diff options
66 files changed, 1729 insertions, 719 deletions
diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig index 5e4f74286ea3..e1c23d1e91e6 100644 --- a/drivers/net/dsa/microchip/Kconfig +++ b/drivers/net/dsa/microchip/Kconfig @@ -5,7 +5,6 @@ config NET_DSA_MICROCHIP_KSZ_COMMON menuconfig NET_DSA_MICROCHIP_KSZ9477 tristate "Microchip KSZ9477 series switch support" depends on NET_DSA - select NET_DSA_TAG_KSZ9477 select NET_DSA_MICROCHIP_KSZ_COMMON help This driver adds support for Microchip KSZ9477 switch chips. diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index ae80b3c6dea2..a23d3ffdf0c4 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -18,7 +18,6 @@ #include <net/dsa.h> #include <net/switchdev.h> -#include "ksz_priv.h" #include "ksz_common.h" #include "ksz8795_reg.h" diff --git a/drivers/net/dsa/microchip/ksz8795_spi.c b/drivers/net/dsa/microchip/ksz8795_spi.c index 50aa0d24effb..d0f8153e86b7 100644 --- a/drivers/net/dsa/microchip/ksz8795_spi.c +++ b/drivers/net/dsa/microchip/ksz8795_spi.c @@ -14,7 +14,6 @@ #include <linux/regmap.h> #include <linux/spi/spi.h> -#include "ksz_priv.h" #include "ksz_common.h" #define SPI_ADDR_SHIFT 12 diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index a8c97f7a79b7..187be42de5f1 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -14,7 +14,6 @@ #include <net/dsa.h> #include <net/switchdev.h> -#include "ksz_priv.h" #include "ksz9477_reg.h" #include "ksz_common.h" diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c index 5a9e27b337a8..a226b389e12d 100644 --- a/drivers/net/dsa/microchip/ksz9477_spi.c +++ b/drivers/net/dsa/microchip/ksz9477_spi.c @@ -13,7 +13,6 @@ #include <linux/regmap.h> #include <linux/spi/spi.h> -#include "ksz_priv.h" #include "ksz_common.h" #define SPI_ADDR_SHIFT 24 diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index ce20cc90f9ef..b45c7b972cec 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -18,17 +18,7 @@ #include <net/dsa.h> #include <net/switchdev.h> -#include "ksz_priv.h" - -void ksz_port_cleanup(struct ksz_device *dev, int port) -{ - /* Common code for port cleanup. */ - mutex_lock(&dev->dev_mutex); - dev->on_ports &= ~(1 << port); - dev->live_ports &= ~(1 << port); - mutex_unlock(&dev->dev_mutex); -} -EXPORT_SYMBOL_GPL(ksz_port_cleanup); +#include "ksz_common.h" void ksz_update_port_member(struct ksz_device *dev, int port) { diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 84fed4a2578b..c44a8d23d973 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -7,9 +7,152 @@ #ifndef __KSZ_COMMON_H #define __KSZ_COMMON_H +#include <linux/etherdevice.h> +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/phy.h> #include <linux/regmap.h> +#include <net/dsa.h> + +struct vlan_table { + u32 table[3]; +}; + +struct ksz_port_mib { + struct mutex cnt_mutex; /* structure access */ + u8 cnt_ptr; + u64 *counters; +}; + +struct ksz_port { + u16 member; + u16 vid_member; + int stp_state; + struct phy_device phydev; + + u32 on:1; /* port is not disabled by hardware */ + u32 phy:1; /* port has a PHY */ + u32 fiber:1; /* port is fiber */ + u32 sgmii:1; /* port is SGMII */ + u32 force:1; + u32 read:1; /* read MIB counters in background */ + u32 freeze:1; /* MIB counter freeze is enabled */ + + struct ksz_port_mib mib; +}; + +struct ksz_device { + struct dsa_switch *ds; + struct ksz_platform_data *pdata; + const char *name; + + struct mutex dev_mutex; /* device access */ + struct mutex stats_mutex; /* status access */ + struct mutex alu_mutex; /* ALU access */ + struct mutex vlan_mutex; /* vlan access */ + const struct ksz_dev_ops *dev_ops; + + struct device *dev; + struct regmap *regmap[3]; + + void *priv; + + struct gpio_desc *reset_gpio; /* Optional reset GPIO */ + + /* chip specific data */ + u32 chip_id; + int num_vlans; + int num_alus; + int num_statics; + int cpu_port; /* port connected to CPU */ + int cpu_ports; /* port bitmap can be cpu port */ + int phy_port_cnt; + int port_cnt; + int reg_mib_cnt; + int mib_cnt; + int mib_port_cnt; + int last_port; /* ports after that not used */ + phy_interface_t interface; + u32 regs_size; + bool phy_errata_9477; + bool synclko_125; + + struct vlan_table *vlan_cache; + + struct ksz_port *ports; + struct timer_list mib_read_timer; + struct work_struct mib_read; + unsigned long mib_read_interval; + u16 br_member; + u16 member; + u16 live_ports; + u16 on_ports; /* ports enabled by DSA */ + u16 rx_ports; + u16 tx_ports; + u16 mirror_rx; + u16 mirror_tx; + u32 features; /* chip specific features */ + u32 overrides; /* chip functions set by user */ + u16 host_mask; + u16 port_mask; +}; + +struct alu_struct { + /* entry 1 */ + u8 is_static:1; + u8 is_src_filter:1; + u8 is_dst_filter:1; + u8 prio_age:3; + u32 _reserv_0_1:23; + u8 mstp:3; + /* entry 2 */ + u8 is_override:1; + u8 is_use_fid:1; + u32 _reserv_1_1:23; + u8 port_forward:7; + /* entry 3 & 4*/ + u32 _reserv_2_1:9; + u8 fid:7; + u8 mac[ETH_ALEN]; +}; + +struct ksz_dev_ops { + u32 (*get_port_addr)(int port, int offset); + void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member); + void (*flush_dyn_mac_table)(struct ksz_device *dev, int port); + void (*phy_setup)(struct ksz_device *dev, int port, + struct phy_device *phy); + void (*port_cleanup)(struct ksz_device *dev, int port); + void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port); + void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val); + void (*w_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 val); + int (*r_dyn_mac_table)(struct ksz_device *dev, u16 addr, u8 *mac_addr, + u8 *fid, u8 *src_port, u8 *timestamp, + u16 *entries); + int (*r_sta_mac_table)(struct ksz_device *dev, u16 addr, + struct alu_struct *alu); + void (*w_sta_mac_table)(struct ksz_device *dev, u16 addr, + struct alu_struct *alu); + void (*r_mib_cnt)(struct ksz_device *dev, int port, u16 addr, + u64 *cnt); + void (*r_mib_pkt)(struct ksz_device *dev, int port, u16 addr, + u64 *dropped, u64 *cnt); + void (*freeze_mib)(struct ksz_device *dev, int port, bool freeze); + void (*port_init_cnt)(struct ksz_device *dev, int port); + int (*shutdown)(struct ksz_device *dev); + int (*detect)(struct ksz_device *dev); + int (*init)(struct ksz_device *dev); + void (*exit)(struct ksz_device *dev); +}; + +struct ksz_device *ksz_switch_alloc(struct device *base, void *priv); +int ksz_switch_register(struct ksz_device *dev, + const struct ksz_dev_ops *ops); +void ksz_switch_remove(struct ksz_device *dev); + +int ksz8795_switch_register(struct ksz_device *dev); +int ksz9477_switch_register(struct ksz_device *dev); -void ksz_port_cleanup(struct ksz_device *dev, int port); void ksz_update_port_member(struct ksz_device *dev, int port); void ksz_init_mib_timer(struct ksz_device *dev); diff --git a/drivers/net/dsa/microchip/ksz_priv.h b/drivers/net/dsa/microchip/ksz_priv.h deleted file mode 100644 index 44c16aaf775c..000000000000 --- a/drivers/net/dsa/microchip/ksz_priv.h +++ /dev/null @@ -1,156 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 - * - * Microchip KSZ series switch common definitions - * - * Copyright (C) 2017-2019 Microchip Technology Inc. - */ - -#ifndef __KSZ_PRIV_H -#define __KSZ_PRIV_H - -#include <linux/kernel.h> -#include <linux/mutex.h> -#include <linux/phy.h> -#include <linux/etherdevice.h> -#include <net/dsa.h> - -struct vlan_table { - u32 table[3]; -}; - -struct ksz_port_mib { - struct mutex cnt_mutex; /* structure access */ - u8 cnt_ptr; - u64 *counters; -}; - -struct ksz_port { - u16 member; - u16 vid_member; - int stp_state; - struct phy_device phydev; - - u32 on:1; /* port is not disabled by hardware */ - u32 phy:1; /* port has a PHY */ - u32 fiber:1; /* port is fiber */ - u32 sgmii:1; /* port is SGMII */ - u32 force:1; - u32 read:1; /* read MIB counters in background */ - u32 freeze:1; /* MIB counter freeze is enabled */ - - struct ksz_port_mib mib; -}; - -struct ksz_device { - struct dsa_switch *ds; - struct ksz_platform_data *pdata; - const char *name; - - struct mutex dev_mutex; /* device access */ - struct mutex stats_mutex; /* status access */ - struct mutex alu_mutex; /* ALU access */ - struct mutex vlan_mutex; /* vlan access */ - const struct ksz_dev_ops *dev_ops; - - struct device *dev; - struct regmap *regmap[3]; - - void *priv; - - struct gpio_desc *reset_gpio; /* Optional reset GPIO */ - - /* chip specific data */ - u32 chip_id; - int num_vlans; - int num_alus; - int num_statics; - int cpu_port; /* port connected to CPU */ - int cpu_ports; /* port bitmap can be cpu port */ - int phy_port_cnt; - int port_cnt; - int reg_mib_cnt; - int mib_cnt; - int mib_port_cnt; - int last_port; /* ports after that not used */ - phy_interface_t interface; - u32 regs_size; - bool phy_errata_9477; - bool synclko_125; - - struct vlan_table *vlan_cache; - - struct ksz_port *ports; - struct timer_list mib_read_timer; - struct work_struct mib_read; - unsigned long mib_read_interval; - u16 br_member; - u16 member; - u16 live_ports; - u16 on_ports; /* ports enabled by DSA */ - u16 rx_ports; - u16 tx_ports; - u16 mirror_rx; - u16 mirror_tx; - u32 features; /* chip specific features */ - u32 overrides; /* chip functions set by user */ - u16 host_mask; - u16 port_mask; -}; - -struct alu_struct { - /* entry 1 */ - u8 is_static:1; - u8 is_src_filter:1; - u8 is_dst_filter:1; - u8 prio_age:3; - u32 _reserv_0_1:23; - u8 mstp:3; - /* entry 2 */ - u8 is_override:1; - u8 is_use_fid:1; - u32 _reserv_1_1:23; - u8 port_forward:7; - /* entry 3 & 4*/ - u32 _reserv_2_1:9; - u8 fid:7; - u8 mac[ETH_ALEN]; -}; - -struct ksz_dev_ops { - u32 (*get_port_addr)(int port, int offset); - void (*cfg_port_member)(struct ksz_device *dev, int port, u8 member); - void (*flush_dyn_mac_table)(struct ksz_device *dev, int port); - void (*phy_setup)(struct ksz_device *dev, int port, - struct phy_device *phy); - void (*port_cleanup)(struct ksz_device *dev, int port); - void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port); - void (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val); - void (*w_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 val); - int (*r_dyn_mac_table)(struct ksz_device *dev, u16 addr, u8 *mac_addr, - u8 *fid, u8 *src_port, u8 *timestamp, - u16 *entries); - int (*r_sta_mac_table)(struct ksz_device *dev, u16 addr, - struct alu_struct *alu); - void (*w_sta_mac_table)(struct ksz_device *dev, u16 addr, - struct alu_struct *alu); - void (*r_mib_cnt)(struct ksz_device *dev, int port, u16 addr, - u64 *cnt); - void (*r_mib_pkt)(struct ksz_device *dev, int port, u16 addr, - u64 *dropped, u64 *cnt); - void (*freeze_mib)(struct ksz_device *dev, int port, bool freeze); - void (*port_init_cnt)(struct ksz_device *dev, int port); - int (*shutdown)(struct ksz_device *dev); - int (*detect)(struct ksz_device *dev); - int (*init)(struct ksz_device *dev); - void (*exit)(struct ksz_device *dev); -}; - -struct ksz_device *ksz_switch_alloc(struct device *base, void *priv); -int ksz_switch_register(struct ksz_device *dev, - const struct ksz_dev_ops *ops); -void ksz_switch_remove(struct ksz_device *dev); - -int ksz8795_switch_register(struct ksz_device *dev); -int ksz9477_switch_register(struct ksz_device *dev); - -#endif diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 57dc3cbff36e..155599dcee76 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -4096,12 +4096,16 @@ static int cnic_cm_alloc_mem(struct cnic_dev *dev) { struct cnic_local *cp = dev->cnic_priv; u32 port_id; + int i; cp->csk_tbl = kvcalloc(MAX_CM_SK_TBL_SZ, sizeof(struct cnic_sock), GFP_KERNEL); if (!cp->csk_tbl) return -ENOMEM; + for (i = 0; i < MAX_CM_SK_TBL_SZ; i++) + atomic_set(&cp->csk_tbl[i].ref_count, 0); + port_id = prandom_u32(); port_id %= CNIC_LOCAL_PORT_RANGE; if (cnic_init_id_tbl(&cp->csk_port_tbl, CNIC_LOCAL_PORT_RANGE, @@ -5480,6 +5484,7 @@ static struct cnic_dev *cnic_alloc_dev(struct net_device *dev, cdev->unregister_device = cnic_unregister_device; cdev->iscsi_nl_msg_recv = cnic_iscsi_nl_msg_recv; cdev->get_fc_npiv_tbl = cnic_get_fc_npiv_tbl; + atomic_set(&cdev->ref_count, 0); cp = cdev->cnic_priv; cp->dev = cdev; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 7d42582ed48d..b14441944b4b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #ifndef _FM10K_H_ #define _FM10K_H_ @@ -177,14 +177,10 @@ static inline struct netdev_queue *txring_txq(const struct fm10k_ring *ring) #define MIN_Q_VECTORS 1 enum fm10k_non_q_vectors { FM10K_MBX_VECTOR, -#define NON_Q_VECTORS_VF NON_Q_VECTORS_PF - NON_Q_VECTORS_PF + NON_Q_VECTORS }; -#define NON_Q_VECTORS(hw) (((hw)->mac.type == fm10k_mac_pf) ? \ - NON_Q_VECTORS_PF : \ - NON_Q_VECTORS_VF) -#define MIN_MSIX_COUNT(hw) (MIN_Q_VECTORS + NON_Q_VECTORS(hw)) +#define MIN_MSIX_COUNT(hw) (MIN_Q_VECTORS + NON_Q_VECTORS) struct fm10k_q_vector { struct fm10k_intfc *interface; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 1f7e4a8f4557..c681d2d28107 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -1114,13 +1114,12 @@ static void fm10k_get_channels(struct net_device *dev, struct ethtool_channels *ch) { struct fm10k_intfc *interface = netdev_priv(dev); - struct fm10k_hw *hw = &interface->hw; /* report maximum channels */ ch->max_combined = fm10k_max_channels(dev); /* report info for other vector */ - ch->max_other = NON_Q_VECTORS(hw); + ch->max_other = NON_Q_VECTORS; ch->other_count = ch->max_other; /* record RSS queues */ @@ -1132,14 +1131,13 @@ static int fm10k_set_channels(struct net_device *dev, { struct fm10k_intfc *interface = netdev_priv(dev); unsigned int count = ch->combined_count; - struct fm10k_hw *hw = &interface->hw; /* verify they are not requesting separate vectors */ if (!count || ch->rx_count || ch->tx_count) return -EINVAL; /* verify other_count has not changed */ - if (ch->other_count != NON_Q_VECTORS(hw)) + if (ch->other_count != NON_Q_VECTORS) return -EINVAL; /* verify the number of channels does not exceed hardware limits */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 9e6bddff7625..e0a2be534b20 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -315,7 +315,7 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring, /* prefetch first cache line of first page */ prefetch(page_addr); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch((void *)((u8 *)page_addr + L1_CACHE_BYTES)); #endif /* allocate a skb to store the frags */ @@ -1824,7 +1824,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) v_budget = min_t(u16, v_budget, num_online_cpus()); /* account for vectors not related to queues */ - v_budget += NON_Q_VECTORS(hw); + v_budget += NON_Q_VECTORS; /* At the same time, hardware can only support a maximum of * hw.mac->max_msix_vectors vectors. With features @@ -1856,7 +1856,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) } /* record the number of queues available for q_vectors */ - interface->num_q_vectors = v_budget - NON_Q_VECTORS(hw); + interface->num_q_vectors = v_budget - NON_Q_VECTORS; return 0; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index aece335b41f8..75e51f91036c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_common.h" @@ -2134,7 +2134,8 @@ fifo_err: * DWORDs, not bytes. Any invalid values will cause the mailbox to return * error. **/ -s32 fm10k_sm_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx, +s32 fm10k_sm_mbx_init(struct fm10k_hw __always_unused *hw, + struct fm10k_mbx_info *mbx, const struct fm10k_msg_data *msg_data) { mbx->mbx_reg = FM10K_GMBX; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 259da075093f..d3e85480f46d 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k.h" #include <linux/vmalloc.h> @@ -54,7 +54,7 @@ err: **/ static int fm10k_setup_all_tx_resources(struct fm10k_intfc *interface) { - int i, err = 0; + int i, err; for (i = 0; i < interface->num_tx_queues; i++) { err = fm10k_setup_tx_resources(interface->tx_ring[i]); @@ -121,7 +121,7 @@ err: **/ static int fm10k_setup_all_rx_resources(struct fm10k_intfc *interface) { - int i, err = 0; + int i, err; for (i = 0; i < interface->num_rx_queues; i++) { err = fm10k_setup_rx_resources(interface->rx_ring[i]); @@ -871,7 +871,7 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err = -EHOSTDOWN; + int err; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; @@ -891,7 +891,7 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err = -EHOSTDOWN; + int err; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; @@ -1463,7 +1463,7 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, struct fm10k_l2_accel *old_l2_accel = NULL; struct fm10k_dglort_cfg dglort = { 0 }; struct fm10k_hw *hw = &interface->hw; - int size = 0, i; + int size, i; u16 vid, glort; /* The hardware supported by fm10k only filters on the destination MAC diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 9522e9f8f8b8..bb236fa44048 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -898,7 +898,7 @@ static void fm10k_configure_tx_ring(struct fm10k_intfc *interface, /* Map interrupt */ if (ring->q_vector) { - txint = ring->q_vector->v_idx + NON_Q_VECTORS(hw); + txint = ring->q_vector->v_idx + NON_Q_VECTORS; txint |= FM10K_INT_MAP_TIMER0; } @@ -1037,7 +1037,7 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface, /* Map interrupt */ if (ring->q_vector) { - rxint = ring->q_vector->v_idx + NON_Q_VECTORS(hw); + rxint = ring->q_vector->v_idx + NON_Q_VECTORS; rxint |= FM10K_INT_MAP_TIMER1; } @@ -1720,10 +1720,9 @@ int fm10k_mbx_request_irq(struct fm10k_intfc *interface) void fm10k_qv_free_irq(struct fm10k_intfc *interface) { int vector = interface->num_q_vectors; - struct fm10k_hw *hw = &interface->hw; struct msix_entry *entry; - entry = &interface->msix_entries[NON_Q_VECTORS(hw) + vector]; + entry = &interface->msix_entries[NON_Q_VECTORS + vector]; while (vector) { struct fm10k_q_vector *q_vector; @@ -1760,7 +1759,7 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface) unsigned int ri = 0, ti = 0; int vector, err; - entry = &interface->msix_entries[NON_Q_VECTORS(hw)]; + entry = &interface->msix_entries[NON_Q_VECTORS]; for (vector = 0; vector < interface->num_q_vectors; vector++) { struct fm10k_q_vector *q_vector = interface->q_vector[vector]; @@ -2340,7 +2339,7 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) /* Restart the MAC/VLAN request queue in-case of outstanding events */ fm10k_macvlan_schedule(interface); - return err; + return 0; } /** diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index e85b2f2eef05..be07bfdb0bb4 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_pf.h" #include "fm10k_vf.h" @@ -1152,7 +1152,7 @@ static void fm10k_iov_update_stats_pf(struct fm10k_hw *hw, * assumption is that in this case it is acceptable to just directly * hand off the message from the VF to the underlying shared code. **/ -s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results, +s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 __always_unused **results, struct fm10k_mbx_info *mbx) { struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; @@ -1565,7 +1565,7 @@ static s32 fm10k_get_fault_pf(struct fm10k_hw *hw, int type, /* read remaining fields */ fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_HI); fault->address <<= 32; - fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO); + fault->address |= fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO); fault->specinfo = fm10k_read_reg(hw, type + FM10K_FAULT_SPECINFO); /* clear valid bit to allow for next error */ @@ -1641,7 +1641,7 @@ const struct fm10k_tlv_attr fm10k_lport_map_msg_attr[] = { * switch API. **/ s32 fm10k_msg_lport_map_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u16 glort, mask; u32 dglort_map; @@ -1684,7 +1684,7 @@ const struct fm10k_tlv_attr fm10k_update_pvid_msg_attr[] = { * This handler configures the default VLAN for the PF **/ static s32 fm10k_msg_update_pvid_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u16 glort, pvid; u32 pvid_update; @@ -1745,7 +1745,7 @@ const struct fm10k_tlv_attr fm10k_err_msg_attr[] = { * messages that the PF has sent. **/ s32 fm10k_msg_err_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { struct fm10k_swapi_error err_msg; s32 err; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c index 2a7a40bf2b1c..21eff0895a7a 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_tlv.h" @@ -472,7 +472,7 @@ static s32 fm10k_tlv_attr_parse(u32 *attr, u32 **results, const struct fm10k_tlv_attr *tlv_attr) { u32 i, attr_id, offset = 0; - s32 err = 0; + s32 err; u16 len; /* verify pointers are not NULL */ @@ -587,8 +587,9 @@ s32 fm10k_tlv_msg_parse(struct fm10k_hw *hw, u32 *msg, * a minimum it just indicates that the message requested was * unimplemented. **/ -s32 fm10k_tlv_msg_error(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) +s32 fm10k_tlv_msg_error(struct fm10k_hw __always_unused *hw, + u32 __always_unused **results, + struct fm10k_mbx_info __always_unused *mbx) { return FM10K_NOT_IMPLEMENTED; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h index 9fb9fca375e3..15ac1c7885bc 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #ifndef _FM10K_TYPE_H_ #define _FM10K_TYPE_H_ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c index a8519c1f0406..dc8ccd378ec9 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_vf.h" @@ -198,7 +198,7 @@ static s32 fm10k_update_vlan_vf(struct fm10k_hw *hw, u32 vid, u8 vsi, bool set) * This function should determine the MAC address for the VF **/ s32 fm10k_msg_mac_vlan_vf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u8 perm_addr[ETH_ALEN]; u16 vid; @@ -267,8 +267,10 @@ static s32 fm10k_read_mac_addr_vf(struct fm10k_hw *hw) * This function is used to add or remove unicast MAC addresses for * the VF. **/ -static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, u16 glort, - const u8 *mac, u16 vid, bool add, u8 flags) +static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, + u16 __always_unused glort, + const u8 *mac, u16 vid, bool add, + u8 __always_unused flags) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[7]; @@ -309,7 +311,8 @@ static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, u16 glort, * This function is used to add or remove multicast MAC addresses for * the VF. **/ -static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw, u16 glort, +static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw, + u16 __always_unused glort, const u8 *mac, u16 vid, bool add) { struct fm10k_mbx_info *mbx = &hw->mbx; @@ -373,7 +376,7 @@ const struct fm10k_tlv_attr fm10k_lport_state_msg_attr[] = { * are ready to bring up the interface. **/ s32 fm10k_msg_lport_state_vf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { hw->mac.dglort_map = !results[FM10K_LPORT_STATE_MSG_READY] ? FM10K_DGLORTMAP_NONE : FM10K_DGLORTMAP_ZERO; @@ -392,8 +395,9 @@ s32 fm10k_msg_lport_state_vf(struct fm10k_hw *hw, u32 **results, * enabled we can add filters, if it is disabled all filters for this * logical port are flushed. **/ -static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, u16 glort, - u16 count, bool enable) +static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, + u16 __always_unused glort, + u16 __always_unused count, bool enable) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[2]; @@ -420,7 +424,8 @@ static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, u16 glort, * so that it can enable either multicast, multicast promiscuous, or * promiscuous mode of operation. **/ -static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw, u16 glort, u8 mode) +static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw, + u16 __always_unused glort, u8 mode) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[3]; @@ -475,7 +480,7 @@ static void fm10k_rebind_hw_stats_vf(struct fm10k_hw *hw, * that information to then populate a DGLORTMAP/DEC entry and the queues * to which it has been assigned. **/ -static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw *hw, +static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw __always_unused *hw, struct fm10k_dglort_cfg *dglort) { /* verify the dglort pointer */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 79d93d6c7d7a..30f13f81c965 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -359,6 +359,7 @@ enum { MLX5E_SQ_STATE_IPSEC, MLX5E_SQ_STATE_AM, MLX5E_SQ_STATE_TLS, + MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, }; struct mlx5e_sq_wqe_info { @@ -483,8 +484,6 @@ struct mlx5e_xdp_mpwqe { struct mlx5e_tx_wqe *wqe; u8 ds_count; u8 pkt_count; - u8 max_ds_count; - u8 complete; u8 inline_on; }; @@ -1134,7 +1133,6 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, u16 num_channels); -u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev); void mlx5e_rx_dim_work(struct work_struct *work); void mlx5e_tx_dim_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h index e78e92753d73..ed7a3881d2c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h @@ -4,7 +4,6 @@ #ifndef __MLX5E_EN_REPORTER_H #define __MLX5E_EN_REPORTER_H -#include <linux/mlx5/driver.h> #include "en.h" int mlx5e_tx_reporter_create(struct mlx5e_priv *priv); 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 f3d98748b211..6e54fefea410 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2019 Mellanox Technologies. */ -#include <net/devlink.h> #include "reporter.h" #include "lib/eq.h" @@ -117,7 +116,7 @@ static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter, char *err_str, struct mlx5e_tx_err_ctx *err_ctx) { - if (IS_ERR_OR_NULL(tx_reporter)) { + if (!tx_reporter) { netdev_err(err_ctx->sq->channel->netdev, err_str); return err_ctx->recover(err_ctx->sq); } @@ -289,23 +288,27 @@ static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { int mlx5e_tx_reporter_create(struct mlx5e_priv *priv) { + struct devlink_health_reporter *reporter; struct mlx5_core_dev *mdev = priv->mdev; struct devlink *devlink = priv_to_devlink(mdev); - priv->tx_reporter = + reporter = devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops, MLX5_REPORTER_TX_GRACEFUL_PERIOD, true, priv); - if (IS_ERR(priv->tx_reporter)) + if (IS_ERR(reporter)) { netdev_warn(priv->netdev, "Failed to create tx reporter, err = %ld\n", - PTR_ERR(priv->tx_reporter)); - return IS_ERR_OR_NULL(priv->tx_reporter); + PTR_ERR(reporter)); + return PTR_ERR(reporter); + } + priv->tx_reporter = reporter; + return 0; } void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv) { - if (IS_ERR_OR_NULL(priv->tx_reporter)) + if (!priv->tx_reporter) return; devlink_health_reporter_destroy(priv->tx_reporter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index ddfe19adb3d9..87be96747902 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -6,7 +6,7 @@ #include "en.h" -#define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS +#define MLX5E_SQ_NOPS_ROOM (MLX5_SEND_WQE_MAX_WQEBBS - 1) #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\ MLX5E_SQ_NOPS_ROOM) @@ -117,9 +117,27 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map, mlx5_write64((__be32 *)ctrl, uar_map); } -static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5e_tx_wqe *wqe) +static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg) { - return !!wqe->ctrl.tisn; + return cseg && !!cseg->tisn; +} + +static inline u8 +mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg, + struct sk_buff *skb) +{ + u8 mode; + + if (mlx5e_transport_inline_tx_wqe(cseg)) + return MLX5_INLINE_MODE_TCP_UDP; + + mode = sq->min_inline_mode; + + if (skb_vlan_tag_present(skb) && + test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state)) + mode = max_t(u8, MLX5_INLINE_MODE_L2, mode); + + return mode; } static inline void mlx5e_cq_arm(struct mlx5e_cq *cq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index b0b982cf69bb..1ed5c33e022f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -179,33 +179,19 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; struct mlx5e_xdpsq_stats *stats = sq->stats; struct mlx5_wq_cyc *wq = &sq->wq; - u8 wqebbs; - u16 pi; - - mlx5e_xdpsq_fetch_wqe(sq, &session->wqe); - - prefetchw(session->wqe->data); - session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; - session->pkt_count = 0; - session->complete = 0; + u16 pi, contig_wqebbs; pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); -/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS - * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment. - * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a - * full-session WQE be cache-aligned. - */ -#if L1_CACHE_BYTES < 128 -#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1) -#else -#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2) -#endif + if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS)) + mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs); - wqebbs = min_t(u16, mlx5_wq_cyc_get_contig_wqebbs(wq, pi), - MLX5E_XDP_MPW_MAX_WQEBBS); + session->wqe = mlx5e_xdpsq_fetch_wqe(sq, &pi); - session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs; + prefetchw(session->wqe->data); + session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; + session->pkt_count = 0; mlx5e_xdp_update_inline_state(sq); @@ -244,7 +230,7 @@ static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq) { if (unlikely(!sq->mpwqe.wqe)) { if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, - MLX5_SEND_WQE_MAX_WQEBBS))) { + MLX5E_XDPSQ_STOP_ROOM))) { /* SQ is full, ring doorbell */ mlx5e_xmit_xdp_doorbell(sq); sq->stats->full++; @@ -285,8 +271,8 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats); - if (unlikely(session->complete || - session->ds_count == session->max_ds_count)) + if (unlikely(mlx5e_xdp_no_room_for_inline_pkt(session) || + session->ds_count == MLX5E_XDP_MPW_MAX_NUM_DS)) mlx5e_xdp_mpwqe_complete(sq); mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index b90923932668..36ac1e3816b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -40,6 +40,26 @@ (sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */) +#define MLX5E_XDPSQ_STOP_ROOM (MLX5E_SQ_STOP_ROOM) + +#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg)) +#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT \ + DIV_ROUND_UP(MLX5E_XDP_INLINE_WQE_SZ_THRSD, MLX5_SEND_WQE_DS) + +/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS + * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment. + * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a + * full-session WQE be cache-aligned. + */ +#if L1_CACHE_BYTES < 128 +#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1) +#else +#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2) +#endif + +#define MLX5E_XDP_MPW_MAX_NUM_DS \ + (MLX5E_XDP_MPW_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS) + struct mlx5e_xsk_param; int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, @@ -114,6 +134,30 @@ static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq) session->inline_on = 1; } +static inline bool +mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session) +{ + return session->inline_on && + session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS; +} + +static inline void +mlx5e_fill_xdpsq_frag_edge(struct mlx5e_xdpsq *sq, struct mlx5_wq_cyc *wq, + u16 pi, u16 nnops) +{ + struct mlx5e_xdp_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi]; + + edge_wi = wi + nnops; + /* fill sq frag edge with nops to avoid wqe wrapping two pages */ + for (; wi < edge_wi; wi++) { + wi->num_wqebbs = 1; + wi->num_pkts = 0; + mlx5e_post_nop(wq, sq->sqn, &sq->pc); + } + + sq->stats->nops += nnops; +} + static inline void mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd, @@ -126,20 +170,12 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, session->pkt_count++; -#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg)) - if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) { struct mlx5_wqe_inline_seg *inline_dseg = (struct mlx5_wqe_inline_seg *)dseg; u16 ds_len = sizeof(*inline_dseg) + dma_len; u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS); - if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) { - /* Not enough space for inline wqe, send with memory pointer */ - session->complete = true; - goto no_inline; - } - inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG); memcpy(inline_dseg->data, xdptxd->data, dma_len); @@ -148,21 +184,23 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, return; } -no_inline: dseg->addr = cpu_to_be64(xdptxd->dma_addr); dseg->byte_count = cpu_to_be32(dma_len); dseg->lkey = sq->mkey_be; session->ds_count++; } -static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, - struct mlx5e_tx_wqe **wqe) +static inline struct mlx5e_tx_wqe * +mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, u16 *pi) { struct mlx5_wq_cyc *wq = &sq->wq; - u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + struct mlx5e_tx_wqe *wqe; + + *pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + wqe = mlx5_wq_cyc_get_wqe(wq, *pi); + memset(wqe, 0, sizeof(*wqe)); - *wqe = mlx5_wq_cyc_get_wqe(wq, pi); - memset(*wqe, 0, sizeof(**wqe)); + return wqe; } static inline void diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 1539cf3de5dc..f7890e0ce96c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -180,15 +180,3 @@ out: return err; } - -u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev) -{ - u8 min_inline_mode; - - mlx5_query_min_inline(mdev, &min_inline_mode); - if (min_inline_mode == MLX5_INLINE_MODE_NONE && - !MLX5_CAP_ETH(mdev, wqe_vlan_insert)) - min_inline_mode = MLX5_INLINE_MODE_L2; - - return min_inline_mode; -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 8dd31b5c740c..01f2918063af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1101,7 +1101,7 @@ void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv) static void mlx5e_trust_update_tx_min_inline_mode(struct mlx5e_priv *priv, struct mlx5e_params *params) { - params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(priv->mdev); + mlx5_query_min_inline(priv->mdev, ¶ms->tx_min_inline_mode); if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP && params->tx_min_inline_mode == MLX5_INLINE_MODE_L2) params->tx_min_inline_mode = MLX5_INLINE_MODE_IP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b2618dd6dd10..4db595a7eb03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1131,6 +1131,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; sq->stop_room = MLX5E_SQ_STOP_ROOM; INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); + if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert)) + set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); if (mlx5_accel_is_tls_device(c->priv->mdev)) { @@ -2323,7 +2325,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, goto err_close_channels; } - if (!IS_ERR_OR_NULL(priv->tx_reporter)) + if (priv->tx_reporter) devlink_health_reporter_state_update(priv->tx_reporter, DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); @@ -4777,7 +4779,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); /* TX inline */ - params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev); + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); /* RSS */ mlx5e_build_rss_params(rss_params, params->num_channels); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 6edf0aeb1e26..bf6f4835457e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1156,6 +1156,23 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv, } } +static +int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + switch (ma->command) { + case TC_CLSMATCHALL_REPLACE: + return mlx5e_tc_configure_matchall(priv, ma); + case TC_CLSMATCHALL_DESTROY: + return mlx5e_tc_delete_matchall(priv, ma); + case TC_CLSMATCHALL_STATS: + mlx5e_tc_stats_matchall(priv, ma); + return 0; + default: + return -EOPNOTSUPP; + } +} + static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { @@ -1165,6 +1182,8 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSFLOWER: return mlx5e_rep_setup_tc_cls_flower(priv, type_data, flags); + case TC_SETUP_CLSMATCHALL: + return mlx5e_rep_setup_tc_cls_matchall(priv, type_data); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 10fafd5fa17b..43eeebe9c8d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -88,6 +88,7 @@ struct mlx5e_rep_priv { struct mlx5_flow_handle *vport_rx_rule; struct list_head vport_sqs_list; struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */ + struct rtnl_link_stats64 prev_vf_vport_stats; struct devlink_port dl_port; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index ac6e586d403d..60570b442fff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -859,13 +859,24 @@ tail_padding_csum(struct sk_buff *skb, int offset, } static void -mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto, - struct mlx5e_rq_stats *stats) +mlx5e_skb_csum_fixup(struct sk_buff *skb, int network_depth, __be16 proto, + struct mlx5e_rq_stats *stats) { struct ipv6hdr *ip6; struct iphdr *ip4; int pkt_len; + /* Fixup vlan headers, if any */ + if (network_depth > ETH_HLEN) + /* CQE csum is calculated from the IP header and does + * not cover VLAN headers (if present). This will add + * the checksum manually. + */ + skb->csum = csum_partial(skb->data + ETH_HLEN, + network_depth - ETH_HLEN, + skb->csum); + + /* Fixup tail padding, if any */ switch (proto) { case htons(ETH_P_IP): ip4 = (struct iphdr *)(skb->data + network_depth); @@ -931,16 +942,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, return; /* CQE csum covers all received bytes */ /* csum might need some fixups ...*/ - if (network_depth > ETH_HLEN) - /* CQE csum is calculated from the IP header and does - * not cover VLAN headers (if present). This will add - * the checksum manually. - */ - skb->csum = csum_partial(skb->data + ETH_HLEN, - network_depth - ETH_HLEN, - skb->csum); - - mlx5e_skb_padding_csum(skb, network_depth, proto, stats); + mlx5e_skb_csum_fixup(skb, network_depth, proto, stats); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 539b4d3656da..6eee3c7d4b06 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -74,6 +74,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_mpwqe) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_inlnw) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_nops) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) }, @@ -90,6 +91,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_mpwqe) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_inlnw) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_nops) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) }, @@ -200,6 +202,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_xdp_tx_xmit += xdpsq_stats->xmit; s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe; s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw; + s->rx_xdp_tx_nops += xdpsq_stats->nops; s->rx_xdp_tx_full += xdpsq_stats->full; s->rx_xdp_tx_err += xdpsq_stats->err; s->rx_xdp_tx_cqe += xdpsq_stats->cqes; @@ -227,6 +230,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_xdp_xmit += xdpsq_red_stats->xmit; s->tx_xdp_mpwqe += xdpsq_red_stats->mpwqe; s->tx_xdp_inlnw += xdpsq_red_stats->inlnw; + s->tx_xdp_nops += xdpsq_red_stats->nops; s->tx_xdp_full += xdpsq_red_stats->full; s->tx_xdp_err += xdpsq_red_stats->err; s->tx_xdp_cqes += xdpsq_red_stats->cqes; @@ -1331,6 +1335,7 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = { { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, + { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, @@ -1340,6 +1345,7 @@ static const struct counter_desc xdpsq_stats_desc[] = { { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, + { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 76ac111e14d0..bf645d42c833 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -81,6 +81,7 @@ struct mlx5e_sw_stats { u64 rx_xdp_tx_xmit; u64 rx_xdp_tx_mpwqe; u64 rx_xdp_tx_inlnw; + u64 rx_xdp_tx_nops; u64 rx_xdp_tx_full; u64 rx_xdp_tx_err; u64 rx_xdp_tx_cqe; @@ -97,6 +98,7 @@ struct mlx5e_sw_stats { u64 tx_xdp_xmit; u64 tx_xdp_mpwqe; u64 tx_xdp_inlnw; + u64 tx_xdp_nops; u64 tx_xdp_full; u64 tx_xdp_err; u64 tx_xdp_cqes; @@ -288,6 +290,7 @@ struct mlx5e_xdpsq_stats { u64 xmit; u64 mpwqe; u64 inlnw; + u64 nops; u64 full; u64 err; /* dirtied @completion */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index f3ed028d5017..c5d75e2ecf54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2485,7 +2485,8 @@ static bool actions_match_supported(struct mlx5e_priv *priv, if (flow_flag_test(flow, EGRESS) && !((actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) || - (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP))) + (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) || + (actions & MLX5_FLOW_CONTEXT_ACTION_DROP))) return false; if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) @@ -3638,6 +3639,106 @@ errout: return err; } +static int apply_police_params(struct mlx5e_priv *priv, u32 rate, + struct netlink_ext_ack *extack) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5_eswitch *esw; + u16 vport_num; + u32 rate_mbps; + int err; + + esw = priv->mdev->priv.eswitch; + /* rate is given in bytes/sec. + * First convert to bits/sec and then round to the nearest mbit/secs. + * mbit means million bits. + * Moreover, if rate is non zero we choose to configure to a minimum of + * 1 mbit/sec. + */ + rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0; + vport_num = rpriv->rep->vport; + + err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); + if (err) + NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware"); + + return err; +} + +static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv, + struct flow_action *flow_action, + struct netlink_ext_ack *extack) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + const struct flow_action_entry *act; + int err; + int i; + + if (!flow_action_has_entries(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "matchall called with no action"); + return -EINVAL; + } + + if (!flow_offload_has_one_action(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "matchall policing support only a single action"); + return -EOPNOTSUPP; + } + + flow_action_for_each(i, act, flow_action) { + switch (act->id) { + case FLOW_ACTION_POLICE: + err = apply_police_params(priv, act->police.rate_bytes_ps, extack); + if (err) + return err; + + rpriv->prev_vf_vport_stats = priv->stats.vf_vport; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "mlx5 supports only police action for matchall"); + return -EOPNOTSUPP; + } + } + + return 0; +} + +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) { + NL_SET_ERR_MSG_MOD(extack, "only priority 1 is supported"); + return -EINVAL; + } + + return scan_tc_matchall_fdb_actions(priv, &ma->rule->action, extack); +} + +int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct netlink_ext_ack *extack = ma->common.extack; + + return apply_police_params(priv, 0, extack); +} + +void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct rtnl_link_stats64 cur_stats; + u64 dbytes; + u64 dpkts; + + cur_stats = priv->stats.vf_vport; + dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets; + dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes; + rpriv->prev_vf_vport_stats = cur_stats; + flow_stats_update(&ma->stats, dpkts, dbytes, jiffies); +} + static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 1cb66bf76997..20f045e96c92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -63,6 +63,13 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv, int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, struct flow_cls_offload *f, unsigned long flags); +int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *f); +int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *f); +void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma); + struct mlx5e_encap_entry; void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index acf25cc38fa1..d3a67a9b4eba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -292,8 +292,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; stats->packets += skb_shinfo(skb)->gso_segs; } else { - u8 mode = mlx5e_transport_inline_tx_wqe(wqe) ? - MLX5_INLINE_MODE_TCP_UDP : sq->min_inline_mode; + u8 mode = mlx5e_tx_wqe_inline_mode(sq, &wqe->ctrl, skb); opcode = MLX5_OPCODE_SEND; mss = 0; @@ -608,9 +607,11 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; stats->packets += skb_shinfo(skb)->gso_segs; } else { + u8 mode = mlx5e_tx_wqe_inline_mode(sq, NULL, skb); + opcode = MLX5_OPCODE_SEND; mss = 0; - ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); + ihs = mlx5e_calc_min_inline(mode, skb); num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); stats->packets++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 41f25ea2e8d9..2df9aaa421c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -215,11 +215,7 @@ static int mlx5_eq_async_int(struct notifier_block *nb, */ dma_rmb(); - if (likely(eqe->type < MLX5_EVENT_TYPE_MAX)) - atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe); - else - mlx5_core_warn_once(dev, "notifier_call_chain is not setup for eqe: %d\n", eqe->type); - + atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe); atomic_notifier_call_chain(&eqt->nh[MLX5_EVENT_TYPE_NOTIFY_ANY], eqe->type, eqe); ++eq->cons_index; @@ -945,9 +941,6 @@ int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb) { struct mlx5_eq_table *eqt = dev->priv.eq_table; - if (nb->event_type >= MLX5_EVENT_TYPE_MAX) - return -EINVAL; - return atomic_notifier_chain_register(&eqt->nh[nb->event_type], &nb->nb); } EXPORT_SYMBOL(mlx5_eq_notifier_register); @@ -956,9 +949,6 @@ int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb) { struct mlx5_eq_table *eqt = dev->priv.eq_table; - if (nb->event_type >= MLX5_EVENT_TYPE_MAX) - return -EINVAL; - return atomic_notifier_chain_unregister(&eqt->nh[nb->event_type], &nb->nb); } EXPORT_SYMBOL(mlx5_eq_notifier_unregister); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 7a0888470fae..5fbebee7254d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -58,20 +58,9 @@ struct vport_addr { bool mc_promisc; }; -enum { - UC_ADDR_CHANGE = BIT(0), - MC_ADDR_CHANGE = BIT(1), - PROMISC_CHANGE = BIT(3), -}; - static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw); static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw); -/* Vport context events */ -#define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \ - MC_ADDR_CHANGE | \ - PROMISC_CHANGE) - struct mlx5_vport *__must_check mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num) { @@ -108,13 +97,13 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, MLX5_SET(nic_vport_context, nic_vport_ctx, arm_change_event, 1); - if (events_mask & UC_ADDR_CHANGE) + if (events_mask & MLX5_VPORT_UC_ADDR_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_uc_address_change, 1); - if (events_mask & MC_ADDR_CHANGE) + if (events_mask & MLX5_VPORT_MC_ADDR_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_mc_address_change, 1); - if (events_mask & PROMISC_CHANGE) + if (events_mask & MLX5_VPORT_PROMISC_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_promisc_change, 1); @@ -463,6 +452,22 @@ static int esw_create_legacy_table(struct mlx5_eswitch *esw) return err; } +#define MLX5_LEGACY_SRIOV_VPORT_EVENTS (MLX5_VPORT_UC_ADDR_CHANGE | \ + MLX5_VPORT_MC_ADDR_CHANGE | \ + MLX5_VPORT_PROMISC_CHANGE) + +static int esw_legacy_enable(struct mlx5_eswitch *esw) +{ + int ret; + + ret = esw_create_legacy_table(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); @@ -470,6 +475,19 @@ static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) esw_destroy_legacy_vepa_table(esw); } +static void esw_legacy_disable(struct mlx5_eswitch *esw) +{ + struct esw_mc_addr *mc_promisc; + + mlx5_eswitch_disable_pf_vf_vports(esw); + + mc_promisc = &esw->mc_promisc; + if (mc_promisc->uplink_rule) + mlx5_del_flow_rules(mc_promisc->uplink_rule); + + esw_destroy_legacy_table(esw); +} + /* E-Switch vport UC/MC lists management */ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw, struct vport_addr *vaddr); @@ -901,21 +919,21 @@ static void esw_vport_change_handle_locked(struct mlx5_vport *vport) esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n", vport->vport, mac); - if (vport->enabled_events & UC_ADDR_CHANGE) { + if (vport->enabled_events & MLX5_VPORT_UC_ADDR_CHANGE) { esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC); esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC); } - if (vport->enabled_events & MC_ADDR_CHANGE) + if (vport->enabled_events & MLX5_VPORT_MC_ADDR_CHANGE) esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC); - if (vport->enabled_events & PROMISC_CHANGE) { + if (vport->enabled_events & MLX5_VPORT_PROMISC_CHANGE) { esw_update_vport_rx_mode(esw, vport); if (!IS_ERR_OR_NULL(vport->allmulti_rule)) esw_update_vport_mc_promisc(esw, vport); } - if (vport->enabled_events & (PROMISC_CHANGE | MC_ADDR_CHANGE)) + if (vport->enabled_events & (MLX5_VPORT_PROMISC_CHANGE | MLX5_VPORT_MC_ADDR_CHANGE)) esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC); esw_debug(esw->dev, "vport[%d] Context Changed: Done\n", vport->vport); @@ -1393,18 +1411,49 @@ out: return err; } +static bool element_type_supported(struct mlx5_eswitch *esw, int type) +{ + struct mlx5_core_dev *dev = esw->dev = esw->dev; + + switch (type) { + case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_TASR; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT_TC; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC; + } + return false; +} + /* Vport QoS management */ -static int esw_create_tsar(struct mlx5_eswitch *esw) +static void esw_create_tsar(struct mlx5_eswitch *esw) { u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; struct mlx5_core_dev *dev = esw->dev; + __be32 *attr; int err; if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) - return 0; + return; + + if (!element_type_supported(esw, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR)) + return; if (esw->qos.enabled) - return -EEXIST; + return; + + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + *attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16); err = mlx5_create_scheduling_element_cmd(dev, SCHEDULING_HIERARCHY_E_SWITCH, @@ -1412,11 +1461,10 @@ static int esw_create_tsar(struct mlx5_eswitch *esw) &esw->qos.root_tsar_id); if (err) { esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err); - return err; + return; } esw->qos.enabled = true; - return 0; } static void esw_destroy_tsar(struct mlx5_eswitch *esw) @@ -1537,6 +1585,22 @@ static int esw_vport_qos_config(struct mlx5_eswitch *esw, return 0; } +int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, + u32 rate_mbps) +{ + u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_vport *vport; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); + + return mlx5_modify_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + ctx, + vport->qos.esw_tsar_ix, + MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW); +} + static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN]) { ((u8 *)node_guid)[7] = mac[0]; @@ -1619,7 +1683,7 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport) } static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, - int enable_events) + enum mlx5_eswitch_vport_event enabled_events) { u16 vport_num = vport->vport; @@ -1641,7 +1705,7 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num); /* Sync with current vport context */ - vport->enabled_events = enable_events; + vport->enabled_events = enabled_events; vport->enabled = true; /* Esw manager is trusted by default. Host PF (vport 0) is trusted as well @@ -1770,11 +1834,46 @@ static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw) /* Public E-Switch API */ #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev)) -int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) +/* mlx5_eswitch_enable_pf_vf_vports() enables vports of PF, ECPF and VFs + * whichever are present on the eswitch. + */ +void +mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, + enum mlx5_eswitch_vport_event enabled_events) { struct mlx5_vport *vport; + int i; + + /* Enable PF vport */ + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); + esw_enable_vport(esw, vport, enabled_events); + + /* Enable ECPF vports */ + if (mlx5_ecpf_vport_exists(esw->dev)) { + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + esw_enable_vport(esw, vport, enabled_events); + } + + /* 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_eswitch_disable_pf_vf_vports() disables vports of PF, ECPF and VFs + * whichever are previously enabled on the eswitch. + */ +void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw) +{ + struct mlx5_vport *vport; + int i; + + mlx5_esw_for_all_vports_reverse(esw, i, vport) + esw_disable_vport(esw, vport); +} + +int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) +{ int err; - int i, enabled_events; if (!ESW_ALLOWED(esw) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { @@ -1788,44 +1887,23 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support)) esw_warn(esw->dev, "engress ACL is not supported by FW\n"); + esw_create_tsar(esw); + esw->mode = mode; mlx5_lag_update(esw->dev); if (mode == MLX5_ESWITCH_LEGACY) { - err = esw_create_legacy_table(esw); - if (err) - goto abort; + err = esw_legacy_enable(esw); } else { mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - err = esw_offloads_init(esw); + err = esw_offloads_enable(esw); } if (err) goto abort; - err = esw_create_tsar(esw); - if (err) - esw_warn(esw->dev, "Failed to create eswitch TSAR"); - - enabled_events = (mode == MLX5_ESWITCH_LEGACY) ? SRIOV_VPORT_EVENTS : - UC_ADDR_CHANGE; - - /* Enable PF vport */ - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - esw_enable_vport(esw, vport, enabled_events); - - /* Enable ECPF vports */ - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - esw_enable_vport(esw, vport, enabled_events); - } - - /* 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_eswitch_event_handlers_register(esw); esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), active vports(%d)\n", @@ -1847,10 +1925,7 @@ abort: void mlx5_eswitch_disable(struct mlx5_eswitch *esw) { - struct esw_mc_addr *mc_promisc; - struct mlx5_vport *vport; int old_mode; - int i; if (!ESW_ALLOWED(esw) || esw->mode == MLX5_ESWITCH_NONE) return; @@ -1859,21 +1934,14 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", esw->esw_funcs.num_vfs, esw->enabled_vports); - mc_promisc = &esw->mc_promisc; mlx5_eswitch_event_handlers_unregister(esw); - mlx5_esw_for_all_vports(esw, i, vport) - esw_disable_vport(esw, vport); - - if (mc_promisc && mc_promisc->uplink_rule) - mlx5_del_flow_rules(mc_promisc->uplink_rule); - - esw_destroy_tsar(esw); - if (esw->mode == MLX5_ESWITCH_LEGACY) - esw_destroy_legacy_table(esw); + esw_legacy_disable(esw); else if (esw->mode == MLX5_ESWITCH_OFFLOADS) - esw_offloads_cleanup(esw); + esw_offloads_disable(esw); + + esw_destroy_tsar(esw); old_mode = esw->mode; esw->mode = MLX5_ESWITCH_NONE; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 60f0c62b447b..804912e38dee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -102,6 +102,13 @@ struct mlx5_vport_info { bool trusted; }; +/* Vport context events */ +enum mlx5_eswitch_vport_event { + MLX5_VPORT_UC_ADDR_CHANGE = BIT(0), + MLX5_VPORT_MC_ADDR_CHANGE = BIT(1), + MLX5_VPORT_PROMISC_CHANGE = BIT(3), +}; + struct mlx5_vport { struct mlx5_core_dev *dev; int vport; @@ -123,7 +130,7 @@ struct mlx5_vport { } qos; bool enabled; - u16 enabled_events; + enum mlx5_eswitch_vport_event enabled_events; }; enum offloads_fdb_flags { @@ -208,8 +215,11 @@ enum { struct mlx5_eswitch { struct mlx5_core_dev *dev; struct mlx5_nb nb; + /* legacy data structures */ struct mlx5_eswitch_fdb fdb_table; struct hlist_head mc_table[MLX5_L2_ADDR_HASH_SIZE]; + struct esw_mc_addr mc_promisc; + /* end of legacy */ struct workqueue_struct *work_queue; struct mlx5_vport *vports; u32 flags; @@ -219,7 +229,6 @@ struct mlx5_eswitch { * and async SRIOV admin state changes */ struct mutex state_lock; - struct esw_mc_addr mc_promisc; struct { bool enabled; @@ -234,8 +243,8 @@ struct mlx5_eswitch { struct mlx5_esw_functions esw_funcs; }; -void esw_offloads_cleanup(struct mlx5_eswitch *esw); -int esw_offloads_init(struct mlx5_eswitch *esw); +void esw_offloads_disable(struct mlx5_eswitch *esw); +int esw_offloads_enable(struct mlx5_eswitch *esw); 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, @@ -252,6 +261,8 @@ 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); /* E-Switch API */ int mlx5_eswitch_init(struct mlx5_core_dev *dev); @@ -514,6 +525,11 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw); (vport) = &(esw)->vports[i], \ (i) < (esw)->total_vports; (i)++) +#define mlx5_esw_for_all_vports_reverse(esw, i, vport) \ + for ((i) = (esw)->total_vports - 1; \ + (vport) = &(esw)->vports[i], \ + (i) >= MLX5_VPORT_PF; (i)--) + #define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs) \ for ((i) = MLX5_VPORT_FIRST_VF; \ (vport) = &(esw)->vports[(i)], \ @@ -575,6 +591,11 @@ 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 +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); + #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 d502c91c148c..8fe5dddf18d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -594,38 +594,15 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule) mlx5_del_flow_rules(rule); } -static int mlx5_eswitch_enable_passing_vport_metadata(struct mlx5_eswitch *esw) +static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable) { u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {}; u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {}; u8 fdb_to_vport_reg_c_id; int err; - err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport, - out, sizeof(out)); - if (err) - return err; - - fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out, - esw_vport_context.fdb_to_vport_reg_c_id); - - fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0; - MLX5_SET(modify_esw_vport_context_in, in, - esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id); - - 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, - in, sizeof(in)); -} - -static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw) -{ - u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {}; - u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {}; - u8 fdb_to_vport_reg_c_id; - int err; + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) + return 0; err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport, out, sizeof(out)); @@ -635,7 +612,10 @@ static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw) fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out, esw_vport_context.fdb_to_vport_reg_c_id); - fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0; + if (enable) + fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0; + else + fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0; MLX5_SET(modify_esw_vport_context_in, in, esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id); @@ -2131,7 +2111,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type return NOTIFY_OK; } -int esw_offloads_init(struct mlx5_eswitch *esw) +int esw_offloads_enable(struct mlx5_eswitch *esw) { int err; @@ -2145,11 +2125,11 @@ int esw_offloads_init(struct mlx5_eswitch *esw) if (err) return err; - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { - err = mlx5_eswitch_enable_passing_vport_metadata(esw); - if (err) - goto err_vport_metadata; - } + err = esw_set_passing_vport_metadata(esw, true); + if (err) + goto err_vport_metadata; + + mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE); err = esw_offloads_load_all_reps(esw); if (err) @@ -2163,8 +2143,8 @@ int esw_offloads_init(struct mlx5_eswitch *esw) return 0; err_reps: - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) - mlx5_eswitch_disable_passing_vport_metadata(esw); + mlx5_eswitch_disable_pf_vf_vports(esw); + esw_set_passing_vport_metadata(esw, false); err_vport_metadata: esw_offloads_steering_cleanup(esw); return err; @@ -2189,13 +2169,13 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, return err; } -void esw_offloads_cleanup(struct mlx5_eswitch *esw) +void esw_offloads_disable(struct mlx5_eswitch *esw) { mlx5_rdma_disable_roce(esw->dev); esw_offloads_devcom_cleanup(esw); esw_offloads_unload_all_reps(esw); - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) - mlx5_eswitch_disable_passing_vport_metadata(esw); + mlx5_eswitch_disable_pf_vf_vports(esw); + esw_set_passing_vport_metadata(esw, false); esw_offloads_steering_cleanup(esw); esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 7ac1249eadc3..b84a225bbe86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -566,7 +566,9 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns, return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) +int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask, + u32 *id) { u32 in[MLX5_ST_SZ_DW(alloc_flow_counter_in)] = {0}; u32 out[MLX5_ST_SZ_DW(alloc_flow_counter_out)] = {0}; @@ -574,6 +576,7 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) MLX5_SET(alloc_flow_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_FLOW_COUNTER); + MLX5_SET(alloc_flow_counter_in, in, flow_counter_bulk, alloc_bitmask); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (!err) @@ -581,6 +584,11 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) return err; } +int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) +{ + return mlx5_cmd_fc_bulk_alloc(dev, 0, id); +} + int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id) { u32 in[MLX5_ST_SZ_DW(dealloc_flow_counter_in)] = {0}; @@ -615,67 +623,24 @@ int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, return 0; } -struct mlx5_cmd_fc_bulk { - u32 id; - int num; - int outlen; - u32 out[0]; -}; - -struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num) -{ - struct mlx5_cmd_fc_bulk *b; - int outlen = - MLX5_ST_SZ_BYTES(query_flow_counter_out) + - MLX5_ST_SZ_BYTES(traffic_counter) * num; - - b = kzalloc(sizeof(*b) + outlen, GFP_KERNEL); - if (!b) - return NULL; - - b->id = id; - b->num = num; - b->outlen = outlen; - - return b; -} - -void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b) +int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len) { - kfree(b); + return MLX5_ST_SZ_BYTES(query_flow_counter_out) + + MLX5_ST_SZ_BYTES(traffic_counter) * bulk_len; } -int -mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b) +int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, + u32 *out) { + int outlen = mlx5_cmd_fc_get_bulk_query_out_len(bulk_len); u32 in[MLX5_ST_SZ_DW(query_flow_counter_in)] = {0}; MLX5_SET(query_flow_counter_in, in, opcode, MLX5_CMD_OP_QUERY_FLOW_COUNTER); MLX5_SET(query_flow_counter_in, in, op_mod, 0); - MLX5_SET(query_flow_counter_in, in, flow_counter_id, b->id); - MLX5_SET(query_flow_counter_in, in, num_of_counters, b->num); - return mlx5_cmd_exec(dev, in, sizeof(in), b->out, b->outlen); -} - -void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u32 id, - u64 *packets, u64 *bytes) -{ - int index = id - b->id; - void *stats; - - if (index < 0 || index >= b->num) { - mlx5_core_warn(dev, "Flow counter id (0x%x) out of range (0x%x..0x%x). Counter ignored.\n", - id, b->id, b->id + b->num - 1); - return; - } - - stats = MLX5_ADDR_OF(query_flow_counter_out, b->out, - flow_statistics[index]); - *packets = MLX5_GET64(traffic_counter, stats, packets); - *bytes = MLX5_GET64(traffic_counter, stats, octets); + MLX5_SET(query_flow_counter_in, in, flow_counter_id, base_id); + MLX5_SET(query_flow_counter_in, in, num_of_counters, bulk_len); + return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index e340f9af2f5a..bc4606306009 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -78,20 +78,16 @@ struct mlx5_flow_cmds { }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); +int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask, + u32 *id); int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id); int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, u64 *packets, u64 *bytes); -struct mlx5_cmd_fc_bulk; - -struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num); -void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b); -int -mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b); -void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u32 id, - u64 *packets, u64 *bytes); +int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len); +int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, + u32 *out); const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index b3762123a69c..51f1736c455d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -40,6 +40,8 @@ #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) /* Max number of counters to query in bulk read is 32K */ #define MLX5_SW_MAX_COUNTERS_BULK BIT(15) +#define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) +#define MLX5_FC_POOL_USED_BUFF_RATIO 10 struct mlx5_fc_cache { u64 packets; @@ -58,12 +60,18 @@ struct mlx5_fc { u64 lastpackets; u64 lastbytes; + struct mlx5_fc_bulk *bulk; u32 id; bool aging; struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; }; +static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev); +static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool); +static struct mlx5_fc *mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool); +static void mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc); + /* locking scheme: * * It is the responsibility of the user to prevent concurrent calls or bad @@ -75,7 +83,7 @@ struct mlx5_fc { * access to counter list: * - create (user context) * - mlx5_fc_create() only adds to an addlist to be used by - * mlx5_fc_stats_query_work(). addlist is a lockless single linked list + * mlx5_fc_stats_work(). addlist is a lockless single linked list * that doesn't require any additional synchronization when adding single * node. * - spawn thread to do the actual destroy @@ -136,81 +144,87 @@ static void mlx5_fc_stats_remove(struct mlx5_core_dev *dev, spin_unlock(&fc_stats->counters_idr_lock); } -/* The function returns the last counter that was queried so the caller - * function can continue calling it till all counters are queried. - */ -static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev, - struct mlx5_fc *first, - u32 last_id) +static int get_max_bulk_query_len(struct mlx5_core_dev *dev) { - struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; - struct mlx5_fc *counter = NULL; - struct mlx5_cmd_fc_bulk *b; - bool more = false; - u32 afirst_id; - int num; - int err; + return min_t(int, MLX5_SW_MAX_COUNTERS_BULK, + (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +} - int max_bulk = min_t(int, MLX5_SW_MAX_COUNTERS_BULK, - (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +static void update_counter_cache(int index, u32 *bulk_raw_data, + struct mlx5_fc_cache *cache) +{ + void *stats = MLX5_ADDR_OF(query_flow_counter_out, bulk_raw_data, + flow_statistics[index]); + u64 packets = MLX5_GET64(traffic_counter, stats, packets); + u64 bytes = MLX5_GET64(traffic_counter, stats, octets); - /* first id must be aligned to 4 when using bulk query */ - afirst_id = first->id & ~0x3; + if (cache->packets == packets) + return; - /* number of counters to query inc. the last counter */ - num = ALIGN(last_id - afirst_id + 1, 4); - if (num > max_bulk) { - num = max_bulk; - last_id = afirst_id + num - 1; - } + cache->packets = packets; + cache->bytes = bytes; + cache->lastuse = jiffies; +} - b = mlx5_cmd_fc_bulk_alloc(dev, afirst_id, num); - if (!b) { - mlx5_core_err(dev, "Error allocating resources for bulk query\n"); - return NULL; - } +static void mlx5_fc_stats_query_counter_range(struct mlx5_core_dev *dev, + struct mlx5_fc *first, + u32 last_id) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + bool query_more_counters = (first->id <= last_id); + int max_bulk_len = get_max_bulk_query_len(dev); + u32 *data = fc_stats->bulk_query_out; + struct mlx5_fc *counter = first; + u32 bulk_base_id; + int bulk_len; + int err; - err = mlx5_cmd_fc_bulk_query(dev, b); - if (err) { - mlx5_core_err(dev, "Error doing bulk query: %d\n", err); - goto out; - } + while (query_more_counters) { + /* first id must be aligned to 4 when using bulk query */ + bulk_base_id = counter->id & ~0x3; - counter = first; - list_for_each_entry_from(counter, &fc_stats->counters, list) { - struct mlx5_fc_cache *c = &counter->cache; - u64 packets; - u64 bytes; + /* number of counters to query inc. the last counter */ + bulk_len = min_t(int, max_bulk_len, + ALIGN(last_id - bulk_base_id + 1, 4)); - if (counter->id > last_id) { - more = true; - break; + err = mlx5_cmd_fc_bulk_query(dev, bulk_base_id, bulk_len, + data); + if (err) { + mlx5_core_err(dev, "Error doing bulk query: %d\n", err); + return; } + query_more_counters = false; - mlx5_cmd_fc_bulk_get(dev, b, - counter->id, &packets, &bytes); + list_for_each_entry_from(counter, &fc_stats->counters, list) { + int counter_index = counter->id - bulk_base_id; + struct mlx5_fc_cache *cache = &counter->cache; - if (c->packets == packets) - continue; + if (counter->id >= bulk_base_id + bulk_len) { + query_more_counters = true; + break; + } - c->packets = packets; - c->bytes = bytes; - c->lastuse = jiffies; + update_counter_cache(counter_index, data, cache); + } } - -out: - mlx5_cmd_fc_bulk_free(b); - - return more ? counter : NULL; } -static void mlx5_free_fc(struct mlx5_core_dev *dev, - struct mlx5_fc *counter) +static void mlx5_fc_free(struct mlx5_core_dev *dev, struct mlx5_fc *counter) { mlx5_cmd_fc_free(dev, counter->id); kfree(counter); } +static void mlx5_fc_release(struct mlx5_core_dev *dev, struct mlx5_fc *counter) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + + if (counter->bulk) + mlx5_fc_pool_release_counter(&fc_stats->fc_pool, counter); + else + mlx5_fc_free(dev, counter); +} + static void mlx5_fc_stats_work(struct work_struct *work) { struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev, @@ -234,7 +248,7 @@ static void mlx5_fc_stats_work(struct work_struct *work) llist_for_each_entry_safe(counter, tmp, dellist, dellist) { mlx5_fc_stats_remove(dev, counter); - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } if (time_before(now, fc_stats->next_query) || @@ -244,32 +258,62 @@ static void mlx5_fc_stats_work(struct work_struct *work) counter = list_first_entry(&fc_stats->counters, struct mlx5_fc, list); - while (counter) - counter = mlx5_fc_stats_query(dev, counter, last->id); + if (counter) + mlx5_fc_stats_query_counter_range(dev, counter, last->id); fc_stats->next_query = now + fc_stats->sampling_interval; } -struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +static struct mlx5_fc *mlx5_fc_single_alloc(struct mlx5_core_dev *dev) { - struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; struct mlx5_fc *counter; int err; counter = kzalloc(sizeof(*counter), GFP_KERNEL); if (!counter) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&counter->list); err = mlx5_cmd_fc_alloc(dev, &counter->id); - if (err) - goto err_out; + if (err) { + kfree(counter); + return ERR_PTR(err); + } + + return counter; +} + +static struct mlx5_fc *mlx5_fc_acquire(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct mlx5_fc *counter; + + if (aging && MLX5_CAP_GEN(dev, flow_counter_bulk_alloc) != 0) { + counter = mlx5_fc_pool_acquire_counter(&fc_stats->fc_pool); + if (!IS_ERR(counter)) + return counter; + } + + return mlx5_fc_single_alloc(dev); +} + +struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc *counter = mlx5_fc_acquire(dev, aging); + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int err; + + if (IS_ERR(counter)) + return counter; + + INIT_LIST_HEAD(&counter->list); + counter->aging = aging; if (aging) { u32 id = counter->id; counter->cache.lastuse = jiffies; - counter->aging = true; + counter->lastbytes = counter->cache.bytes; + counter->lastpackets = counter->cache.packets; idr_preload(GFP_KERNEL); spin_lock(&fc_stats->counters_idr_lock); @@ -290,10 +334,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) return counter; err_out_alloc: - mlx5_cmd_fc_free(dev, counter->id); -err_out: - kfree(counter); - + mlx5_fc_release(dev, counter); return ERR_PTR(err); } EXPORT_SYMBOL(mlx5_fc_create); @@ -317,13 +358,15 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter) return; } - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } EXPORT_SYMBOL(mlx5_fc_destroy); int mlx5_init_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int max_bulk_len; + int max_out_len; spin_lock_init(&fc_stats->counters_idr_lock); idr_init(&fc_stats->counters_idr); @@ -331,14 +374,25 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) init_llist_head(&fc_stats->addlist); init_llist_head(&fc_stats->dellist); + max_bulk_len = get_max_bulk_query_len(dev); + max_out_len = mlx5_cmd_fc_get_bulk_query_out_len(max_bulk_len); + fc_stats->bulk_query_out = kzalloc(max_out_len, GFP_KERNEL); + if (!fc_stats->bulk_query_out) + return -ENOMEM; + fc_stats->wq = create_singlethread_workqueue("mlx5_fc"); if (!fc_stats->wq) - return -ENOMEM; + goto err_wq_create; fc_stats->sampling_interval = MLX5_FC_STATS_PERIOD; INIT_DELAYED_WORK(&fc_stats->work, mlx5_fc_stats_work); + mlx5_fc_pool_init(&fc_stats->fc_pool, dev); return 0; + +err_wq_create: + kfree(fc_stats->bulk_query_out); + return -ENOMEM; } void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) @@ -348,18 +402,21 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) struct mlx5_fc *counter; struct mlx5_fc *tmp; + mlx5_fc_pool_cleanup(&fc_stats->fc_pool); cancel_delayed_work_sync(&dev->priv.fc_stats.work); destroy_workqueue(dev->priv.fc_stats.wq); dev->priv.fc_stats.wq = NULL; + kfree(fc_stats->bulk_query_out); + idr_destroy(&fc_stats->counters_idr); tmplist = llist_del_all(&fc_stats->addlist); llist_for_each_entry_safe(counter, tmp, tmplist, addlist) - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list) - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, @@ -401,3 +458,243 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, fc_stats->sampling_interval = min_t(unsigned long, interval, fc_stats->sampling_interval); } + +/* Flow counter bluks */ + +struct mlx5_fc_bulk { + struct list_head pool_list; + u32 base_id; + int bulk_len; + unsigned long *bitmask; + struct mlx5_fc fcs[0]; +}; + +static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, + u32 id) +{ + counter->bulk = bulk; + counter->id = id; +} + +static int mlx5_fc_bulk_get_free_fcs_amount(struct mlx5_fc_bulk *bulk) +{ + return bitmap_weight(bulk->bitmask, bulk->bulk_len); +} + +static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev) +{ + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask; + struct mlx5_fc_bulk *bulk; + int err = -ENOMEM; + int bulk_len; + u32 base_id; + int i; + + alloc_bitmask = MLX5_CAP_GEN(dev, flow_counter_bulk_alloc); + bulk_len = alloc_bitmask > 0 ? MLX5_FC_BULK_NUM_FCS(alloc_bitmask) : 1; + + bulk = kzalloc(sizeof(*bulk) + bulk_len * sizeof(struct mlx5_fc), + GFP_KERNEL); + if (!bulk) + goto err_alloc_bulk; + + bulk->bitmask = kcalloc(BITS_TO_LONGS(bulk_len), sizeof(unsigned long), + GFP_KERNEL); + if (!bulk->bitmask) + goto err_alloc_bitmask; + + err = mlx5_cmd_fc_bulk_alloc(dev, alloc_bitmask, &base_id); + if (err) + goto err_mlx5_cmd_bulk_alloc; + + bulk->base_id = base_id; + bulk->bulk_len = bulk_len; + for (i = 0; i < bulk_len; i++) { + mlx5_fc_init(&bulk->fcs[i], bulk, base_id + i); + set_bit(i, bulk->bitmask); + } + + return bulk; + +err_mlx5_cmd_bulk_alloc: + kfree(bulk->bitmask); +err_alloc_bitmask: + kfree(bulk); +err_alloc_bulk: + return ERR_PTR(err); +} + +static int +mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fc_bulk *bulk) +{ + if (mlx5_fc_bulk_get_free_fcs_amount(bulk) < bulk->bulk_len) { + mlx5_core_err(dev, "Freeing bulk before all counters were released\n"); + return -EBUSY; + } + + mlx5_cmd_fc_free(dev, bulk->base_id); + kfree(bulk->bitmask); + kfree(bulk); + + return 0; +} + +static struct mlx5_fc *mlx5_fc_bulk_acquire_fc(struct mlx5_fc_bulk *bulk) +{ + int free_fc_index = find_first_bit(bulk->bitmask, bulk->bulk_len); + + if (free_fc_index >= bulk->bulk_len) + return ERR_PTR(-ENOSPC); + + clear_bit(free_fc_index, bulk->bitmask); + return &bulk->fcs[free_fc_index]; +} + +static int mlx5_fc_bulk_release_fc(struct mlx5_fc_bulk *bulk, struct mlx5_fc *fc) +{ + int fc_index = fc->id - bulk->base_id; + + if (test_bit(fc_index, bulk->bitmask)) + return -EINVAL; + + set_bit(fc_index, bulk->bitmask); + return 0; +} + +/* Flow counters pool API */ + +static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev) +{ + fc_pool->dev = dev; + mutex_init(&fc_pool->pool_lock); + INIT_LIST_HEAD(&fc_pool->fully_used); + INIT_LIST_HEAD(&fc_pool->partially_used); + INIT_LIST_HEAD(&fc_pool->unused); + fc_pool->available_fcs = 0; + fc_pool->used_fcs = 0; + fc_pool->threshold = 0; +} + +static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *bulk; + struct mlx5_fc_bulk *tmp; + + list_for_each_entry_safe(bulk, tmp, &fc_pool->fully_used, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &fc_pool->partially_used, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &fc_pool->unused, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); +} + +static void mlx5_fc_pool_update_threshold(struct mlx5_fc_pool *fc_pool) +{ + fc_pool->threshold = min_t(int, MLX5_FC_POOL_MAX_THRESHOLD, + fc_pool->used_fcs / MLX5_FC_POOL_USED_BUFF_RATIO); +} + +static struct mlx5_fc_bulk * +mlx5_fc_pool_alloc_new_bulk(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *new_bulk; + + new_bulk = mlx5_fc_bulk_create(dev); + if (!IS_ERR(new_bulk)) + fc_pool->available_fcs += new_bulk->bulk_len; + mlx5_fc_pool_update_threshold(fc_pool); + return new_bulk; +} + +static void +mlx5_fc_pool_free_bulk(struct mlx5_fc_pool *fc_pool, struct mlx5_fc_bulk *bulk) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + + fc_pool->available_fcs -= bulk->bulk_len; + mlx5_fc_bulk_destroy(dev, bulk); + mlx5_fc_pool_update_threshold(fc_pool); +} + +static struct mlx5_fc * +mlx5_fc_pool_acquire_from_list(struct list_head *src_list, + struct list_head *next_list, + bool move_non_full_bulk) +{ + struct mlx5_fc_bulk *bulk; + struct mlx5_fc *fc; + + if (list_empty(src_list)) + return ERR_PTR(-ENODATA); + + bulk = list_first_entry(src_list, struct mlx5_fc_bulk, pool_list); + fc = mlx5_fc_bulk_acquire_fc(bulk); + if (move_non_full_bulk || mlx5_fc_bulk_get_free_fcs_amount(bulk) == 0) + list_move(&bulk->pool_list, next_list); + return fc; +} + +static struct mlx5_fc * +mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_fc_bulk *new_bulk; + struct mlx5_fc *fc; + + mutex_lock(&fc_pool->pool_lock); + + fc = mlx5_fc_pool_acquire_from_list(&fc_pool->partially_used, + &fc_pool->fully_used, false); + if (IS_ERR(fc)) + fc = mlx5_fc_pool_acquire_from_list(&fc_pool->unused, + &fc_pool->partially_used, + true); + if (IS_ERR(fc)) { + new_bulk = mlx5_fc_pool_alloc_new_bulk(fc_pool); + if (IS_ERR(new_bulk)) { + fc = ERR_CAST(new_bulk); + goto out; + } + fc = mlx5_fc_bulk_acquire_fc(new_bulk); + list_add(&new_bulk->pool_list, &fc_pool->partially_used); + } + fc_pool->available_fcs--; + fc_pool->used_fcs++; + +out: + mutex_unlock(&fc_pool->pool_lock); + return fc; +} + +static void +mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *bulk = fc->bulk; + int bulk_free_fcs_amount; + + mutex_lock(&fc_pool->pool_lock); + + if (mlx5_fc_bulk_release_fc(bulk, fc)) { + mlx5_core_warn(dev, "Attempted to release a counter which is not acquired\n"); + goto unlock; + } + + fc_pool->available_fcs++; + fc_pool->used_fcs--; + + bulk_free_fcs_amount = mlx5_fc_bulk_get_free_fcs_amount(bulk); + if (bulk_free_fcs_amount == 1) + list_move_tail(&bulk->pool_list, &fc_pool->partially_used); + if (bulk_free_fcs_amount == bulk->bulk_len) { + list_del(&bulk->pool_list); + if (fc_pool->available_fcs > fc_pool->threshold) + mlx5_fc_pool_free_bulk(fc_pool, bulk); + else + list_add(&bulk->pool_list, &fc_pool->unused); + } + +unlock: + mutex_unlock(&fc_pool->pool_lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b15b27a497fc..fa0e991f1983 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1217,8 +1217,10 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup) { int err = 0; - if (cleanup) + if (cleanup) { + mlx5_unregister_device(dev); mlx5_drain_health_wq(dev); + } mutex_lock(&dev->intf_state_mutex); if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { @@ -1369,7 +1371,6 @@ static void remove_one(struct pci_dev *pdev) mlx5_crdump_disable(dev); mlx5_devlink_unregister(devlink); - mlx5_unregister_device(dev); if (mlx5_unload_one(dev, true)) { mlx5_core_err(dev, "mlx5_unload_one failed\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index c912d82ca64b..30f7848a6f88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -122,12 +122,13 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline_mode) { switch (MLX5_CAP_ETH(mdev, wqe_inline_mode)) { + case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: + if (!mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode)) + break; + /* fall through */ case MLX5_CAP_INLINE_MODE_L2: *min_inline_mode = MLX5_INLINE_MODE_L2; break; - case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: - mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode); - break; case MLX5_CAP_INLINE_MODE_NOT_REQUIRED: *min_inline_mode = MLX5_INLINE_MODE_NONE; break; diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index ff2f419ae352..1b019fdfcd97 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -173,7 +173,7 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, struct nfp_fl_payload *nfp_flow, bool last, struct net_device *in_dev, enum nfp_flower_tun_type tun_type, int *tun_out_cnt, - struct netlink_ext_ack *extack) + bool pkt_host, struct netlink_ext_ack *extack) { size_t act_size = sizeof(struct nfp_fl_output); struct nfp_flower_priv *priv = app->priv; @@ -218,6 +218,20 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, return gid; } output->port = cpu_to_be32(NFP_FL_LAG_OUT | gid); + } else if (nfp_flower_internal_port_can_offload(app, out_dev)) { + if (!(priv->flower_ext_feats & NFP_FL_FEATS_PRE_TUN_RULES)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pre-tunnel rules not supported in loaded firmware"); + return -EOPNOTSUPP; + } + + if (nfp_flow->pre_tun_rule.dev || !pkt_host) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pre-tunnel rules require single egress dev and ptype HOST action"); + return -EOPNOTSUPP; + } + + nfp_flow->pre_tun_rule.dev = out_dev; + + return 0; } else { /* Set action output parameters. */ output->flags = cpu_to_be16(tmp_flags); @@ -885,7 +899,7 @@ nfp_flower_output_action(struct nfp_app *app, struct nfp_fl_payload *nfp_fl, int *a_len, struct net_device *netdev, bool last, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, - int *out_cnt, u32 *csum_updated, + int *out_cnt, u32 *csum_updated, bool pkt_host, struct netlink_ext_ack *extack) { struct nfp_flower_priv *priv = app->priv; @@ -907,7 +921,7 @@ nfp_flower_output_action(struct nfp_app *app, output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len]; err = nfp_fl_output(app, output, act, nfp_fl, last, netdev, *tun_type, - tun_out_cnt, extack); + tun_out_cnt, pkt_host, extack); if (err) return err; @@ -939,7 +953,7 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, struct net_device *netdev, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, int *out_cnt, u32 *csum_updated, - struct nfp_flower_pedit_acts *set_act, + struct nfp_flower_pedit_acts *set_act, bool *pkt_host, struct netlink_ext_ack *extack, int act_idx) { struct nfp_fl_set_ipv4_tun *set_tun; @@ -955,17 +969,21 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, case FLOW_ACTION_DROP: nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_DROP); break; + case FLOW_ACTION_REDIRECT_INGRESS: case FLOW_ACTION_REDIRECT: err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev, true, tun_type, tun_out_cnt, - out_cnt, csum_updated, extack); + out_cnt, csum_updated, *pkt_host, + extack); if (err) return err; break; + case FLOW_ACTION_MIRRED_INGRESS: case FLOW_ACTION_MIRRED: err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev, false, tun_type, tun_out_cnt, - out_cnt, csum_updated, extack); + out_cnt, csum_updated, *pkt_host, + extack); if (err) return err; break; @@ -1095,6 +1113,13 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, nfp_fl_set_mpls(set_m, act); *a_len += sizeof(struct nfp_fl_set_mpls); break; + case FLOW_ACTION_PTYPE: + /* TC ptype skbedit sets PACKET_HOST for ingress redirect. */ + if (act->ptype != PACKET_HOST) + return -EOPNOTSUPP; + + *pkt_host = true; + break; default: /* Currently we do not handle any other actions. */ NL_SET_ERR_MSG_MOD(extack, "unsupported offload: unsupported action in action list"); @@ -1150,6 +1175,7 @@ int nfp_flower_compile_action(struct nfp_app *app, struct nfp_flower_pedit_acts set_act; enum nfp_flower_tun_type tun_type; struct flow_action_entry *act; + bool pkt_host = false; u32 csum_updated = 0; memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ); @@ -1166,7 +1192,7 @@ int nfp_flower_compile_action(struct nfp_app *app, err = nfp_flower_loop_action(app, act, flow, nfp_flow, &act_len, netdev, &tun_type, &tun_out_cnt, &out_cnt, &csum_updated, - &set_act, extack, i); + &set_act, &pkt_host, extack, i); if (err) return err; act_cnt++; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 332439400d85..7eb2ec8969c3 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -220,7 +220,8 @@ struct nfp_fl_set_ipv4_tun { __be16 tun_flags; u8 ttl; u8 tos; - __be32 extra; + __be16 outer_vlan_tpid; + __be16 outer_vlan_tci; u8 tun_len; u8 res2; __be16 tun_proto; @@ -483,6 +484,7 @@ enum nfp_flower_cmsg_type_port { NFP_FLOWER_CMSG_TYPE_QOS_MOD = 18, NFP_FLOWER_CMSG_TYPE_QOS_DEL = 19, NFP_FLOWER_CMSG_TYPE_QOS_STATS = 20, + NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE = 21, NFP_FLOWER_CMSG_TYPE_MAX = 32, }; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index eb846133943b..7a20447cca19 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -781,6 +781,7 @@ static int nfp_flower_init(struct nfp_app *app) INIT_LIST_HEAD(&app_priv->indr_block_cb_priv); INIT_LIST_HEAD(&app_priv->non_repr_priv); + app_priv->pre_tun_rule_cnt = 0; return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index af9441d5787f..31d94592a7c0 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -42,6 +42,7 @@ struct nfp_app; #define NFP_FL_FEATS_VLAN_PCP BIT(3) #define NFP_FL_FEATS_VF_RLIM BIT(4) #define NFP_FL_FEATS_FLOW_MOD BIT(5) +#define NFP_FL_FEATS_PRE_TUN_RULES BIT(6) #define NFP_FL_FEATS_FLOW_MERGE BIT(30) #define NFP_FL_FEATS_LAG BIT(31) @@ -162,6 +163,7 @@ struct nfp_fl_internal_ports { * @qos_stats_work: Workqueue for qos stats processing * @qos_rate_limiters: Current active qos rate limiters * @qos_stats_lock: Lock on qos stats updates + * @pre_tun_rule_cnt: Number of pre-tunnel rules offloaded */ struct nfp_flower_priv { struct nfp_app *app; @@ -193,6 +195,7 @@ struct nfp_flower_priv { struct delayed_work qos_stats_work; unsigned int qos_rate_limiters; spinlock_t qos_stats_lock; /* Protect the qos stats */ + int pre_tun_rule_cnt; }; /** @@ -218,6 +221,7 @@ struct nfp_fl_qos { * @block_shared: Flag indicating if offload applies to shared blocks * @mac_list: List entry of reprs that share the same offloaded MAC * @qos_table: Stored info on filters implementing qos + * @on_bridge: Indicates if the repr is attached to a bridge */ struct nfp_flower_repr_priv { struct nfp_repr *nfp_repr; @@ -227,6 +231,7 @@ struct nfp_flower_repr_priv { bool block_shared; struct list_head mac_list; struct nfp_fl_qos qos_table; + bool on_bridge; }; /** @@ -280,6 +285,11 @@ struct nfp_fl_payload { char *action_data; struct list_head linked_flows; bool in_hw; + struct { + struct net_device *dev; + __be16 vlan_tci; + __be16 port_idx; + } pre_tun_rule; }; struct nfp_fl_payload_link { @@ -333,6 +343,11 @@ static inline bool nfp_flower_is_merge_flow(struct nfp_fl_payload *flow_pay) return flow_pay->tc_flower_cookie == (unsigned long)flow_pay; } +static inline bool nfp_flower_is_supported_bridge(struct net_device *netdev) +{ + return netif_is_ovs_master(netdev); +} + int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, unsigned int host_ctx_split); void nfp_flower_metadata_cleanup(struct nfp_app *app); @@ -415,4 +430,8 @@ void nfp_flower_non_repr_priv_put(struct nfp_app *app, struct net_device *netdev); u32 nfp_flower_get_port_id_from_netdev(struct nfp_app *app, struct net_device *netdev); +int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, + struct nfp_fl_payload *flow); +int nfp_flower_xmit_pre_tun_del_flow(struct nfp_app *app, + struct nfp_fl_payload *flow); #endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index e209f150c5f2..ff8a9f1a38f8 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -61,6 +61,11 @@ NFP_FLOWER_LAYER_IPV4 | \ NFP_FLOWER_LAYER_IPV6) +#define NFP_FLOWER_PRE_TUN_RULE_FIELDS \ + (NFP_FLOWER_LAYER_PORT | \ + NFP_FLOWER_LAYER_MAC | \ + NFP_FLOWER_LAYER_IPV4) + struct nfp_flower_merge_check { union { struct { @@ -489,6 +494,7 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer) flow_pay->meta.flags = 0; INIT_LIST_HEAD(&flow_pay->linked_flows); flow_pay->in_hw = false; + flow_pay->pre_tun_rule.dev = NULL; return flow_pay; @@ -732,28 +738,62 @@ nfp_flower_copy_pre_actions(char *act_dst, char *act_src, int len, return act_off; } -static int nfp_fl_verify_post_tun_acts(char *acts, int len) +static int +nfp_fl_verify_post_tun_acts(char *acts, int len, struct nfp_fl_push_vlan **vlan) { struct nfp_fl_act_head *a; unsigned int act_off = 0; while (act_off < len) { a = (struct nfp_fl_act_head *)&acts[act_off]; - if (a->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) + + if (a->jump_id == NFP_FL_ACTION_OPCODE_PUSH_VLAN && !act_off) + *vlan = (struct nfp_fl_push_vlan *)a; + else if (a->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) return -EOPNOTSUPP; act_off += a->len_lw << NFP_FL_LW_SIZ; } + /* Ensure any VLAN push also has an egress action. */ + if (*vlan && act_off <= sizeof(struct nfp_fl_push_vlan)) + return -EOPNOTSUPP; + return 0; } static int +nfp_fl_push_vlan_after_tun(char *acts, int len, struct nfp_fl_push_vlan *vlan) +{ + struct nfp_fl_set_ipv4_tun *tun; + struct nfp_fl_act_head *a; + unsigned int act_off = 0; + + while (act_off < len) { + a = (struct nfp_fl_act_head *)&acts[act_off]; + + if (a->jump_id == NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL) { + tun = (struct nfp_fl_set_ipv4_tun *)a; + tun->outer_vlan_tpid = vlan->vlan_tpid; + tun->outer_vlan_tci = vlan->vlan_tci; + + return 0; + } + + act_off += a->len_lw << NFP_FL_LW_SIZ; + } + + /* Return error if no tunnel action is found. */ + return -EOPNOTSUPP; +} + +static int nfp_flower_merge_action(struct nfp_fl_payload *sub_flow1, struct nfp_fl_payload *sub_flow2, struct nfp_fl_payload *merge_flow) { unsigned int sub1_act_len, sub2_act_len, pre_off1, pre_off2; + struct nfp_fl_push_vlan *post_tun_push_vlan = NULL; bool tunnel_act = false; char *merge_act; int err; @@ -790,18 +830,36 @@ nfp_flower_merge_action(struct nfp_fl_payload *sub_flow1, sub2_act_len -= pre_off2; /* FW does a tunnel push when egressing, therefore, if sub_flow 1 pushes - * a tunnel, sub_flow 2 can only have output actions for a valid merge. + * a tunnel, there are restrictions on what sub_flow 2 actions lead to a + * valid merge. */ if (tunnel_act) { char *post_tun_acts = &sub_flow2->action_data[pre_off2]; - err = nfp_fl_verify_post_tun_acts(post_tun_acts, sub2_act_len); + err = nfp_fl_verify_post_tun_acts(post_tun_acts, sub2_act_len, + &post_tun_push_vlan); if (err) return err; + + if (post_tun_push_vlan) { + pre_off2 += sizeof(*post_tun_push_vlan); + sub2_act_len -= sizeof(*post_tun_push_vlan); + } } /* Copy remaining actions from sub_flows 1 and 2. */ memcpy(merge_act, sub_flow1->action_data + pre_off1, sub1_act_len); + + if (post_tun_push_vlan) { + /* Update tunnel action in merge to include VLAN push. */ + err = nfp_fl_push_vlan_after_tun(merge_act, sub1_act_len, + post_tun_push_vlan); + if (err) + return err; + + merge_flow->meta.act_len -= sizeof(*post_tun_push_vlan); + } + merge_act += sub1_act_len; memcpy(merge_act, sub_flow2->action_data + pre_off2, sub2_act_len); @@ -945,6 +1003,106 @@ err_destroy_merge_flow: } /** + * nfp_flower_validate_pre_tun_rule() + * @app: Pointer to the APP handle + * @flow: Pointer to NFP flow representation of rule + * @extack: Netlink extended ACK report + * + * Verifies the flow as a pre-tunnel rule. + * + * Return: negative value on error, 0 if verified. + */ +static int +nfp_flower_validate_pre_tun_rule(struct nfp_app *app, + struct nfp_fl_payload *flow, + struct netlink_ext_ack *extack) +{ + struct nfp_flower_meta_tci *meta_tci; + struct nfp_flower_mac_mpls *mac; + struct nfp_fl_act_head *act; + u8 *mask = flow->mask_data; + bool vlan = false; + int act_offset; + u8 key_layer; + + meta_tci = (struct nfp_flower_meta_tci *)flow->unmasked_data; + if (meta_tci->tci & cpu_to_be16(NFP_FLOWER_MASK_VLAN_PRESENT)) { + u16 vlan_tci = be16_to_cpu(meta_tci->tci); + + vlan_tci &= ~NFP_FLOWER_MASK_VLAN_PRESENT; + flow->pre_tun_rule.vlan_tci = cpu_to_be16(vlan_tci); + vlan = true; + } else { + flow->pre_tun_rule.vlan_tci = cpu_to_be16(0xffff); + } + + key_layer = meta_tci->nfp_flow_key_layer; + if (key_layer & ~NFP_FLOWER_PRE_TUN_RULE_FIELDS) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: too many match fields"); + return -EOPNOTSUPP; + } + + if (!(key_layer & NFP_FLOWER_LAYER_MAC)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: MAC fields match required"); + return -EOPNOTSUPP; + } + + /* Skip fields known to exist. */ + mask += sizeof(struct nfp_flower_meta_tci); + mask += sizeof(struct nfp_flower_in_port); + + /* Ensure destination MAC address is fully matched. */ + mac = (struct nfp_flower_mac_mpls *)mask; + if (!is_broadcast_ether_addr(&mac->mac_dst[0])) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: dest MAC field must not be masked"); + return -EOPNOTSUPP; + } + + if (key_layer & NFP_FLOWER_LAYER_IPV4) { + int ip_flags = offsetof(struct nfp_flower_ipv4, ip_ext.flags); + int ip_proto = offsetof(struct nfp_flower_ipv4, ip_ext.proto); + int i; + + mask += sizeof(struct nfp_flower_mac_mpls); + + /* Ensure proto and flags are the only IP layer fields. */ + for (i = 0; i < sizeof(struct nfp_flower_ipv4); i++) + if (mask[i] && i != ip_flags && i != ip_proto) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: only flags and proto can be matched in ip header"); + return -EOPNOTSUPP; + } + } + + /* Action must be a single egress or pop_vlan and egress. */ + act_offset = 0; + act = (struct nfp_fl_act_head *)&flow->action_data[act_offset]; + if (vlan) { + if (act->jump_id != NFP_FL_ACTION_OPCODE_POP_VLAN) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: match on VLAN must have VLAN pop as first action"); + return -EOPNOTSUPP; + } + + act_offset += act->len_lw << NFP_FL_LW_SIZ; + act = (struct nfp_fl_act_head *)&flow->action_data[act_offset]; + } + + if (act->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: non egress action detected where egress was expected"); + return -EOPNOTSUPP; + } + + act_offset += act->len_lw << NFP_FL_LW_SIZ; + + /* Ensure there are no more actions after egress. */ + if (act_offset != flow->meta.act_len) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: egress is not the last action"); + return -EOPNOTSUPP; + } + + return 0; +} + +/** * nfp_flower_add_offload() - Adds a new flow to hardware. * @app: Pointer to the APP handle * @netdev: netdev structure. @@ -994,6 +1152,12 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, if (err) goto err_destroy_flow; + if (flow_pay->pre_tun_rule.dev) { + err = nfp_flower_validate_pre_tun_rule(app, flow_pay, extack); + if (err) + goto err_destroy_flow; + } + err = nfp_compile_flow_metadata(app, flow, flow_pay, netdev, extack); if (err) goto err_destroy_flow; @@ -1006,8 +1170,11 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, goto err_release_metadata; } - err = nfp_flower_xmit_flow(app, flow_pay, - NFP_FLOWER_CMSG_TYPE_FLOW_ADD); + if (flow_pay->pre_tun_rule.dev) + err = nfp_flower_xmit_pre_tun_flow(app, flow_pay); + else + err = nfp_flower_xmit_flow(app, flow_pay, + NFP_FLOWER_CMSG_TYPE_FLOW_ADD); if (err) goto err_remove_rhash; @@ -1149,8 +1316,11 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, goto err_free_merge_flow; } - err = nfp_flower_xmit_flow(app, nfp_flow, - NFP_FLOWER_CMSG_TYPE_FLOW_DEL); + if (nfp_flow->pre_tun_rule.dev) + err = nfp_flower_xmit_pre_tun_del_flow(app, nfp_flow); + else + err = nfp_flower_xmit_flow(app, nfp_flow, + NFP_FLOWER_CMSG_TYPE_FLOW_DEL); /* Fall through on error. */ err_free_merge_flow: diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index a7a80f4b722a..def8c198b016 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -15,6 +15,24 @@ #define NFP_FL_MAX_ROUTES 32 +#define NFP_TUN_PRE_TUN_RULE_LIMIT 32 +#define NFP_TUN_PRE_TUN_RULE_DEL 0x1 +#define NFP_TUN_PRE_TUN_IDX_BIT 0x8 + +/** + * struct nfp_tun_pre_run_rule - rule matched before decap + * @flags: options for the rule offset + * @port_idx: index of destination MAC address for the rule + * @vlan_tci: VLAN info associated with MAC + * @host_ctx_id: stats context of rule to update + */ +struct nfp_tun_pre_tun_rule { + __be32 flags; + __be16 port_idx; + __be16 vlan_tci; + __be32 host_ctx_id; +}; + /** * struct nfp_tun_active_tuns - periodic message of active tunnels * @seq: sequence number of the message @@ -124,11 +142,12 @@ enum nfp_flower_mac_offload_cmd { /** * struct nfp_tun_offloaded_mac - hashtable entry for an offloaded MAC - * @ht_node: Hashtable entry - * @addr: Offloaded MAC address - * @index: Offloaded index for given MAC address - * @ref_count: Number of devs using this MAC address - * @repr_list: List of reprs sharing this MAC address + * @ht_node: Hashtable entry + * @addr: Offloaded MAC address + * @index: Offloaded index for given MAC address + * @ref_count: Number of devs using this MAC address + * @repr_list: List of reprs sharing this MAC address + * @bridge_count: Number of bridge/internal devs with MAC */ struct nfp_tun_offloaded_mac { struct rhash_head ht_node; @@ -136,6 +155,7 @@ struct nfp_tun_offloaded_mac { u16 index; int ref_count; struct list_head repr_list; + int bridge_count; }; static const struct rhashtable_params offloaded_macs_params = { @@ -556,6 +576,8 @@ nfp_tunnel_offloaded_macs_inc_ref_and_link(struct nfp_tun_offloaded_mac *entry, list_del(&repr_priv->mac_list); list_add_tail(&repr_priv->mac_list, &entry->repr_list); + } else if (nfp_flower_is_supported_bridge(netdev)) { + entry->bridge_count++; } entry->ref_count++; @@ -572,20 +594,35 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev, entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr); if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) { - nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, netdev, mod); - return 0; + if (entry->bridge_count || + !nfp_flower_is_supported_bridge(netdev)) { + nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, + netdev, mod); + return 0; + } + + /* MAC is global but matches need to go to pre_tun table. */ + nfp_mac_idx = entry->index | NFP_TUN_PRE_TUN_IDX_BIT; } - /* Assign a global index if non-repr or MAC address is now shared. */ - if (entry || !port) { - ida_idx = ida_simple_get(&priv->tun.mac_off_ids, 0, - NFP_MAX_MAC_INDEX, GFP_KERNEL); - if (ida_idx < 0) - return ida_idx; + if (!nfp_mac_idx) { + /* Assign a global index if non-repr or MAC is now shared. */ + if (entry || !port) { + ida_idx = ida_simple_get(&priv->tun.mac_off_ids, 0, + NFP_MAX_MAC_INDEX, GFP_KERNEL); + if (ida_idx < 0) + return ida_idx; - nfp_mac_idx = nfp_tunnel_get_global_mac_idx_from_ida(ida_idx); - } else { - nfp_mac_idx = nfp_tunnel_get_mac_idx_from_phy_port_id(port); + nfp_mac_idx = + nfp_tunnel_get_global_mac_idx_from_ida(ida_idx); + + if (nfp_flower_is_supported_bridge(netdev)) + nfp_mac_idx |= NFP_TUN_PRE_TUN_IDX_BIT; + + } else { + nfp_mac_idx = + nfp_tunnel_get_mac_idx_from_phy_port_id(port); + } } if (!entry) { @@ -654,6 +691,25 @@ nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, list_del(&repr_priv->mac_list); } + if (nfp_flower_is_supported_bridge(netdev)) { + entry->bridge_count--; + + if (!entry->bridge_count && entry->ref_count) { + u16 nfp_mac_idx; + + nfp_mac_idx = entry->index & ~NFP_TUN_PRE_TUN_IDX_BIT; + if (__nfp_tunnel_offload_mac(app, mac, nfp_mac_idx, + false)) { + nfp_flower_cmsg_warn(app, "MAC offload index revert failed on %s.\n", + netdev_name(netdev)); + return 0; + } + + entry->index = nfp_mac_idx; + return 0; + } + } + /* If MAC is now used by 1 repr set the offloaded MAC index to port. */ if (entry->ref_count == 1 && list_is_singular(&entry->repr_list)) { u16 nfp_mac_idx; @@ -713,6 +769,9 @@ nfp_tunnel_offload_mac(struct nfp_app *app, struct net_device *netdev, return 0; repr_priv = repr->app_priv; + if (repr_priv->on_bridge) + return 0; + mac_offloaded = &repr_priv->mac_offloaded; off_mac = &repr_priv->offloaded_mac_addr[0]; port = nfp_repr_get_port_id(netdev); @@ -828,10 +887,119 @@ int nfp_tunnel_mac_event_handler(struct nfp_app *app, if (err) nfp_flower_cmsg_warn(app, "Failed to offload MAC change on %s.\n", netdev_name(netdev)); + } else if (event == NETDEV_CHANGEUPPER) { + /* If a repr is attached to a bridge then tunnel packets + * entering the physical port are directed through the bridge + * datapath and cannot be directly detunneled. Therefore, + * associated offloaded MACs and indexes should not be used + * by fw for detunneling. + */ + struct netdev_notifier_changeupper_info *info = ptr; + struct net_device *upper = info->upper_dev; + struct nfp_flower_repr_priv *repr_priv; + struct nfp_repr *repr; + + if (!nfp_netdev_is_nfp_repr(netdev) || + !nfp_flower_is_supported_bridge(upper)) + return NOTIFY_OK; + + repr = netdev_priv(netdev); + if (repr->app != app) + return NOTIFY_OK; + + repr_priv = repr->app_priv; + + if (info->linking) { + if (nfp_tunnel_offload_mac(app, netdev, + NFP_TUNNEL_MAC_OFFLOAD_DEL)) + nfp_flower_cmsg_warn(app, "Failed to delete offloaded MAC on %s.\n", + netdev_name(netdev)); + repr_priv->on_bridge = true; + } else { + repr_priv->on_bridge = false; + + if (!(netdev->flags & IFF_UP)) + return NOTIFY_OK; + + if (nfp_tunnel_offload_mac(app, netdev, + NFP_TUNNEL_MAC_OFFLOAD_ADD)) + nfp_flower_cmsg_warn(app, "Failed to offload MAC on %s.\n", + netdev_name(netdev)); + } } return NOTIFY_OK; } +int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, + struct nfp_fl_payload *flow) +{ + struct nfp_flower_priv *app_priv = app->priv; + struct nfp_tun_offloaded_mac *mac_entry; + struct nfp_tun_pre_tun_rule payload; + struct net_device *internal_dev; + int err; + + if (app_priv->pre_tun_rule_cnt == NFP_TUN_PRE_TUN_RULE_LIMIT) + return -ENOSPC; + + memset(&payload, 0, sizeof(struct nfp_tun_pre_tun_rule)); + + internal_dev = flow->pre_tun_rule.dev; + payload.vlan_tci = flow->pre_tun_rule.vlan_tci; + payload.host_ctx_id = flow->meta.host_ctx_id; + + /* Lookup MAC index for the pre-tunnel rule egress device. + * Note that because the device is always an internal port, it will + * have a constant global index so does not need to be tracked. + */ + mac_entry = nfp_tunnel_lookup_offloaded_macs(app, + internal_dev->dev_addr); + if (!mac_entry) + return -ENOENT; + + payload.port_idx = cpu_to_be16(mac_entry->index); + + /* Copy mac id and vlan to flow - dev may not exist at delete time. */ + flow->pre_tun_rule.vlan_tci = payload.vlan_tci; + flow->pre_tun_rule.port_idx = payload.port_idx; + + err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE, + sizeof(struct nfp_tun_pre_tun_rule), + (unsigned char *)&payload, GFP_KERNEL); + if (err) + return err; + + app_priv->pre_tun_rule_cnt++; + + return 0; +} + +int nfp_flower_xmit_pre_tun_del_flow(struct nfp_app *app, + struct nfp_fl_payload *flow) +{ + struct nfp_flower_priv *app_priv = app->priv; + struct nfp_tun_pre_tun_rule payload; + u32 tmp_flags = 0; + int err; + + memset(&payload, 0, sizeof(struct nfp_tun_pre_tun_rule)); + + tmp_flags |= NFP_TUN_PRE_TUN_RULE_DEL; + payload.flags = cpu_to_be32(tmp_flags); + payload.vlan_tci = flow->pre_tun_rule.vlan_tci; + payload.port_idx = flow->pre_tun_rule.port_idx; + + err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE, + sizeof(struct nfp_tun_pre_tun_rule), + (unsigned char *)&payload, GFP_KERNEL); + if (err) + return err; + + app_priv->pre_tun_rule_cnt--; + + return 0; +} + int nfp_tunnel_config_start(struct nfp_app *app) { struct nfp_flower_priv *priv = app->priv; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 109779e449cd..a10ff9e1efec 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -271,7 +271,6 @@ enum rtl_registers { Config3 = 0x54, Config4 = 0x55, Config5 = 0x56, - MultiIntr = 0x5c, PHYAR = 0x60, PHYstatus = 0x6c, RxMaxSize = 0xda, @@ -851,6 +850,14 @@ static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) return RTL_R32(tp, OCPDR); } +static void r8168_mac_ocp_modify(struct rtl8169_private *tp, u32 reg, u16 mask, + u16 set) +{ + u16 data = r8168_mac_ocp_read(tp, reg); + + r8168_mac_ocp_write(tp, reg, (data & ~mask) | set); +} + #define OCP_STD_PHY_BASE 0xa400 static void r8168g_mdio_write(struct rtl8169_private *tp, int reg, int value) @@ -4408,7 +4415,7 @@ static void rtl_hw_start_8168c_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168c_2[] = { { 0x01, 0, 0x0001 }, - { 0x03, 0x0400, 0x0220 } + { 0x03, 0x0400, 0x0020 } }; rtl_set_def_aspm_entry_latency(tp); @@ -4455,7 +4462,8 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) static const struct ephy_info e_info_8168d_4[] = { { 0x0b, 0x0000, 0x0048 }, { 0x19, 0x0020, 0x0050 }, - { 0x0c, 0x0100, 0x0020 } + { 0x0c, 0x0100, 0x0020 }, + { 0x10, 0x0004, 0x0000 }, }; rtl_set_def_aspm_entry_latency(tp); @@ -4505,7 +4513,9 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168e_2[] = { { 0x09, 0x0000, 0x0080 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_set_def_aspm_entry_latency(tp); @@ -4567,7 +4577,9 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp) { 0x06, 0x00c0, 0x0020 }, { 0x08, 0x0001, 0x0002 }, { 0x09, 0x0000, 0x0080 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_hw_start_8168f(tp); @@ -4582,8 +4594,9 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp) static const struct ephy_info e_info_8168f_1[] = { { 0x06, 0x00c0, 0x0020 }, { 0x0f, 0xffff, 0x5200 }, - { 0x1e, 0x0000, 0x4000 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_hw_start_8168f(tp); @@ -4622,8 +4635,8 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp) static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168g_1[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x37d0, 0x0820 }, + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x3ff0, 0x0820 }, { 0x1e, 0x0000, 0x0001 }, { 0x19, 0x8000, 0x0000 } }; @@ -4639,10 +4652,15 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168g_2[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x3df0, 0x0200 }, - { 0x19, 0xffff, 0xfc00 }, - { 0x1e, 0xffff, 0x20eb } + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x3ff0, 0x0820 }, + { 0x19, 0xffff, 0x7c00 }, + { 0x1e, 0xffff, 0x20eb }, + { 0x0d, 0xffff, 0x1666 }, + { 0x00, 0xffff, 0x10a3 }, + { 0x06, 0xffff, 0xf050 }, + { 0x04, 0x0000, 0x0010 }, + { 0x1d, 0x4000, 0x0000 }, }; rtl_hw_start_8168g(tp); @@ -4656,11 +4674,16 @@ static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) static void rtl_hw_start_8411_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8411_2[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x3df0, 0x0200 }, - { 0x0f, 0xffff, 0x5200 }, - { 0x19, 0x0020, 0x0000 }, - { 0x1e, 0x0000, 0x2000 } + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x37d0, 0x0820 }, + { 0x1e, 0x0000, 0x0001 }, + { 0x19, 0x8021, 0x0000 }, + { 0x1e, 0x0000, 0x2000 }, + { 0x0d, 0x0100, 0x0200 }, + { 0x00, 0x0000, 0x0080 }, + { 0x06, 0x0000, 0x0010 }, + { 0x04, 0x0000, 0x0010 }, + { 0x1d, 0x0000, 0x4000 }, }; rtl_hw_start_8168g(tp); @@ -4810,16 +4833,15 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp) static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) { - int rg_saw_cnt; - u32 data; static const struct ephy_info e_info_8168h_1[] = { { 0x1e, 0x0800, 0x0001 }, { 0x1d, 0x0000, 0x0800 }, { 0x05, 0xffff, 0x2089 }, { 0x06, 0xffff, 0x5881 }, - { 0x04, 0xffff, 0x154a }, + { 0x04, 0xffff, 0x854a }, { 0x01, 0xffff, 0x068b } }; + int rg_saw_cnt; /* disable aspm and clock request before access ephy */ rtl_hw_aspm_clkreq_enable(tp, false); @@ -4864,31 +4886,13 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) sw_cnt_1ms_ini = 16000000/rg_saw_cnt; sw_cnt_1ms_ini &= 0x0fff; - data = r8168_mac_ocp_read(tp, 0xd412); - data &= ~0x0fff; - data |= sw_cnt_1ms_ini; - r8168_mac_ocp_write(tp, 0xd412, data); + r8168_mac_ocp_modify(tp, 0xd412, 0x0fff, sw_cnt_1ms_ini); } - data = r8168_mac_ocp_read(tp, 0xe056); - data &= ~0xf0; - data |= 0x70; - r8168_mac_ocp_write(tp, 0xe056, data); - - data = r8168_mac_ocp_read(tp, 0xe052); - data &= ~0x6000; - data |= 0x8008; - r8168_mac_ocp_write(tp, 0xe052, data); - - data = r8168_mac_ocp_read(tp, 0xe0d6); - data &= ~0x01ff; - data |= 0x017f; - r8168_mac_ocp_write(tp, 0xe0d6, data); - - data = r8168_mac_ocp_read(tp, 0xd420); - data &= ~0x0fff; - data |= 0x047f; - r8168_mac_ocp_write(tp, 0xd420, data); + r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0070); + r8168_mac_ocp_modify(tp, 0xe052, 0x6000, 0x8008); + r8168_mac_ocp_modify(tp, 0xe0d6, 0x01ff, 0x017f); + r8168_mac_ocp_modify(tp, 0xd420, 0x0fff, 0x047f); r8168_mac_ocp_write(tp, 0xe63e, 0x0001); r8168_mac_ocp_write(tp, 0xe63e, 0x0000); @@ -4970,12 +4974,11 @@ static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp) static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) { - u32 data; static const struct ephy_info e_info_8168ep_3[] = { - { 0x00, 0xffff, 0x10a3 }, - { 0x19, 0xffff, 0x7c00 }, - { 0x1e, 0xffff, 0x20eb }, - { 0x0d, 0xffff, 0x1666 } + { 0x00, 0x0000, 0x0080 }, + { 0x0d, 0x0100, 0x0200 }, + { 0x19, 0x8021, 0x0000 }, + { 0x1e, 0x0000, 0x2000 }, }; /* disable aspm and clock request before access ephy */ @@ -4987,18 +4990,9 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN); - data = r8168_mac_ocp_read(tp, 0xd3e2); - data &= 0xf000; - data |= 0x0271; - r8168_mac_ocp_write(tp, 0xd3e2, data); - - data = r8168_mac_ocp_read(tp, 0xd3e4); - data &= 0xff00; - r8168_mac_ocp_write(tp, 0xd3e4, data); - - data = r8168_mac_ocp_read(tp, 0xe860); - data |= 0x0080; - r8168_mac_ocp_write(tp, 0xe860, data); + r8168_mac_ocp_modify(tp, 0xd3e2, 0x0fff, 0x0271); + r8168_mac_ocp_modify(tp, 0xd3e4, 0x00ff, 0x0000); + r8168_mac_ocp_modify(tp, 0xe860, 0x0000, 0x0080); rtl_hw_aspm_clkreq_enable(tp, true); } @@ -5241,10 +5235,7 @@ static void rtl_hw_start(struct rtl8169_private *tp) RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); rtl_init_rxcfg(tp); rtl_set_tx_config_registers(tp); - rtl_set_rx_mode(tp->dev); - /* no early-rx interrupts */ - RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); rtl_irq_enable(tp); } @@ -6661,8 +6652,6 @@ static int r8169_mdio_register(struct rtl8169_private *tp) static void rtl_hw_init_8168g(struct rtl8169_private *tp) { - u32 data; - tp->ocp_base = OCP_STD_PHY_BASE; RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN); @@ -6677,16 +6666,12 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp) msleep(1); RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); - data = r8168_mac_ocp_read(tp, 0xe8de); - data &= ~(1 << 14); - r8168_mac_ocp_write(tp, 0xe8de, data); + r8168_mac_ocp_modify(tp, 0xe8de, BIT(14), 0); if (!rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42)) return; - data = r8168_mac_ocp_read(tp, 0xe8de); - data |= (1 << 15); - r8168_mac_ocp_write(tp, 0xe8de, data); + r8168_mac_ocp_modify(tp, 0xe8de, 0, BIT(15)); rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42); } diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 206d8650ee7f..48ca213c0ada 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -172,8 +172,8 @@ config MDIO_MSCC_MIIM config MDIO_OCTEON tristate "Octeon and some ThunderX SOCs MDIO buses" - depends on 64BIT - depends on HAS_IOMEM && OF_MDIO + depends on (64BIT && OF_MDIO) || COMPILE_TEST + depends on HAS_IOMEM select MDIO_CAVIUM help This module provides a driver for the Octeon and ThunderX MDIO diff --git a/drivers/net/phy/mdio-cavium.h b/drivers/net/phy/mdio-cavium.h index ed5f9bb5448d..b7f89ad27465 100644 --- a/drivers/net/phy/mdio-cavium.h +++ b/drivers/net/phy/mdio-cavium.h @@ -108,6 +108,8 @@ static inline u64 oct_mdio_readq(u64 addr) return cvmx_read_csr(addr); } #else +#include <linux/io-64-nonatomic-lo-hi.h> + #define oct_mdio_writeq(val, addr) writeq(val, (void *)addr) #define oct_mdio_readq(addr) readq((void *)addr) #endif diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 0e6da1840c7d..d8f348ef9c33 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -477,6 +477,17 @@ struct mlx5_core_sriov { u16 max_vfs; }; +struct mlx5_fc_pool { + struct mlx5_core_dev *dev; + struct mutex pool_lock; /* protects pool lists */ + struct list_head fully_used; + struct list_head partially_used; + struct list_head unused; + int available_fcs; + int used_fcs; + int threshold; +}; + struct mlx5_fc_stats { spinlock_t counters_idr_lock; /* protects counters_idr */ struct idr counters_idr; @@ -488,6 +499,8 @@ struct mlx5_fc_stats { struct delayed_work work; unsigned long next_query; unsigned long sampling_interval; /* jiffies */ + u32 *bulk_query_out; + struct mlx5_fc_pool fc_pool; }; struct mlx5_events; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b3d5752657d9..30d15e80bcc7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1040,6 +1040,21 @@ enum { MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1, }; +#define MLX5_FC_BULK_SIZE_FACTOR 128 + +enum mlx5_fc_bulk_alloc_bitmask { + MLX5_FC_BULK_128 = (1 << 0), + MLX5_FC_BULK_256 = (1 << 1), + MLX5_FC_BULK_512 = (1 << 2), + MLX5_FC_BULK_1024 = (1 << 3), + MLX5_FC_BULK_2048 = (1 << 4), + MLX5_FC_BULK_4096 = (1 << 5), + MLX5_FC_BULK_8192 = (1 << 6), + MLX5_FC_BULK_16384 = (1 << 7), +}; + +#define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum)) + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x30]; u8 vhca_id[0x10]; @@ -1244,7 +1259,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_2e0[0x7]; u8 max_qp_mcg[0x19]; - u8 reserved_at_300[0x18]; + u8 reserved_at_300[0x10]; + u8 flow_counter_bulk_alloc[0x8]; u8 log_max_mcg[0x8]; u8 reserved_at_320[0x3]; @@ -2766,7 +2782,7 @@ struct mlx5_ifc_traffic_counter_bits { struct mlx5_ifc_tisc_bits { u8 strict_lag_tx_port_affinity[0x1]; u8 tls_en[0x1]; - u8 reserved_at_1[0x2]; + u8 reserved_at_2[0x2]; u8 lag_tx_port_affinity[0x04]; u8 reserved_at_8[0x4]; @@ -2941,6 +2957,13 @@ enum { SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3, }; +enum { + ELEMENT_TYPE_CAP_MASK_TASR = 1 << 0, + ELEMENT_TYPE_CAP_MASK_VPORT = 1 << 1, + ELEMENT_TYPE_CAP_MASK_VPORT_TC = 1 << 2, + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC = 1 << 3, +}; + struct mlx5_ifc_scheduling_context_bits { u8 element_type[0x8]; u8 reserved_at_8[0x18]; @@ -7815,7 +7838,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x40]; + u8 reserved_at_40[0x38]; + u8 flow_counter_bulk[0x8]; }; struct mlx5_ifc_add_vxlan_udp_dport_out_bits { diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 00b9aab5fdc1..d3b12bc8a114 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -117,6 +117,8 @@ enum flow_action_id { FLOW_ACTION_GOTO, FLOW_ACTION_REDIRECT, FLOW_ACTION_MIRRED, + FLOW_ACTION_REDIRECT_INGRESS, + FLOW_ACTION_MIRRED_INGRESS, FLOW_ACTION_VLAN_PUSH, FLOW_ACTION_VLAN_POP, FLOW_ACTION_VLAN_MANGLE, @@ -126,6 +128,7 @@ enum flow_action_id { FLOW_ACTION_ADD, FLOW_ACTION_CSUM, FLOW_ACTION_MARK, + FLOW_ACTION_PTYPE, FLOW_ACTION_WAKE, FLOW_ACTION_QUEUE, FLOW_ACTION_SAMPLE, @@ -168,6 +171,7 @@ struct flow_action_entry { const struct ip_tunnel_info *tunnel; /* FLOW_ACTION_TUNNEL_ENCAP */ u32 csum_flags; /* FLOW_ACTION_CSUM */ u32 mark; /* FLOW_ACTION_MARK */ + u16 ptype; /* FLOW_ACTION_PTYPE */ struct { /* FLOW_ACTION_QUEUE */ u32 ctx; u32 index; diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index c757585a05b0..1cace4c69e44 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -32,6 +32,24 @@ static inline bool is_tcf_mirred_egress_mirror(const struct tc_action *a) return false; } +static inline bool is_tcf_mirred_ingress_redirect(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->id == TCA_ID_MIRRED) + return to_mirred(a)->tcfm_eaction == TCA_INGRESS_REDIR; +#endif + return false; +} + +static inline bool is_tcf_mirred_ingress_mirror(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->id == TCA_ID_MIRRED) + return to_mirred(a)->tcfm_eaction == TCA_INGRESS_MIRROR; +#endif + return false; +} + static inline struct net_device *tcf_mirred_dev(const struct tc_action *a) { return rtnl_dereference(to_mirred(a)->tcfm_dev); diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 4c04e2985508..b22a1f641f02 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -54,4 +54,31 @@ static inline u32 tcf_skbedit_mark(const struct tc_action *a) return mark; } +/* Return true iff action is ptype */ +static inline bool is_tcf_skbedit_ptype(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + u32 flags; + + if (a->ops && a->ops->id == TCA_ID_SKBEDIT) { + rcu_read_lock(); + flags = rcu_dereference(to_skbedit(a)->params)->flags; + rcu_read_unlock(); + return flags == SKBEDIT_F_PTYPE; + } +#endif + return false; +} + +static inline u32 tcf_skbedit_ptype(const struct tc_action *a) +{ + u16 ptype; + + rcu_read_lock(); + ptype = rcu_dereference(to_skbedit(a)->params)->ptype; + rcu_read_unlock(); + + return ptype; +} + #endif /* __NET_TC_SKBEDIT_H */ diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 4ea4347f5062..4deb86f990f1 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -43,10 +43,16 @@ * netlink alerts */ static int trace_state = TRACE_OFF; -static DEFINE_MUTEX(trace_state_mutex); + +/* net_dm_mutex + * + * An overall lock guarding every operation coming from userspace. + * It also guards the global 'hw_stats_list' list. + */ +static DEFINE_MUTEX(net_dm_mutex); struct per_cpu_dm_data { - spinlock_t lock; + spinlock_t lock; /* Protects 'skb' and 'send_timer' */ struct sk_buff *skb; struct work_struct dm_alert_work; struct timer_list send_timer; @@ -235,22 +241,21 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi, rcu_read_unlock(); } -static int set_all_monitor_traces(int state) +static int set_all_monitor_traces(int state, struct netlink_ext_ack *extack) { int rc = 0; struct dm_hw_stat_delta *new_stat = NULL; struct dm_hw_stat_delta *temp; - mutex_lock(&trace_state_mutex); - if (state == trace_state) { - rc = -EAGAIN; - goto out_unlock; + NL_SET_ERR_MSG_MOD(extack, "Trace state already set to requested state"); + return -EAGAIN; } switch (state) { case TRACE_ON: if (!try_module_get(THIS_MODULE)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); rc = -ENODEV; break; } @@ -288,17 +293,15 @@ static int set_all_monitor_traces(int state) else rc = -EINPROGRESS; -out_unlock: - mutex_unlock(&trace_state_mutex); - return rc; } - static int net_dm_cmd_config(struct sk_buff *skb, struct genl_info *info) { - return -ENOTSUPP; + NL_SET_ERR_MSG_MOD(info->extack, "Command not supported"); + + return -EOPNOTSUPP; } static int net_dm_cmd_trace(struct sk_buff *skb, @@ -306,12 +309,12 @@ static int net_dm_cmd_trace(struct sk_buff *skb, { switch (info->genlhdr->cmd) { case NET_DM_CMD_START: - return set_all_monitor_traces(TRACE_ON); + return set_all_monitor_traces(TRACE_ON, info->extack); case NET_DM_CMD_STOP: - return set_all_monitor_traces(TRACE_OFF); + return set_all_monitor_traces(TRACE_OFF, info->extack); } - return -ENOTSUPP; + return -EOPNOTSUPP; } static int dropmon_net_event(struct notifier_block *ev_block, @@ -330,12 +333,12 @@ static int dropmon_net_event(struct notifier_block *ev_block, new_stat->dev = dev; new_stat->last_rx = jiffies; - mutex_lock(&trace_state_mutex); + mutex_lock(&net_dm_mutex); list_add_rcu(&new_stat->list, &hw_stats_list); - mutex_unlock(&trace_state_mutex); + mutex_unlock(&net_dm_mutex); break; case NETDEV_UNREGISTER: - mutex_lock(&trace_state_mutex); + mutex_lock(&net_dm_mutex); list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { if (new_stat->dev == dev) { new_stat->dev = NULL; @@ -346,7 +349,7 @@ static int dropmon_net_event(struct notifier_block *ev_block, } } } - mutex_unlock(&trace_state_mutex); + mutex_unlock(&net_dm_mutex); break; } out: @@ -371,10 +374,26 @@ static const struct genl_ops dropmon_ops[] = { }, }; +static int net_dm_nl_pre_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + mutex_lock(&net_dm_mutex); + + return 0; +} + +static void net_dm_nl_post_doit(const struct genl_ops *ops, + struct sk_buff *skb, struct genl_info *info) +{ + mutex_unlock(&net_dm_mutex); +} + static struct genl_family net_drop_monitor_family __ro_after_init = { .hdrsize = 0, .name = "NET_DM", .version = 2, + .pre_doit = net_dm_nl_pre_doit, + .post_doit = net_dm_nl_post_doit, .module = THIS_MODULE, .ops = dropmon_ops, .n_ops = ARRAY_SIZE(dropmon_ops), @@ -421,7 +440,6 @@ static int __init init_net_drop_monitor(void) reset_per_cpu_data(data); } - goto out; out_unreg: diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 6e942dda1bcd..2f69d4b53d46 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -84,13 +84,6 @@ config NET_DSA_TAG_KSZ Say Y if you want to enable support for tagging frames for the Microchip 9893 family of switches. -config NET_DSA_TAG_KSZ9477 - tristate "Tag driver for Microchip 9477 family of switches" - select NET_DSA_TAG_KSZ_COMMON - help - Say Y if you want to enable support for tagging frames for the - Microchip 9477 family of switches. - config NET_DSA_TAG_QCA tristate "Tag driver for Qualcomm Atheros QCA8K switches" help diff --git a/net/dsa/master.c b/net/dsa/master.c index 4b52f8bac5e1..a8e52c9967f4 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -8,6 +8,70 @@ #include "dsa_priv.h" +static int dsa_master_get_regs_len(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; + int ret = 0; + int len; + + if (ops->get_regs_len) { + len = ops->get_regs_len(dev); + if (len < 0) + return len; + ret += len; + } + + ret += sizeof(struct ethtool_drvinfo); + ret += sizeof(struct ethtool_regs); + + if (ds->ops->get_regs_len) { + len = ds->ops->get_regs_len(ds, port); + if (len < 0) + return len; + ret += len; + } + + return ret; +} + +static void dsa_master_get_regs(struct net_device *dev, + struct ethtool_regs *regs, void *data) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + struct ethtool_drvinfo *cpu_info; + struct ethtool_regs *cpu_regs; + int port = cpu_dp->index; + int len; + + if (ops->get_regs_len && ops->get_regs) { + len = ops->get_regs_len(dev); + if (len < 0) + return; + regs->len = len; + ops->get_regs(dev, regs, data); + data += regs->len; + } + + cpu_info = (struct ethtool_drvinfo *)data; + strlcpy(cpu_info->driver, "dsa", sizeof(cpu_info->driver)); + data += sizeof(*cpu_info); + cpu_regs = (struct ethtool_regs *)data; + data += sizeof(*cpu_regs); + + if (ds->ops->get_regs_len && ds->ops->get_regs) { + len = ds->ops->get_regs_len(ds, port); + if (len < 0) + return; + cpu_regs->len = len; + ds->ops->get_regs(ds, port, cpu_regs, data); + } +} + static void dsa_master_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) @@ -147,6 +211,8 @@ static int dsa_master_ethtool_setup(struct net_device *dev) if (cpu_dp->orig_ethtool_ops) memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops)); + ops->get_regs_len = dsa_master_get_regs_len; + ops->get_regs = dsa_master_get_regs; ops->get_sset_count = dsa_master_get_sset_count; ops->get_ethtool_stats = dsa_master_get_ethtool_stats; ops->get_strings = dsa_master_get_strings; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e49fec767a10..3c5c331b50f1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2725,10 +2725,9 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, rcu_read_lock(); res.f6i = rcu_dereference(rt6->from); - if (!res.f6i) { - rcu_read_unlock(); - return; - } + if (!res.f6i) + goto out_unlock; + res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; @@ -2744,10 +2743,8 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev + gw. Should be impossible. */ - if (!arg.match) { - rcu_read_unlock(); - return; - } + if (!arg.match) + goto out_unlock; res.nh = arg.match; } else { @@ -2760,6 +2757,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (rt6_insert_exception(nrt6, &res)) dst_release_immediate(&nrt6->dst); } +out_unlock: rcu_read_unlock(); } } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 892287d06c17..12d985029eb1 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -222,6 +222,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) struct dp_stats_percpu *stats; u64 *stats_counter; u32 n_mask_hit; + int error; stats = this_cpu_ptr(dp->stats_percpu); @@ -229,7 +230,6 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) flow = ovs_flow_tbl_lookup_stats(&dp->table, key, &n_mask_hit); if (unlikely(!flow)) { struct dp_upcall_info upcall; - int error; memset(&upcall, 0, sizeof(upcall)); upcall.cmd = OVS_PACKET_CMD_MISS; @@ -246,7 +246,10 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) ovs_flow_stats_update(flow, key->tp.flags, skb); sf_acts = rcu_dereference(flow->sf_acts); - ovs_execute_actions(dp, skb, sf_acts, key); + error = ovs_execute_actions(dp, skb, sf_acts, key); + if (unlikely(error)) + net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n", + ovs_dp_name(dp), error); stats_counter = &stats->n_hit; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 3565d9aa09aa..9d85d3295c7c 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3205,6 +3205,12 @@ int tc_setup_flow_action(struct flow_action *flow_action, } else if (is_tcf_mirred_egress_mirror(act)) { entry->id = FLOW_ACTION_MIRRED; entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_ingress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT_INGRESS; + entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_ingress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED_INGRESS; + entry->dev = tcf_mirred_dev(act); } else if (is_tcf_vlan(act)) { switch (tcf_vlan_action(act)) { case TCA_VLAN_ACT_PUSH: @@ -3294,6 +3300,9 @@ int tc_setup_flow_action(struct flow_action *flow_action, default: goto err_out; } + } else if (is_tcf_skbedit_ptype(act)) { + entry->id = FLOW_ACTION_PTYPE; + entry->ptype = tcf_skbedit_ptype(act); } else { goto err_out; } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index d59fbcc745d1..9edd0f495001 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -45,7 +45,6 @@ struct fq_codel_flow { struct sk_buff *tail; struct list_head flowchain; int deficit; - u32 dropped; /* number of drops (or ECN marks) on this flow */ struct codel_vars cvars; }; /* please try to keep this structure <= 64 bytes */ @@ -173,7 +172,8 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets, __qdisc_drop(skb, to_free); } while (++i < max_packets && len < threshold); - flow->dropped += i; + /* Tell codel to increase its signal strength also */ + flow->cvars.count += i; q->backlogs[idx] -= len; q->memory_usage -= mem; sch->qstats.drops += i; @@ -211,7 +211,6 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, list_add_tail(&flow->flowchain, &q->new_flows); q->new_flow_count++; flow->deficit = q->quantum; - flow->dropped = 0; } get_codel_cb(skb)->mem_usage = skb->truesize; q->memory_usage += get_codel_cb(skb)->mem_usage; @@ -310,9 +309,6 @@ begin: &flow->cvars, &q->cstats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); - flow->dropped += q->cstats.drop_count - prev_drop_count; - flow->dropped += q->cstats.ecn_mark - prev_ecn_mark; - if (!skb) { /* force a pass through old_flows to prevent starvation */ if ((head == &q->new_flows) && !list_empty(&q->old_flows)) @@ -658,7 +654,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, sch_tree_unlock(sch); } qs.backlog = q->backlogs[idx]; - qs.drops = flow->dropped; + qs.drops = 0; } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; |