From f1cdaa077ccacb0d78a2da5c9df9b4aa7b7a0927 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 30 Sep 2019 10:15:11 +0200 Subject: mlxsw: spectrum: Use per-netns netdevice notifier registration The mlxsw_sp instance is not interested in events happening in other network namespaces. So use "_net" variants for netdevice notifier registration/unregistration and get only events which are happening in the net the instance is in. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index dcf9562bce8a..a54a0dc82ff2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4864,7 +4864,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, * respin. */ mlxsw_sp->netdevice_nb.notifier_call = mlxsw_sp_netdevice_event; - err = register_netdevice_notifier(&mlxsw_sp->netdevice_nb); + err = register_netdevice_notifier_net(&init_net, + &mlxsw_sp->netdevice_nb); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to register netdev notifier\n"); goto err_netdev_notifier; @@ -4887,7 +4888,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, err_ports_create: mlxsw_sp_dpipe_fini(mlxsw_sp); err_dpipe_init: - unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); + unregister_netdevice_notifier_net(&init_net, + &mlxsw_sp->netdevice_nb); err_netdev_notifier: if (mlxsw_sp->clock) mlxsw_sp->ptp_ops->fini(mlxsw_sp->ptp_state); @@ -4973,7 +4975,8 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_ports_remove(mlxsw_sp); mlxsw_sp_dpipe_fini(mlxsw_sp); - unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); + unregister_netdevice_notifier_net(&init_net, + &mlxsw_sp->netdevice_nb); if (mlxsw_sp->clock) { mlxsw_sp->ptp_ops->fini(mlxsw_sp->ptp_state); mlxsw_sp->ptp_ops->clock_fini(mlxsw_sp->clock); -- cgit v1.2.3-59-g8ed1b From 6aaee55cc8c6c305bb758545e7ceadc1bfcf7684 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Thu, 3 Oct 2019 08:44:49 +0300 Subject: mlxsw: PCI: Send EMAD traffic on a separate queue Currently mlxsw distributes sent traffic among all the available send queues. That includes control traffic as well as EMADs, which are used for configuration of the device. However because all the queues have the same traffic class of 3, they all end up being directed to the same traffic class buffer. If the control traffic in the buffer cannot be serviced quickly enough, the EMAD traffic might be shut out, which causes transient failures, typically in FDB maintenance, counter upkeep and other periodic work. To address this issue, dedicate SDQ 0 to EMAD traffic, with TC 0. Distribute the control traffic among the remaining queues, which are left with their current TC 3. Suggested-by: Ido Schimmel Signed-off-by: Petr Machata Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/pci.c | 16 ++++++++++++++-- drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 5 +++++ 2 files changed, 19 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 615455a21567..f1294b00efdf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -284,15 +284,18 @@ static dma_addr_t __mlxsw_pci_queue_page_get(struct mlxsw_pci_queue *q, static int mlxsw_pci_sdq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, struct mlxsw_pci_queue *q) { + int tclass; int i; int err; q->producer_counter = 0; q->consumer_counter = 0; + tclass = q->num == MLXSW_PCI_SDQ_EMAD_INDEX ? MLXSW_PCI_SDQ_EMAD_TC : + MLXSW_PCI_SDQ_CTL_TC; /* Set CQ of same number of this SDQ. */ mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, q->num); - mlxsw_cmd_mbox_sw2hw_dq_sdq_tclass_set(mbox, 3); + mlxsw_cmd_mbox_sw2hw_dq_sdq_tclass_set(mbox, tclass); mlxsw_cmd_mbox_sw2hw_dq_log2_dq_sz_set(mbox, 3); /* 8 pages */ for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) { dma_addr_t mapaddr = __mlxsw_pci_queue_page_get(q, i); @@ -963,6 +966,7 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox) eq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_eq_sz_get(mbox); if (num_sdqs + num_rdqs > num_cqs || + num_sdqs < MLXSW_PCI_SDQS_MIN || num_cqs > MLXSW_PCI_CQS_MAX || num_eqs != MLXSW_PCI_EQS_COUNT) { dev_err(&pdev->dev, "Unsupported number of queues\n"); return -EINVAL; @@ -1520,7 +1524,15 @@ static struct mlxsw_pci_queue * mlxsw_pci_sdq_pick(struct mlxsw_pci *mlxsw_pci, const struct mlxsw_tx_info *tx_info) { - u8 sdqn = tx_info->local_port % mlxsw_pci_sdq_count(mlxsw_pci); + u8 ctl_sdq_count = mlxsw_pci_sdq_count(mlxsw_pci) - 1; + u8 sdqn; + + if (tx_info->is_emad) { + sdqn = MLXSW_PCI_SDQ_EMAD_INDEX; + } else { + BUILD_BUG_ON(MLXSW_PCI_SDQ_EMAD_INDEX != 0); + sdqn = 1 + (tx_info->local_port % ctl_sdq_count); + } return mlxsw_pci_sdq_get(mlxsw_pci, sdqn); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index e57e42e2d2b2..2b3aec482742 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -51,6 +51,11 @@ #define MLXSW_PCI_EQ_ASYNC_NUM 0 #define MLXSW_PCI_EQ_COMP_NUM 1 +#define MLXSW_PCI_SDQS_MIN 2 /* EMAD and control traffic */ +#define MLXSW_PCI_SDQ_EMAD_INDEX 0 +#define MLXSW_PCI_SDQ_EMAD_TC 0 +#define MLXSW_PCI_SDQ_CTL_TC 3 + #define MLXSW_PCI_AQ_PAGES 8 #define MLXSW_PCI_AQ_SIZE (MLXSW_PCI_PAGE_SIZE * MLXSW_PCI_AQ_PAGES) #define MLXSW_PCI_WQE_SIZE 32 /* 32 bytes per element */ -- cgit v1.2.3-59-g8ed1b From 7c550daffe22a97282effa75fe7c1f6b83563ecb Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:27 +0200 Subject: net: fib_notifier: make FIB notifier per-netns Currently all users of FIB notifier only cares about events in init_net. Later in this patchset, users get interested in other namespaces too. However, for every registered block user is interested only about one namespace. Make the FIB notifier registration per-netns and avoid unnecessary calls of notifier block for other namespaces. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c | 7 +- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 9 +-- drivers/net/ethernet/rocker/rocker_main.c | 9 +-- drivers/net/netdevsim/fib.c | 8 +- include/linux/mroute_base.h | 10 +-- include/net/fib_notifier.h | 7 +- include/net/ip6_fib.h | 2 +- include/net/ip_fib.h | 2 +- net/core/fib_notifier.c | 87 ++++++++++------------ net/core/fib_rules.c | 7 +- net/ipv4/fib_notifier.c | 4 +- net/ipv4/fib_trie.c | 17 ++--- net/ipv4/ipmr_base.c | 4 +- net/ipv6/fib6_notifier.c | 4 +- net/ipv6/ip6_fib.c | 6 +- 15 files changed, 78 insertions(+), 105 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index 5d20d615663e..fe0cc969cf94 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -248,9 +248,6 @@ static int mlx5_lag_fib_event(struct notifier_block *nb, struct net_device *fib_dev; struct fib_info *fi; - if (!net_eq(info->net, &init_net)) - return NOTIFY_DONE; - if (info->family != AF_INET) return NOTIFY_DONE; @@ -311,7 +308,7 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev) return 0; mp->fib_nb.notifier_call = mlx5_lag_fib_event; - err = register_fib_notifier(&mp->fib_nb, + err = register_fib_notifier(&init_net, &mp->fib_nb, mlx5_lag_fib_event_flush); if (err) mp->fib_nb.notifier_call = NULL; @@ -326,6 +323,6 @@ void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) if (!mp->fib_nb.notifier_call) return; - unregister_fib_notifier(&mp->fib_nb); + unregister_fib_notifier(&init_net, &mp->fib_nb); mp->fib_nb.notifier_call = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index a330b369e899..d0db9ea71323 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -6213,7 +6213,7 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, rule = fr_info->rule; /* Rule only affects locally generated traffic */ - if (rule->iifindex == info->net->loopback_dev->ifindex) + if (rule->iifindex == init_net.loopback_dev->ifindex) return 0; switch (info->family) { @@ -6250,8 +6250,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, struct mlxsw_sp_router *router; int err; - if (!net_eq(info->net, &init_net) || - (info->family != AF_INET && info->family != AF_INET6 && + if ((info->family != AF_INET && info->family != AF_INET6 && info->family != RTNL_FAMILY_IPMR && info->family != RTNL_FAMILY_IP6MR)) return NOTIFY_DONE; @@ -8155,7 +8154,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) goto err_dscp_init; mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; - err = register_fib_notifier(&mlxsw_sp->router->fib_nb, + err = register_fib_notifier(&init_net, &mlxsw_sp->router->fib_nb, mlxsw_sp_router_fib_dump_flush); if (err) goto err_register_fib_notifier; @@ -8195,7 +8194,7 @@ err_register_inetaddr_notifier: void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) { - unregister_fib_notifier(&mlxsw_sp->router->fib_nb); + unregister_fib_notifier(&init_net, &mlxsw_sp->router->fib_nb); unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 786b158bd305..e54f6341a785 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2189,9 +2189,6 @@ static int rocker_router_fib_event(struct notifier_block *nb, struct rocker_fib_event_work *fib_work; struct fib_notifier_info *info = ptr; - if (!net_eq(info->net, &init_net)) - return NOTIFY_DONE; - if (info->family != AF_INET) return NOTIFY_DONE; @@ -2994,7 +2991,7 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) * the device, so no need to pass a callback. */ rocker->fib_nb.notifier_call = rocker_router_fib_event; - err = register_fib_notifier(&rocker->fib_nb, NULL); + err = register_fib_notifier(&init_net, &rocker->fib_nb, NULL); if (err) goto err_register_fib_notifier; @@ -3021,7 +3018,7 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_register_switchdev_blocking_notifier: unregister_switchdev_notifier(&rocker_switchdev_notifier); err_register_switchdev_notifier: - unregister_fib_notifier(&rocker->fib_nb); + unregister_fib_notifier(&init_net, &rocker->fib_nb); err_register_fib_notifier: rocker_remove_ports(rocker); err_probe_ports: @@ -3057,7 +3054,7 @@ static void rocker_remove(struct pci_dev *pdev) unregister_switchdev_blocking_notifier(nb); unregister_switchdev_notifier(&rocker_switchdev_notifier); - unregister_fib_notifier(&rocker->fib_nb); + unregister_fib_notifier(&init_net, &rocker->fib_nb); rocker_remove_ports(rocker); rocker_write32(rocker, CONTROL, ROCKER_CONTROL_RESET); destroy_workqueue(rocker->rocker_owq); diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index 7de17e42d77a..01ee9cc54605 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -182,9 +182,6 @@ static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event, struct fib_notifier_info *info = ptr; int err = 0; - if (!net_eq(info->net, &init_net)) - return NOTIFY_DONE; - switch (event) { case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: @@ -258,7 +255,8 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink) data->ipv6.rules.max = (u64)-1; data->fib_nb.notifier_call = nsim_fib_event_nb; - err = register_fib_notifier(&data->fib_nb, nsim_fib_dump_inconsistent); + err = register_fib_notifier(&init_net, &data->fib_nb, + nsim_fib_dump_inconsistent); if (err) { pr_err("Failed to register fib notifier\n"); goto err_out; @@ -297,6 +295,6 @@ void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data) NSIM_RESOURCE_IPV4_FIB_RULES); devlink_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV4_FIB); - unregister_fib_notifier(&data->fib_nb); + unregister_fib_notifier(&init_net, &data->fib_nb); kfree(data); } diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 34de06b426ef..0931631bbc13 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -47,7 +47,6 @@ struct vif_entry_notifier_info { }; static inline int mr_call_vif_notifier(struct notifier_block *nb, - struct net *net, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, @@ -56,7 +55,6 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, struct vif_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .dev = vif->dev, .vif_index = vif_index, @@ -64,7 +62,7 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, .tb_id = tb_id, }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_vif_notifiers(struct net *net, @@ -77,7 +75,6 @@ static inline int mr_call_vif_notifiers(struct net *net, struct vif_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .dev = vif->dev, .vif_index = vif_index, @@ -173,7 +170,6 @@ struct mfc_entry_notifier_info { }; static inline int mr_call_mfc_notifier(struct notifier_block *nb, - struct net *net, unsigned short family, enum fib_event_type event_type, struct mr_mfc *mfc, u32 tb_id) @@ -181,13 +177,12 @@ static inline int mr_call_mfc_notifier(struct notifier_block *nb, struct mfc_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .mfc = mfc, .tb_id = tb_id }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_mfc_notifiers(struct net *net, @@ -199,7 +194,6 @@ static inline int mr_call_mfc_notifiers(struct net *net, struct mfc_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .mfc = mfc, .tb_id = tb_id diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h index c49d7bfb5c30..23353f67b2b0 100644 --- a/include/net/fib_notifier.h +++ b/include/net/fib_notifier.h @@ -8,7 +8,6 @@ struct module; struct fib_notifier_info { - struct net *net; int family; struct netlink_ext_ack *extack; }; @@ -35,14 +34,14 @@ struct fib_notifier_ops { struct rcu_head rcu; }; -int call_fib_notifier(struct notifier_block *nb, struct net *net, +int call_fib_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); -int register_fib_notifier(struct notifier_block *nb, +int register_fib_notifier(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb)); -int unregister_fib_notifier(struct notifier_block *nb); +int unregister_fib_notifier(struct net *net, struct notifier_block *nb); struct fib_notifier_ops * fib_notifier_ops_register(const struct fib_notifier_ops *tmpl, struct net *net); void fib_notifier_ops_unregister(struct fib_notifier_ops *ops); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 4b5656c71abc..14e9fca0e326 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -478,7 +478,7 @@ struct ipv6_route_iter { extern const struct seq_operations ipv6_route_seq_ops; -int call_fib6_notifier(struct notifier_block *nb, struct net *net, +int call_fib6_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index ab1ca9e238d2..a9df85304f40 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -219,7 +219,7 @@ struct fib_nh_notifier_info { struct fib_nh *fib_nh; }; -int call_fib4_notifier(struct notifier_block *nb, struct net *net, +int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c index 470a606d5e8d..fbd029425638 100644 --- a/net/core/fib_notifier.c +++ b/net/core/fib_notifier.c @@ -12,17 +12,15 @@ static unsigned int fib_notifier_net_id; struct fib_notifier_net { struct list_head fib_notifier_ops; + struct atomic_notifier_head fib_chain; }; -static ATOMIC_NOTIFIER_HEAD(fib_chain); - -int call_fib_notifier(struct notifier_block *nb, struct net *net, +int call_fib_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { int err; - info->net = net; err = nb->notifier_call(nb, event_type, info); return notifier_to_errno(err); } @@ -31,35 +29,29 @@ EXPORT_SYMBOL(call_fib_notifier); int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info) { + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); int err; - info->net = net; - err = atomic_notifier_call_chain(&fib_chain, event_type, info); + err = atomic_notifier_call_chain(&fn_net->fib_chain, event_type, info); return notifier_to_errno(err); } EXPORT_SYMBOL(call_fib_notifiers); -static unsigned int fib_seq_sum(void) +static unsigned int fib_seq_sum(struct net *net) { - struct fib_notifier_net *fn_net; + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; unsigned int fib_seq = 0; - struct net *net; rtnl_lock(); - down_read(&net_rwsem); - for_each_net(net) { - fn_net = net_generic(net, fib_notifier_net_id); - rcu_read_lock(); - list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { - if (!try_module_get(ops->owner)) - continue; - fib_seq += ops->fib_seq_read(net); - module_put(ops->owner); - } - rcu_read_unlock(); + rcu_read_lock(); + list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { + if (!try_module_get(ops->owner)) + continue; + fib_seq += ops->fib_seq_read(net); + module_put(ops->owner); } - up_read(&net_rwsem); + rcu_read_unlock(); rtnl_unlock(); return fib_seq; @@ -69,68 +61,66 @@ static int fib_net_dump(struct net *net, struct notifier_block *nb) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; + int err = 0; + rcu_read_lock(); list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { - int err; - if (!try_module_get(ops->owner)) continue; err = ops->fib_dump(net, nb); module_put(ops->owner); if (err) - return err; + goto unlock; } - return 0; +unlock: + rcu_read_unlock(); + + return err; } -static bool fib_dump_is_consistent(struct notifier_block *nb, +static bool fib_dump_is_consistent(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb), unsigned int fib_seq) { - atomic_notifier_chain_register(&fib_chain, nb); - if (fib_seq == fib_seq_sum()) + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); + + atomic_notifier_chain_register(&fn_net->fib_chain, nb); + if (fib_seq == fib_seq_sum(net)) return true; - atomic_notifier_chain_unregister(&fib_chain, nb); + atomic_notifier_chain_unregister(&fn_net->fib_chain, nb); if (cb) cb(nb); return false; } #define FIB_DUMP_MAX_RETRIES 5 -int register_fib_notifier(struct notifier_block *nb, +int register_fib_notifier(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb)) { int retries = 0; int err; do { - unsigned int fib_seq = fib_seq_sum(); - struct net *net; - - rcu_read_lock(); - for_each_net_rcu(net) { - err = fib_net_dump(net, nb); - if (err) - goto err_fib_net_dump; - } - rcu_read_unlock(); - - if (fib_dump_is_consistent(nb, cb, fib_seq)) + unsigned int fib_seq = fib_seq_sum(net); + + err = fib_net_dump(net, nb); + if (err) + return err; + + if (fib_dump_is_consistent(net, nb, cb, fib_seq)) return 0; } while (++retries < FIB_DUMP_MAX_RETRIES); return -EBUSY; - -err_fib_net_dump: - rcu_read_unlock(); - return err; } EXPORT_SYMBOL(register_fib_notifier); -int unregister_fib_notifier(struct notifier_block *nb) +int unregister_fib_notifier(struct net *net, struct notifier_block *nb) { - return atomic_notifier_chain_unregister(&fib_chain, nb); + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); + + return atomic_notifier_chain_unregister(&fn_net->fib_chain, nb); } EXPORT_SYMBOL(unregister_fib_notifier); @@ -181,6 +171,7 @@ static int __net_init fib_notifier_net_init(struct net *net) struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); INIT_LIST_HEAD(&fn_net->fib_notifier_ops); + ATOMIC_INIT_NOTIFIER_HEAD(&fn_net->fib_chain); return 0; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index dd220ce7ca7a..28cbf07102bc 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -321,7 +321,7 @@ out: } EXPORT_SYMBOL_GPL(fib_rules_lookup); -static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, +static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_rule *rule, int family) { @@ -330,7 +330,7 @@ static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, .rule = rule, }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static int call_fib_rule_notifiers(struct net *net, @@ -359,8 +359,7 @@ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family) if (!ops) return -EAFNOSUPPORT; list_for_each_entry_rcu(rule, &ops->rules_list, list) - call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule, - family); + call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, rule, family); rules_ops_put(ops); return 0; diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c index b804ccbdb241..1a128c1346fb 100644 --- a/net/ipv4/fib_notifier.c +++ b/net/ipv4/fib_notifier.c @@ -9,12 +9,12 @@ #include #include -int call_fib4_notifier(struct notifier_block *nb, struct net *net, +int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET; - return call_fib_notifier(nb, net, event_type, info); + return call_fib_notifier(nb, event_type, info); } int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 1ab2fb6bb37d..5b600b2a2aa3 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -74,7 +74,7 @@ #include #include "fib_lookup.h" -static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, +static int call_fib_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa) { @@ -86,7 +86,7 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, .type = fa->fa_type, .tb_id = fa->tb_id, }; - return call_fib4_notifier(nb, net, event_type, &info.info); + return call_fib4_notifier(nb, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, @@ -2015,8 +2015,8 @@ void fib_info_notify_update(struct net *net, struct nl_info *info) } } -static void fib_leaf_notify(struct net *net, struct key_vector *l, - struct fib_table *tb, struct notifier_block *nb) +static void fib_leaf_notify(struct key_vector *l, struct fib_table *tb, + struct notifier_block *nb) { struct fib_alias *fa; @@ -2032,20 +2032,19 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l, if (tb->tb_id != fa->tb_id) continue; - call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key, + call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_ADD, l->key, KEYLENGTH - fa->fa_slen, fa); } } -static void fib_table_notify(struct net *net, struct fib_table *tb, - struct notifier_block *nb) +static void fib_table_notify(struct fib_table *tb, struct notifier_block *nb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - fib_leaf_notify(net, l, tb, nb); + fib_leaf_notify(l, tb, nb); key = l->key + 1; /* stop in case of wrap around */ @@ -2063,7 +2062,7 @@ void fib_notify(struct net *net, struct notifier_block *nb) struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) - fib_table_notify(net, tb, nb); + fib_table_notify(tb, nb); } } diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index ea48bd15a575..4dcc3214e3cc 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -409,7 +409,7 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, if (!v->dev) continue; - mr_call_vif_notifier(nb, net, family, + mr_call_vif_notifier(nb, family, FIB_EVENT_VIF_ADD, v, vifi, mrt->id); } @@ -417,7 +417,7 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, /* Notify on table MFC entries */ list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) - mr_call_mfc_notifier(nb, net, family, + mr_call_mfc_notifier(nb, family, FIB_EVENT_ENTRY_ADD, mfc, mrt->id); } diff --git a/net/ipv6/fib6_notifier.c b/net/ipv6/fib6_notifier.c index 05f82baaa99e..4fe79296999a 100644 --- a/net/ipv6/fib6_notifier.c +++ b/net/ipv6/fib6_notifier.c @@ -7,12 +7,12 @@ #include #include -int call_fib6_notifier(struct notifier_block *nb, struct net *net, +int call_fib6_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET6; - return call_fib_notifier(nb, net, event_type, info); + return call_fib_notifier(nb, event_type, info); } int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 6e2af411cd9c..f6fae48b2e18 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -357,7 +357,7 @@ unsigned int fib6_tables_seq_read(struct net *net) return fib_seq; } -static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, +static int call_fib6_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt) { @@ -365,7 +365,7 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, .rt = rt, }; - return call_fib6_notifier(nb, net, event_type, &info.info); + return call_fib6_notifier(nb, event_type, &info.info); } int call_fib6_entry_notifiers(struct net *net, @@ -407,7 +407,7 @@ static void fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { if (rt == arg->net->ipv6.fib6_null_entry) return; - call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt); + call_fib6_entry_notifier(arg->nb, FIB_EVENT_ENTRY_ADD, rt); } static int fib6_node_dump(struct fib6_walker *w) -- cgit v1.2.3-59-g8ed1b From 3f9e5c119a47d0fce01f8524ff0aba3acca71bb9 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:29 +0200 Subject: mlxsw: spectrum_router: Don't rely on missing extack to symbolize dump Currently if info->extack is NULL, mlxsw assumes that the event came down from dump. Originally, the dump did not propagate the return value back to the original caller (fib_notifier_register()). However, that is now happening. So benefit from this and push the error up if it happened. Remove rule cases in work handlers that are now dead code. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 22 +--------------------- 1 file changed, 1 insertion(+), 21 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index d0db9ea71323..1eeff1d23b13 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -6019,12 +6019,6 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info); fib_info_put(fib_work->fen_info.fi); break; - case FIB_EVENT_RULE_ADD: - /* if we get here, a rule was added that we do not support. - * just do the fib_abort - */ - mlxsw_sp_router_fib_abort(mlxsw_sp); - break; case FIB_EVENT_NH_ADD: /* fall through */ case FIB_EVENT_NH_DEL: mlxsw_sp_nexthop4_event(mlxsw_sp, fib_work->event, @@ -6065,12 +6059,6 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) fib_work->fib6_work.nrt6); mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work); break; - case FIB_EVENT_RULE_ADD: - /* if we get here, a rule was added that we do not support. - * just do the fib_abort - */ - mlxsw_sp_router_fib_abort(mlxsw_sp); - break; } rtnl_unlock(); kfree(fib_work); @@ -6112,12 +6100,6 @@ static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) &fib_work->ven_info); dev_put(fib_work->ven_info.dev); break; - case FIB_EVENT_RULE_ADD: - /* if we get here, a rule was added that we do not support. - * just do the fib_abort - */ - mlxsw_sp_router_fib_abort(mlxsw_sp); - break; } rtnl_unlock(); kfree(fib_work); @@ -6262,9 +6244,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, case FIB_EVENT_RULE_DEL: err = mlxsw_sp_router_fib_rule_event(event, info, router->mlxsw_sp); - if (!err || info->extack) - return notifier_from_errno(err); - break; + return notifier_from_errno(err); case FIB_EVENT_ENTRY_ADD: case FIB_EVENT_ENTRY_REPLACE: /* fall through */ case FIB_EVENT_ENTRY_APPEND: /* fall through */ -- cgit v1.2.3-59-g8ed1b From b7a595577ef3dc9add2b3e6d00869d017306bfbe Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:30 +0200 Subject: net: fib_notifier: propagate extack down to the notifier block callback Since errors are propagated all the way up to the caller, propagate possible extack of the caller all the way down to the notifier block callback. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c | 2 +- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +- drivers/net/ethernet/rocker/rocker_main.c | 2 +- drivers/net/netdevsim/fib.c | 2 +- include/linux/mroute_base.h | 18 ++++++++++++------ include/net/fib_notifier.h | 6 ++++-- include/net/fib_rules.h | 3 ++- include/net/ip6_fib.h | 9 ++++++--- include/net/ip_fib.h | 9 ++++++--- net/core/fib_notifier.c | 10 ++++++---- net/core/fib_rules.c | 9 ++++++--- net/ipv4/fib_notifier.c | 7 ++++--- net/ipv4/fib_rules.c | 5 +++-- net/ipv4/fib_trie.c | 20 +++++++++++++------- net/ipv4/ipmr.c | 13 ++++++++----- net/ipv4/ipmr_base.c | 12 +++++++----- net/ipv6/fib6_notifier.c | 7 ++++--- net/ipv6/fib6_rules.c | 5 +++-- net/ipv6/ip6_fib.c | 12 +++++++++--- net/ipv6/ip6mr.c | 13 ++++++++----- 20 files changed, 105 insertions(+), 61 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index fe0cc969cf94..13e2944b1274 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -309,7 +309,7 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev) mp->fib_nb.notifier_call = mlx5_lag_fib_event; err = register_fib_notifier(&init_net, &mp->fib_nb, - mlx5_lag_fib_event_flush); + mlx5_lag_fib_event_flush, NULL); if (err) mp->fib_nb.notifier_call = NULL; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 1eeff1d23b13..445e2daa54ac 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -8135,7 +8135,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; err = register_fib_notifier(&init_net, &mlxsw_sp->router->fib_nb, - mlxsw_sp_router_fib_dump_flush); + mlxsw_sp_router_fib_dump_flush, NULL); if (err) goto err_register_fib_notifier; diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index e54f6341a785..bc4f951315da 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2991,7 +2991,7 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) * the device, so no need to pass a callback. */ rocker->fib_nb.notifier_call = rocker_router_fib_event; - err = register_fib_notifier(&init_net, &rocker->fib_nb, NULL); + err = register_fib_notifier(&init_net, &rocker->fib_nb, NULL, NULL); if (err) goto err_register_fib_notifier; diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index 01ee9cc54605..d2aeac0f4c2c 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -256,7 +256,7 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink) data->fib_nb.notifier_call = nsim_fib_event_nb; err = register_fib_notifier(&init_net, &data->fib_nb, - nsim_fib_dump_inconsistent); + nsim_fib_dump_inconsistent, NULL); if (err) { pr_err("Failed to register fib notifier\n"); goto err_out; diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 0931631bbc13..8071148f29a6 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -50,11 +50,13 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, - unsigned short vif_index, u32 tb_id) + unsigned short vif_index, u32 tb_id, + struct netlink_ext_ack *extack) { struct vif_entry_notifier_info info = { .info = { .family = family, + .extack = extack, }, .dev = vif->dev, .vif_index = vif_index, @@ -172,11 +174,13 @@ struct mfc_entry_notifier_info { static inline int mr_call_mfc_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, - struct mr_mfc *mfc, u32 tb_id) + struct mr_mfc *mfc, u32 tb_id, + struct netlink_ext_ack *extack) { struct mfc_entry_notifier_info info = { .info = { .family = family, + .extack = extack, }, .mfc = mfc, .tb_id = tb_id @@ -295,10 +299,11 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + struct notifier_block *nb, + struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock); + rwlock_t *mrt_lock, struct netlink_ext_ack *extack); #else static inline void vif_device_init(struct vif_device *v, struct net_device *dev, @@ -349,10 +354,11 @@ mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, static inline int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + struct notifier_block *nb, + struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock) + rwlock_t *mrt_lock, struct netlink_ext_ack *extack) { return -EINVAL; } diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h index 23353f67b2b0..6d59221ff05a 100644 --- a/include/net/fib_notifier.h +++ b/include/net/fib_notifier.h @@ -29,7 +29,8 @@ struct fib_notifier_ops { int family; struct list_head list; unsigned int (*fib_seq_read)(struct net *net); - int (*fib_dump)(struct net *net, struct notifier_block *nb); + int (*fib_dump)(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); struct module *owner; struct rcu_head rcu; }; @@ -40,7 +41,8 @@ int call_fib_notifier(struct notifier_block *nb, int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int register_fib_notifier(struct net *net, struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)); + void (*cb)(struct notifier_block *nb), + struct netlink_ext_ack *extack); int unregister_fib_notifier(struct net *net, struct notifier_block *nb); struct fib_notifier_ops * fib_notifier_ops_register(const struct fib_notifier_ops *tmpl, struct net *net); diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 20dcadd8eed9..54e227e6b06a 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -194,7 +194,8 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags, int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); bool fib_rule_matchall(const struct fib_rule *rule); -int fib_rules_dump(struct net *net, struct notifier_block *nb, int family); +int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, + struct netlink_ext_ack *extack); unsigned int fib_rules_seq_read(struct net *net, int family); int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 14e9fca0e326..5d1615463138 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -488,7 +488,8 @@ int __net_init fib6_notifier_init(struct net *net); void __net_exit fib6_notifier_exit(struct net *net); unsigned int fib6_tables_seq_read(struct net *net); -int fib6_tables_dump(struct net *net, struct notifier_block *nb); +int fib6_tables_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); void fib6_update_sernum(struct net *net, struct fib6_info *rt); void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); @@ -504,7 +505,8 @@ static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) int fib6_rules_init(void); void fib6_rules_cleanup(void); bool fib6_rule_default(const struct fib_rule *rule); -int fib6_rules_dump(struct net *net, struct notifier_block *nb); +int fib6_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); unsigned int fib6_rules_seq_read(struct net *net); static inline bool fib6_rules_early_flow_dissect(struct net *net, @@ -537,7 +539,8 @@ static inline bool fib6_rule_default(const struct fib_rule *rule) { return true; } -static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb) +static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 05c1fd9c5e23..52b2406a5dfc 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -229,7 +229,8 @@ int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); void fib_info_notify_update(struct net *net, struct nl_info *info); -int fib_notify(struct net *net, struct notifier_block *nb); +int fib_notify(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); struct fib_table { struct hlist_node tb_hlist; @@ -315,7 +316,8 @@ static inline bool fib4_rule_default(const struct fib_rule *rule) return true; } -static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb) +static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } @@ -377,7 +379,8 @@ out: } bool fib4_rule_default(const struct fib_rule *rule); -int fib4_rules_dump(struct net *net, struct notifier_block *nb); +int fib4_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); unsigned int fib4_rules_seq_read(struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c index fbd029425638..fc96259807b6 100644 --- a/net/core/fib_notifier.c +++ b/net/core/fib_notifier.c @@ -57,7 +57,8 @@ static unsigned int fib_seq_sum(struct net *net) return fib_seq; } -static int fib_net_dump(struct net *net, struct notifier_block *nb) +static int fib_net_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; @@ -67,7 +68,7 @@ static int fib_net_dump(struct net *net, struct notifier_block *nb) list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { if (!try_module_get(ops->owner)) continue; - err = ops->fib_dump(net, nb); + err = ops->fib_dump(net, nb, extack); module_put(ops->owner); if (err) goto unlock; @@ -96,7 +97,8 @@ static bool fib_dump_is_consistent(struct net *net, struct notifier_block *nb, #define FIB_DUMP_MAX_RETRIES 5 int register_fib_notifier(struct net *net, struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)) + void (*cb)(struct notifier_block *nb), + struct netlink_ext_ack *extack) { int retries = 0; int err; @@ -104,7 +106,7 @@ int register_fib_notifier(struct net *net, struct notifier_block *nb, do { unsigned int fib_seq = fib_seq_sum(net); - err = fib_net_dump(net, nb); + err = fib_net_dump(net, nb, extack); if (err) return err; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 592d8aef90e3..3e7e15278c46 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -323,10 +323,12 @@ EXPORT_SYMBOL_GPL(fib_rules_lookup); static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, - struct fib_rule *rule, int family) + struct fib_rule *rule, int family, + struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = family, + .info.extack = extack, .rule = rule, }; @@ -350,7 +352,8 @@ static int call_fib_rule_notifiers(struct net *net, } /* Called with rcu_read_lock() */ -int fib_rules_dump(struct net *net, struct notifier_block *nb, int family) +int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, + struct netlink_ext_ack *extack) { struct fib_rules_ops *ops; struct fib_rule *rule; @@ -361,7 +364,7 @@ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family) return -EAFNOSUPPORT; list_for_each_entry_rcu(rule, &ops->rules_list, list) { err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, - rule, family); + rule, family, extack); if (err) break; } diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c index 0c57f68a9340..0c28bd469a68 100644 --- a/net/ipv4/fib_notifier.c +++ b/net/ipv4/fib_notifier.c @@ -34,15 +34,16 @@ static unsigned int fib4_seq_read(struct net *net) return net->ipv4.fib_seq + fib4_rules_seq_read(net); } -static int fib4_dump(struct net *net, struct notifier_block *nb) +static int fib4_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { int err; - err = fib4_rules_dump(net, nb); + err = fib4_rules_dump(net, nb, extack); if (err) return err; - return fib_notify(net, nb); + return fib_notify(net, nb, extack); } static const struct fib_notifier_ops fib4_notifier_ops_template = { diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index b43a7ba5c6a4..f99e3bac5cab 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -65,9 +65,10 @@ bool fib4_rule_default(const struct fib_rule *rule) } EXPORT_SYMBOL_GPL(fib4_rule_default); -int fib4_rules_dump(struct net *net, struct notifier_block *nb) +int fib4_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return fib_rules_dump(net, nb, AF_INET); + return fib_rules_dump(net, nb, AF_INET, extack); } unsigned int fib4_rules_seq_read(struct net *net) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 568e59423773..b9df9c09b84e 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -76,9 +76,11 @@ static int call_fib_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, u32 dst, - int dst_len, struct fib_alias *fa) + int dst_len, struct fib_alias *fa, + struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { + .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, @@ -2016,7 +2018,8 @@ void fib_info_notify_update(struct net *net, struct nl_info *info) } static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, - struct notifier_block *nb) + struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct fib_alias *fa; int err; @@ -2034,14 +2037,16 @@ static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, continue; err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_ADD, l->key, - KEYLENGTH - fa->fa_slen, fa); + KEYLENGTH - fa->fa_slen, + fa, extack); if (err) return err; } return 0; } -static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb) +static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; @@ -2049,7 +2054,7 @@ static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb) int err; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - err = fib_leaf_notify(l, tb, nb); + err = fib_leaf_notify(l, tb, nb, extack); if (err) return err; @@ -2061,7 +2066,8 @@ static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb) return 0; } -int fib_notify(struct net *net, struct notifier_block *nb) +int fib_notify(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { unsigned int h; int err; @@ -2071,7 +2077,7 @@ int fib_notify(struct net *net, struct notifier_block *nb) struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { - err = fib_table_notify(tb, nb); + err = fib_table_notify(tb, nb, extack); if (err) return err; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 313470f6bb14..051f365b64d2 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -278,9 +278,10 @@ static void __net_exit ipmr_rules_exit(struct net *net) rtnl_unlock(); } -static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR); + return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR, extack); } static unsigned int ipmr_rules_seq_read(struct net *net) @@ -336,7 +337,8 @@ static void __net_exit ipmr_rules_exit(struct net *net) rtnl_unlock(); } -static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } @@ -3040,10 +3042,11 @@ static unsigned int ipmr_seq_read(struct net *net) return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net); } -static int ipmr_dump(struct net *net, struct notifier_block *nb) +static int ipmr_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IPMR, ipmr_rules_dump, - ipmr_mr_table_iter, &mrt_lock); + ipmr_mr_table_iter, &mrt_lock, extack); } static const struct fib_notifier_ops ipmr_notifier_ops_template = { diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index c4e23c2a0d5c..aa8738a91210 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -386,15 +386,17 @@ EXPORT_SYMBOL(mr_rtm_dumproute); int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + struct notifier_block *nb, + struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock) + rwlock_t *mrt_lock, + struct netlink_ext_ack *extack) { struct mr_table *mrt; int err; - err = rules_dump(net, nb); + err = rules_dump(net, nb, extack); if (err) return err; @@ -411,7 +413,7 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, err = mr_call_vif_notifier(nb, family, FIB_EVENT_VIF_ADD, - v, vifi, mrt->id); + v, vifi, mrt->id, extack); if (err) break; } @@ -424,7 +426,7 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { err = mr_call_mfc_notifier(nb, family, FIB_EVENT_ENTRY_ADD, - mfc, mrt->id); + mfc, mrt->id, extack); if (err) return err; } diff --git a/net/ipv6/fib6_notifier.c b/net/ipv6/fib6_notifier.c index 4fe79296999a..f87ae33e1d01 100644 --- a/net/ipv6/fib6_notifier.c +++ b/net/ipv6/fib6_notifier.c @@ -27,15 +27,16 @@ static unsigned int fib6_seq_read(struct net *net) return fib6_tables_seq_read(net) + fib6_rules_seq_read(net); } -static int fib6_dump(struct net *net, struct notifier_block *nb) +static int fib6_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { int err; - err = fib6_rules_dump(net, nb); + err = fib6_rules_dump(net, nb, extack); if (err) return err; - return fib6_tables_dump(net, nb); + return fib6_tables_dump(net, nb, extack); } static const struct fib_notifier_ops fib6_notifier_ops_template = { diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index f9e8fe3ff0c5..fafe556d21e0 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -47,9 +47,10 @@ bool fib6_rule_default(const struct fib_rule *rule) } EXPORT_SYMBOL_GPL(fib6_rule_default); -int fib6_rules_dump(struct net *net, struct notifier_block *nb) +int fib6_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return fib_rules_dump(net, nb, AF_INET6); + return fib_rules_dump(net, nb, AF_INET6, extack); } unsigned int fib6_rules_seq_read(struct net *net) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 76124a909395..f66bc2af4e9d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -359,9 +359,11 @@ unsigned int fib6_tables_seq_read(struct net *net) static int call_fib6_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, - struct fib6_info *rt) + struct fib6_info *rt, + struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { + .info.extack = extack, .rt = rt, }; @@ -401,13 +403,15 @@ int call_fib6_multipath_entry_notifiers(struct net *net, struct fib6_dump_arg { struct net *net; struct notifier_block *nb; + struct netlink_ext_ack *extack; }; static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { if (rt == arg->net->ipv6.fib6_null_entry) return 0; - return call_fib6_entry_notifier(arg->nb, FIB_EVENT_ENTRY_ADD, rt); + return call_fib6_entry_notifier(arg->nb, FIB_EVENT_ENTRY_ADD, + rt, arg->extack); } static int fib6_node_dump(struct fib6_walker *w) @@ -437,7 +441,8 @@ static int fib6_table_dump(struct net *net, struct fib6_table *tb, } /* Called with rcu_read_lock() */ -int fib6_tables_dump(struct net *net, struct notifier_block *nb) +int fib6_tables_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct fib6_dump_arg arg; struct fib6_walker *w; @@ -451,6 +456,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb) w->func = fib6_node_dump; arg.net = net; arg.nb = nb; + arg.extack = extack; w->args = &arg; for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 857a89ad4d6c..bfa49ff70531 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -265,9 +265,10 @@ static void __net_exit ip6mr_rules_exit(struct net *net) rtnl_unlock(); } -static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb) +static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR); + return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR, extack); } static unsigned int ip6mr_rules_seq_read(struct net *net) @@ -324,7 +325,8 @@ static void __net_exit ip6mr_rules_exit(struct net *net) rtnl_unlock(); } -static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb) +static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } @@ -1256,10 +1258,11 @@ static unsigned int ip6mr_seq_read(struct net *net) return net->ipv6.ipmr_seq + ip6mr_rules_seq_read(net); } -static int ip6mr_dump(struct net *net, struct notifier_block *nb) +static int ip6mr_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump, - ip6mr_mr_table_iter, &mrt_lock); + ip6mr_mr_table_iter, &mrt_lock, extack); } static struct notifier_block ip6_mr_notifier = { -- cgit v1.2.3-59-g8ed1b From 053e92aa3c20d37ab40692a851d63b4a40d1ff79 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:32 +0200 Subject: mlxsw: spectrum: Take devlink net instead of init_net Follow-up patch is going to allow to reload devlink instance into different network namespace, so use devlink_net() helper instead of init_net. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.h | 6 +++++ drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 6 ++--- drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 6 +++++ drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c | 2 +- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 29 +++++++++++++--------- .../ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 +- 6 files changed, 34 insertions(+), 17 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 5d7d2ab6d155..e1ef4d255b93 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include "trap.h" @@ -350,6 +351,11 @@ u64 mlxsw_core_res_get(struct mlxsw_core *mlxsw_core, #define MLXSW_CORE_RES_GET(mlxsw_core, short_res_id) \ mlxsw_core_res_get(mlxsw_core, MLXSW_RES_ID_##short_res_id) +static inline struct net *mlxsw_core_net(struct mlxsw_core *mlxsw_core) +{ + return devlink_net(priv_to_devlink(mlxsw_core)); +} + #define MLXSW_BUS_F_TXRX BIT(0) #define MLXSW_BUS_F_RESET BIT(1) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index a54a0dc82ff2..250448aecd67 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4864,7 +4864,7 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, * respin. */ mlxsw_sp->netdevice_nb.notifier_call = mlxsw_sp_netdevice_event; - err = register_netdevice_notifier_net(&init_net, + err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->netdevice_nb); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to register netdev notifier\n"); @@ -4888,7 +4888,7 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, err_ports_create: mlxsw_sp_dpipe_fini(mlxsw_sp); err_dpipe_init: - unregister_netdevice_notifier_net(&init_net, + unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->netdevice_nb); err_netdev_notifier: if (mlxsw_sp->clock) @@ -4975,7 +4975,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_ports_remove(mlxsw_sp); mlxsw_sp_dpipe_fini(mlxsw_sp); - unregister_netdevice_notifier_net(&init_net, + unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->netdevice_nb); if (mlxsw_sp->clock) { mlxsw_sp->ptp_ops->fini(mlxsw_sp->ptp_state); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index b2a0028b1694..f58d45e770cd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -982,4 +983,9 @@ int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, const struct devlink_trap_group *group); +static inline struct net *mlxsw_sp_net(struct mlxsw_sp *mlxsw_sp) +{ + return mlxsw_core_net(mlxsw_sp->core); +} + #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index 17f334b46c40..2153bcc4b585 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -870,7 +870,7 @@ void mlxsw_sp_nve_fid_disable(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_fid_vni(fid, &vni))) goto out; - nve_dev = dev_get_by_index(&init_net, nve_ifindex); + nve_dev = dev_get_by_index(mlxsw_sp_net(mlxsw_sp), nve_ifindex); if (!nve_dev) goto out; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 445e2daa54ac..3479f805b377 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -2551,14 +2552,14 @@ static int mlxsw_sp_router_schedule_work(struct net *net, struct mlxsw_sp_netevent_work *net_work; struct mlxsw_sp_router *router; - if (!net_eq(net, &init_net)) + router = container_of(nb, struct mlxsw_sp_router, netevent_nb); + if (!net_eq(net, mlxsw_sp_net(router->mlxsw_sp))) return NOTIFY_DONE; net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC); if (!net_work) return NOTIFY_BAD; - router = container_of(nb, struct mlxsw_sp_router, netevent_nb); INIT_WORK(&net_work->work, cb); net_work->mlxsw_sp = router->mlxsw_sp; mlxsw_core_schedule_work(&net_work->work); @@ -6195,7 +6196,7 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, rule = fr_info->rule; /* Rule only affects locally generated traffic */ - if (rule->iifindex == init_net.loopback_dev->ifindex) + if (rule->iifindex == mlxsw_sp_net(mlxsw_sp)->loopback_dev->ifindex) return 0; switch (info->family) { @@ -7953,9 +7954,10 @@ static void mlxsw_sp_mp_hash_field_set(char *recr2_pl, int field) mlxsw_reg_recr2_outer_header_fields_enable_set(recr2_pl, field, true); } -static void mlxsw_sp_mp4_hash_init(char *recr2_pl) +static void mlxsw_sp_mp4_hash_init(struct mlxsw_sp *mlxsw_sp, char *recr2_pl) { - bool only_l3 = !init_net.ipv4.sysctl_fib_multipath_hash_policy; + struct net *net = mlxsw_sp_net(mlxsw_sp); + bool only_l3 = !net->ipv4.sysctl_fib_multipath_hash_policy; mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV4_EN_NOT_TCP_NOT_UDP); @@ -7970,9 +7972,9 @@ static void mlxsw_sp_mp4_hash_init(char *recr2_pl) mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_TCP_UDP_DPORT); } -static void mlxsw_sp_mp6_hash_init(char *recr2_pl) +static void mlxsw_sp_mp6_hash_init(struct mlxsw_sp *mlxsw_sp, char *recr2_pl) { - bool only_l3 = !ip6_multipath_hash_policy(&init_net); + bool only_l3 = !ip6_multipath_hash_policy(mlxsw_sp_net(mlxsw_sp)); mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV6_EN_NOT_TCP_NOT_UDP); @@ -8000,8 +8002,8 @@ static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp) seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0); mlxsw_reg_recr2_pack(recr2_pl, seed); - mlxsw_sp_mp4_hash_init(recr2_pl); - mlxsw_sp_mp6_hash_init(recr2_pl); + mlxsw_sp_mp4_hash_init(mlxsw_sp, recr2_pl); + mlxsw_sp_mp6_hash_init(mlxsw_sp, recr2_pl); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(recr2), recr2_pl); } @@ -8032,7 +8034,8 @@ static int mlxsw_sp_dscp_init(struct mlxsw_sp *mlxsw_sp) static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) { - bool usp = init_net.ipv4.sysctl_ip_fwd_update_priority; + struct net *net = mlxsw_sp_net(mlxsw_sp); + bool usp = net->ipv4.sysctl_ip_fwd_update_priority; char rgcr_pl[MLXSW_REG_RGCR_LEN]; u64 max_rifs; int err; @@ -8134,7 +8137,8 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) goto err_dscp_init; mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; - err = register_fib_notifier(&init_net, &mlxsw_sp->router->fib_nb, + err = register_fib_notifier(mlxsw_sp_net(mlxsw_sp), + &mlxsw_sp->router->fib_nb, mlxsw_sp_router_fib_dump_flush, NULL); if (err) goto err_register_fib_notifier; @@ -8174,7 +8178,8 @@ err_register_inetaddr_notifier: void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) { - unregister_fib_notifier(&init_net, &mlxsw_sp->router->fib_nb); + unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), + &mlxsw_sp->router->fib_nb); unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 5ecb45118400..a3af171c6358 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -2591,7 +2591,7 @@ __mlxsw_sp_fdb_notify_mac_uc_tunnel_process(struct mlxsw_sp *mlxsw_sp, if (err) return err; - dev = __dev_get_by_index(&init_net, nve_ifindex); + dev = __dev_get_by_index(mlxsw_sp_net(mlxsw_sp), nve_ifindex); if (!dev) return -EINVAL; *nve_dev = dev; -- cgit v1.2.3-59-g8ed1b From 6b2a880f9dd1c8632f1afc5e3f77759ce3ff815f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:33 +0200 Subject: mlxsw: Register port netdevices into net of core When creating netdevices for ports, put them under network namespace that the core/parent devlink belongs to. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/minimal.c | 1 + drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 + drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 1 + 3 files changed, 3 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index 471b0ca6d69a..cee16ad58307 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -172,6 +172,7 @@ mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u8 local_port, u8 module) } SET_NETDEV_DEV(dev, mlxsw_m->bus_info->dev); + dev_net_set(dev, mlxsw_core_net(mlxsw_m->core)); mlxsw_m_port = netdev_priv(dev); mlxsw_m_port->dev = dev; mlxsw_m_port->mlxsw_m = mlxsw_m; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 250448aecd67..a9ea9c7b9e59 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3635,6 +3635,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, goto err_alloc_etherdev; } SET_NETDEV_DEV(dev, mlxsw_sp->bus_info->dev); + dev_net_set(dev, mlxsw_sp_net(mlxsw_sp)); mlxsw_sp_port = netdev_priv(dev); mlxsw_sp_port->dev = dev; mlxsw_sp_port->mlxsw_sp = mlxsw_sp; diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 1c14c051ee52..a4d09392a8d7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -992,6 +992,7 @@ static int __mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port, if (!dev) return -ENOMEM; SET_NETDEV_DEV(dev, mlxsw_sx->bus_info->dev); + dev_net_set(dev, mlxsw_core_net(mlxsw_sx->core)); mlxsw_sx_port = netdev_priv(dev); mlxsw_sx_port->dev = dev; mlxsw_sx_port->mlxsw_sx = mlxsw_sx; -- cgit v1.2.3-59-g8ed1b From 5bcfb6a45a614253a65ad45904fba4d93bde372d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:34 +0200 Subject: mlxsw: Propagate extack down to register_fib_notifier() During the devlink reaload the extack is present, so propagate it all the way down to register_fib_notifier() call in spectrum_router.c. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 13 ++++++++----- drivers/net/ethernet/mellanox/mlxsw/core.h | 6 ++++-- drivers/net/ethernet/mellanox/mlxsw/i2c.c | 2 +- drivers/net/ethernet/mellanox/mlxsw/minimal.c | 3 ++- drivers/net/ethernet/mellanox/mlxsw/pci.c | 2 +- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 15 +++++++++------ drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 3 ++- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 5 +++-- drivers/net/ethernet/mellanox/mlxsw/switchib.c | 3 ++- drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 3 ++- 10 files changed, 34 insertions(+), 21 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 14dcc786926d..1e61a012ca43 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1005,7 +1005,7 @@ mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink, return mlxsw_core_bus_device_register(mlxsw_core->bus_info, mlxsw_core->bus, mlxsw_core->bus_priv, true, - devlink); + devlink, extack); } static int mlxsw_devlink_flash_update(struct devlink *devlink, @@ -1098,7 +1098,8 @@ static int __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, const struct mlxsw_bus *mlxsw_bus, void *bus_priv, bool reload, - struct devlink *devlink) + struct devlink *devlink, + struct netlink_ext_ack *extack) { const char *device_kind = mlxsw_bus_info->device_kind; struct mlxsw_core *mlxsw_core; @@ -1172,7 +1173,7 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, } if (mlxsw_driver->init) { - err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info); + err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info, extack); if (err) goto err_driver_init; } @@ -1223,14 +1224,16 @@ err_devlink_alloc: int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, const struct mlxsw_bus *mlxsw_bus, void *bus_priv, bool reload, - struct devlink *devlink) + struct devlink *devlink, + struct netlink_ext_ack *extack) { bool called_again = false; int err; again: err = __mlxsw_core_bus_device_register(mlxsw_bus_info, mlxsw_bus, - bus_priv, reload, devlink); + bus_priv, reload, + devlink, extack); /* -EAGAIN is returned in case the FW was updated. FW needs * a reset, so lets try to call __mlxsw_core_bus_device_register() * again. diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index e1ef4d255b93..3377a1b39b03 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -37,7 +37,8 @@ void mlxsw_core_driver_unregister(struct mlxsw_driver *mlxsw_driver); int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, const struct mlxsw_bus *mlxsw_bus, void *bus_priv, bool reload, - struct devlink *devlink); + struct devlink *devlink, + struct netlink_ext_ack *extack); void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, bool reload); struct mlxsw_tx_info { @@ -253,7 +254,8 @@ struct mlxsw_driver { const char *kind; size_t priv_size; int (*init)(struct mlxsw_core *mlxsw_core, - const struct mlxsw_bus_info *mlxsw_bus_info); + const struct mlxsw_bus_info *mlxsw_bus_info, + struct netlink_ext_ack *extack); void (*fini)(struct mlxsw_core *mlxsw_core); int (*basic_trap_groups_set)(struct mlxsw_core *mlxsw_core); int (*port_type_set)(struct mlxsw_core *mlxsw_core, u8 local_port, diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 95f408d0e103..34566eb62c47 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -640,7 +640,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client, err = mlxsw_core_bus_device_register(&mlxsw_i2c->bus_info, &mlxsw_i2c_bus, mlxsw_i2c, false, - NULL); + NULL, NULL); if (err) { dev_err(&client->dev, "Fail to register core bus\n"); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index cee16ad58307..5edd8de57a24 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -327,7 +327,8 @@ static void mlxsw_m_ports_remove(struct mlxsw_m *mlxsw_m) } static int mlxsw_m_init(struct mlxsw_core *mlxsw_core, - const struct mlxsw_bus_info *mlxsw_bus_info) + const struct mlxsw_bus_info *mlxsw_bus_info, + struct netlink_ext_ack *extack) { struct mlxsw_m *mlxsw_m = mlxsw_core_driver_priv(mlxsw_core); int err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index f1294b00efdf..914c33e46fb4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1802,7 +1802,7 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) err = mlxsw_core_bus_device_register(&mlxsw_pci->bus_info, &mlxsw_pci_bus, mlxsw_pci, false, - NULL); + NULL, NULL); if (err) { dev_err(&pdev->dev, "cannot register bus device\n"); goto err_bus_device_register; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index a9ea9c7b9e59..c91b8238c8c5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4739,7 +4739,8 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr); static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, - const struct mlxsw_bus_info *mlxsw_bus_info) + const struct mlxsw_bus_info *mlxsw_bus_info, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); int err; @@ -4832,7 +4833,7 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_acl_init; } - err = mlxsw_sp_router_init(mlxsw_sp); + err = mlxsw_sp_router_init(mlxsw_sp, extack); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n"); goto err_router_init; @@ -4927,7 +4928,8 @@ err_fids_init: } static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core, - const struct mlxsw_bus_info *mlxsw_bus_info) + const struct mlxsw_bus_info *mlxsw_bus_info, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); @@ -4947,11 +4949,12 @@ static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->listeners = mlxsw_sp1_listener; mlxsw_sp->listeners_count = ARRAY_SIZE(mlxsw_sp1_listener); - return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info); + return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info, extack); } static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core, - const struct mlxsw_bus_info *mlxsw_bus_info) + const struct mlxsw_bus_info *mlxsw_bus_info, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); @@ -4967,7 +4970,7 @@ static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->port_type_speed_ops = &mlxsw_sp2_port_type_speed_ops; mlxsw_sp->ptp_ops = &mlxsw_sp2_ptp_ops; - return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info); + return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info, extack); } static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index f58d45e770cd..8f99d70d6b8b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -525,7 +525,8 @@ union mlxsw_sp_l3addr { struct in6_addr addr6; }; -int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, + struct netlink_ext_ack *extack); void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp); int mlxsw_sp_netdevice_router_port_event(struct net_device *dev, unsigned long event, void *ptr); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 3479f805b377..0e99b64450ca 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -8061,7 +8061,8 @@ static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); } -int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) +int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, + struct netlink_ext_ack *extack) { struct mlxsw_sp_router *router; int err; @@ -8139,7 +8140,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; err = register_fib_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->fib_nb, - mlxsw_sp_router_fib_dump_flush, NULL); + mlxsw_sp_router_fib_dump_flush, extack); if (err) goto err_register_fib_notifier; diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchib.c b/drivers/net/ethernet/mellanox/mlxsw/switchib.c index 0d9356b3f65d..4ff1e623aa76 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchib.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchib.c @@ -446,7 +446,8 @@ static int mlxsw_sib_basic_trap_groups_set(struct mlxsw_core *mlxsw_core) } static int mlxsw_sib_init(struct mlxsw_core *mlxsw_core, - const struct mlxsw_bus_info *mlxsw_bus_info) + const struct mlxsw_bus_info *mlxsw_bus_info, + struct netlink_ext_ack *extack) { struct mlxsw_sib *mlxsw_sib = mlxsw_core_driver_priv(mlxsw_core); int err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index a4d09392a8d7..de6cb22f68b1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -1564,7 +1564,8 @@ static int mlxsw_sx_basic_trap_groups_set(struct mlxsw_core *mlxsw_core) } static int mlxsw_sx_init(struct mlxsw_core *mlxsw_core, - const struct mlxsw_bus_info *mlxsw_bus_info) + const struct mlxsw_bus_info *mlxsw_bus_info, + struct netlink_ext_ack *extack) { struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core); int err; -- cgit v1.2.3-59-g8ed1b From 070c63f20f6c739a3c534555f56c7327536bfcc2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:39 +0200 Subject: net: devlink: allow to change namespaces during reload All devlink instances are created in init_net and stay there for a lifetime. Allow user to be able to move devlink instances into namespaces during devlink reload operation. That ensures proper re-instantiation of driver objects, including netdevices. Signed-off-by: Jiri Pirko Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/main.c | 6 +- drivers/net/ethernet/mellanox/mlxsw/core.c | 1 + drivers/net/netdevsim/dev.c | 2 +- include/net/devlink.h | 2 +- include/uapi/linux/devlink.h | 4 + net/core/devlink.c | 154 +++++++++++++++++++++++++++-- 6 files changed, 158 insertions(+), 11 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index fce9b3a24347..22c72fb7206a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3935,13 +3935,17 @@ static void mlx4_restart_one_down(struct pci_dev *pdev); static int mlx4_restart_one_up(struct pci_dev *pdev, bool reload, struct devlink *devlink); -static int mlx4_devlink_reload_down(struct devlink *devlink, +static int mlx4_devlink_reload_down(struct devlink *devlink, bool netns_change, struct netlink_ext_ack *extack) { struct mlx4_priv *priv = devlink_priv(devlink); struct mlx4_dev *dev = &priv->dev; struct mlx4_dev_persistent *persist = dev->persist; + if (netns_change) { + NL_SET_ERR_MSG_MOD(extack, "Namespace change is not supported"); + return -EOPNOTSUPP; + } if (persist->num_vfs) mlx4_warn(persist->dev, "Reload performed on PF, will cause reset on operating Virtual Functions\n"); mlx4_restart_one_down(persist->pdev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 1e61a012ca43..1c29522a2af3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -985,6 +985,7 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, static int mlxsw_devlink_core_bus_device_reload_down(struct devlink *devlink, + bool netns_change, struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 7de80faab047..3f3c7cc21077 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -473,7 +473,7 @@ static int nsim_dev_reload_create(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack); static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev); -static int nsim_dev_reload_down(struct devlink *devlink, +static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change, struct netlink_ext_ack *extack) { struct nsim_dev *nsim_dev = devlink_priv(devlink); diff --git a/include/net/devlink.h b/include/net/devlink.h index 5ac2be0f0857..3c9d4a063c98 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -643,7 +643,7 @@ enum devlink_trap_group_generic_id { } struct devlink_ops { - int (*reload_down)(struct devlink *devlink, + int (*reload_down)(struct devlink *devlink, bool netns_change, struct netlink_ext_ack *extack); int (*reload_up)(struct devlink *devlink, struct netlink_ext_ack *extack); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 580b7a2e40e1..b558ea88b766 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -421,6 +421,10 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_FAILED, /* u8 0 or 1 */ + DEVLINK_ATTR_NETNS_FD, /* u32 */ + DEVLINK_ATTR_NETNS_PID, /* u32 */ + DEVLINK_ATTR_NETNS_ID, /* u32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 362cbbcca225..c4d8c4ab0fb5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -435,8 +435,16 @@ static void devlink_nl_post_doit(const struct genl_ops *ops, { struct devlink *devlink; - devlink = devlink_get_from_info(info); - if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK) + /* When devlink changes netns, it would not be found + * by devlink_get_from_info(). So try if it is stored first. + */ + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) { + devlink = info->user_ptr[0]; + } else { + devlink = devlink_get_from_info(info); + WARN_ON(IS_ERR(devlink)); + } + if (!IS_ERR(devlink) && ~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK) mutex_unlock(&devlink->lock); mutex_unlock(&devlink_mutex); } @@ -2675,6 +2683,72 @@ devlink_resources_validate(struct devlink *devlink, return err; } +static struct net *devlink_netns_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; + struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; + struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; + struct net *net; + + if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { + NL_SET_ERR_MSG(info->extack, "multiple netns identifying attributes specified"); + return ERR_PTR(-EINVAL); + } + + if (netns_pid_attr) { + net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); + } else if (netns_fd_attr) { + net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); + } else if (netns_id_attr) { + net = get_net_ns_by_id(sock_net(skb->sk), + nla_get_u32(netns_id_attr)); + if (!net) + net = ERR_PTR(-EINVAL); + } else { + WARN_ON(1); + net = ERR_PTR(-EINVAL); + } + if (IS_ERR(net)) { + NL_SET_ERR_MSG(info->extack, "Unknown network namespace"); + return ERR_PTR(-EINVAL); + } + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return ERR_PTR(-EPERM); + } + return net; +} + +static void devlink_param_notify(struct devlink *devlink, + unsigned int port_index, + struct devlink_param_item *param_item, + enum devlink_command cmd); + +static void devlink_reload_netns_change(struct devlink *devlink, + struct net *dest_net) +{ + struct devlink_param_item *param_item; + + /* Userspace needs to be notified about devlink objects + * removed from original and entering new network namespace. + * The rest of the devlink objects are re-created during + * reload process so the notifications are generated separatelly. + */ + + list_for_each_entry(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_DEL); + devlink_notify(devlink, DEVLINK_CMD_DEL); + + devlink_net_set(devlink, dest_net); + + devlink_notify(devlink, DEVLINK_CMD_NEW); + list_for_each_entry(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_NEW); +} + static bool devlink_reload_supported(struct devlink *devlink) { return devlink->ops->reload_down && devlink->ops->reload_up; @@ -2695,9 +2769,27 @@ bool devlink_is_reload_failed(const struct devlink *devlink) } EXPORT_SYMBOL_GPL(devlink_is_reload_failed); +static int devlink_reload(struct devlink *devlink, struct net *dest_net, + struct netlink_ext_ack *extack) +{ + int err; + + err = devlink->ops->reload_down(devlink, !!dest_net, extack); + if (err) + return err; + + if (dest_net && !net_eq(dest_net, devlink_net(devlink))) + devlink_reload_netns_change(devlink, dest_net); + + err = devlink->ops->reload_up(devlink, extack); + devlink_reload_failed_set(devlink, !!err); + return err; +} + static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; + struct net *dest_net = NULL; int err; if (!devlink_reload_supported(devlink)) @@ -2708,11 +2800,20 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); return err; } - err = devlink->ops->reload_down(devlink, info->extack); - if (err) - return err; - err = devlink->ops->reload_up(devlink, info->extack); - devlink_reload_failed_set(devlink, !!err); + + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + + err = devlink_reload(devlink, dest_net, info->extack); + + if (dest_net) + put_net(dest_net); + return err; } @@ -5794,6 +5895,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -8061,9 +8165,43 @@ int devlink_compat_switch_id_get(struct net_device *dev, return 0; } +static void __net_exit devlink_pernet_pre_exit(struct net *net) +{ + struct devlink *devlink; + int err; + + /* In case network namespace is getting destroyed, reload + * all devlink instances from this namespace into init_net. + */ + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (net_eq(devlink_net(devlink), net)) { + if (WARN_ON(!devlink_reload_supported(devlink))) + continue; + err = devlink_reload(devlink, &init_net, NULL); + if (err) + pr_warn("Failed to reload devlink instance into init_net\n"); + } + } + mutex_unlock(&devlink_mutex); +} + +static struct pernet_operations devlink_pernet_ops __net_initdata = { + .pre_exit = devlink_pernet_pre_exit, +}; + static int __init devlink_init(void) { - return genl_register_family(&devlink_nl_family); + int err; + + err = genl_register_family(&devlink_nl_family); + if (err) + goto out; + err = register_pernet_subsys(&devlink_pernet_ops); + +out: + WARN_ON(err); + return err; } subsys_initcall(devlink_init); -- cgit v1.2.3-59-g8ed1b From 5cfa030a1c2cf70e2fb0815a74fab1b459bc2a2b Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Sun, 6 Oct 2019 09:34:48 +0300 Subject: mlxsw: reg: Extend MGPIR register with new field exposing the number of QSFP modules Extend MGPIR - Management General Peripheral Information Register with new field "num_of_modules" exposing the number of modules supported by specific system. Signed-off-by: Vadim Pasternak Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c | 2 +- drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 3 ++- drivers/net/ethernet/mellanox/mlxsw/reg.h | 10 +++++++++- 3 files changed, 12 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c index 5b00726c4346..69c192839bf9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c @@ -590,7 +590,7 @@ static int mlxsw_hwmon_gearbox_init(struct mlxsw_hwmon *mlxsw_hwmon) if (err) return err; - mlxsw_reg_mgpir_unpack(mgpir_pl, &gbox_num, NULL, NULL); + mlxsw_reg_mgpir_unpack(mgpir_pl, &gbox_num, NULL, NULL, NULL); if (!gbox_num) return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index 35a1dc89c28a..b2c76a95f671 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -913,7 +913,8 @@ mlxsw_thermal_gearboxes_init(struct device *dev, struct mlxsw_core *core, if (err) return err; - mlxsw_reg_mgpir_unpack(mgpir_pl, &thermal->tz_gearbox_num, NULL, NULL); + mlxsw_reg_mgpir_unpack(mgpir_pl, &thermal->tz_gearbox_num, NULL, NULL, + NULL); if (!thermal->tz_gearbox_num) return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 5494cf93f34c..7b538e698a3d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -9531,6 +9531,12 @@ MLXSW_ITEM32(reg, mgpir, devices_per_flash, 0x00, 16, 8); */ MLXSW_ITEM32(reg, mgpir, num_of_devices, 0x00, 0, 8); +/* num_of_modules + * Number of modules. + * Access: RO + */ +MLXSW_ITEM32(reg, mgpir, num_of_modules, 0x04, 0, 8); + static inline void mlxsw_reg_mgpir_pack(char *payload) { MLXSW_REG_ZERO(mgpir, payload); @@ -9539,7 +9545,7 @@ static inline void mlxsw_reg_mgpir_pack(char *payload) static inline void mlxsw_reg_mgpir_unpack(char *payload, u8 *num_of_devices, enum mlxsw_reg_mgpir_device_type *device_type, - u8 *devices_per_flash) + u8 *devices_per_flash, u8 *num_of_modules) { if (num_of_devices) *num_of_devices = mlxsw_reg_mgpir_num_of_devices_get(payload); @@ -9548,6 +9554,8 @@ mlxsw_reg_mgpir_unpack(char *payload, u8 *num_of_devices, if (devices_per_flash) *devices_per_flash = mlxsw_reg_mgpir_devices_per_flash_get(payload); + if (num_of_modules) + *num_of_modules = mlxsw_reg_mgpir_num_of_modules_get(payload); } /* TNGCR - Tunneling NVE General Configuration Register -- cgit v1.2.3-59-g8ed1b From ea30a92a4674eab955aee7bb8a017791f0e7d002 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Sun, 6 Oct 2019 09:34:49 +0300 Subject: mlxsw: hwmon: Provide optimization for QSFP modules number detection Use new field "num_of_modules" of MGPIR register for "hwmon" interface in order to get the number of modules supported by system directly from the system configuration, instead of getting it from port to module mapping info. Reading this info through MGPIR register is faster and does not depend on possible dynamic re-configuration of ports. In case of port dynamic re-configuration some modules can logically "disappear" as a result of port split and un-spilt operations, which can cause missing of some modules, in case this info is taken from port to module mapping info. Signed-off-by: Vadim Pasternak Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c | 64 +++++++++++------------- 1 file changed, 29 insertions(+), 35 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c index 69c192839bf9..9bf8da5f6daf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c @@ -41,7 +41,7 @@ struct mlxsw_hwmon { struct mlxsw_hwmon_attr hwmon_attrs[MLXSW_HWMON_ATTR_COUNT]; unsigned int attrs_count; u8 sensor_count; - u8 module_sensor_count; + u8 module_sensor_max; }; static ssize_t mlxsw_hwmon_temp_show(struct device *dev, @@ -56,7 +56,7 @@ static ssize_t mlxsw_hwmon_temp_show(struct device *dev, int err; index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index, - mlxsw_hwmon->module_sensor_count); + mlxsw_hwmon->module_sensor_max); mlxsw_reg_mtmp_pack(mtmp_pl, index, false, false); err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl); if (err) { @@ -79,7 +79,7 @@ static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev, int err; index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index, - mlxsw_hwmon->module_sensor_count); + mlxsw_hwmon->module_sensor_max); mlxsw_reg_mtmp_pack(mtmp_pl, index, false, false); err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl); if (err) { @@ -109,7 +109,7 @@ static ssize_t mlxsw_hwmon_temp_rst_store(struct device *dev, return -EINVAL; index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index, - mlxsw_hwmon->module_sensor_count); + mlxsw_hwmon->module_sensor_max); mlxsw_reg_mtmp_pack(mtmp_pl, index, true, true); err = mlxsw_reg_write(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl); if (err) { @@ -336,7 +336,7 @@ mlxsw_hwmon_gbox_temp_label_show(struct device *dev, container_of(attr, struct mlxsw_hwmon_attr, dev_attr); struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; int index = mlwsw_hwmon_attr->type_index - - mlxsw_hwmon->module_sensor_count + 1; + mlxsw_hwmon->module_sensor_max + 1; return sprintf(buf, "gearbox %03u\n", index); } @@ -528,51 +528,45 @@ static int mlxsw_hwmon_fans_init(struct mlxsw_hwmon *mlxsw_hwmon) static int mlxsw_hwmon_module_init(struct mlxsw_hwmon *mlxsw_hwmon) { - unsigned int module_count = mlxsw_core_max_ports(mlxsw_hwmon->core); - char pmlp_pl[MLXSW_REG_PMLP_LEN] = {0}; - int i, index; - u8 width; - int err; + char mgpir_pl[MLXSW_REG_MGPIR_LEN]; + u8 module_sensor_max; + int i, err; if (!mlxsw_core_res_query_enabled(mlxsw_hwmon->core)) return 0; + mlxsw_reg_mgpir_pack(mgpir_pl); + err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mgpir), mgpir_pl); + if (err) + return err; + + mlxsw_reg_mgpir_unpack(mgpir_pl, NULL, NULL, NULL, + &module_sensor_max); + /* Add extra attributes for module temperature. Sensor index is * assigned to sensor_count value, while all indexed before * sensor_count are already utilized by the sensors connected through * mtmp register by mlxsw_hwmon_temp_init(). */ - index = mlxsw_hwmon->sensor_count; - for (i = 1; i < module_count; i++) { - mlxsw_reg_pmlp_pack(pmlp_pl, i); - err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(pmlp), - pmlp_pl); - if (err) { - dev_err(mlxsw_hwmon->bus_info->dev, "Failed to read module index %d\n", - i); - return err; - } - width = mlxsw_reg_pmlp_width_get(pmlp_pl); - if (!width) - continue; + mlxsw_hwmon->module_sensor_max = mlxsw_hwmon->sensor_count + + module_sensor_max; + for (i = mlxsw_hwmon->sensor_count; + i < mlxsw_hwmon->module_sensor_max; i++) { mlxsw_hwmon_attr_add(mlxsw_hwmon, - MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE, index, - index); + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE, i, i); mlxsw_hwmon_attr_add(mlxsw_hwmon, MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT, - index, index); + i, i); mlxsw_hwmon_attr_add(mlxsw_hwmon, - MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT, - index, index); + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT, i, + i); mlxsw_hwmon_attr_add(mlxsw_hwmon, MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG, - index, index); + i, i); mlxsw_hwmon_attr_add(mlxsw_hwmon, MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL, - index, index); - index++; + i, i); } - mlxsw_hwmon->module_sensor_count = index; return 0; } @@ -594,10 +588,10 @@ static int mlxsw_hwmon_gearbox_init(struct mlxsw_hwmon *mlxsw_hwmon) if (!gbox_num) return 0; - index = mlxsw_hwmon->module_sensor_count; - max_index = mlxsw_hwmon->module_sensor_count + gbox_num; + index = mlxsw_hwmon->module_sensor_max; + max_index = mlxsw_hwmon->module_sensor_max + gbox_num; while (index < max_index) { - sensor_index = index % mlxsw_hwmon->module_sensor_count + + sensor_index = index % mlxsw_hwmon->module_sensor_max + MLXSW_REG_MTMP_GBOX_INDEX_MIN; mlxsw_reg_mtmp_pack(mtmp_pl, sensor_index, true, true); err = mlxsw_reg_write(mlxsw_hwmon->core, -- cgit v1.2.3-59-g8ed1b From c5cb92d59b30229e22c286651640f55621586e84 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Sun, 6 Oct 2019 09:34:50 +0300 Subject: mlxsw: thermal: Provide optimization for QSFP modules number detection Use new field "num_of_modules" of MGPIR register for "thermal" interface in order to get the number of modules supported by system directly from the system configuration, instead of getting it from port to module mapping info. Signed-off-by: Vadim Pasternak Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 37 ++++++++++------------ 1 file changed, 16 insertions(+), 21 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index b2c76a95f671..c721b171bd8d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -112,6 +112,7 @@ struct mlxsw_thermal { struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS]; enum thermal_device_mode mode; struct mlxsw_thermal_module *tz_module_arr; + u8 tz_module_num; struct mlxsw_thermal_module *tz_gearbox_arr; u8 tz_gearbox_num; unsigned int tz_highest_score; @@ -775,23 +776,10 @@ static void mlxsw_thermal_module_tz_fini(struct thermal_zone_device *tzdev) static int mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core, - struct mlxsw_thermal *thermal, u8 local_port) + struct mlxsw_thermal *thermal, u8 module) { struct mlxsw_thermal_module *module_tz; - char pmlp_pl[MLXSW_REG_PMLP_LEN]; - u8 width, module; - int err; - - mlxsw_reg_pmlp_pack(pmlp_pl, local_port); - err = mlxsw_reg_query(core, MLXSW_REG(pmlp), pmlp_pl); - if (err) - return err; - width = mlxsw_reg_pmlp_width_get(pmlp_pl); - if (!width) - return 0; - - module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0); module_tz = &thermal->tz_module_arr[module]; /* Skip if parent is already set (case of port split). */ if (module_tz->parent) @@ -819,26 +807,34 @@ static int mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core, struct mlxsw_thermal *thermal) { - unsigned int module_count = mlxsw_core_max_ports(core); struct mlxsw_thermal_module *module_tz; + char mgpir_pl[MLXSW_REG_MGPIR_LEN]; int i, err; if (!mlxsw_core_res_query_enabled(core)) return 0; - thermal->tz_module_arr = kcalloc(module_count, + mlxsw_reg_mgpir_pack(mgpir_pl); + err = mlxsw_reg_query(core, MLXSW_REG(mgpir), mgpir_pl); + if (err) + return err; + + mlxsw_reg_mgpir_unpack(mgpir_pl, NULL, NULL, NULL, + &thermal->tz_module_num); + + thermal->tz_module_arr = kcalloc(thermal->tz_module_num, sizeof(*thermal->tz_module_arr), GFP_KERNEL); if (!thermal->tz_module_arr) return -ENOMEM; - for (i = 1; i < module_count; i++) { + for (i = 0; i < thermal->tz_module_num; i++) { err = mlxsw_thermal_module_init(dev, core, thermal, i); if (err) goto err_unreg_tz_module_arr; } - for (i = 0; i < module_count - 1; i++) { + for (i = 0; i < thermal->tz_module_num; i++) { module_tz = &thermal->tz_module_arr[i]; if (!module_tz->parent) continue; @@ -850,7 +846,7 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core, return 0; err_unreg_tz_module_arr: - for (i = module_count - 1; i >= 0; i--) + for (i = thermal->tz_module_num - 1; i >= 0; i--) mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]); kfree(thermal->tz_module_arr); return err; @@ -859,13 +855,12 @@ err_unreg_tz_module_arr: static void mlxsw_thermal_modules_fini(struct mlxsw_thermal *thermal) { - unsigned int module_count = mlxsw_core_max_ports(thermal->core); int i; if (!mlxsw_core_res_query_enabled(thermal->core)) return; - for (i = module_count - 1; i >= 0; i--) + for (i = thermal->tz_module_num - 1; i >= 0; i--) mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]); kfree(thermal->tz_module_arr); } -- cgit v1.2.3-59-g8ed1b From 762effaad63edca1d927bd6c98f21b870ee3f2a5 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Sun, 6 Oct 2019 09:34:51 +0300 Subject: mlxsw: core: Push minor/subminor fw version check into helper Add new API for FW "minor" and "subminor" version validation for sharing it between "spectrum" and "minimal" drivers. Use it in "spectrum" driver. Signed-off-by: Vadim Pasternak Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 10 ++++++++++ drivers/net/ethernet/mellanox/mlxsw/core.h | 5 +++++ drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 +--- 3 files changed, 16 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 1c29522a2af3..2b59f84b14f9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -127,6 +127,16 @@ bool mlxsw_core_res_query_enabled(const struct mlxsw_core *mlxsw_core) } EXPORT_SYMBOL(mlxsw_core_res_query_enabled); +bool +mlxsw_core_fw_rev_minor_subminor_validate(const struct mlxsw_fw_rev *rev, + const struct mlxsw_fw_rev *req_rev) +{ + return rev->minor > req_rev->minor || + (rev->minor == req_rev->minor && + rev->subminor >= req_rev->subminor); +} +EXPORT_SYMBOL(mlxsw_core_fw_rev_minor_subminor_validate); + struct mlxsw_rx_listener_item { struct list_head list; struct mlxsw_rx_listener rxl; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 3377a1b39b03..f25037074e2d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -24,6 +24,7 @@ struct mlxsw_core_port; struct mlxsw_driver; struct mlxsw_bus; struct mlxsw_bus_info; +struct mlxsw_fw_rev; unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core); @@ -31,6 +32,10 @@ void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core); bool mlxsw_core_res_query_enabled(const struct mlxsw_core *mlxsw_core); +bool +mlxsw_core_fw_rev_minor_subminor_validate(const struct mlxsw_fw_rev *rev, + const struct mlxsw_fw_rev *req_rev); + int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver); void mlxsw_core_driver_unregister(struct mlxsw_driver *mlxsw_driver); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index c91b8238c8c5..3c5154e559b2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -409,9 +409,7 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp) } if (MLXSW_SP_FWREV_MINOR_TO_BRANCH(rev->minor) == MLXSW_SP_FWREV_MINOR_TO_BRANCH(req_rev->minor) && - (rev->minor > req_rev->minor || - (rev->minor == req_rev->minor && - rev->subminor >= req_rev->subminor))) + mlxsw_core_fw_rev_minor_subminor_validate(rev, req_rev)) return 0; dev_info(mlxsw_sp->bus_info->dev, "The firmware version %d.%d.%d is incompatible with the driver\n", -- cgit v1.2.3-59-g8ed1b From 6935af8073a02ffd11a7e495dc318c0a51e18012 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Sun, 6 Oct 2019 09:34:52 +0300 Subject: mlxsw: minimal: Add validation for FW version Add validation for FW version in order to prevent driver initialization in case FW version is older than expected. FW version validation is necessary, because use of a new field 'num_of_modules' in MGPIR register is not backward compatible. FW 'minor' and 'subminor' versions are expected to be greater than or equal to 2000 and 1886, respectively. Signed-off-by: Vadim Pasternak Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/minimal.c | 30 +++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index 5edd8de57a24..2b543911ae00 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -16,6 +16,14 @@ static const char mlxsw_m_driver_name[] = "mlxsw_minimal"; +#define MLXSW_M_FWREV_MINOR 2000 +#define MLXSW_M_FWREV_SUBMINOR 1886 + +static const struct mlxsw_fw_rev mlxsw_m_fw_rev = { + .minor = MLXSW_M_FWREV_MINOR, + .subminor = MLXSW_M_FWREV_SUBMINOR, +}; + struct mlxsw_m_port; struct mlxsw_m { @@ -326,6 +334,24 @@ static void mlxsw_m_ports_remove(struct mlxsw_m *mlxsw_m) kfree(mlxsw_m->ports); } +static int mlxsw_m_fw_rev_validate(struct mlxsw_m *mlxsw_m) +{ + const struct mlxsw_fw_rev *rev = &mlxsw_m->bus_info->fw_rev; + + /* Validate driver and FW are compatible. + * Do not check major version, since it defines chip type, while + * driver is supposed to support any type. + */ + if (mlxsw_core_fw_rev_minor_subminor_validate(rev, &mlxsw_m_fw_rev)) + return 0; + + dev_err(mlxsw_m->bus_info->dev, "The firmware version %d.%d.%d is incompatible with the driver (required >= %d.%d.%d)\n", + rev->major, rev->minor, rev->subminor, rev->major, + mlxsw_m_fw_rev.minor, mlxsw_m_fw_rev.subminor); + + return -EINVAL; +} + static int mlxsw_m_init(struct mlxsw_core *mlxsw_core, const struct mlxsw_bus_info *mlxsw_bus_info, struct netlink_ext_ack *extack) @@ -336,6 +362,10 @@ static int mlxsw_m_init(struct mlxsw_core *mlxsw_core, mlxsw_m->core = mlxsw_core; mlxsw_m->bus_info = mlxsw_bus_info; + err = mlxsw_m_fw_rev_validate(mlxsw_m); + if (err) + return err; + err = mlxsw_m_base_mac_get(mlxsw_m); if (err) { dev_err(mlxsw_m->bus_info->dev, "Failed to get base mac\n"); -- cgit v1.2.3-59-g8ed1b From e7a981050a7fb9a14b652365c00d9c5a025704ce Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 10 Oct 2019 15:18:49 +0200 Subject: devlink: propagate extack down to health reporter ops During health reporter operations, driver might want to fill-up the extack message, so propagate extack down to the health reporter ops. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 9 ++++++--- .../net/ethernet/mellanox/mlx5/core/en/reporter_rx.c | 6 ++++-- .../net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 6 ++++-- drivers/net/ethernet/mellanox/mlx5/core/health.c | 12 ++++++++---- include/net/devlink.h | 8 +++++--- net/core/devlink.c | 20 +++++++++++--------- 6 files changed, 38 insertions(+), 23 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index e664392dccc0..ff1bc0ec2e7c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -16,7 +16,8 @@ #include "bnxt_devlink.h" static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg) + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) { struct bnxt *bp = devlink_health_reporter_priv(reporter); struct bnxt_fw_health *health = bp->fw_health; @@ -66,7 +67,8 @@ static const struct devlink_health_reporter_ops bnxt_dl_fw_reporter_ops = { }; static int bnxt_fw_reset_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, + struct netlink_ext_ack *extack) { struct bnxt *bp = devlink_health_reporter_priv(reporter); @@ -84,7 +86,8 @@ struct devlink_health_reporter_ops bnxt_dl_fw_reset_reporter_ops = { }; static int bnxt_fw_fatal_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, + struct netlink_ext_ack *extack) { struct bnxt *bp = devlink_health_reporter_priv(reporter); struct bnxt_fw_reporter_ctx *fw_reporter_ctx = priv_ctx; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index b860569d4247..6c72b592315b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -222,7 +222,8 @@ static int mlx5e_rx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx) } static int mlx5e_rx_reporter_recover(struct devlink_health_reporter *reporter, - void *context) + void *context, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_err_ctx *err_ctx = context; @@ -301,7 +302,8 @@ static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq, } static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg) + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_params *params = &priv->channels.params; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index bfed558637c2..b468549e96ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -135,7 +135,8 @@ static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx) } static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter, - void *context) + void *context, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_err_ctx *err_ctx = context; @@ -205,7 +206,8 @@ mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, } static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg) + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_txqsq *generic_sq = priv->txq2sq[0]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index d685122d9ff7..be3c3c704bfc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -390,7 +390,8 @@ static void print_health_info(struct mlx5_core_dev *dev) static int mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg) + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); struct mlx5_core_health *health = &dev->priv.health; @@ -491,7 +492,8 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev, static int mlx5_fw_reporter_dump(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, void *priv_ctx) + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); int err; @@ -545,7 +547,8 @@ static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = { static int mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); @@ -555,7 +558,8 @@ mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter, #define MLX5_CR_DUMP_CHUNK_SIZE 256 static int mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, void *priv_ctx) + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); u32 crdump_size = dev->priv.health.crdump_size; diff --git a/include/net/devlink.h b/include/net/devlink.h index 4095657fc23f..6bf3b9e0595a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -507,11 +507,13 @@ enum devlink_health_reporter_state { struct devlink_health_reporter_ops { char *name; int (*recover)(struct devlink_health_reporter *reporter, - void *priv_ctx); + void *priv_ctx, struct netlink_ext_ack *extack); int (*dump)(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, void *priv_ctx); + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack); int (*diagnose)(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg); + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack); }; /** diff --git a/net/core/devlink.c b/net/core/devlink.c index 95887462eecf..97e9a2246929 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4847,7 +4847,7 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); static int devlink_health_reporter_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, struct netlink_ext_ack *extack) { int err; @@ -4857,7 +4857,7 @@ devlink_health_reporter_recover(struct devlink_health_reporter *reporter, if (!reporter->ops->recover) return -EOPNOTSUPP; - err = reporter->ops->recover(reporter, priv_ctx); + err = reporter->ops->recover(reporter, priv_ctx, extack); if (err) return err; @@ -4878,7 +4878,8 @@ devlink_health_dump_clear(struct devlink_health_reporter *reporter) } static int devlink_health_do_dump(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, + struct netlink_ext_ack *extack) { int err; @@ -4899,7 +4900,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter, goto dump_err; err = reporter->ops->dump(reporter, reporter->dump_fmsg, - priv_ctx); + priv_ctx, extack); if (err) goto dump_err; @@ -4946,11 +4947,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter, mutex_lock(&reporter->dump_lock); /* store current dump of current error, for later analysis */ - devlink_health_do_dump(reporter, priv_ctx); + devlink_health_do_dump(reporter, priv_ctx, NULL); mutex_unlock(&reporter->dump_lock); if (reporter->auto_recover) - return devlink_health_reporter_recover(reporter, priv_ctx); + return devlink_health_reporter_recover(reporter, + priv_ctx, NULL); return 0; } @@ -5188,7 +5190,7 @@ static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, if (!reporter) return -EINVAL; - err = devlink_health_reporter_recover(reporter, NULL); + err = devlink_health_reporter_recover(reporter, NULL, info->extack); devlink_health_reporter_put(reporter); return err; @@ -5221,7 +5223,7 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, if (err) goto out; - err = reporter->ops->diagnose(reporter, fmsg); + err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) goto out; @@ -5256,7 +5258,7 @@ devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, } mutex_lock(&reporter->dump_lock); if (!start) { - err = devlink_health_do_dump(reporter, NULL); + err = devlink_health_do_dump(reporter, NULL, cb->extack); if (err) goto unlock; cb->args[1] = reporter->dump_ts; -- cgit v1.2.3-59-g8ed1b From 5bd29b9b357569d2be6de29eaa79a7dfc215b0e8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 12 Oct 2019 18:27:58 +0200 Subject: mlxsw: spectrum: Add support for 400Gbps (50Gbps per lane) link modes Extend speed support with 400Gbps Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 1 + drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 52 +++++++++++++++++++++----- 2 files changed, 43 insertions(+), 10 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 7b538e698a3d..f5e39758c6ac 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4111,6 +4111,7 @@ MLXSW_ITEM32(reg, ptys, an_status, 0x04, 28, 4); #define MLXSW_REG_PTYS_EXT_ETH_SPEED_CAUI_4_100GBASE_CR4_KR4 BIT(9) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_100GAUI_2_100GBASE_CR2_KR2 BIT(10) #define MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_4_200GBASE_CR4_KR4 BIT(12) +#define MLXSW_REG_PTYS_EXT_ETH_SPEED_400GAUI_8 BIT(15) /* reg_ptys_ext_eth_proto_cap * Extended Ethernet port supported speeds and protocols. diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3c5154e559b2..ae3c4da11520 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2912,9 +2912,22 @@ mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4[] = { #define MLXSW_SP2_MASK_ETHTOOL_200GAUI_4_200GBASE_CR4_KR4_LEN \ ARRAY_SIZE(mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4) +static const enum ethtool_link_mode_bit_indices +mlxsw_sp2_mask_ethtool_400gaui_8[] = { + ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT, + ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT, + ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT, + ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT, + ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT, +}; + +#define MLXSW_SP2_MASK_ETHTOOL_400GAUI_8_LEN \ + ARRAY_SIZE(mlxsw_sp2_mask_ethtool_400gaui_8) + #define MLXSW_SP_PORT_MASK_WIDTH_1X BIT(0) #define MLXSW_SP_PORT_MASK_WIDTH_2X BIT(1) #define MLXSW_SP_PORT_MASK_WIDTH_4X BIT(2) +#define MLXSW_SP_PORT_MASK_WIDTH_8X BIT(3) static u8 mlxsw_sp_port_mask_width_get(u8 width) { @@ -2925,6 +2938,8 @@ static u8 mlxsw_sp_port_mask_width_get(u8 width) return MLXSW_SP_PORT_MASK_WIDTH_2X; case 4: return MLXSW_SP_PORT_MASK_WIDTH_4X; + case 8: + return MLXSW_SP_PORT_MASK_WIDTH_8X; default: WARN_ON_ONCE(1); return 0; @@ -2946,7 +2961,8 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_SGMII_100M_LEN, .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | MLXSW_SP_PORT_MASK_WIDTH_2X | - MLXSW_SP_PORT_MASK_WIDTH_4X, + MLXSW_SP_PORT_MASK_WIDTH_4X | + MLXSW_SP_PORT_MASK_WIDTH_8X, .speed = SPEED_100, }, { @@ -2955,7 +2971,8 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_1000BASE_X_SGMII_LEN, .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | MLXSW_SP_PORT_MASK_WIDTH_2X | - MLXSW_SP_PORT_MASK_WIDTH_4X, + MLXSW_SP_PORT_MASK_WIDTH_4X | + MLXSW_SP_PORT_MASK_WIDTH_8X, .speed = SPEED_1000, }, { @@ -2964,7 +2981,8 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_2_5GBASE_X_2_5GMII_LEN, .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | MLXSW_SP_PORT_MASK_WIDTH_2X | - MLXSW_SP_PORT_MASK_WIDTH_4X, + MLXSW_SP_PORT_MASK_WIDTH_4X | + MLXSW_SP_PORT_MASK_WIDTH_8X, .speed = SPEED_2500, }, { @@ -2973,7 +2991,8 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_5GBASE_R_LEN, .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | MLXSW_SP_PORT_MASK_WIDTH_2X | - MLXSW_SP_PORT_MASK_WIDTH_4X, + MLXSW_SP_PORT_MASK_WIDTH_4X | + MLXSW_SP_PORT_MASK_WIDTH_8X, .speed = SPEED_5000, }, { @@ -2982,14 +3001,16 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_XFI_XAUI_1_10G_LEN, .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | MLXSW_SP_PORT_MASK_WIDTH_2X | - MLXSW_SP_PORT_MASK_WIDTH_4X, + MLXSW_SP_PORT_MASK_WIDTH_4X | + MLXSW_SP_PORT_MASK_WIDTH_8X, .speed = SPEED_10000, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_XLAUI_4_XLPPI_4_40G, .mask_ethtool = mlxsw_sp2_mask_ethtool_xlaui_4_xlppi_4_40g, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_XLAUI_4_XLPPI_4_40G_LEN, - .mask_width = MLXSW_SP_PORT_MASK_WIDTH_4X, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_4X | + MLXSW_SP_PORT_MASK_WIDTH_8X, .speed = SPEED_40000, }, { @@ -2998,7 +3019,8 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_25GAUI_1_25GBASE_CR_KR_LEN, .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | MLXSW_SP_PORT_MASK_WIDTH_2X | - MLXSW_SP_PORT_MASK_WIDTH_4X, + MLXSW_SP_PORT_MASK_WIDTH_4X | + MLXSW_SP_PORT_MASK_WIDTH_8X, .speed = SPEED_25000, }, { @@ -3006,7 +3028,8 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .mask_ethtool = mlxsw_sp2_mask_ethtool_50gaui_2_laui_2_50gbase_cr2_kr2, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_50GAUI_2_LAUI_2_50GBASE_CR2_KR2_LEN, .mask_width = MLXSW_SP_PORT_MASK_WIDTH_2X | - MLXSW_SP_PORT_MASK_WIDTH_4X, + MLXSW_SP_PORT_MASK_WIDTH_4X | + MLXSW_SP_PORT_MASK_WIDTH_8X, .speed = SPEED_50000, }, { @@ -3020,7 +3043,8 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_CAUI_4_100GBASE_CR4_KR4, .mask_ethtool = mlxsw_sp2_mask_ethtool_caui_4_100gbase_cr4_kr4, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_CAUI_4_100GBASE_CR4_KR4_LEN, - .mask_width = MLXSW_SP_PORT_MASK_WIDTH_4X, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_4X | + MLXSW_SP_PORT_MASK_WIDTH_8X, .speed = SPEED_100000, }, { @@ -3034,9 +3058,17 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_4_200GBASE_CR4_KR4, .mask_ethtool = mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_200GAUI_4_200GBASE_CR4_KR4_LEN, - .mask_width = MLXSW_SP_PORT_MASK_WIDTH_4X, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_4X | + MLXSW_SP_PORT_MASK_WIDTH_8X, .speed = SPEED_200000, }, + { + .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_400GAUI_8, + .mask_ethtool = mlxsw_sp2_mask_ethtool_400gaui_8, + .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_400GAUI_8_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_8X, + .speed = SPEED_400000, + }, }; #define MLXSW_SP2_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp2_port_link_mode) -- cgit v1.2.3-59-g8ed1b From 868678c574ecbd09d14331cf3b5418b5b28f7288 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Thu, 17 Oct 2019 09:55:14 +0300 Subject: mlxsw: spectrum: Register switched port analyzers (SPAN) as resource The switch supports an enhanced switched port analyzer that enables selecting network traffic for analysis by a network analyzer. SPAN agents are configured and consumed whenever a tc filter is added with a mirror action to a new destination. The destination can either be a physical port (e.g., swp1), a VLAN device or a gretap. Expose the maximum number of SPAN agents and their current usage to the user. Signed-off-by: Danielle Ratson Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 51 +++++++++++++++++++++- drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 3 ++ .../net/ethernet/mellanox/mlxsw/spectrum_span.c | 21 +++++++++ 3 files changed, 73 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index ae3c4da11520..1275d21e8fbd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -5202,14 +5202,61 @@ static int mlxsw_sp2_resources_kvd_register(struct mlxsw_core *mlxsw_core) &kvd_size_params); } +static int mlxsw_sp_resources_span_register(struct mlxsw_core *mlxsw_core) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_core); + struct devlink_resource_size_params span_size_params; + u32 max_span; + + if (!MLXSW_CORE_RES_VALID(mlxsw_core, MAX_SPAN)) + return -EIO; + + max_span = MLXSW_CORE_RES_GET(mlxsw_core, MAX_SPAN); + devlink_resource_size_params_init(&span_size_params, max_span, max_span, + 1, DEVLINK_RESOURCE_UNIT_ENTRY); + + return devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_SPAN, + max_span, MLXSW_SP_RESOURCE_SPAN, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &span_size_params); +} + static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core) { - return mlxsw_sp1_resources_kvd_register(mlxsw_core); + int err; + + err = mlxsw_sp1_resources_kvd_register(mlxsw_core); + if (err) + return err; + + err = mlxsw_sp_resources_span_register(mlxsw_core); + if (err) + goto err_resources_span_register; + + return 0; + +err_resources_span_register: + devlink_resources_unregister(priv_to_devlink(mlxsw_core), NULL); + return err; } static int mlxsw_sp2_resources_register(struct mlxsw_core *mlxsw_core) { - return mlxsw_sp2_resources_kvd_register(mlxsw_core); + int err; + + err = mlxsw_sp2_resources_kvd_register(mlxsw_core); + if (err) + return err; + + err = mlxsw_sp_resources_span_register(mlxsw_core); + if (err) + goto err_resources_span_register; + + return 0; + +err_resources_span_register: + devlink_resources_unregister(priv_to_devlink(mlxsw_core), NULL); + return err; } static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 8f99d70d6b8b..a5fdd84b4ca7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -48,6 +48,8 @@ #define MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS "chunks" #define MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS "large_chunks" +#define MLXSW_SP_RESOURCE_NAME_SPAN "span_agents" + enum mlxsw_sp_resource_id { MLXSW_SP_RESOURCE_KVD = 1, MLXSW_SP_RESOURCE_KVD_LINEAR, @@ -56,6 +58,7 @@ enum mlxsw_sp_resource_id { MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE, MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS, MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS, + MLXSW_SP_RESOURCE_SPAN, }; struct mlxsw_sp_port; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 560a60e522f9..200d324e6d99 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -14,8 +14,23 @@ #include "spectrum_span.h" #include "spectrum_switchdev.h" +static u64 mlxsw_sp_span_occ_get(void *priv) +{ + const struct mlxsw_sp *mlxsw_sp = priv; + u64 occ = 0; + int i; + + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + if (mlxsw_sp->span.entries[i].ref_count) + occ++; + } + + return occ; +} + int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) { + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); int i; if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_SPAN)) @@ -36,13 +51,19 @@ int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) curr->id = i; } + devlink_resource_occ_get_register(devlink, MLXSW_SP_RESOURCE_SPAN, + mlxsw_sp_span_occ_get, mlxsw_sp); + return 0; } void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp) { + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); int i; + devlink_resource_occ_get_unregister(devlink, MLXSW_SP_RESOURCE_SPAN); + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; -- cgit v1.2.3-59-g8ed1b From f366cd2a2e510b155e18b21a2d149332aa08eb61 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 21 Oct 2019 13:30:30 +0300 Subject: mlxsw: reg: Add macro for getting QSFP module EEPROM page number Provide a macro for getting QSFP module EEPROM page number from the optional upper page number row offset, specified in request. Signed-off-by: Vadim Pasternak Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index f5e39758c6ac..adb63a266fc7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -8412,6 +8412,7 @@ MLXSW_ITEM32(reg, mcia, device_address, 0x04, 0, 16); MLXSW_ITEM32(reg, mcia, size, 0x08, 0, 16); #define MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH 256 +#define MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH 128 #define MLXSW_REG_MCIA_EEPROM_SIZE 48 #define MLXSW_REG_MCIA_I2C_ADDR_LOW 0x50 #define MLXSW_REG_MCIA_I2C_ADDR_HIGH 0x51 @@ -8447,6 +8448,14 @@ enum mlxsw_reg_mcia_eeprom_module_info { */ MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_REG_MCIA_EEPROM_SIZE); +/* This is used to access the optional upper pages (1-3) in the QSFP+ + * memory map. Page 1 is available on offset 256 through 383, page 2 - + * on offset 384 through 511, page 3 - on offset 512 through 639. + */ +#define MLXSW_REG_MCIA_PAGE_GET(off) (((off) - \ + MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) / \ + MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH + 1) + static inline void mlxsw_reg_mcia_pack(char *payload, u8 module, u8 lock, u8 page_number, u16 device_addr, u8 size, u8 i2c_device_addr) -- cgit v1.2.3-59-g8ed1b From a45bfb5a50701cec6799cf24386c2be56770328d Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 21 Oct 2019 13:30:31 +0300 Subject: mlxsw: core: Extend QSFP EEPROM size for ethtool Extend the size of QSFP EEPROM for the cable types SSF8436 and SFF8636 from 256 to 640 bytes in order to expose all the EEPROM pages by ethtool. For SFF-8636 and SFF-8436 specifications, the driver exposes 256 bytes of data for ethtool's get_module_eeprom() callback. This is because the driver uses the below defines to specify SFF module length in ethtool's get_module_info() callback: 'ETH_MODULE_SFF_8636_LEN' and 'ETH_MODULE_SFF_8436_LEN' (both are 256). As a result of exposing 256 bytes only, ethtool shows wrong "zero" info for pages 1, 2, 3. The patch changes the length returned by callback for get_module_info() to the values from the next defines: 'ETH_MODULE_SFF_8636_MAX_LEN' and 'ETH_MODULE_SFF_8436_MAX_LEN' (both are 640) to allow exposing of upper page 1, 2 and 3. Signed-off-by: Vadim Pasternak Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlxsw/core_env.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index d2c7ce67c300..08215fed193d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -50,6 +50,7 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module, char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; char mcia_pl[MLXSW_REG_MCIA_LEN]; u16 i2c_addr; + u8 page = 0; int status; int err; @@ -62,11 +63,21 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module, i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_LOW; if (offset >= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) { - i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_HIGH; - offset -= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH; + page = MLXSW_REG_MCIA_PAGE_GET(offset); + offset -= MLXSW_REG_MCIA_EEPROM_UP_PAGE_LENGTH * page; + /* When reading upper pages 1, 2 and 3 the offset starts at + * 128. Please refer to "QSFP+ Memory Map" figure in SFF-8436 + * specification for graphical depiction. + * MCIA register accepts buffer size <= 48. Page of size 128 + * should be read by chunks of size 48, 48, 32. Align the size + * of the last chunk to avoid reading after the end of the + * page. + */ + if (offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) + size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset; } - mlxsw_reg_mcia_pack(mcia_pl, module, 0, 0, offset, size, i2c_addr); + mlxsw_reg_mcia_pack(mcia_pl, module, 0, page, offset, size, i2c_addr); err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcia), mcia_pl); if (err) @@ -168,7 +179,7 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, switch (module_id) { case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; break; case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */ case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: @@ -176,10 +187,10 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, module_rev_id >= MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8636) { modinfo->type = ETH_MODULE_SFF_8636; - modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN; } else { modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; } break; case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP: -- cgit v1.2.3-59-g8ed1b From 914c4fc1b792dd963f9606b2e8b33e3d6606eb84 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 23 Oct 2019 09:04:59 +0300 Subject: mlxsw: spectrum: Use guaranteed buffer size as pool size limit There are two resources associated with shared buffer size: cap_total_buffer_size, and cap_guaranteed_shared_buffer. So far, mlxsw has been using the former as a limit to determine how large a pool size is allowed to be. However, the total size also includes headrooms and reserved space, which really cannot be used for shared buffer pools. Therefore convert mlxsw to use the latter resource as a limit. Adjust hard-coded pool sizes to be the guaranteed size minus 256000 bytes for CPU port pool. On Spectrum-1 that actually leads to an increase. A follow-up patch will have this size calculated automatically. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/resources.h | 4 ++-- drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 15 ++++++++------- drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c | 3 ++- 3 files changed, 12 insertions(+), 10 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index 33a9fc9ef6a4..85f919fe851b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -26,7 +26,7 @@ enum mlxsw_res_id { MLXSW_RES_ID_MAX_LAG_MEMBERS, MLXSW_RES_ID_LOCAL_PORTS_IN_1X, MLXSW_RES_ID_LOCAL_PORTS_IN_2X, - MLXSW_RES_ID_MAX_BUFFER_SIZE, + MLXSW_RES_ID_GUARANTEED_SHARED_BUFFER, MLXSW_RES_ID_CELL_SIZE, MLXSW_RES_ID_MAX_HEADROOM_SIZE, MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS, @@ -82,7 +82,7 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521, [MLXSW_RES_ID_LOCAL_PORTS_IN_1X] = 0x2610, [MLXSW_RES_ID_LOCAL_PORTS_IN_2X] = 0x2611, - [MLXSW_RES_ID_MAX_BUFFER_SIZE] = 0x2802, /* Bytes */ + [MLXSW_RES_ID_GUARANTEED_SHARED_BUFFER] = 0x2805, /* Bytes */ [MLXSW_RES_ID_CELL_SIZE] = 0x2803, /* Bytes */ [MLXSW_RES_ID_MAX_HEADROOM_SIZE] = 0x2811, /* Bytes */ [MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS] = 0x2901, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index b9eeae37a4dc..637151682cf2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -421,8 +421,8 @@ static void mlxsw_sp_sb_ports_fini(struct mlxsw_sp *mlxsw_sp) .freeze_size = _freeze_size, \ } -#define MLXSW_SP1_SB_PR_INGRESS_SIZE 12440000 -#define MLXSW_SP1_SB_PR_EGRESS_SIZE 13232000 +#define MLXSW_SP1_SB_PR_INGRESS_SIZE 13768608 +#define MLXSW_SP1_SB_PR_EGRESS_SIZE 13768608 #define MLXSW_SP1_SB_PR_CPU_SIZE (256 * 1000) /* Order according to mlxsw_sp1_sb_pool_dess */ @@ -445,8 +445,8 @@ static const struct mlxsw_sp_sb_pr mlxsw_sp1_sb_prs[] = { MLXSW_SP1_SB_PR_CPU_SIZE, true, false), }; -#define MLXSW_SP2_SB_PR_INGRESS_SIZE 35297568 -#define MLXSW_SP2_SB_PR_EGRESS_SIZE 35297568 +#define MLXSW_SP2_SB_PR_INGRESS_SIZE 34084800 +#define MLXSW_SP2_SB_PR_EGRESS_SIZE 34084800 #define MLXSW_SP2_SB_PR_CPU_SIZE (256 * 1000) /* Order according to mlxsw_sp2_sb_pool_dess */ @@ -904,7 +904,7 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp) if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, CELL_SIZE)) return -EIO; - if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_BUFFER_SIZE)) + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, GUARANTEED_SHARED_BUFFER)) return -EIO; if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_HEADROOM_SIZE)) @@ -915,7 +915,7 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp) return -ENOMEM; mlxsw_sp->sb->cell_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, CELL_SIZE); mlxsw_sp->sb->sb_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, - MAX_BUFFER_SIZE); + GUARANTEED_SHARED_BUFFER); max_headroom_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_HEADROOM_SIZE); /* Round down, because this limit must not be overstepped. */ @@ -1013,7 +1013,8 @@ int mlxsw_sp_sb_pool_set(struct mlxsw_core *mlxsw_core, mode = (enum mlxsw_reg_sbpr_mode) threshold_type; pr = &mlxsw_sp->sb_vals->prs[pool_index]; - if (size > MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE)) { + if (size > MLXSW_CORE_RES_GET(mlxsw_sp->core, + GUARANTEED_SHARED_BUFFER)) { NL_SET_ERR_MSG_MOD(extack, "Exceeded shared buffer size"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index bdf53cf350f6..68cc6737d45c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -305,7 +305,8 @@ mlxsw_sp_qdisc_red_check_params(struct mlxsw_sp_port *mlxsw_sp_port, p->max); return -EINVAL; } - if (p->max > MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE)) { + if (p->max > MLXSW_CORE_RES_GET(mlxsw_sp->core, + GUARANTEED_SHARED_BUFFER)) { dev_err(mlxsw_sp->bus_info->dev, "spectrum: RED: max value %u is too big\n", p->max); return -EINVAL; -- cgit v1.2.3-59-g8ed1b From bc9f6e94bcb5652860c1b3bc82ca27697c496b4d Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 23 Oct 2019 09:05:00 +0300 Subject: mlxsw: spectrum_buffers: Calculate the size of the main pool Instead of hard-coding the size of the largest pool, calculate it from the reported guaranteed shared buffer size and sizes of other pools (currently only the CPU port pool). Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 46 ++++++++++++++++------ 1 file changed, 34 insertions(+), 12 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 637151682cf2..5fd9a72c8471 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -35,6 +35,7 @@ struct mlxsw_sp_sb_cm { }; #define MLXSW_SP_SB_INFI -1U +#define MLXSW_SP_SB_REST -2U struct mlxsw_sp_sb_pm { u32 min_buff; @@ -421,19 +422,16 @@ static void mlxsw_sp_sb_ports_fini(struct mlxsw_sp *mlxsw_sp) .freeze_size = _freeze_size, \ } -#define MLXSW_SP1_SB_PR_INGRESS_SIZE 13768608 -#define MLXSW_SP1_SB_PR_EGRESS_SIZE 13768608 #define MLXSW_SP1_SB_PR_CPU_SIZE (256 * 1000) /* Order according to mlxsw_sp1_sb_pool_dess */ static const struct mlxsw_sp_sb_pr mlxsw_sp1_sb_prs[] = { - MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, - MLXSW_SP1_SB_PR_INGRESS_SIZE), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_REST), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), - MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_DYNAMIC, - MLXSW_SP1_SB_PR_EGRESS_SIZE, true, false), + MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_REST, + true, false), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0), @@ -445,19 +443,16 @@ static const struct mlxsw_sp_sb_pr mlxsw_sp1_sb_prs[] = { MLXSW_SP1_SB_PR_CPU_SIZE, true, false), }; -#define MLXSW_SP2_SB_PR_INGRESS_SIZE 34084800 -#define MLXSW_SP2_SB_PR_EGRESS_SIZE 34084800 #define MLXSW_SP2_SB_PR_CPU_SIZE (256 * 1000) /* Order according to mlxsw_sp2_sb_pool_dess */ static const struct mlxsw_sp_sb_pr mlxsw_sp2_sb_prs[] = { - MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, - MLXSW_SP2_SB_PR_INGRESS_SIZE), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_REST), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), - MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_DYNAMIC, - MLXSW_SP2_SB_PR_EGRESS_SIZE, true, false), + MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_REST, + true, false), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), @@ -471,11 +466,33 @@ static const struct mlxsw_sp_sb_pr mlxsw_sp2_sb_prs[] = { static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_sb_pr *prs, + const struct mlxsw_sp_sb_pool_des *pool_dess, size_t prs_len) { + /* Round down, unlike mlxsw_sp_bytes_cells(). */ + u32 sb_cells = mlxsw_sp->sb->sb_size / mlxsw_sp->sb->cell_size; + u32 rest_cells[2] = {sb_cells, sb_cells}; int i; int err; + /* Calculate how much space to give to the "REST" pools in either + * direction. + */ + for (i = 0; i < prs_len; i++) { + enum mlxsw_reg_sbxx_dir dir = pool_dess[i].dir; + u32 size = prs[i].size; + u32 size_cells; + + if (size == MLXSW_SP_SB_INFI || size == MLXSW_SP_SB_REST) + continue; + + size_cells = mlxsw_sp_bytes_cells(mlxsw_sp, size); + if (WARN_ON_ONCE(size_cells > rest_cells[dir])) + continue; + + rest_cells[dir] -= size_cells; + } + for (i = 0; i < prs_len; i++) { u32 size = prs[i].size; u32 size_cells; @@ -483,6 +500,10 @@ static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp, if (size == MLXSW_SP_SB_INFI) { err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, prs[i].mode, 0, true); + } else if (size == MLXSW_SP_SB_REST) { + size_cells = rest_cells[pool_dess[i].dir]; + err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, prs[i].mode, + size_cells, false); } else { size_cells = mlxsw_sp_bytes_cells(mlxsw_sp, size); err = mlxsw_sp_sb_pr_write(mlxsw_sp, i, prs[i].mode, @@ -926,6 +947,7 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp) if (err) goto err_sb_ports_init; err = mlxsw_sp_sb_prs_init(mlxsw_sp, mlxsw_sp->sb_vals->prs, + mlxsw_sp->sb_vals->pool_dess, mlxsw_sp->sb_vals->pool_count); if (err) goto err_sb_prs_init; -- cgit v1.2.3-59-g8ed1b From c199ce4f9dd896c716aece33e6750be34aea1151 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 24 Oct 2019 17:22:01 +0200 Subject: net: Fix misspellings of "configure" and "configuration" Fix various misspellings of "configuration" and "configure". Signed-off-by: Geert Uytterhoeven Acked-by: Kalle Valo Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_int.h | 4 ++-- drivers/net/ethernet/qlogic/qed/qed_sriov.h | 2 +- drivers/net/ethernet/qlogic/qede/qede_filter.c | 2 +- drivers/net/wireless/ath/ath9k/ar9003_hw.c | 2 +- drivers/net/wireless/intel/iwlwifi/iwl-fh.h | 2 +- drivers/net/wireless/ti/wlcore/spi.c | 2 +- include/uapi/linux/dcbnl.h | 2 +- 8 files changed, 9 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 633b117eb13e..7b672ada63a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -175,7 +175,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, * @port_buffer: port receive buffer configuration * @change: * - * Update buffer configuration based on pfc configuraiton and + * Update buffer configuration based on pfc configuration and * priority to buffer mapping. * Buffer's lossy bit is changed to: * lossless if there is at least one PFC enabled priority diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index d473b522afc5..9ad568d93ae6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -37,14 +37,14 @@ #include #include "qed.h" -/* Fields of IGU PF CONFIGRATION REGISTER */ +/* Fields of IGU PF CONFIGURATION REGISTER */ #define IGU_PF_CONF_FUNC_EN (0x1 << 0) /* function enable */ #define IGU_PF_CONF_MSI_MSIX_EN (0x1 << 1) /* MSI/MSIX enable */ #define IGU_PF_CONF_INT_LINE_EN (0x1 << 2) /* INT enable */ #define IGU_PF_CONF_ATTN_BIT_EN (0x1 << 3) /* attention enable */ #define IGU_PF_CONF_SINGLE_ISR_EN (0x1 << 4) /* single ISR mode enable */ #define IGU_PF_CONF_SIMD_MODE (0x1 << 5) /* simd all ones mode */ -/* Fields of IGU VF CONFIGRATION REGISTER */ +/* Fields of IGU VF CONFIGURATION REGISTER */ #define IGU_VF_CONF_FUNC_EN (0x1 << 0) /* function enable */ #define IGU_VF_CONF_MSI_MSIX_EN (0x1 << 1) /* MSI/MSIX enable */ #define IGU_VF_CONF_SINGLE_ISR_EN (0x1 << 4) /* single ISR mode enable */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h index 9a8fd79611f2..368e88565783 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h @@ -305,7 +305,7 @@ void qed_iov_bulletin_set_udp_ports(struct qed_hwfn *p_hwfn, /** * @brief Read sriov related information and allocated resources - * reads from configuraiton space, shmem, etc. + * reads from configuration space, shmem, etc. * * @param p_hwfn * diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 9a6a9a008714..d6cfe4ffbaf3 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1298,7 +1298,7 @@ void qede_config_rx_mode(struct net_device *ndev) rx_mode.type = QED_FILTER_TYPE_RX_MODE; /* Remove all previous unicast secondary macs and multicast macs - * (configrue / leave the primary mac) + * (configure / leave the primary mac) */ rc = qede_set_ucast_rx_mac(edev, QED_FILTER_XCAST_TYPE_REPLACE, edev->ndev->dev_addr); diff --git a/drivers/net/wireless/ath/ath9k/ar9003_hw.c b/drivers/net/wireless/ath/ath9k/ar9003_hw.c index 2fe12b0de5b4..42f00a2a8c80 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_hw.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_hw.c @@ -1037,7 +1037,7 @@ static void ar9003_hw_configpcipowersave(struct ath_hw *ah, } /* - * Configire PCIE after Ini init. SERDES values now come from ini file + * Configure PCIE after Ini init. SERDES values now come from ini file * This enables PCIe low power mode. */ array = power_off ? &ah->iniPcieSerdes : diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h index 0c12df558240..05c1c77c88a0 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h @@ -148,7 +148,7 @@ static inline unsigned int FH_MEM_CBBC_QUEUE(struct iwl_trans *trans, * * Bits 3:0: * Define the maximum number of pending read requests. - * Maximum configration value allowed is 0xC + * Maximum configuration value allowed is 0xC * Bits 9:8: * Define the maximum transfer size. (64 / 128 / 256) * Bit 10: diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c index d4c09e54fd63..18c4d998ce4b 100644 --- a/drivers/net/wireless/ti/wlcore/spi.c +++ b/drivers/net/wireless/ti/wlcore/spi.c @@ -186,7 +186,7 @@ static void wl12xx_spi_init(struct device *child) spi_sync(to_spi_device(glue->dev), &m); - /* Restore chip select configration to normal */ + /* Restore chip select configuration to normal */ spi->mode ^= SPI_CS_HIGH; kfree(cmd); } diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index 69df19aa8e72..a791a94013a6 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -286,7 +286,7 @@ struct dcbmsg { * @DCB_CMD_GNUMTCS: get the number of traffic classes currently supported * @DCB_CMD_SNUMTCS: set the number of traffic classes * @DCB_CMD_GBCN: set backward congestion notification configuration - * @DCB_CMD_SBCN: get backward congestion notification configration. + * @DCB_CMD_SBCN: get backward congestion notification configuration. * @DCB_CMD_GAPP: get application protocol configuration * @DCB_CMD_SAPP: set application protocol configuration * @DCB_CMD_IEEE_SET: set IEEE 802.1Qaz configuration -- cgit v1.2.3-59-g8ed1b From acf5133b1d27edca6aee2a82cb2ffb2bc7c58468 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 25 Oct 2019 17:09:48 +0800 Subject: mlxsw: spectrum_buffers: remove unneeded semicolon Remove excess semicolon after closing parenthesis. Signed-off-by: YueHaibing Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 5fd9a72c8471..33a978af80d6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -1044,12 +1044,12 @@ int mlxsw_sp_sb_pool_set(struct mlxsw_core *mlxsw_core, if (pr->freeze_mode && pr->mode != mode) { NL_SET_ERR_MSG_MOD(extack, "Changing this pool's threshold type is forbidden"); return -EINVAL; - }; + } if (pr->freeze_size && pr->size != size) { NL_SET_ERR_MSG_MOD(extack, "Changing this pool's size is forbidden"); return -EINVAL; - }; + } return mlxsw_sp_sb_pr_write(mlxsw_sp, pool_index, mode, pool_size, false); -- cgit v1.2.3-59-g8ed1b From 5075066a77822edf416fa3001df1144ac6b848be Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 30 Oct 2019 11:34:48 +0200 Subject: mlxsw: reg: Increase size of MPAR register In new firmware versions this register is extended with a sampling rate for Spectrum-2 and future ASICs. Increase the size of the register to ensure the field is initialized to 0 which means every packet is mirrored. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index adb63a266fc7..7f7f1b95290f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -8680,7 +8680,7 @@ mlxsw_reg_mpat_eth_rspan_l3_ipv6_pack(char *payload, u8 ttl, * properties. */ #define MLXSW_REG_MPAR_ID 0x901B -#define MLXSW_REG_MPAR_LEN 0x08 +#define MLXSW_REG_MPAR_LEN 0x0C MLXSW_REG_DEFINE(mpar, MLXSW_REG_MPAR_ID, MLXSW_REG_MPAR_LEN); -- cgit v1.2.3-59-g8ed1b From ff298839b6737ccb512d0fe8c6bc241ee5a94c49 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 30 Oct 2019 11:34:49 +0200 Subject: mlxsw: pci: Increase PCI reset timeout for SN3800 systems SN3800 Spectrum-2 based systems have gearboxes that need to be initialized by the firmware during its initialization flow. In certain cases, the firmware might need to flash these gearboxes, which is currently a time-consuming process. In newer firmware versions, the firmware will not signal to the driver that it is ready until the gearboxes are flashed. Increase the PCI reset timeout for these situations. In normal cases, the driver will need to wait no longer than 5 seconds. Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/pci_hw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index 2b3aec482742..e0d7d2d9a0c8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -27,7 +27,7 @@ #define MLXSW_PCI_SW_RESET 0xF0010 #define MLXSW_PCI_SW_RESET_RST_BIT BIT(0) -#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 20000 +#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000 #define MLXSW_PCI_SW_RESET_WAIT_MSECS 100 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF -- cgit v1.2.3-59-g8ed1b From 5fd2ef46890625f79fe4650a47c2e86473845a5b Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 30 Oct 2019 11:34:50 +0200 Subject: mlxsw: Bump firmware version to 13.2000.2308 The version adds support for querying port module type. It will be used by a followup patch set from Jiri to make port split code more generic. Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 1275d21e8fbd..8a797fad2d56 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -48,7 +48,7 @@ #define MLXSW_SP1_FWREV_MAJOR 13 #define MLXSW_SP1_FWREV_MINOR 2000 -#define MLXSW_SP1_FWREV_SUBMINOR 1886 +#define MLXSW_SP1_FWREV_SUBMINOR 2308 #define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { -- cgit v1.2.3-59-g8ed1b From a72afb6879bb427143230bd0d892801c16b528ea Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 30 Oct 2019 11:34:51 +0200 Subject: mlxsw: Enforce firmware version for Spectrum-2 In a similar fashion to Spectrum-1, enforce a specific firmware version for Spectrum-2 so that the driver and firmware are always in sync with regards to new features. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 8a797fad2d56..97be4bc9a02f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -63,6 +63,21 @@ static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { "." __stringify(MLXSW_SP1_FWREV_MINOR) \ "." __stringify(MLXSW_SP1_FWREV_SUBMINOR) ".mfa2" +#define MLXSW_SP2_FWREV_MAJOR 29 +#define MLXSW_SP2_FWREV_MINOR 2000 +#define MLXSW_SP2_FWREV_SUBMINOR 2308 + +static const struct mlxsw_fw_rev mlxsw_sp2_fw_rev = { + .major = MLXSW_SP2_FWREV_MAJOR, + .minor = MLXSW_SP2_FWREV_MINOR, + .subminor = MLXSW_SP2_FWREV_SUBMINOR, +}; + +#define MLXSW_SP2_FW_FILENAME \ + "mellanox/mlxsw_spectrum2-" __stringify(MLXSW_SP2_FWREV_MAJOR) \ + "." __stringify(MLXSW_SP2_FWREV_MINOR) \ + "." __stringify(MLXSW_SP2_FWREV_SUBMINOR) ".mfa2" + static const char mlxsw_sp1_driver_name[] = "mlxsw_spectrum"; static const char mlxsw_sp2_driver_name[] = "mlxsw_spectrum2"; static const char mlxsw_sp3_driver_name[] = "mlxsw_spectrum3"; @@ -4988,6 +5003,8 @@ static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core, { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + mlxsw_sp->req_rev = &mlxsw_sp2_fw_rev; + mlxsw_sp->fw_filename = MLXSW_SP2_FW_FILENAME; mlxsw_sp->kvdl_ops = &mlxsw_sp2_kvdl_ops; mlxsw_sp->afa_ops = &mlxsw_sp2_act_afa_ops; mlxsw_sp->afk_ops = &mlxsw_sp2_afk_ops; @@ -6649,3 +6666,4 @@ MODULE_DEVICE_TABLE(pci, mlxsw_sp1_pci_id_table); MODULE_DEVICE_TABLE(pci, mlxsw_sp2_pci_id_table); MODULE_DEVICE_TABLE(pci, mlxsw_sp3_pci_id_table); MODULE_FIRMWARE(MLXSW_SP1_FW_FILENAME); +MODULE_FIRMWARE(MLXSW_SP2_FW_FILENAME); -- cgit v1.2.3-59-g8ed1b From 94e768373ae10d72528307256a869c846dc4ba00 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:06 +0200 Subject: mlxsw: reg: Extend PMLP tx/rx lane value size to 4 bits The tx/rx lane fields got extended to 4 bits, update the reg field description accordingly. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 7f7f1b95290f..7fd6fd9c5244 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -3969,6 +3969,7 @@ MLXSW_ITEM32(reg, pmlp, local_port, 0x00, 16, 8); * 1 - Lane 0 is used. * 2 - Lanes 0 and 1 are used. * 4 - Lanes 0, 1, 2 and 3 are used. + * 8 - Lanes 0-7 are used. * Access: RW */ MLXSW_ITEM32(reg, pmlp, width, 0x00, 0, 8); @@ -3983,14 +3984,14 @@ MLXSW_ITEM32_INDEXED(reg, pmlp, module, 0x04, 0, 8, 0x04, 0x00, false); * Tx Lane. When rxtx field is cleared, this field is used for Rx as well. * Access: RW */ -MLXSW_ITEM32_INDEXED(reg, pmlp, tx_lane, 0x04, 16, 2, 0x04, 0x00, false); +MLXSW_ITEM32_INDEXED(reg, pmlp, tx_lane, 0x04, 16, 4, 0x04, 0x00, false); /* reg_pmlp_rx_lane * Rx Lane. When rxtx field is cleared, this field is ignored and Rx lane is * equal to Tx lane. * Access: RW */ -MLXSW_ITEM32_INDEXED(reg, pmlp, rx_lane, 0x04, 24, 2, 0x04, 0x00, false); +MLXSW_ITEM32_INDEXED(reg, pmlp, rx_lane, 0x04, 24, 4, 0x04, 0x00, false); static inline void mlxsw_reg_pmlp_pack(char *payload, u8 local_port) { -- cgit v1.2.3-59-g8ed1b From a513b1a5910bfc15d5a42e969e66a7986fd32819 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:07 +0200 Subject: mlxsw: reg: Add Port Module Type Mapping Register The PMTM allows query or configuration of module types. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 50 +++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 7fd6fd9c5244..bec035ee5349 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5375,6 +5375,55 @@ static inline void mlxsw_reg_pplr_pack(char *payload, u8 local_port, MLXSW_REG_PPLR_LB_TYPE_BIT_PHY_LOCAL : 0); } +/* PMTM - Port Module Type Mapping Register + * ---------------------------------------- + * The PMTM allows query or configuration of module types. + */ +#define MLXSW_REG_PMTM_ID 0x5067 +#define MLXSW_REG_PMTM_LEN 0x10 + +MLXSW_REG_DEFINE(pmtm, MLXSW_REG_PMTM_ID, MLXSW_REG_PMTM_LEN); + +/* reg_pmtm_module + * Module number. + * Access: Index + */ +MLXSW_ITEM32(reg, pmtm, module, 0x00, 16, 8); + +enum mlxsw_reg_pmtm_module_type { + /* Backplane with 4 lanes */ + MLXSW_REG_PMTM_MODULE_TYPE_BP_4X, + /* QSFP */ + MLXSW_REG_PMTM_MODULE_TYPE_BP_QSFP, + /* SFP */ + MLXSW_REG_PMTM_MODULE_TYPE_BP_SFP, + /* Backplane with single lane */ + MLXSW_REG_PMTM_MODULE_TYPE_BP_1X = 4, + /* Backplane with two lane */ + MLXSW_REG_PMTM_MODULE_TYPE_BP_2X = 8, + /* Chip2Chip */ + MLXSW_REG_PMTM_MODULE_TYPE_C2C = 10, +}; + +/* reg_pmtm_module_type + * Module type. + * Access: RW + */ +MLXSW_ITEM32(reg, pmtm, module_type, 0x04, 0, 4); + +static inline void mlxsw_reg_pmtm_pack(char *payload, u8 module) +{ + MLXSW_REG_ZERO(pmtm, payload); + mlxsw_reg_pmtm_module_set(payload, module); +} + +static inline void +mlxsw_reg_pmtm_unpack(char *payload, + enum mlxsw_reg_pmtm_module_type *module_type) +{ + *module_type = mlxsw_reg_pmtm_module_type_get(payload); +} + /* HTGT - Host Trap Group Table * ---------------------------- * Configures the properties for forwarding to CPU. @@ -10545,6 +10594,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(pbmc), MLXSW_REG(pspa), MLXSW_REG(pplr), + MLXSW_REG(pmtm), MLXSW_REG(htgt), MLXSW_REG(hpkt), MLXSW_REG(rgcr), -- cgit v1.2.3-59-g8ed1b From 25911e1b97971a06b4c053f70c7c1eb0c33a607e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:08 +0200 Subject: mlxsw: spectrum: Use PMTM register to get max module width Currently the max module width is hard-coded according to ASIC type. That is not entirely correct, as the max module width might differ per-board. Use PMTM register to query FW for maximal width of a module. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 29 ++++++++++++++ drivers/net/ethernet/mellanox/mlxsw/core.h | 1 + drivers/net/ethernet/mellanox/mlxsw/port.h | 2 - drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 54 ++++++++++++++++++-------- 4 files changed, 67 insertions(+), 19 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 2b59f84b14f9..235d1990c127 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -2017,6 +2017,35 @@ mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_port_devlink_port_get); +int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module) +{ + enum mlxsw_reg_pmtm_module_type module_type; + char pmtm_pl[MLXSW_REG_PMTM_LEN]; + int err; + + mlxsw_reg_pmtm_pack(pmtm_pl, module); + err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(pmtm), pmtm_pl); + if (err) + return err; + mlxsw_reg_pmtm_unpack(pmtm_pl, &module_type); + + /* Here we need to get the module width according to the module type. */ + + switch (module_type) { + case MLXSW_REG_PMTM_MODULE_TYPE_BP_4X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_BP_QSFP: + return 4; + case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X: + return 2; + case MLXSW_REG_PMTM_MODULE_TYPE_BP_SFP: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X: + return 1; + default: + return -EINVAL; + } +} +EXPORT_SYMBOL(mlxsw_core_module_max_width); + static void mlxsw_core_buf_dump_dbg(struct mlxsw_core *mlxsw_core, const char *buf, size_t size) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index f25037074e2d..0d18bee6d140 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -200,6 +200,7 @@ enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core, struct devlink_port * mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, u8 local_port); +int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module); int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay); bool mlxsw_core_schedule_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h index a33eeef0b00c..741fd2989d12 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/port.h +++ b/drivers/net/ethernet/mellanox/mlxsw/port.h @@ -24,8 +24,6 @@ #define MLXSW_PORT_DONT_CARE 0xFF -#define MLXSW_PORT_MODULE_MAX_WIDTH 4 - enum mlxsw_port_admin_status { MLXSW_PORT_ADMIN_STATUS_UP = 1, MLXSW_PORT_ADMIN_STATUS_DOWN = 2, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 97be4bc9a02f..149b2cc2b4fd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4038,17 +4038,18 @@ err_port_to_module_alloc: return err; } -static u8 mlxsw_sp_cluster_base_port_get(u8 local_port) +static u8 mlxsw_sp_cluster_base_port_get(u8 local_port, unsigned int max_width) { - u8 offset = (local_port - 1) % MLXSW_SP_PORTS_PER_CLUSTER_MAX; + u8 offset = (local_port - 1) % max_width; return local_port - offset; } static int mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, - u8 module, unsigned int count, u8 offset) + u8 module, unsigned int count, u8 offset, + unsigned int max_width) { - u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count; + u8 width = max_width / count; int err, i; for (i = 0; i < count; i++) { @@ -4068,9 +4069,10 @@ err_port_create: } static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, - u8 base_port, unsigned int count) + u8 base_port, unsigned int count, + unsigned int max_width) { - u8 local_port, module, width = MLXSW_PORT_MODULE_MAX_WIDTH; + u8 local_port, module, width = max_width; int i; /* Split by four means we need to re-create two ports, otherwise @@ -4096,7 +4098,8 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); u8 local_ports_in_1x, local_ports_in_2x, offset; struct mlxsw_sp_port *mlxsw_sp_port; - u8 module, cur_width, base_port; + u8 module, base_port; + int max_width; int i; int err; @@ -4116,7 +4119,14 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, } module = mlxsw_sp_port->mapping.module; - cur_width = mlxsw_sp_port->mapping.width; + + max_width = mlxsw_core_module_max_width(mlxsw_core, + mlxsw_sp_port->mapping.module); + if (max_width < 0) { + netdev_err(mlxsw_sp_port->dev, "Cannot get max width of port module\n"); + NL_SET_ERR_MSG_MOD(extack, "Cannot get max width of port module"); + return max_width; + } if (count != 2 && count != 4) { netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n"); @@ -4124,7 +4134,8 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } - if (cur_width != MLXSW_PORT_MODULE_MAX_WIDTH) { + /* Split port with non-max module width cannot be split. */ + if (mlxsw_sp_port->mapping.width != max_width) { netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n"); NL_SET_ERR_MSG_MOD(extack, "Port cannot be split further"); return -EINVAL; @@ -4141,7 +4152,8 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, } } else { offset = local_ports_in_1x; - base_port = mlxsw_sp_cluster_base_port_get(local_port); + base_port = mlxsw_sp_cluster_base_port_get(local_port, + max_width); if (mlxsw_sp->ports[base_port + 1] || mlxsw_sp->ports[base_port + 3]) { netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n"); @@ -4155,7 +4167,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, module, count, - offset); + offset, max_width); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to create split ports\n"); goto err_port_split_create; @@ -4164,7 +4176,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return 0; err_port_split_create: - mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count); + mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count, max_width); return err; } @@ -4174,8 +4186,9 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); u8 local_ports_in_1x, local_ports_in_2x, offset; struct mlxsw_sp_port *mlxsw_sp_port; - u8 cur_width, base_port; unsigned int count; + int max_width; + u8 base_port; int i; if (!MLXSW_CORE_RES_VALID(mlxsw_core, LOCAL_PORTS_IN_1X) || @@ -4199,15 +4212,22 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } - cur_width = mlxsw_sp_port->mapping.width; - count = cur_width == 1 ? 4 : 2; + max_width = mlxsw_core_module_max_width(mlxsw_core, + mlxsw_sp_port->mapping.module); + if (max_width < 0) { + netdev_err(mlxsw_sp_port->dev, "Cannot get max width of port module\n"); + NL_SET_ERR_MSG_MOD(extack, "Cannot get max width of port module"); + return max_width; + } + + count = max_width / mlxsw_sp_port->mapping.width; if (count == 2) offset = local_ports_in_2x; else offset = local_ports_in_1x; - base_port = mlxsw_sp_cluster_base_port_get(local_port); + base_port = mlxsw_sp_cluster_base_port_get(local_port, max_width); /* Determine which ports to remove. */ if (count == 2 && local_port >= base_port + 2) @@ -4217,7 +4237,7 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); - mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count); + mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count, max_width); return 0; } -- cgit v1.2.3-59-g8ed1b From 2e6a2d7b4508ea01b276d8c7350582a07dca1c23 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:09 +0200 Subject: mlxsw: spectrum: Move max_width check up before count check The fact that the port cannot be split further should be checked before checking the count, so move it. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 149b2cc2b4fd..e0111e0a1a35 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4128,12 +4128,6 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return max_width; } - if (count != 2 && count != 4) { - netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n"); - NL_SET_ERR_MSG_MOD(extack, "Port can only be split into 2 or 4 ports"); - return -EINVAL; - } - /* Split port with non-max module width cannot be split. */ if (mlxsw_sp_port->mapping.width != max_width) { netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n"); @@ -4141,6 +4135,12 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } + if (count != 2 && count != 4) { + netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n"); + NL_SET_ERR_MSG_MOD(extack, "Port can only be split into 2 or 4 ports"); + return -EINVAL; + } + /* Make sure we have enough slave (even) ports for the split. */ if (count == 2) { offset = local_ports_in_2x; -- cgit v1.2.3-59-g8ed1b From 26a6befa5df79dddb1a1c464b5758de9d618ee23 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:10 +0200 Subject: mlxsw: spectrum: Distinguish between unsplittable and split port Currently when user does split, he is not able to distinguish if the port cannot be split because it is already split, or because it cannot be split at all. Add another check for split flag to distinguish this. Also add check forbidding split when maximal width is 1. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index e0111e0a1a35..3644fca096ac 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4118,6 +4118,13 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } + /* Split ports cannot be split. */ + if (mlxsw_sp_port->split) { + netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n"); + NL_SET_ERR_MSG_MOD(extack, "Port cannot be split further"); + return -EINVAL; + } + module = mlxsw_sp_port->mapping.module; max_width = mlxsw_core_module_max_width(mlxsw_core, @@ -4128,10 +4135,10 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return max_width; } - /* Split port with non-max module width cannot be split. */ - if (mlxsw_sp_port->mapping.width != max_width) { - netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n"); - NL_SET_ERR_MSG_MOD(extack, "Port cannot be split further"); + /* Split port with non-max and 1 module width cannot be split. */ + if (mlxsw_sp_port->mapping.width != max_width || max_width == 1) { + netdev_err(mlxsw_sp_port->dev, "Port cannot be split\n"); + NL_SET_ERR_MSG_MOD(extack, "Port cannot be split"); return -EINVAL; } -- cgit v1.2.3-59-g8ed1b From 4a7f970f1240523b1bbabac88811e429de4697cb Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:11 +0200 Subject: mlxsw: spectrum: Replace port_to_module array with array of structs Store the initial PMLP register configuration into array of structures instead of just simple array of module numbers. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 105 +++++++++++++++++-------- drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 18 +++-- 2 files changed, 84 insertions(+), 39 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3644fca096ac..ee15428ca740 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -748,9 +748,9 @@ mlxsw_sp_port_system_port_mapping_set(struct mlxsw_sp_port *mlxsw_sp_port) return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sspr), sspr_pl); } -static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp, - u8 local_port, u8 *p_module, - u8 *p_width, u8 *p_lane) +static int +mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp, u8 local_port, + struct mlxsw_sp_port_mapping *port_mapping) { char pmlp_pl[MLXSW_REG_PMLP_LEN]; int err; @@ -759,9 +759,9 @@ static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp, err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); if (err) return err; - *p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0); - *p_width = mlxsw_reg_pmlp_width_get(pmlp_pl); - *p_lane = mlxsw_reg_pmlp_tx_lane_get(pmlp_pl, 0); + port_mapping->module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0); + port_mapping->width = mlxsw_reg_pmlp_width_get(pmlp_pl); + port_mapping->lane = mlxsw_reg_pmlp_tx_lane_get(pmlp_pl, 0); return 0; } @@ -3979,14 +3979,13 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp) if (mlxsw_sp_port_created(mlxsw_sp, i)) mlxsw_sp_port_remove(mlxsw_sp, i); mlxsw_sp_cpu_port_remove(mlxsw_sp); - kfree(mlxsw_sp->port_to_module); kfree(mlxsw_sp->ports); } static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp) { unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); - u8 module, width, lane; + struct mlxsw_sp_port_mapping *port_mapping; size_t alloc_size; int i; int err; @@ -3996,48 +3995,78 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp) if (!mlxsw_sp->ports) return -ENOMEM; - mlxsw_sp->port_to_module = kmalloc_array(max_ports, sizeof(int), - GFP_KERNEL); - if (!mlxsw_sp->port_to_module) { - err = -ENOMEM; - goto err_port_to_module_alloc; - } - err = mlxsw_sp_cpu_port_create(mlxsw_sp); if (err) goto err_cpu_port_create; for (i = 1; i < max_ports; i++) { - /* Mark as invalid */ - mlxsw_sp->port_to_module[i] = -1; - - err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &module, - &width, &lane); - if (err) - goto err_port_module_info_get; - if (!width) + port_mapping = mlxsw_sp->port_mapping[i]; + if (!port_mapping) continue; - mlxsw_sp->port_to_module[i] = module; err = mlxsw_sp_port_create(mlxsw_sp, i, false, - module, width, lane); + port_mapping->module, + port_mapping->width, + port_mapping->lane); if (err) goto err_port_create; } return 0; err_port_create: -err_port_module_info_get: for (i--; i >= 1; i--) if (mlxsw_sp_port_created(mlxsw_sp, i)) mlxsw_sp_port_remove(mlxsw_sp, i); mlxsw_sp_cpu_port_remove(mlxsw_sp); err_cpu_port_create: - kfree(mlxsw_sp->port_to_module); -err_port_to_module_alloc: kfree(mlxsw_sp->ports); return err; } +static int mlxsw_sp_port_module_info_init(struct mlxsw_sp *mlxsw_sp) +{ + unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); + struct mlxsw_sp_port_mapping port_mapping; + int i; + int err; + + mlxsw_sp->port_mapping = kcalloc(max_ports, + sizeof(struct mlxsw_sp_port_mapping *), + GFP_KERNEL); + if (!mlxsw_sp->port_mapping) + return -ENOMEM; + + for (i = 1; i < max_ports; i++) { + err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &port_mapping); + if (err) + goto err_port_module_info_get; + if (!port_mapping.width) + continue; + + mlxsw_sp->port_mapping[i] = kmemdup(&port_mapping, + sizeof(port_mapping), + GFP_KERNEL); + if (!mlxsw_sp->port_mapping[i]) + goto err_port_module_info_dup; + } + return 0; + +err_port_module_info_get: +err_port_module_info_dup: + for (i--; i >= 1; i--) + kfree(mlxsw_sp->port_mapping[i]); + kfree(mlxsw_sp->port_mapping); + return err; +} + +static void mlxsw_sp_port_module_info_fini(struct mlxsw_sp *mlxsw_sp) +{ + int i; + + for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++) + kfree(mlxsw_sp->port_mapping[i]); + kfree(mlxsw_sp->port_mapping); +} + static u8 mlxsw_sp_cluster_base_port_get(u8 local_port, unsigned int max_width) { u8 offset = (local_port - 1) % max_width; @@ -4072,7 +4101,8 @@ static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, unsigned int count, unsigned int max_width) { - u8 local_port, module, width = max_width; + struct mlxsw_sp_port_mapping *port_mapping; + u8 local_port, width = max_width; int i; /* Split by four means we need to re-create two ports, otherwise @@ -4082,12 +4112,12 @@ static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < count; i++) { local_port = base_port + i * 2; - if (mlxsw_sp->port_to_module[local_port] < 0) + port_mapping = mlxsw_sp->port_mapping[local_port]; + if (!port_mapping) continue; - module = mlxsw_sp->port_to_module[local_port]; - mlxsw_sp_port_create(mlxsw_sp, local_port, false, module, - width, 0); + mlxsw_sp_port_create(mlxsw_sp, local_port, false, + port_mapping->module, width, 0); } } @@ -4951,6 +4981,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_dpipe_init; } + err = mlxsw_sp_port_module_info_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to init port module info\n"); + goto err_port_module_info_init; + } + err = mlxsw_sp_ports_create(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to create ports\n"); @@ -4960,6 +4996,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, return 0; err_ports_create: + mlxsw_sp_port_module_info_fini(mlxsw_sp); +err_port_module_info_init: mlxsw_sp_dpipe_fini(mlxsw_sp); err_dpipe_init: unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), @@ -5052,6 +5090,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); mlxsw_sp_ports_remove(mlxsw_sp); + mlxsw_sp_port_module_info_fini(mlxsw_sp); mlxsw_sp_dpipe_fini(mlxsw_sp); unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->netdevice_nb); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index a5fdd84b4ca7..3a823911a9d9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -143,6 +143,12 @@ struct mlxsw_sp_port_type_speed_ops; struct mlxsw_sp_ptp_state; struct mlxsw_sp_ptp_ops; +struct mlxsw_sp_port_mapping { + u8 module; + u8 width; + u8 lane; +}; + struct mlxsw_sp { struct mlxsw_sp_port **ports; struct mlxsw_core *core; @@ -150,7 +156,7 @@ struct mlxsw_sp { unsigned char base_mac[ETH_ALEN]; const unsigned char *mac_mask; struct mlxsw_sp_upper *lags; - int *port_to_module; + struct mlxsw_sp_port_mapping **port_mapping; struct mlxsw_sp_sb *sb; struct mlxsw_sp_bridge *bridge; struct mlxsw_sp_router *router; @@ -259,11 +265,11 @@ struct mlxsw_sp_port { struct ieee_pfc *pfc; enum mlxsw_reg_qpts_trust_state trust_state; } dcb; - struct { - u8 module; - u8 width; - u8 lane; - } mapping; + struct mlxsw_sp_port_mapping mapping; /* mapping is constant during the + * mlxsw_sp_port lifetime, however + * the same localport can have + * different mapping. + */ /* TC handles */ struct list_head mall_tc_list; struct { -- cgit v1.2.3-59-g8ed1b From 7b39fa5befbb531a91bbd91ecac516251063afe3 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:12 +0200 Subject: mlxsw: spectrum: Use mapping of port being split for creating split ports Don't use constant max width value and instead of that, use the actual width of the port. Also don't pass module value and use the value stored in the same structure. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index ee15428ca740..2145975af103 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4074,16 +4074,18 @@ static u8 mlxsw_sp_cluster_base_port_get(u8 local_port, unsigned int max_width) return local_port - offset; } -static int mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, - u8 module, unsigned int count, u8 offset, - unsigned int max_width) +static int +mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, + struct mlxsw_sp_port_mapping *port_mapping, + unsigned int count, u8 offset) { - u8 width = max_width / count; + u8 width = port_mapping->width / count; int err, i; for (i = 0; i < count; i++) { err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * offset, - true, module, width, i * width); + true, port_mapping->module, + width, i * width); if (err) goto err_port_create; } @@ -4127,9 +4129,10 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); u8 local_ports_in_1x, local_ports_in_2x, offset; + struct mlxsw_sp_port_mapping port_mapping; struct mlxsw_sp_port *mlxsw_sp_port; - u8 module, base_port; int max_width; + u8 base_port; int i; int err; @@ -4155,8 +4158,6 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } - module = mlxsw_sp_port->mapping.module; - max_width = mlxsw_core_module_max_width(mlxsw_core, mlxsw_sp_port->mapping.module); if (max_width < 0) { @@ -4199,12 +4200,14 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, } } + port_mapping = mlxsw_sp_port->mapping; + for (i = 0; i < count; i++) if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); - err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, module, count, - offset, max_width); + err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, &port_mapping, + count, offset); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to create split ports\n"); goto err_port_split_create; -- cgit v1.2.3-59-g8ed1b From 35896d9641db1af0d6054b03ec3e13f6be83c6b8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:13 +0200 Subject: mlxsw: spectrum: Pass mapping values in port mapping structure Pass the port mapping structure down to create, module_map and other function instead of individual values. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 56 ++++++++++++-------------- 1 file changed, 26 insertions(+), 30 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 2145975af103..68f1461d9919 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -765,18 +765,18 @@ mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp, u8 local_port, return 0; } -static int mlxsw_sp_port_module_map(struct mlxsw_sp_port *mlxsw_sp_port, - u8 module, u8 width, u8 lane) +static int mlxsw_sp_port_module_map(struct mlxsw_sp_port *mlxsw_sp_port) { + struct mlxsw_sp_port_mapping *port_mapping = &mlxsw_sp_port->mapping; struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char pmlp_pl[MLXSW_REG_PMLP_LEN]; int i; mlxsw_reg_pmlp_pack(pmlp_pl, mlxsw_sp_port->local_port); - mlxsw_reg_pmlp_width_set(pmlp_pl, width); - for (i = 0; i < width; i++) { - mlxsw_reg_pmlp_module_set(pmlp_pl, i, module); - mlxsw_reg_pmlp_tx_lane_set(pmlp_pl, i, lane + i); /* Rx & Tx */ + mlxsw_reg_pmlp_width_set(pmlp_pl, port_mapping->width); + for (i = 0; i < port_mapping->width; i++) { + mlxsw_reg_pmlp_module_set(pmlp_pl, i, port_mapping->module); + mlxsw_reg_pmlp_tx_lane_set(pmlp_pl, i, port_mapping->lane + i); /* Rx & Tx */ } return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); @@ -3480,7 +3480,7 @@ static const struct ethtool_ops mlxsw_sp_port_ethtool_ops = { }; static int -mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 width) +mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; const struct mlxsw_sp_port_type_speed_ops *ops; @@ -3496,7 +3496,7 @@ mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 width) &base_speed); if (err) return err; - upper_speed = base_speed * width; + upper_speed = base_speed * mlxsw_sp_port->mapping.width; eth_proto_admin = ops->to_ptys_upper_speed(mlxsw_sp, upper_speed); ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port, @@ -3657,7 +3657,8 @@ static int mlxsw_sp_port_tc_mc_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, } static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, - bool split, u8 module, u8 width, u8 lane) + bool split, + struct mlxsw_sp_port_mapping *port_mapping) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; struct mlxsw_sp_port *mlxsw_sp_port; @@ -3665,7 +3666,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, int err; err = mlxsw_core_port_init(mlxsw_sp->core, local_port, - module + 1, split, lane / width, + port_mapping->module + 1, split, + port_mapping->lane / port_mapping->width, mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac)); if (err) { @@ -3687,9 +3689,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, mlxsw_sp_port->local_port = local_port; mlxsw_sp_port->pvid = MLXSW_SP_DEFAULT_VID; mlxsw_sp_port->split = split; - mlxsw_sp_port->mapping.module = module; - mlxsw_sp_port->mapping.width = width; - mlxsw_sp_port->mapping.lane = lane; + mlxsw_sp_port->mapping = *port_mapping; mlxsw_sp_port->link.autoneg = 1; INIT_LIST_HEAD(&mlxsw_sp_port->vlans_list); INIT_LIST_HEAD(&mlxsw_sp_port->mall_tc_list); @@ -3714,7 +3714,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, dev->netdev_ops = &mlxsw_sp_port_netdev_ops; dev->ethtool_ops = &mlxsw_sp_port_ethtool_ops; - err = mlxsw_sp_port_module_map(mlxsw_sp_port, module, width, lane); + err = mlxsw_sp_port_module_map(mlxsw_sp_port); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to map module\n", mlxsw_sp_port->local_port); @@ -3756,7 +3756,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, goto err_port_system_port_mapping_set; } - err = mlxsw_sp_port_speed_by_width_set(mlxsw_sp_port, width); + err = mlxsw_sp_port_speed_by_width_set(mlxsw_sp_port); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to enable speeds\n", mlxsw_sp_port->local_port); @@ -4003,10 +4003,7 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp) port_mapping = mlxsw_sp->port_mapping[i]; if (!port_mapping) continue; - err = mlxsw_sp_port_create(mlxsw_sp, i, false, - port_mapping->module, - port_mapping->width, - port_mapping->lane); + err = mlxsw_sp_port_create(mlxsw_sp, i, false, port_mapping); if (err) goto err_port_create; } @@ -4079,15 +4076,17 @@ mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, struct mlxsw_sp_port_mapping *port_mapping, unsigned int count, u8 offset) { - u8 width = port_mapping->width / count; + struct mlxsw_sp_port_mapping split_port_mapping; int err, i; + split_port_mapping = *port_mapping; + split_port_mapping.width /= count; for (i = 0; i < count; i++) { err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * offset, - true, port_mapping->module, - width, i * width); + true, &split_port_mapping); if (err) goto err_port_create; + split_port_mapping.lane += split_port_mapping.width; } return 0; @@ -4100,11 +4099,10 @@ err_port_create: } static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, - u8 base_port, unsigned int count, - unsigned int max_width) + u8 base_port, unsigned int count) { struct mlxsw_sp_port_mapping *port_mapping; - u8 local_port, width = max_width; + u8 local_port; int i; /* Split by four means we need to re-create two ports, otherwise @@ -4117,9 +4115,7 @@ static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, port_mapping = mlxsw_sp->port_mapping[local_port]; if (!port_mapping) continue; - - mlxsw_sp_port_create(mlxsw_sp, local_port, false, - port_mapping->module, width, 0); + mlxsw_sp_port_create(mlxsw_sp, local_port, false, port_mapping); } } @@ -4216,7 +4212,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return 0; err_port_split_create: - mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count, max_width); + mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count); return err; } @@ -4277,7 +4273,7 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); - mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count, max_width); + mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count); return 0; } -- cgit v1.2.3-59-g8ed1b From c8fc10dc17c2675212982934d6de7fb19aabe73c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:14 +0200 Subject: mlxsw: spectrum: Add sanity checks into module info get Driver assumes certain values in the PMLP register. Add checks that verify that PMLP register provides fitting values. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 39 ++++++++++++++++++++++++-- 1 file changed, 37 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 68f1461d9919..938803cd29ca 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -753,14 +754,48 @@ mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp, u8 local_port, struct mlxsw_sp_port_mapping *port_mapping) { char pmlp_pl[MLXSW_REG_PMLP_LEN]; + bool separate_rxtx; + u8 module; + u8 width; int err; + int i; mlxsw_reg_pmlp_pack(pmlp_pl, local_port); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); if (err) return err; - port_mapping->module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0); - port_mapping->width = mlxsw_reg_pmlp_width_get(pmlp_pl); + module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0); + width = mlxsw_reg_pmlp_width_get(pmlp_pl); + separate_rxtx = mlxsw_reg_pmlp_rxtx_get(pmlp_pl); + + if (width && !is_power_of_2(width)) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Unsupported module config: width value is not power of 2\n", + local_port); + return -EINVAL; + } + + for (i = 0; i < width; i++) { + if (mlxsw_reg_pmlp_module_get(pmlp_pl, i) != module) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Unsupported module config: contains multiple modules\n", + local_port); + return -EINVAL; + } + if (separate_rxtx && + mlxsw_reg_pmlp_tx_lane_get(pmlp_pl, i) != + mlxsw_reg_pmlp_rx_lane_get(pmlp_pl, i)) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Unsupported module config: TX and RX lane numbers are different\n", + local_port); + return -EINVAL; + } + if (mlxsw_reg_pmlp_tx_lane_get(pmlp_pl, i) != i) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Unsupported module config: TX and RX lane numbers are not sequential\n", + local_port); + return -EINVAL; + } + } + + port_mapping->module = module; + port_mapping->width = width; port_mapping->lane = mlxsw_reg_pmlp_tx_lane_get(pmlp_pl, 0); return 0; } -- cgit v1.2.3-59-g8ed1b From d0846ce9aa9096e53e532a1c36c57efe63509b26 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:15 +0200 Subject: mlxsw: spectrum: Push getting offsets of split ports into a helper Get local port offsets of split port in a separate helper function and use it in both split and unsplit function. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 58 ++++++++++++++++---------- 1 file changed, 35 insertions(+), 23 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 938803cd29ca..39ea408deec1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4154,26 +4154,38 @@ static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, } } +static int mlxsw_sp_local_ports_offset(struct mlxsw_core *mlxsw_core, + unsigned int count, + unsigned int max_width) +{ + enum mlxsw_res_id local_ports_in_x_res_id; + int split_width = max_width / count; + + if (split_width == 1) + local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_1X; + else if (split_width == 2) + local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_2X; + else + return -EINVAL; + + if (!mlxsw_core_res_valid(mlxsw_core, local_ports_in_x_res_id)) + return -EINVAL; + return mlxsw_core_res_get(mlxsw_core, local_ports_in_x_res_id); +} + static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, unsigned int count, struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - u8 local_ports_in_1x, local_ports_in_2x, offset; struct mlxsw_sp_port_mapping port_mapping; struct mlxsw_sp_port *mlxsw_sp_port; int max_width; u8 base_port; + int offset; int i; int err; - if (!MLXSW_CORE_RES_VALID(mlxsw_core, LOCAL_PORTS_IN_1X) || - !MLXSW_CORE_RES_VALID(mlxsw_core, LOCAL_PORTS_IN_2X)) - return -EIO; - - local_ports_in_1x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_1X); - local_ports_in_2x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_2X); - mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) { dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n", @@ -4210,17 +4222,22 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } + offset = mlxsw_sp_local_ports_offset(mlxsw_core, count, max_width); + if (offset < 0) { + netdev_err(mlxsw_sp_port->dev, "Cannot obtain local port offset\n"); + NL_SET_ERR_MSG_MOD(extack, "Cannot obtain local port offset"); + return -EINVAL; + } + /* Make sure we have enough slave (even) ports for the split. */ if (count == 2) { - offset = local_ports_in_2x; base_port = local_port; - if (mlxsw_sp->ports[base_port + local_ports_in_2x]) { + if (mlxsw_sp->ports[base_port + offset]) { netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n"); NL_SET_ERR_MSG_MOD(extack, "Invalid split configuration"); return -EINVAL; } } else { - offset = local_ports_in_1x; base_port = mlxsw_sp_cluster_base_port_get(local_port, max_width); if (mlxsw_sp->ports[base_port + 1] || @@ -4255,20 +4272,13 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - u8 local_ports_in_1x, local_ports_in_2x, offset; struct mlxsw_sp_port *mlxsw_sp_port; unsigned int count; int max_width; u8 base_port; + int offset; int i; - if (!MLXSW_CORE_RES_VALID(mlxsw_core, LOCAL_PORTS_IN_1X) || - !MLXSW_CORE_RES_VALID(mlxsw_core, LOCAL_PORTS_IN_2X)) - return -EIO; - - local_ports_in_1x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_1X); - local_ports_in_2x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_2X); - mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) { dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n", @@ -4293,10 +4303,12 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, count = max_width / mlxsw_sp_port->mapping.width; - if (count == 2) - offset = local_ports_in_2x; - else - offset = local_ports_in_1x; + offset = mlxsw_sp_local_ports_offset(mlxsw_core, count, max_width); + if (WARN_ON(offset < 0)) { + netdev_err(mlxsw_sp_port->dev, "Cannot obtain local port offset\n"); + NL_SET_ERR_MSG_MOD(extack, "Cannot obtain local port offset"); + return -EINVAL; + } base_port = mlxsw_sp_cluster_base_port_get(local_port, max_width); -- cgit v1.2.3-59-g8ed1b From 038784a9dfc2180dde36d34a92cb4427eb1e928f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:16 +0200 Subject: mlxsw: spectrum: Introduce resource for getting offset of 4 lanes split port In Spectrum-3 the modules have 8 lanes, so split by count 2 results in two split ports each of 4 lanes. Add a resource that can be used to obtain local port offset in that case. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/resources.h | 2 ++ drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index 85f919fe851b..6534184cb942 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -26,6 +26,7 @@ enum mlxsw_res_id { MLXSW_RES_ID_MAX_LAG_MEMBERS, MLXSW_RES_ID_LOCAL_PORTS_IN_1X, MLXSW_RES_ID_LOCAL_PORTS_IN_2X, + MLXSW_RES_ID_LOCAL_PORTS_IN_4X, MLXSW_RES_ID_GUARANTEED_SHARED_BUFFER, MLXSW_RES_ID_CELL_SIZE, MLXSW_RES_ID_MAX_HEADROOM_SIZE, @@ -82,6 +83,7 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521, [MLXSW_RES_ID_LOCAL_PORTS_IN_1X] = 0x2610, [MLXSW_RES_ID_LOCAL_PORTS_IN_2X] = 0x2611, + [MLXSW_RES_ID_LOCAL_PORTS_IN_4X] = 0x2612, [MLXSW_RES_ID_GUARANTEED_SHARED_BUFFER] = 0x2805, /* Bytes */ [MLXSW_RES_ID_CELL_SIZE] = 0x2803, /* Bytes */ [MLXSW_RES_ID_MAX_HEADROOM_SIZE] = 0x2811, /* Bytes */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 39ea408deec1..d336e54d7a76 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4165,6 +4165,8 @@ static int mlxsw_sp_local_ports_offset(struct mlxsw_core *mlxsw_core, local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_1X; else if (split_width == 2) local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_2X; + else if (split_width == 4) + local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_4X; else return -EINVAL; -- cgit v1.2.3-59-g8ed1b From 49185277cc451ebae894456384cc8996e8ec4fdc Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:17 +0200 Subject: mlxsw: spectrum: Remember split base local port and use it in unsplit Don't compute the original base local port during unsplit, rather remember it in mlxsw_sp_port structure during split port creation. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 16 +++++++--------- drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 1 + 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index d336e54d7a76..db05118adc44 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3692,10 +3692,11 @@ static int mlxsw_sp_port_tc_mc_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, } static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, - bool split, + u8 split_base_local_port, struct mlxsw_sp_port_mapping *port_mapping) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; + bool split = !!split_base_local_port; struct mlxsw_sp_port *mlxsw_sp_port; struct net_device *dev; int err; @@ -3724,6 +3725,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, mlxsw_sp_port->local_port = local_port; mlxsw_sp_port->pvid = MLXSW_SP_DEFAULT_VID; mlxsw_sp_port->split = split; + mlxsw_sp_port->split_base_local_port = split_base_local_port; mlxsw_sp_port->mapping = *port_mapping; mlxsw_sp_port->link.autoneg = 1; INIT_LIST_HEAD(&mlxsw_sp_port->vlans_list); @@ -4038,7 +4040,7 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp) port_mapping = mlxsw_sp->port_mapping[i]; if (!port_mapping) continue; - err = mlxsw_sp_port_create(mlxsw_sp, i, false, port_mapping); + err = mlxsw_sp_port_create(mlxsw_sp, i, 0, port_mapping); if (err) goto err_port_create; } @@ -4118,7 +4120,7 @@ mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, split_port_mapping.width /= count; for (i = 0; i < count; i++) { err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * offset, - true, &split_port_mapping); + base_port, &split_port_mapping); if (err) goto err_port_create; split_port_mapping.lane += split_port_mapping.width; @@ -4150,7 +4152,7 @@ static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, port_mapping = mlxsw_sp->port_mapping[local_port]; if (!port_mapping) continue; - mlxsw_sp_port_create(mlxsw_sp, local_port, false, port_mapping); + mlxsw_sp_port_create(mlxsw_sp, local_port, 0, port_mapping); } } @@ -4312,11 +4314,7 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } - base_port = mlxsw_sp_cluster_base_port_get(local_port, max_width); - - /* Determine which ports to remove. */ - if (count == 2 && local_port >= base_port + 2) - base_port = base_port + 2; + base_port = mlxsw_sp_port->split_base_local_port; for (i = 0; i < count; i++) if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 3a823911a9d9..ec6c9756791d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -293,6 +293,7 @@ struct mlxsw_sp_port { u16 egr_types; struct mlxsw_sp_ptp_port_stats stats; } ptp; + u8 split_base_local_port; }; struct mlxsw_sp_port_type_speed_ops { -- cgit v1.2.3-59-g8ed1b From 013da297911830882611c4ae4764117dacf6713f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:18 +0200 Subject: mlxsw: spectrum: Use port_module_max_width to compute base port index Instead of using constant value, use port_module_max_width which is aligned with the cluster size. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index ec6c9756791d..347bec9d1ecf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -32,8 +32,6 @@ #define MLXSW_SP_MID_MAX 7000 -#define MLXSW_SP_PORTS_PER_CLUSTER_MAX 4 - #define MLXSW_SP_PORT_BASE_SPEED_25G 25000 /* Mb/s */ #define MLXSW_SP_PORT_BASE_SPEED_50G 50000 /* Mb/s */ -- cgit v1.2.3-59-g8ed1b From c3a64b5173e1416cf3d982b02e1c1b918382f701 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:19 +0200 Subject: mlxsw: spectrum: Fix base port get for split count 4 and 8 The current code considers only split by 2 or 4. Make the base port getting generic and allow split by 8 to be handled correctly. Generalize the used port checks as well. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 28 ++++++++++++++------------ 1 file changed, 15 insertions(+), 13 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index db05118adc44..0a5a4a252248 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4233,19 +4233,21 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } - /* Make sure we have enough slave (even) ports for the split. */ - if (count == 2) { - base_port = local_port; - if (mlxsw_sp->ports[base_port + offset]) { - netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n"); - NL_SET_ERR_MSG_MOD(extack, "Invalid split configuration"); - return -EINVAL; - } - } else { - base_port = mlxsw_sp_cluster_base_port_get(local_port, - max_width); - if (mlxsw_sp->ports[base_port + 1] || - mlxsw_sp->ports[base_port + 3]) { + /* Only in case max split is being done, the local port and + * base port may differ. + */ + base_port = count == max_width ? + mlxsw_sp_cluster_base_port_get(local_port, max_width) : + local_port; + + for (i = 0; i < count * offset; i++) { + /* Expect base port to exist and also the one in the middle in + * case of maximal split count. + */ + if (i == 0 || (count == max_width && i == count / 2)) + continue; + + if (mlxsw_sp_port_created(mlxsw_sp, base_port + i)) { netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n"); NL_SET_ERR_MSG_MOD(extack, "Invalid split configuration"); return -EINVAL; -- cgit v1.2.3-59-g8ed1b From fbbeea31026767706f0644f14c3cf13cbc2fa3c8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:20 +0200 Subject: mlxsw: spectrum: Iterate over all ports in gap during unsplit create During recreation of original unsplit ports, just simply iterate over the whole gap and recreate whatever originally existed. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 0a5a4a252248..3ce48d0df37f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4136,23 +4136,18 @@ err_port_create: } static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, - u8 base_port, unsigned int count) + u8 base_port, + unsigned int count, u8 offset) { struct mlxsw_sp_port_mapping *port_mapping; - u8 local_port; int i; - /* Split by four means we need to re-create two ports, otherwise - * only one. - */ - count = count / 2; - - for (i = 0; i < count; i++) { - local_port = base_port + i * 2; - port_mapping = mlxsw_sp->port_mapping[local_port]; + /* Go over original unsplit ports in the gap and recreate them. */ + for (i = 0; i < count * offset; i++) { + port_mapping = mlxsw_sp->port_mapping[base_port + i]; if (!port_mapping) continue; - mlxsw_sp_port_create(mlxsw_sp, local_port, 0, port_mapping); + mlxsw_sp_port_create(mlxsw_sp, base_port + i, 0, port_mapping); } } @@ -4270,7 +4265,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return 0; err_port_split_create: - mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count); + mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count, offset); return err; } @@ -4322,7 +4317,7 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); - mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count); + mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count, offset); return 0; } -- cgit v1.2.3-59-g8ed1b From 973b7fdb5ff17e5f19eba9103c3fcb77a01b93df Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 31 Oct 2019 11:42:21 +0200 Subject: mlxsw: spectrum: Generalize split count check Make the check generic for any possible value, not only 2 and 4. Signed-off-by: Jiri Pirko Reviewed-by: Shalom Toledo Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3ce48d0df37f..ea4cc2aa99e0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4215,9 +4215,9 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } - if (count != 2 && count != 4) { - netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n"); - NL_SET_ERR_MSG_MOD(extack, "Port can only be split into 2 or 4 ports"); + if (count == 1 || !is_power_of_2(count) || count > max_width) { + netdev_err(mlxsw_sp_port->dev, "Invalid split count\n"); + NL_SET_ERR_MSG_MOD(extack, "Invalid split count"); return -EINVAL; } -- cgit v1.2.3-59-g8ed1b From d170eb69d40e9e5fccb8d57edbbacb97427dcf1c Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 30 Oct 2019 09:01:52 -0700 Subject: mlxsw: Fix 64-bit division in mlxsw_sp_sb_prs_init When building for 32-bit ARM, there is a link time error because of a 64-bit division: ld.lld: error: undefined symbol: __aeabi_uldivmod >>> referenced by spectrum_buffers.c >>> net/ethernet/mellanox/mlxsw/spectrum_buffers.o:(mlxsw_sp_buffers_init) in archive drivers/built-in.a >>> did you mean: __aeabi_uidivmod >>> defined in: arch/arm/lib/lib.a(lib1funcs.o Avoid this by using div_u64, which is designed to avoid this problem. Fixes: bc9f6e94bcb5 ("mlxsw: spectrum_buffers: Calculate the size of the main pool") Signed-off-by: Nathan Chancellor Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 33a978af80d6..968f0902e4fe 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -470,7 +470,7 @@ static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp, size_t prs_len) { /* Round down, unlike mlxsw_sp_bytes_cells(). */ - u32 sb_cells = mlxsw_sp->sb->sb_size / mlxsw_sp->sb->cell_size; + u32 sb_cells = div_u64(mlxsw_sp->sb->sb_size, mlxsw_sp->sb->cell_size); u32 rest_cells[2] = {sb_cells, sb_cells}; int i; int err; -- cgit v1.2.3-59-g8ed1b From e019cb536d046ea1c7ba5d370845ea362610b348 Mon Sep 17 00:00:00 2001 From: Qing Huang Date: Mon, 28 Oct 2019 23:34:56 +0000 Subject: net/mlx5: Fixed a typo in a comment in esw_del_uc_addr() Changed "managerss" to "managers". Fixes: a1b3839ac4a4 ("net/mlx5: E-Switch, Properly refer to the esw manager vport") Signed-off-by: Qing Huang Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 30aae76b6a1d..4c18ac1299ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -530,7 +530,7 @@ static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) u16 vport = vaddr->vport; int err = 0; - /* Skip mlx5_mpfs_del_mac for eswitch managerss, + /* Skip mlx5_mpfs_del_mac for eswitch managers, * it is already done by its netdev in mlx5e_execute_l2_action */ if (!vaddr->mpfs || esw->manager_vport == vport) -- cgit v1.2.3-59-g8ed1b From 6d94e610e4b6a77007d50952d3c859d3e300c0ab Mon Sep 17 00:00:00 2001 From: Vu Pham Date: Mon, 28 Oct 2019 23:34:58 +0000 Subject: net/mlx5: E-Switch, Rename egress config to generic name Refactor vport egress config in offloads mode Refactoring vport egress configuration in offloads mode that includes egress prio tag configuration. This makes code symmetric to ingress configuration. Signed-off-by: Vu Pham Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 50 +++++++++++----------- 1 file changed, 26 insertions(+), 24 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 00d71db15f22..506cea8181f9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1864,32 +1864,16 @@ static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec; int err = 0; - if (!MLX5_CAP_GEN(esw->dev, prio_tag_required)) - return 0; - /* For prio tag mode, there is only 1 FTEs: * 1) prio tag packets - pop the prio tag VLAN, allow * Unmatched traffic is allowed by default */ - - esw_vport_cleanup_egress_rules(esw, vport); - - err = esw_vport_enable_egress_acl(esw, vport); - if (err) { - mlx5_core_warn(esw->dev, - "failed to enable egress acl (%d) on vport[%d]\n", - err, vport->vport); - return err; - } - esw_debug(esw->dev, "vport[%d] configure prio tag egress rules\n", vport->vport); spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) { - err = -ENOMEM; - goto out_no_mem; - } + if (!spec) + return -ENOMEM; /* prio tag vlan rule - pop it so VF receives untagged packets */ MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag); @@ -1909,14 +1893,9 @@ static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw, "vport[%d] configure egress pop prio tag vlan rule failed, err(%d)\n", vport->vport, err); vport->egress.allowed_vlan = NULL; - goto out; } -out: kvfree(spec); -out_no_mem: - if (err) - esw_vport_cleanup_egress_rules(esw, vport); return err; } @@ -1961,6 +1940,29 @@ out: return err; } +static int esw_vport_egress_config(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + int err; + + if (!MLX5_CAP_GEN(esw->dev, prio_tag_required)) + return 0; + + esw_vport_cleanup_egress_rules(esw, vport); + + err = esw_vport_enable_egress_acl(esw, vport); + if (err) + return err; + + esw_debug(esw->dev, "vport(%d) configure egress rules\n", vport->vport); + + err = esw_vport_egress_prio_tag_config(esw, vport); + if (err) + esw_vport_disable_egress_acl(esw, vport); + + return err; +} + static bool esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw) { @@ -1996,7 +1998,7 @@ static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw) goto err_ingress; if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) { - err = esw_vport_egress_prio_tag_config(esw, vport); + err = esw_vport_egress_config(esw, vport); if (err) goto err_egress; } -- cgit v1.2.3-59-g8ed1b From b1a3380aa709082761c1dba89234ac16c19037c6 Mon Sep 17 00:00:00 2001 From: Vu Pham Date: Mon, 28 Oct 2019 23:35:00 +0000 Subject: net/mlx5: E-Switch, Rename ingress acl config in offloads mode Changing the function name esw_ingress_acl_common_config() to esw_ingress_acl_config() to be consistent with egress config function naming in offloads mode. Signed-off-by: Vu Pham Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 506cea8181f9..48adec168a7c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1899,8 +1899,8 @@ static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw, return err; } -static int esw_vport_ingress_common_config(struct mlx5_eswitch *esw, - struct mlx5_vport *vport) +static int esw_vport_ingress_config(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) { int err; @@ -1993,7 +1993,7 @@ static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw) esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA; mlx5_esw_for_all_vports(esw, i, vport) { - err = esw_vport_ingress_common_config(esw, vport); + err = esw_vport_ingress_config(esw, vport); if (err) goto err_ingress; -- cgit v1.2.3-59-g8ed1b From fdde49e00b9d2041086568b52670043a8def96ff Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:03 +0000 Subject: net/mlx5: E-switch, Introduce and use vlan rule config helper Between legacy mode and switchdev mode, only two fields are changed, vlan_tag and flow action. Hence to avoid duplicte code between two modes, introduce and and use helper function to configure allowed VLAN rule. While at it, get rid of duplicate debug message. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 68 ++++++++++++++-------- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 4 ++ .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 54 ++++------------- 3 files changed, 58 insertions(+), 68 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 4c18ac1299ae..ef7d84a1dbc2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1328,6 +1328,43 @@ out: return err; } +int mlx5_esw_create_vport_egress_acl_vlan(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + u16 vlan_id, u32 flow_action) +{ + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_spec *spec; + int err = 0; + + if (vport->egress.allowed_vlan) + return -EEXIST; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vlan_id); + + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + flow_act.action = flow_action; + vport->egress.allowed_vlan = + mlx5_add_flow_rules(vport->egress.acl, spec, + &flow_act, NULL, 0); + if (IS_ERR(vport->egress.allowed_vlan)) { + err = PTR_ERR(vport->egress.allowed_vlan); + esw_warn(esw->dev, + "vport[%d] configure egress vlan rule failed, err(%d)\n", + vport->vport, err); + vport->egress.allowed_vlan = NULL; + } + + kvfree(spec); + return err; +} + static int esw_vport_egress_config(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { @@ -1358,34 +1395,17 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw, "vport[%d] configure egress rules, vlan(%d) qos(%d)\n", vport->vport, vport->info.vlan, vport->info.qos); - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) { - err = -ENOMEM; - goto out; - } - /* Allowed vlan rule */ - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag); - MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag); - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid); - MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vport->info.vlan); + err = mlx5_esw_create_vport_egress_acl_vlan(esw, vport, vport->info.vlan, + MLX5_FLOW_CONTEXT_ACTION_ALLOW); + if (err) + return err; - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW; - vport->egress.allowed_vlan = - mlx5_add_flow_rules(vport->egress.acl, spec, - &flow_act, NULL, 0); - if (IS_ERR(vport->egress.allowed_vlan)) { - err = PTR_ERR(vport->egress.allowed_vlan); - esw_warn(esw->dev, - "vport[%d] configure egress allowed vlan rule failed, err(%d)\n", - vport->vport, err); - vport->egress.allowed_vlan = NULL; + /* Drop others rule (star rule) */ + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) goto out; - } - /* Drop others rule (star rule) */ - memset(spec, 0, sizeof(*spec)); flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; /* Attach egress drop flow counter */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 6bd6f5895244..1824b0ad7c9f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -421,6 +421,10 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, u16 vport, u16 vlan, u8 qos, u8 set_flags); +int mlx5_esw_create_vport_egress_acl_vlan(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + u16 vlan_id, u32 flow_action); + static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev, u8 vlan_depth) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 48adec168a7c..f0c7abd09120 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1857,48 +1857,6 @@ void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, } } -static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw, - struct mlx5_vport *vport) -{ - struct mlx5_flow_act flow_act = {0}; - struct mlx5_flow_spec *spec; - int err = 0; - - /* For prio tag mode, there is only 1 FTEs: - * 1) prio tag packets - pop the prio tag VLAN, allow - * Unmatched traffic is allowed by default - */ - esw_debug(esw->dev, - "vport[%d] configure prio tag egress rules\n", vport->vport); - - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) - return -ENOMEM; - - /* prio tag vlan rule - pop it so VF receives untagged packets */ - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag); - MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag); - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid); - MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, 0); - - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_VLAN_POP | - MLX5_FLOW_CONTEXT_ACTION_ALLOW; - vport->egress.allowed_vlan = - mlx5_add_flow_rules(vport->egress.acl, spec, - &flow_act, NULL, 0); - if (IS_ERR(vport->egress.allowed_vlan)) { - err = PTR_ERR(vport->egress.allowed_vlan); - esw_warn(esw->dev, - "vport[%d] configure egress pop prio tag vlan rule failed, err(%d)\n", - vport->vport, err); - vport->egress.allowed_vlan = NULL; - } - - kvfree(spec); - return err; -} - static int esw_vport_ingress_config(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { @@ -1954,9 +1912,17 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw, if (err) return err; - esw_debug(esw->dev, "vport(%d) configure egress rules\n", vport->vport); + /* For prio tag mode, there is only 1 FTEs: + * 1) prio tag packets - pop the prio tag VLAN, allow + * Unmatched traffic is allowed by default + */ + esw_debug(esw->dev, + "vport[%d] configure prio tag egress rules\n", vport->vport); - err = esw_vport_egress_prio_tag_config(esw, vport); + /* prio tag vlan rule - pop it so VF receives untagged packets */ + err = mlx5_esw_create_vport_egress_acl_vlan(esw, vport, 0, + MLX5_FLOW_CONTEXT_ACTION_VLAN_POP | + MLX5_FLOW_CONTEXT_ACTION_ALLOW); if (err) esw_vport_disable_egress_acl(esw, vport); -- cgit v1.2.3-59-g8ed1b From ea2300e02a71207b11111a44cbe7185a94f78a72 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:05 +0000 Subject: net/mlx5: Introduce and use mlx5_esw_is_manager_vport() Currently esw_enable_vport() does vport check for zero to enable drop counters regardless of execution on ECPF/PF. While esw_disable_vport() considers such scenario. To keep consistency across code for checking for manager_vport, introduce and use mlx5_esw_is_manager_vport() to check if a specified vport is eswitch manager vport or not. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 13 +++++++------ drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 6 ++++++ 2 files changed, 13 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index ef7d84a1dbc2..fa1228a8005f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -501,7 +501,7 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) /* Skip mlx5_mpfs_add_mac for eswitch_managers, * it is already done by its netdev in mlx5e_execute_l2_action */ - if (esw->manager_vport == vport) + if (mlx5_esw_is_manager_vport(esw, vport)) goto fdb_add; err = mlx5_mpfs_add_mac(esw->dev, mac); @@ -533,7 +533,7 @@ static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) /* Skip mlx5_mpfs_del_mac for eswitch managers, * it is already done by its netdev in mlx5e_execute_l2_action */ - if (!vaddr->mpfs || esw->manager_vport == vport) + if (!vaddr->mpfs || mlx5_esw_is_manager_vport(esw, vport)) goto fdb_del; err = mlx5_mpfs_del_mac(esw->dev, mac); @@ -1639,7 +1639,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw, u16 vport_num = vport->vport; int flags; - if (esw->manager_vport == vport_num) + if (mlx5_esw_is_manager_vport(esw, vport_num)) return; mlx5_modify_vport_admin_state(esw->dev, @@ -1713,7 +1713,8 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num); /* Create steering drop counters for ingress and egress ACLs */ - if (vport_num && esw->mode == MLX5_ESWITCH_LEGACY) + if (!mlx5_esw_is_manager_vport(esw, vport_num) && + esw->mode == MLX5_ESWITCH_LEGACY) esw_vport_create_drop_counters(vport); /* Restore old vport configuration */ @@ -1731,7 +1732,7 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, /* Esw manager is trusted by default. Host PF (vport 0) is trusted as well * in smartNIC as it's a vport group manager. */ - if (esw->manager_vport == vport_num || + if (mlx5_esw_is_manager_vport(esw, vport_num) || (!vport_num && mlx5_core_is_ecpf(esw->dev))) vport->info.trusted = true; @@ -1766,7 +1767,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, esw_vport_change_handle_locked(vport); vport->enabled_events = 0; esw_vport_disable_qos(esw, vport); - if (esw->manager_vport != vport_num && + if (!mlx5_esw_is_manager_vport(esw, vport_num) && esw->mode == MLX5_ESWITCH_LEGACY) { mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 1824b0ad7c9f..75e69644d70e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -463,6 +463,12 @@ static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev) MLX5_VPORT_ECPF : MLX5_VPORT_PF; } +static inline bool +mlx5_esw_is_manager_vport(const struct mlx5_eswitch *esw, u16 vport_num) +{ + return esw->manager_vport == vport_num; +} + static inline u16 mlx5_eswitch_first_host_vport_num(struct mlx5_core_dev *dev) { return mlx5_core_is_ecpf_esw_manager(dev) ? -- cgit v1.2.3-59-g8ed1b From 99ecd64631ef9873619be493c711afb83aff75fc Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:07 +0000 Subject: net/mlx5: Correct comment for legacy fields fdb_table is used for both legacy and offloads mode. It was incorrect to comment that fdb_table is legacy specific. Hence, fix the comment to reflect that fdb_table is used in legacy and offloads mode. Fixes: 131ce7014043 ("net/mlx5: E-Switch, Remove redundant mc_promisc NULL check") Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 75e69644d70e..a41d4aad9d28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -217,8 +217,8 @@ enum { struct mlx5_eswitch { struct mlx5_core_dev *dev; struct mlx5_nb nb; - /* legacy data structures */ struct mlx5_eswitch_fdb fdb_table; + /* legacy data structures */ struct hlist_head mc_table[MLX5_L2_ADDR_HASH_SIZE]; struct esw_mc_addr mc_promisc; /* end of legacy */ -- cgit v1.2.3-59-g8ed1b From d68316b5a1046b489097c5e5e24139548b79971f Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:10 +0000 Subject: net/mlx5: Move metdata fields under offloads structure Metadata fields are offload mode specific. To improve code readability, move metadata under offloads structure. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 6 ++-- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 33 +++++++++++----------- 2 files changed, 21 insertions(+), 18 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index a41d4aad9d28..5f862992b9c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -69,11 +69,13 @@ struct vport_ingress { struct mlx5_flow_group *allow_spoofchk_only_grp; struct mlx5_flow_group *allow_untagged_only_grp; struct mlx5_flow_group *drop_grp; - struct mlx5_modify_hdr *modify_metadata; - struct mlx5_flow_handle *modify_metadata_rule; struct mlx5_flow_handle *allow_rule; struct mlx5_flow_handle *drop_rule; struct mlx5_fc *drop_counter; + struct { + struct mlx5_modify_hdr *modify_metadata; + struct mlx5_flow_handle *modify_metadata_rule; + } offloads; }; struct vport_egress { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f0c7abd09120..874e70e3792a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1778,9 +1778,9 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw, flow_act.vlan[0].vid = 0; flow_act.vlan[0].prio = 0; - if (vport->ingress.modify_metadata_rule) { + if (vport->ingress.offloads.modify_metadata_rule) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - flow_act.modify_hdr = vport->ingress.modify_metadata; + flow_act.modify_hdr = vport->ingress.offloads.modify_metadata; } vport->ingress.allow_rule = @@ -1816,11 +1816,11 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, MLX5_SET(set_action_in, action, data, mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport)); - vport->ingress.modify_metadata = + vport->ingress.offloads.modify_metadata = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, 1, action); - if (IS_ERR(vport->ingress.modify_metadata)) { - err = PTR_ERR(vport->ingress.modify_metadata); + if (IS_ERR(vport->ingress.offloads.modify_metadata)) { + err = PTR_ERR(vport->ingress.offloads.modify_metadata); esw_warn(esw->dev, "failed to alloc modify header for vport %d ingress acl (%d)\n", vport->vport, err); @@ -1828,32 +1828,33 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, } flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW; - flow_act.modify_hdr = vport->ingress.modify_metadata; - vport->ingress.modify_metadata_rule = mlx5_add_flow_rules(vport->ingress.acl, - &spec, &flow_act, NULL, 0); - if (IS_ERR(vport->ingress.modify_metadata_rule)) { - err = PTR_ERR(vport->ingress.modify_metadata_rule); + flow_act.modify_hdr = vport->ingress.offloads.modify_metadata; + vport->ingress.offloads.modify_metadata_rule = + mlx5_add_flow_rules(vport->ingress.acl, + &spec, &flow_act, NULL, 0); + if (IS_ERR(vport->ingress.offloads.modify_metadata_rule)) { + err = PTR_ERR(vport->ingress.offloads.modify_metadata_rule); esw_warn(esw->dev, "failed to add setting metadata rule for vport %d ingress acl, err(%d)\n", vport->vport, err); - vport->ingress.modify_metadata_rule = NULL; + vport->ingress.offloads.modify_metadata_rule = NULL; goto out; } out: if (err) - mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata); + mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata); return err; } void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { - if (vport->ingress.modify_metadata_rule) { - mlx5_del_flow_rules(vport->ingress.modify_metadata_rule); - mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata); + if (vport->ingress.offloads.modify_metadata_rule) { + mlx5_del_flow_rules(vport->ingress.offloads.modify_metadata_rule); + mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata); - vport->ingress.modify_metadata_rule = NULL; + vport->ingress.offloads.modify_metadata_rule = NULL; } } -- cgit v1.2.3-59-g8ed1b From 853b53520c9d11db7652e3603665b0ad475741a5 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:11 +0000 Subject: net/mlx5: Move legacy drop counter and rule under legacy structure To improve code readability, move legacy drop counters and droup rule under legacy structure. While at it, (a) prefix drop flow counters helper with legacy_. (b) nullify the rule pointers only if they were valid. Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 82 ++++++++++++----------- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 12 ++-- 2 files changed, 50 insertions(+), 44 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index fa1228a8005f..0dd5e5d5ea35 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1040,14 +1040,15 @@ out: void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { - if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan)) + if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan)) { mlx5_del_flow_rules(vport->egress.allowed_vlan); + vport->egress.allowed_vlan = NULL; + } - if (!IS_ERR_OR_NULL(vport->egress.drop_rule)) - mlx5_del_flow_rules(vport->egress.drop_rule); - - vport->egress.allowed_vlan = NULL; - vport->egress.drop_rule = NULL; + if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_rule)) { + mlx5_del_flow_rules(vport->egress.legacy.drop_rule); + vport->egress.legacy.drop_rule = NULL; + } } void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw, @@ -1202,14 +1203,15 @@ out: void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { - if (!IS_ERR_OR_NULL(vport->ingress.drop_rule)) - mlx5_del_flow_rules(vport->ingress.drop_rule); + if (!IS_ERR_OR_NULL(vport->ingress.legacy.drop_rule)) { + mlx5_del_flow_rules(vport->ingress.legacy.drop_rule); + vport->ingress.legacy.drop_rule = NULL; + } - if (!IS_ERR_OR_NULL(vport->ingress.allow_rule)) + if (!IS_ERR_OR_NULL(vport->ingress.allow_rule)) { mlx5_del_flow_rules(vport->ingress.allow_rule); - - vport->ingress.drop_rule = NULL; - vport->ingress.allow_rule = NULL; + vport->ingress.allow_rule = NULL; + } esw_vport_del_ingress_acl_modify_metadata(esw, vport); } @@ -1238,7 +1240,7 @@ void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw, static int esw_vport_ingress_config(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { - struct mlx5_fc *counter = vport->ingress.drop_counter; + struct mlx5_fc *counter = vport->ingress.legacy.drop_counter; struct mlx5_flow_destination drop_ctr_dst = {0}; struct mlx5_flow_destination *dst = NULL; struct mlx5_flow_act flow_act = {0}; @@ -1309,15 +1311,15 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, dst = &drop_ctr_dst; dest_num++; } - vport->ingress.drop_rule = + vport->ingress.legacy.drop_rule = mlx5_add_flow_rules(vport->ingress.acl, spec, &flow_act, dst, dest_num); - if (IS_ERR(vport->ingress.drop_rule)) { - err = PTR_ERR(vport->ingress.drop_rule); + if (IS_ERR(vport->ingress.legacy.drop_rule)) { + err = PTR_ERR(vport->ingress.legacy.drop_rule); esw_warn(esw->dev, "vport[%d] configure ingress drop rule, err(%d)\n", vport->vport, err); - vport->ingress.drop_rule = NULL; + vport->ingress.legacy.drop_rule = NULL; goto out; } @@ -1368,7 +1370,7 @@ int mlx5_esw_create_vport_egress_acl_vlan(struct mlx5_eswitch *esw, static int esw_vport_egress_config(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { - struct mlx5_fc *counter = vport->egress.drop_counter; + struct mlx5_fc *counter = vport->egress.legacy.drop_counter; struct mlx5_flow_destination drop_ctr_dst = {0}; struct mlx5_flow_destination *dst = NULL; struct mlx5_flow_act flow_act = {0}; @@ -1416,15 +1418,15 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw, dst = &drop_ctr_dst; dest_num++; } - vport->egress.drop_rule = + vport->egress.legacy.drop_rule = mlx5_add_flow_rules(vport->egress.acl, spec, &flow_act, dst, dest_num); - if (IS_ERR(vport->egress.drop_rule)) { - err = PTR_ERR(vport->egress.drop_rule); + if (IS_ERR(vport->egress.legacy.drop_rule)) { + err = PTR_ERR(vport->egress.legacy.drop_rule); esw_warn(esw->dev, "vport[%d] configure egress drop rule failed, err(%d)\n", vport->vport, err); - vport->egress.drop_rule = NULL; + vport->egress.legacy.drop_rule = NULL; } out: kvfree(spec); @@ -1667,39 +1669,39 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw, } } -static void esw_vport_create_drop_counters(struct mlx5_vport *vport) +static void esw_legacy_vport_create_drop_counters(struct mlx5_vport *vport) { struct mlx5_core_dev *dev = vport->dev; if (MLX5_CAP_ESW_INGRESS_ACL(dev, flow_counter)) { - vport->ingress.drop_counter = mlx5_fc_create(dev, false); - if (IS_ERR(vport->ingress.drop_counter)) { + vport->ingress.legacy.drop_counter = mlx5_fc_create(dev, false); + if (IS_ERR(vport->ingress.legacy.drop_counter)) { esw_warn(dev, "vport[%d] configure ingress drop rule counter failed\n", vport->vport); - vport->ingress.drop_counter = NULL; + vport->ingress.legacy.drop_counter = NULL; } } if (MLX5_CAP_ESW_EGRESS_ACL(dev, flow_counter)) { - vport->egress.drop_counter = mlx5_fc_create(dev, false); - if (IS_ERR(vport->egress.drop_counter)) { + vport->egress.legacy.drop_counter = mlx5_fc_create(dev, false); + if (IS_ERR(vport->egress.legacy.drop_counter)) { esw_warn(dev, "vport[%d] configure egress drop rule counter failed\n", vport->vport); - vport->egress.drop_counter = NULL; + vport->egress.legacy.drop_counter = NULL; } } } -static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport) +static void esw_legacy_vport_destroy_drop_counters(struct mlx5_vport *vport) { struct mlx5_core_dev *dev = vport->dev; - if (vport->ingress.drop_counter) - mlx5_fc_destroy(dev, vport->ingress.drop_counter); - if (vport->egress.drop_counter) - mlx5_fc_destroy(dev, vport->egress.drop_counter); + if (vport->ingress.legacy.drop_counter) + mlx5_fc_destroy(dev, vport->ingress.legacy.drop_counter); + if (vport->egress.legacy.drop_counter) + mlx5_fc_destroy(dev, vport->egress.legacy.drop_counter); } static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, @@ -1715,7 +1717,7 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, /* Create steering drop counters for ingress and egress ACLs */ if (!mlx5_esw_is_manager_vport(esw, vport_num) && esw->mode == MLX5_ESWITCH_LEGACY) - esw_vport_create_drop_counters(vport); + esw_legacy_vport_create_drop_counters(vport); /* Restore old vport configuration */ esw_apply_vport_conf(esw, vport); @@ -1775,7 +1777,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, MLX5_VPORT_ADMIN_STATE_DOWN); esw_vport_disable_egress_acl(esw, vport); esw_vport_disable_ingress_acl(esw, vport); - esw_vport_destroy_drop_counters(vport); + esw_legacy_vport_destroy_drop_counters(vport); } esw->enabled_vports--; mutex_unlock(&esw->state_lock); @@ -2495,12 +2497,12 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev, if (!vport->enabled || esw->mode != MLX5_ESWITCH_LEGACY) return 0; - if (vport->egress.drop_counter) - mlx5_fc_query(dev, vport->egress.drop_counter, + if (vport->egress.legacy.drop_counter) + mlx5_fc_query(dev, vport->egress.legacy.drop_counter, &stats->rx_dropped, &bytes); - if (vport->ingress.drop_counter) - mlx5_fc_query(dev, vport->ingress.drop_counter, + if (vport->ingress.legacy.drop_counter) + mlx5_fc_query(dev, vport->ingress.legacy.drop_counter, &stats->tx_dropped, &bytes); if (!MLX5_CAP_GEN(dev, receive_discard_vport_down) && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 5f862992b9c8..ec0ef7c5d539 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -70,8 +70,10 @@ struct vport_ingress { struct mlx5_flow_group *allow_untagged_only_grp; struct mlx5_flow_group *drop_grp; struct mlx5_flow_handle *allow_rule; - struct mlx5_flow_handle *drop_rule; - struct mlx5_fc *drop_counter; + struct { + struct mlx5_flow_handle *drop_rule; + struct mlx5_fc *drop_counter; + } legacy; struct { struct mlx5_modify_hdr *modify_metadata; struct mlx5_flow_handle *modify_metadata_rule; @@ -83,8 +85,10 @@ struct vport_egress { struct mlx5_flow_group *allowed_vlans_grp; struct mlx5_flow_group *drop_grp; struct mlx5_flow_handle *allowed_vlan; - struct mlx5_flow_handle *drop_rule; - struct mlx5_fc *drop_counter; + struct { + struct mlx5_flow_handle *drop_rule; + struct mlx5_fc *drop_counter; + } legacy; }; struct mlx5_vport_drop_stats { -- cgit v1.2.3-59-g8ed1b From 77b094305b1ba23e716bb34d3e33c8fe30a5f487 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:13 +0000 Subject: net/mlx5: Tide up state_lock and vport enabled flag usage When eswitch is disabled, vport event handler is unregistered. This unregistration already synchronizes with running EQ event handler in below code flow. mlx5_eswitch_disable() mlx5_eswitch_event_handlers_unregister() mlx5_eq_notifier_unregister() atomic_notifier_chain_unregister() synchronize_rcu() notifier_callchain eswitch_vport_event() queue_work() Additionally vport->enabled flag is set under state_lock during esw_enable_vport() but is not read under state_lock in (a) esw_disable_vport() and (b) under atomic context eswitch_vport_event(). It is also necessary to synchronize with already scheduled vport event. This is already achieved using below sequence. mlx5_eswitch_event_handlers_unregister() [..] flush_workqueue() Hence, (a) Remove vport->enabled check in eswitch_vport_event() which doesn't make any sense. (b) Remove redundant flush_workqueue() on every vport disable. (c) Keep esw_disable_vport() symmetric with esw_enable_vport() for state_lock. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 0dd5e5d5ea35..f15ffb8f5cac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1750,18 +1750,16 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, { u16 vport_num = vport->vport; + mutex_lock(&esw->state_lock); if (!vport->enabled) - return; + goto done; esw_debug(esw->dev, "Disabling vport(%d)\n", vport_num); /* Mark this vport as disabled to discard new events */ vport->enabled = false; - /* Wait for current already scheduled events to complete */ - flush_workqueue(esw->work_queue); /* Disable events from this vport */ arm_vport_context_events_cmd(esw->dev, vport->vport, 0); - mutex_lock(&esw->state_lock); /* We don't assume VFs will cleanup after themselves. * Calling vport change handler while vport is disabled will cleanup * the vport resources. @@ -1780,6 +1778,8 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, esw_legacy_vport_destroy_drop_counters(vport); } esw->enabled_vports--; + +done: mutex_unlock(&esw->state_lock); } @@ -1793,12 +1793,8 @@ static int eswitch_vport_event(struct notifier_block *nb, vport_num = be16_to_cpu(eqe->data.vport_change.vport_num); vport = mlx5_eswitch_get_vport(esw, vport_num); - if (IS_ERR(vport)) - return NOTIFY_OK; - - if (vport->enabled) + if (!IS_ERR(vport)) queue_work(esw->work_queue, &vport->vport_change_handler); - return NOTIFY_OK; } -- cgit v1.2.3-59-g8ed1b From 925a6acc77a70f8b5bfd0df75e36557aa400b0a0 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:15 +0000 Subject: net/mlx5: E-switch, Prepare code to handle vport enable error In subsequent patch, esw_enable_vport() could fail and return error. Prepare code to handle such error. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 62 ++++++++++++++++------ drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 2 +- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 5 +- 3 files changed, 50 insertions(+), 19 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index f15ffb8f5cac..0bdaef508e74 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -452,6 +452,13 @@ static int esw_create_legacy_table(struct mlx5_eswitch *esw) return err; } +static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) +{ + esw_cleanup_vepa_rules(esw); + esw_destroy_legacy_fdb_table(esw); + esw_destroy_legacy_vepa_table(esw); +} + #define MLX5_LEGACY_SRIOV_VPORT_EVENTS (MLX5_VPORT_UC_ADDR_CHANGE | \ MLX5_VPORT_MC_ADDR_CHANGE | \ MLX5_VPORT_PROMISC_CHANGE) @@ -464,15 +471,10 @@ static int esw_legacy_enable(struct mlx5_eswitch *esw) if (ret) return ret; - mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS); - return 0; -} - -static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) -{ - esw_cleanup_vepa_rules(esw); - esw_destroy_legacy_fdb_table(esw); - esw_destroy_legacy_vepa_table(esw); + ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS); + if (ret) + esw_destroy_legacy_table(esw); + return ret; } static void esw_legacy_disable(struct mlx5_eswitch *esw) @@ -1704,8 +1706,8 @@ static void esw_legacy_vport_destroy_drop_counters(struct mlx5_vport *vport) mlx5_fc_destroy(dev, vport->egress.legacy.drop_counter); } -static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, - enum mlx5_eswitch_vport_event enabled_events) +static int esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, + enum mlx5_eswitch_vport_event enabled_events) { u16 vport_num = vport->vport; @@ -1743,6 +1745,7 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, esw->enabled_vports++; esw_debug(esw->dev, "Enabled VPORT(%d)\n", vport_num); mutex_unlock(&esw->state_lock); + return 0; } static void esw_disable_vport(struct mlx5_eswitch *esw, @@ -1856,26 +1859,51 @@ static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw) /* mlx5_eswitch_enable_pf_vf_vports() enables vports of PF, ECPF and VFs * whichever are present on the eswitch. */ -void +int mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, enum mlx5_eswitch_vport_event enabled_events) { struct mlx5_vport *vport; + int num_vfs; + int ret; int i; /* Enable PF vport */ vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - esw_enable_vport(esw, vport, enabled_events); + ret = esw_enable_vport(esw, vport, enabled_events); + if (ret) + return ret; - /* Enable ECPF vports */ + /* Enable ECPF vport */ if (mlx5_ecpf_vport_exists(esw->dev)) { vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - esw_enable_vport(esw, vport, enabled_events); + ret = esw_enable_vport(esw, vport, enabled_events); + if (ret) + goto ecpf_err; } /* Enable VF vports */ - mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) - esw_enable_vport(esw, vport, enabled_events); + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) { + ret = esw_enable_vport(esw, vport, enabled_events); + if (ret) + goto vf_err; + } + return 0; + +vf_err: + num_vfs = i - 1; + mlx5_esw_for_each_vf_vport_reverse(esw, i, vport, num_vfs) + esw_disable_vport(esw, vport); + + if (mlx5_ecpf_vport_exists(esw->dev)) { + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + esw_disable_vport(esw, vport); + } + +ecpf_err: + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); + esw_disable_vport(esw, vport); + return ret; } /* mlx5_eswitch_disable_pf_vf_vports() disables vports of PF, ECPF and VFs diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index ec0ef7c5d539..36edee35f155 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -609,7 +609,7 @@ bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num); void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs); int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data); -void +int mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, enum mlx5_eswitch_vport_event enabled_events); void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 874e70e3792a..98df1eeee873 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2139,7 +2139,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) if (err) goto err_vport_metadata; - mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE); + err = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE); + if (err) + goto err_vports; err = esw_offloads_load_all_reps(esw); if (err) @@ -2152,6 +2154,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) err_reps: mlx5_eswitch_disable_pf_vf_vports(esw); +err_vports: esw_set_passing_vport_metadata(esw, false); err_vport_metadata: esw_offloads_steering_cleanup(esw); -- cgit v1.2.3-59-g8ed1b From f5d0c01d65adba2b898836894d200e85c8a8def3 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:17 +0000 Subject: net/mlx5: E-switch, Legacy introduce and use per vport acl tables APIs Introduce and use per vport ACL tables creation and destroy APIs, so that subsequently patch can use them during enabling/disabling a vport in unified way for legacy vs offloads mode. Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 73 +++++++++++++++++++---- 1 file changed, 60 insertions(+), 13 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 0bdaef508e74..47555e272dda 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1663,12 +1663,6 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw, SET_VLAN_STRIP | SET_VLAN_INSERT : 0; modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos, flags); - - /* Only legacy mode needs ACLs */ - if (esw->mode == MLX5_ESWITCH_LEGACY) { - esw_vport_ingress_config(esw, vport); - esw_vport_egress_config(esw, vport); - } } static void esw_legacy_vport_create_drop_counters(struct mlx5_vport *vport) @@ -1706,10 +1700,59 @@ static void esw_legacy_vport_destroy_drop_counters(struct mlx5_vport *vport) mlx5_fc_destroy(dev, vport->egress.legacy.drop_counter); } +static int esw_vport_create_legacy_acl_tables(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + int ret; + + /* Only non manager vports need ACL in legacy mode */ + if (mlx5_esw_is_manager_vport(esw, vport->vport)) + return 0; + + ret = esw_vport_ingress_config(esw, vport); + if (ret) + return ret; + + ret = esw_vport_egress_config(esw, vport); + if (ret) + esw_vport_disable_ingress_acl(esw, vport); + + return ret; +} + +static int esw_vport_setup_acl(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + if (esw->mode == MLX5_ESWITCH_LEGACY) + return esw_vport_create_legacy_acl_tables(esw, vport); + + return 0; +} + +static void esw_vport_destroy_legacy_acl_tables(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) + +{ + if (mlx5_esw_is_manager_vport(esw, vport->vport)) + return; + + esw_vport_disable_egress_acl(esw, vport); + esw_vport_disable_ingress_acl(esw, vport); + esw_legacy_vport_destroy_drop_counters(vport); +} + +static void esw_vport_cleanup_acl(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + if (esw->mode == MLX5_ESWITCH_LEGACY) + esw_vport_destroy_legacy_acl_tables(esw, vport); +} + static int esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, enum mlx5_eswitch_vport_event enabled_events) { u16 vport_num = vport->vport; + int ret; mutex_lock(&esw->state_lock); WARN_ON(vport->enabled); @@ -1724,6 +1767,10 @@ static int esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, /* Restore old vport configuration */ esw_apply_vport_conf(esw, vport); + ret = esw_vport_setup_acl(esw, vport); + if (ret) + goto done; + /* Attach vport to the eswitch rate limiter */ if (esw_vport_enable_qos(esw, vport, vport->info.max_rate, vport->qos.bw_share)) @@ -1744,8 +1791,9 @@ static int esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, esw->enabled_vports++; esw_debug(esw->dev, "Enabled VPORT(%d)\n", vport_num); +done: mutex_unlock(&esw->state_lock); - return 0; + return ret; } static void esw_disable_vport(struct mlx5_eswitch *esw, @@ -1770,16 +1818,15 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, esw_vport_change_handle_locked(vport); vport->enabled_events = 0; esw_vport_disable_qos(esw, vport); - if (!mlx5_esw_is_manager_vport(esw, vport_num) && - esw->mode == MLX5_ESWITCH_LEGACY) { + + if (!mlx5_esw_is_manager_vport(esw, vport->vport) && + esw->mode == MLX5_ESWITCH_LEGACY) mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, vport_num, 1, MLX5_VPORT_ADMIN_STATE_DOWN); - esw_vport_disable_egress_acl(esw, vport); - esw_vport_disable_ingress_acl(esw, vport); - esw_legacy_vport_destroy_drop_counters(vport); - } + + esw_vport_cleanup_acl(esw, vport); esw->enabled_vports--; done: -- cgit v1.2.3-59-g8ed1b From b7752f8341c4fecc4720fbd58f868e114a57fdea Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:19 +0000 Subject: net/mlx5: Move ACL drop counters life cycle close to ACL lifecycle It is better to create/destroy ACL related drop counters where the actual drop rule ACLs are created/destroyed, so that ACL configuration is self contained for ingress and egress. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 74 +++++++++++------------ 1 file changed, 35 insertions(+), 39 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 47555e272dda..0e5113167739 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1665,58 +1665,55 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw, flags); } -static void esw_legacy_vport_create_drop_counters(struct mlx5_vport *vport) +static int esw_vport_create_legacy_acl_tables(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) { - struct mlx5_core_dev *dev = vport->dev; + int ret; - if (MLX5_CAP_ESW_INGRESS_ACL(dev, flow_counter)) { - vport->ingress.legacy.drop_counter = mlx5_fc_create(dev, false); + /* Only non manager vports need ACL in legacy mode */ + if (mlx5_esw_is_manager_vport(esw, vport->vport)) + return 0; + + if (!mlx5_esw_is_manager_vport(esw, vport->vport) && + MLX5_CAP_ESW_INGRESS_ACL(esw->dev, flow_counter)) { + vport->ingress.legacy.drop_counter = mlx5_fc_create(esw->dev, false); if (IS_ERR(vport->ingress.legacy.drop_counter)) { - esw_warn(dev, + esw_warn(esw->dev, "vport[%d] configure ingress drop rule counter failed\n", vport->vport); vport->ingress.legacy.drop_counter = NULL; } } - if (MLX5_CAP_ESW_EGRESS_ACL(dev, flow_counter)) { - vport->egress.legacy.drop_counter = mlx5_fc_create(dev, false); + ret = esw_vport_ingress_config(esw, vport); + if (ret) + goto ingress_err; + + if (!mlx5_esw_is_manager_vport(esw, vport->vport) && + MLX5_CAP_ESW_EGRESS_ACL(esw->dev, flow_counter)) { + vport->egress.legacy.drop_counter = mlx5_fc_create(esw->dev, false); if (IS_ERR(vport->egress.legacy.drop_counter)) { - esw_warn(dev, + esw_warn(esw->dev, "vport[%d] configure egress drop rule counter failed\n", vport->vport); vport->egress.legacy.drop_counter = NULL; } } -} - -static void esw_legacy_vport_destroy_drop_counters(struct mlx5_vport *vport) -{ - struct mlx5_core_dev *dev = vport->dev; - - if (vport->ingress.legacy.drop_counter) - mlx5_fc_destroy(dev, vport->ingress.legacy.drop_counter); - if (vport->egress.legacy.drop_counter) - mlx5_fc_destroy(dev, vport->egress.legacy.drop_counter); -} - -static int esw_vport_create_legacy_acl_tables(struct mlx5_eswitch *esw, - struct mlx5_vport *vport) -{ - int ret; - - /* Only non manager vports need ACL in legacy mode */ - if (mlx5_esw_is_manager_vport(esw, vport->vport)) - return 0; - - ret = esw_vport_ingress_config(esw, vport); - if (ret) - return ret; ret = esw_vport_egress_config(esw, vport); if (ret) - esw_vport_disable_ingress_acl(esw, vport); + goto egress_err; + + return 0; +egress_err: + esw_vport_disable_ingress_acl(esw, vport); + mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter); + vport->egress.legacy.drop_counter = NULL; + +ingress_err: + mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter); + vport->ingress.legacy.drop_counter = NULL; return ret; } @@ -1737,8 +1734,12 @@ static void esw_vport_destroy_legacy_acl_tables(struct mlx5_eswitch *esw, return; esw_vport_disable_egress_acl(esw, vport); + mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter); + vport->egress.legacy.drop_counter = NULL; + esw_vport_disable_ingress_acl(esw, vport); - esw_legacy_vport_destroy_drop_counters(vport); + mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter); + vport->ingress.legacy.drop_counter = NULL; } static void esw_vport_cleanup_acl(struct mlx5_eswitch *esw, @@ -1759,11 +1760,6 @@ static int esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num); - /* Create steering drop counters for ingress and egress ACLs */ - if (!mlx5_esw_is_manager_vport(esw, vport_num) && - esw->mode == MLX5_ESWITCH_LEGACY) - esw_legacy_vport_create_drop_counters(vport); - /* Restore old vport configuration */ esw_apply_vport_conf(esw, vport); -- cgit v1.2.3-59-g8ed1b From 89a0f1fb16adca959ea1485a856fbcfcd1d24208 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:20 +0000 Subject: net/mlx5: E-switch, Offloads introduce and use per vport acl tables APIs Introduce and use per vport ACL tables creation and destroy APIs, so that subsequently patch can use them during enabling/disabling a vport. Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 49 ++++++++++++++-------- 1 file changed, 32 insertions(+), 17 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 98df1eeee873..94eb18ae33a4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1950,6 +1950,32 @@ esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw) return true; } +static int +esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + int err; + + err = esw_vport_ingress_config(esw, vport); + if (err) + return err; + + if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) { + err = esw_vport_egress_config(esw, vport); + if (err) + esw_vport_disable_ingress_acl(esw, vport); + } + return err; +} + +static void +esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + esw_vport_disable_egress_acl(esw, vport); + esw_vport_disable_ingress_acl(esw, vport); +} + static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw) { struct mlx5_vport *vport; @@ -1960,15 +1986,9 @@ static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw) esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA; mlx5_esw_for_all_vports(esw, i, vport) { - err = esw_vport_ingress_config(esw, vport); + err = esw_vport_create_offloads_acl_tables(esw, vport); if (err) - goto err_ingress; - - if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) { - err = esw_vport_egress_config(esw, vport); - if (err) - goto err_egress; - } + goto err_acl_table; } if (mlx5_eswitch_vport_match_metadata_enabled(esw)) @@ -1976,13 +1996,10 @@ static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw) return 0; -err_egress: - esw_vport_disable_ingress_acl(esw, vport); -err_ingress: +err_acl_table: for (j = MLX5_VPORT_PF; j < i; j++) { vport = &esw->vports[j]; - esw_vport_disable_egress_acl(esw, vport); - esw_vport_disable_ingress_acl(esw, vport); + esw_vport_destroy_offloads_acl_tables(esw, vport); } return err; @@ -1993,10 +2010,8 @@ static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw) struct mlx5_vport *vport; int i; - mlx5_esw_for_all_vports(esw, i, vport) { - esw_vport_disable_egress_acl(esw, vport); - esw_vport_disable_ingress_acl(esw, vport); - } + mlx5_esw_for_all_vports(esw, i, vport) + esw_vport_destroy_offloads_acl_tables(esw, vport); esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA; } -- cgit v1.2.3-59-g8ed1b From 748da30b376e034ae54b53e7e38e15cfa2bf4dda Mon Sep 17 00:00:00 2001 From: Vu Pham Date: Mon, 28 Oct 2019 23:35:22 +0000 Subject: net/mlx5: E-switch, Offloads shift ACL programming during enable/disable vport Currently legacy mode enables ACL while enabling vport, while offloads mode enable ACL when moving to offloads mode. Bring consistency to both modes by enabling/disabling ACL when enabling/disabling a vport. It also eliminates creating ingress ACL table on unused ECPF vport in offloads mode. Signed-off-by: Vu Pham Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 6 ++-- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 7 ++++ .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 42 +++++++--------------- 3 files changed, 24 insertions(+), 31 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 0e5113167739..1ce6ae1c446e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1722,8 +1722,8 @@ static int esw_vport_setup_acl(struct mlx5_eswitch *esw, { if (esw->mode == MLX5_ESWITCH_LEGACY) return esw_vport_create_legacy_acl_tables(esw, vport); - - return 0; + else + return esw_vport_create_offloads_acl_tables(esw, vport); } static void esw_vport_destroy_legacy_acl_tables(struct mlx5_eswitch *esw, @@ -1747,6 +1747,8 @@ static void esw_vport_cleanup_acl(struct mlx5_eswitch *esw, { if (esw->mode == MLX5_ESWITCH_LEGACY) esw_vport_destroy_legacy_acl_tables(esw, vport); + else + esw_vport_destroy_offloads_acl_tables(esw, vport); } static int esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 36edee35f155..d926bdacbdcc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -614,6 +614,13 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, enum mlx5_eswitch_vport_event enabled_events); void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw); +int +esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw, + struct mlx5_vport *vport); +void +esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw, + struct mlx5_vport *vport); + #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 94eb18ae33a4..ce30ead90617 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1950,7 +1950,7 @@ esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw) return true; } -static int +int esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { @@ -1968,7 +1968,7 @@ esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw, return err; } -static void +void esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { @@ -1976,43 +1976,27 @@ esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw, esw_vport_disable_ingress_acl(esw, vport); } -static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw) +static int esw_create_uplink_offloads_acl_tables(struct mlx5_eswitch *esw) { struct mlx5_vport *vport; - int i, j; int err; if (esw_check_vport_match_metadata_supported(esw)) esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA; - mlx5_esw_for_all_vports(esw, i, vport) { - err = esw_vport_create_offloads_acl_tables(esw, vport); - if (err) - goto err_acl_table; - } - - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) - esw_info(esw->dev, "Use metadata reg_c as source vport to match\n"); - - return 0; - -err_acl_table: - for (j = MLX5_VPORT_PF; j < i; j++) { - vport = &esw->vports[j]; - esw_vport_destroy_offloads_acl_tables(esw, vport); - } - + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK); + err = esw_vport_create_offloads_acl_tables(esw, vport); + if (err) + esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA; return err; } -static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw) +static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw) { struct mlx5_vport *vport; - int i; - - mlx5_esw_for_all_vports(esw, i, vport) - esw_vport_destroy_offloads_acl_tables(esw, vport); + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK); + esw_vport_destroy_offloads_acl_tables(esw, vport); esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA; } @@ -2030,7 +2014,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb)); mutex_init(&esw->fdb_table.offloads.fdb_prio_lock); - err = esw_create_offloads_acl_tables(esw); + err = esw_create_uplink_offloads_acl_tables(esw); if (err) return err; @@ -2055,7 +2039,7 @@ create_ft_err: esw_destroy_offloads_fdb_tables(esw); create_fdb_err: - esw_destroy_offloads_acl_tables(esw); + esw_destroy_uplink_offloads_acl_tables(esw); return err; } @@ -2065,7 +2049,7 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) esw_destroy_vport_rx_group(esw); esw_destroy_offloads_table(esw); esw_destroy_offloads_fdb_tables(esw); - esw_destroy_offloads_acl_tables(esw); + esw_destroy_uplink_offloads_acl_tables(esw); } static void -- cgit v1.2.3-59-g8ed1b From a962d7a61e2404cda6a89bfa5cc193c62223bb5e Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:24 +0000 Subject: net/mlx5: Restrict metadata disablement to offloads mode Now that there is clear separation for acl setup/cleanup between legacy and offloads mode, limit metdata disablement to offloads mode. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 -- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 2 -- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 9 ++++++--- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 1ce6ae1c446e..61459c06f56c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1214,8 +1214,6 @@ void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw, mlx5_del_flow_rules(vport->ingress.allow_rule); vport->ingress.allow_rule = NULL; } - - esw_vport_del_ingress_acl_modify_metadata(esw, vport); } void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index d926bdacbdcc..aa3588446cba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -267,8 +267,6 @@ void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw, struct mlx5_vport *vport); void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw, struct mlx5_vport *vport); -void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, - struct mlx5_vport *vport); int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 rate_mbps); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index ce30ead90617..b536c8fa0061 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1847,8 +1847,8 @@ out: return err; } -void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, - struct mlx5_vport *vport) +static void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) { if (vport->ingress.offloads.modify_metadata_rule) { mlx5_del_flow_rules(vport->ingress.offloads.modify_metadata_rule); @@ -1962,8 +1962,10 @@ esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw, if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) { err = esw_vport_egress_config(esw, vport); - if (err) + if (err) { + esw_vport_del_ingress_acl_modify_metadata(esw, vport); esw_vport_disable_ingress_acl(esw, vport); + } } return err; } @@ -1973,6 +1975,7 @@ esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { esw_vport_disable_egress_acl(esw, vport); + esw_vport_del_ingress_acl_modify_metadata(esw, vport); esw_vport_disable_ingress_acl(esw, vport); } -- cgit v1.2.3-59-g8ed1b From 10652f39943ec19d32a6fa44a8523b0d40abcbcf Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:26 +0000 Subject: net/mlx5: Refactor ingress acl configuration Drop, untagged, spoof check and untagged spoof check flow groups are limited to legacy mode only. Therefore, following refactoring is done to (a) improve code readability (b) have better code split between legacy and offloads mode 1. Move legacy flow groups under legacy structure 2. Add validity check for group deletion 3. Restrict scope of esw_vport_disable_ingress_acl to legacy mode 4. Rename esw_vport_enable_ingress_acl() to esw_vport_create_ingress_acl_table() and limit its scope to table creation 5. Introduce legacy flow groups creation helper esw_legacy_create_ingress_acl_groups() and keep its scope to legacy mode 6. Reduce offloads ingress groups from 4 to just 1 metadata group per vport 7. Removed redundant IS_ERR_OR_NULL as entries are marked NULL on free. 8. Shortern error message to remove redundant 'E-switch' Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 228 ++++++++++++--------- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 19 +- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 67 +++++- 3 files changed, 200 insertions(+), 114 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 61459c06f56c..cc8d43d8c469 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1070,57 +1070,21 @@ void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw, vport->egress.acl = NULL; } -int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, - struct mlx5_vport *vport) +static int +esw_vport_create_legacy_ingress_acl_groups(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_core_dev *dev = esw->dev; - struct mlx5_flow_namespace *root_ns; - struct mlx5_flow_table *acl; struct mlx5_flow_group *g; void *match_criteria; u32 *flow_group_in; - /* The ingress acl table contains 4 groups - * (2 active rules at the same time - - * 1 allow rule from one of the first 3 groups. - * 1 drop rule from the last group): - * 1)Allow untagged traffic with smac=original mac. - * 2)Allow untagged traffic. - * 3)Allow traffic with smac=original mac. - * 4)Drop all other traffic. - */ - int table_size = 4; - int err = 0; - - if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) - return -EOPNOTSUPP; - - if (!IS_ERR_OR_NULL(vport->ingress.acl)) - return 0; - - esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n", - vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size)); - - root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, - mlx5_eswitch_vport_num_to_index(esw, vport->vport)); - if (!root_ns) { - esw_warn(dev, "Failed to get E-Switch ingress flow namespace for vport (%d)\n", vport->vport); - return -EOPNOTSUPP; - } + int err; flow_group_in = kvzalloc(inlen, GFP_KERNEL); if (!flow_group_in) return -ENOMEM; - acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport); - if (IS_ERR(acl)) { - err = PTR_ERR(acl); - esw_warn(dev, "Failed to create E-Switch vport[%d] ingress flow Table, err(%d)\n", - vport->vport, err); - goto out; - } - vport->ingress.acl = acl; - match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria); MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); @@ -1130,14 +1094,14 @@ int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0); - g = mlx5_create_flow_group(acl, flow_group_in); + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); if (IS_ERR(g)) { err = PTR_ERR(g); - esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged spoofchk flow group, err(%d)\n", + esw_warn(dev, "vport[%d] ingress create untagged spoofchk flow group, err(%d)\n", vport->vport, err); - goto out; + goto spoof_err; } - vport->ingress.allow_untagged_spoofchk_grp = g; + vport->ingress.legacy.allow_untagged_spoofchk_grp = g; memset(flow_group_in, 0, inlen); MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); @@ -1145,14 +1109,14 @@ int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1); - g = mlx5_create_flow_group(acl, flow_group_in); + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); if (IS_ERR(g)) { err = PTR_ERR(g); - esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged flow group, err(%d)\n", + esw_warn(dev, "vport[%d] ingress create untagged flow group, err(%d)\n", vport->vport, err); - goto out; + goto untagged_err; } - vport->ingress.allow_untagged_only_grp = g; + vport->ingress.legacy.allow_untagged_only_grp = g; memset(flow_group_in, 0, inlen); MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); @@ -1161,80 +1125,134 @@ int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 2); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 2); - g = mlx5_create_flow_group(acl, flow_group_in); + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); if (IS_ERR(g)) { err = PTR_ERR(g); - esw_warn(dev, "Failed to create E-Switch vport[%d] ingress spoofchk flow group, err(%d)\n", + esw_warn(dev, "vport[%d] ingress create spoofchk flow group, err(%d)\n", vport->vport, err); - goto out; + goto allow_spoof_err; } - vport->ingress.allow_spoofchk_only_grp = g; + vport->ingress.legacy.allow_spoofchk_only_grp = g; memset(flow_group_in, 0, inlen); MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 3); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 3); - g = mlx5_create_flow_group(acl, flow_group_in); + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); if (IS_ERR(g)) { err = PTR_ERR(g); - esw_warn(dev, "Failed to create E-Switch vport[%d] ingress drop flow group, err(%d)\n", + esw_warn(dev, "vport[%d] ingress create drop flow group, err(%d)\n", vport->vport, err); - goto out; + goto drop_err; } - vport->ingress.drop_grp = g; + vport->ingress.legacy.drop_grp = g; + kvfree(flow_group_in); + return 0; -out: - if (err) { - if (!IS_ERR_OR_NULL(vport->ingress.allow_spoofchk_only_grp)) - mlx5_destroy_flow_group( - vport->ingress.allow_spoofchk_only_grp); - if (!IS_ERR_OR_NULL(vport->ingress.allow_untagged_only_grp)) - mlx5_destroy_flow_group( - vport->ingress.allow_untagged_only_grp); - if (!IS_ERR_OR_NULL(vport->ingress.allow_untagged_spoofchk_grp)) - mlx5_destroy_flow_group( - vport->ingress.allow_untagged_spoofchk_grp); - if (!IS_ERR_OR_NULL(vport->ingress.acl)) - mlx5_destroy_flow_table(vport->ingress.acl); +drop_err: + if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_spoofchk_only_grp)) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_spoofchk_only_grp); + vport->ingress.legacy.allow_spoofchk_only_grp = NULL; } - +allow_spoof_err: + if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_untagged_only_grp)) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_only_grp); + vport->ingress.legacy.allow_untagged_only_grp = NULL; + } +untagged_err: + if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_untagged_spoofchk_grp)) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_spoofchk_grp); + vport->ingress.legacy.allow_untagged_spoofchk_grp = NULL; + } +spoof_err: kvfree(flow_group_in); return err; } +int esw_vport_create_ingress_acl_table(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, int table_size) +{ + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *root_ns; + struct mlx5_flow_table *acl; + int vport_index; + int err; + + if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) + return -EOPNOTSUPP; + + esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n", + vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size)); + + vport_index = mlx5_eswitch_vport_num_to_index(esw, vport->vport); + root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, + vport_index); + if (!root_ns) { + esw_warn(dev, "Failed to get E-Switch ingress flow namespace for vport (%d)\n", + vport->vport); + return -EOPNOTSUPP; + } + + acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport); + if (IS_ERR(acl)) { + err = PTR_ERR(acl); + esw_warn(dev, "vport[%d] ingress create flow Table, err(%d)\n", + vport->vport, err); + return err; + } + vport->ingress.acl = acl; + return 0; +} + +void esw_vport_destroy_ingress_acl_table(struct mlx5_vport *vport) +{ + if (!vport->ingress.acl) + return; + + mlx5_destroy_flow_table(vport->ingress.acl); + vport->ingress.acl = NULL; +} + void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { - if (!IS_ERR_OR_NULL(vport->ingress.legacy.drop_rule)) { + if (vport->ingress.legacy.drop_rule) { mlx5_del_flow_rules(vport->ingress.legacy.drop_rule); vport->ingress.legacy.drop_rule = NULL; } - if (!IS_ERR_OR_NULL(vport->ingress.allow_rule)) { + if (vport->ingress.allow_rule) { mlx5_del_flow_rules(vport->ingress.allow_rule); vport->ingress.allow_rule = NULL; } } -void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw, - struct mlx5_vport *vport) +static void esw_vport_disable_legacy_ingress_acl(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) { - if (IS_ERR_OR_NULL(vport->ingress.acl)) + if (!vport->ingress.acl) return; esw_debug(esw->dev, "Destroy vport[%d] E-Switch ingress ACL\n", vport->vport); esw_vport_cleanup_ingress_rules(esw, vport); - mlx5_destroy_flow_group(vport->ingress.allow_spoofchk_only_grp); - mlx5_destroy_flow_group(vport->ingress.allow_untagged_only_grp); - mlx5_destroy_flow_group(vport->ingress.allow_untagged_spoofchk_grp); - mlx5_destroy_flow_group(vport->ingress.drop_grp); - mlx5_destroy_flow_table(vport->ingress.acl); - vport->ingress.acl = NULL; - vport->ingress.drop_grp = NULL; - vport->ingress.allow_spoofchk_only_grp = NULL; - vport->ingress.allow_untagged_only_grp = NULL; - vport->ingress.allow_untagged_spoofchk_grp = NULL; + if (vport->ingress.legacy.allow_spoofchk_only_grp) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_spoofchk_only_grp); + vport->ingress.legacy.allow_spoofchk_only_grp = NULL; + } + if (vport->ingress.legacy.allow_untagged_only_grp) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_only_grp); + vport->ingress.legacy.allow_untagged_only_grp = NULL; + } + if (vport->ingress.legacy.allow_untagged_spoofchk_grp) { + mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_spoofchk_grp); + vport->ingress.legacy.allow_untagged_spoofchk_grp = NULL; + } + if (vport->ingress.legacy.drop_grp) { + mlx5_destroy_flow_group(vport->ingress.legacy.drop_grp); + vport->ingress.legacy.drop_grp = NULL; + } + esw_vport_destroy_ingress_acl_table(vport); } static int esw_vport_ingress_config(struct mlx5_eswitch *esw, @@ -1249,19 +1267,36 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, int err = 0; u8 *smac_v; + /* The ingress acl table contains 4 groups + * (2 active rules at the same time - + * 1 allow rule from one of the first 3 groups. + * 1 drop rule from the last group): + * 1)Allow untagged traffic with smac=original mac. + * 2)Allow untagged traffic. + * 3)Allow traffic with smac=original mac. + * 4)Drop all other traffic. + */ + int table_size = 4; + esw_vport_cleanup_ingress_rules(esw, vport); if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) { - esw_vport_disable_ingress_acl(esw, vport); + esw_vport_disable_legacy_ingress_acl(esw, vport); return 0; } - err = esw_vport_enable_ingress_acl(esw, vport); - if (err) { - mlx5_core_warn(esw->dev, - "failed to enable ingress acl (%d) on vport[%d]\n", - err, vport->vport); - return err; + if (!vport->ingress.acl) { + err = esw_vport_create_ingress_acl_table(esw, vport, table_size); + if (err) { + esw_warn(esw->dev, + "vport[%d] enable ingress acl err (%d)\n", + err, vport->vport); + return err; + } + + err = esw_vport_create_legacy_ingress_acl_groups(esw, vport); + if (err) + goto out; } esw_debug(esw->dev, @@ -1322,10 +1357,11 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, vport->ingress.legacy.drop_rule = NULL; goto out; } + kvfree(spec); + return 0; out: - if (err) - esw_vport_cleanup_ingress_rules(esw, vport); + esw_vport_disable_legacy_ingress_acl(esw, vport); kvfree(spec); return err; } @@ -1705,7 +1741,7 @@ static int esw_vport_create_legacy_acl_tables(struct mlx5_eswitch *esw, return 0; egress_err: - esw_vport_disable_ingress_acl(esw, vport); + esw_vport_disable_legacy_ingress_acl(esw, vport); mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter); vport->egress.legacy.drop_counter = NULL; @@ -1735,7 +1771,7 @@ static void esw_vport_destroy_legacy_acl_tables(struct mlx5_eswitch *esw, mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter); vport->egress.legacy.drop_counter = NULL; - esw_vport_disable_ingress_acl(esw, vport); + esw_vport_disable_legacy_ingress_acl(esw, vport); mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter); vport->ingress.legacy.drop_counter = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index aa3588446cba..5e91735726b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -65,16 +65,17 @@ struct vport_ingress { struct mlx5_flow_table *acl; - struct mlx5_flow_group *allow_untagged_spoofchk_grp; - struct mlx5_flow_group *allow_spoofchk_only_grp; - struct mlx5_flow_group *allow_untagged_only_grp; - struct mlx5_flow_group *drop_grp; - struct mlx5_flow_handle *allow_rule; + struct mlx5_flow_handle *allow_rule; struct { + struct mlx5_flow_group *allow_spoofchk_only_grp; + struct mlx5_flow_group *allow_untagged_spoofchk_grp; + struct mlx5_flow_group *allow_untagged_only_grp; + struct mlx5_flow_group *drop_grp; struct mlx5_flow_handle *drop_rule; struct mlx5_fc *drop_counter; } legacy; struct { + struct mlx5_flow_group *metadata_grp; struct mlx5_modify_hdr *modify_metadata; struct mlx5_flow_handle *modify_metadata_rule; } offloads; @@ -257,16 +258,16 @@ void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw); int esw_offloads_init_reps(struct mlx5_eswitch *esw); void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw, struct mlx5_vport *vport); -int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, - struct mlx5_vport *vport); +int esw_vport_create_ingress_acl_table(struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + int table_size); +void esw_vport_destroy_ingress_acl_table(struct mlx5_vport *vport); void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw, struct mlx5_vport *vport); int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw, struct mlx5_vport *vport); void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw, struct mlx5_vport *vport); -void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw, - struct mlx5_vport *vport); int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 rate_mbps); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b536c8fa0061..807372a7211b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1858,6 +1858,44 @@ static void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, } } +static int esw_vport_create_ingress_acl_group(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *g; + u32 *flow_group_in; + int ret = 0; + + flow_group_in = kvzalloc(inlen, GFP_KERNEL); + if (!flow_group_in) + return -ENOMEM; + + memset(flow_group_in, 0, inlen); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0); + + g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in); + if (IS_ERR(g)) { + ret = PTR_ERR(g); + esw_warn(esw->dev, + "Failed to create vport[%d] ingress metdata group, err(%d)\n", + vport->vport, ret); + goto grp_err; + } + vport->ingress.offloads.metadata_grp = g; +grp_err: + kvfree(flow_group_in); + return ret; +} + +static void esw_vport_destroy_ingress_acl_group(struct mlx5_vport *vport) +{ + if (vport->ingress.offloads.metadata_grp) { + mlx5_destroy_flow_group(vport->ingress.offloads.metadata_grp); + vport->ingress.offloads.metadata_grp = NULL; + } +} + static int esw_vport_ingress_config(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { @@ -1868,8 +1906,7 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, return 0; esw_vport_cleanup_ingress_rules(esw, vport); - - err = esw_vport_enable_ingress_acl(esw, vport); + err = esw_vport_create_ingress_acl_table(esw, vport, 1); if (err) { esw_warn(esw->dev, "failed to enable ingress acl (%d) on vport[%d]\n", @@ -1877,25 +1914,34 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, return err; } + err = esw_vport_create_ingress_acl_group(esw, vport); + if (err) + goto group_err; + esw_debug(esw->dev, "vport[%d] configure ingress rules\n", vport->vport); if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { err = esw_vport_add_ingress_acl_modify_metadata(esw, vport); if (err) - goto out; + goto metadata_err; } if (MLX5_CAP_GEN(esw->dev, prio_tag_required) && mlx5_eswitch_is_vf_vport(esw, vport->vport)) { err = esw_vport_ingress_prio_tag_config(esw, vport); if (err) - goto out; + goto prio_tag_err; } + return 0; -out: - if (err) - esw_vport_disable_ingress_acl(esw, vport); +prio_tag_err: + esw_vport_del_ingress_acl_modify_metadata(esw, vport); +metadata_err: + esw_vport_cleanup_ingress_rules(esw, vport); + esw_vport_destroy_ingress_acl_group(vport); +group_err: + esw_vport_destroy_ingress_acl_table(vport); return err; } @@ -1964,7 +2010,8 @@ esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw, err = esw_vport_egress_config(esw, vport); if (err) { esw_vport_del_ingress_acl_modify_metadata(esw, vport); - esw_vport_disable_ingress_acl(esw, vport); + esw_vport_cleanup_ingress_rules(esw, vport); + esw_vport_destroy_ingress_acl_table(vport); } } return err; @@ -1976,7 +2023,9 @@ esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw, { esw_vport_disable_egress_acl(esw, vport); esw_vport_del_ingress_acl_modify_metadata(esw, vport); - esw_vport_disable_ingress_acl(esw, vport); + esw_vport_cleanup_ingress_rules(esw, vport); + esw_vport_destroy_ingress_acl_group(vport); + esw_vport_destroy_ingress_acl_table(vport); } static int esw_create_uplink_offloads_acl_tables(struct mlx5_eswitch *esw) -- cgit v1.2.3-59-g8ed1b From 238302fae0216cb2e6a087ba403f3ecc3450b18b Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:28 +0000 Subject: net/mlx5: E-switch, Enable metadata on own vport Currently on ECPF, metadata is enabled on the ECPF vport = 0xfffe (manager vport). Metadata when supported, must be enabled on own vport which is used to pass metadata to vport of NIC Rx Flow Table. Due to this error, traffic tagged by ingress ACL is not processed correctly at NIC rx flow table level which is supposed to work on metadata tag. Hence, instead of working on eswitch manager vport, always working on eswitch own vport regardless of PF or ECPF. Given that mlx5_eswitch_query/modify_esw_vport_context() is used to access other vport in legacy mode and own vport settings in switchdev mode, extend low level API to explicitly specify other_vport. Fixes: c1286050cf47 ("net/mlx5: E-Switch, Pass metadata from FDB to eswitch manager") Signed-off-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 29 ++++++++-------------- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 6 +++-- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 4 +-- 3 files changed, 16 insertions(+), 23 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index cc8d43d8c469..24c2217a4ce8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -111,42 +111,32 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, } /* E-Switch vport context HW commands */ -static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport, - void *in, int inlen) +int mlx5_eswitch_modify_esw_vport_context(struct mlx5_core_dev *dev, u16 vport, + bool other_vport, + void *in, int inlen) { u32 out[MLX5_ST_SZ_DW(modify_esw_vport_context_out)] = {0}; MLX5_SET(modify_esw_vport_context_in, in, opcode, MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT); MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport); - MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1); + MLX5_SET(modify_esw_vport_context_in, in, other_vport, other_vport); return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); } -int mlx5_eswitch_modify_esw_vport_context(struct mlx5_eswitch *esw, u16 vport, - void *in, int inlen) -{ - return modify_esw_vport_context_cmd(esw->dev, vport, in, inlen); -} - -static int query_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport, - void *out, int outlen) +int mlx5_eswitch_query_esw_vport_context(struct mlx5_core_dev *dev, u16 vport, + bool other_vport, + void *out, int outlen) { u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {}; MLX5_SET(query_esw_vport_context_in, in, opcode, MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT); MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport); - MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1); + MLX5_SET(modify_esw_vport_context_in, in, other_vport, other_vport); return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } -int mlx5_eswitch_query_esw_vport_context(struct mlx5_eswitch *esw, u16 vport, - void *out, int outlen) -{ - return query_esw_vport_context_cmd(esw->dev, vport, out, outlen); -} - static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport, u16 vlan, u8 qos, u8 set_flags) { @@ -179,7 +169,8 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport, MLX5_SET(modify_esw_vport_context_in, in, field_select.vport_cvlan_insert, 1); - return modify_esw_vport_context_cmd(dev, vport, in, sizeof(in)); + return mlx5_eswitch_modify_esw_vport_context(dev, vport, true, + in, sizeof(in)); } /* E-Switch FDB */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 5e91735726b7..a05b948a6287 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -297,9 +297,11 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, struct ifla_vf_stats *vf_stats); void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule); -int mlx5_eswitch_modify_esw_vport_context(struct mlx5_eswitch *esw, u16 vport, +int mlx5_eswitch_modify_esw_vport_context(struct mlx5_core_dev *dev, u16 vport, + bool other_vport, void *in, int inlen); -int mlx5_eswitch_query_esw_vport_context(struct mlx5_eswitch *esw, u16 vport, +int mlx5_eswitch_query_esw_vport_context(struct mlx5_core_dev *dev, u16 vport, + bool other_vport, void *out, int outlen); struct mlx5_flow_spec; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 807372a7211b..59eebcae5df6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -600,7 +600,7 @@ static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable) if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) return 0; - err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport, + err = mlx5_eswitch_query_esw_vport_context(esw->dev, 0, false, out, sizeof(out)); if (err) return err; @@ -619,7 +619,7 @@ static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable) MLX5_SET(modify_esw_vport_context_in, in, field_select.fdb_to_vport_reg_c_id, 1); - return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport, + return mlx5_eswitch_modify_esw_vport_context(esw->dev, 0, false, in, sizeof(in)); } -- cgit v1.2.3-59-g8ed1b From 40416d8ede651d26ce334f496a336aa1d38d1c97 Mon Sep 17 00:00:00 2001 From: Hamdan Igbaria Date: Sun, 8 Sep 2019 13:46:25 +0300 Subject: net/mlx5: DR, Replace CRC32 implementation to use kernel lib Use kernel function to calculate crc32 Instead of dr implementation since it has the same algorithm "slice by 8". Fixes: 26d688e33f88 ("net/mlx5: DR, Add Steering entry (STE) utilities") Signed-off-by: Hamdan Igbaria Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- .../mellanox/mlx5/core/steering/dr_crc32.c | 98 ---------------------- .../mellanox/mlx5/core/steering/dr_domain.c | 3 - .../ethernet/mellanox/mlx5/core/steering/dr_ste.c | 10 ++- .../mellanox/mlx5/core/steering/dr_types.h | 3 - 5 files changed, 10 insertions(+), 106 deletions(-) delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 5708fcc079ca..a6f390fdb971 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -70,7 +70,7 @@ mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/t mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o \ steering/dr_matcher.o steering/dr_rule.o \ - steering/dr_icm_pool.o steering/dr_crc32.o \ + steering/dr_icm_pool.o \ steering/dr_ste.o steering/dr_send.o \ steering/dr_cmd.o steering/dr_fw.o \ steering/dr_action.o steering/fs_dr.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c deleted file mode 100644 index 9e2eccbb1eb8..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c +++ /dev/null @@ -1,98 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB -/* Copyright (c) 2019 Mellanox Technologies. */ - -/* Copyright (c) 2011-2015 Stephan Brumme. All rights reserved. - * Slicing-by-16 contributed by Bulat Ziganshin - * - * This software is provided 'as-is', without any express or implied warranty. - * In no event will the author be held liable for any damages arising from the - * of this software. - * - * Permission is granted to anyone to use this software for any purpose, - * including commercial applications, and to alter it and redistribute it - * freely, subject to the following restrictions: - * - * 1. The origin of this software must not be misrepresented; you must not - * claim that you wrote the original software. - * 2. If you use this software in a product, an acknowledgment in the product - * documentation would be appreciated but is not required. - * 3. Altered source versions must be plainly marked as such, and must not be - * misrepresented as being the original software. - * - * Taken from http://create.stephan-brumme.com/crc32/ and adapted. - */ - -#include "dr_types.h" - -#define DR_STE_CRC_POLY 0xEDB88320L - -static u32 dr_ste_crc_tab32[8][256]; - -static void dr_crc32_calc_lookup_entry(u32 (*tbl)[256], u8 i, u8 j) -{ - tbl[i][j] = (tbl[i - 1][j] >> 8) ^ tbl[0][tbl[i - 1][j] & 0xff]; -} - -void mlx5dr_crc32_init_table(void) -{ - u32 crc, i, j; - - for (i = 0; i < 256; i++) { - crc = i; - for (j = 0; j < 8; j++) { - if (crc & 0x00000001L) - crc = (crc >> 1) ^ DR_STE_CRC_POLY; - else - crc = crc >> 1; - } - dr_ste_crc_tab32[0][i] = crc; - } - - /* Init CRC lookup tables according to crc_slice_8 algorithm */ - for (i = 0; i < 256; i++) { - dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 1, i); - dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 2, i); - dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 3, i); - dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 4, i); - dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 5, i); - dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 6, i); - dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 7, i); - } -} - -/* Compute CRC32 (Slicing-by-8 algorithm) */ -u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length) -{ - const u32 *curr = (const u32 *)input_data; - const u8 *curr_char; - u32 crc = 0, one, two; - - if (!input_data) - return 0; - - /* Process eight bytes at once (Slicing-by-8) */ - while (length >= 8) { - one = *curr++ ^ crc; - two = *curr++; - - crc = dr_ste_crc_tab32[0][(two >> 24) & 0xff] - ^ dr_ste_crc_tab32[1][(two >> 16) & 0xff] - ^ dr_ste_crc_tab32[2][(two >> 8) & 0xff] - ^ dr_ste_crc_tab32[3][two & 0xff] - ^ dr_ste_crc_tab32[4][(one >> 24) & 0xff] - ^ dr_ste_crc_tab32[5][(one >> 16) & 0xff] - ^ dr_ste_crc_tab32[6][(one >> 8) & 0xff] - ^ dr_ste_crc_tab32[7][one & 0xff]; - - length -= 8; - } - - curr_char = (const u8 *)curr; - /* Remaining 1 to 7 bytes (standard algorithm) */ - while (length-- != 0) - crc = (crc >> 8) ^ dr_ste_crc_tab32[0][(crc & 0xff) - ^ *curr_char++]; - - return ((crc >> 24) & 0xff) | ((crc << 8) & 0xff0000) | - ((crc >> 8) & 0xff00) | ((crc << 24) & 0xff000000); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 5b24732b18c0..a9da961d4d2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -326,9 +326,6 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) goto uninit_resourses; } - /* Init CRC table for htbl CRC calculation */ - mlx5dr_crc32_init_table(); - return dmn; uninit_resourses: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 4efe1b0be4a8..7e9d6cfc356f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019 Mellanox Technologies. */ #include +#include #include "dr_types.h" #define DR_STE_CRC_POLY 0xEDB88320L @@ -107,6 +108,13 @@ struct dr_hw_ste_format { u8 mask[DR_STE_SIZE_MASK]; }; +static u32 dr_ste_crc32_calc(const void *input_data, size_t length) +{ + u32 crc = crc32(0, input_data, length); + + return htonl(crc); +} + u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl) { struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; @@ -128,7 +136,7 @@ u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl) bit = bit >> 1; } - crc32 = mlx5dr_crc32_slice8_calc(masked, DR_STE_SIZE_TAG); + crc32 = dr_ste_crc32_calc(masked, DR_STE_SIZE_TAG); index = crc32 & (htbl->chunk->num_of_entries - 1); return index; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 1cb3769d4e3c..d6d9bc5f4adf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -962,9 +962,6 @@ void mlx5dr_ste_copy_param(u8 match_criteria, struct mlx5dr_match_param *set_param, struct mlx5dr_match_parameters *mask); -void mlx5dr_crc32_init_table(void); -u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length); - struct mlx5dr_qp { struct mlx5_core_dev *mdev; struct mlx5_wq_qp wq; -- cgit v1.2.3-59-g8ed1b From cc4db579e69b4c92a51fdc9f44bc671b40427824 Mon Sep 17 00:00:00 2001 From: Igor Leshenko Date: Thu, 5 Sep 2019 18:56:28 +0300 Subject: net/mlx5: FPGA, support network cards with standalone FPGA Not all mlx5 cards with FPGA device use it for network processing. mlx5_core driver configures network connection to FPGA device for all mlx5 cards with installed FPGA. If FPGA is not a part of network path, driver crashes in this case Check FPGA name in function mlx5_fpga_device_start() and continue integrate FPGA into packets flow only for dedicated cards. Currently there are Newton and Edison cards. Signed-off-by: Igor Leshenko Reviewed-by: Meir Lichtinger Reviewed-by: Boris Pismenny Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h | 10 ++-- .../net/ethernet/mellanox/mlx5/core/fpga/core.c | 61 +++++++++++++++------- 2 files changed, 46 insertions(+), 25 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h index eb8b0fe0b4e1..11621d265d7e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h @@ -35,11 +35,11 @@ #include -enum mlx5_fpga_device_id { - MLX5_FPGA_DEVICE_UNKNOWN = 0, - MLX5_FPGA_DEVICE_KU040 = 1, - MLX5_FPGA_DEVICE_KU060 = 2, - MLX5_FPGA_DEVICE_KU060_2 = 3, +enum mlx5_fpga_id { + MLX5_FPGA_NEWTON = 0, + MLX5_FPGA_EDISON = 1, + MLX5_FPGA_MORSE = 2, + MLX5_FPGA_MORSEQ = 3, }; enum mlx5_fpga_image { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c index d046d1ec2a86..2ce4241459ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c @@ -81,19 +81,28 @@ static const char *mlx5_fpga_image_name(enum mlx5_fpga_image image) } } -static const char *mlx5_fpga_device_name(u32 device) +static const char *mlx5_fpga_name(u32 fpga_id) { - switch (device) { - case MLX5_FPGA_DEVICE_KU040: - return "ku040"; - case MLX5_FPGA_DEVICE_KU060: - return "ku060"; - case MLX5_FPGA_DEVICE_KU060_2: - return "ku060_2"; - case MLX5_FPGA_DEVICE_UNKNOWN: - default: - return "unknown"; + static char ret[32]; + + switch (fpga_id) { + case MLX5_FPGA_NEWTON: + return "Newton"; + case MLX5_FPGA_EDISON: + return "Edison"; + case MLX5_FPGA_MORSE: + return "Morse"; + case MLX5_FPGA_MORSEQ: + return "MorseQ"; } + + snprintf(ret, sizeof(ret), "Unknown %d", fpga_id); + return ret; +} + +static int mlx5_is_fpga_lookaside(u32 fpga_id) +{ + return fpga_id != MLX5_FPGA_NEWTON && fpga_id != MLX5_FPGA_EDISON; } static int mlx5_fpga_device_load_check(struct mlx5_fpga_device *fdev) @@ -110,8 +119,12 @@ static int mlx5_fpga_device_load_check(struct mlx5_fpga_device *fdev) fdev->last_admin_image = query.admin_image; fdev->last_oper_image = query.oper_image; - mlx5_fpga_dbg(fdev, "Status %u; Admin image %u; Oper image %u\n", - query.status, query.admin_image, query.oper_image); + mlx5_fpga_info(fdev, "Status %u; Admin image %u; Oper image %u\n", + query.status, query.admin_image, query.oper_image); + + /* for FPGA lookaside projects FPGA load status is not important */ + if (mlx5_is_fpga_lookaside(MLX5_CAP_FPGA(fdev->mdev, fpga_id))) + return 0; if (query.status != MLX5_FPGA_STATUS_SUCCESS) { mlx5_fpga_err(fdev, "%s image failed to load; status %u\n", @@ -167,25 +180,30 @@ int mlx5_fpga_device_start(struct mlx5_core_dev *mdev) struct mlx5_fpga_device *fdev = mdev->fpga; unsigned int max_num_qps; unsigned long flags; - u32 fpga_device_id; + u32 fpga_id; int err; if (!fdev) return 0; - err = mlx5_fpga_device_load_check(fdev); + err = mlx5_fpga_caps(fdev->mdev); if (err) goto out; - err = mlx5_fpga_caps(fdev->mdev); + err = mlx5_fpga_device_load_check(fdev); if (err) goto out; - fpga_device_id = MLX5_CAP_FPGA(fdev->mdev, fpga_device); - mlx5_fpga_info(fdev, "%s:%u; %s image, version %u; SBU %06x:%04x version %d\n", - mlx5_fpga_device_name(fpga_device_id), - fpga_device_id, + fpga_id = MLX5_CAP_FPGA(fdev->mdev, fpga_id); + mlx5_fpga_info(fdev, "FPGA card %s:%u\n", mlx5_fpga_name(fpga_id), fpga_id); + + /* No QPs if FPGA does not participate in net processing */ + if (mlx5_is_fpga_lookaside(fpga_id)) + goto out; + + mlx5_fpga_info(fdev, "%s(%d): image, version %u; SBU %06x:%04x version %d\n", mlx5_fpga_image_name(fdev->last_oper_image), + fdev->last_oper_image, MLX5_CAP_FPGA(fdev->mdev, image_version), MLX5_CAP_FPGA(fdev->mdev, ieee_vendor_id), MLX5_CAP_FPGA(fdev->mdev, sandbox_product_id), @@ -264,6 +282,9 @@ void mlx5_fpga_device_stop(struct mlx5_core_dev *mdev) if (!fdev) return; + if (mlx5_is_fpga_lookaside(MLX5_CAP_FPGA(fdev->mdev, fpga_id))) + return; + spin_lock_irqsave(&fdev->state_lock, flags); if (fdev->state != MLX5_FPGA_STATUS_SUCCESS) { spin_unlock_irqrestore(&fdev->state_lock, flags); -- cgit v1.2.3-59-g8ed1b From 32680da7103439095ba8c2dbe30c3e4d0e05e4c2 Mon Sep 17 00:00:00 2001 From: zhong jiang Date: Fri, 13 Sep 2019 00:59:02 +0800 Subject: net/mlx5: Remove unneeded variable in mlx5_unload_one mlx5_unload_one do not need local variable to store different value, Hence just remove it. Signed-off-by: zhong jiang Acked-by: Saeed Mahameed Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e47dd7c1b909..c9a091d3226c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1228,8 +1228,6 @@ function_teardown: static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup) { - int err = 0; - if (cleanup) { mlx5_unregister_device(dev); mlx5_drain_health_wq(dev); @@ -1257,7 +1255,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup) mlx5_function_teardown(dev, cleanup); out: mutex_unlock(&dev->intf_state_mutex); - return err; + return 0; } static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) -- cgit v1.2.3-59-g8ed1b From 556b9d16d3f53d1e72b988f37501bb7e6d3f358b Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 3 Sep 2019 17:45:47 +0300 Subject: net/mlx5: Clear VF's configuration on disabling SRIOV When setting number of VFs to 0 (disable SRIOV), clear VF's configuration. Signed-off-by: Aya Levin Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 13 ++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 10 +++++----- 4 files changed, 21 insertions(+), 10 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 30aae76b6a1d..89a2806eceb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1831,6 +1831,15 @@ static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw) flush_workqueue(esw->work_queue); } +static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw) +{ + struct mlx5_vport *vport; + int i; + + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) + memset(&vport->info, 0, sizeof(vport->info)); +} + /* Public E-Switch API */ #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev)) @@ -1923,7 +1932,7 @@ abort: return err; } -void mlx5_eswitch_disable(struct mlx5_eswitch *esw) +void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf) { int old_mode; @@ -1952,6 +1961,8 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); } + if (clear_vf) + mlx5_eswitch_clear_vf_vports_info(esw); } int mlx5_eswitch_init(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 6bd6f5895244..804a7ed2b969 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -270,7 +270,7 @@ int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, int mlx5_eswitch_init(struct mlx5_core_dev *dev); void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw); int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode); -void mlx5_eswitch_disable(struct mlx5_eswitch *esw); +void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf); int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, u16 vport, u8 mac[ETH_ALEN]); int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, @@ -603,7 +603,7 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw); static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {} static inline int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) { return 0; } -static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw) {} +static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf) {} static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; } static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; } static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 00d71db15f22..cbd88f42350e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1370,7 +1370,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, return -EINVAL; } - mlx5_eswitch_disable(esw); + mlx5_eswitch_disable(esw, false); mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs); err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS); if (err) { @@ -2196,7 +2196,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, { int err, err1; - mlx5_eswitch_disable(esw); + mlx5_eswitch_disable(esw, false); err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 61fcfd8b39b4..f641f1336402 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -108,7 +108,7 @@ enable_vfs_hca: return 0; } -static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev) +static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev, bool clear_vf) { struct mlx5_core_sriov *sriov = &dev->priv.sriov; int num_vfs = pci_num_vf(dev->pdev); @@ -127,7 +127,7 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev) } if (MLX5_ESWITCH_MANAGER(dev)) - mlx5_eswitch_disable(dev->priv.eswitch); + mlx5_eswitch_disable(dev->priv.eswitch, clear_vf); if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages)) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); @@ -147,7 +147,7 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs) err = pci_enable_sriov(pdev, num_vfs); if (err) { mlx5_core_warn(dev, "pci_enable_sriov failed : %d\n", err); - mlx5_device_disable_sriov(dev); + mlx5_device_disable_sriov(dev, true); } return err; } @@ -157,7 +157,7 @@ static void mlx5_sriov_disable(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); pci_disable_sriov(pdev); - mlx5_device_disable_sriov(dev); + mlx5_device_disable_sriov(dev, true); } int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs) @@ -192,7 +192,7 @@ void mlx5_sriov_detach(struct mlx5_core_dev *dev) if (!mlx5_core_is_pf(dev)) return; - mlx5_device_disable_sriov(dev); + mlx5_device_disable_sriov(dev, false); } static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev) -- cgit v1.2.3-59-g8ed1b From ae2741e2b6ce2bf1b656b1152c4ef147ff35b096 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Wed, 11 Sep 2019 21:14:54 +0300 Subject: net/mlx5e: Verify that rule has at least one fwd/drop action Currently, mlx5 tc layer doesn't verify that rule has at least one forward or drop action which leads to following firmware syndrome when user tries to offload such action: [ 1824.860501] mlx5_core 0000:81:00.0: mlx5_cmd_check:753:(pid 29458): SET_FLOW_TABLE_ENTRY(0x936) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x144b7a) Add check at the end of parse_tc_fdb_actions() that verifies that resulting attribute has action fwd or drop flag set. Signed-off-by: Vlad Buslov Reviewed-by: Paul Blakey Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3e78a727f3e6..8c4bce940bfb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3423,6 +3423,12 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; } + if (!(attr->action & + (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { + NL_SET_ERR_MSG(extack, "Rule must have at least one forward/drop action"); + return -EOPNOTSUPP; + } + if (attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) { NL_SET_ERR_MSG_MOD(extack, "current firmware doesn't support split rule for port mirroring"); -- cgit v1.2.3-59-g8ed1b From 84c7af637512be9c3254189bd5910dae0d2a8602 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Thu, 19 Sep 2019 17:22:19 -0500 Subject: net/mlx5: Do not hold group lock while allocating FTE in software FTE memory allocation using alloc_fte() doesn't have any dependency on the flow group. Hence, do not hold flow group lock while performing alloc_fte(). This helps to reduce contention of flow group lock. Signed-off-by: Parav Pandit Reviewed-by: Daniel Jurgens Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3bbb49354829..e5591f4f19b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1814,6 +1814,13 @@ search_again_locked: return rule; } + fte = alloc_fte(ft, spec, flow_act); + if (IS_ERR(fte)) { + up_write_ref_node(&ft->node, false); + err = PTR_ERR(fte); + goto err_alloc_fte; + } + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); up_write_ref_node(&ft->node, false); @@ -1821,17 +1828,9 @@ search_again_locked: if (err) goto err_release_fg; - fte = alloc_fte(ft, spec, flow_act); - if (IS_ERR(fte)) { - err = PTR_ERR(fte); - goto err_release_fg; - } - err = insert_fte(g, fte); - if (err) { - kmem_cache_free(steering->ftes_cache, fte); + if (err) goto err_release_fg; - } nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); up_write_ref_node(&g->node, false); @@ -1843,6 +1842,8 @@ search_again_locked: err_release_fg: up_write_ref_node(&g->node, false); + kmem_cache_free(steering->ftes_cache, fte); +err_alloc_fte: tree_put_node(&g->node, false); return ERR_PTR(err); } -- cgit v1.2.3-59-g8ed1b From 7dee607ed0e04500459db53001d8e02f8831f084 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 18 Sep 2019 18:50:32 -0500 Subject: net/mlx5: Support lockless FTE read lookups During connection tracking offloads with high number of connections, (40K connections per second), flow table group lock contention is observed. To improve the performance by reducing lock contention, lockless FTE read lookup is performed as described below. Each flow table entry is refcounted. Flow table entry is removed when refcount drops to zero. rhash table allows rcu protected lookup. Each hash table entry insertion and removal is write lock protected. Hence, it is possible to perform lockless lookup in rhash table using following scheme. (a) Guard FTE entry lookup per group using rcu read lock. (b) Before freeing the FTE entry, wait for all readers to finish accessing the FTE. Below example of one reader and write in parallel racing, shows protection in effect with rcu lock. lookup_fte_locked() rcu_read_lock(); search_hash_table() existing_flow_group_write_lock(); tree_put_node(fte) drop_ref_cnt(fte) del_sw_fte(fte) del_hash_table_entry(); call_rcu(); existing_flow_group_write_unlock(); get_ref_cnt(fte) fails rcu_read_unlock(); rcu grace period(); [..] kmem_cache_free(fte); Signed-off-by: Parav Pandit Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 70 ++++++++++++++++++----- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 1 + 2 files changed, 56 insertions(+), 15 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index e5591f4f19b7..0246f5cdd355 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -531,9 +531,16 @@ static void del_hw_fte(struct fs_node *node) } } +static void del_sw_fte_rcu(struct rcu_head *head) +{ + struct fs_fte *fte = container_of(head, struct fs_fte, rcu); + struct mlx5_flow_steering *steering = get_steering(&fte->node); + + kmem_cache_free(steering->ftes_cache, fte); +} + static void del_sw_fte(struct fs_node *node) { - struct mlx5_flow_steering *steering = get_steering(node); struct mlx5_flow_group *fg; struct fs_fte *fte; int err; @@ -546,7 +553,8 @@ static void del_sw_fte(struct fs_node *node) rhash_fte); WARN_ON(err); ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index); - kmem_cache_free(steering->ftes_cache, fte); + + call_rcu(&fte->rcu, del_sw_fte_rcu); } static void del_hw_flow_group(struct fs_node *node) @@ -1623,22 +1631,47 @@ static u64 matched_fgs_get_version(struct list_head *match_head) } static struct fs_fte * -lookup_fte_locked(struct mlx5_flow_group *g, - const u32 *match_value, - bool take_write) +lookup_fte_for_write_locked(struct mlx5_flow_group *g, const u32 *match_value) { struct fs_fte *fte_tmp; - if (take_write) - nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); - else - nested_down_read_ref_node(&g->node, FS_LOCK_PARENT); - fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value, - rhash_fte); + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); + + fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value, rhash_fte); if (!fte_tmp || !tree_get_node(&fte_tmp->node)) { fte_tmp = NULL; goto out; } + + if (!fte_tmp->node.active) { + tree_put_node(&fte_tmp->node, false); + fte_tmp = NULL; + goto out; + } + nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); + +out: + up_write_ref_node(&g->node, false); + return fte_tmp; +} + +static struct fs_fte * +lookup_fte_for_read_locked(struct mlx5_flow_group *g, const u32 *match_value) +{ + struct fs_fte *fte_tmp; + + if (!tree_get_node(&g->node)) + return NULL; + + rcu_read_lock(); + fte_tmp = rhashtable_lookup(&g->ftes_hash, match_value, rhash_fte); + if (!fte_tmp || !tree_get_node(&fte_tmp->node)) { + rcu_read_unlock(); + fte_tmp = NULL; + goto out; + } + rcu_read_unlock(); + if (!fte_tmp->node.active) { tree_put_node(&fte_tmp->node, false); fte_tmp = NULL; @@ -1646,14 +1679,21 @@ lookup_fte_locked(struct mlx5_flow_group *g, } nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); + out: - if (take_write) - up_write_ref_node(&g->node, false); - else - up_read_ref_node(&g->node); + tree_put_node(&g->node, false); return fte_tmp; } +static struct fs_fte * +lookup_fte_locked(struct mlx5_flow_group *g, const u32 *match_value, bool write) +{ + if (write) + return lookup_fte_for_write_locked(g, match_value); + else + return lookup_fte_for_read_locked(g, match_value); +} + static struct mlx5_flow_handle * try_add_to_existing_fg(struct mlx5_flow_table *ft, struct list_head *match_head, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 00717eba2256..f278298b0f6e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -202,6 +202,7 @@ struct fs_fte { enum fs_fte_status status; struct mlx5_fc *counter; struct rhash_head hash; + struct rcu_head rcu; int modify_mask; }; -- cgit v1.2.3-59-g8ed1b From 130c7b46c93d313ca07d85a30d90021e424c7e9b Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 7 May 2019 08:56:38 -0700 Subject: net/mlx5e: TX, Dump WQs wqe descriptors on CQE with error events Dump the Work Queue's TX WQE descriptor when a completion with error is received. Example: [5.331832] mlx5_core 0000:00:04.0 enp0s4: Error cqe on cqn 0xa, ci 0x1, TXQ-SQ qpn 0xe, opcode 0xd, syndrome 0x2, vendor syndrome 0x0 [5.333127] 00000000: 55 65 02 75 31 fe c2 d2 6b 6c 62 1e f9 e1 d8 5c [5.333837] 00000010: d3 b2 6c b8 89 e4 84 20 0b f4 3c e0 f3 75 41 ca [5.334568] 00000020: 46 00 00 00 cd 70 a0 92 18 3a 01 de 00 00 00 00 [5.335313] 00000030: 7d bc 05 89 b2 e9 00 02 1e 00 00 0e 00 00 30 d2 [5.335972] WQE DUMP: WQ size 1024 WQ cur size 0, WQE index 0x0, len: 64 [5.336710] 00000000: 00 00 00 1e 00 00 0e 04 00 00 00 08 00 00 00 00 [5.337524] 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 12 33 33 [5.338151] 00000020: 00 00 00 16 52 54 00 00 00 01 86 dd 60 00 00 00 [5.338740] 00000030: 00 00 00 48 00 00 00 00 00 00 00 00 66 ba 58 14 Signed-off-by: Saeed Mahameed Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 6 ++++++ drivers/net/ethernet/mellanox/mlx5/core/wq.c | 18 ++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/wq.h | 1 + 3 files changed, 25 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index d3a67a9b4eba..29730f52e315 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -458,8 +458,14 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) { if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { + struct mlx5e_tx_wqe_info *wi; + u16 ci; + + ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc); + wi = &sq->db.wqe_info[ci]; mlx5e_dump_error_cqe(sq, (struct mlx5_err_cqe *)cqe); + mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs); queue_work(cq->channel->priv->wq, &sq->recover_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index dd2315ce4441..dab2625e1e59 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -96,6 +96,24 @@ err_db_free: return err; } +void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides) +{ + size_t len; + void *wqe; + + if (!net_ratelimit()) + return; + + nstrides = max_t(u8, nstrides, 1); + + len = nstrides << wq->fbc.log_stride; + wqe = mlx5_wq_cyc_get_wqe(wq, ix); + + pr_info("WQE DUMP: WQ size %d WQ cur size %d, WQE index 0x%x, len: %ld\n", + mlx5_wq_cyc_get_size(wq), wq->cur_sz, ix, len); + print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false); +} + int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 55791f71a778..27338c3c6136 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -79,6 +79,7 @@ struct mlx5_wq_ll { int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl); +void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides); u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq); int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, -- cgit v1.2.3-59-g8ed1b From 769619ee39dfa8297a1fe2bc2865eb1e73a9f824 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 16 Oct 2019 13:29:16 +0300 Subject: net/mlx5: WQ, Move short getters into header file Move short Work Queue API getter functions into the WQ header file. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/wq.c | 20 -------------------- drivers/net/ethernet/mellanox/mlx5/core/wq.h | 24 ++++++++++++++++++++---- 2 files changed, 20 insertions(+), 24 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index dab2625e1e59..f2a0e72285ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -34,26 +34,6 @@ #include "wq.h" #include "mlx5_core.h" -u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq) -{ - return (u32)wq->fbc.sz_m1 + 1; -} - -u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) -{ - return wq->fbc.sz_m1 + 1; -} - -u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq) -{ - return wq->fbc.log_stride; -} - -u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq) -{ - return (u32)wq->fbc.sz_m1 + 1; -} - static u32 wq_get_byte_sz(u8 log_sz, u8 log_stride) { return ((u32)1 << log_sz) << log_stride; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 27338c3c6136..d9a94bc223c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -80,7 +80,6 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl); void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides); -u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq); int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, @@ -89,16 +88,18 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *cqc, struct mlx5_cqwq *wq, struct mlx5_wq_ctrl *wq_ctrl); -u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq); -u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq); int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_ll *wq, struct mlx5_wq_ctrl *wq_ctrl); -u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq); void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl); +static inline u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq) +{ + return (u32)wq->fbc.sz_m1 + 1; +} + static inline int mlx5_wq_cyc_is_full(struct mlx5_wq_cyc *wq) { return wq->cur_sz == wq->sz; @@ -169,6 +170,16 @@ static inline int mlx5_wq_cyc_cc_bigger(u16 cc1, u16 cc2) return !equal && !smaller; } +static inline u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) +{ + return wq->fbc.sz_m1 + 1; +} + +static inline u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq) +{ + return wq->fbc.log_stride; +} + static inline u32 mlx5_cqwq_ctr2ix(struct mlx5_cqwq *wq, u32 ctr) { return ctr & wq->fbc.sz_m1; @@ -225,6 +236,11 @@ static inline struct mlx5_cqe64 *mlx5_cqwq_get_cqe(struct mlx5_cqwq *wq) return cqe; } +static inline u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq) +{ + return (u32)wq->fbc.sz_m1 + 1; +} + static inline int mlx5_wq_ll_is_full(struct mlx5_wq_ll *wq) { return wq->cur_sz == wq->fbc.sz_m1; -- cgit v1.2.3-59-g8ed1b From 88f30bbcbaaa1b124fcc622ff49e3d427da9c96c Mon Sep 17 00:00:00 2001 From: Dmytro Linkin Date: Wed, 2 Oct 2019 07:37:08 +0000 Subject: net/mlx5e: Bit sized fields rewrite support This patch doesn't change any functionality, but is a pre-step for adding support for rewriting of bit-sized fields, like DSCP and ECN in IPv4 header, similar fields in IPv6, etc. Signed-off-by: Dmytro Linkin Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 122 ++++++++++++------------ 1 file changed, 62 insertions(+), 60 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 8c4bce940bfb..67b73a00f8fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2238,13 +2238,14 @@ out_err: struct mlx5_fields { u8 field; - u8 size; + u8 field_bsize; + u32 field_mask; u32 offset; u32 match_offset; }; -#define OFFLOAD(fw_field, size, field, off, match_field) \ - {MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, \ +#define OFFLOAD(fw_field, field_bsize, field_mask, field, off, match_field) \ + {MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, field_bsize, field_mask, \ offsetof(struct pedit_headers, field) + (off), \ MLX5_BYTE_OFF(fte_match_set_lyr_2_4, match_field)} @@ -2262,18 +2263,18 @@ struct mlx5_fields { }) static bool cmp_val_mask(void *valp, void *maskp, void *matchvalp, - void *matchmaskp, int size) + void *matchmaskp, u8 bsize) { bool same = false; - switch (size) { - case sizeof(u8): + switch (bsize) { + case 8: same = SAME_VAL_MASK(u8, valp, maskp, matchvalp, matchmaskp); break; - case sizeof(u16): + case 16: same = SAME_VAL_MASK(u16, valp, maskp, matchvalp, matchmaskp); break; - case sizeof(u32): + case 32: same = SAME_VAL_MASK(u32, valp, maskp, matchvalp, matchmaskp); break; } @@ -2282,41 +2283,42 @@ static bool cmp_val_mask(void *valp, void *maskp, void *matchvalp, } static struct mlx5_fields fields[] = { - OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0, dmac_47_16), - OFFLOAD(DMAC_15_0, 2, eth.h_dest[4], 0, dmac_15_0), - OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0, smac_47_16), - OFFLOAD(SMAC_15_0, 2, eth.h_source[4], 0, smac_15_0), - OFFLOAD(ETHERTYPE, 2, eth.h_proto, 0, ethertype), - OFFLOAD(FIRST_VID, 2, vlan.h_vlan_TCI, 0, first_vid), - - OFFLOAD(IP_TTL, 1, ip4.ttl, 0, ttl_hoplimit), - OFFLOAD(SIPV4, 4, ip4.saddr, 0, src_ipv4_src_ipv6.ipv4_layout.ipv4), - OFFLOAD(DIPV4, 4, ip4.daddr, 0, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), - - OFFLOAD(SIPV6_127_96, 4, ip6.saddr.s6_addr32[0], 0, + OFFLOAD(DMAC_47_16, 32, U32_MAX, eth.h_dest[0], 0, dmac_47_16), + OFFLOAD(DMAC_15_0, 16, U16_MAX, eth.h_dest[4], 0, dmac_15_0), + OFFLOAD(SMAC_47_16, 32, U32_MAX, eth.h_source[0], 0, smac_47_16), + OFFLOAD(SMAC_15_0, 16, U16_MAX, eth.h_source[4], 0, smac_15_0), + OFFLOAD(ETHERTYPE, 16, U16_MAX, eth.h_proto, 0, ethertype), + OFFLOAD(FIRST_VID, 16, U16_MAX, vlan.h_vlan_TCI, 0, first_vid), + + OFFLOAD(IP_TTL, 8, U8_MAX, ip4.ttl, 0, ttl_hoplimit), + OFFLOAD(SIPV4, 32, U32_MAX, ip4.saddr, 0, src_ipv4_src_ipv6.ipv4_layout.ipv4), + OFFLOAD(DIPV4, 32, U32_MAX, ip4.daddr, 0, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), + + OFFLOAD(SIPV6_127_96, 32, U32_MAX, ip6.saddr.s6_addr32[0], 0, src_ipv4_src_ipv6.ipv6_layout.ipv6[0]), - OFFLOAD(SIPV6_95_64, 4, ip6.saddr.s6_addr32[1], 0, + OFFLOAD(SIPV6_95_64, 32, U32_MAX, ip6.saddr.s6_addr32[1], 0, src_ipv4_src_ipv6.ipv6_layout.ipv6[4]), - OFFLOAD(SIPV6_63_32, 4, ip6.saddr.s6_addr32[2], 0, + OFFLOAD(SIPV6_63_32, 32, U32_MAX, ip6.saddr.s6_addr32[2], 0, src_ipv4_src_ipv6.ipv6_layout.ipv6[8]), - OFFLOAD(SIPV6_31_0, 4, ip6.saddr.s6_addr32[3], 0, + OFFLOAD(SIPV6_31_0, 32, U32_MAX, ip6.saddr.s6_addr32[3], 0, src_ipv4_src_ipv6.ipv6_layout.ipv6[12]), - OFFLOAD(DIPV6_127_96, 4, ip6.daddr.s6_addr32[0], 0, + OFFLOAD(DIPV6_127_96, 32, U32_MAX, ip6.daddr.s6_addr32[0], 0, dst_ipv4_dst_ipv6.ipv6_layout.ipv6[0]), - OFFLOAD(DIPV6_95_64, 4, ip6.daddr.s6_addr32[1], 0, + OFFLOAD(DIPV6_95_64, 32, U32_MAX, ip6.daddr.s6_addr32[1], 0, dst_ipv4_dst_ipv6.ipv6_layout.ipv6[4]), - OFFLOAD(DIPV6_63_32, 4, ip6.daddr.s6_addr32[2], 0, + OFFLOAD(DIPV6_63_32, 32, U32_MAX, ip6.daddr.s6_addr32[2], 0, dst_ipv4_dst_ipv6.ipv6_layout.ipv6[8]), - OFFLOAD(DIPV6_31_0, 4, ip6.daddr.s6_addr32[3], 0, + OFFLOAD(DIPV6_31_0, 32, U32_MAX, ip6.daddr.s6_addr32[3], 0, dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]), - OFFLOAD(IPV6_HOPLIMIT, 1, ip6.hop_limit, 0, ttl_hoplimit), + OFFLOAD(IPV6_HOPLIMIT, 8, U8_MAX, ip6.hop_limit, 0, ttl_hoplimit), - OFFLOAD(TCP_SPORT, 2, tcp.source, 0, tcp_sport), - OFFLOAD(TCP_DPORT, 2, tcp.dest, 0, tcp_dport), - OFFLOAD(TCP_FLAGS, 1, tcp.ack_seq, 5, tcp_flags), + OFFLOAD(TCP_SPORT, 16, U16_MAX, tcp.source, 0, tcp_sport), + OFFLOAD(TCP_DPORT, 16, U16_MAX, tcp.dest, 0, tcp_dport), + /* in linux iphdr tcp_flags is 8 bits long */ + OFFLOAD(TCP_FLAGS, 8, U8_MAX, tcp.ack_seq, 5, tcp_flags), - OFFLOAD(UDP_SPORT, 2, udp.source, 0, udp_sport), - OFFLOAD(UDP_DPORT, 2, udp.dest, 0, udp_dport), + OFFLOAD(UDP_SPORT, 16, U16_MAX, udp.source, 0, udp_sport), + OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest, 0, udp_dport), }; /* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at @@ -2329,19 +2331,17 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs, struct netlink_ext_ack *extack) { struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals; - void *headers_c = get_match_headers_criteria(*action_flags, - &parse_attr->spec); - void *headers_v = get_match_headers_value(*action_flags, - &parse_attr->spec); int i, action_size, nactions, max_actions, first, last, next_z; - void *s_masks_p, *a_masks_p, *vals_p; + void *headers_c, *headers_v, *action, *vals_p; + u32 *s_masks_p, *a_masks_p, s_mask, a_mask; struct mlx5_fields *f; - u8 cmd, field_bsize; - u32 s_mask, a_mask; unsigned long mask; __be32 mask_be32; __be16 mask_be16; - void *action; + u8 cmd; + + headers_c = get_match_headers_criteria(*action_flags, &parse_attr->spec); + headers_v = get_match_headers_value(*action_flags, &parse_attr->spec); set_masks = &hdrs[0].masks; add_masks = &hdrs[1].masks; @@ -2366,8 +2366,8 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs, s_masks_p = (void *)set_masks + f->offset; a_masks_p = (void *)add_masks + f->offset; - memcpy(&s_mask, s_masks_p, f->size); - memcpy(&a_mask, a_masks_p, f->size); + s_mask = *s_masks_p & f->field_mask; + a_mask = *a_masks_p & f->field_mask; if (!s_mask && !a_mask) /* nothing to offload here */ continue; @@ -2396,38 +2396,34 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs, vals_p = (void *)set_vals + f->offset; /* don't rewrite if we have a match on the same value */ if (cmp_val_mask(vals_p, s_masks_p, match_val, - match_mask, f->size)) + match_mask, f->field_bsize)) skip = true; /* clear to denote we consumed this field */ - memset(s_masks_p, 0, f->size); + *s_masks_p &= ~f->field_mask; } else { - u32 zero = 0; - cmd = MLX5_ACTION_TYPE_ADD; mask = a_mask; vals_p = (void *)add_vals + f->offset; /* add 0 is no change */ - if (!memcmp(vals_p, &zero, f->size)) + if ((*(u32 *)vals_p & f->field_mask) == 0) skip = true; /* clear to denote we consumed this field */ - memset(a_masks_p, 0, f->size); + *a_masks_p &= ~f->field_mask; } if (skip) continue; - field_bsize = f->size * BITS_PER_BYTE; - - if (field_bsize == 32) { + if (f->field_bsize == 32) { mask_be32 = *(__be32 *)&mask; mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32)); - } else if (field_bsize == 16) { + } else if (f->field_bsize == 16) { mask_be16 = *(__be16 *)&mask; mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16)); } - first = find_first_bit(&mask, field_bsize); - next_z = find_next_zero_bit(&mask, field_bsize, first); - last = find_last_bit(&mask, field_bsize); + first = find_first_bit(&mask, f->field_bsize); + next_z = find_next_zero_bit(&mask, f->field_bsize, first); + last = find_last_bit(&mask, f->field_bsize); if (first < next_z && next_z < last) { NL_SET_ERR_MSG_MOD(extack, "rewrite of few sub-fields isn't supported"); @@ -2440,16 +2436,22 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs, MLX5_SET(set_action_in, action, field, f->field); if (cmd == MLX5_ACTION_TYPE_SET) { - MLX5_SET(set_action_in, action, offset, first); + int start; + + /* if field is bit sized it can start not from first bit */ + start = find_first_bit((unsigned long *)&f->field_mask, + f->field_bsize); + + MLX5_SET(set_action_in, action, offset, first - start); /* length is num of bits to be written, zero means length of 32 */ MLX5_SET(set_action_in, action, length, (last - first + 1)); } - if (field_bsize == 32) + if (f->field_bsize == 32) MLX5_SET(set_action_in, action, data, ntohl(*(__be32 *)vals_p) >> first); - else if (field_bsize == 16) + else if (f->field_bsize == 16) MLX5_SET(set_action_in, action, data, ntohs(*(__be16 *)vals_p) >> first); - else if (field_bsize == 8) + else if (f->field_bsize == 8) MLX5_SET(set_action_in, action, data, *(u8 *)vals_p >> first); action += action_size; -- cgit v1.2.3-59-g8ed1b From ab9341b54969a2d02dbb7819e2f17c2f0d9cf5b5 Mon Sep 17 00:00:00 2001 From: Dmytro Linkin Date: Mon, 7 Oct 2019 10:48:00 +0000 Subject: net/mlx5e: Add ToS (DSCP) header rewrite support Add support for rewriting of DSCP part of ToS field. Next commands, for example, can be used to offload rewrite action: OVS: $ ovs-ofctl add-flow ovs-sriov "ip, in_port=REP, \ actions=mod_nw_tos:68, output:NIC" iproute2 (used retain mask, as tc command rewrite whole ToS field): $ tc filter add dev REP ingress protocol ip prio 1 flower skip_sw \ ip_proto icmp action pedit munge ip tos set 68 retain 0xfc pipe \ action mirred egress redirect dev NIC Signed-off-by: Dmytro Linkin Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 67b73a00f8fa..4b4be896383f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2290,6 +2290,7 @@ static struct mlx5_fields fields[] = { OFFLOAD(ETHERTYPE, 16, U16_MAX, eth.h_proto, 0, ethertype), OFFLOAD(FIRST_VID, 16, U16_MAX, vlan.h_vlan_TCI, 0, first_vid), + OFFLOAD(IP_DSCP, 8, 0xfc, ip4.tos, 0, ip_dscp), OFFLOAD(IP_TTL, 8, U8_MAX, ip4.ttl, 0, ttl_hoplimit), OFFLOAD(SIPV4, 32, U32_MAX, ip4.saddr, 0, src_ipv4_src_ipv6.ipv4_layout.ipv4), OFFLOAD(DIPV4, 32, U32_MAX, ip4.daddr, 0, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), -- cgit v1.2.3-59-g8ed1b From 5a212e0cac548e5e4fb3f2ba1b5b2f6c8949687d Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Thu, 24 Oct 2019 16:23:33 +0800 Subject: net/mlx5: rate limit alloc_ent error messages when debug a bug, which triggers TX hang, and kernel log is spammed with the following info message [ 1172.044764] mlx5_core 0000:21:00.0: cmd_work_handler:930:(pid 8): failed to allocate command entry Signed-off-by: Li RongQing Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index ea934cd02448..34cba97f7bf4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -866,7 +866,7 @@ static void cmd_work_handler(struct work_struct *work) if (!ent->page_queue) { alloc_ret = alloc_ent(cmd); if (alloc_ret < 0) { - mlx5_core_err(dev, "failed to allocate command entry\n"); + mlx5_core_err_rl(dev, "failed to allocate command entry\n"); if (ent->callback) { ent->callback(-EAGAIN, ent->context); mlx5_free_cmd_msg(dev, ent->out); -- cgit v1.2.3-59-g8ed1b From 84d2dbb0aaaf1098aa2c2ca07003bf3f973732ac Mon Sep 17 00:00:00 2001 From: Erez Alfasi Date: Mon, 16 Sep 2019 13:59:58 +0300 Subject: net/mlx5: LAG, Use port enumerators Instead of using explicit array indexes, simply use ports enumerators to make the code more readable. Fixes: 7907f23adc18 ("net/mlx5: Implement RoCE LAG feature") Signed-off-by: Erez Alfasi Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lag.c | 65 +++++++++++++----------- drivers/net/ethernet/mellanox/mlx5/core/lag.h | 5 ++ drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c | 56 ++++++++++---------- 3 files changed, 69 insertions(+), 57 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index c5ef2ff26465..fc0d9583475d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -145,34 +145,35 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker, { *port1 = 1; *port2 = 2; - if (!tracker->netdev_state[0].tx_enabled || - !tracker->netdev_state[0].link_up) { + if (!tracker->netdev_state[MLX5_LAG_P1].tx_enabled || + !tracker->netdev_state[MLX5_LAG_P1].link_up) { *port1 = 2; return; } - if (!tracker->netdev_state[1].tx_enabled || - !tracker->netdev_state[1].link_up) + if (!tracker->netdev_state[MLX5_LAG_P2].tx_enabled || + !tracker->netdev_state[MLX5_LAG_P2].link_up) *port2 = 1; } void mlx5_modify_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker) { - struct mlx5_core_dev *dev0 = ldev->pf[0].dev; + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; u8 v2p_port1, v2p_port2; int err; mlx5_infer_tx_affinity_mapping(tracker, &v2p_port1, &v2p_port2); - if (v2p_port1 != ldev->v2p_map[0] || - v2p_port2 != ldev->v2p_map[1]) { - ldev->v2p_map[0] = v2p_port1; - ldev->v2p_map[1] = v2p_port2; + if (v2p_port1 != ldev->v2p_map[MLX5_LAG_P1] || + v2p_port2 != ldev->v2p_map[MLX5_LAG_P2]) { + ldev->v2p_map[MLX5_LAG_P1] = v2p_port1; + ldev->v2p_map[MLX5_LAG_P2] = v2p_port2; mlx5_core_info(dev0, "modify lag map port 1:%d port 2:%d", - ldev->v2p_map[0], ldev->v2p_map[1]); + ldev->v2p_map[MLX5_LAG_P1], + ldev->v2p_map[MLX5_LAG_P2]); err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2); if (err) @@ -185,16 +186,17 @@ void mlx5_modify_lag(struct mlx5_lag *ldev, static int mlx5_create_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker) { - struct mlx5_core_dev *dev0 = ldev->pf[0].dev; + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; int err; - mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[0], - &ldev->v2p_map[1]); + mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1], + &ldev->v2p_map[MLX5_LAG_P2]); mlx5_core_info(dev0, "lag map port 1:%d port 2:%d", - ldev->v2p_map[0], ldev->v2p_map[1]); + ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2]); - err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[0], ldev->v2p_map[1]); + err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[MLX5_LAG_P1], + ldev->v2p_map[MLX5_LAG_P2]); if (err) mlx5_core_err(dev0, "Failed to create LAG (%d)\n", @@ -207,7 +209,7 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, u8 flags) { bool roce_lag = !!(flags & MLX5_LAG_FLAG_ROCE); - struct mlx5_core_dev *dev0 = ldev->pf[0].dev; + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; int err; err = mlx5_create_lag(ldev, tracker); @@ -229,7 +231,7 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, static int mlx5_deactivate_lag(struct mlx5_lag *ldev) { - struct mlx5_core_dev *dev0 = ldev->pf[0].dev; + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; bool roce_lag = __mlx5_lag_is_roce(ldev); int err; @@ -252,14 +254,15 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev) static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) { - if (!ldev->pf[0].dev || !ldev->pf[1].dev) + if (!ldev->pf[MLX5_LAG_P1].dev || !ldev->pf[MLX5_LAG_P2].dev) return false; #ifdef CONFIG_MLX5_ESWITCH - return mlx5_esw_lag_prereq(ldev->pf[0].dev, ldev->pf[1].dev); + return mlx5_esw_lag_prereq(ldev->pf[MLX5_LAG_P1].dev, + ldev->pf[MLX5_LAG_P2].dev); #else - return (!mlx5_sriov_is_enabled(ldev->pf[0].dev) && - !mlx5_sriov_is_enabled(ldev->pf[1].dev)); + return (!mlx5_sriov_is_enabled(ldev->pf[MLX5_LAG_P1].dev) && + !mlx5_sriov_is_enabled(ldev->pf[MLX5_LAG_P2].dev)); #endif } @@ -285,8 +288,8 @@ static void mlx5_lag_remove_ib_devices(struct mlx5_lag *ldev) static void mlx5_do_bond(struct mlx5_lag *ldev) { - struct mlx5_core_dev *dev0 = ldev->pf[0].dev; - struct mlx5_core_dev *dev1 = ldev->pf[1].dev; + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; struct lag_tracker tracker; bool do_bond, roce_lag; int err; @@ -692,10 +695,11 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev) goto unlock; if (ldev->tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) { - ndev = ldev->tracker.netdev_state[0].tx_enabled ? - ldev->pf[0].netdev : ldev->pf[1].netdev; + ndev = ldev->tracker.netdev_state[MLX5_LAG_P1].tx_enabled ? + ldev->pf[MLX5_LAG_P1].netdev : + ldev->pf[MLX5_LAG_P2].netdev; } else { - ndev = ldev->pf[0].netdev; + ndev = ldev->pf[MLX5_LAG_P1].netdev; } if (ndev) dev_hold(ndev); @@ -717,7 +721,8 @@ bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv) return true; ldev = mlx5_lag_dev_get(dev); - if (!ldev || !__mlx5_lag_is_roce(ldev) || ldev->pf[0].dev == dev) + if (!ldev || !__mlx5_lag_is_roce(ldev) || + ldev->pf[MLX5_LAG_P1].dev == dev) return true; /* If bonded, we do not add an IB device for PF1. */ @@ -746,11 +751,11 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, ldev = mlx5_lag_dev_get(dev); if (ldev && __mlx5_lag_is_roce(ldev)) { num_ports = MLX5_MAX_PORTS; - mdev[0] = ldev->pf[0].dev; - mdev[1] = ldev->pf[1].dev; + mdev[MLX5_LAG_P1] = ldev->pf[MLX5_LAG_P1].dev; + mdev[MLX5_LAG_P2] = ldev->pf[MLX5_LAG_P2].dev; } else { num_ports = 1; - mdev[0] = dev; + mdev[MLX5_LAG_P1] = dev; } for (i = 0; i < num_ports; ++i) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h index 1dea0b1c9826..f1068aac6406 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h @@ -7,6 +7,11 @@ #include "mlx5_core.h" #include "lag_mp.h" +enum { + MLX5_LAG_P1, + MLX5_LAG_P2, +}; + enum { MLX5_LAG_FLAG_ROCE = 1 << 0, MLX5_LAG_FLAG_SRIOV = 1 << 1, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index 13e2944b1274..5169864dd656 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -11,10 +11,11 @@ static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) { - if (!ldev->pf[0].dev || !ldev->pf[1].dev) + if (!ldev->pf[MLX5_LAG_P1].dev || !ldev->pf[MLX5_LAG_P2].dev) return false; - return mlx5_esw_multipath_prereq(ldev->pf[0].dev, ldev->pf[1].dev); + return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev, + ldev->pf[MLX5_LAG_P2].dev); } static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev) @@ -52,36 +53,36 @@ static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev, int port) switch (port) { case 0: - tracker.netdev_state[0].tx_enabled = true; - tracker.netdev_state[1].tx_enabled = true; - tracker.netdev_state[0].link_up = true; - tracker.netdev_state[1].link_up = true; + tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true; + tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true; + tracker.netdev_state[MLX5_LAG_P1].link_up = true; + tracker.netdev_state[MLX5_LAG_P2].link_up = true; break; case 1: - tracker.netdev_state[0].tx_enabled = true; - tracker.netdev_state[0].link_up = true; - tracker.netdev_state[1].tx_enabled = false; - tracker.netdev_state[1].link_up = false; + tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true; + tracker.netdev_state[MLX5_LAG_P1].link_up = true; + tracker.netdev_state[MLX5_LAG_P2].tx_enabled = false; + tracker.netdev_state[MLX5_LAG_P2].link_up = false; break; case 2: - tracker.netdev_state[0].tx_enabled = false; - tracker.netdev_state[0].link_up = false; - tracker.netdev_state[1].tx_enabled = true; - tracker.netdev_state[1].link_up = true; + tracker.netdev_state[MLX5_LAG_P1].tx_enabled = false; + tracker.netdev_state[MLX5_LAG_P1].link_up = false; + tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true; + tracker.netdev_state[MLX5_LAG_P2].link_up = true; break; default: - mlx5_core_warn(ldev->pf[0].dev, "Invalid affinity port %d", - port); + mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev, + "Invalid affinity port %d", port); return; } - if (tracker.netdev_state[0].tx_enabled) - mlx5_notifier_call_chain(ldev->pf[0].dev->priv.events, + if (tracker.netdev_state[MLX5_LAG_P1].tx_enabled) + mlx5_notifier_call_chain(ldev->pf[MLX5_LAG_P1].dev->priv.events, MLX5_DEV_EVENT_PORT_AFFINITY, (void *)0); - if (tracker.netdev_state[1].tx_enabled) - mlx5_notifier_call_chain(ldev->pf[1].dev->priv.events, + if (tracker.netdev_state[MLX5_LAG_P2].tx_enabled) + mlx5_notifier_call_chain(ldev->pf[MLX5_LAG_P2].dev->priv.events, MLX5_DEV_EVENT_PORT_AFFINITY, (void *)0); @@ -141,11 +142,12 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, /* Verify next hops are ports of the same hca */ fib_nh0 = fib_info_nh(fi, 0); fib_nh1 = fib_info_nh(fi, 1); - if (!(fib_nh0->fib_nh_dev == ldev->pf[0].netdev && - fib_nh1->fib_nh_dev == ldev->pf[1].netdev) && - !(fib_nh0->fib_nh_dev == ldev->pf[1].netdev && - fib_nh1->fib_nh_dev == ldev->pf[0].netdev)) { - mlx5_core_warn(ldev->pf[0].dev, "Multipath offload require two ports of the same HCA\n"); + if (!(fib_nh0->fib_nh_dev == ldev->pf[MLX5_LAG_P1].netdev && + fib_nh1->fib_nh_dev == ldev->pf[MLX5_LAG_P2].netdev) && + !(fib_nh0->fib_nh_dev == ldev->pf[MLX5_LAG_P2].netdev && + fib_nh1->fib_nh_dev == ldev->pf[MLX5_LAG_P1].netdev)) { + mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev, + "Multipath offload require two ports of the same HCA\n"); return; } @@ -267,8 +269,8 @@ static int mlx5_lag_fib_event(struct notifier_block *nb, return notifier_from_errno(-EINVAL); } fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev; - if (fib_dev != ldev->pf[0].netdev && - fib_dev != ldev->pf[1].netdev) { + if (fib_dev != ldev->pf[MLX5_LAG_P1].netdev && + fib_dev != ldev->pf[MLX5_LAG_P2].netdev) { return NOTIFY_DONE; } fib_work = mlx5_lag_init_fib_work(ldev, event); -- cgit v1.2.3-59-g8ed1b From 1cdc14e9d134a48d86673fd75a6abcbe0e58a29c Mon Sep 17 00:00:00 2001 From: Erez Alfasi Date: Mon, 16 Sep 2019 14:34:55 +0300 Subject: net/mlx5: LAG, Use affinity type enumerators Instead of using explicit indexes, simply use affinity type enumerators to make the code more readable. Fixes: 544fe7c2e654 ("net/mlx5e: Activate HW multipath and handle port affinity based on FIB events") Signed-off-by: Erez Alfasi Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c | 13 +++++++------ drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h | 6 ++++++ 2 files changed, 13 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index 5169864dd656..b70afa310ad2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -44,7 +44,8 @@ bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) * 2 - set affinity to port 2. * **/ -static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev, int port) +static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev, + enum mlx5_lag_port_affinity port) { struct lag_tracker tracker; @@ -52,19 +53,19 @@ static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev, int port) return; switch (port) { - case 0: + case MLX5_LAG_NORMAL_AFFINITY: tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true; tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true; tracker.netdev_state[MLX5_LAG_P1].link_up = true; tracker.netdev_state[MLX5_LAG_P2].link_up = true; break; - case 1: + case MLX5_LAG_P1_AFFINITY: tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true; tracker.netdev_state[MLX5_LAG_P1].link_up = true; tracker.netdev_state[MLX5_LAG_P2].tx_enabled = false; tracker.netdev_state[MLX5_LAG_P2].link_up = false; break; - case 2: + case MLX5_LAG_P2_AFFINITY: tracker.netdev_state[MLX5_LAG_P1].tx_enabled = false; tracker.netdev_state[MLX5_LAG_P1].link_up = false; tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true; @@ -159,7 +160,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, mlx5_activate_lag(ldev, &tracker, MLX5_LAG_FLAG_MULTIPATH); } - mlx5_lag_set_port_affinity(ldev, 0); + mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY); mp->mfi = fi; } @@ -184,7 +185,7 @@ static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev, } } else if (event == FIB_EVENT_NH_ADD && fib_info_num_path(fi) == 2) { - mlx5_lag_set_port_affinity(ldev, 0); + mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h index 6d14b1100be9..79be89e9c7a4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h @@ -7,6 +7,12 @@ #include "lag.h" #include "mlx5_core.h" +enum mlx5_lag_port_affinity { + MLX5_LAG_NORMAL_AFFINITY, + MLX5_LAG_P1_AFFINITY, + MLX5_LAG_P2_AFFINITY, +}; + struct lag_mp { struct notifier_block fib_nb; struct fib_info *mfi; /* used in tracking fib events */ -- cgit v1.2.3-59-g8ed1b From 667f264676c7f83f57a7695010f889d6fd36dcbf Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Sun, 27 Oct 2019 09:10:17 +0200 Subject: net/mlx5: DR, Support IPv4 and IPv6 mixed matcher Until now SW steering supported matchers that are IPv4 and IPv6. The limitation was mixed matchers in which the outer header IP version was different from the inner header IP version. To support the mixed matcher we create all the possible ste_builder combinations, once we create a rule we select the correct one to be used for rule creation. Signed-off-by: Alex Vesker Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/steering/dr_matcher.c | 65 +++++++++++----------- .../ethernet/mellanox/mlx5/core/steering/dr_rule.c | 13 +++-- .../mellanox/mlx5/core/steering/dr_types.h | 17 ++++-- 3 files changed, 52 insertions(+), 43 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 67dea7698fc9..5db947df8763 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -146,17 +146,15 @@ dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_domain *dmn) int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher, - bool ipv6) + enum mlx5dr_ipv outer_ipv, + enum mlx5dr_ipv inner_ipv) { - if (ipv6) { - nic_matcher->ste_builder = nic_matcher->ste_builder6; - nic_matcher->num_of_builders = nic_matcher->num_of_builders6; - } else { - nic_matcher->ste_builder = nic_matcher->ste_builder4; - nic_matcher->num_of_builders = nic_matcher->num_of_builders4; - } + nic_matcher->ste_builder = + nic_matcher->ste_builder_arr[outer_ipv][inner_ipv]; + nic_matcher->num_of_builders = + nic_matcher->num_of_builders_arr[outer_ipv][inner_ipv]; - if (!nic_matcher->num_of_builders) { + if (!nic_matcher->ste_builder) { mlx5dr_dbg(matcher->tbl->dmn, "Rule not supported on this matcher due to IP related fields\n"); return -EINVAL; @@ -167,26 +165,19 @@ int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher, - bool ipv6) + enum mlx5dr_ipv outer_ipv, + enum mlx5dr_ipv inner_ipv) { struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; struct mlx5dr_domain *dmn = matcher->tbl->dmn; struct mlx5dr_match_param mask = {}; struct mlx5dr_match_misc3 *misc3; struct mlx5dr_ste_build *sb; - u8 *num_of_builders; bool inner, rx; int idx = 0; int ret, i; - if (ipv6) { - sb = nic_matcher->ste_builder6; - num_of_builders = &nic_matcher->num_of_builders6; - } else { - sb = nic_matcher->ste_builder4; - num_of_builders = &nic_matcher->num_of_builders4; - } - + sb = nic_matcher->ste_builder_arr[outer_ipv][inner_ipv]; rx = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX; /* Create a temporary mask to track and clear used mask fields */ @@ -249,7 +240,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (DR_MASK_IS_L2_DST(mask.outer, mask.misc, outer)) mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx); - if (ipv6) { + if (outer_ipv == DR_RULE_IPV6) { if (dr_mask_is_dst_addr_set(&mask.outer)) mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask, inner, rx); @@ -325,7 +316,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (DR_MASK_IS_L2_DST(mask.inner, mask.misc, inner)) mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx); - if (ipv6) { + if (inner_ipv == DR_RULE_IPV6) { if (dr_mask_is_dst_addr_set(&mask.inner)) mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask, inner, rx); @@ -373,7 +364,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, } } - *num_of_builders = idx; + nic_matcher->ste_builder = sb; + nic_matcher->num_of_builders_arr[outer_ipv][inner_ipv] = idx; return 0; } @@ -524,24 +516,33 @@ static void dr_matcher_uninit(struct mlx5dr_matcher *matcher) } } -static int dr_matcher_init_nic(struct mlx5dr_matcher *matcher, - struct mlx5dr_matcher_rx_tx *nic_matcher) +static int dr_matcher_set_all_ste_builders(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher) { struct mlx5dr_domain *dmn = matcher->tbl->dmn; - int ret, ret_v4, ret_v6; - ret_v4 = dr_matcher_set_ste_builders(matcher, nic_matcher, false); - ret_v6 = dr_matcher_set_ste_builders(matcher, nic_matcher, true); + dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV4, DR_RULE_IPV4); + dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV4, DR_RULE_IPV6); + dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV6, DR_RULE_IPV4); + dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV6, DR_RULE_IPV6); - if (ret_v4 && ret_v6) { + if (!nic_matcher->ste_builder) { mlx5dr_dbg(dmn, "Cannot generate IPv4 or IPv6 rules with given mask\n"); return -EINVAL; } - if (!ret_v4) - nic_matcher->ste_builder = nic_matcher->ste_builder4; - else - nic_matcher->ste_builder = nic_matcher->ste_builder6; + return 0; +} + +static int dr_matcher_init_nic(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher) +{ + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + int ret; + + ret = dr_matcher_set_all_ste_builders(matcher, nic_matcher); + if (ret) + return ret; nic_matcher->e_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, DR_CHUNK_SIZE_1, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index e8b656075c6f..90c79a133692 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -954,12 +954,12 @@ static int dr_rule_destroy_rule(struct mlx5dr_rule *rule) return 0; } -static bool dr_rule_is_ipv6(struct mlx5dr_match_param *param) +static enum mlx5dr_ipv dr_rule_get_ipv(struct mlx5dr_match_spec *spec) { - return (param->outer.ip_version == 6 || - param->inner.ip_version == 6 || - param->outer.ethertype == ETH_P_IPV6 || - param->inner.ethertype == ETH_P_IPV6); + if (spec->ip_version == 6 || spec->ethertype == ETH_P_IPV6) + return DR_RULE_IPV6; + + return DR_RULE_IPV4; } static bool dr_rule_skip(enum mlx5dr_domain_type domain, @@ -1023,7 +1023,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, ret = mlx5dr_matcher_select_builders(matcher, nic_matcher, - dr_rule_is_ipv6(param)); + dr_rule_get_ipv(¶m->outer), + dr_rule_get_ipv(¶m->inner)); if (ret) goto out_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index d6d9bc5f4adf..c1f45a60ee6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -106,6 +106,12 @@ enum mlx5dr_action_type { DR_ACTION_TYP_MAX, }; +enum mlx5dr_ipv { + DR_RULE_IPV4, + DR_RULE_IPV6, + DR_RULE_IPV_MAX, +}; + struct mlx5dr_icm_pool; struct mlx5dr_icm_chunk; struct mlx5dr_icm_bucket; @@ -679,11 +685,11 @@ struct mlx5dr_matcher_rx_tx { struct mlx5dr_ste_htbl *s_htbl; struct mlx5dr_ste_htbl *e_anchor; struct mlx5dr_ste_build *ste_builder; - struct mlx5dr_ste_build ste_builder4[DR_RULE_MAX_STES]; - struct mlx5dr_ste_build ste_builder6[DR_RULE_MAX_STES]; + struct mlx5dr_ste_build ste_builder_arr[DR_RULE_IPV_MAX] + [DR_RULE_IPV_MAX] + [DR_RULE_MAX_STES]; u8 num_of_builders; - u8 num_of_builders4; - u8 num_of_builders6; + u8 num_of_builders_arr[DR_RULE_IPV_MAX][DR_RULE_IPV_MAX]; u64 default_icm_addr; struct mlx5dr_table_rx_tx *nic_tbl; }; @@ -812,7 +818,8 @@ mlx5dr_matcher_supp_flex_parser_icmp_v6(struct mlx5dr_cmd_caps *caps) int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher, - bool ipv6); + enum mlx5dr_ipv outer_ipv, + enum mlx5dr_ipv inner_ipv); static inline u32 mlx5dr_icm_pool_chunk_size_to_entries(enum mlx5dr_icm_chunk_size chunk_size) -- cgit v1.2.3-59-g8ed1b From 8b3f2eb038d3098b37715afced1e62bbc72da90f Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 5 Nov 2019 18:27:40 +0000 Subject: net/mlx5: fix kvfree of uninitialized pointer spec Currently when a call to esw_vport_create_legacy_ingress_acl_group fails the error exit path to label 'out' will cause a kvfree on the uninitialized pointer spec. Fix this by ensuring pointer spec is initialized to NULL to avoid this issue. Addresses-Coverity: ("Uninitialized pointer read") Fixes: 10652f39943e ("net/mlx5: Refactor ingress acl configuration") Signed-off-by: Colin Ian King Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 24c2217a4ce8..48627472a691 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1253,7 +1253,7 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, struct mlx5_flow_destination drop_ctr_dst = {0}; struct mlx5_flow_destination *dst = NULL; struct mlx5_flow_act flow_act = {0}; - struct mlx5_flow_spec *spec; + struct mlx5_flow_spec *spec = NULL; int dest_num = 0; int err = 0; u8 *smac_v; -- cgit v1.2.3-59-g8ed1b From 9ea7f01f470a25bb795224cc0ecc57c91a1519c6 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 5 Nov 2019 14:54:16 +0000 Subject: net/mlx5: fix spelling mistake "metdata" -> "metadata" There is a spelling mistake in a esw_warn warning message. Fix it. Signed-off-by: Colin Ian King Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 59eebcae5df6..d8e25416a15d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1878,7 +1878,7 @@ static int esw_vport_create_ingress_acl_group(struct mlx5_eswitch *esw, if (IS_ERR(g)) { ret = PTR_ERR(g); esw_warn(esw->dev, - "Failed to create vport[%d] ingress metdata group, err(%d)\n", + "Failed to create vport[%d] ingress metadata group, err(%d)\n", vport->vport, ret); goto grp_err; } -- cgit v1.2.3-59-g8ed1b From 630d4e75dd2969bf7da40beb3d4704356d12ae39 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Wed, 6 Nov 2019 14:52:31 +0000 Subject: mlxsw: spectrum: Fix error return code in mlxsw_sp_port_module_info_init() Fix to return negative error code -ENOMEM from the error handling case instead of 0, as done elsewhere in this function. Fixes: 4a7f970f1240 ("mlxsw: spectrum: Replace port_to_module array with array of structs") Signed-off-by: Wei Yongjun Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index ea4cc2aa99e0..838c014f6ed1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4079,8 +4079,10 @@ static int mlxsw_sp_port_module_info_init(struct mlxsw_sp *mlxsw_sp) mlxsw_sp->port_mapping[i] = kmemdup(&port_mapping, sizeof(port_mapping), GFP_KERNEL); - if (!mlxsw_sp->port_mapping[i]) + if (!mlxsw_sp->port_mapping[i]) { + err = -ENOMEM; goto err_port_module_info_dup; + } } return 0; -- cgit v1.2.3-59-g8ed1b From dbc684f15818c081421300560dc7edc856a33e73 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 7 Nov 2019 18:42:10 +0200 Subject: mlxsw: Add layer 3 devlink-trap support Add the trap IDs and trap group used to report layer 3 drops. Register layer 3 packet traps and associated layer 3 trap group with devlink during driver initialization. Signed-off-by: Amit Cohen Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 1 + .../net/ethernet/mellanox/mlxsw/spectrum_trap.c | 37 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlxsw/trap.h | 11 +++++++ 3 files changed, 49 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index bec035ee5349..5294a1622643 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5480,6 +5480,7 @@ enum mlxsw_reg_htgt_trap_group { enum mlxsw_reg_htgt_discard_trap_group { MLXSW_REG_HTGT_DISCARD_TRAP_GROUP_BASE = MLXSW_REG_HTGT_TRAP_GROUP_MAX, MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS, + MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS, }; /* reg_htgt_trap_group diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 7c03b661ae7e..f0e6811baa1c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -30,6 +30,16 @@ static struct devlink_trap mlxsw_sp_traps_arr[] = { MLXSW_SP_TRAP_DROP(INGRESS_STP_FILTER, L2_DROPS), MLXSW_SP_TRAP_DROP(EMPTY_TX_LIST, L2_DROPS), MLXSW_SP_TRAP_DROP(PORT_LOOPBACK_FILTER, L2_DROPS), + MLXSW_SP_TRAP_DROP(BLACKHOLE_ROUTE, L3_DROPS), + MLXSW_SP_TRAP_DROP(NON_IP_PACKET, L3_DROPS), + MLXSW_SP_TRAP_DROP(UC_DIP_MC_DMAC, L3_DROPS), + MLXSW_SP_TRAP_DROP(DIP_LB, L3_DROPS), + MLXSW_SP_TRAP_DROP(SIP_MC, L3_DROPS), + MLXSW_SP_TRAP_DROP(SIP_LB, L3_DROPS), + MLXSW_SP_TRAP_DROP(CORRUPTED_IP_HDR, L3_DROPS), + MLXSW_SP_TRAP_DROP(IPV4_SIP_BC, L3_DROPS), + MLXSW_SP_TRAP_DROP(IPV6_MC_DIP_RESERVED_SCOPE, L3_DROPS), + MLXSW_SP_TRAP_DROP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, L3_DROPS), }; static struct mlxsw_listener mlxsw_sp_listeners_arr[] = { @@ -40,6 +50,16 @@ static struct mlxsw_listener mlxsw_sp_listeners_arr[] = { MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_UC, L2_DISCARDS), MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_MC_NULL, L2_DISCARDS), MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_LB, L2_DISCARDS), + MLXSW_SP_RXL_DISCARD(ROUTER2, L3_DISCARDS), + MLXSW_SP_RXL_DISCARD(ING_ROUTER_NON_IP_PACKET, L3_DISCARDS), + MLXSW_SP_RXL_DISCARD(ING_ROUTER_UC_DIP_MC_DMAC, L3_DISCARDS), + MLXSW_SP_RXL_DISCARD(ING_ROUTER_DIP_LB, L3_DISCARDS), + MLXSW_SP_RXL_DISCARD(ING_ROUTER_SIP_MC, L3_DISCARDS), + MLXSW_SP_RXL_DISCARD(ING_ROUTER_SIP_LB, L3_DISCARDS), + MLXSW_SP_RXL_DISCARD(ING_ROUTER_CORRUPTED_IP_HDR, L3_DISCARDS), + MLXSW_SP_RXL_DISCARD(ING_ROUTER_IPV4_SIP_BC, L3_DISCARDS), + MLXSW_SP_RXL_DISCARD(IPV6_MC_DIP_RESERVED_SCOPE, L3_DISCARDS), + MLXSW_SP_RXL_DISCARD(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, L3_DISCARDS), }; /* Mapping between hardware trap and devlink trap. Multiple hardware traps can @@ -54,6 +74,16 @@ static u16 mlxsw_sp_listener_devlink_map[] = { DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST, DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST, DEVLINK_TRAP_GENERIC_ID_PORT_LOOPBACK_FILTER, + DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_ROUTE, + DEVLINK_TRAP_GENERIC_ID_NON_IP_PACKET, + DEVLINK_TRAP_GENERIC_ID_UC_DIP_MC_DMAC, + DEVLINK_TRAP_GENERIC_ID_DIP_LB, + DEVLINK_TRAP_GENERIC_ID_SIP_MC, + DEVLINK_TRAP_GENERIC_ID_SIP_LB, + DEVLINK_TRAP_GENERIC_ID_CORRUPTED_IP_HDR, + DEVLINK_TRAP_GENERIC_ID_IPV4_SIP_BC, + DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_RESERVED_SCOPE, + DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, }; static int mlxsw_sp_rx_listener(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb, @@ -211,6 +241,7 @@ mlxsw_sp_trap_group_policer_init(struct mlxsw_sp *mlxsw_sp, u32 rate; switch (group->id) { + case DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS:/* fall through */ case DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS: policer_id = MLXSW_SP_DISCARD_POLICER_ID; ir_units = MLXSW_REG_QPCR_IR_UNITS_M; @@ -242,6 +273,12 @@ __mlxsw_sp_trap_group_init(struct mlxsw_sp *mlxsw_sp, priority = 0; tc = 1; break; + case DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS: + group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS; + policer_id = MLXSW_SP_DISCARD_POLICER_ID; + priority = 0; + tc = 1; + break; default: return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 7618f084cae9..a4969982fce1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -66,6 +66,7 @@ enum { MLXSW_TRAP_ID_NVE_ENCAP_ARP = 0xBD, MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6, MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7, + MLXSW_TRAP_ID_DISCARD_ROUTER2 = 0x130, MLXSW_TRAP_ID_DISCARD_ING_PACKET_SMAC_MC = 0x140, MLXSW_TRAP_ID_DISCARD_ING_SWITCH_VTAG_ALLOW = 0x148, MLXSW_TRAP_ID_DISCARD_ING_SWITCH_VLAN = 0x149, @@ -73,6 +74,16 @@ enum { MLXSW_TRAP_ID_DISCARD_LOOKUP_SWITCH_UC = 0x150, MLXSW_TRAP_ID_DISCARD_LOOKUP_SWITCH_MC_NULL = 0x151, MLXSW_TRAP_ID_DISCARD_LOOKUP_SWITCH_LB = 0x152, + MLXSW_TRAP_ID_DISCARD_ING_ROUTER_NON_IP_PACKET = 0x160, + MLXSW_TRAP_ID_DISCARD_ING_ROUTER_UC_DIP_MC_DMAC = 0x161, + MLXSW_TRAP_ID_DISCARD_ING_ROUTER_DIP_LB = 0x162, + MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_MC = 0x163, + MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_LB = 0x165, + MLXSW_TRAP_ID_DISCARD_ING_ROUTER_CORRUPTED_IP_HDR = 0x167, + MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_SIP_BC = 0x16A, + MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_DIP_LOCAL_NET = 0x16B, + MLXSW_TRAP_ID_DISCARD_IPV6_MC_DIP_RESERVED_SCOPE = 0x1B0, + MLXSW_TRAP_ID_DISCARD_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE = 0x1B1, MLXSW_TRAP_ID_ACL0 = 0x1C0, /* Multicast trap used for routes with trap action */ MLXSW_TRAP_ID_ACL1 = 0x1C1, -- cgit v1.2.3-59-g8ed1b From 21151f64a458bef8308d57cc08551e043d20ace0 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 7 Nov 2019 18:42:15 +0200 Subject: mlxsw: Add new FIB entry type for reject routes Currently, packets that cannot be routed in hardware (e.g., nexthop device is not upper of mlxsw), are trapped to the kernel for forwarding. Such packets are trapped using "RTR_INGRESS0" trap. This trap also traps packets that hit reject routes (e.g., "unreachable") so that the kernel will generate the appropriate ICMP error message for them. Subsequent patch will need to only report to devlink packets that hit a reject route, which is impossible as long as "RTR_INGRESS0" is overloaded like that. Solve this by using "RTR_INGRESS1" trap for packets that hit reject routes. Signed-off-by: Amit Cohen Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 + .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 25 ++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlxsw/trap.h | 1 + 3 files changed, 25 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 838c014f6ed1..f7b29872db6c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4515,6 +4515,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MARK(MTUERROR, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_MARK(TTLERROR, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_L3_MARK(LBERROR, MIRROR_TO_CPU, LBERROR, false), + MLXSW_SP_RXL_MARK(RTR_INGRESS1, TRAP_TO_CPU, REMOTE_ROUTE, false), MLXSW_SP_RXL_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false), MLXSW_SP_RXL_MARK(IPV6_UNSPECIFIED_ADDRESS, TRAP_TO_CPU, ROUTER_EXP, false), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 0e99b64450ca..39c573b39faf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -367,6 +367,7 @@ enum mlxsw_sp_fib_entry_type { MLXSW_SP_FIB_ENTRY_TYPE_LOCAL, MLXSW_SP_FIB_ENTRY_TYPE_TRAP, MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE, + MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE, /* This is a special case of local delivery, where a packet should be * decapsulated on reception. Note that there is no corresponding ENCAP, @@ -4273,6 +4274,23 @@ static int mlxsw_sp_fib_entry_op_blackhole(struct mlxsw_sp *mlxsw_sp, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } +static int +mlxsw_sp_fib_entry_op_unreachable(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) +{ + enum mlxsw_reg_ralue_trap_action trap_action; + char ralue_pl[MLXSW_REG_RALUE_LEN]; + u16 trap_id; + + trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; + trap_id = MLXSW_TRAP_ID_RTR_INGRESS1; + + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); + mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); +} + static int mlxsw_sp_fib_entry_op_ipip_decap(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, @@ -4314,6 +4332,9 @@ static int __mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE: return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, fib_entry, op); + case MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE: + return mlxsw_sp_fib_entry_op_unreachable(mlxsw_sp, fib_entry, + op); case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp, fib_entry, op); @@ -4391,7 +4412,7 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, * can do so with a lower priority than packets directed * at the host, so use action type local instead of trap. */ - fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE; return 0; case RTN_UNICAST: if (mlxsw_sp_fi_is_gateway(mlxsw_sp, fi)) @@ -5351,7 +5372,7 @@ static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, else if (rt->fib6_type == RTN_BLACKHOLE) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE; else if (rt->fib6_flags & RTF_REJECT) - fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE; else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt)) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; else diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index a4969982fce1..b7d83c67491f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -49,6 +49,7 @@ enum { MLXSW_TRAP_ID_IPV6_DHCP = 0x69, MLXSW_TRAP_ID_IPV6_ALL_ROUTERS_LINK = 0x6F, MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70, + MLXSW_TRAP_ID_RTR_INGRESS1 = 0x71, MLXSW_TRAP_ID_IPV6_PIM = 0x79, MLXSW_TRAP_ID_IPV6_VRRP = 0x7A, MLXSW_TRAP_ID_IPV4_BGP = 0x88, -- cgit v1.2.3-59-g8ed1b From 0c3cbbf96def619ef1c766c53a7db5f3602898df Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 7 Nov 2019 18:42:16 +0200 Subject: mlxsw: Add specific trap for packets routed via invalid nexthops Currently, mlxsw does not differentiate between these two cases of routes with invalid nexthops: 1. Nexthops whose nexthop device is a mlxsw upper (has a RIF), but whose neighbour could not be resolved 2. Nexthops whose nexthop device is not a mlxsw upper (e.g., management interface) Up until now this did not matter and mlxsw trapped packets for both cases using the same trap ID. However, packets that should have been routed in hardware (case 1), but incurred a problem are considered exceptions and should be reported to the user. The two cases should therefore be split between two different trap IDs. Allocate a new adjacency entry during initialization and upon the insertion of the first route with an invalid mlxsw nexthop, program this entry to discard packets. Packets hitting this entry will be reported using new trap ID - "DISCARD_ROUTER3". In the future, the entry could be written during initialization, but currently firmware requires a valid RIF, which is not available at this stage. Signed-off-by: Amit Cohen Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 ++ .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 36 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlxsw/trap.h | 1 + 3 files changed, 39 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index f7b29872db6c..d9bcb3b8d032 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4528,6 +4528,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MARK(IPV6_OSPF, TRAP_TO_CPU, OSPF, false), MLXSW_SP_RXL_MARK(IPV6_DHCP, TRAP_TO_CPU, DHCP, false), MLXSW_SP_RXL_MARK(RTR_INGRESS0, TRAP_TO_CPU, REMOTE_ROUTE, false), + MLXSW_SP_RXL_MARK(DISCARD_ROUTER3, TRAP_EXCEPTION_TO_CPU, REMOTE_ROUTE, + false), MLXSW_SP_RXL_MARK(IPV4_BGP, TRAP_TO_CPU, BGP, false), MLXSW_SP_RXL_MARK(IPV6_BGP, TRAP_TO_CPU, BGP, false), MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_SOLICITATION, TRAP_TO_CPU, IPV6_ND, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 39c573b39faf..1aa436054490 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -77,6 +77,7 @@ struct mlxsw_sp_router { struct notifier_block inet6addr_nb; const struct mlxsw_sp_rif_ops **rif_ops_arr; const struct mlxsw_sp_ipip_ops **ipip_ops_arr; + u32 adj_discard_index; }; struct mlxsw_sp_rif { @@ -4197,15 +4198,31 @@ mlxsw_sp_fib_entry_ralue_pack(char *ralue_pl, } } +static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp, u16 rif_index) +{ + u32 adj_discard_index = mlxsw_sp->router->adj_discard_index; + enum mlxsw_reg_ratr_trap_action trap_action; + char ratr_pl[MLXSW_REG_RATR_LEN]; + + trap_action = MLXSW_REG_RATR_TRAP_ACTION_DISCARD_ERRORS; + mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, + MLXSW_REG_RATR_TYPE_ETHERNET, adj_discard_index, + rif_index); + mlxsw_reg_ratr_trap_action_set(ratr_pl, trap_action); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); +} + static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, enum mlxsw_reg_ralue_op op) { + struct mlxsw_sp_nexthop_group *nh_group = fib_entry->nh_group; char ralue_pl[MLXSW_REG_RALUE_LEN]; enum mlxsw_reg_ralue_trap_action trap_action; u16 trap_id = 0; u32 adjacency_index = 0; u16 ecmp_size = 0; + int err; /* In case the nexthop group adjacency index is valid, use it * with provided ECMP size. Otherwise, setup trap and pass @@ -4215,6 +4232,15 @@ static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; adjacency_index = fib_entry->nh_group->adj_index; ecmp_size = fib_entry->nh_group->ecmp_size; + } else if (!nh_group->adj_index_valid && nh_group->count && + nh_group->nh_rif) { + err = mlxsw_sp_adj_discard_write(mlxsw_sp, + nh_group->nh_rif->rif_index); + if (err) + return err; + trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; + adjacency_index = mlxsw_sp->router->adj_discard_index; + ecmp_size = 1; } else { trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; @@ -8144,6 +8170,11 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_neigh_init; + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + &router->adj_discard_index); + if (err) + goto err_adj_discard_index_alloc; + mlxsw_sp->router->netevent_nb.notifier_call = mlxsw_sp_router_netevent_event; err = register_netevent_notifier(&mlxsw_sp->router->netevent_nb); @@ -8172,6 +8203,9 @@ err_dscp_init: err_mp_hash_init: unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); err_register_netevent_notifier: + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + router->adj_discard_index); +err_adj_discard_index_alloc: mlxsw_sp_neigh_fini(mlxsw_sp); err_neigh_init: mlxsw_sp_vrs_fini(mlxsw_sp); @@ -8203,6 +8237,8 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->fib_nb); unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + mlxsw_sp->router->adj_discard_index); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); mlxsw_sp_mr_fini(mlxsw_sp); diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index b7d83c67491f..b84b7f07dce2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -68,6 +68,7 @@ enum { MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6, MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7, MLXSW_TRAP_ID_DISCARD_ROUTER2 = 0x130, + MLXSW_TRAP_ID_DISCARD_ROUTER3 = 0x131, MLXSW_TRAP_ID_DISCARD_ING_PACKET_SMAC_MC = 0x140, MLXSW_TRAP_ID_DISCARD_ING_SWITCH_VTAG_ALLOW = 0x148, MLXSW_TRAP_ID_DISCARD_ING_SWITCH_VLAN = 0x149, -- cgit v1.2.3-59-g8ed1b From fd74feeb2452c94f6e381e1fcef00d69b55723b8 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 7 Nov 2019 18:42:17 +0200 Subject: mlxsw: Add layer 3 devlink-trap exceptions support Add the trap IDs used to report layer 3 exceptions. Trapped packets are first reported to devlink and then injected to the kernel's receive path. All the packets have 'offload_fwd_mark' set in order to prevent them from potentially being forwarded by the bridge again. Signed-off-by: Amit Cohen Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 8 --- .../net/ethernet/mellanox/mlxsw/spectrum_trap.c | 63 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlxsw/trap.h | 2 + 3 files changed, 65 insertions(+), 8 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index d9bcb3b8d032..471478eb1d86 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4512,10 +4512,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_NO_MARK(IPV6_MLDV2_LISTENER_REPORT, TRAP_TO_CPU, IPV6_MLD, false), /* L3 traps */ - MLXSW_SP_RXL_MARK(MTUERROR, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_MARK(TTLERROR, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_L3_MARK(LBERROR, MIRROR_TO_CPU, LBERROR, false), - MLXSW_SP_RXL_MARK(RTR_INGRESS1, TRAP_TO_CPU, REMOTE_ROUTE, false), MLXSW_SP_RXL_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false), MLXSW_SP_RXL_MARK(IPV6_UNSPECIFIED_ADDRESS, TRAP_TO_CPU, ROUTER_EXP, false), @@ -4528,8 +4525,6 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MARK(IPV6_OSPF, TRAP_TO_CPU, OSPF, false), MLXSW_SP_RXL_MARK(IPV6_DHCP, TRAP_TO_CPU, DHCP, false), MLXSW_SP_RXL_MARK(RTR_INGRESS0, TRAP_TO_CPU, REMOTE_ROUTE, false), - MLXSW_SP_RXL_MARK(DISCARD_ROUTER3, TRAP_EXCEPTION_TO_CPU, REMOTE_ROUTE, - false), MLXSW_SP_RXL_MARK(IPV4_BGP, TRAP_TO_CPU, BGP, false), MLXSW_SP_RXL_MARK(IPV6_BGP, TRAP_TO_CPU, BGP, false), MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_SOLICITATION, TRAP_TO_CPU, IPV6_ND, @@ -4543,8 +4538,6 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MARK(L3_IPV6_REDIRECTION, TRAP_TO_CPU, IPV6_ND, false), MLXSW_SP_RXL_MARK(IPV6_MC_LINK_LOCAL_DEST, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_MARK(HOST_MISS_IPV4, TRAP_TO_CPU, HOST_MISS, false), - MLXSW_SP_RXL_MARK(HOST_MISS_IPV6, TRAP_TO_CPU, HOST_MISS, false), MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false), MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false), @@ -4559,7 +4552,6 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { /* Multicast Router Traps */ MLXSW_SP_RXL_MARK(IPV4_PIM, TRAP_TO_CPU, PIM, false), MLXSW_SP_RXL_MARK(IPV6_PIM, TRAP_TO_CPU, PIM, false), - MLXSW_SP_RXL_MARK(RPF, TRAP_TO_CPU, RPF, false), MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false), MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false), /* NVE traps */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index f0e6811baa1c..e0d7c49ffae0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -13,16 +13,27 @@ static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port, void *priv); +static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port, + void *trap_ctx); #define MLXSW_SP_TRAP_DROP(_id, _group_id) \ DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ MLXSW_SP_TRAP_METADATA) +#define MLXSW_SP_TRAP_EXCEPTION(_id, _group_id) \ + DEVLINK_TRAP_GENERIC(EXCEPTION, TRAP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + MLXSW_SP_TRAP_METADATA) + #define MLXSW_SP_RXL_DISCARD(_id, _group_id) \ MLXSW_RXL(mlxsw_sp_rx_drop_listener, DISCARD_##_id, SET_FW_DEFAULT, \ false, SP_##_group_id, DISCARD) +#define MLXSW_SP_RXL_EXCEPTION(_id, _group_id, _action) \ + MLXSW_RXL(mlxsw_sp_rx_exception_listener, _id, \ + _action, false, SP_##_group_id, DISCARD) + static struct devlink_trap mlxsw_sp_traps_arr[] = { MLXSW_SP_TRAP_DROP(SMAC_MC, L2_DROPS), MLXSW_SP_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS), @@ -40,6 +51,13 @@ static struct devlink_trap mlxsw_sp_traps_arr[] = { MLXSW_SP_TRAP_DROP(IPV4_SIP_BC, L3_DROPS), MLXSW_SP_TRAP_DROP(IPV6_MC_DIP_RESERVED_SCOPE, L3_DROPS), MLXSW_SP_TRAP_DROP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, L3_DROPS), + MLXSW_SP_TRAP_EXCEPTION(MTU_ERROR, L3_DROPS), + MLXSW_SP_TRAP_EXCEPTION(TTL_ERROR, L3_DROPS), + MLXSW_SP_TRAP_EXCEPTION(RPF, L3_DROPS), + MLXSW_SP_TRAP_EXCEPTION(REJECT_ROUTE, L3_DROPS), + MLXSW_SP_TRAP_EXCEPTION(UNRESOLVED_NEIGH, L3_DROPS), + MLXSW_SP_TRAP_EXCEPTION(IPV4_LPM_UNICAST_MISS, L3_DROPS), + MLXSW_SP_TRAP_EXCEPTION(IPV6_LPM_UNICAST_MISS, L3_DROPS), }; static struct mlxsw_listener mlxsw_sp_listeners_arr[] = { @@ -60,6 +78,18 @@ static struct mlxsw_listener mlxsw_sp_listeners_arr[] = { MLXSW_SP_RXL_DISCARD(ING_ROUTER_IPV4_SIP_BC, L3_DISCARDS), MLXSW_SP_RXL_DISCARD(IPV6_MC_DIP_RESERVED_SCOPE, L3_DISCARDS), MLXSW_SP_RXL_DISCARD(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, L3_DISCARDS), + MLXSW_SP_RXL_EXCEPTION(MTUERROR, ROUTER_EXP, TRAP_TO_CPU), + MLXSW_SP_RXL_EXCEPTION(TTLERROR, ROUTER_EXP, TRAP_TO_CPU), + MLXSW_SP_RXL_EXCEPTION(RPF, RPF, TRAP_TO_CPU), + MLXSW_SP_RXL_EXCEPTION(RTR_INGRESS1, REMOTE_ROUTE, TRAP_TO_CPU), + MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV4, HOST_MISS, TRAP_TO_CPU), + MLXSW_SP_RXL_EXCEPTION(HOST_MISS_IPV6, HOST_MISS, TRAP_TO_CPU), + MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER3, REMOTE_ROUTE, + TRAP_EXCEPTION_TO_CPU), + MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM4, ROUTER_EXP, + TRAP_EXCEPTION_TO_CPU), + MLXSW_SP_RXL_EXCEPTION(DISCARD_ROUTER_LPM6, ROUTER_EXP, + TRAP_EXCEPTION_TO_CPU), }; /* Mapping between hardware trap and devlink trap. Multiple hardware traps can @@ -84,6 +114,15 @@ static u16 mlxsw_sp_listener_devlink_map[] = { DEVLINK_TRAP_GENERIC_ID_IPV4_SIP_BC, DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_RESERVED_SCOPE, DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, + DEVLINK_TRAP_GENERIC_ID_MTU_ERROR, + DEVLINK_TRAP_GENERIC_ID_TTL_ERROR, + DEVLINK_TRAP_GENERIC_ID_RPF, + DEVLINK_TRAP_GENERIC_ID_REJECT_ROUTE, + DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH, + DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH, + DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH, + DEVLINK_TRAP_GENERIC_ID_IPV4_LPM_UNICAST_MISS, + DEVLINK_TRAP_GENERIC_ID_IPV6_LPM_UNICAST_MISS, }; static int mlxsw_sp_rx_listener(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb, @@ -134,6 +173,30 @@ static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port, consume_skb(skb); } +static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port, + void *trap_ctx) +{ + struct devlink_port *in_devlink_port; + struct mlxsw_sp_port *mlxsw_sp_port; + struct mlxsw_sp *mlxsw_sp; + struct devlink *devlink; + + mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + + if (mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port)) + return; + + devlink = priv_to_devlink(mlxsw_sp->core); + in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, + local_port); + skb_push(skb, ETH_HLEN); + devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port); + skb_pull(skb, ETH_HLEN); + skb->offload_fwd_mark = 1; + netif_receive_skb(skb); +} + int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index b84b7f07dce2..0c1c142bb6b0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -84,6 +84,8 @@ enum { MLXSW_TRAP_ID_DISCARD_ING_ROUTER_CORRUPTED_IP_HDR = 0x167, MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_SIP_BC = 0x16A, MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_DIP_LOCAL_NET = 0x16B, + MLXSW_TRAP_ID_DISCARD_ROUTER_LPM4 = 0x17B, + MLXSW_TRAP_ID_DISCARD_ROUTER_LPM6 = 0x17C, MLXSW_TRAP_ID_DISCARD_IPV6_MC_DIP_RESERVED_SCOPE = 0x1B0, MLXSW_TRAP_ID_DISCARD_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE = 0x1B1, MLXSW_TRAP_ID_ACL0 = 0x1C0, -- cgit v1.2.3-59-g8ed1b From a0c76345e3d3dbc40c39de2e00d15a3b7eef7885 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 8 Nov 2019 21:42:43 +0100 Subject: devlink: disallow reload operation during device cleanup There is a race between driver code that does setup/cleanup of device and devlink reload operation that in some drivers works with the same code. Use after free could we easily obtained by running: while true; do echo 10 > /sys/bus/netdevsim/new_device devlink dev reload netdevsim/netdevsim10 & echo 10 > /sys/bus/netdevsim/del_device done Fix this by enabling reload only after setup of device is complete and disabling it at the beginning of the cleanup process. Reported-by: Ido Schimmel Fixes: 2d8dc5bbf4e7 ("devlink: Add support for reload") Signed-off-by: Jiri Pirko Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/main.c | 3 +++ drivers/net/ethernet/mellanox/mlxsw/core.c | 6 ++++- drivers/net/netdevsim/dev.c | 3 +++ include/net/devlink.h | 7 +++-- net/core/devlink.c | 42 +++++++++++++++++++++++++++++- 5 files changed, 57 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 22c72fb7206a..77f056b0895e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4015,6 +4015,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_params_unregister; devlink_params_publish(devlink); + devlink_reload_enable(devlink); pci_save_state(pdev); return 0; @@ -4126,6 +4127,8 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; + devlink_reload_disable(devlink); + if (mlx4_is_slave(dev)) persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e1a90f5bddd0..da436a6aad2f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1198,8 +1198,10 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (err) goto err_thermal_init; - if (mlxsw_driver->params_register) + if (mlxsw_driver->params_register) { devlink_params_publish(devlink); + devlink_reload_enable(devlink); + } return 0; @@ -1263,6 +1265,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); + if (!reload) + devlink_reload_disable(devlink); if (devlink_is_reload_failed(devlink)) { if (!reload) /* Only the parts that were not de-initialized in the diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 3da96c7e8265..059711edfc61 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -820,6 +820,7 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) goto err_bpf_dev_exit; devlink_params_publish(devlink); + devlink_reload_enable(devlink); return 0; err_bpf_dev_exit: @@ -865,6 +866,8 @@ void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev) struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); struct devlink *devlink = priv_to_devlink(nsim_dev); + devlink_reload_disable(devlink); + nsim_dev_reload_destroy(nsim_dev); nsim_bpf_dev_exit(nsim_dev); diff --git a/include/net/devlink.h b/include/net/devlink.h index 8d6b5846822c..7891611868e4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -38,8 +38,9 @@ struct devlink { struct device *dev; possible_net_t _net; struct mutex lock; - bool reload_failed; - bool registered; + u8 reload_failed:1, + reload_enabled:1, + registered:1; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -824,6 +825,8 @@ void devlink_net_set(struct devlink *devlink, struct net *net); struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); int devlink_register(struct devlink *devlink, struct device *dev); void devlink_unregister(struct devlink *devlink); +void devlink_reload_enable(struct devlink *devlink); +void devlink_reload_disable(struct devlink *devlink); void devlink_free(struct devlink *devlink); int devlink_port_register(struct devlink *devlink, struct devlink_port *devlink_port, diff --git a/net/core/devlink.c b/net/core/devlink.c index ff53f7d29dea..2e027c9436e0 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2791,6 +2791,9 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, { int err; + if (!devlink->reload_enabled) + return -EOPNOTSUPP; + err = devlink->ops->reload_down(devlink, !!dest_net, extack); if (err) return err; @@ -6308,12 +6311,49 @@ EXPORT_SYMBOL_GPL(devlink_register); void devlink_unregister(struct devlink *devlink) { mutex_lock(&devlink_mutex); + WARN_ON(devlink_reload_supported(devlink) && + devlink->reload_enabled); devlink_notify(devlink, DEVLINK_CMD_DEL); list_del(&devlink->list); mutex_unlock(&devlink_mutex); } EXPORT_SYMBOL_GPL(devlink_unregister); +/** + * devlink_reload_enable - Enable reload of devlink instance + * + * @devlink: devlink + * + * Should be called at end of device initialization + * process when reload operation is supported. + */ +void devlink_reload_enable(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + devlink->reload_enabled = true; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_reload_enable); + +/** + * devlink_reload_disable - Disable reload of devlink instance + * + * @devlink: devlink + * + * Should be called at the beginning of device cleanup + * process when reload operation is supported. + */ +void devlink_reload_disable(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + /* Mutex is taken which ensures that no reload operation is in + * progress while setting up forbidded flag. + */ + devlink->reload_enabled = false; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_reload_disable); + /** * devlink_free - Free devlink instance resources * @@ -8201,7 +8241,7 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net) if (WARN_ON(!devlink_reload_supported(devlink))) continue; err = devlink_reload(devlink, &init_net, NULL); - if (err) + if (err && err != -EOPNOTSUPP) pr_warn("Failed to reload devlink instance into init_net\n"); } } -- cgit v1.2.3-59-g8ed1b From cc9defcbb8fae52810f7795b039223edae51ef95 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Fri, 8 Nov 2019 23:45:24 +0000 Subject: net/mlx5: Handle "enable_roce" devlink param Register "enable_roce" param, default value is RoCE enabled. Current configuration is stored on mlx5_core_dev and exposed to user through the cmode runtime devlink param. Changing configuration requires changing the cmode driverinit devlink param and calling devlink reload. Signed-off-by: Michael Guralnik Acked-by: Jiri Pirko Signed-off-by: Saeed Mahameed --- .../networking/device_drivers/mellanox/mlx5.rst | 21 +++++++++++++++++++++ Documentation/networking/devlink-params-mlx5.txt | 5 +++++ drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 22 ++++++++++++++++++++++ include/linux/mlx5/driver.h | 11 +++++++++++ 4 files changed, 59 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/Documentation/networking/device_drivers/mellanox/mlx5.rst b/Documentation/networking/device_drivers/mellanox/mlx5.rst index d071c6b49e1f..7599dceba9f1 100644 --- a/Documentation/networking/device_drivers/mellanox/mlx5.rst +++ b/Documentation/networking/device_drivers/mellanox/mlx5.rst @@ -154,6 +154,27 @@ User command examples: values: cmode runtime value smfs +enable_roce: RoCE enablement state +---------------------------------- +RoCE enablement state controls driver support for RoCE traffic. +When RoCE is disabled, there is no gid table, only raw ethernet QPs are supported and traffic on the well known UDP RoCE port is handled as raw ethernet traffic. + +To change RoCE enablement state a user must change the driverinit cmode value and run devlink reload. + +User command examples: + +- Disable RoCE:: + + $ devlink dev param set pci/0000:06:00.0 name enable_roce value false cmode driverinit + $ devlink dev reload pci/0000:06:00.0 + +- Read RoCE enablement state:: + + $ devlink dev param show pci/0000:06:00.0 name enable_roce + pci/0000:06:00.0: + name enable_roce type generic + values: + cmode driverinit value true Devlink health reporters ======================== diff --git a/Documentation/networking/devlink-params-mlx5.txt b/Documentation/networking/devlink-params-mlx5.txt index 8c0b82d655dc..5071467118bd 100644 --- a/Documentation/networking/devlink-params-mlx5.txt +++ b/Documentation/networking/devlink-params-mlx5.txt @@ -10,3 +10,8 @@ flow_steering_mode [DEVICE, DRIVER-SPECIFIC] without firmware intervention. Type: String Configuration mode: runtime + +enable_roce [DEVICE, GENERIC] + Enable handling of RoCE traffic in the device. + Defaultly enabled. + Configuration mode: driverinit diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 381925c90d94..b2c26388edb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -177,12 +177,29 @@ enum mlx5_devlink_param_id { MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, }; +static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + bool new_state = val.vbool; + + if (new_state && !MLX5_CAP_GEN(dev, roce)) { + NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE"); + return -EOPNOTSUPP; + } + + return 0; +} + static const struct devlink_param mlx5_devlink_params[] = { DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, "flow_steering_mode", DEVLINK_PARAM_TYPE_STRING, BIT(DEVLINK_PARAM_CMODE_RUNTIME), mlx5_devlink_fs_mode_get, mlx5_devlink_fs_mode_set, mlx5_devlink_fs_mode_validate), + DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, mlx5_devlink_enable_roce_validate), }; static void mlx5_devlink_set_params_init_values(struct devlink *devlink) @@ -197,6 +214,11 @@ static void mlx5_devlink_set_params_init_values(struct devlink *devlink) devlink_param_driverinit_value_set(devlink, MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, value); + + value.vbool = MLX5_CAP_GEN(dev, roce); + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + value); } int mlx5_devlink_register(struct devlink *devlink, struct device *dev) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7b4801e96feb..1884513aac90 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1191,4 +1191,15 @@ enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; +static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(dev); + union devlink_param_value val; + + devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + &val); + return val.vbool; +} + #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3-59-g8ed1b From 5b67a3ed4fe3f859045cfcc5b1dbd80d058075b5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sun, 10 Nov 2019 16:31:44 +0100 Subject: mlxsw: core: Enable devlink reload only on probe Call devlink enable only during probe time and avoid deadlock during reload. Reported-by: Shalom Toledo Fixes: a0c76345e3d3 ("devlink: disallow reload operation during device cleanup") Signed-off-by: Jiri Pirko Tested-by: Shalom Toledo Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index da436a6aad2f..42e1ce3e39e1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1198,10 +1198,11 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (err) goto err_thermal_init; - if (mlxsw_driver->params_register) { + if (mlxsw_driver->params_register) devlink_params_publish(devlink); + + if (!reload) devlink_reload_enable(devlink); - } return 0; -- cgit v1.2.3-59-g8ed1b From 5aa4165c60aaade3aebe0c5278111781142a5636 Mon Sep 17 00:00:00 2001 From: Shalom Toledo Date: Tue, 12 Nov 2019 08:48:24 +0200 Subject: mlxsw: core: Parse TLVs' offsets of incoming EMADs Until now the code assumes a fixed structure which makes it difficult to support EMADs with and without new TLVs. Make it more generic by parsing the TLVs when the EMADs are received and store the offset to the different TLVs in the control block. Using these offsets to extract information from the EMADs without relying on a specific structure. Signed-off-by: Shalom Toledo Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 53 +++++++++++++++++++++++------- 1 file changed, 42 insertions(+), 11 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 42e1ce3e39e1..698c7bcb1aad 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -361,20 +361,45 @@ static void mlxsw_emad_construct(struct sk_buff *skb, mlxsw_emad_construct_eth_hdr(skb); } +struct mlxsw_emad_tlv_offsets { + u16 op_tlv; + u16 reg_tlv; +}; + +static void mlxsw_emad_tlv_parse(struct sk_buff *skb) +{ + struct mlxsw_emad_tlv_offsets *offsets = + (struct mlxsw_emad_tlv_offsets *) skb->cb; + + offsets->op_tlv = MLXSW_EMAD_ETH_HDR_LEN; + offsets->reg_tlv = MLXSW_EMAD_ETH_HDR_LEN + + MLXSW_EMAD_OP_TLV_LEN * sizeof(u32); +} + static char *mlxsw_emad_op_tlv(const struct sk_buff *skb) { - return ((char *) (skb->data + MLXSW_EMAD_ETH_HDR_LEN)); + struct mlxsw_emad_tlv_offsets *offsets = + (struct mlxsw_emad_tlv_offsets *) skb->cb; + + return ((char *) (skb->data + offsets->op_tlv)); } static char *mlxsw_emad_reg_tlv(const struct sk_buff *skb) { - return ((char *) (skb->data + MLXSW_EMAD_ETH_HDR_LEN + - MLXSW_EMAD_OP_TLV_LEN * sizeof(u32))); + struct mlxsw_emad_tlv_offsets *offsets = + (struct mlxsw_emad_tlv_offsets *) skb->cb; + + return ((char *) (skb->data + offsets->reg_tlv)); } -static char *mlxsw_emad_reg_payload(const char *op_tlv) +static char *mlxsw_emad_reg_payload(const char *reg_tlv) { - return ((char *) (op_tlv + (MLXSW_EMAD_OP_TLV_LEN + 1) * sizeof(u32))); + return ((char *) (reg_tlv + sizeof(u32))); +} + +static char *mlxsw_emad_reg_payload_cmd(const char *mbox) +{ + return ((char *) (mbox + (MLXSW_EMAD_OP_TLV_LEN + 1) * sizeof(u32))); } static u64 mlxsw_emad_get_tid(const struct sk_buff *skb) @@ -535,11 +560,11 @@ static void mlxsw_emad_process_response(struct mlxsw_core *mlxsw_core, mlxsw_emad_transmit_retry(mlxsw_core, trans); } else { if (err == 0) { - char *op_tlv = mlxsw_emad_op_tlv(skb); + char *reg_tlv = mlxsw_emad_reg_tlv(skb); if (trans->cb) trans->cb(mlxsw_core, - mlxsw_emad_reg_payload(op_tlv), + mlxsw_emad_reg_payload(reg_tlv), trans->reg->len, trans->cb_priv); } mlxsw_emad_trans_finish(trans, err); @@ -556,6 +581,8 @@ static void mlxsw_emad_rx_listener_func(struct sk_buff *skb, u8 local_port, trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), true, 0, skb->data, skb->len); + mlxsw_emad_tlv_parse(skb); + if (!mlxsw_emad_is_resp(skb)) goto free_skb; @@ -1395,12 +1422,16 @@ static void mlxsw_core_event_listener_func(struct sk_buff *skb, u8 local_port, struct mlxsw_event_listener_item *event_listener_item = priv; struct mlxsw_reg_info reg; char *payload; - char *op_tlv = mlxsw_emad_op_tlv(skb); - char *reg_tlv = mlxsw_emad_reg_tlv(skb); + char *reg_tlv; + char *op_tlv; + + mlxsw_emad_tlv_parse(skb); + op_tlv = mlxsw_emad_op_tlv(skb); + reg_tlv = mlxsw_emad_reg_tlv(skb); reg.id = mlxsw_emad_op_tlv_register_id_get(op_tlv); reg.len = (mlxsw_emad_reg_tlv_len_get(reg_tlv) - 1) * sizeof(u32); - payload = mlxsw_emad_reg_payload(op_tlv); + payload = mlxsw_emad_reg_payload(reg_tlv); event_listener_item->el.func(®, payload, event_listener_item->priv); dev_kfree_skb(skb); } @@ -1713,7 +1744,7 @@ retry: } if (!err) - memcpy(payload, mlxsw_emad_reg_payload(out_mbox), + memcpy(payload, mlxsw_emad_reg_payload_cmd(out_mbox), reg->len); mlxsw_cmd_mbox_free(out_mbox); -- cgit v1.2.3-59-g8ed1b From d17eb4030cc3061d3d2f313b9b898103701c44a4 Mon Sep 17 00:00:00 2001 From: Shalom Toledo Date: Tue, 12 Nov 2019 08:48:25 +0200 Subject: mlxsw: emad: Remove deprecated EMAD TLVs Remove deprecated EMAD TLVs. Signed-off-by: Shalom Toledo Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/emad.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/emad.h b/drivers/net/ethernet/mellanox/mlxsw/emad.h index a33b896f4bb8..5d7c78419fa7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/emad.h +++ b/drivers/net/ethernet/mellanox/mlxsw/emad.h @@ -19,10 +19,7 @@ enum { MLXSW_EMAD_TLV_TYPE_END, MLXSW_EMAD_TLV_TYPE_OP, - MLXSW_EMAD_TLV_TYPE_DR, - MLXSW_EMAD_TLV_TYPE_REG, - MLXSW_EMAD_TLV_TYPE_USERDATA, - MLXSW_EMAD_TLV_TYPE_OOBETH, + MLXSW_EMAD_TLV_TYPE_REG = 0x3, }; /* OP TLV */ -- cgit v1.2.3-59-g8ed1b From 664b3dd9ba58462d1f74f2c9536e500898450edc Mon Sep 17 00:00:00 2001 From: Shalom Toledo Date: Tue, 12 Nov 2019 08:48:26 +0200 Subject: mlxsw: core: Add EMAD string TLV Add EMAD string TLV, an ASCII string the driver can receive from the firmware in case of an error. Signed-off-by: Shalom Toledo Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 19 +++++++++++++++++++ drivers/net/ethernet/mellanox/mlxsw/emad.h | 6 +++++- 2 files changed, 24 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 698c7bcb1aad..a50a36f9584b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -249,6 +249,25 @@ MLXSW_ITEM32(emad, op_tlv, class, 0x04, 0, 8); */ MLXSW_ITEM64(emad, op_tlv, tid, 0x08, 0, 64); +/* emad_string_tlv_type + * Type of the TLV. + * Must be set to 0x2 (string TLV). + */ +MLXSW_ITEM32(emad, string_tlv, type, 0x00, 27, 5); + +/* emad_string_tlv_len + * Length of the string TLV in u32. + */ +MLXSW_ITEM32(emad, string_tlv, len, 0x00, 16, 11); + +#define MLXSW_EMAD_STRING_TLV_STRING_LEN 128 + +/* emad_string_tlv_string + * String provided by the device's firmware in case of erroneous register access + */ +MLXSW_ITEM_BUF(emad, string_tlv, string, 0x04, + MLXSW_EMAD_STRING_TLV_STRING_LEN); + /* emad_reg_tlv_type * Type of the TLV. * Must be set to 0x3 (register TLV). diff --git a/drivers/net/ethernet/mellanox/mlxsw/emad.h b/drivers/net/ethernet/mellanox/mlxsw/emad.h index 5d7c78419fa7..acfbbec52424 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/emad.h +++ b/drivers/net/ethernet/mellanox/mlxsw/emad.h @@ -19,7 +19,8 @@ enum { MLXSW_EMAD_TLV_TYPE_END, MLXSW_EMAD_TLV_TYPE_OP, - MLXSW_EMAD_TLV_TYPE_REG = 0x3, + MLXSW_EMAD_TLV_TYPE_STRING, + MLXSW_EMAD_TLV_TYPE_REG, }; /* OP TLV */ @@ -86,6 +87,9 @@ enum { MLXSW_EMAD_OP_TLV_METHOD_EVENT = 5, }; +/* STRING TLV */ +#define MLXSW_EMAD_STRING_TLV_LEN 33 /* Length in u32 */ + /* END TLV */ #define MLXSW_EMAD_END_TLV_LEN 1 /* Length in u32 */ -- cgit v1.2.3-59-g8ed1b From 2aa4aa2051f86d032ef86a268b38569cb3d450d0 Mon Sep 17 00:00:00 2001 From: Shalom Toledo Date: Tue, 12 Nov 2019 08:48:27 +0200 Subject: mlxsw: core: Add support for EMAD string TLV parsing During parsing of incoming EMADs, fill the string TLV's offset when it is used. Signed-off-by: Shalom Toledo Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index a50a36f9584b..d834bdc632ef 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -382,17 +382,32 @@ static void mlxsw_emad_construct(struct sk_buff *skb, struct mlxsw_emad_tlv_offsets { u16 op_tlv; + u16 string_tlv; u16 reg_tlv; }; +static bool mlxsw_emad_tlv_is_string_tlv(const char *tlv) +{ + u8 tlv_type = mlxsw_emad_string_tlv_type_get(tlv); + + return tlv_type == MLXSW_EMAD_TLV_TYPE_STRING; +} + static void mlxsw_emad_tlv_parse(struct sk_buff *skb) { struct mlxsw_emad_tlv_offsets *offsets = (struct mlxsw_emad_tlv_offsets *) skb->cb; offsets->op_tlv = MLXSW_EMAD_ETH_HDR_LEN; + offsets->string_tlv = 0; offsets->reg_tlv = MLXSW_EMAD_ETH_HDR_LEN + MLXSW_EMAD_OP_TLV_LEN * sizeof(u32); + + /* If string TLV is present, it must come after the operation TLV. */ + if (mlxsw_emad_tlv_is_string_tlv(skb->data + offsets->reg_tlv)) { + offsets->string_tlv = offsets->reg_tlv; + offsets->reg_tlv += MLXSW_EMAD_STRING_TLV_LEN * sizeof(u32); + } } static char *mlxsw_emad_op_tlv(const struct sk_buff *skb) -- cgit v1.2.3-59-g8ed1b From 72c8f428b5dc786d901d00370fa88923b40d7539 Mon Sep 17 00:00:00 2001 From: Shalom Toledo Date: Tue, 12 Nov 2019 08:48:28 +0200 Subject: mlxsw: core: Extend EMAD information reported to devlink hwerr Extend EMAD information reported to devlink hwerr tracepoint with transaction id and reg id (both, hex and string). Signed-off-by: Shalom Toledo Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index d834bdc632ef..d6a10727d4e6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1683,8 +1683,11 @@ int mlxsw_reg_trans_write(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_reg_trans_write); +#define MLXSW_REG_TRANS_ERR_STRING_SIZE 256 + static int mlxsw_reg_trans_wait(struct mlxsw_reg_trans *trans) { + char err_string[MLXSW_REG_TRANS_ERR_STRING_SIZE]; struct mlxsw_core *mlxsw_core = trans->core; int err; @@ -1702,9 +1705,14 @@ static int mlxsw_reg_trans_wait(struct mlxsw_reg_trans *trans) mlxsw_core_reg_access_type_str(trans->type), trans->emad_status, mlxsw_emad_op_tlv_status_str(trans->emad_status)); + + snprintf(err_string, MLXSW_REG_TRANS_ERR_STRING_SIZE, + "(tid=%llx,reg_id=%x(%s)) %s\n", trans->tid, + trans->reg->id, mlxsw_reg_id_str(trans->reg->id), + mlxsw_emad_op_tlv_status_str(trans->emad_status)); + trace_devlink_hwerr(priv_to_devlink(mlxsw_core), - trans->emad_status, - mlxsw_emad_op_tlv_status_str(trans->emad_status)); + trans->emad_status, err_string); } list_del(&trans->bulk_list); -- cgit v1.2.3-59-g8ed1b From 5d716ab45ad5e02461cb3b33062573d7cf43596a Mon Sep 17 00:00:00 2001 From: Shalom Toledo Date: Tue, 12 Nov 2019 08:48:29 +0200 Subject: mlxsw: core: Add support for using EMAD string TLV In case the firmware had an error while processing EMADs, it can send back an ASCII string with the reason using EMAD string TLV. This patch adds the support for using EMAD string TLV. In case of an error, reports the reason using devlink hwerr tracepoint. Signed-off-by: Shalom Toledo Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 76 +++++++++++++++++++++++++++--- drivers/net/ethernet/mellanox/mlxsw/core.h | 2 + 2 files changed, 72 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index d6a10727d4e6..e9f791c43f20 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -71,6 +71,7 @@ struct mlxsw_core { struct list_head trans_list; spinlock_t trans_list_lock; /* protects trans_list writes */ bool use_emad; + bool enable_string_tlv; } emad; struct { u8 *mapping; /* lag_id+port_index to local_port mapping */ @@ -323,6 +324,12 @@ static void mlxsw_emad_pack_reg_tlv(char *reg_tlv, memcpy(reg_tlv + sizeof(u32), payload, reg->len); } +static void mlxsw_emad_pack_string_tlv(char *string_tlv) +{ + mlxsw_emad_string_tlv_type_set(string_tlv, MLXSW_EMAD_TLV_TYPE_STRING); + mlxsw_emad_string_tlv_len_set(string_tlv, MLXSW_EMAD_STRING_TLV_LEN); +} + static void mlxsw_emad_pack_op_tlv(char *op_tlv, const struct mlxsw_reg_info *reg, enum mlxsw_core_reg_access_type type, @@ -364,7 +371,7 @@ static void mlxsw_emad_construct(struct sk_buff *skb, const struct mlxsw_reg_info *reg, char *payload, enum mlxsw_core_reg_access_type type, - u64 tid) + u64 tid, bool enable_string_tlv) { char *buf; @@ -374,6 +381,11 @@ static void mlxsw_emad_construct(struct sk_buff *skb, buf = skb_push(skb, reg->len + sizeof(u32)); mlxsw_emad_pack_reg_tlv(buf, reg, payload); + if (enable_string_tlv) { + buf = skb_push(skb, MLXSW_EMAD_STRING_TLV_LEN * sizeof(u32)); + mlxsw_emad_pack_string_tlv(buf); + } + buf = skb_push(skb, MLXSW_EMAD_OP_TLV_LEN * sizeof(u32)); mlxsw_emad_pack_op_tlv(buf, reg, type, tid); @@ -418,6 +430,17 @@ static char *mlxsw_emad_op_tlv(const struct sk_buff *skb) return ((char *) (skb->data + offsets->op_tlv)); } +static char *mlxsw_emad_string_tlv(const struct sk_buff *skb) +{ + struct mlxsw_emad_tlv_offsets *offsets = + (struct mlxsw_emad_tlv_offsets *) skb->cb; + + if (!offsets->string_tlv) + return NULL; + + return ((char *) (skb->data + offsets->string_tlv)); +} + static char *mlxsw_emad_reg_tlv(const struct sk_buff *skb) { struct mlxsw_emad_tlv_offsets *offsets = @@ -499,10 +522,31 @@ struct mlxsw_reg_trans { const struct mlxsw_reg_info *reg; enum mlxsw_core_reg_access_type type; int err; + char *emad_err_string; enum mlxsw_emad_op_tlv_status emad_status; struct rcu_head rcu; }; +static void mlxsw_emad_process_string_tlv(const struct sk_buff *skb, + struct mlxsw_reg_trans *trans) +{ + char *string_tlv; + char *string; + + string_tlv = mlxsw_emad_string_tlv(skb); + if (!string_tlv) + return; + + trans->emad_err_string = kzalloc(MLXSW_EMAD_STRING_TLV_STRING_LEN, + GFP_ATOMIC); + if (!trans->emad_err_string) + return; + + string = mlxsw_emad_string_tlv_string_data(string_tlv); + strlcpy(trans->emad_err_string, string, + MLXSW_EMAD_STRING_TLV_STRING_LEN); +} + #define MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS 3000 #define MLXSW_EMAD_TIMEOUT_MS 200 @@ -600,6 +644,8 @@ static void mlxsw_emad_process_response(struct mlxsw_core *mlxsw_core, trans->cb(mlxsw_core, mlxsw_emad_reg_payload(reg_tlv), trans->reg->len, trans->cb_priv); + } else { + mlxsw_emad_process_string_tlv(skb, trans); } mlxsw_emad_trans_finish(trans, err); } @@ -692,7 +738,7 @@ static void mlxsw_emad_fini(struct mlxsw_core *mlxsw_core) } static struct sk_buff *mlxsw_emad_alloc(const struct mlxsw_core *mlxsw_core, - u16 reg_len) + u16 reg_len, bool enable_string_tlv) { struct sk_buff *skb; u16 emad_len; @@ -700,6 +746,8 @@ static struct sk_buff *mlxsw_emad_alloc(const struct mlxsw_core *mlxsw_core, emad_len = (reg_len + sizeof(u32) + MLXSW_EMAD_ETH_HDR_LEN + (MLXSW_EMAD_OP_TLV_LEN + MLXSW_EMAD_END_TLV_LEN) * sizeof(u32) + mlxsw_core->driver->txhdr_len); + if (enable_string_tlv) + emad_len += MLXSW_EMAD_STRING_TLV_LEN * sizeof(u32); if (emad_len > MLXSW_EMAD_MAX_FRAME_LEN) return NULL; @@ -721,6 +769,7 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core, mlxsw_reg_trans_cb_t *cb, unsigned long cb_priv, u64 tid) { + bool enable_string_tlv; struct sk_buff *skb; int err; @@ -728,7 +777,12 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core, tid, reg->id, mlxsw_reg_id_str(reg->id), mlxsw_core_reg_access_type_str(type)); - skb = mlxsw_emad_alloc(mlxsw_core, reg->len); + /* Since this can be changed during emad_reg_access, read it once and + * use the value all the way. + */ + enable_string_tlv = mlxsw_core->emad.enable_string_tlv; + + skb = mlxsw_emad_alloc(mlxsw_core, reg->len, enable_string_tlv); if (!skb) return -ENOMEM; @@ -745,7 +799,8 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core, trans->reg = reg; trans->type = type; - mlxsw_emad_construct(skb, reg, payload, type, trans->tid); + mlxsw_emad_construct(skb, reg, payload, type, trans->tid, + enable_string_tlv); mlxsw_core->driver->txhdr_construct(skb, &trans->tx_info); spin_lock_bh(&mlxsw_core->emad.trans_list_lock); @@ -1707,12 +1762,15 @@ static int mlxsw_reg_trans_wait(struct mlxsw_reg_trans *trans) mlxsw_emad_op_tlv_status_str(trans->emad_status)); snprintf(err_string, MLXSW_REG_TRANS_ERR_STRING_SIZE, - "(tid=%llx,reg_id=%x(%s)) %s\n", trans->tid, + "(tid=%llx,reg_id=%x(%s)) %s (%s)\n", trans->tid, trans->reg->id, mlxsw_reg_id_str(trans->reg->id), - mlxsw_emad_op_tlv_status_str(trans->emad_status)); + mlxsw_emad_op_tlv_status_str(trans->emad_status), + trans->emad_err_string ? trans->emad_err_string : ""); trace_devlink_hwerr(priv_to_devlink(mlxsw_core), trans->emad_status, err_string); + + kfree(trans->emad_err_string); } list_del(&trans->bulk_list); @@ -2283,6 +2341,12 @@ u32 mlxsw_core_read_frc_l(struct mlxsw_core *mlxsw_core) } EXPORT_SYMBOL(mlxsw_core_read_frc_l); +void mlxsw_core_emad_string_tlv_enable(struct mlxsw_core *mlxsw_core) +{ + mlxsw_core->emad.enable_string_tlv = true; +} +EXPORT_SYMBOL(mlxsw_core_emad_string_tlv_enable); + static int __init mlxsw_core_module_init(void) { int err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 0d18bee6d140..543476a2e503 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -347,6 +347,8 @@ void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core); u32 mlxsw_core_read_frc_h(struct mlxsw_core *mlxsw_core); u32 mlxsw_core_read_frc_l(struct mlxsw_core *mlxsw_core); +void mlxsw_core_emad_string_tlv_enable(struct mlxsw_core *mlxsw_core); + bool mlxsw_core_res_valid(struct mlxsw_core *mlxsw_core, enum mlxsw_res_id res_id); -- cgit v1.2.3-59-g8ed1b From 9032b9e8f2107c6d30327492e4e4b32f92956a8f Mon Sep 17 00:00:00 2001 From: Shalom Toledo Date: Tue, 12 Nov 2019 08:48:30 +0200 Subject: mlxsw: spectrum: Enable EMAD string TLV Make sure to enable EMAD string TLV only after using the required firmware version. Signed-off-by: Shalom Toledo Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 471478eb1d86..556dca328bb5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4894,6 +4894,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, if (err) return err; + mlxsw_core_emad_string_tlv_enable(mlxsw_core); + err = mlxsw_sp_base_mac_get(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to get base mac\n"); -- cgit v1.2.3-59-g8ed1b From d4e82cf4df300368e8d271a2caf14611a5e176a6 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 12 Nov 2019 14:07:50 +0200 Subject: net/mlx5: Dump of fw_fatal use updated devlink binary interface Remove redundant code from fw_fatal reporter's dump callback. Use updated devlink interface of binary fmsg pair which breaks the output into chunks internally. Signed-off-by: Aya Levin Acked-by: Jiri Pirko Acked-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index e718170a80c3..d9f4e8c59c1f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -555,7 +555,6 @@ mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter, return mlx5_health_try_recover(dev); } -#define MLX5_CR_DUMP_CHUNK_SIZE 256 static int mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, void *priv_ctx, @@ -564,8 +563,6 @@ mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); u32 crdump_size = dev->priv.health.crdump_size; u32 *cr_data; - u32 data_size; - u32 offset; int err; if (!mlx5_core_is_pf(dev)) @@ -586,20 +583,7 @@ mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, goto free_data; } - err = devlink_fmsg_arr_pair_nest_start(fmsg, "crdump_data"); - if (err) - goto free_data; - for (offset = 0; offset < crdump_size; offset += data_size) { - if (crdump_size - offset < MLX5_CR_DUMP_CHUNK_SIZE) - data_size = crdump_size - offset; - else - data_size = MLX5_CR_DUMP_CHUNK_SIZE; - err = devlink_fmsg_binary_put(fmsg, (char *)cr_data + offset, - data_size); - if (err) - goto free_data; - } - err = devlink_fmsg_arr_pair_nest_end(fmsg); + err = devlink_fmsg_binary_pair_put(fmsg, "crdump_data", cr_data, crdump_size); free_data: kvfree(cr_data); -- cgit v1.2.3-59-g8ed1b From 12063c2e4c0e38f36c0e6f0942cd138feed022b3 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 12 Nov 2019 00:34:24 +0100 Subject: net/mlx5: Simplify fdb chain and prio eswitch defines FDB_MAX_CHAIN and FDB_MAX_PRIO were defined differently depending on if CONFIG_MLX5_ESWITCH is enabled to save space on allocations. This is a minor space saving, and there is no real need for it. Simplify things instead, and define them the same in both cases. Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Acked-by: Pablo Neira Ayuso Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index a05b948a6287..ab8cdd3dd8d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -43,6 +43,10 @@ #include #include "lib/mpfs.h" +#define FDB_MAX_CHAIN 3 +#define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1) +#define FDB_MAX_PRIO 16 + #ifdef CONFIG_MLX5_ESWITCH #define MLX5_MAX_UC_PER_VPORT(dev) \ @@ -59,10 +63,6 @@ #define mlx5_esw_has_fwd_fdb(dev) \ MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_to_table) -#define FDB_MAX_CHAIN 3 -#define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1) -#define FDB_MAX_PRIO 16 - struct vport_ingress { struct mlx5_flow_table *acl; struct mlx5_flow_handle *allow_rule; @@ -637,10 +637,6 @@ static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev) static inline void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs) {} -#define FDB_MAX_CHAIN 1 -#define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1) -#define FDB_MAX_PRIO 1 - #endif /* CONFIG_MLX5_ESWITCH */ #endif /* __MLX5_ESWITCH_H__ */ -- cgit v1.2.3-59-g8ed1b From 2cf2954bd7ffd8250ae257b45b96915003c26d7d Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 12 Nov 2019 00:34:25 +0100 Subject: net/mlx5: Rename FDB_* tc related defines to FDB_TC_* defines Rename it to prepare for next patch that will add a different type of offload to the FDB. Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Acked-by: Pablo Neira Ayuso Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 8 ++++---- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 10 +++++----- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 8 ++++---- 4 files changed, 15 insertions(+), 15 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3e78a727f3e6..15b771b6c09d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1074,7 +1074,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr)); slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; slow_attr->split_count = 0; - slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN; + slow_attr->dest_chain = FDB_TC_SLOW_PATH_CHAIN; rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr); if (!IS_ERR(rule)) @@ -1091,7 +1091,7 @@ mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr)); slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; slow_attr->split_count = 0; - slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN; + slow_attr->dest_chain = FDB_TC_SLOW_PATH_CHAIN; mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr); flow_flag_clear(flow, SLOW); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index ab8cdd3dd8d0..d73187bdbc06 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -43,9 +43,9 @@ #include #include "lib/mpfs.h" -#define FDB_MAX_CHAIN 3 -#define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1) -#define FDB_MAX_PRIO 16 +#define FDB_TC_MAX_CHAIN 3 +#define FDB_TC_SLOW_PATH_CHAIN (FDB_TC_MAX_CHAIN + 1) +#define FDB_TC_MAX_PRIO 16 #ifdef CONFIG_MLX5_ESWITCH @@ -173,7 +173,7 @@ struct mlx5_eswitch_fdb { struct { struct mlx5_flow_table *fdb; u32 num_rules; - } fdb_prio[FDB_MAX_CHAIN + 1][FDB_MAX_PRIO + 1][PRIO_LEVELS]; + } fdb_prio[FDB_TC_MAX_CHAIN + 1][FDB_TC_MAX_PRIO + 1][PRIO_LEVELS]; /* Protects fdb_prio table */ struct mutex fdb_prio_lock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d8e25416a15d..9c51fedd890f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -75,7 +75,7 @@ bool mlx5_eswitch_prios_supported(struct mlx5_eswitch *esw) u32 mlx5_eswitch_get_chain_range(struct mlx5_eswitch *esw) { if (esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED) - return FDB_MAX_CHAIN; + return FDB_TC_MAX_CHAIN; return 0; } @@ -83,7 +83,7 @@ u32 mlx5_eswitch_get_chain_range(struct mlx5_eswitch *esw) u16 mlx5_eswitch_get_prio_range(struct mlx5_eswitch *esw) { if (esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED) - return FDB_MAX_PRIO; + return FDB_TC_MAX_PRIO; return 1; } @@ -928,7 +928,7 @@ esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level) int table_prio, l = 0; u32 flags = 0; - if (chain == FDB_SLOW_PATH_CHAIN) + if (chain == FDB_TC_SLOW_PATH_CHAIN) return esw->fdb_table.offloads.slow_fdb; mutex_lock(&esw->fdb_table.offloads.fdb_prio_lock); @@ -953,7 +953,7 @@ esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level) flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); - table_prio = (chain * FDB_MAX_PRIO) + prio - 1; + table_prio = (chain * FDB_TC_MAX_PRIO) + prio - 1; /* create earlier levels for correct fs_core lookup when * connecting tables @@ -990,7 +990,7 @@ esw_put_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level) { int l; - if (chain == FDB_SLOW_PATH_CHAIN) + if (chain == FDB_TC_SLOW_PATH_CHAIN) return; mutex_lock(&esw->fdb_table.offloads.fdb_prio_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3bbb49354829..b33f77892d10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2565,7 +2565,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) return -ENOMEM; steering->fdb_sub_ns = kzalloc(sizeof(steering->fdb_sub_ns) * - (FDB_MAX_CHAIN + 1), GFP_KERNEL); + (FDB_TC_MAX_CHAIN + 1), GFP_KERNEL); if (!steering->fdb_sub_ns) return -ENOMEM; @@ -2576,7 +2576,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) goto out_err; } - levels = 2 * FDB_MAX_PRIO * (FDB_MAX_CHAIN + 1); + levels = 2 * FDB_TC_MAX_PRIO * (FDB_TC_MAX_CHAIN + 1); maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, FDB_FAST_PATH, levels); @@ -2585,14 +2585,14 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) goto out_err; } - for (chain = 0; chain <= FDB_MAX_CHAIN; chain++) { + for (chain = 0; chain <= FDB_TC_MAX_CHAIN; chain++) { ns = fs_create_namespace(maj_prio, MLX5_FLOW_TABLE_MISS_ACTION_DEF); if (IS_ERR(ns)) { err = PTR_ERR(ns); goto out_err; } - for (prio = 0; prio < FDB_MAX_PRIO * (chain + 1); prio++) { + for (prio = 0; prio < FDB_TC_MAX_PRIO * (chain + 1); prio++) { min_prio = fs_create_prio(ns, prio, 2); if (IS_ERR(min_prio)) { err = PTR_ERR(min_prio); -- cgit v1.2.3-59-g8ed1b From 4db7b98e943225dc2a7435811767e44f63640462 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 12 Nov 2019 00:34:26 +0100 Subject: net/mlx5: Define fdb tc levels per prio Define FDB_TC_LEVELS_PER_PRIO instead of magic number 2. This is the number of levels used by each tc prio table in the fdb. Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Acked-by: Pablo Neira Ayuso Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 6 ++++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index d73187bdbc06..8c9d8dc85861 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -46,6 +46,7 @@ #define FDB_TC_MAX_CHAIN 3 #define FDB_TC_SLOW_PATH_CHAIN (FDB_TC_MAX_CHAIN + 1) #define FDB_TC_MAX_PRIO 16 +#define FDB_TC_LEVELS_PER_PRIO 2 #ifdef CONFIG_MLX5_ESWITCH @@ -146,7 +147,6 @@ enum offloads_fdb_flags { extern const unsigned int ESW_POOLS[4]; -#define PRIO_LEVELS 2 struct mlx5_eswitch_fdb { union { struct legacy_fdb { @@ -173,7 +173,7 @@ struct mlx5_eswitch_fdb { struct { struct mlx5_flow_table *fdb; u32 num_rules; - } fdb_prio[FDB_TC_MAX_CHAIN + 1][FDB_TC_MAX_PRIO + 1][PRIO_LEVELS]; + } fdb_prio[FDB_TC_MAX_CHAIN + 1][FDB_TC_MAX_PRIO + 1][FDB_TC_LEVELS_PER_PRIO]; /* Protects fdb_prio table */ struct mutex fdb_prio_lock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index b33f77892d10..190c5c71b534 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2576,7 +2576,8 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) goto out_err; } - levels = 2 * FDB_TC_MAX_PRIO * (FDB_TC_MAX_CHAIN + 1); + levels = FDB_TC_LEVELS_PER_PRIO * + FDB_TC_MAX_PRIO * (FDB_TC_MAX_CHAIN + 1); maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, FDB_FAST_PATH, levels); @@ -2593,7 +2594,8 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) } for (prio = 0; prio < FDB_TC_MAX_PRIO * (chain + 1); prio++) { - min_prio = fs_create_prio(ns, prio, 2); + min_prio = fs_create_prio(ns, prio, + FDB_TC_LEVELS_PER_PRIO); if (IS_ERR(min_prio)) { err = PTR_ERR(min_prio); goto out_err; -- cgit v1.2.3-59-g8ed1b From 34b13cb3eaa5ad205f4497da6420262da4940b9e Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 12 Nov 2019 00:34:27 +0100 Subject: net/mlx5: Accumulate levels for chains prio namespaces Tc chains are implemented by creating a chained prio steering type, and inside it there is a namespace for each chain (FDB_TC_MAX_CHAINS). Each of those has a list of priorities. Currently, all namespaces in a prio start at the parent prio level. But since we can jump from chain (namespace) to another chain in the same prio, we need the levels for higher chains to be higher as well. So we created unused prios to account for levels in previous namespaces. Fix that by accumulating the namespaces levels if we are inside a chained type prio, and removing the unused prios. Fixes: 328edb499f99 ('net/mlx5: Split FDB fast path prio to multiple namespaces') Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Acked-by: Pablo Neira Ayuso Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 +++++++++- 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 9c51fedd890f..60d3d88e406c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -953,7 +953,7 @@ esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level) flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); - table_prio = (chain * FDB_TC_MAX_PRIO) + prio - 1; + table_prio = prio - 1; /* create earlier levels for correct fs_core lookup when * connecting tables diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 190c5c71b534..3cdad1d1021f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2359,9 +2359,17 @@ static void set_prio_attrs_in_prio(struct fs_prio *prio, int acc_level) int acc_level_ns = acc_level; prio->start_level = acc_level; - fs_for_each_ns(ns, prio) + fs_for_each_ns(ns, prio) { /* This updates start_level and num_levels of ns's priority descendants */ acc_level_ns = set_prio_attrs_in_ns(ns, acc_level); + + /* If this a prio with chains, and we can jump from one chain + * (namepsace) to another, so we accumulate the levels + */ + if (prio->node.type == FS_TYPE_PRIO_CHAINS) + acc_level = acc_level_ns; + } + if (!prio->num_levels) prio->num_levels = acc_level_ns - prio->start_level; WARN_ON(prio->num_levels < acc_level_ns - prio->start_level); -- cgit v1.2.3-59-g8ed1b From 439e843f1f43640fd52530433d803db8585cd028 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 12 Nov 2019 00:34:28 +0100 Subject: net/mlx5: Refactor creating fast path prio chains Next patch will re-use this to add a new chain but in a different prio. Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Acked-by: Pablo Neira Ayuso Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 118 +++++++++++++++------- 1 file changed, 82 insertions(+), 36 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3cdad1d1021f..4aa6990a38b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2558,60 +2558,106 @@ out_err: steering->rdma_rx_root_ns = NULL; return err; } -static int init_fdb_root_ns(struct mlx5_flow_steering *steering) + +/* FT and tc chains are stored in the same array so we can re-use the + * mlx5_get_fdb_sub_ns() and tc api for FT chains. + * When creating a new ns for each chain store it in the first available slot. + * Assume tc chains are created and stored first and only then the FT chain. + */ +static void store_fdb_sub_ns_prio_chain(struct mlx5_flow_steering *steering, + struct mlx5_flow_namespace *ns) +{ + int chain = 0; + + while (steering->fdb_sub_ns[chain]) + ++chain; + + steering->fdb_sub_ns[chain] = ns; +} + +static int create_fdb_sub_ns_prio_chain(struct mlx5_flow_steering *steering, + struct fs_prio *maj_prio) { struct mlx5_flow_namespace *ns; - struct fs_prio *maj_prio; struct fs_prio *min_prio; + int prio; + + ns = fs_create_namespace(maj_prio, MLX5_FLOW_TABLE_MISS_ACTION_DEF); + if (IS_ERR(ns)) + return PTR_ERR(ns); + + for (prio = 0; prio < FDB_TC_MAX_PRIO; prio++) { + min_prio = fs_create_prio(ns, prio, FDB_TC_LEVELS_PER_PRIO); + if (IS_ERR(min_prio)) + return PTR_ERR(min_prio); + } + + store_fdb_sub_ns_prio_chain(steering, ns); + + return 0; +} + +static int create_fdb_chains(struct mlx5_flow_steering *steering, + int fs_prio, + int chains) +{ + struct fs_prio *maj_prio; int levels; int chain; - int prio; int err; - steering->fdb_root_ns = create_root_ns(steering, FS_FT_FDB); - if (!steering->fdb_root_ns) - return -ENOMEM; + levels = FDB_TC_LEVELS_PER_PRIO * FDB_TC_MAX_PRIO * chains; + maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, + fs_prio, + levels); + if (IS_ERR(maj_prio)) + return PTR_ERR(maj_prio); + + for (chain = 0; chain < chains; chain++) { + err = create_fdb_sub_ns_prio_chain(steering, maj_prio); + if (err) + return err; + } + + return 0; +} - steering->fdb_sub_ns = kzalloc(sizeof(steering->fdb_sub_ns) * - (FDB_TC_MAX_CHAIN + 1), GFP_KERNEL); +static int create_fdb_fast_path(struct mlx5_flow_steering *steering) +{ + const int total_chains = FDB_TC_MAX_CHAIN + 1; + int err; + + steering->fdb_sub_ns = kcalloc(total_chains, + sizeof(*steering->fdb_sub_ns), + GFP_KERNEL); if (!steering->fdb_sub_ns) return -ENOMEM; + err = create_fdb_chains(steering, FDB_FAST_PATH, FDB_TC_MAX_CHAIN + 1); + if (err) + return err; + + return 0; +} + +static int init_fdb_root_ns(struct mlx5_flow_steering *steering) +{ + struct fs_prio *maj_prio; + int err; + + steering->fdb_root_ns = create_root_ns(steering, FS_FT_FDB); + if (!steering->fdb_root_ns) + return -ENOMEM; + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BYPASS_PATH, 1); if (IS_ERR(maj_prio)) { err = PTR_ERR(maj_prio); goto out_err; } - - levels = FDB_TC_LEVELS_PER_PRIO * - FDB_TC_MAX_PRIO * (FDB_TC_MAX_CHAIN + 1); - maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, - FDB_FAST_PATH, - levels); - if (IS_ERR(maj_prio)) { - err = PTR_ERR(maj_prio); + err = create_fdb_fast_path(steering); + if (err) goto out_err; - } - - for (chain = 0; chain <= FDB_TC_MAX_CHAIN; chain++) { - ns = fs_create_namespace(maj_prio, MLX5_FLOW_TABLE_MISS_ACTION_DEF); - if (IS_ERR(ns)) { - err = PTR_ERR(ns); - goto out_err; - } - - for (prio = 0; prio < FDB_TC_MAX_PRIO * (chain + 1); prio++) { - min_prio = fs_create_prio(ns, prio, - FDB_TC_LEVELS_PER_PRIO); - if (IS_ERR(min_prio)) { - err = PTR_ERR(min_prio); - goto out_err; - } - } - - steering->fdb_sub_ns[chain] = ns; - } maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_SLOW_PATH, 1); if (IS_ERR(maj_prio)) { -- cgit v1.2.3-59-g8ed1b From 975b992fdd4b38028d7c1dcf38286d6e7991c1b2 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 12 Nov 2019 00:34:29 +0100 Subject: net/mlx5: Add new chain for netfilter flow table offload Netfilter tables (nftables) implements a software datapath that comes after tc ingress datapath. The datapath supports offloading such rules via the flow table offload API. This API is currently only used by NFT and it doesn't provide the global priority in regards to tc offload, so we assume offloading such rules must come after tc. It does provide a flow table priority parameter, so we need to provide some supported priority range. For that, split fastpath prio to two, flow table offload and tc offload, with one dedicated priority chain for flow table offload. Next patch will re-use the multi chain API to access this chain by allowing access to this chain by the fdb_sub_namespace. Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Acked-by: Pablo Neira Ayuso Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 9 +++++++-- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 9 ++++++--- include/linux/mlx5/fs.h | 3 ++- 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 8c9d8dc85861..2b563700c664 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -44,7 +44,12 @@ #include "lib/mpfs.h" #define FDB_TC_MAX_CHAIN 3 -#define FDB_TC_SLOW_PATH_CHAIN (FDB_TC_MAX_CHAIN + 1) +#define FDB_FT_CHAIN (FDB_TC_MAX_CHAIN + 1) +#define FDB_TC_SLOW_PATH_CHAIN (FDB_FT_CHAIN + 1) + +/* The index of the last real chain (FT) + 1 as chain zero is valid as well */ +#define FDB_NUM_CHAINS (FDB_FT_CHAIN + 1) + #define FDB_TC_MAX_PRIO 16 #define FDB_TC_LEVELS_PER_PRIO 2 @@ -173,7 +178,7 @@ struct mlx5_eswitch_fdb { struct { struct mlx5_flow_table *fdb; u32 num_rules; - } fdb_prio[FDB_TC_MAX_CHAIN + 1][FDB_TC_MAX_PRIO + 1][FDB_TC_LEVELS_PER_PRIO]; + } fdb_prio[FDB_NUM_CHAINS][FDB_TC_MAX_PRIO + 1][FDB_TC_LEVELS_PER_PRIO]; /* Protects fdb_prio table */ struct mutex fdb_prio_lock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 4aa6990a38b3..84e90b21e148 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2624,16 +2624,19 @@ static int create_fdb_chains(struct mlx5_flow_steering *steering, static int create_fdb_fast_path(struct mlx5_flow_steering *steering) { - const int total_chains = FDB_TC_MAX_CHAIN + 1; int err; - steering->fdb_sub_ns = kcalloc(total_chains, + steering->fdb_sub_ns = kcalloc(FDB_NUM_CHAINS, sizeof(*steering->fdb_sub_ns), GFP_KERNEL); if (!steering->fdb_sub_ns) return -ENOMEM; - err = create_fdb_chains(steering, FDB_FAST_PATH, FDB_TC_MAX_CHAIN + 1); + err = create_fdb_chains(steering, FDB_TC_OFFLOAD, FDB_TC_MAX_CHAIN + 1); + if (err) + return err; + + err = create_fdb_chains(steering, FDB_FT_OFFLOAD, 1); if (err) return err; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 724d276ea133..4e5b84e66822 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -80,7 +80,8 @@ enum mlx5_flow_namespace_type { enum { FDB_BYPASS_PATH, - FDB_FAST_PATH, + FDB_TC_OFFLOAD, + FDB_FT_OFFLOAD, FDB_SLOW_PATH, }; -- cgit v1.2.3-59-g8ed1b From 86bb811b08086f98744ecc600907673af7f2aec5 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Sun, 10 Nov 2019 18:10:13 +0200 Subject: net/mlx5: DR, Fix matcher builders select check When selecting a matcher ste_builder_arr will always be evaluated as true, instead check if num_of_builders is set for validity. Fixes: 667f264676c7 ("net/mlx5: DR, Support IPv4 and IPv6 mixed matcher") Signed-off-by: Alex Vesker Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 5db947df8763..c6548980daf0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -154,7 +154,7 @@ int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, nic_matcher->num_of_builders = nic_matcher->num_of_builders_arr[outer_ipv][inner_ipv]; - if (!nic_matcher->ste_builder) { + if (!nic_matcher->num_of_builders) { mlx5dr_dbg(matcher->tbl->dmn, "Rule not supported on this matcher due to IP related fields\n"); return -EINVAL; -- cgit v1.2.3-59-g8ed1b From a7cba0a4d508d2d78f2932ee944feadd38c97c2c Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 13:29:17 -0500 Subject: net/mlx5: Read num_vfs before disabling SR-IOV mlx5_device_disable_sriov() currently reads num_vfs from the PCI core. However when mlx5_device_disable_sriov() is executed, SR-IOV is already disabled at the PCI level. Due to this disable_hca() cleanup is not done during SR-IOV disable flow. mlx5_sriov_disable() pci_enable_sriov() mlx5_device_disable_sriov() <- num_vfs is zero here. When SR-IOV enablement fails during mlx5_sriov_enable(), HCA's are left in enabled stage because mlx5_device_disable_sriov() relies on num_vfs from PCI core. mlx5_sriov_enable() mlx5_device_enable_sriov() pci_enable_sriov() <- Fails Hence, to overcome above issues, (a) Read num_vfs before disabling SR-IOV and use it. (b) Use num_vfs given when enabling sriov in error unwinding path. Fixes: d886aba677a0 ("net/mlx5: Reduce dependency on enabled_vfs counter and num_vfs") Signed-off-by: Parav Pandit Reviewed-by: Daniel Jurgens Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/sriov.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index f641f1336402..03f037811f1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -108,10 +108,10 @@ enable_vfs_hca: return 0; } -static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev, bool clear_vf) +static void +mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf) { struct mlx5_core_sriov *sriov = &dev->priv.sriov; - int num_vfs = pci_num_vf(dev->pdev); int err; int vf; @@ -147,7 +147,7 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs) err = pci_enable_sriov(pdev, num_vfs); if (err) { mlx5_core_warn(dev, "pci_enable_sriov failed : %d\n", err); - mlx5_device_disable_sriov(dev, true); + mlx5_device_disable_sriov(dev, num_vfs, true); } return err; } @@ -155,9 +155,10 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs) static void mlx5_sriov_disable(struct pci_dev *pdev) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + int num_vfs = pci_num_vf(dev->pdev); pci_disable_sriov(pdev); - mlx5_device_disable_sriov(dev, true); + mlx5_device_disable_sriov(dev, num_vfs, true); } int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs) @@ -192,7 +193,7 @@ void mlx5_sriov_detach(struct mlx5_core_dev *dev) if (!mlx5_core_is_pf(dev)) return; - mlx5_device_disable_sriov(dev, false); + mlx5_device_disable_sriov(dev, pci_num_vf(dev->pdev), false); } static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev) -- cgit v1.2.3-59-g8ed1b From e6014afd1c5717d556778ec1307cf7ab27ba5a2d Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 30 Oct 2019 16:48:15 +0200 Subject: net/mlx5: Remove redundant NULL initializations Neighbour initializations to NULL are not necessary as the pointers are not used if an error is returned, and if success returned, pointers are initialized. Signed-off-by: Eli Cohen Reviewed-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 13af72556987..4f78efeb6ee8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -77,8 +77,8 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, struct neighbour **out_n, u8 *out_ttl) { + struct neighbour *n; struct rtable *rt; - struct neighbour *n = NULL; #if IS_ENABLED(CONFIG_INET) struct mlx5_core_dev *mdev = priv->mdev; @@ -138,8 +138,8 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, struct neighbour **out_n, u8 *out_ttl) { - struct neighbour *n = NULL; struct dst_entry *dst; + struct neighbour *n; #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) int ret; @@ -212,8 +212,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); const struct ip_tunnel_key *tun_key = &e->tun_info->key; struct net_device *out_dev, *route_dev; - struct neighbour *n = NULL; struct flowi4 fl4 = {}; + struct neighbour *n; int ipv4_encap_size; char *encap_header; u8 nud_state, ttl; @@ -328,9 +328,9 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); const struct ip_tunnel_key *tun_key = &e->tun_info->key; struct net_device *out_dev, *route_dev; - struct neighbour *n = NULL; struct flowi6 fl6 = {}; struct ipv6hdr *ip6h; + struct neighbour *n; int ipv6_encap_size; char *encap_header; u8 nud_state, ttl; -- cgit v1.2.3-59-g8ed1b From 85bf490af1e2e4b6263898f0d47af13ee1bb4d28 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 31 Oct 2019 09:00:43 +0200 Subject: net/mlx5e: Fix error flow cleanup in mlx5e_tc_tun_create_header_ipv4/6 Be sure to release the neighbour in case of failures after successful route lookup. Signed-off-by: Eli Cohen Reviewed-by: Roi Dayan Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 4f78efeb6ee8..5316cedd78bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -239,12 +239,15 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, if (max_encap_size < ipv4_encap_size) { mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", ipv4_encap_size, max_encap_size); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto out; } encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL); - if (!encap_header) - return -ENOMEM; + if (!encap_header) { + err = -ENOMEM; + goto out; + } /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule @@ -355,12 +358,15 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, if (max_encap_size < ipv6_encap_size) { mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", ipv6_encap_size, max_encap_size); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto out; } encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL); - if (!encap_header) - return -ENOMEM; + if (!encap_header) { + err = -ENOMEM; + goto out; + } /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule -- cgit v1.2.3-59-g8ed1b From 71c6eaebf06aa8353b0dcd57786b801b96fe2c08 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Tue, 29 Oct 2019 17:04:30 +0200 Subject: net/mlx5e: Set netdev name space on creation Use devlink instance name space to set the netdev net namespace. Preparation patch for devlink reload implementation. Signed-off-by: Michael Guralnik Acked-by: Jiri Pirko Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h | 5 +++++ 3 files changed, 9 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 772bfdbdeb9c..06a592fb62bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -63,6 +63,7 @@ #include "en/xsk/rx.h" #include "en/xsk/tx.h" #include "en/hv_vhca_stats.h" +#include "lib/mlx5.h" bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) @@ -5427,6 +5428,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) return NULL; } + dev_net_set(netdev, mlx5_core_net(mdev)); priv = netdev_priv(netdev); err = mlx5e_attach(mdev, priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index cd9bb7c7b341..c7f98f1fd9b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -47,6 +47,7 @@ #include "en/tc_tun.h" #include "fs_core.h" #include "lib/port_tun.h" +#include "lib/mlx5.h" #define CREATE_TRACE_POINTS #include "diag/en_rep_tracepoint.h" @@ -1877,6 +1878,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) return -EINVAL; } + dev_net_set(netdev, mlx5_core_net(dev)); rpriv->netdev = netdev; rep->rep_data[REP_ETH].priv = rpriv; INIT_LIST_HEAD(&rpriv->vport_sqs_list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index b99d469e4e64..249539247e2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -84,4 +84,9 @@ int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, void *key, u32 sz_bytes, u32 *p_key_id); void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id); +static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev) +{ + return devlink_net(priv_to_devlink(dev)); +} + #endif -- cgit v1.2.3-59-g8ed1b From 4383cfcc65e7879e1858da56954dae9fc20dfae9 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Sun, 27 Oct 2019 14:34:11 +0200 Subject: net/mlx5: Add devlink reload Implement devlink reload for mlx5. Usage example: devlink dev reload pci/0000:06:00.0 Signed-off-by: Michael Guralnik Acked-by: Jiri Pirko Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 20 ++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 3 +++ 3 files changed, 25 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index b2c26388edb1..ac108f1e5bd6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -85,6 +85,22 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, return 0; } +static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + return mlx5_unload_one(dev, false); +} + +static int mlx5_devlink_reload_up(struct devlink *devlink, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + return mlx5_load_one(dev, false); +} + static const struct devlink_ops mlx5_devlink_ops = { #ifdef CONFIG_MLX5_ESWITCH .eswitch_mode_set = mlx5_devlink_eswitch_mode_set, @@ -96,6 +112,8 @@ static const struct devlink_ops mlx5_devlink_ops = { #endif .flash_update = mlx5_devlink_flash_update, .info_get = mlx5_devlink_info_get, + .reload_down = mlx5_devlink_reload_down, + .reload_up = mlx5_devlink_reload_up, }; struct devlink *mlx5_devlink_alloc(void) @@ -235,6 +253,7 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev) goto params_reg_err; mlx5_devlink_set_params_init_values(devlink); devlink_params_publish(devlink); + devlink_reload_enable(devlink); return 0; params_reg_err: @@ -244,6 +263,7 @@ params_reg_err: void mlx5_devlink_unregister(struct devlink *devlink) { + devlink_reload_disable(devlink); devlink_params_unregister(devlink, mlx5_devlink_params, ARRAY_SIZE(mlx5_devlink_params)); devlink_unregister(devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c9a091d3226c..31fbfd6e8bb9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1168,7 +1168,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev) mlx5_put_uars_page(dev, dev->priv.uar); } -static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot) +int mlx5_load_one(struct mlx5_core_dev *dev, bool boot) { int err = 0; @@ -1226,7 +1226,7 @@ function_teardown: return err; } -static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup) +int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup) { if (cleanup) { mlx5_unregister_device(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b100489dc85c..da67b28d6e23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -243,4 +243,7 @@ enum { u8 mlx5_get_nic_state(struct mlx5_core_dev *dev); void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state); + +int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup); +int mlx5_load_one(struct mlx5_core_dev *dev, bool boot); #endif /* __MLX5_CORE_H__ */ -- cgit v1.2.3-59-g8ed1b From 84179981317fb4fb3e9df5acd42ea33cf6037793 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 12 Nov 2019 00:34:30 +0100 Subject: net/mlx5: TC: Offload flow table rules Since both tc rules and flow table rules are of the same format, we can re-use tc parsing for that, and move the flow table rules to their steering domain - In this case, the next chain after max tc chain. Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Acked-by: Pablo Neira Ayuso Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 45 ++++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 28 ++++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 3 +- 3 files changed, 71 insertions(+), 5 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index c7f98f1fd9b1..f175cb24bb67 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1244,21 +1244,60 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, } } -static LIST_HEAD(mlx5e_rep_block_cb_list); +static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct flow_cls_offload *f = type_data; + struct flow_cls_offload cls_flower; + struct mlx5e_priv *priv = cb_priv; + struct mlx5_eswitch *esw; + unsigned long flags; + int err; + + flags = MLX5_TC_FLAG(INGRESS) | + MLX5_TC_FLAG(ESW_OFFLOAD) | + MLX5_TC_FLAG(FT_OFFLOAD); + esw = priv->mdev->priv.eswitch; + switch (type) { + case TC_SETUP_CLSFLOWER: + if (!mlx5_eswitch_prios_supported(esw) || f->common.chain_index) + return -EOPNOTSUPP; + + /* Re-use tc offload path by moving the ft flow to the + * reserved ft chain. + */ + memcpy(&cls_flower, f, sizeof(*f)); + cls_flower.common.chain_index = FDB_FT_CHAIN; + err = mlx5e_rep_setup_tc_cls_flower(priv, &cls_flower, flags); + memcpy(&f->stats, &cls_flower.stats, sizeof(f->stats)); + return err; + default: + return -EOPNOTSUPP; + } +} + +static LIST_HEAD(mlx5e_rep_block_tc_cb_list); +static LIST_HEAD(mlx5e_rep_block_ft_cb_list); static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct mlx5e_priv *priv = netdev_priv(dev); struct flow_block_offload *f = type_data; + f->unlocked_driver_cb = true; + switch (type) { case TC_SETUP_BLOCK: - f->unlocked_driver_cb = true; return flow_block_cb_setup_simple(type_data, - &mlx5e_rep_block_cb_list, + &mlx5e_rep_block_tc_cb_list, mlx5e_rep_setup_tc_cb, priv, priv, true); + case TC_SETUP_FT: + return flow_block_cb_setup_simple(type_data, + &mlx5e_rep_block_ft_cb_list, + mlx5e_rep_setup_ft_cb, + priv, priv, true); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 0c1022cda128..3a707d788022 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -74,6 +74,7 @@ enum { MLX5E_TC_FLOW_FLAG_INGRESS = MLX5E_TC_FLAG_INGRESS_BIT, MLX5E_TC_FLOW_FLAG_EGRESS = MLX5E_TC_FLAG_EGRESS_BIT, MLX5E_TC_FLOW_FLAG_ESWITCH = MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, + MLX5E_TC_FLOW_FLAG_FT = MLX5E_TC_FLAG_FT_OFFLOAD_BIT, MLX5E_TC_FLOW_FLAG_NIC = MLX5E_TC_FLAG_NIC_OFFLOAD_BIT, MLX5E_TC_FLOW_FLAG_OFFLOADED = MLX5E_TC_FLOW_BASE, MLX5E_TC_FLOW_FLAG_HAIRPIN = MLX5E_TC_FLOW_BASE + 1, @@ -276,6 +277,11 @@ static bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow) return flow_flag_test(flow, ESWITCH); } +static bool mlx5e_is_ft_flow(struct mlx5e_tc_flow *flow) +{ + return flow_flag_test(flow, FT); +} + static bool mlx5e_is_offloaded_flow(struct mlx5e_tc_flow *flow) { return flow_flag_test(flow, OFFLOADED); @@ -1168,7 +1174,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (attr->chain > max_chain) { + /* We check chain range only for tc flows. + * For ft flows, we checked attr->chain was originally 0 and set it to + * FDB_FT_CHAIN which is outside tc range. + * See mlx5e_rep_setup_ft_cb(). + */ + if (!mlx5e_is_ft_flow(flow) && attr->chain > max_chain) { NL_SET_ERR_MSG(extack, "Requested chain is out of supported range"); return -EOPNOTSUPP; } @@ -3217,6 +3228,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; struct mlx5e_rep_priv *rpriv = priv->ppriv; const struct ip_tunnel_info *info = NULL; + bool ft_flow = mlx5e_is_ft_flow(flow); const struct flow_action_entry *act; bool encap = false; u32 action = 0; @@ -3261,6 +3273,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, return -EINVAL; } + if (ft_flow && out_dev == priv->netdev) { + /* Ignore forward to self rules generated + * by adding both mlx5 devs to the flow table + * block on a normal nft offload setup. + */ + return -EOPNOTSUPP; + } + if (attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) { NL_SET_ERR_MSG_MOD(extack, "can't support more output ports, can't offload forwarding"); @@ -3385,6 +3405,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, u32 dest_chain = act->chain_index; u32 max_chain = mlx5_eswitch_get_chain_range(esw); + if (ft_flow) { + NL_SET_ERR_MSG_MOD(extack, "Goto action is not supported"); + return -EOPNOTSUPP; + } if (dest_chain <= attr->chain) { NL_SET_ERR_MSG(extack, "Goto earlier chain isn't supported"); return -EOPNOTSUPP; @@ -3475,6 +3499,8 @@ static void get_flags(int flags, unsigned long *flow_flags) __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_ESWITCH); if (flags & MLX5_TC_FLAG(NIC_OFFLOAD)) __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_NIC); + if (flags & MLX5_TC_FLAG(FT_OFFLOAD)) + __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_FT); *flow_flags = __flow_flags; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 924c6ef86a14..262cdb7b69b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -44,7 +44,8 @@ enum { MLX5E_TC_FLAG_EGRESS_BIT, MLX5E_TC_FLAG_NIC_OFFLOAD_BIT, MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, - MLX5E_TC_FLAG_LAST_EXPORTED_BIT = MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, + MLX5E_TC_FLAG_FT_OFFLOAD_BIT, + MLX5E_TC_FLAG_LAST_EXPORTED_BIT = MLX5E_TC_FLAG_FT_OFFLOAD_BIT, }; #define MLX5_TC_FLAG(flag) BIT(MLX5E_TC_FLAG_##flag##_BIT) -- cgit v1.2.3-59-g8ed1b From 983db6198f0d0ee406f365069901387e7834c3c0 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 14 Nov 2019 11:54:19 +0200 Subject: mlxsw: spectrum_router: Allocate discard adjacency entry when needed Commit 0c3cbbf96def ("mlxsw: Add specific trap for packets routed via invalid nexthops") allocated an adjacency entry during driver initialization whose purpose is to discard packets hitting the route pointing to it. These adjacency entries are allocated from a resource called KVD linear (KVDL). There are situations in which the user can decide to set the size of this resource (via devlink-resource) to 0, in which case the driver will not be able to load. Therefore, instead of pre-allocating this adjacency entry, simply allocate it only when needed. A variable indicating the validity of the entry is added and is used to ensure it is only allocated and written once and that it is freed after all the routes were flushed. Fixes: 0c3cbbf96def ("mlxsw: Add specific trap for packets routed via invalid nexthops") Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 43 ++++++++++++++++------ 1 file changed, 32 insertions(+), 11 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 1aa436054490..517cb8b14b1d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -78,6 +78,7 @@ struct mlxsw_sp_router { const struct mlxsw_sp_rif_ops **rif_ops_arr; const struct mlxsw_sp_ipip_ops **ipip_ops_arr; u32 adj_discard_index; + bool adj_discard_index_valid; }; struct mlxsw_sp_rif { @@ -4203,13 +4204,33 @@ static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp, u16 rif_index) u32 adj_discard_index = mlxsw_sp->router->adj_discard_index; enum mlxsw_reg_ratr_trap_action trap_action; char ratr_pl[MLXSW_REG_RATR_LEN]; + int err; + + if (mlxsw_sp->router->adj_discard_index_valid) + return 0; + + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + &mlxsw_sp->router->adj_discard_index); + if (err) + return err; trap_action = MLXSW_REG_RATR_TRAP_ACTION_DISCARD_ERRORS; mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, MLXSW_REG_RATR_TYPE_ETHERNET, adj_discard_index, rif_index); mlxsw_reg_ratr_trap_action_set(ratr_pl, trap_action); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); + if (err) + goto err_ratr_write; + + mlxsw_sp->router->adj_discard_index_valid = true; + + return 0; + +err_ratr_write: + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + mlxsw_sp->router->adj_discard_index); + return err; } static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, @@ -5956,6 +5977,16 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) continue; mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV6); } + + /* After flushing all the routes, it is not possible anyone is still + * using the adjacency index that is discarding packets, so free it in + * case it was allocated. + */ + if (!mlxsw_sp->router->adj_discard_index_valid) + return; + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + mlxsw_sp->router->adj_discard_index); + mlxsw_sp->router->adj_discard_index_valid = false; } static void mlxsw_sp_router_fib_abort(struct mlxsw_sp *mlxsw_sp) @@ -8170,11 +8201,6 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_neigh_init; - err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, - &router->adj_discard_index); - if (err) - goto err_adj_discard_index_alloc; - mlxsw_sp->router->netevent_nb.notifier_call = mlxsw_sp_router_netevent_event; err = register_netevent_notifier(&mlxsw_sp->router->netevent_nb); @@ -8203,9 +8229,6 @@ err_dscp_init: err_mp_hash_init: unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); err_register_netevent_notifier: - mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, - router->adj_discard_index); -err_adj_discard_index_alloc: mlxsw_sp_neigh_fini(mlxsw_sp); err_neigh_init: mlxsw_sp_vrs_fini(mlxsw_sp); @@ -8237,8 +8260,6 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &mlxsw_sp->router->fib_nb); unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); - mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, - mlxsw_sp->router->adj_discard_index); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); mlxsw_sp_mr_fini(mlxsw_sp); -- cgit v1.2.3-59-g8ed1b From 34e59836565e36fade1464e054a3551c1a0364be Mon Sep 17 00:00:00 2001 From: Luigi Rizzo Date: Fri, 15 Nov 2019 12:12:25 -0800 Subject: net/mlx4_en: fix mlx4 ethtool -N insertion ethtool expects ETHTOOL_GRXCLSRLALL to set ethtool_rxnfc->data with the total number of entries in the rx classifier table. Surprisingly, mlx4 is missing this part (in principle ethtool could still move forward and try the insert). Tested: compiled and run command: phh13:~# ethtool -N eth1 flow-type udp4 queue 4 Added rule with ID 255 Signed-off-by: Luigi Rizzo Reviewed-by: Tariq Toukan --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index d8313e2ee600..c12da02c2d1b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1745,6 +1745,7 @@ static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, err = mlx4_en_get_flow(dev, cmd, cmd->fs.location); break; case ETHTOOL_GRXCLSRLALL: + cmd->data = MAX_NUM_OF_FS_RULES; while ((!err || err == -ENOENT) && priority < cmd->rule_cnt) { err = mlx4_en_get_flow(dev, cmd, i); if (!err) -- cgit v1.2.3-59-g8ed1b From 85192dbf4de08795afe2b88e52a36fc6abfc3dba Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 17 Nov 2019 09:28:03 -0800 Subject: bpf: Convert bpf_prog refcnt to atomic64_t Similarly to bpf_map's refcnt/usercnt, convert bpf_prog's refcnt to atomic64 and remove artificial 32k limit. This allows to make bpf_prog's refcounting non-failing, simplifying logic of users of bpf_prog_add/bpf_prog_inc. Validated compilation by running allyesconfig kernel build. Suggested-by: Daniel Borkmann Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20191117172806.2195367-3-andriin@fb.com --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++----- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 9 ++----- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 7 ++---- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 24 +++++------------- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 18 ++++---------- drivers/net/ethernet/qlogic/qede/qede_main.c | 8 ++---- drivers/net/virtio_net.c | 7 ++---- include/linux/bpf.h | 13 ++++------ kernel/bpf/inode.c | 5 ++-- kernel/bpf/syscall.c | 30 +++++++---------------- kernel/events/core.c | 7 ++---- 11 files changed, 40 insertions(+), 97 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c07172429c70..9da4fbee3cf7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3171,13 +3171,8 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) bnxt_init_rxbd_pages(ring, type); if (BNXT_RX_PAGE_MODE(bp) && bp->xdp_prog) { - rxr->xdp_prog = bpf_prog_add(bp->xdp_prog, 1); - if (IS_ERR(rxr->xdp_prog)) { - int rc = PTR_ERR(rxr->xdp_prog); - - rxr->xdp_prog = NULL; - return rc; - } + bpf_prog_add(bp->xdp_prog, 1); + rxr->xdp_prog = bp->xdp_prog; } prod = rxr->rx_prod; for (i = 0; i < bp->rx_ring_size; i++) { diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 40a44dcb3d9b..f28409279ea4 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1876,13 +1876,8 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog) if (nic->xdp_prog) { /* Attach BPF program */ - nic->xdp_prog = bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1); - if (!IS_ERR(nic->xdp_prog)) { - bpf_attached = true; - } else { - ret = PTR_ERR(nic->xdp_prog); - nic->xdp_prog = NULL; - } + bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1); + bpf_attached = true; } /* Calculate Tx queues needed for XDP and network stack */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index c26c0a7cbb6b..acc56606d3a5 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1807,11 +1807,8 @@ static int setup_xdp(struct net_device *dev, struct bpf_prog *prog) if (prog && !xdp_mtu_valid(priv, dev->mtu)) return -EINVAL; - if (prog) { - prog = bpf_prog_add(prog, priv->num_channels); - if (IS_ERR(prog)) - return PTR_ERR(prog); - } + if (prog) + bpf_prog_add(prog, priv->num_channels); up = netif_running(dev); need_update = (!!priv->xdp_prog != !!prog); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 40ec5acf79c0..d4697beeacc2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2286,11 +2286,7 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, lockdep_is_held(&priv->mdev->state_lock)); if (xdp_prog && carry_xdp_prog) { - xdp_prog = bpf_prog_add(xdp_prog, tmp->rx_ring_num); - if (IS_ERR(xdp_prog)) { - mlx4_en_free_resources(tmp); - return PTR_ERR(xdp_prog); - } + bpf_prog_add(xdp_prog, tmp->rx_ring_num); for (i = 0; i < tmp->rx_ring_num; i++) rcu_assign_pointer(tmp->rx_ring[i]->xdp_prog, xdp_prog); @@ -2782,11 +2778,9 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) * program for a new one. */ if (priv->tx_ring_num[TX_XDP] == xdp_ring_num) { - if (prog) { - prog = bpf_prog_add(prog, priv->rx_ring_num - 1); - if (IS_ERR(prog)) - return PTR_ERR(prog); - } + if (prog) + bpf_prog_add(prog, priv->rx_ring_num - 1); + mutex_lock(&mdev->state_lock); for (i = 0; i < priv->rx_ring_num; i++) { old_prog = rcu_dereference_protected( @@ -2807,13 +2801,8 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) if (!tmp) return -ENOMEM; - if (prog) { - prog = bpf_prog_add(prog, priv->rx_ring_num - 1); - if (IS_ERR(prog)) { - err = PTR_ERR(prog); - goto out; - } - } + if (prog) + bpf_prog_add(prog, priv->rx_ring_num - 1); mutex_lock(&mdev->state_lock); memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); @@ -2862,7 +2851,6 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) unlock_out: mutex_unlock(&mdev->state_lock); -out: kfree(tmp); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 772bfdbdeb9c..1d4a66fb466a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -408,12 +408,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->stats = &c->priv->channel_stats[c->ix].rq; INIT_WORK(&rq->recover_work, mlx5e_rq_err_cqe_work); - rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL; - if (IS_ERR(rq->xdp_prog)) { - err = PTR_ERR(rq->xdp_prog); - rq->xdp_prog = NULL; - goto err_rq_wq_destroy; - } + if (params->xdp_prog) + bpf_prog_inc(params->xdp_prog); + rq->xdp_prog = params->xdp_prog; rq_xdp_ix = rq->ix; if (xsk) @@ -4406,16 +4403,11 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) /* no need for full reset when exchanging programs */ reset = (!priv->channels.params.xdp_prog || !prog); - if (was_opened && !reset) { + if (was_opened && !reset) /* num_channels is invariant here, so we can take the * batched reference right upfront. */ - prog = bpf_prog_add(prog, priv->channels.num); - if (IS_ERR(prog)) { - err = PTR_ERR(prog); - goto unlock; - } - } + bpf_prog_add(prog, priv->channels.num); if (was_opened && reset) { struct mlx5e_channels new_channels = {}; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 8d1c208f778f..1e26964fe4e9 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -2107,12 +2107,8 @@ static int qede_start_queues(struct qede_dev *edev, bool clear_stats) if (rc) goto out; - fp->rxq->xdp_prog = bpf_prog_add(edev->xdp_prog, 1); - if (IS_ERR(fp->rxq->xdp_prog)) { - rc = PTR_ERR(fp->rxq->xdp_prog); - fp->rxq->xdp_prog = NULL; - goto out; - } + bpf_prog_add(edev->xdp_prog, 1); + fp->rxq->xdp_prog = edev->xdp_prog; } if (fp->type & QEDE_FASTPATH_TX) { diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 5a635f028bdc..4d7d5434cc5d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2445,11 +2445,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (!prog && !old_prog) return 0; - if (prog) { - prog = bpf_prog_add(prog, vi->max_queue_pairs - 1); - if (IS_ERR(prog)) - return PTR_ERR(prog); - } + if (prog) + bpf_prog_add(prog, vi->max_queue_pairs - 1); /* Make sure NAPI is not using any XDP TX queues for RX. */ if (netif_running(dev)) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 34a34445c009..fb606dc61a3a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -485,7 +485,7 @@ struct bpf_func_info_aux { }; struct bpf_prog_aux { - atomic_t refcnt; + atomic64_t refcnt; u32 used_map_cnt; u32 max_ctx_offset; u32 max_pkt_offset; @@ -770,9 +770,9 @@ extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv); -struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); +void bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); -struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); +void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); @@ -912,10 +912,8 @@ static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, return ERR_PTR(-EOPNOTSUPP); } -static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, - int i) +static inline void bpf_prog_add(struct bpf_prog *prog, int i) { - return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_prog_sub(struct bpf_prog *prog, int i) @@ -926,9 +924,8 @@ static inline void bpf_prog_put(struct bpf_prog *prog) { } -static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog) +static inline void bpf_prog_inc(struct bpf_prog *prog) { - return ERR_PTR(-EOPNOTSUPP); } static inline struct bpf_prog *__must_check diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 2f17f24258dc..ecf42bec38c0 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -31,7 +31,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: - raw = bpf_prog_inc(raw); + bpf_prog_inc(raw); break; case BPF_TYPE_MAP: bpf_map_inc_with_uref(raw); @@ -534,7 +534,8 @@ static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type if (!bpf_prog_get_ok(prog, &type, false)) return ERR_PTR(-EINVAL); - return bpf_prog_inc(prog); + bpf_prog_inc(prog); + return prog; } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 20030751b7a2..52fe4bacb330 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1339,7 +1339,7 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { - if (atomic_dec_and_test(&prog->aux->refcnt)) { + if (atomic64_dec_and_test(&prog->aux->refcnt)) { perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); @@ -1445,16 +1445,9 @@ static struct bpf_prog *____bpf_prog_get(struct fd f) return f.file->private_data; } -/* prog's refcnt limit */ -#define BPF_MAX_REFCNT 32768 - -struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) +void bpf_prog_add(struct bpf_prog *prog, int i) { - if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) { - atomic_sub(i, &prog->aux->refcnt); - return ERR_PTR(-EBUSY); - } - return prog; + atomic64_add(i, &prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_add); @@ -1465,13 +1458,13 @@ void bpf_prog_sub(struct bpf_prog *prog, int i) * path holds a reference to the program, thus atomic_sub() can * be safely used in such cases! */ - WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0); + WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0); } EXPORT_SYMBOL_GPL(bpf_prog_sub); -struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +void bpf_prog_inc(struct bpf_prog *prog) { - return bpf_prog_add(prog, 1); + atomic64_inc(&prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_inc); @@ -1480,12 +1473,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; - refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0); - - if (refold >= BPF_MAX_REFCNT) { - __bpf_prog_put(prog, false); - return ERR_PTR(-EBUSY); - } + refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); @@ -1523,7 +1511,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, goto out; } - prog = bpf_prog_inc(prog); + bpf_prog_inc(prog); out: fdput(f); return prog; @@ -1714,7 +1702,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) prog->orig_prog = NULL; prog->jited = 0; - atomic_set(&prog->aux->refcnt, 1); + atomic64_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0; if (bpf_prog_is_dev_bound(prog->aux)) { diff --git a/kernel/events/core.c b/kernel/events/core.c index aec8dba2bea4..73c616876597 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10477,12 +10477,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, context = parent_event->overflow_handler_context; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_EVENT_TRACING) if (overflow_handler == bpf_overflow_handler) { - struct bpf_prog *prog = bpf_prog_inc(parent_event->prog); + struct bpf_prog *prog = parent_event->prog; - if (IS_ERR(prog)) { - err = PTR_ERR(prog); - goto err_ns; - } + bpf_prog_inc(prog); event->prog = prog; event->orig_overflow_handler = parent_event->orig_overflow_handler; -- cgit v1.2.3-59-g8ed1b From 1fc1657775dc1b19e9ac1d46b4054ed8ae5d99ab Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Mon, 18 Nov 2019 09:18:42 +0200 Subject: mlxsw: spectrum_router: Fix determining underlay for a GRE tunnel The helper mlxsw_sp_ipip_dev_ul_tb_id() determines the underlay VRF of a GRE tunnel. For a tunnel without a bound device, it uses the same VRF that the tunnel is in. However in Linux, a GRE tunnel without a bound device uses the main VRF as the underlay. Fix the function accordingly. mlxsw further assumed that moving a tunnel to a different VRF could cause conflict in local tunnel endpoint address, which cannot be offloaded. However, the only way that an underlay could be changed by moving the tunnel device itself is if the tunnel device does not have a bound device. But in that case the underlay is always the main VRF, so there is no opportunity to introduce a conflict by moving such device. Thus this check constitutes a dead code, and can be removed, which do. Fixes: 6ddb7426a7d4 ("mlxsw: spectrum_router: Introduce loopback RIFs") Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index a330b369e899..39d600c8b92d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -994,7 +994,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) if (d) return l3mdev_fib_table(d) ? : RT_TABLE_MAIN; else - return l3mdev_fib_table(ol_dev) ? : RT_TABLE_MAIN; + return RT_TABLE_MAIN; } static struct mlxsw_sp_rif * @@ -1598,27 +1598,10 @@ static int mlxsw_sp_netdevice_ipip_ol_vrf_event(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_ipip_entry *ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev); - enum mlxsw_sp_l3proto ul_proto; - union mlxsw_sp_l3addr saddr; - u32 ul_tb_id; if (!ipip_entry) return 0; - /* For flat configuration cases, moving overlay to a different VRF might - * cause local address conflict, and the conflicting tunnels need to be - * demoted. - */ - ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev); - ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto; - saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev); - if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto, - saddr, ul_tb_id, - ipip_entry)) { - mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); - return 0; - } - return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry, true, false, false, extack); } -- cgit v1.2.3-59-g8ed1b From 2744bf42680f64ebf2ee8a00354897857c073331 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 18 Nov 2019 11:41:04 +0200 Subject: net/mlx4_en: Fix wrong limitation for number of TX rings XDP_TX rings should not be limited by max_num_tx_rings_p_up. To make sure total number of TX rings never exceed MAX_TX_RINGS, add similar check in mlx4_en_alloc_tx_queue_per_tc(), where a new value is assigned for num_up. Fixes: 7e1dc5e926d5 ("net/mlx4_en: Limit the number of TX rings") Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 8 ++++---- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 9 +++++++++ 2 files changed, 13 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index c12da02c2d1b..a1202e53710c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1812,6 +1812,7 @@ static int mlx4_en_set_channels(struct net_device *dev, struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_port_profile new_prof; struct mlx4_en_priv *tmp; + int total_tx_count; int port_up = 0; int xdp_count; int err = 0; @@ -1826,13 +1827,12 @@ static int mlx4_en_set_channels(struct net_device *dev, mutex_lock(&mdev->state_lock); xdp_count = priv->tx_ring_num[TX_XDP] ? channel->rx_count : 0; - if (channel->tx_count * priv->prof->num_up + xdp_count > - priv->mdev->profile.max_num_tx_rings_p_up * priv->prof->num_up) { + total_tx_count = channel->tx_count * priv->prof->num_up + xdp_count; + if (total_tx_count > MAX_TX_RINGS) { err = -EINVAL; en_err(priv, "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", - channel->tx_count * priv->prof->num_up + xdp_count, - MAX_TX_RINGS); + total_tx_count, MAX_TX_RINGS); goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 40ec5acf79c0..70fd246840e2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -91,6 +91,7 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc) struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_port_profile new_prof; struct mlx4_en_priv *tmp; + int total_count; int port_up = 0; int err = 0; @@ -104,6 +105,14 @@ int mlx4_en_alloc_tx_queue_per_tc(struct net_device *dev, u8 tc) MLX4_EN_NUM_UP_HIGH; new_prof.tx_ring_num[TX] = new_prof.num_tx_rings_p_up * new_prof.num_up; + total_count = new_prof.tx_ring_num[TX] + new_prof.tx_ring_num[TX_XDP]; + if (total_count > MAX_TX_RINGS) { + err = -EINVAL; + en_err(priv, + "Total number of TX and XDP rings (%d) exceeds the maximum supported (%d)\n", + total_count, MAX_TX_RINGS); + goto out; + } err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) goto out; -- cgit v1.2.3-59-g8ed1b From 6849c6d86bada8bd269fe0ee0c4a93892ccaf2c3 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Wed, 20 Nov 2019 00:15:21 +0000 Subject: net/mlx5e: Rx, Update page pool numa node when changed Once every napi poll cycle, check if numa node is different than the page pool's numa id, and update it using page_pool_update_nid(). Alternatively, we could have registered an irq affinity change handler, but page_pool_update_nid() must be called from napi context anyways, so the handler won't actually help. Performance testing: XDP drop/tx rate and TCP single/multi stream, on mlx5 driver while migrating rx ring irq from close to far numa: mlx5 internal page cache was locally disabled to get pure page pool results. CPU: Intel(R) Xeon(R) CPU E5-2603 v4 @ 1.70GHz NIC: Mellanox Technologies MT27700 Family [ConnectX-4] (100G) XDP Drop/TX single core: NUMA | XDP | Before | After --------------------------------------- Close | Drop | 11 Mpps | 10.9 Mpps Far | Drop | 4.4 Mpps | 5.8 Mpps Close | TX | 6.5 Mpps | 6.5 Mpps Far | TX | 3.5 Mpps | 4 Mpps Improvement is about 30% drop packet rate, 15% tx packet rate for numa far test. No degradation for numa close tests. TCP single/multi cpu/stream: NUMA | #cpu | Before | After -------------------------------------- Close | 1 | 18 Gbps | 18 Gbps Far | 1 | 15 Gbps | 18 Gbps Close | 12 | 80 Gbps | 80 Gbps Far | 12 | 68 Gbps | 80 Gbps In all test cases we see improvement for the far numa case, and no impact on the close numa case. Signed-off-by: Saeed Mahameed Acked-by: Jonathan Lemon Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 82cffb3a9964..9e9960146e5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1386,6 +1386,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) return 0; + if (rq->page_pool) + page_pool_nid_changed(rq->page_pool, numa_mem_id()); + if (rq->cqd.left) { work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget); if (rq->cqd.left || work_done >= budget) -- cgit v1.2.3-59-g8ed1b From a86db2269fca8019074b720baf2e0a35cddac4e9 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 31 Oct 2019 09:00:43 +0200 Subject: net/mlx5e: Fix error flow cleanup in mlx5e_tc_tun_create_header_ipv4/6 Be sure to release the neighbour in case of failures after successful route lookup. Fixes: 101f4de9dd52 ("net/mlx5e: Move TC tunnel offloading code to separate source file") Signed-off-by: Eli Cohen Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 13af72556987..745ab6cd7c30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -239,12 +239,15 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, if (max_encap_size < ipv4_encap_size) { mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", ipv4_encap_size, max_encap_size); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto out; } encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL); - if (!encap_header) - return -ENOMEM; + if (!encap_header) { + err = -ENOMEM; + goto out; + } /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule @@ -355,12 +358,15 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, if (max_encap_size < ipv6_encap_size) { mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", ipv6_encap_size, max_encap_size); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto out; } encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL); - if (!encap_header) - return -ENOMEM; + if (!encap_header) { + err = -ENOMEM; + goto out; + } /* used by mlx5e_detach_encap to lookup a neigh hash table * entry in the neigh hash table when a user deletes a rule -- cgit v1.2.3-59-g8ed1b From 7b83355f6df9ead2f8c4b06c105505a2999f5dc1 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 7 Nov 2019 09:07:34 +0200 Subject: net/mlx5e: Fix ingress rate configuration for representors Current code uses the old method of prio encoding in flow_cls_common_offload. Fix to follow the changes introduced in commit ef01adae0e43 ("net: sched: use major priority number as hardware priority"). Fixes: fcb64c0f5640 ("net/mlx5: E-Switch, add ingress rate support") Signed-off-by: Eli Cohen Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index fda0b37075e8..b7889d93ddca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4000,9 +4000,8 @@ int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, struct tc_cls_matchall_offload *ma) { struct netlink_ext_ack *extack = ma->common.extack; - int prio = TC_H_MAJ(ma->common.prio) >> 16; - if (prio != 1) { + if (ma->common.prio != 1) { NL_SET_ERR_MSG_MOD(extack, "only priority 1 is supported"); return -EINVAL; } -- cgit v1.2.3-59-g8ed1b From b6a4ac24c14be1247b0fd896737a01b8fa121318 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 7 Nov 2019 13:37:57 +0200 Subject: net/mlx5e: Reorder mirrer action parsing to check for encap first Mirred action parsing code in parse_tc_fdb_actions() first checks if out_dev has same parent id, and only verifies that there is a pending encap action that was parsed before. Recent change in vxlan module made function netdev_port_same_parent_id() to return true when called for mlx5 eswitch representor and vxlan device created explicitly on mlx5 representor device (vxlan devices created with "external" flag without explicitly specifying parent interface are not affected). With call to netdev_port_same_parent_id() returning true, incorrect code path is chosen and encap rules fail to offload because vxlan dev is not a valid eswitch forwarding dev. Dmesg log of error: [ 1784.389797] devices ens1f0_0 vxlan1 not on same switch HW, can't offload forwarding In order to fix the issue, rearrange conditional in parse_tc_fdb_actions() to check for pending encap action before checking if out_dev has the same parent id. Fixes: 0ce1822c2a08 ("vxlan: add adjacent link to limit depth level") Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 28 ++++++++++++------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index b7889d93ddca..f90a9f8e0fc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3268,7 +3268,20 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - if (netdev_port_same_parent_id(priv->netdev, out_dev)) { + if (encap) { + parse_attr->mirred_ifindex[attr->out_count] = + out_dev->ifindex; + parse_attr->tun_info[attr->out_count] = dup_tun_info(info); + if (!parse_attr->tun_info[attr->out_count]) + return -ENOMEM; + encap = false; + attr->dests[attr->out_count].flags |= + MLX5_ESW_DEST_ENCAP; + attr->out_count++; + /* attr->dests[].rep is resolved when we + * handle encap + */ + } else if (netdev_port_same_parent_id(priv->netdev, out_dev)) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); struct net_device *uplink_upper; @@ -3310,19 +3323,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, attr->dests[attr->out_count].rep = rpriv->rep; attr->dests[attr->out_count].mdev = out_priv->mdev; attr->out_count++; - } else if (encap) { - parse_attr->mirred_ifindex[attr->out_count] = - out_dev->ifindex; - parse_attr->tun_info[attr->out_count] = dup_tun_info(info); - if (!parse_attr->tun_info[attr->out_count]) - return -ENOMEM; - encap = false; - attr->dests[attr->out_count].flags |= - MLX5_ESW_DEST_ENCAP; - attr->out_count++; - /* attr->dests[].rep is resolved when we - * handle encap - */ } else if (parse_attr->filter_dev != priv->netdev) { /* All mlx5 devices are called to configure * high level device filters. Therefore, the -- cgit v1.2.3-59-g8ed1b From 829969956f97e880dd01086be47747226e48a3f0 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Mon, 4 Nov 2019 11:59:21 +0200 Subject: net/mlx5: DR, Fix invalid EQ vector number on CQ creation When creating a CQ, the CPU id is used for the vector value. This would fail in-case the CPU id was higher than the maximum vector value. Fixes: 297cccebdc5a ("net/mlx5: DR, Expose an internal API to issue RDMA operations") Signed-off-by: Alex Vesker Reviewed-by: Tariq Toukan Reviewed-by: Erez Shitrit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 5df8436b2ae3..51803eef13dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -700,6 +700,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, unsigned int irqn; void *cqc, *in; __be64 *pas; + int vector; u32 i; cq = kzalloc(sizeof(*cq), GFP_KERNEL); @@ -728,7 +729,8 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, if (!in) goto err_cqwq; - err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn); + vector = smp_processor_id() % mlx5_comp_vectors_count(mdev); + err = mlx5_vector2eqn(mdev, vector, &eqn, &irqn); if (err) { kvfree(in); goto err_cqwq; -- cgit v1.2.3-59-g8ed1b From 83e79489135bdf13590ad09f3341f9ef509c2cf9 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 31 Oct 2019 15:24:59 +0200 Subject: net/mlx5: DR, Skip rehash for tables with byte mask zero The byte mask fields affect on the hash index distribution, when the byte mask is zero, the hash calculation will always be equal to the same index. To avoid unneeded rehash of hash tables mark the table to skip rehash. This is needed by the next patch which will limit table rehash to reduce memory consumption. Fixes: 41d07074154c ("net/mlx5: DR, Expose steering rule functionality") Signed-off-by: Alex Vesker Reviewed-by: Erez Shitrit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 4efe1b0be4a8..80680765d59c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -671,7 +671,7 @@ static void dr_ste_set_ctrl(struct mlx5dr_ste_htbl *htbl) htbl->ctrl.may_grow = true; - if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1) + if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1 || !htbl->byte_mask) htbl->ctrl.may_grow = false; /* Threshold is 50%, one is added to table of size 1 */ -- cgit v1.2.3-59-g8ed1b From 21586a0fc44caf43c5ac5df9bb5620fdfb95ba92 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Sun, 10 Nov 2019 15:39:36 +0200 Subject: net/mlx5: DR, Limit STE hash table enlarge based on bytemask When an ste hash table has too many collision we enlarge it to a bigger hash table (rehash). Rehashing collision improvement depends on the bytemask value. The more 1 bits we have in bytemask means better spreading in the table. Without this fix tables can grow in size without providing any improvement which can lead to memory depletion and failures. This patch will limit table rehash to reduce memory and improve the performance. Fixes: 41d07074154c ("net/mlx5: DR, Expose steering rule functionality") Signed-off-by: Alex Vesker Reviewed-by: Erez Shitrit Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/steering/dr_rule.c | 15 +++++++++++++++ .../ethernet/mellanox/mlx5/core/steering/dr_ste.c | 20 -------------------- 2 files changed, 15 insertions(+), 20 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index 5dcb8baf491a..bd1699e62142 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -595,6 +595,18 @@ static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule, } } +static u16 dr_get_bits_per_mask(u16 byte_mask) +{ + u16 bits = 0; + + while (byte_mask) { + byte_mask = byte_mask & (byte_mask - 1); + bits++; + } + + return bits; +} + static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl, struct mlx5dr_domain *dmn, struct mlx5dr_domain_rx_tx *nic_dmn) @@ -607,6 +619,9 @@ static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl, if (!ctrl->may_grow) return false; + if (dr_get_bits_per_mask(htbl->byte_mask) * BITS_PER_BYTE <= htbl->chunk_size) + return false; + if (ctrl->num_of_collisions >= ctrl->increase_threshold && (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= ctrl->increase_threshold) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 80680765d59c..3cbf74b44d1f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -560,18 +560,6 @@ bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste) return !refcount_read(&ste->refcount); } -static u16 get_bits_per_mask(u16 byte_mask) -{ - u16 bits = 0; - - while (byte_mask) { - byte_mask = byte_mask & (byte_mask - 1); - bits++; - } - - return bits; -} - /* Init one ste as a pattern for ste data array */ void mlx5dr_ste_set_formatted_ste(u16 gvmi, struct mlx5dr_domain_rx_tx *nic_dmn, @@ -620,20 +608,12 @@ int mlx5dr_ste_create_next_htbl(struct mlx5dr_matcher *matcher, struct mlx5dr_ste_htbl *next_htbl; if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste->ste_chain_location)) { - u32 bits_in_mask; u8 next_lu_type; u16 byte_mask; next_lu_type = MLX5_GET(ste_general, hw_ste, next_lu_type); byte_mask = MLX5_GET(ste_general, hw_ste, byte_mask); - /* Don't allocate table more than required, - * the size of the table defined via the byte_mask, so no need - * to allocate more than that. - */ - bits_in_mask = get_bits_per_mask(byte_mask) * BITS_PER_BYTE; - log_table_size = min(log_table_size, bits_in_mask); - next_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, log_table_size, next_lu_type, -- cgit v1.2.3-59-g8ed1b From 751021218f7e66ee9bbaa2be23056e447cd75ec4 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Wed, 13 Nov 2019 14:42:00 +0200 Subject: net/mlx5e: Fix set vf link state error flow Before this commit the ndo always returned success. Fix that. Fixes: 1ab2068a4c66 ("net/mlx5: Implement vports admin state backup/restore") Signed-off-by: Roi Dayan Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 30aae76b6a1d..60fddf8afc99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2117,7 +2117,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, unlock: mutex_unlock(&esw->state_lock); - return 0; + return err; } int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, -- cgit v1.2.3-59-g8ed1b From 24960574505c49b102ca1dfa6bf109669bca2a66 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Sun, 17 Nov 2019 15:17:05 +0200 Subject: net/mlx5e: Do not use non-EXT link modes in EXT mode On some old Firmwares, connector type value was not supported, and value read from FW was 0. For those, driver used link mode in order to set connector type in link_ksetting. After FW exposed the connector type, driver translated the value to ethtool definitions. However, as 0 is a valid value, before returning PORT_OTHER, driver run the check of link mode in order to maintain backward compatibility. Cited patch added support to EXT mode. With both features (connector type and EXT link modes) ,if connector_type read from FW is 0 and EXT mode is set, driver mistakenly compare EXT link modes to non-EXT link mode. Fixed that by skipping this comparison if we are in EXT mode, as connector type value is valid in this scenario. Fixes: 6a897372417e ("net/mlx5: ethtool, Add ethtool support for 50Gbps per lane link modes") Signed-off-by: Eran Ben Elisha Reviewed-by: Aya Levin Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 327c93a7bd55..95601269fa2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -708,9 +708,9 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev, static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings *link_ksettings, u32 eth_proto_cap, - u8 connector_type) + u8 connector_type, bool ext) { - if (!connector_type || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) { + if ((!connector_type && !ext) || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) { if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR) | MLX5E_PROT_MASK(MLX5E_10GBASE_SR) | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4) @@ -842,9 +842,9 @@ static int ptys2connector_type[MLX5E_CONNECTOR_TYPE_NUMBER] = { [MLX5E_PORT_OTHER] = PORT_OTHER, }; -static u8 get_connector_port(u32 eth_proto, u8 connector_type) +static u8 get_connector_port(u32 eth_proto, u8 connector_type, bool ext) { - if (connector_type && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER) + if ((connector_type || ext) && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER) return ptys2connector_type[connector_type]; if (eth_proto & @@ -945,9 +945,9 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; link_ksettings->base.port = get_connector_port(eth_proto_oper, - connector_type); + connector_type, ext); ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin, - connector_type); + connector_type, ext); get_lp_advertising(mdev, eth_proto_lp, link_ksettings); if (an_status == MLX5_AN_COMPLETE) -- cgit v1.2.3-59-g8ed1b From 9c98f7ec01d78b5c12db97d1e5edb7022eefa398 Mon Sep 17 00:00:00 2001 From: Marina Varshaver Date: Tue, 19 Nov 2019 18:52:13 +0200 Subject: net/mlx5e: Add missing capability bit check for IP-in-IP Device that doesn't support IP-in-IP offloads has to filter csum and gso offload support, otherwise kernel will conclude that device is capable of offloading csum and gso for IP-in-IP tunnels and that might result in IP-in-IP tunnel not functioning. Fixes: 25948b87dda2 ("net/mlx5e: Support TSO and TX checksum offloads for IP-in-IP") Signed-off-by: Marina Varshaver Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 772bfdbdeb9c..2a56e66f58d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4252,9 +4252,12 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, switch (proto) { case IPPROTO_GRE: + return features; case IPPROTO_IPIP: case IPPROTO_IPV6: - return features; + if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP)) + return features; + break; case IPPROTO_UDP: udph = udp_hdr(skb); port = be16_to_cpu(udph->dest); -- cgit v1.2.3-59-g8ed1b From 97fd8da281f80e7e69e0114bc906575734d4dfaf Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 5 Sep 2019 09:56:10 +0300 Subject: net/mlx5: Fix auto group size calculation Once all the large flow groups (defined by the user when the flow table is created - max_num_groups) were created, then all the following new flow groups will have only one flow table entry, even though the flow table has place to larger groups. Fix the condition to prefer large flow group. Fixes: f0d22d187473 ("net/mlx5_core: Introduce flow steering autogrouped flow table") Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 ++++++---- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 1 + 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3bbb49354829..791e14ac26f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -579,7 +579,7 @@ static void del_sw_flow_group(struct fs_node *node) rhashtable_destroy(&fg->ftes_hash); ida_destroy(&fg->fte_allocator); - if (ft->autogroup.active) + if (ft->autogroup.active && fg->max_ftes == ft->autogroup.group_size) ft->autogroup.num_groups--; err = rhltable_remove(&ft->fgs_hash, &fg->hash, @@ -1126,6 +1126,8 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, ft->autogroup.active = true; ft->autogroup.required_groups = max_num_groups; + /* We save place for flow groups in addition to max types */ + ft->autogroup.group_size = ft->max_fte / (max_num_groups + 1); return ft; } @@ -1328,8 +1330,7 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft return ERR_PTR(-ENOENT); if (ft->autogroup.num_groups < ft->autogroup.required_groups) - /* We save place for flow groups in addition to max types */ - group_size = ft->max_fte / (ft->autogroup.required_groups + 1); + group_size = ft->autogroup.group_size; /* ft->max_fte == ft->autogroup.max_types */ if (group_size == 0) @@ -1356,7 +1357,8 @@ static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table *ft if (IS_ERR(fg)) goto out; - ft->autogroup.num_groups++; + if (group_size == ft->autogroup.group_size) + ft->autogroup.num_groups++; out: return fg; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 00717eba2256..c2621b911563 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -162,6 +162,7 @@ struct mlx5_flow_table { struct { bool active; unsigned int required_groups; + unsigned int group_size; unsigned int num_groups; } autogroup; /* Protect fwd_rules */ -- cgit v1.2.3-59-g8ed1b From b7eca940322f47fd30dafb70da04d193a0154090 Mon Sep 17 00:00:00 2001 From: Shani Shapp Date: Tue, 12 Nov 2019 15:10:00 +0200 Subject: net/mlx5: Update the list of the PCI supported devices Add the upcoming ConnectX-6 LX device ID. Fixes: 85327a9c4150 ("net/mlx5: Update the list of the PCI supported devices") Signed-off-by: Shani Shapp Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e47dd7c1b909..50ab88d80033 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1566,6 +1566,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF}, /* ConnectX-6 VF */ { PCI_VDEVICE(MELLANOX, 0x101d) }, /* ConnectX-6 Dx */ { PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF}, /* ConnectX Family mlx5Gen Virtual Function */ + { PCI_VDEVICE(MELLANOX, 0x101f) }, /* ConnectX-6 LX */ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ -- cgit v1.2.3-59-g8ed1b From 30e9e0550bf693c94bc15827781fe42dd60be634 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Sun, 17 Nov 2019 10:18:59 +0200 Subject: net/mlxfw: Verify FSM error code translation doesn't exceed array size Array mlxfw_fsm_state_err_str contains value to string translation, when values are provided by mlxfw_dev. If value is larger than MLXFW_FSM_STATE_ERR_MAX, return "unknown error" as expected instead of reading an address than exceed array size. Fixes: 410ed13cae39 ("Add the mlxfw module for Mellanox firmware flash process") Signed-off-by: Eran Ben Elisha Acked-by: Jiri Pirko Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c index 67990406cba2..29e95d0a6ad1 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c @@ -66,6 +66,8 @@ retry: return err; if (fsm_state_err != MLXFW_FSM_STATE_ERR_OK) { + fsm_state_err = min_t(enum mlxfw_fsm_state_err, + fsm_state_err, MLXFW_FSM_STATE_ERR_MAX); pr_err("Firmware flash failed: %s\n", mlxfw_fsm_state_err_str[fsm_state_err]); NL_SET_ERR_MSG_MOD(extack, "Firmware flash failed"); -- cgit v1.2.3-59-g8ed1b From ab118da4c10a70b8437f5c90ab77adae1835963e Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 13 Nov 2019 12:03:47 +0200 Subject: net/mlx5: Don't write read-only fields in MODIFY_HCA_VPORT_CONTEXT command The MODIFY_HCA_VPORT_CONTEXT uses field_selector to mask fields needed to be written, other fields are required to be zero according to the HW specification. The supported fields are controlled by bitfield and limited to vport state, node and port GUIDs. Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/vport.c | 27 +++++++------------------ 1 file changed, 7 insertions(+), 20 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 30f7848a6f88..1faac31f74d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -1064,26 +1064,13 @@ int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev, ctx = MLX5_ADDR_OF(modify_hca_vport_context_in, in, hca_vport_context); MLX5_SET(hca_vport_context, ctx, field_select, req->field_select); - MLX5_SET(hca_vport_context, ctx, sm_virt_aware, req->sm_virt_aware); - MLX5_SET(hca_vport_context, ctx, has_smi, req->has_smi); - MLX5_SET(hca_vport_context, ctx, has_raw, req->has_raw); - MLX5_SET(hca_vport_context, ctx, vport_state_policy, req->policy); - MLX5_SET(hca_vport_context, ctx, port_physical_state, req->phys_state); - MLX5_SET(hca_vport_context, ctx, vport_state, req->vport_state); - MLX5_SET64(hca_vport_context, ctx, port_guid, req->port_guid); - MLX5_SET64(hca_vport_context, ctx, node_guid, req->node_guid); - MLX5_SET(hca_vport_context, ctx, cap_mask1, req->cap_mask1); - MLX5_SET(hca_vport_context, ctx, cap_mask1_field_select, req->cap_mask1_perm); - MLX5_SET(hca_vport_context, ctx, cap_mask2, req->cap_mask2); - MLX5_SET(hca_vport_context, ctx, cap_mask2_field_select, req->cap_mask2_perm); - MLX5_SET(hca_vport_context, ctx, lid, req->lid); - MLX5_SET(hca_vport_context, ctx, init_type_reply, req->init_type_reply); - MLX5_SET(hca_vport_context, ctx, lmc, req->lmc); - MLX5_SET(hca_vport_context, ctx, subnet_timeout, req->subnet_timeout); - MLX5_SET(hca_vport_context, ctx, sm_lid, req->sm_lid); - MLX5_SET(hca_vport_context, ctx, sm_sl, req->sm_sl); - MLX5_SET(hca_vport_context, ctx, qkey_violation_counter, req->qkey_violation_counter); - MLX5_SET(hca_vport_context, ctx, pkey_violation_counter, req->pkey_violation_counter); + if (req->field_select & MLX5_HCA_VPORT_SEL_STATE_POLICY) + MLX5_SET(hca_vport_context, ctx, vport_state_policy, + req->policy); + if (req->field_select & MLX5_HCA_VPORT_SEL_PORT_GUID) + MLX5_SET64(hca_vport_context, ctx, port_guid, req->port_guid); + if (req->field_select & MLX5_HCA_VPORT_SEL_NODE_GUID) + MLX5_SET64(hca_vport_context, ctx, node_guid, req->node_guid); err = mlx5_cmd_exec(dev, in, in_sz, out, sizeof(out)); ex: kfree(in); -- cgit v1.2.3-59-g8ed1b From 6e9e286e4ad53311b51b28fdc4b952ab7d2520c4 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 28 Oct 2019 16:30:27 +0200 Subject: net/mlx5: DR, Refactor VXLAN GPE flex parser tunnel code for SW steering Refactor flex parser tunnel code: - Add definition for flex parser tunneling header for VXLAN-GPE - Use macros for VXLAN-GPE SW steering when building STE - Refactor the code to reflect that this is a VXLAN GPE only code and not a general flex parser code. This also significantly simplifies addition of more flex parser protocols, such as Geneve. Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/steering/dr_matcher.c | 33 ++++++---- .../ethernet/mellanox/mlx5/core/steering/dr_ste.c | 73 +++++++++------------- .../mellanox/mlx5/core/steering/dr_types.h | 6 +- .../mellanox/mlx5/core/steering/mlx5_ifc_dr.h | 11 ++++ 4 files changed, 66 insertions(+), 57 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index c6548980daf0..f177c468b740 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -102,13 +102,29 @@ static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc) DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), gre) || \ DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), udp)) -static bool dr_mask_is_flex_parser_tnl_set(struct mlx5dr_match_misc3 *misc3) +static bool +dr_mask_is_misc3_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3) { return (misc3->outer_vxlan_gpe_vni || misc3->outer_vxlan_gpe_next_protocol || misc3->outer_vxlan_gpe_flags); } +static bool +dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_protocols & + MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED; +} + +static bool +dr_mask_is_flex_parser_tnl_vxlan_gpe_set(struct mlx5dr_match_param *mask, + struct mlx5dr_domain *dmn) +{ + return dr_mask_is_misc3_vxlan_gpe_set(&mask->misc3) && + dr_matcher_supp_flex_parser_vxlan_gpe(&dmn->info.caps); +} + static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3) { return (misc3->icmpv6_type || misc3->icmpv6_code || @@ -137,13 +153,6 @@ static bool dr_mask_is_gvmi_or_qpn_set(struct mlx5dr_match_misc *misc) return (misc->source_sqn || misc->source_port); } -static bool -dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_domain *dmn) -{ - return dmn->info.caps.flex_protocols & - MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED; -} - int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher, enum mlx5dr_ipv outer_ipv, @@ -262,10 +271,10 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, inner, rx); } - if (dr_mask_is_flex_parser_tnl_set(&mask.misc3) && - dr_matcher_supp_flex_parser_vxlan_gpe(dmn)) - mlx5dr_ste_build_flex_parser_tnl(&sb[idx++], &mask, - inner, rx); + if (dr_mask_is_flex_parser_tnl_vxlan_gpe_set(&mask, dmn)) + mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(&sb[idx++], + &mask, + inner, rx); if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer)) mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 7e9d6cfc356f..7a906938ceb9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -2103,68 +2103,57 @@ void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb, sb->ste_build_tag_func = &dr_ste_build_eth_l4_misc_tag; } -static void dr_ste_build_flex_parser_tnl_bit_mask(struct mlx5dr_match_param *value, - bool inner, u8 *bit_mask) +static void +dr_ste_build_flex_parser_tnl_vxlan_gpe_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) { struct mlx5dr_match_misc3 *misc_3_mask = &value->misc3; - if (misc_3_mask->outer_vxlan_gpe_flags || - misc_3_mask->outer_vxlan_gpe_next_protocol) { - MLX5_SET(ste_flex_parser_tnl, bit_mask, - flex_parser_tunneling_header_63_32, - (misc_3_mask->outer_vxlan_gpe_flags << 24) | - (misc_3_mask->outer_vxlan_gpe_next_protocol)); - misc_3_mask->outer_vxlan_gpe_flags = 0; - misc_3_mask->outer_vxlan_gpe_next_protocol = 0; - } - - if (misc_3_mask->outer_vxlan_gpe_vni) { - MLX5_SET(ste_flex_parser_tnl, bit_mask, - flex_parser_tunneling_header_31_0, - misc_3_mask->outer_vxlan_gpe_vni << 8); - misc_3_mask->outer_vxlan_gpe_vni = 0; - } + DR_STE_SET_MASK_V(flex_parser_tnl_vxlan_gpe, bit_mask, + outer_vxlan_gpe_flags, + misc_3_mask, outer_vxlan_gpe_flags); + DR_STE_SET_MASK_V(flex_parser_tnl_vxlan_gpe, bit_mask, + outer_vxlan_gpe_next_protocol, + misc_3_mask, outer_vxlan_gpe_next_protocol); + DR_STE_SET_MASK_V(flex_parser_tnl_vxlan_gpe, bit_mask, + outer_vxlan_gpe_vni, + misc_3_mask, outer_vxlan_gpe_vni); } -static int dr_ste_build_flex_parser_tnl_tag(struct mlx5dr_match_param *value, - struct mlx5dr_ste_build *sb, - u8 *hw_ste_p) +static int +dr_ste_build_flex_parser_tnl_vxlan_gpe_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) { struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; struct mlx5dr_match_misc3 *misc3 = &value->misc3; u8 *tag = hw_ste->tag; - if (misc3->outer_vxlan_gpe_flags || - misc3->outer_vxlan_gpe_next_protocol) { - MLX5_SET(ste_flex_parser_tnl, tag, - flex_parser_tunneling_header_63_32, - (misc3->outer_vxlan_gpe_flags << 24) | - (misc3->outer_vxlan_gpe_next_protocol)); - misc3->outer_vxlan_gpe_flags = 0; - misc3->outer_vxlan_gpe_next_protocol = 0; - } - - if (misc3->outer_vxlan_gpe_vni) { - MLX5_SET(ste_flex_parser_tnl, tag, - flex_parser_tunneling_header_31_0, - misc3->outer_vxlan_gpe_vni << 8); - misc3->outer_vxlan_gpe_vni = 0; - } + DR_STE_SET_TAG(flex_parser_tnl_vxlan_gpe, tag, + outer_vxlan_gpe_flags, misc3, + outer_vxlan_gpe_flags); + DR_STE_SET_TAG(flex_parser_tnl_vxlan_gpe, tag, + outer_vxlan_gpe_next_protocol, misc3, + outer_vxlan_gpe_next_protocol); + DR_STE_SET_TAG(flex_parser_tnl_vxlan_gpe, tag, + outer_vxlan_gpe_vni, misc3, + outer_vxlan_gpe_vni); return 0; } -void mlx5dr_ste_build_flex_parser_tnl(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx) +void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) { - dr_ste_build_flex_parser_tnl_bit_mask(mask, inner, sb->bit_mask); + dr_ste_build_flex_parser_tnl_vxlan_gpe_bit_mask(mask, inner, + sb->bit_mask); sb->rx = rx; sb->inner = inner; sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER; sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); - sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_tag; + sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_vxlan_gpe_tag; } static void dr_ste_build_register_0_bit_mask(struct mlx5dr_match_param *value, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index c1f45a60ee6b..a64af56b825f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -325,9 +325,9 @@ int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, struct mlx5dr_cmd_caps *caps, bool inner, bool rx); -void mlx5dr_ste_build_flex_parser_tnl(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx); +void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h index 596c927220d9..6d78b027fe56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h @@ -548,6 +548,17 @@ struct mlx5_ifc_ste_flex_parser_tnl_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_ste_flex_parser_tnl_vxlan_gpe_bits { + u8 outer_vxlan_gpe_flags[0x8]; + u8 reserved_at_8[0x10]; + u8 outer_vxlan_gpe_next_protocol[0x8]; + + u8 outer_vxlan_gpe_vni[0x18]; + u8 reserved_at_38[0x8]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_ste_general_purpose_bits { u8 general_purpose_lookup_field[0x20]; -- cgit v1.2.3-59-g8ed1b From a18fab48dbacbb7ff104a13e987778b7995bec07 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 28 Oct 2019 16:58:53 +0200 Subject: net/mlx5: DR, Add HW bits and definitions for Geneve flex parser Add definition for flex parser tunneling header for Geneve. Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h | 13 +++++++++++++ include/linux/mlx5/mlx5_ifc.h | 1 + 2 files changed, 14 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h index 6d78b027fe56..1722f4668269 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h @@ -559,6 +559,19 @@ struct mlx5_ifc_ste_flex_parser_tnl_vxlan_gpe_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_ste_flex_parser_tnl_geneve_bits { + u8 reserved_at_0[0x2]; + u8 geneve_opt_len[0x6]; + u8 geneve_oam[0x1]; + u8 reserved_at_9[0x7]; + u8 geneve_protocol_type[0x10]; + + u8 geneve_vni[0x18]; + u8 reserved_at_38[0x8]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_ste_general_purpose_bits { u8 general_purpose_lookup_field[0x20]; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4f912d4e67bc..5d54fccf87fc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1110,6 +1110,7 @@ enum { }; enum { + MLX5_FLEX_PARSER_GENEVE_ENABLED = 1 << 3, MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED = 1 << 7, MLX5_FLEX_PARSER_ICMP_V4_ENABLED = 1 << 8, MLX5_FLEX_PARSER_ICMP_V6_ENABLED = 1 << 9, -- cgit v1.2.3-59-g8ed1b From b6d12238459d2f3c1140689c8fbb1bf1e0fe1927 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 28 Oct 2019 17:22:06 +0200 Subject: net/mlx5: DR, Add support for Geneve packets SW steering Add support for SW steering matching on Geneve header fields: - VNI - OAM - protocol type - options length Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/steering/dr_matcher.c | 27 +++++++++++ .../ethernet/mellanox/mlx5/core/steering/dr_ste.c | 53 ++++++++++++++++++++++ .../mellanox/mlx5/core/steering/dr_types.h | 3 ++ 3 files changed, 83 insertions(+) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index f177c468b740..c6dbd856df94 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -125,6 +125,29 @@ dr_mask_is_flex_parser_tnl_vxlan_gpe_set(struct mlx5dr_match_param *mask, dr_matcher_supp_flex_parser_vxlan_gpe(&dmn->info.caps); } +static bool dr_mask_is_misc_geneve_set(struct mlx5dr_match_misc *misc) +{ + return misc->geneve_vni || + misc->geneve_oam || + misc->geneve_protocol_type || + misc->geneve_opt_len; +} + +static bool +dr_matcher_supp_flex_parser_geneve(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_protocols & + MLX5_FLEX_PARSER_GENEVE_ENABLED; +} + +static bool +dr_mask_is_flex_parser_tnl_geneve_set(struct mlx5dr_match_param *mask, + struct mlx5dr_domain *dmn) +{ + return dr_mask_is_misc_geneve_set(&mask->misc) && + dr_matcher_supp_flex_parser_geneve(&dmn->info.caps); +} + static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3) { return (misc3->icmpv6_type || misc3->icmpv6_code || @@ -275,6 +298,10 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(&sb[idx++], &mask, inner, rx); + else if (dr_mask_is_flex_parser_tnl_geneve_set(&mask, dmn)) + mlx5dr_ste_build_flex_parser_tnl_geneve(&sb[idx++], + &mask, + inner, rx); if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer)) mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 7a906938ceb9..53068d508b21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -2156,6 +2156,59 @@ void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_vxlan_gpe_tag; } +static void +dr_ste_build_flex_parser_tnl_geneve_bit_mask(struct mlx5dr_match_param *value, + u8 *bit_mask) +{ + struct mlx5dr_match_misc *misc_mask = &value->misc; + + DR_STE_SET_MASK_V(flex_parser_tnl_geneve, bit_mask, + geneve_protocol_type, + misc_mask, geneve_protocol_type); + DR_STE_SET_MASK_V(flex_parser_tnl_geneve, bit_mask, + geneve_oam, + misc_mask, geneve_oam); + DR_STE_SET_MASK_V(flex_parser_tnl_geneve, bit_mask, + geneve_opt_len, + misc_mask, geneve_opt_len); + DR_STE_SET_MASK_V(flex_parser_tnl_geneve, bit_mask, + geneve_vni, + misc_mask, geneve_vni); +} + +static int +dr_ste_build_flex_parser_tnl_geneve_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc *misc = &value->misc; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(flex_parser_tnl_geneve, tag, + geneve_protocol_type, misc, geneve_protocol_type); + DR_STE_SET_TAG(flex_parser_tnl_geneve, tag, + geneve_oam, misc, geneve_oam); + DR_STE_SET_TAG(flex_parser_tnl_geneve, tag, + geneve_opt_len, misc, geneve_opt_len); + DR_STE_SET_TAG(flex_parser_tnl_geneve, tag, + geneve_vni, misc, geneve_vni); + + return 0; +} + +void mlx5dr_ste_build_flex_parser_tnl_geneve(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_flex_parser_tnl_geneve_bit_mask(mask, sb->bit_mask); + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_geneve_tag; +} + static void dr_ste_build_register_0_bit_mask(struct mlx5dr_match_param *value, u8 *bit_mask) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index a64af56b825f..290fe61c33d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -328,6 +328,9 @@ int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb, void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); +void mlx5dr_ste_build_flex_parser_tnl_geneve(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); -- cgit v1.2.3-59-g8ed1b From e689e998e102100bdf7991763d4c244704846f2d Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 1 Nov 2019 15:38:30 -0700 Subject: net/mlx5e: TC, Stub out ipv6 tun create header function Improve mlx5e_route_lookup_ipv6 function structure by avoiding #ifdef then return -EOPNOTSUPP in the middle of the function code. To do so, we stub out mlx5e_tc_tun_create_header_ipv6 which is the only caller of this helper function to avoid calling it altogether when ipv6 is compiled out, which should also cleanup some compiler warnings of unused variables. Signed-off-by: Saeed Mahameed Reviewed-by: Eli Cohen Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 4 ---- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h | 7 +++++++ 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 5316cedd78bf..fe227713fe94 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -141,7 +141,6 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, struct dst_entry *dst; struct neighbour *n; -#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) int ret; ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst, @@ -157,9 +156,6 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, dst_release(dst); return ret; } -#else - return -EOPNOTSUPP; -#endif n = dst_neigh_lookup(dst, &fl6->daddr); dst_release(dst); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h index c362b9225dc2..6f9a78c85ffd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -58,9 +58,16 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, struct net_device *mirred_dev, struct mlx5e_encap_entry *e); +#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, struct net_device *mirred_dev, struct mlx5e_encap_entry *e); +#else +static inline int +mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct mlx5e_encap_entry *e) { return -EOPNOTSUPP; } +#endif bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv, struct net_device *netdev); -- cgit v1.2.3-59-g8ed1b From 90ac245814abc30d2423474310654d31e3908b2f Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 31 Oct 2019 09:12:18 +0200 Subject: net/mlx5e: Remove redundant pointer check When code reaches the "out" label, n is guaranteed to be valid so we can unconditionally call neigh_release. Also change the label to release_neigh to better reflect the fact that we unconditionally free the neighbour and also match other labels convention. Signed-off-by: Eli Cohen Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index fe227713fe94..784b1e26f414 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -236,13 +236,13 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", ipv4_encap_size, max_encap_size); err = -EOPNOTSUPP; - goto out; + goto release_neigh; } encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL); if (!encap_header) { err = -ENOMEM; - goto out; + goto release_neigh; } /* used by mlx5e_detach_encap to lookup a neigh hash table @@ -294,7 +294,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, /* the encap entry will be made valid on neigh update event * and not used before that. */ - goto out; + goto release_neigh; } e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, e->reformat_type, @@ -314,9 +314,8 @@ destroy_neigh_entry: mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); free_encap: kfree(encap_header); -out: - if (n) - neigh_release(n); +release_neigh: + neigh_release(n); return err; } @@ -355,13 +354,13 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n", ipv6_encap_size, max_encap_size); err = -EOPNOTSUPP; - goto out; + goto release_neigh; } encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL); if (!encap_header) { err = -ENOMEM; - goto out; + goto release_neigh; } /* used by mlx5e_detach_encap to lookup a neigh hash table @@ -412,7 +411,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, /* the encap entry will be made valid on neigh update event * and not used before that. */ - goto out; + goto release_neigh; } e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, @@ -433,9 +432,8 @@ destroy_neigh_entry: mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); free_encap: kfree(encap_header); -out: - if (n) - neigh_release(n); +release_neigh: + neigh_release(n); return err; } -- cgit v1.2.3-59-g8ed1b From ab818362c9054beb950b97a09ce7b0d56f5a32a1 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 22 Nov 2019 08:15:19 +0000 Subject: net: use rhashtable_lookup() instead of rhashtable_lookup_fast() rhashtable_lookup_fast() internally calls rcu_read_lock() then, calls rhashtable_lookup(). So if rcu_read_lock() is already held, rhashtable_lookup() is enough. Signed-off-by: Taehee Yoo Signed-off-by: Jakub Kicinski --- drivers/infiniband/hw/hfi1/sdma.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- drivers/net/ethernet/netronome/nfp/bpf/offload.c | 4 ++-- net/tipc/socket.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index c61b6022575e..5774dfc22e18 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -881,8 +881,8 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd, cpu_id = smp_processor_id(); rcu_read_lock(); - rht_node = rhashtable_lookup_fast(dd->sdma_rht, &cpu_id, - sdma_rht_params); + rht_node = rhashtable_lookup(dd->sdma_rht, &cpu_id, + sdma_rht_params); if (rht_node && rht_node->map[vl]) { struct sdma_rht_map_elem *map = rht_node->map[vl]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 761fc35c4aab..0d5d84b5fa23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3876,7 +3876,7 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv, int err; rcu_read_lock(); - flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); + flow = rhashtable_lookup(tc_ht, &f->cookie, tc_ht_params); if (!flow || !same_flow_direction(flow, flags)) { err = -EINVAL; goto errout; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 06927ba5a3ae..95a0d3910e31 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -458,8 +458,8 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data, return -EINVAL; rcu_read_lock(); - record = rhashtable_lookup_fast(&bpf->maps_neutral, &map_id, - nfp_bpf_maps_neutral_params); + record = rhashtable_lookup(&bpf->maps_neutral, &map_id, + nfp_bpf_maps_neutral_params); if (!record || map_id_full > U32_MAX) { rcu_read_unlock(); cmsg_warn(bpf, "perf event: map id %lld (0x%llx) not recognized, dropping event\n", diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 5d7859aac78e..a1c8d722ca20 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2880,7 +2880,7 @@ static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid) struct tipc_sock *tsk; rcu_read_lock(); - tsk = rhashtable_lookup_fast(&tn->sk_rht, &portid, tsk_rht_params); + tsk = rhashtable_lookup(&tn->sk_rht, &portid, tsk_rht_params); if (tsk) sock_hold(&tsk->sk); rcu_read_unlock(); -- cgit v1.2.3-59-g8ed1b From c5731cc5ebcbfdb0b34c7ce29d488c52d8af957b Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Sun, 24 Nov 2019 09:48:02 +0200 Subject: mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels When a GRE tunnel is bound to an underlay netdevice and that netdevice is moved to a different VRF, that could cause two tunnels to have the same underlay local address in the same VRF. Linux in this situation dispatches the traffic according to the tunnel key (or lack thereof), but that cannot be offloaded to Spectrum devices. Detect this situation and unoffload the two impacted tunnels when it happens. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 39 +++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 86e25824fcd8..4c4d99ab15a0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1614,8 +1614,25 @@ static int mlxsw_sp_netdevice_ipip_ul_vrf_event(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry, struct net_device *ul_dev, + bool *demote_this, struct netlink_ext_ack *extack) { + u32 ul_tb_id = l3mdev_fib_table(ul_dev) ? : RT_TABLE_MAIN; + enum mlxsw_sp_l3proto ul_proto; + union mlxsw_sp_l3addr saddr; + + /* Moving underlay to a different VRF might cause local address + * conflict, and the conflicting tunnels need to be demoted. + */ + ul_proto = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto; + saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ipip_entry->ol_dev); + if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, ul_proto, + saddr, ul_tb_id, + ipip_entry)) { + *demote_this = true; + return 0; + } + return __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry, true, true, false, extack); } @@ -1766,6 +1783,7 @@ static int __mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry, struct net_device *ul_dev, + bool *demote_this, unsigned long event, struct netdev_notifier_info *info) { @@ -1780,6 +1798,7 @@ __mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_netdevice_ipip_ul_vrf_event(mlxsw_sp, ipip_entry, ul_dev, + demote_this, extack); break; @@ -1806,13 +1825,31 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, while ((ipip_entry = mlxsw_sp_ipip_entry_find_by_ul_dev(mlxsw_sp, ul_dev, ipip_entry))) { + struct mlxsw_sp_ipip_entry *prev; + bool demote_this = false; + err = __mlxsw_sp_netdevice_ipip_ul_event(mlxsw_sp, ipip_entry, - ul_dev, event, info); + ul_dev, &demote_this, + event, info); if (err) { mlxsw_sp_ipip_demote_tunnel_by_ul_netdev(mlxsw_sp, ul_dev); return err; } + + if (demote_this) { + if (list_is_first(&ipip_entry->ipip_list_node, + &mlxsw_sp->router->ipip_list)) + prev = NULL; + else + /* This can't be cached from previous iteration, + * because that entry could be gone now. + */ + prev = list_prev_entry(ipip_entry, + ipip_list_node); + mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); + ipip_entry = prev; + } } return 0; -- cgit v1.2.3-59-g8ed1b From ed43cff065d7ca2ffa60a7a1ea62be4a574529f9 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Sun, 24 Nov 2019 09:48:03 +0200 Subject: mlxsw: spectrum_router: Fix use of uninitialized adjacency index When mlxsw_sp_adj_discard_write() is called for the first time, the value stored in 'mlxsw_sp->router->adj_discard_index' is invalid, as indicated by 'mlxsw_sp->router->adj_discard_index_valid' being set to 'false'. In this case, we should not use the value initially stored in 'mlxsw_sp->router->adj_discard_index' (0) and instead use the value allocated later in the function. Fixes: 983db6198f0d ("mlxsw: spectrum_router: Allocate discard adjacency entry when needed") Signed-off-by: Amit Cohen Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'drivers/net/ethernet/mellanox') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 4c4d99ab15a0..30bfe3880faf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -4221,7 +4221,6 @@ mlxsw_sp_fib_entry_ralue_pack(char *ralue_pl, static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp, u16 rif_index) { - u32 adj_discard_index = mlxsw_sp->router->adj_discard_index; enum mlxsw_reg_ratr_trap_action trap_action; char ratr_pl[MLXSW_REG_RATR_LEN]; int err; @@ -4236,8 +4235,8 @@ static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp, u16 rif_index) trap_action = MLXSW_REG_RATR_TRAP_ACTION_DISCARD_ERRORS; mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, - MLXSW_REG_RATR_TYPE_ETHERNET, adj_discard_index, - rif_index); + MLXSW_REG_RATR_TYPE_ETHERNET, + mlxsw_sp->router->adj_discard_index, rif_index); mlxsw_reg_ratr_trap_action_set(ratr_pl, trap_action); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); if (err) -- cgit v1.2.3-59-g8ed1b