan Signed-off-by: Paul Blakey Reviewed-by: Oz Shlomo Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/en/tc_ct.c | 23 ++++++++++--------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 16416eaac39e..a172c5e39710 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "esw/chains.h" #include "en/tc_ct.h" @@ -35,7 +36,7 @@ struct mlx5_tc_ct_priv { struct mlx5_eswitch *esw; const struct net_device *netdev; struct idr fte_ids; - struct idr tuple_ids; + struct xarray tuple_ids; struct rhashtable zone_ht; struct mlx5_flow_table *ct; struct mlx5_flow_table *ct_nat; @@ -238,7 +239,7 @@ mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv, mlx5_eswitch_del_offloaded_rule(esw, zone_rule->rule, attr); mlx5_modify_header_dealloc(esw->dev, attr->modify_hdr); - idr_remove(&ct_priv->tuple_ids, zone_rule->tupleid); + xa_erase(&ct_priv->tuple_ids, zone_rule->tupleid); } static void @@ -483,7 +484,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_esw_flow_attr *attr = &zone_rule->attr; struct mlx5_eswitch *esw = ct_priv->esw; struct mlx5_flow_spec *spec = NULL; - u32 tupleid = 1; + u32 tupleid; int err; zone_rule->nat = nat; @@ -493,12 +494,12 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, return -ENOMEM; /* Get tuple unique id */ - err = idr_alloc_u32(&ct_priv->tuple_ids, zone_rule, &tupleid, - TUPLE_ID_MAX, GFP_KERNEL); + err = xa_alloc(&ct_priv->tuple_ids, &tupleid, zone_rule, + XA_LIMIT(1, TUPLE_ID_MAX), GFP_KERNEL); if (err) { netdev_warn(ct_priv->netdev, "Failed to allocate tuple id, err: %d\n", err); - goto err_idr_alloc; + goto err_xa_alloc; } zone_rule->tupleid = tupleid; @@ -539,8 +540,8 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, err_rule: mlx5_modify_header_dealloc(esw->dev, attr->modify_hdr); err_mod_hdr: - idr_remove(&ct_priv->tuple_ids, zone_rule->tupleid); -err_idr_alloc: + xa_erase(&ct_priv->tuple_ids, zone_rule->tupleid); +err_xa_alloc: kfree(spec); return err; } @@ -1299,7 +1300,7 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv) } idr_init(&ct_priv->fte_ids); - idr_init(&ct_priv->tuple_ids); + xa_init_flags(&ct_priv->tuple_ids, XA_FLAGS_ALLOC1); mutex_init(&ct_priv->control_lock); rhashtable_init(&ct_priv->zone_ht, &zone_params); @@ -1334,7 +1335,7 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv) rhashtable_destroy(&ct_priv->zone_ht); mutex_destroy(&ct_priv->control_lock); - idr_destroy(&ct_priv->tuple_ids); + xa_destroy(&ct_priv->tuple_ids); idr_destroy(&ct_priv->fte_ids); kfree(ct_priv); @@ -1352,7 +1353,7 @@ mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv, if (!ct_priv || !tupleid) return true; - zone_rule = idr_find(&ct_priv->tuple_ids, tupleid); + zone_rule = xa_load(&ct_priv->tuple_ids, tupleid); if (!zone_rule) return false; From e7e0004abdd6f83ae4be5613b29ed396beff576c Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 11 Feb 2020 16:02:35 +0200 Subject: [PATCH 3/5] net/mlx5e: Don't trigger IRQ multiple times on XSK wakeup to avoid WQ overruns XSK wakeup function triggers NAPI by posting a NOP WQE to a special XSK ICOSQ. When the application floods the driver with wakeup requests by calling sendto() in a certain pattern that ends up in mlx5e_trigger_irq, the XSK ICOSQ may overflow. Multiple NOPs are not required and won't accelerate the process, so avoid posting a second NOP if there is one already on the way. This way we also avoid increasing the queue size (which might not help anyway). Fixes: db05815b36cb ("net/mlx5e: Add XSK zero-copy support") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c | 3 +++ drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 8 +++++--- drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c | 6 +++++- 4 files changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 12a61bf82c14..23701c0e36ec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -367,6 +367,7 @@ enum { MLX5E_SQ_STATE_AM, MLX5E_SQ_STATE_TLS, MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, + MLX5E_SQ_STATE_PENDING_XSK_TX, }; struct mlx5e_sq_wqe_info { @@ -960,7 +961,7 @@ void mlx5e_page_release_dynamic(struct mlx5e_rq *rq, void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); -void mlx5e_poll_ico_cq(struct mlx5e_cq *cq); +int mlx5e_poll_ico_cq(struct mlx5e_cq *cq); bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq); void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix); void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index fe2d596cb361..3bcdb5b2fc20 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -33,6 +33,9 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &c->xskicosq.state))) return 0; + if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->xskicosq.state)) + return 0; + spin_lock(&c->xskicosq_lock); mlx5e_trigger_irq(&c->xskicosq); spin_unlock(&c->xskicosq_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 6173faf542b0..e2beb89c1832 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -589,7 +589,7 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) return !!err; } -void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) +int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) { struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq); struct mlx5_cqe64 *cqe; @@ -597,11 +597,11 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) int i; if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) - return; + return 0; cqe = mlx5_cqwq_get_cqe(&cq->wq); if (likely(!cqe)) - return; + return 0; /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), * otherwise a cq overrun may occur @@ -650,6 +650,8 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) sq->cc = sqcc; mlx5_cqwq_update_db_record(&cq->wq); + + return i; } bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 87c49e7a164c..acb20215a33b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -152,7 +152,11 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) mlx5e_post_rx_wqes, rq); if (xsk_open) { - mlx5e_poll_ico_cq(&c->xskicosq.cq); + if (mlx5e_poll_ico_cq(&c->xskicosq.cq)) + /* Don't clear the flag if nothing was polled to prevent + * queueing more WQEs and overflowing XSKICOSQ. + */ + clear_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->xskicosq.state); busy |= mlx5e_poll_xdpsq_cq(&xsksq->cq); busy_xsk |= mlx5e_napi_xsk_post(xsksq, xskrq); } From 96c34151d15779bcac4022e0f10e881ab33fd80f Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 16 Apr 2020 15:04:02 -0700 Subject: [PATCH 4/5] net/mlx5: Kconfig: convert imply usage to weak dependency MLX5_CORE uses the 'imply' keyword to depend on VXLAN, PTP_1588_CLOCK, MLXFW and PCI_HYPERV_INTERFACE. This was useful to force vxlan, ptp, etc.. to be reachable to mlx5 regardless of their config states. Due to the changes in the cited commit below, the semantics of 'imply' was changed to not force any restriction on the implied config. As a result of this change, the compilation of MLX5_CORE=y and VXLAN=m would result in undefined references, as VXLAN now would stay as 'm'. To fix this we change MLX5_CORE to have a weak dependency on these modules/configs and make sure they are reachable, by adding: depend on symbol || !symbol. For example: VXLAN=m MLX5_CORE=y, this will force MLX5_CORE to m Fixes: def2fbffe62c ("kconfig: allow symbols implied by y to become m") Signed-off-by: Saeed Mahameed Cc: Masahiro Yamada Cc: Nicolas Pitre Cc: Arnd Bergmann Reported-by: Randy Dunlap --- drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 312e0a1ad43d..7d69a3061f17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -7,10 +7,10 @@ config MLX5_CORE tristate "Mellanox 5th generation network adapters (ConnectX series) core driver" depends on PCI select NET_DEVLINK - imply PTP_1588_CLOCK - imply VXLAN - imply MLXFW - imply PCI_HYPERV_INTERFACE + depends on VXLAN || !VXLAN + depends on MLXFW || !MLXFW + depends on PTP_1588_CLOCK || !PTP_1588_CLOCK + depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE default n ---help--- Core driver for low level functionality of the ConnectX-4 and From dcdf4ce0ff4ba206fc362e149c8ae81d6a2f849c Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Wed, 8 Apr 2020 14:51:52 +0800 Subject: [PATCH 5/5] net/mlx5e: Get the latest values from counters in switchdev mode In the switchdev mode, when running "cat /sys/class/net/NIC/statistics/tx_packets", the ppcnt register is accessed to get the latest values. But currently this command can not get the correct values from ppcnt. From firmware manual, before getting the 802_3 counters, the 802_3 data layout should be set to the ppcnt register. When the command "cat /sys/class/net/NIC/statistics/tx_packets" is run, before updating 802_3 data layout with ppcnt register, the monitor counters are tested. The test result will decide the 802_3 data layout is updated or not. Actually the monitor counters do not support to monitor rx/tx stats of 802_3 in switchdev mode. So the rx/tx counters change will not trigger monitor counters. So the 802_3 data layout will not be updated in ppcnt register. Finally this command can not get the latest values from ppcnt register with 802_3 data layout. Fixes: 5c7e8bbb0257 ("net/mlx5e: Use monitor counters for update stats") Signed-off-by: Zhu Yanjun Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f02150a97ac8..b314adf438da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3583,7 +3583,12 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) struct mlx5e_vport_stats *vstats = &priv->stats.vport; struct mlx5e_pport_stats *pstats = &priv->stats.pport; - if (!mlx5e_monitor_counter_supported(priv)) { + /* In switchdev mode, monitor counters doesn't monitor + * rx/tx stats of 802_3. The update stats mechanism + * should keep the 802_3 layout counters updated + */ + if (!mlx5e_monitor_counter_supported(priv) || + mlx5e_is_uplink_rep(priv)) { /* update HW stats in background for next time */ mlx5e_queue_update_stats(priv); }