From 0207dd1173fe31c153ffd439c4bb33d1341829b1 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 19 Apr 2018 01:02:59 +0200 Subject: net: phy: mdio-gpio: Remove redundant platform data header The platform data header file is now unused. Remove it, but add an extra include which it brought in. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index b60179d948bb..a7321687cae9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5321,7 +5321,6 @@ F: include/linux/*mdio*.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h -F: include/linux/platform_data/mdio-gpio.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/trace/events/mdio.h F: include/uapi/linux/mdio.h -- cgit v1.2.3-58-ga151 From 1827b0678863bc97a1653fdf5308762b2aefcd56 Mon Sep 17 00:00:00 2001 From: Phil Elwell Date: Thu, 19 Apr 2018 17:59:39 +0100 Subject: lan78xx: Read LED states from Device Tree Add support for DT property "microchip,led-modes", a vector of zero to four cells (u32s) in the range 0-15, each of which sets the mode for one of the LEDs. Some possible values are: 0=link/activity 1=link1000/activity 2=link100/activity 3=link10/activity 4=link100/1000/activity 5=link10/1000/activity 6=link10/100/activity 14=off 15=on These values are given symbolic constants in a dt-bindings header. Also use the presence of the DT property to indicate that the LEDs should be enabled - necessary in the event that no valid OTP or EEPROM is available. Signed-off-by: Phil Elwell Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- MAINTAINERS | 1 + drivers/net/phy/microchip.c | 25 ++++++++++++++++++++++ drivers/net/usb/lan78xx.c | 32 ++++++++++++++++++++++++++++- include/dt-bindings/net/microchip-lan78xx.h | 21 +++++++++++++++++++ include/linux/microchipphy.h | 3 +++ 5 files changed, 81 insertions(+), 1 deletion(-) create mode 100644 include/dt-bindings/net/microchip-lan78xx.h (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index a7321687cae9..c952d3076a65 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14572,6 +14572,7 @@ M: Microchip Linux Driver Support L: netdev@vger.kernel.org S: Maintained F: drivers/net/usb/lan78xx.* +F: include/dt-bindings/net/microchip-lan78xx.h USB MASS STORAGE DRIVER M: Alan Stern diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c index 0f293ef28935..ef5e160fe9dc 100644 --- a/drivers/net/phy/microchip.c +++ b/drivers/net/phy/microchip.c @@ -20,6 +20,8 @@ #include #include #include +#include +#include #define DRIVER_AUTHOR "WOOJUNG HUH " #define DRIVER_DESC "Microchip LAN88XX PHY driver" @@ -70,6 +72,8 @@ static int lan88xx_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; struct lan88xx_priv *priv; + u32 led_modes[4]; + int len; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -77,6 +81,27 @@ static int lan88xx_probe(struct phy_device *phydev) priv->wolopts = 0; + len = of_property_read_variable_u32_array(dev->of_node, + "microchip,led-modes", + led_modes, + 0, + ARRAY_SIZE(led_modes)); + if (len >= 0) { + u32 reg = 0; + int i; + + for (i = 0; i < len; i++) { + if (led_modes[i] > 15) + return -EINVAL; + reg |= led_modes[i] << (i * 4); + } + for (; i < ARRAY_SIZE(led_modes); i++) + reg |= LAN78XX_FORCE_LED_OFF << (i * 4); + (void)phy_write(phydev, LAN78XX_PHY_LED_MODE_SELECT, reg); + } else if (len == -EOVERFLOW) { + return -EINVAL; + } + /* these values can be used to identify internal PHY */ priv->chip_id = phy_read_mmd(phydev, 3, LAN88XX_MMD3_CHIP_ID); priv->chip_rev = phy_read_mmd(phydev, 3, LAN88XX_MMD3_CHIP_REV); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index a823f010de30..6b03b973083e 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include "lan78xx.h" @@ -1760,6 +1761,7 @@ done: static int lan78xx_mdio_init(struct lan78xx_net *dev) { + struct device_node *node; int ret; dev->mdiobus = mdiobus_alloc(); @@ -1788,7 +1790,13 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev) break; } - ret = mdiobus_register(dev->mdiobus); + node = of_get_child_by_name(dev->udev->dev.of_node, "mdio"); + if (node) { + ret = of_mdiobus_register(dev->mdiobus, node); + of_node_put(node); + } else { + ret = mdiobus_register(dev->mdiobus); + } if (ret) { netdev_err(dev->net, "can't register MDIO bus\n"); goto exit1; @@ -2077,6 +2085,28 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) mii_adv = (u32)mii_advertise_flowctrl(dev->fc_request_control); phydev->advertising |= mii_adv_to_ethtool_adv_t(mii_adv); + if (phydev->mdio.dev.of_node) { + u32 reg; + int len; + + len = of_property_count_elems_of_size(phydev->mdio.dev.of_node, + "microchip,led-modes", + sizeof(u32)); + if (len >= 0) { + /* Ensure the appropriate LEDs are enabled */ + lan78xx_read_reg(dev, HW_CFG, ®); + reg &= ~(HW_CFG_LED0_EN_ | + HW_CFG_LED1_EN_ | + HW_CFG_LED2_EN_ | + HW_CFG_LED3_EN_); + reg |= (len > 0) * HW_CFG_LED0_EN_ | + (len > 1) * HW_CFG_LED1_EN_ | + (len > 2) * HW_CFG_LED2_EN_ | + (len > 3) * HW_CFG_LED3_EN_; + lan78xx_write_reg(dev, HW_CFG, reg); + } + } + genphy_config_aneg(phydev); dev->fc_autoneg = phydev->autoneg; diff --git a/include/dt-bindings/net/microchip-lan78xx.h b/include/dt-bindings/net/microchip-lan78xx.h new file mode 100644 index 000000000000..0742ff075307 --- /dev/null +++ b/include/dt-bindings/net/microchip-lan78xx.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _DT_BINDINGS_MICROCHIP_LAN78XX_H +#define _DT_BINDINGS_MICROCHIP_LAN78XX_H + +/* LED modes for LAN7800/LAN7850 embedded PHY */ + +#define LAN78XX_LINK_ACTIVITY 0 +#define LAN78XX_LINK_1000_ACTIVITY 1 +#define LAN78XX_LINK_100_ACTIVITY 2 +#define LAN78XX_LINK_10_ACTIVITY 3 +#define LAN78XX_LINK_100_1000_ACTIVITY 4 +#define LAN78XX_LINK_10_1000_ACTIVITY 5 +#define LAN78XX_LINK_10_100_ACTIVITY 6 +#define LAN78XX_DUPLEX_COLLISION 8 +#define LAN78XX_COLLISION 9 +#define LAN78XX_ACTIVITY 10 +#define LAN78XX_AUTONEG_FAULT 12 +#define LAN78XX_FORCE_LED_OFF 14 +#define LAN78XX_FORCE_LED_ON 15 + +#endif diff --git a/include/linux/microchipphy.h b/include/linux/microchipphy.h index eb492d47f717..8e4015e7f8d3 100644 --- a/include/linux/microchipphy.h +++ b/include/linux/microchipphy.h @@ -70,4 +70,7 @@ #define LAN88XX_MMD3_CHIP_ID (32877) #define LAN88XX_MMD3_CHIP_REV (32878) +/* Registers specific to the LAN7800/LAN7850 embedded phy */ +#define LAN78XX_PHY_LED_MODE_SELECT (0x1D) + #endif /* _MICROCHIPPHY_H */ -- cgit v1.2.3-58-ga151 From 01d26589dee4b23376642fba333539605c52d324 Mon Sep 17 00:00:00 2001 From: Phil Elwell Date: Thu, 19 Apr 2018 17:59:40 +0100 Subject: dt-bindings: Document the DT bindings for lan78xx The Microchip LAN78XX family of devices are Ethernet controllers with a USB interface. Despite being discoverable devices it can be useful to be able to configure them from Device Tree, particularly in low-cost applications without an EEPROM or programmed OTP. Document the supported properties in a bindings file. Signed-off-by: Phil Elwell Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- .../devicetree/bindings/net/microchip,lan78xx.txt | 54 ++++++++++++++++++++++ MAINTAINERS | 1 + 2 files changed, 55 insertions(+) create mode 100644 Documentation/devicetree/bindings/net/microchip,lan78xx.txt (limited to 'MAINTAINERS') diff --git a/Documentation/devicetree/bindings/net/microchip,lan78xx.txt b/Documentation/devicetree/bindings/net/microchip,lan78xx.txt new file mode 100644 index 000000000000..76786a0f6d3d --- /dev/null +++ b/Documentation/devicetree/bindings/net/microchip,lan78xx.txt @@ -0,0 +1,54 @@ +Microchip LAN78xx Gigabit Ethernet controller + +The LAN78XX devices are usually configured by programming their OTP or with +an external EEPROM, but some platforms (e.g. Raspberry Pi 3 B+) have neither. +The Device Tree properties, if present, override the OTP and EEPROM. + +Required properties: +- compatible: Should be one of "usb424,7800", "usb424,7801" or "usb424,7850". + +Optional properties: +- local-mac-address: see ethernet.txt +- mac-address: see ethernet.txt + +Optional properties of the embedded PHY: +- microchip,led-modes: a 0..4 element vector, with each element configuring + the operating mode of an LED. Omitted LEDs are turned off. Allowed values + are defined in "include/dt-bindings/net/microchip-lan78xx.h". + +Example: + +/* Based on the configuration for a Raspberry Pi 3 B+ */ +&usb { + usb-port@1 { + compatible = "usb424,2514"; + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + usb-port@1 { + compatible = "usb424,2514"; + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + ethernet: ethernet@1 { + compatible = "usb424,7800"; + reg = <1>; + local-mac-address = [ 00 11 22 33 44 55 ]; + + mdio { + #address-cells = <0x1>; + #size-cells = <0x0>; + eth_phy: ethernet-phy@1 { + reg = <1>; + microchip,led-modes = < + LAN78XX_LINK_1000_ACTIVITY + LAN78XX_LINK_10_100_ACTIVITY + >; + }; + }; + }; + }; + }; +}; diff --git a/MAINTAINERS b/MAINTAINERS index c952d3076a65..81465707d8a8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14571,6 +14571,7 @@ M: Woojung Huh M: Microchip Linux Driver Support L: netdev@vger.kernel.org S: Maintained +F: Documentation/devicetree/bindings/net/microchip,lan78xx.txt F: drivers/net/usb/lan78xx.* F: include/dt-bindings/net/microchip-lan78xx.h -- cgit v1.2.3-58-ga151 From 4d220ed0f8140c478ab7b0a14d96821da639b646 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sat, 28 Apr 2018 19:56:37 -0700 Subject: bpf: remove tracepoints from bpf core tracepoints to bpf core were added as a way to provide introspection to bpf programs and maps, but after some time it became clear that this approach is inadequate, so prog_id, map_id and corresponding get_next_id, get_fd_by_id, get_info_by_fd, prog_query APIs were introduced and fully adopted by bpftool and other applications. The tracepoints in bpf core started to rot and causing syzbot warnings: WARNING: CPU: 0 PID: 3008 at kernel/trace/trace_event_perf.c:274 Kernel panic - not syncing: panic_on_warn set ... perf_trace_bpf_map_keyval+0x260/0xbd0 include/trace/events/bpf.h:228 trace_bpf_map_update_elem include/trace/events/bpf.h:274 [inline] map_update_elem kernel/bpf/syscall.c:597 [inline] SYSC_bpf kernel/bpf/syscall.c:1478 [inline] Hence this patch deletes tracepoints in bpf core. Reported-by: Eric Biggers Reported-by: syzbot Signed-off-by: Alexei Starovoitov Acked-by: David S. Miller Signed-off-by: Daniel Borkmann --- MAINTAINERS | 1 - include/linux/bpf_trace.h | 1 - include/trace/events/bpf.h | 355 --------------------------------------------- kernel/bpf/core.c | 6 - kernel/bpf/inode.c | 16 +- kernel/bpf/syscall.c | 15 +- 6 files changed, 2 insertions(+), 392 deletions(-) delete mode 100644 include/trace/events/bpf.h (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index a52800867850..537fd17a211b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2727,7 +2727,6 @@ F: Documentation/networking/filter.txt F: Documentation/bpf/ F: include/linux/bpf* F: include/linux/filter.h -F: include/trace/events/bpf.h F: include/trace/events/xdp.h F: include/uapi/linux/bpf* F: include/uapi/linux/filter.h diff --git a/include/linux/bpf_trace.h b/include/linux/bpf_trace.h index e6fe98ae3794..ddf896abcfb6 100644 --- a/include/linux/bpf_trace.h +++ b/include/linux/bpf_trace.h @@ -2,7 +2,6 @@ #ifndef __LINUX_BPF_TRACE_H__ #define __LINUX_BPF_TRACE_H__ -#include #include #endif /* __LINUX_BPF_TRACE_H__ */ diff --git a/include/trace/events/bpf.h b/include/trace/events/bpf.h deleted file mode 100644 index 150185647e6b..000000000000 --- a/include/trace/events/bpf.h +++ /dev/null @@ -1,355 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM bpf - -#if !defined(_TRACE_BPF_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_BPF_H - -/* These are only used within the BPF_SYSCALL code */ -#ifdef CONFIG_BPF_SYSCALL - -#include -#include -#include -#include - -#define __PROG_TYPE_MAP(FN) \ - FN(SOCKET_FILTER) \ - FN(KPROBE) \ - FN(SCHED_CLS) \ - FN(SCHED_ACT) \ - FN(TRACEPOINT) \ - FN(XDP) \ - FN(PERF_EVENT) \ - FN(CGROUP_SKB) \ - FN(CGROUP_SOCK) \ - FN(LWT_IN) \ - FN(LWT_OUT) \ - FN(LWT_XMIT) - -#define __MAP_TYPE_MAP(FN) \ - FN(HASH) \ - FN(ARRAY) \ - FN(PROG_ARRAY) \ - FN(PERF_EVENT_ARRAY) \ - FN(PERCPU_HASH) \ - FN(PERCPU_ARRAY) \ - FN(STACK_TRACE) \ - FN(CGROUP_ARRAY) \ - FN(LRU_HASH) \ - FN(LRU_PERCPU_HASH) \ - FN(LPM_TRIE) - -#define __PROG_TYPE_TP_FN(x) \ - TRACE_DEFINE_ENUM(BPF_PROG_TYPE_##x); -#define __PROG_TYPE_SYM_FN(x) \ - { BPF_PROG_TYPE_##x, #x }, -#define __PROG_TYPE_SYM_TAB \ - __PROG_TYPE_MAP(__PROG_TYPE_SYM_FN) { -1, 0 } -__PROG_TYPE_MAP(__PROG_TYPE_TP_FN) - -#define __MAP_TYPE_TP_FN(x) \ - TRACE_DEFINE_ENUM(BPF_MAP_TYPE_##x); -#define __MAP_TYPE_SYM_FN(x) \ - { BPF_MAP_TYPE_##x, #x }, -#define __MAP_TYPE_SYM_TAB \ - __MAP_TYPE_MAP(__MAP_TYPE_SYM_FN) { -1, 0 } -__MAP_TYPE_MAP(__MAP_TYPE_TP_FN) - -DECLARE_EVENT_CLASS(bpf_prog_event, - - TP_PROTO(const struct bpf_prog *prg), - - TP_ARGS(prg), - - TP_STRUCT__entry( - __array(u8, prog_tag, 8) - __field(u32, type) - ), - - TP_fast_assign( - BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag)); - memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag)); - __entry->type = prg->type; - ), - - TP_printk("prog=%s type=%s", - __print_hex_str(__entry->prog_tag, 8), - __print_symbolic(__entry->type, __PROG_TYPE_SYM_TAB)) -); - -DEFINE_EVENT(bpf_prog_event, bpf_prog_get_type, - - TP_PROTO(const struct bpf_prog *prg), - - TP_ARGS(prg) -); - -DEFINE_EVENT(bpf_prog_event, bpf_prog_put_rcu, - - TP_PROTO(const struct bpf_prog *prg), - - TP_ARGS(prg) -); - -TRACE_EVENT(bpf_prog_load, - - TP_PROTO(const struct bpf_prog *prg, int ufd), - - TP_ARGS(prg, ufd), - - TP_STRUCT__entry( - __array(u8, prog_tag, 8) - __field(u32, type) - __field(int, ufd) - ), - - TP_fast_assign( - BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag)); - memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag)); - __entry->type = prg->type; - __entry->ufd = ufd; - ), - - TP_printk("prog=%s type=%s ufd=%d", - __print_hex_str(__entry->prog_tag, 8), - __print_symbolic(__entry->type, __PROG_TYPE_SYM_TAB), - __entry->ufd) -); - -TRACE_EVENT(bpf_map_create, - - TP_PROTO(const struct bpf_map *map, int ufd), - - TP_ARGS(map, ufd), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, size_key) - __field(u32, size_value) - __field(u32, max_entries) - __field(u32, flags) - __field(int, ufd) - ), - - TP_fast_assign( - __entry->type = map->map_type; - __entry->size_key = map->key_size; - __entry->size_value = map->value_size; - __entry->max_entries = map->max_entries; - __entry->flags = map->map_flags; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=%u val=%u max=%u flags=%x", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, __entry->size_key, __entry->size_value, - __entry->max_entries, __entry->flags) -); - -DECLARE_EVENT_CLASS(bpf_obj_prog, - - TP_PROTO(const struct bpf_prog *prg, int ufd, - const struct filename *pname), - - TP_ARGS(prg, ufd, pname), - - TP_STRUCT__entry( - __array(u8, prog_tag, 8) - __field(int, ufd) - __string(path, pname->name) - ), - - TP_fast_assign( - BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag)); - memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag)); - __assign_str(path, pname->name); - __entry->ufd = ufd; - ), - - TP_printk("prog=%s path=%s ufd=%d", - __print_hex_str(__entry->prog_tag, 8), - __get_str(path), __entry->ufd) -); - -DEFINE_EVENT(bpf_obj_prog, bpf_obj_pin_prog, - - TP_PROTO(const struct bpf_prog *prg, int ufd, - const struct filename *pname), - - TP_ARGS(prg, ufd, pname) -); - -DEFINE_EVENT(bpf_obj_prog, bpf_obj_get_prog, - - TP_PROTO(const struct bpf_prog *prg, int ufd, - const struct filename *pname), - - TP_ARGS(prg, ufd, pname) -); - -DECLARE_EVENT_CLASS(bpf_obj_map, - - TP_PROTO(const struct bpf_map *map, int ufd, - const struct filename *pname), - - TP_ARGS(map, ufd, pname), - - TP_STRUCT__entry( - __field(u32, type) - __field(int, ufd) - __string(path, pname->name) - ), - - TP_fast_assign( - __assign_str(path, pname->name); - __entry->type = map->map_type; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d path=%s", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, __get_str(path)) -); - -DEFINE_EVENT(bpf_obj_map, bpf_obj_pin_map, - - TP_PROTO(const struct bpf_map *map, int ufd, - const struct filename *pname), - - TP_ARGS(map, ufd, pname) -); - -DEFINE_EVENT(bpf_obj_map, bpf_obj_get_map, - - TP_PROTO(const struct bpf_map *map, int ufd, - const struct filename *pname), - - TP_ARGS(map, ufd, pname) -); - -DECLARE_EVENT_CLASS(bpf_map_keyval, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *val), - - TP_ARGS(map, ufd, key, val), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, key_len) - __dynamic_array(u8, key, map->key_size) - __field(bool, key_trunc) - __field(u32, val_len) - __dynamic_array(u8, val, map->value_size) - __field(bool, val_trunc) - __field(int, ufd) - ), - - TP_fast_assign( - memcpy(__get_dynamic_array(key), key, map->key_size); - memcpy(__get_dynamic_array(val), val, map->value_size); - __entry->type = map->map_type; - __entry->key_len = min(map->key_size, 16U); - __entry->key_trunc = map->key_size != __entry->key_len; - __entry->val_len = min(map->value_size, 16U); - __entry->val_trunc = map->value_size != __entry->val_len; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=[%s%s] val=[%s%s]", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, - __print_hex(__get_dynamic_array(key), __entry->key_len), - __entry->key_trunc ? " ..." : "", - __print_hex(__get_dynamic_array(val), __entry->val_len), - __entry->val_trunc ? " ..." : "") -); - -DEFINE_EVENT(bpf_map_keyval, bpf_map_lookup_elem, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *val), - - TP_ARGS(map, ufd, key, val) -); - -DEFINE_EVENT(bpf_map_keyval, bpf_map_update_elem, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *val), - - TP_ARGS(map, ufd, key, val) -); - -TRACE_EVENT(bpf_map_delete_elem, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key), - - TP_ARGS(map, ufd, key), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, key_len) - __dynamic_array(u8, key, map->key_size) - __field(bool, key_trunc) - __field(int, ufd) - ), - - TP_fast_assign( - memcpy(__get_dynamic_array(key), key, map->key_size); - __entry->type = map->map_type; - __entry->key_len = min(map->key_size, 16U); - __entry->key_trunc = map->key_size != __entry->key_len; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=[%s%s]", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, - __print_hex(__get_dynamic_array(key), __entry->key_len), - __entry->key_trunc ? " ..." : "") -); - -TRACE_EVENT(bpf_map_next_key, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *key_next), - - TP_ARGS(map, ufd, key, key_next), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, key_len) - __dynamic_array(u8, key, map->key_size) - __dynamic_array(u8, nxt, map->key_size) - __field(bool, key_trunc) - __field(bool, key_null) - __field(int, ufd) - ), - - TP_fast_assign( - if (key) - memcpy(__get_dynamic_array(key), key, map->key_size); - __entry->key_null = !key; - memcpy(__get_dynamic_array(nxt), key_next, map->key_size); - __entry->type = map->map_type; - __entry->key_len = min(map->key_size, 16U); - __entry->key_trunc = map->key_size != __entry->key_len; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=[%s%s] next=[%s%s]", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, - __entry->key_null ? "NULL" : __print_hex(__get_dynamic_array(key), - __entry->key_len), - __entry->key_trunc && !__entry->key_null ? " ..." : "", - __print_hex(__get_dynamic_array(nxt), __entry->key_len), - __entry->key_trunc ? " ..." : "") -); -#endif /* CONFIG_BPF_SYSCALL */ -#endif /* _TRACE_BPF_H */ - -#include diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9349a5db3cf2..90feeba3a1a1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1845,9 +1845,3 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, #include EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); - -/* These are only used within the BPF_SYSCALL code */ -#ifdef CONFIG_BPF_SYSCALL -EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type); -EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu); -#endif diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index a41343009ccc..ed13645bd80c 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -429,13 +429,6 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname) ret = bpf_obj_do_pin(pname, raw, type); if (ret != 0) bpf_any_put(raw, type); - if ((trace_bpf_obj_pin_prog_enabled() || - trace_bpf_obj_pin_map_enabled()) && !ret) { - if (type == BPF_TYPE_PROG) - trace_bpf_obj_pin_prog(raw, ufd, pname); - if (type == BPF_TYPE_MAP) - trace_bpf_obj_pin_map(raw, ufd, pname); - } out: putname(pname); return ret; @@ -502,15 +495,8 @@ int bpf_obj_get_user(const char __user *pathname, int flags) else goto out; - if (ret < 0) { + if (ret < 0) bpf_any_put(raw, type); - } else if (trace_bpf_obj_get_prog_enabled() || - trace_bpf_obj_get_map_enabled()) { - if (type == BPF_TYPE_PROG) - trace_bpf_obj_get_prog(raw, ret, pname); - if (type == BPF_TYPE_MAP) - trace_bpf_obj_get_map(raw, ret, pname); - } out: putname(pname); return ret; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0bd2944eafb9..263e13ede029 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -503,7 +503,6 @@ static int map_create(union bpf_attr *attr) return err; } - trace_bpf_map_create(map, err); return err; free_map: @@ -663,7 +662,6 @@ static int map_lookup_elem(union bpf_attr *attr) if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; - trace_bpf_map_lookup_elem(map, ufd, key, value); err = 0; free_value: @@ -760,8 +758,6 @@ static int map_update_elem(union bpf_attr *attr) __this_cpu_dec(bpf_prog_active); preempt_enable(); out: - if (!err) - trace_bpf_map_update_elem(map, ufd, key, value); free_value: kfree(value); free_key: @@ -814,8 +810,6 @@ static int map_delete_elem(union bpf_attr *attr) __this_cpu_dec(bpf_prog_active); preempt_enable(); out: - if (!err) - trace_bpf_map_delete_elem(map, ufd, key); kfree(key); err_put: fdput(f); @@ -879,7 +873,6 @@ out: if (copy_to_user(unext_key, next_key, map->key_size) != 0) goto free_next_key; - trace_bpf_map_next_key(map, ufd, key, next_key); err = 0; free_next_key: @@ -1027,7 +1020,6 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) if (atomic_dec_and_test(&prog->aux->refcnt)) { int i; - trace_bpf_prog_put_rcu(prog); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); @@ -1194,11 +1186,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd) struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { - struct bpf_prog *prog = __bpf_prog_get(ufd, &type, attach_drv); - - if (!IS_ERR(prog)) - trace_bpf_prog_get_type(prog); - return prog; + return __bpf_prog_get(ufd, &type, attach_drv); } EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); @@ -1373,7 +1361,6 @@ static int bpf_prog_load(union bpf_attr *attr) } bpf_prog_kallsyms_add(prog); - trace_bpf_prog_load(prog, err); return err; free_used_maps: -- cgit v1.2.3-58-ga151 From a051505c7ec025772983419cc309dc593843f3d2 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Mon, 30 Apr 2018 10:16:22 +0300 Subject: MAINTAINERS: Update mlx5 innova driver maintainers Signed-off-by: Boris Pismenny Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- MAINTAINERS | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index a52800867850..8f0fc25f0042 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9037,26 +9037,17 @@ W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* -MELLANOX ETHERNET INNOVA DRIVER -M: Ilan Tayari -R: Boris Pismenny +MELLANOX ETHERNET INNOVA DRIVERS +M: Boris Pismenny L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ +F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/* +F: drivers/net/ethernet/mellanox/mlx5/core/accel/* F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* F: include/linux/mlx5/mlx5_ifc_fpga.h -MELLANOX ETHERNET INNOVA IPSEC DRIVER -M: Ilan Tayari -R: Boris Pismenny -L: netdev@vger.kernel.org -S: Supported -W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ -F: drivers/net/ethernet/mellanox/mlx5/core/en_ipsec/* -F: drivers/net/ethernet/mellanox/mlx5/core/ipsec* - MELLANOX ETHERNET SWITCH DRIVERS M: Jiri Pirko M: Ido Schimmel -- cgit v1.2.3-58-ga151 From f9c8141fc10324cef00f7e5a3358ccdbe1bd10b4 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Mon, 30 Apr 2018 10:16:23 +0300 Subject: MAINTAINERS: Update TLS maintainers Signed-off-by: Boris Pismenny Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index 8f0fc25f0042..4ee8bec9c9bd 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9839,7 +9839,7 @@ F: net/netfilter/xt_CONNSECMARK.c F: net/netfilter/xt_SECMARK.c NETWORKING [TLS] -M: Ilya Lesokhin +M: Boris Pismenny M: Aviad Yehezkel M: Dave Watson L: netdev@vger.kernel.org -- cgit v1.2.3-58-ga151 From 68e8b849b221b37a78a110a0307717d45e3593a0 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Wed, 2 May 2018 13:01:22 +0200 Subject: net: initial AF_XDP skeleton MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Buildable skeleton of AF_XDP without any functionality. Just what it takes to register a new address family. Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov --- MAINTAINERS | 8 ++++++++ include/linux/socket.h | 5 ++++- net/Kconfig | 1 + net/core/sock.c | 12 ++++++++---- net/xdp/Kconfig | 7 +++++++ security/selinux/hooks.c | 4 +++- security/selinux/include/classmap.h | 4 +++- 7 files changed, 34 insertions(+), 7 deletions(-) create mode 100644 net/xdp/Kconfig (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index 537fd17a211b..52d246fd29c9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15424,6 +15424,14 @@ T: git git://linuxtv.org/media_tree.git S: Maintained F: drivers/media/tuners/tuner-xc2028.* +XDP SOCKETS (AF_XDP) +M: Björn Töpel +M: Magnus Karlsson +L: netdev@vger.kernel.org +S: Maintained +F: kernel/bpf/xskmap.c +F: net/xdp/ + XEN BLOCK SUBSYSTEM M: Konrad Rzeszutek Wilk M: Roger Pau Monné diff --git a/include/linux/socket.h b/include/linux/socket.h index ea50f4a65816..7ed4713d5337 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -207,8 +207,9 @@ struct ucred { * PF_SMC protocol family that * reuses AF_INET address family */ +#define AF_XDP 44 /* XDP sockets */ -#define AF_MAX 44 /* For now.. */ +#define AF_MAX 45 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -257,6 +258,7 @@ struct ucred { #define PF_KCM AF_KCM #define PF_QIPCRTR AF_QIPCRTR #define PF_SMC AF_SMC +#define PF_XDP AF_XDP #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -338,6 +340,7 @@ struct ucred { #define SOL_NFC 280 #define SOL_KCM 281 #define SOL_TLS 282 +#define SOL_XDP 283 /* IPX options */ #define IPX_TYPE 1 diff --git a/net/Kconfig b/net/Kconfig index 6fa1a4493b8c..86471a1c1ed4 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -59,6 +59,7 @@ source "net/tls/Kconfig" source "net/xfrm/Kconfig" source "net/iucv/Kconfig" source "net/smc/Kconfig" +source "net/xdp/Kconfig" config INET bool "TCP/IP networking" diff --git a/net/core/sock.c b/net/core/sock.c index b2c3db169ca1..e7d8b6c955c6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -226,7 +226,8 @@ static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ - x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX" + x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ + x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { _sock_locks("sk_lock-") @@ -262,7 +263,8 @@ static const char *const af_family_rlock_key_strings[AF_MAX+1] = { "rlock-AF_RXRPC" , "rlock-AF_ISDN" , "rlock-AF_PHONET" , "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG" , "rlock-AF_NFC" , "rlock-AF_VSOCK" , "rlock-AF_KCM" , - "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_MAX" + "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_XDP" , + "rlock-AF_MAX" }; static const char *const af_family_wlock_key_strings[AF_MAX+1] = { "wlock-AF_UNSPEC", "wlock-AF_UNIX" , "wlock-AF_INET" , @@ -279,7 +281,8 @@ static const char *const af_family_wlock_key_strings[AF_MAX+1] = { "wlock-AF_RXRPC" , "wlock-AF_ISDN" , "wlock-AF_PHONET" , "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG" , "wlock-AF_NFC" , "wlock-AF_VSOCK" , "wlock-AF_KCM" , - "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_MAX" + "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_XDP" , + "wlock-AF_MAX" }; static const char *const af_family_elock_key_strings[AF_MAX+1] = { "elock-AF_UNSPEC", "elock-AF_UNIX" , "elock-AF_INET" , @@ -296,7 +299,8 @@ static const char *const af_family_elock_key_strings[AF_MAX+1] = { "elock-AF_RXRPC" , "elock-AF_ISDN" , "elock-AF_PHONET" , "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG" , "elock-AF_NFC" , "elock-AF_VSOCK" , "elock-AF_KCM" , - "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_MAX" + "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_XDP" , + "elock-AF_MAX" }; /* diff --git a/net/xdp/Kconfig b/net/xdp/Kconfig new file mode 100644 index 000000000000..90e4a7152854 --- /dev/null +++ b/net/xdp/Kconfig @@ -0,0 +1,7 @@ +config XDP_SOCKETS + bool "XDP sockets" + depends on BPF_SYSCALL + default n + help + XDP sockets allows a channel between XDP programs and + userspace applications. diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4cafe6a19167..5c508d26b367 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1471,7 +1471,9 @@ static inline u16 socket_type_to_security_class(int family, int type, int protoc return SECCLASS_QIPCRTR_SOCKET; case PF_SMC: return SECCLASS_SMC_SOCKET; -#if PF_MAX > 44 + case PF_XDP: + return SECCLASS_XDP_SOCKET; +#if PF_MAX > 45 #error New address family defined, please update this function. #endif } diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index 7f0372426494..bd5fe0d3204a 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -240,9 +240,11 @@ struct security_class_mapping secclass_map[] = { { "manage_subnet", NULL } }, { "bpf", {"map_create", "map_read", "map_write", "prog_load", "prog_run"} }, + { "xdp_socket", + { COMMON_SOCK_PERMS, NULL } }, { NULL } }; -#if PF_MAX > 44 +#if PF_MAX > 45 #error New address family defined, please update secclass_map. #endif -- cgit v1.2.3-58-ga151 From 96faf246d07cb35e7cc2c926b4e32fefab0dd8a6 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Mon, 14 May 2018 10:29:56 +0100 Subject: net: stmmac: Add Jose Abreu as co-maintainer I'm offering to be a co-maintainer for stmmac driver. As per discussion with Alexandre, I will arrange to get STM32 boards to test patches in GMAC version 3.x and 4.1. I also have HW to test GMAC version 5. Looking forward to contribute to net-dev! Signed-off-by: Jose Abreu Cc: David S. Miller Cc: Joao Pinto Cc: Alexandre Torgue Cc: Giuseppe Cavallaro Acked-by: Alexandre TORGUE Signed-off-by: David S. Miller --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index cecf461678b5..c6989d04afef 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13385,6 +13385,7 @@ F: drivers/media/usb/stk1160/ STMMAC ETHERNET DRIVER M: Giuseppe Cavallaro M: Alexandre Torgue +M: Jose Abreu L: netdev@vger.kernel.org W: http://www.stlinux.com S: Supported -- cgit v1.2.3-58-ga151 From 0ce60edd78d3efa8570362846ea76ce1beb3c2b8 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 14 May 2018 22:05:00 +0200 Subject: MAINTAINERS: Add entry for Microsemi Ethernet switches Add myself as a maintainer for the Microsemi Ethernet switches. Signed-off-by: Alexandre Belloni Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index c6989d04afef..658880464b9d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9279,6 +9279,12 @@ F: include/linux/cciss*.h F: include/uapi/linux/cciss*.h F: Documentation/scsi/smartpqi.txt +MICROSEMI ETHERNET SWITCH DRIVER +M: Alexandre Belloni +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/ethernet/mscc/ + MICROSOFT SURFACE PRO 3 BUTTON DRIVER M: Chen Yu L: platform-driver-x86@vger.kernel.org -- cgit v1.2.3-58-ga151 From 877b7cb0b6f283593a663134ee52703f12c895cc Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 19 May 2018 22:31:34 +0200 Subject: net: dsa: mv88e6xxx: Add minimal platform_data support Not all the world uses device tree. Some parts of the world still use platform devices and platform data. Add basic support for probing a Marvell switch via platform data. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- MAINTAINERS | 1 + drivers/net/dsa/mv88e6xxx/chip.c | 56 ++++++++++++++++++++++++++++----- include/linux/platform_data/mv88e6xxx.h | 17 ++++++++++ 3 files changed, 67 insertions(+), 7 deletions(-) create mode 100644 include/linux/platform_data/mv88e6xxx.h (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index 658880464b9d..9f2045a5adac 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8466,6 +8466,7 @@ M: Vivien Didelot L: netdev@vger.kernel.org S: Maintained F: drivers/net/dsa/mv88e6xxx/ +F: linux/platform_data/mv88e6xxx.h F: Documentation/devicetree/bindings/net/dsa/marvell.txt MARVELL ARMADA DRM SUPPORT diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 2bb3f03ee1cb..5b40382036ea 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -4350,6 +4351,7 @@ static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip) return -ENOMEM; ds->priv = chip; + ds->dev = dev; ds->ops = &mv88e6xxx_switch_ops; ds->ageing_time_min = chip->info->age_time_coeff; ds->ageing_time_max = chip->info->age_time_coeff * U8_MAX; @@ -4364,36 +4366,73 @@ static void mv88e6xxx_unregister_switch(struct mv88e6xxx_chip *chip) dsa_unregister_switch(chip->ds); } +static const void *pdata_device_get_match_data(struct device *dev) +{ + const struct of_device_id *matches = dev->driver->of_match_table; + const struct dsa_mv88e6xxx_pdata *pdata = dev->platform_data; + + for (; matches->name[0] || matches->type[0] || matches->compatible[0]; + matches++) { + if (!strcmp(pdata->compatible, matches->compatible)) + return matches->data; + } + return NULL; +} + static int mv88e6xxx_probe(struct mdio_device *mdiodev) { + struct dsa_mv88e6xxx_pdata *pdata = mdiodev->dev.platform_data; struct device *dev = &mdiodev->dev; struct device_node *np = dev->of_node; const struct mv88e6xxx_info *compat_info; struct mv88e6xxx_chip *chip; u32 eeprom_len; + int port; int err; - compat_info = of_device_get_match_data(dev); + if (np) + compat_info = of_device_get_match_data(dev); + + if (pdata) { + compat_info = pdata_device_get_match_data(dev); + + if (!pdata->netdev) + return -EINVAL; + + for (port = 0; port < DSA_MAX_PORTS; port++) { + if (!(pdata->enabled_ports & (1 << port))) + continue; + if (strcmp(pdata->cd.port_names[port], "cpu")) + continue; + pdata->cd.netdev[port] = &pdata->netdev->dev; + break; + } + } + if (!compat_info) return -EINVAL; chip = mv88e6xxx_alloc_chip(dev); - if (!chip) - return -ENOMEM; + if (!chip) { + err = -ENOMEM; + goto out; + } chip->info = compat_info; err = mv88e6xxx_smi_init(chip, mdiodev->bus, mdiodev->addr); if (err) - return err; + goto out; chip->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); - if (IS_ERR(chip->reset)) - return PTR_ERR(chip->reset); + if (IS_ERR(chip->reset)) { + err = PTR_ERR(chip->reset); + goto out; + } err = mv88e6xxx_detect(chip); if (err) - return err; + goto out; mv88e6xxx_phy_init(chip); @@ -4468,6 +4507,9 @@ out_g1_irq: mv88e6xxx_irq_poll_free(chip); mutex_unlock(&chip->reg_lock); out: + if (pdata) + dev_put(pdata->netdev); + return err; } diff --git a/include/linux/platform_data/mv88e6xxx.h b/include/linux/platform_data/mv88e6xxx.h new file mode 100644 index 000000000000..88e91e05f48f --- /dev/null +++ b/include/linux/platform_data/mv88e6xxx.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __DSA_MV88E6XXX_H +#define __DSA_MV88E6XXX_H + +#include + +struct dsa_mv88e6xxx_pdata { + /* Must be first, such that dsa_register_switch() can access this + * without gory pointer manipulations + */ + struct dsa_chip_data cd; + const char *compatible; + unsigned int enabled_ports; + struct net_device *netdev; +}; + +#endif -- cgit v1.2.3-58-ga151 From 30c8bd5aa8b2c78546c3e52337101b9c85879320 Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Thu, 24 May 2018 09:55:13 -0700 Subject: net: Introduce generic failover module The failover module provides a generic interface for paravirtual drivers to register a netdev and a set of ops with a failover instance. The ops are used as event handlers that get called to handle netdev register/ unregister/link change/name change events on slave pci ethernet devices with the same mac address as the failover netdev. This enables paravirtual drivers to use a VF as an accelerated low latency datapath. It also allows migration of VMs with direct attached VFs by failing over to the paravirtual datapath when the VF is unplugged. Signed-off-by: Sridhar Samudrala Signed-off-by: David S. Miller --- Documentation/networking/failover.rst | 18 ++ MAINTAINERS | 8 + include/linux/netdevice.h | 16 ++ include/net/failover.h | 36 ++++ net/Kconfig | 13 ++ net/core/Makefile | 1 + net/core/failover.c | 315 ++++++++++++++++++++++++++++++++++ 7 files changed, 407 insertions(+) create mode 100644 Documentation/networking/failover.rst create mode 100644 include/net/failover.h create mode 100644 net/core/failover.c (limited to 'MAINTAINERS') diff --git a/Documentation/networking/failover.rst b/Documentation/networking/failover.rst new file mode 100644 index 000000000000..f0c8483cdbf5 --- /dev/null +++ b/Documentation/networking/failover.rst @@ -0,0 +1,18 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======== +FAILOVER +======== + +Overview +======== + +The failover module provides a generic interface for paravirtual drivers +to register a netdev and a set of ops with a failover instance. The ops +are used as event handlers that get called to handle netdev register/ +unregister/link change/name change events on slave pci ethernet devices +with the same mac address as the failover netdev. + +This enables paravirtual drivers to use a VF as an accelerated low latency +datapath. It also allows live migration of VMs with direct attached VFs by +failing over to the paravirtual datapath when the VF is unplugged. diff --git a/MAINTAINERS b/MAINTAINERS index f492431b239b..6c59bdf49a8a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5411,6 +5411,14 @@ S: Maintained F: Documentation/hwmon/f71805f F: drivers/hwmon/f71805f.c +FAILOVER MODULE +M: Sridhar Samudrala +L: netdev@vger.kernel.org +S: Supported +F: net/core/failover.c +F: include/net/failover.h +F: Documentation/networking/failover.rst + FANOTIFY M: Jan Kara R: Amir Goldstein diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8452f72087ef..f45b1a4e37ab 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1425,6 +1425,8 @@ struct net_device_ops { * entity (i.e. the master device for bridged veth) * @IFF_MACSEC: device is a MACsec device * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook + * @IFF_FAILOVER: device is a failover master device + * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1454,6 +1456,8 @@ enum netdev_priv_flags { IFF_PHONY_HEADROOM = 1<<24, IFF_MACSEC = 1<<25, IFF_NO_RX_HANDLER = 1<<26, + IFF_FAILOVER = 1<<27, + IFF_FAILOVER_SLAVE = 1<<28, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1482,6 +1486,8 @@ enum netdev_priv_flags { #define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED #define IFF_MACSEC IFF_MACSEC #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER +#define IFF_FAILOVER IFF_FAILOVER +#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE /** * struct net_device - The DEVICE structure. @@ -4336,6 +4342,16 @@ static inline bool netif_is_rxfh_configured(const struct net_device *dev) return dev->priv_flags & IFF_RXFH_CONFIGURED; } +static inline bool netif_is_failover(const struct net_device *dev) +{ + return dev->priv_flags & IFF_FAILOVER; +} + +static inline bool netif_is_failover_slave(const struct net_device *dev) +{ + return dev->priv_flags & IFF_FAILOVER_SLAVE; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { diff --git a/include/net/failover.h b/include/net/failover.h new file mode 100644 index 000000000000..bb15438f39c7 --- /dev/null +++ b/include/net/failover.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _FAILOVER_H +#define _FAILOVER_H + +#include + +struct failover_ops { + int (*slave_pre_register)(struct net_device *slave_dev, + struct net_device *failover_dev); + int (*slave_register)(struct net_device *slave_dev, + struct net_device *failover_dev); + int (*slave_pre_unregister)(struct net_device *slave_dev, + struct net_device *failover_dev); + int (*slave_unregister)(struct net_device *slave_dev, + struct net_device *failover_dev); + int (*slave_link_change)(struct net_device *slave_dev, + struct net_device *failover_dev); + int (*slave_name_change)(struct net_device *slave_dev, + struct net_device *failover_dev); + rx_handler_result_t (*slave_handle_frame)(struct sk_buff **pskb); +}; + +struct failover { + struct list_head list; + struct net_device __rcu *failover_dev; + struct failover_ops __rcu *ops; +}; + +struct failover *failover_register(struct net_device *dev, + struct failover_ops *ops); +void failover_unregister(struct failover *failover); +int failover_slave_unregister(struct net_device *slave_dev); + +#endif /* _FAILOVER_H */ diff --git a/net/Kconfig b/net/Kconfig index ba554cedb615..f738a6f27665 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -432,6 +432,19 @@ config MAY_USE_DEVLINK config PAGE_POOL bool +config FAILOVER + tristate "Generic failover module" + help + The failover module provides a generic interface for paravirtual + drivers to register a netdev and a set of ops with a failover + instance. The ops are used as event handlers that get called to + handle netdev register/unregister/link change/name change events + on slave pci ethernet devices with the same mac address as the + failover netdev. This enables paravirtual drivers to use a + VF as an accelerated low latency datapath. It also allows live + migration of VMs with direct attached VFs by failing over to the + paravirtual datapath when the VF is unplugged. + endif # if NET # Used by archs to tell that they support BPF JIT compiler plus which flavour. diff --git a/net/core/Makefile b/net/core/Makefile index 7080417f8bc8..80175e6a2eb8 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -31,3 +31,4 @@ obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o +obj-$(CONFIG_FAILOVER) += failover.o diff --git a/net/core/failover.c b/net/core/failover.c new file mode 100644 index 000000000000..4a92a98ccce9 --- /dev/null +++ b/net/core/failover.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +/* A common module to handle registrations and notifications for paravirtual + * drivers to enable accelerated datapath and support VF live migration. + * + * The notifier and event handling code is based on netvsc driver. + */ + +#include +#include +#include +#include +#include +#include + +static LIST_HEAD(failover_list); +static DEFINE_SPINLOCK(failover_lock); + +static struct net_device *failover_get_bymac(u8 *mac, struct failover_ops **ops) +{ + struct net_device *failover_dev; + struct failover *failover; + + spin_lock(&failover_lock); + list_for_each_entry(failover, &failover_list, list) { + failover_dev = rtnl_dereference(failover->failover_dev); + if (ether_addr_equal(failover_dev->perm_addr, mac)) { + *ops = rtnl_dereference(failover->ops); + spin_unlock(&failover_lock); + return failover_dev; + } + } + spin_unlock(&failover_lock); + return NULL; +} + +/** + * failover_slave_register - Register a slave netdev + * + * @slave_dev: slave netdev that is being registered + * + * Registers a slave device to a failover instance. Only ethernet devices + * are supported. + */ +static int failover_slave_register(struct net_device *slave_dev) +{ + struct netdev_lag_upper_info lag_upper_info; + struct net_device *failover_dev; + struct failover_ops *fops; + int err; + + if (slave_dev->type != ARPHRD_ETHER) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (fops && fops->slave_pre_register && + fops->slave_pre_register(slave_dev, failover_dev)) + goto done; + + err = netdev_rx_handler_register(slave_dev, fops->slave_handle_frame, + failover_dev); + if (err) { + netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n", + err); + goto done; + } + + lag_upper_info.tx_type = NETDEV_LAG_TX_TYPE_ACTIVEBACKUP; + err = netdev_master_upper_dev_link(slave_dev, failover_dev, NULL, + &lag_upper_info, NULL); + if (err) { + netdev_err(slave_dev, "can not set failover device %s (err = %d)\n", + failover_dev->name, err); + goto err_upper_link; + } + + slave_dev->priv_flags |= IFF_FAILOVER_SLAVE; + + if (fops && fops->slave_register && + !fops->slave_register(slave_dev, failover_dev)) + return NOTIFY_OK; + + netdev_upper_dev_unlink(slave_dev, failover_dev); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; +err_upper_link: + netdev_rx_handler_unregister(slave_dev); +done: + return NOTIFY_DONE; +} + +/** + * failover_slave_unregister - Unregister a slave netdev + * + * @slave_dev: slave netdev that is being unregistered + * + * Unregisters a slave device from a failover instance. + */ +int failover_slave_unregister(struct net_device *slave_dev) +{ + struct net_device *failover_dev; + struct failover_ops *fops; + + if (!netif_is_failover_slave(slave_dev)) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (fops && fops->slave_pre_unregister && + fops->slave_pre_unregister(slave_dev, failover_dev)) + goto done; + + netdev_rx_handler_unregister(slave_dev); + netdev_upper_dev_unlink(slave_dev, failover_dev); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + + if (fops && fops->slave_unregister && + !fops->slave_unregister(slave_dev, failover_dev)) + return NOTIFY_OK; + +done: + return NOTIFY_DONE; +} +EXPORT_SYMBOL_GPL(failover_slave_unregister); + +static int failover_slave_link_change(struct net_device *slave_dev) +{ + struct net_device *failover_dev; + struct failover_ops *fops; + + if (!netif_is_failover_slave(slave_dev)) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (!netif_running(failover_dev)) + goto done; + + if (fops && fops->slave_link_change && + !fops->slave_link_change(slave_dev, failover_dev)) + return NOTIFY_OK; + +done: + return NOTIFY_DONE; +} + +static int failover_slave_name_change(struct net_device *slave_dev) +{ + struct net_device *failover_dev; + struct failover_ops *fops; + + if (!netif_is_failover_slave(slave_dev)) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (!netif_running(failover_dev)) + goto done; + + if (fops && fops->slave_name_change && + !fops->slave_name_change(slave_dev, failover_dev)) + return NOTIFY_OK; + +done: + return NOTIFY_DONE; +} + +static int +failover_event(struct notifier_block *this, unsigned long event, void *ptr) +{ + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + + /* Skip parent events */ + if (netif_is_failover(event_dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_REGISTER: + return failover_slave_register(event_dev); + case NETDEV_UNREGISTER: + return failover_slave_unregister(event_dev); + case NETDEV_UP: + case NETDEV_DOWN: + case NETDEV_CHANGE: + return failover_slave_link_change(event_dev); + case NETDEV_CHANGENAME: + return failover_slave_name_change(event_dev); + default: + return NOTIFY_DONE; + } +} + +static struct notifier_block failover_notifier = { + .notifier_call = failover_event, +}; + +static void +failover_existing_slave_register(struct net_device *failover_dev) +{ + struct net *net = dev_net(failover_dev); + struct net_device *dev; + + rtnl_lock(); + for_each_netdev(net, dev) { + if (netif_is_failover(dev)) + continue; + if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr)) + failover_slave_register(dev); + } + rtnl_unlock(); +} + +/** + * failover_register - Register a failover instance + * + * @dev: failover netdev + * @ops: failover ops + * + * Allocate and register a failover instance for a failover netdev. ops + * provides handlers for slave device register/unregister/link change/ + * name change events. + * + * Return: pointer to failover instance + */ +struct failover *failover_register(struct net_device *dev, + struct failover_ops *ops) +{ + struct failover *failover; + + if (dev->type != ARPHRD_ETHER) + return ERR_PTR(-EINVAL); + + failover = kzalloc(sizeof(*failover), GFP_KERNEL); + if (!failover) + return ERR_PTR(-ENOMEM); + + rcu_assign_pointer(failover->ops, ops); + dev_hold(dev); + dev->priv_flags |= IFF_FAILOVER; + rcu_assign_pointer(failover->failover_dev, dev); + + spin_lock(&failover_lock); + list_add_tail(&failover->list, &failover_list); + spin_unlock(&failover_lock); + + netdev_info(dev, "failover master:%s registered\n", dev->name); + + failover_existing_slave_register(dev); + + return failover; +} +EXPORT_SYMBOL_GPL(failover_register); + +/** + * failover_unregister - Unregister a failover instance + * + * @failover: pointer to failover instance + * + * Unregisters and frees a failover instance. + */ +void failover_unregister(struct failover *failover) +{ + struct net_device *failover_dev; + + failover_dev = rcu_dereference(failover->failover_dev); + + netdev_info(failover_dev, "failover master:%s unregistered\n", + failover_dev->name); + + failover_dev->priv_flags &= ~IFF_FAILOVER; + dev_put(failover_dev); + + spin_lock(&failover_lock); + list_del(&failover->list); + spin_unlock(&failover_lock); + + kfree(failover); +} +EXPORT_SYMBOL_GPL(failover_unregister); + +static __init int +failover_init(void) +{ + register_netdevice_notifier(&failover_notifier); + + return 0; +} +module_init(failover_init); + +static __exit +void failover_exit(void) +{ + unregister_netdevice_notifier(&failover_notifier); +} +module_exit(failover_exit); + +MODULE_DESCRIPTION("Generic failover infrastructure/interface"); +MODULE_LICENSE("GPL v2"); -- cgit v1.2.3-58-ga151 From cfc80d9a11635404a40199a1c9471c96890f3f74 Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Thu, 24 May 2018 09:55:15 -0700 Subject: net: Introduce net_failover driver The net_failover driver provides an automated failover mechanism via APIs to create and destroy a failover master netdev and manages a primary and standby slave netdevs that get registered via the generic failover infrastructure. The failover netdev acts a master device and controls 2 slave devices. The original paravirtual interface gets registered as 'standby' slave netdev and a passthru/vf device with the same MAC gets registered as 'primary' slave netdev. Both 'standby' and 'failover' netdevs are associated with the same 'pci' device. The user accesses the network interface via 'failover' netdev. The 'failover' netdev chooses 'primary' netdev as default for transmits when it is available with link up and running. This can be used by paravirtual drivers to enable an alternate low latency datapath. It also enables hypervisor controlled live migration of a VM with direct attached VF by failing over to the paravirtual datapath when the VF is unplugged. Signed-off-by: Sridhar Samudrala Signed-off-by: David S. Miller --- Documentation/networking/net_failover.rst | 26 + MAINTAINERS | 8 + drivers/net/Kconfig | 12 + drivers/net/Makefile | 1 + drivers/net/net_failover.c | 836 ++++++++++++++++++++++++++++++ include/net/net_failover.h | 40 ++ 6 files changed, 923 insertions(+) create mode 100644 Documentation/networking/net_failover.rst create mode 100644 drivers/net/net_failover.c create mode 100644 include/net/net_failover.h (limited to 'MAINTAINERS') diff --git a/Documentation/networking/net_failover.rst b/Documentation/networking/net_failover.rst new file mode 100644 index 000000000000..d4513ad31809 --- /dev/null +++ b/Documentation/networking/net_failover.rst @@ -0,0 +1,26 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============ +NET_FAILOVER +============ + +Overview +======== + +The net_failover driver provides an automated failover mechanism via APIs +to create and destroy a failover master netdev and mananges a primary and +standby slave netdevs that get registered via the generic failover +infrastructrure. + +The failover netdev acts a master device and controls 2 slave devices. The +original paravirtual interface is registered as 'standby' slave netdev and +a passthru/vf device with the same MAC gets registered as 'primary' slave +netdev. Both 'standby' and 'failover' netdevs are associated with the same +'pci' device. The user accesses the network interface via 'failover' netdev. +The 'failover' netdev chooses 'primary' netdev as default for transmits when +it is available with link up and running. + +This can be used by paravirtual drivers to enable an alternate low latency +datapath. It also enables hypervisor controlled live migration of a VM with +direct attached VF by failing over to the paravirtual datapath when the VF +is unplugged. diff --git a/MAINTAINERS b/MAINTAINERS index 6c59bdf49a8a..1831ff5863a1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9654,6 +9654,14 @@ S: Maintained F: Documentation/hwmon/nct6775 F: drivers/hwmon/nct6775.c +NET_FAILOVER MODULE +M: Sridhar Samudrala +L: netdev@vger.kernel.org +S: Supported +F: driver/net/net_failover.c +F: include/net/net_failover.h +F: Documentation/networking/net_failover.rst + NETEFFECT IWARP RNIC DRIVER (IW_NES) M: Faisal Latif L: linux-rdma@vger.kernel.org diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index a029b27fd002..2cdaff90a9ec 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -510,4 +510,16 @@ config NETDEVSIM To compile this driver as a module, choose M here: the module will be called netdevsim. +config NET_FAILOVER + tristate "Failover driver" + select FAILOVER + help + This provides an automated failover mechanism via APIs to create + and destroy a failover master netdev and manages a primary and + standby slave netdevs that get registered via the generic failover + infrastructure. This can be used by paravirtual drivers to enable + an alternate low latency datapath. It alsoenables live migration of + a VM with direct attached VF by failing over to the paravirtual + datapath when the VF is unplugged. + endif # NETDEVICES diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 91e67e375dd4..21cde7e78621 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -78,3 +78,4 @@ obj-$(CONFIG_FUJITSU_ES) += fjes/ thunderbolt-net-y += thunderbolt.o obj-$(CONFIG_THUNDERBOLT_NET) += thunderbolt-net.o obj-$(CONFIG_NETDEVSIM) += netdevsim/ +obj-$(CONFIG_NET_FAILOVER) += net_failover.o diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c new file mode 100644 index 000000000000..8b508e2cf29b --- /dev/null +++ b/drivers/net/net_failover.c @@ -0,0 +1,836 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +/* This provides a net_failover interface for paravirtual drivers to + * provide an alternate datapath by exporting APIs to create and + * destroy a upper 'net_failover' netdev. The upper dev manages the + * original paravirtual interface as a 'standby' netdev and uses the + * generic failover infrastructure to register and manage a direct + * attached VF as a 'primary' netdev. This enables live migration of + * a VM with direct attached VF by failing over to the paravirtual + * datapath when the VF is unplugged. + * + * Some of the netdev management routines are based on bond/team driver as + * this driver provides active-backup functionality similar to those drivers. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static bool net_failover_xmit_ready(struct net_device *dev) +{ + return netif_running(dev) && netif_carrier_ok(dev); +} + +static int net_failover_open(struct net_device *dev) +{ + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *primary_dev, *standby_dev; + int err; + + primary_dev = rtnl_dereference(nfo_info->primary_dev); + if (primary_dev) { + err = dev_open(primary_dev); + if (err) + goto err_primary_open; + } + + standby_dev = rtnl_dereference(nfo_info->standby_dev); + if (standby_dev) { + err = dev_open(standby_dev); + if (err) + goto err_standby_open; + } + + if ((primary_dev && net_failover_xmit_ready(primary_dev)) || + (standby_dev && net_failover_xmit_ready(standby_dev))) { + netif_carrier_on(dev); + netif_tx_wake_all_queues(dev); + } + + return 0; + +err_standby_open: + dev_close(primary_dev); +err_primary_open: + netif_tx_disable(dev); + return err; +} + +static int net_failover_close(struct net_device *dev) +{ + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *slave_dev; + + netif_tx_disable(dev); + + slave_dev = rtnl_dereference(nfo_info->primary_dev); + if (slave_dev) + dev_close(slave_dev); + + slave_dev = rtnl_dereference(nfo_info->standby_dev); + if (slave_dev) + dev_close(slave_dev); + + return 0; +} + +static netdev_tx_t net_failover_drop_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + atomic_long_inc(&dev->tx_dropped); + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; +} + +static netdev_tx_t net_failover_start_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *xmit_dev; + + /* Try xmit via primary netdev followed by standby netdev */ + xmit_dev = rcu_dereference_bh(nfo_info->primary_dev); + if (!xmit_dev || !net_failover_xmit_ready(xmit_dev)) { + xmit_dev = rcu_dereference_bh(nfo_info->standby_dev); + if (!xmit_dev || !net_failover_xmit_ready(xmit_dev)) + return net_failover_drop_xmit(skb, dev); + } + + skb->dev = xmit_dev; + skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping; + + return dev_queue_xmit(skb); +} + +static u16 net_failover_select_queue(struct net_device *dev, + struct sk_buff *skb, void *accel_priv, + select_queue_fallback_t fallback) +{ + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *primary_dev; + u16 txq; + + primary_dev = rcu_dereference(nfo_info->primary_dev); + if (primary_dev) { + const struct net_device_ops *ops = primary_dev->netdev_ops; + + if (ops->ndo_select_queue) + txq = ops->ndo_select_queue(primary_dev, skb, + accel_priv, fallback); + else + txq = fallback(primary_dev, skb); + + qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; + + return txq; + } + + txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; + + /* Save the original txq to restore before passing to the driver */ + qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; + + if (unlikely(txq >= dev->real_num_tx_queues)) { + do { + txq -= dev->real_num_tx_queues; + } while (txq >= dev->real_num_tx_queues); + } + + return txq; +} + +/* fold stats, assuming all rtnl_link_stats64 fields are u64, but + * that some drivers can provide 32bit values only. + */ +static void net_failover_fold_stats(struct rtnl_link_stats64 *_res, + const struct rtnl_link_stats64 *_new, + const struct rtnl_link_stats64 *_old) +{ + const u64 *new = (const u64 *)_new; + const u64 *old = (const u64 *)_old; + u64 *res = (u64 *)_res; + int i; + + for (i = 0; i < sizeof(*_res) / sizeof(u64); i++) { + u64 nv = new[i]; + u64 ov = old[i]; + s64 delta = nv - ov; + + /* detects if this particular field is 32bit only */ + if (((nv | ov) >> 32) == 0) + delta = (s64)(s32)((u32)nv - (u32)ov); + + /* filter anomalies, some drivers reset their stats + * at down/up events. + */ + if (delta > 0) + res[i] += delta; + } +} + +static void net_failover_get_stats(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct net_failover_info *nfo_info = netdev_priv(dev); + const struct rtnl_link_stats64 *new; + struct rtnl_link_stats64 temp; + struct net_device *slave_dev; + + spin_lock(&nfo_info->stats_lock); + memcpy(stats, &nfo_info->failover_stats, sizeof(*stats)); + + rcu_read_lock(); + + slave_dev = rcu_dereference(nfo_info->primary_dev); + if (slave_dev) { + new = dev_get_stats(slave_dev, &temp); + net_failover_fold_stats(stats, new, &nfo_info->primary_stats); + memcpy(&nfo_info->primary_stats, new, sizeof(*new)); + } + + slave_dev = rcu_dereference(nfo_info->standby_dev); + if (slave_dev) { + new = dev_get_stats(slave_dev, &temp); + net_failover_fold_stats(stats, new, &nfo_info->standby_stats); + memcpy(&nfo_info->standby_stats, new, sizeof(*new)); + } + + rcu_read_unlock(); + + memcpy(&nfo_info->failover_stats, stats, sizeof(*stats)); + spin_unlock(&nfo_info->stats_lock); +} + +static int net_failover_change_mtu(struct net_device *dev, int new_mtu) +{ + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *primary_dev, *standby_dev; + int ret = 0; + + primary_dev = rcu_dereference(nfo_info->primary_dev); + if (primary_dev) { + ret = dev_set_mtu(primary_dev, new_mtu); + if (ret) + return ret; + } + + standby_dev = rcu_dereference(nfo_info->standby_dev); + if (standby_dev) { + ret = dev_set_mtu(standby_dev, new_mtu); + if (ret) { + if (primary_dev) + dev_set_mtu(primary_dev, dev->mtu); + return ret; + } + } + + dev->mtu = new_mtu; + + return 0; +} + +static void net_failover_set_rx_mode(struct net_device *dev) +{ + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *slave_dev; + + rcu_read_lock(); + + slave_dev = rcu_dereference(nfo_info->primary_dev); + if (slave_dev) { + dev_uc_sync_multiple(slave_dev, dev); + dev_mc_sync_multiple(slave_dev, dev); + } + + slave_dev = rcu_dereference(nfo_info->standby_dev); + if (slave_dev) { + dev_uc_sync_multiple(slave_dev, dev); + dev_mc_sync_multiple(slave_dev, dev); + } + + rcu_read_unlock(); +} + +static int net_failover_vlan_rx_add_vid(struct net_device *dev, __be16 proto, + u16 vid) +{ + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *primary_dev, *standby_dev; + int ret = 0; + + primary_dev = rcu_dereference(nfo_info->primary_dev); + if (primary_dev) { + ret = vlan_vid_add(primary_dev, proto, vid); + if (ret) + return ret; + } + + standby_dev = rcu_dereference(nfo_info->standby_dev); + if (standby_dev) { + ret = vlan_vid_add(standby_dev, proto, vid); + if (ret) + if (primary_dev) + vlan_vid_del(primary_dev, proto, vid); + } + + return ret; +} + +static int net_failover_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, + u16 vid) +{ + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *slave_dev; + + slave_dev = rcu_dereference(nfo_info->primary_dev); + if (slave_dev) + vlan_vid_del(slave_dev, proto, vid); + + slave_dev = rcu_dereference(nfo_info->standby_dev); + if (slave_dev) + vlan_vid_del(slave_dev, proto, vid); + + return 0; +} + +static const struct net_device_ops failover_dev_ops = { + .ndo_open = net_failover_open, + .ndo_stop = net_failover_close, + .ndo_start_xmit = net_failover_start_xmit, + .ndo_select_queue = net_failover_select_queue, + .ndo_get_stats64 = net_failover_get_stats, + .ndo_change_mtu = net_failover_change_mtu, + .ndo_set_rx_mode = net_failover_set_rx_mode, + .ndo_vlan_rx_add_vid = net_failover_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = net_failover_vlan_rx_kill_vid, + .ndo_validate_addr = eth_validate_addr, + .ndo_features_check = passthru_features_check, +}; + +#define FAILOVER_NAME "net_failover" +#define FAILOVER_VERSION "0.1" + +static void nfo_ethtool_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *drvinfo) +{ + strlcpy(drvinfo->driver, FAILOVER_NAME, sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, FAILOVER_VERSION, sizeof(drvinfo->version)); +} + +static int nfo_ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) +{ + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *slave_dev; + + slave_dev = rtnl_dereference(nfo_info->primary_dev); + if (!slave_dev || !net_failover_xmit_ready(slave_dev)) { + slave_dev = rtnl_dereference(nfo_info->standby_dev); + if (!slave_dev || !net_failover_xmit_ready(slave_dev)) { + cmd->base.duplex = DUPLEX_UNKNOWN; + cmd->base.port = PORT_OTHER; + cmd->base.speed = SPEED_UNKNOWN; + + return 0; + } + } + + return __ethtool_get_link_ksettings(slave_dev, cmd); +} + +static const struct ethtool_ops failover_ethtool_ops = { + .get_drvinfo = nfo_ethtool_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_link_ksettings = nfo_ethtool_get_link_ksettings, +}; + +/* Called when slave dev is injecting data into network stack. + * Change the associated network device from lower dev to failover dev. + * note: already called with rcu_read_lock + */ +static rx_handler_result_t net_failover_handle_frame(struct sk_buff **pskb) +{ + struct sk_buff *skb = *pskb; + struct net_device *dev = rcu_dereference(skb->dev->rx_handler_data); + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *primary_dev, *standby_dev; + + primary_dev = rcu_dereference(nfo_info->primary_dev); + standby_dev = rcu_dereference(nfo_info->standby_dev); + + if (primary_dev && skb->dev == standby_dev) + return RX_HANDLER_EXACT; + + skb->dev = dev; + + return RX_HANDLER_ANOTHER; +} + +static void net_failover_compute_features(struct net_device *dev) +{ + u32 vlan_features = FAILOVER_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL; + netdev_features_t enc_features = FAILOVER_ENC_FEATURES; + unsigned short max_hard_header_len = ETH_HLEN; + unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | + IFF_XMIT_DST_RELEASE_PERM; + struct net_failover_info *nfo_info = netdev_priv(dev); + struct net_device *primary_dev, *standby_dev; + + primary_dev = rcu_dereference(nfo_info->primary_dev); + if (primary_dev) { + vlan_features = + netdev_increment_features(vlan_features, + primary_dev->vlan_features, + FAILOVER_VLAN_FEATURES); + enc_features = + netdev_increment_features(enc_features, + primary_dev->hw_enc_features, + FAILOVER_ENC_FEATURES); + + dst_release_flag &= primary_dev->priv_flags; + if (primary_dev->hard_header_len > max_hard_header_len) + max_hard_header_len = primary_dev->hard_header_len; + } + + standby_dev = rcu_dereference(nfo_info->standby_dev); + if (standby_dev) { + vlan_features = + netdev_increment_features(vlan_features, + standby_dev->vlan_features, + FAILOVER_VLAN_FEATURES); + enc_features = + netdev_increment_features(enc_features, + standby_dev->hw_enc_features, + FAILOVER_ENC_FEATURES); + + dst_release_flag &= standby_dev->priv_flags; + if (standby_dev->hard_header_len > max_hard_header_len) + max_hard_header_len = standby_dev->hard_header_len; + } + + dev->vlan_features = vlan_features; + dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL; + dev->hard_header_len = max_hard_header_len; + + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + if (dst_release_flag == (IFF_XMIT_DST_RELEASE | + IFF_XMIT_DST_RELEASE_PERM)) + dev->priv_flags |= IFF_XMIT_DST_RELEASE; + + netdev_change_features(dev); +} + +static void net_failover_lower_state_changed(struct net_device *slave_dev, + struct net_device *primary_dev, + struct net_device *standby_dev) +{ + struct netdev_lag_lower_state_info info; + + if (netif_carrier_ok(slave_dev)) + info.link_up = true; + else + info.link_up = false; + + if (slave_dev == primary_dev) { + if (netif_running(primary_dev)) + info.tx_enabled = true; + else + info.tx_enabled = false; + } else { + if ((primary_dev && netif_running(primary_dev)) || + (!netif_running(standby_dev))) + info.tx_enabled = false; + else + info.tx_enabled = true; + } + + netdev_lower_state_changed(slave_dev, &info); +} + +static int net_failover_slave_pre_register(struct net_device *slave_dev, + struct net_device *failover_dev) +{ + struct net_device *standby_dev, *primary_dev; + struct net_failover_info *nfo_info; + bool slave_is_standby; + + nfo_info = netdev_priv(failover_dev); + standby_dev = rtnl_dereference(nfo_info->standby_dev); + primary_dev = rtnl_dereference(nfo_info->primary_dev); + slave_is_standby = slave_dev->dev.parent == failover_dev->dev.parent; + if (slave_is_standby ? standby_dev : primary_dev) { + netdev_err(failover_dev, "%s attempting to register as slave dev when %s already present\n", + slave_dev->name, + slave_is_standby ? "standby" : "primary"); + return -EINVAL; + } + + /* We want to allow only a direct attached VF device as a primary + * netdev. As there is no easy way to check for a VF device, restrict + * this to a pci device. + */ + if (!slave_is_standby && (!slave_dev->dev.parent || + !dev_is_pci(slave_dev->dev.parent))) + return -EINVAL; + + if (failover_dev->features & NETIF_F_VLAN_CHALLENGED && + vlan_uses_dev(failover_dev)) { + netdev_err(failover_dev, "Device %s is VLAN challenged and failover device has VLAN set up\n", + failover_dev->name); + return -EINVAL; + } + + return 0; +} + +static int net_failover_slave_register(struct net_device *slave_dev, + struct net_device *failover_dev) +{ + struct net_device *standby_dev, *primary_dev; + struct net_failover_info *nfo_info; + bool slave_is_standby; + u32 orig_mtu; + int err; + + /* Align MTU of slave with failover dev */ + orig_mtu = slave_dev->mtu; + err = dev_set_mtu(slave_dev, failover_dev->mtu); + if (err) { + netdev_err(failover_dev, "unable to change mtu of %s to %u register failed\n", + slave_dev->name, failover_dev->mtu); + goto done; + } + + dev_hold(slave_dev); + + if (netif_running(failover_dev)) { + err = dev_open(slave_dev); + if (err && (err != -EBUSY)) { + netdev_err(failover_dev, "Opening slave %s failed err:%d\n", + slave_dev->name, err); + goto err_dev_open; + } + } + + netif_addr_lock_bh(failover_dev); + dev_uc_sync_multiple(slave_dev, failover_dev); + dev_uc_sync_multiple(slave_dev, failover_dev); + netif_addr_unlock_bh(failover_dev); + + err = vlan_vids_add_by_dev(slave_dev, failover_dev); + if (err) { + netdev_err(failover_dev, "Failed to add vlan ids to device %s err:%d\n", + slave_dev->name, err); + goto err_vlan_add; + } + + nfo_info = netdev_priv(failover_dev); + standby_dev = rtnl_dereference(nfo_info->standby_dev); + primary_dev = rtnl_dereference(nfo_info->primary_dev); + slave_is_standby = slave_dev->dev.parent == failover_dev->dev.parent; + + if (slave_is_standby) { + rcu_assign_pointer(nfo_info->standby_dev, slave_dev); + standby_dev = slave_dev; + dev_get_stats(standby_dev, &nfo_info->standby_stats); + } else { + rcu_assign_pointer(nfo_info->primary_dev, slave_dev); + primary_dev = slave_dev; + dev_get_stats(primary_dev, &nfo_info->primary_stats); + failover_dev->min_mtu = slave_dev->min_mtu; + failover_dev->max_mtu = slave_dev->max_mtu; + } + + net_failover_lower_state_changed(slave_dev, primary_dev, standby_dev); + net_failover_compute_features(failover_dev); + + call_netdevice_notifiers(NETDEV_JOIN, slave_dev); + + netdev_info(failover_dev, "failover %s slave:%s registered\n", + slave_is_standby ? "standby" : "primary", slave_dev->name); + + return 0; + +err_vlan_add: + dev_uc_unsync(slave_dev, failover_dev); + dev_mc_unsync(slave_dev, failover_dev); + dev_close(slave_dev); +err_dev_open: + dev_put(slave_dev); + dev_set_mtu(slave_dev, orig_mtu); +done: + return err; +} + +static int net_failover_slave_pre_unregister(struct net_device *slave_dev, + struct net_device *failover_dev) +{ + struct net_device *standby_dev, *primary_dev; + struct net_failover_info *nfo_info; + + nfo_info = netdev_priv(failover_dev); + primary_dev = rtnl_dereference(nfo_info->primary_dev); + standby_dev = rtnl_dereference(nfo_info->standby_dev); + + if (slave_dev != primary_dev && slave_dev != standby_dev) + return -ENODEV; + + return 0; +} + +static int net_failover_slave_unregister(struct net_device *slave_dev, + struct net_device *failover_dev) +{ + struct net_device *standby_dev, *primary_dev; + struct net_failover_info *nfo_info; + bool slave_is_standby; + + nfo_info = netdev_priv(failover_dev); + primary_dev = rtnl_dereference(nfo_info->primary_dev); + standby_dev = rtnl_dereference(nfo_info->standby_dev); + + vlan_vids_del_by_dev(slave_dev, failover_dev); + dev_uc_unsync(slave_dev, failover_dev); + dev_mc_unsync(slave_dev, failover_dev); + dev_close(slave_dev); + + nfo_info = netdev_priv(failover_dev); + dev_get_stats(failover_dev, &nfo_info->failover_stats); + + slave_is_standby = slave_dev->dev.parent == failover_dev->dev.parent; + if (slave_is_standby) { + RCU_INIT_POINTER(nfo_info->standby_dev, NULL); + } else { + RCU_INIT_POINTER(nfo_info->primary_dev, NULL); + if (standby_dev) { + failover_dev->min_mtu = standby_dev->min_mtu; + failover_dev->max_mtu = standby_dev->max_mtu; + } + } + + dev_put(slave_dev); + + net_failover_compute_features(failover_dev); + + netdev_info(failover_dev, "failover %s slave:%s unregistered\n", + slave_is_standby ? "standby" : "primary", slave_dev->name); + + return 0; +} + +static int net_failover_slave_link_change(struct net_device *slave_dev, + struct net_device *failover_dev) +{ + struct net_device *primary_dev, *standby_dev; + struct net_failover_info *nfo_info; + + nfo_info = netdev_priv(failover_dev); + + primary_dev = rtnl_dereference(nfo_info->primary_dev); + standby_dev = rtnl_dereference(nfo_info->standby_dev); + + if (slave_dev != primary_dev && slave_dev != standby_dev) + return -ENODEV; + + if ((primary_dev && net_failover_xmit_ready(primary_dev)) || + (standby_dev && net_failover_xmit_ready(standby_dev))) { + netif_carrier_on(failover_dev); + netif_tx_wake_all_queues(failover_dev); + } else { + dev_get_stats(failover_dev, &nfo_info->failover_stats); + netif_carrier_off(failover_dev); + netif_tx_stop_all_queues(failover_dev); + } + + net_failover_lower_state_changed(slave_dev, primary_dev, standby_dev); + + return 0; +} + +static int net_failover_slave_name_change(struct net_device *slave_dev, + struct net_device *failover_dev) +{ + struct net_device *primary_dev, *standby_dev; + struct net_failover_info *nfo_info; + + nfo_info = netdev_priv(failover_dev); + + primary_dev = rtnl_dereference(nfo_info->primary_dev); + standby_dev = rtnl_dereference(nfo_info->standby_dev); + + if (slave_dev != primary_dev && slave_dev != standby_dev) + return -ENODEV; + + /* We need to bring up the slave after the rename by udev in case + * open failed with EBUSY when it was registered. + */ + dev_open(slave_dev); + + return 0; +} + +static struct failover_ops net_failover_ops = { + .slave_pre_register = net_failover_slave_pre_register, + .slave_register = net_failover_slave_register, + .slave_pre_unregister = net_failover_slave_pre_unregister, + .slave_unregister = net_failover_slave_unregister, + .slave_link_change = net_failover_slave_link_change, + .slave_name_change = net_failover_slave_name_change, + .slave_handle_frame = net_failover_handle_frame, +}; + +/** + * net_failover_create - Create and register a failover instance + * + * @dev: standby netdev + * + * Creates a failover netdev and registers a failover instance for a standby + * netdev. Used by paravirtual drivers that use 3-netdev model. + * The failover netdev acts as a master device and controls 2 slave devices - + * the original standby netdev and a VF netdev with the same MAC gets + * registered as primary netdev. + * + * Return: pointer to failover instance + */ +struct failover *net_failover_create(struct net_device *standby_dev) +{ + struct device *dev = standby_dev->dev.parent; + struct net_device *failover_dev; + struct failover *failover; + int err; + + /* Alloc at least 2 queues, for now we are going with 16 assuming + * that VF devices being enslaved won't have too many queues. + */ + failover_dev = alloc_etherdev_mq(sizeof(struct net_failover_info), 16); + if (!failover_dev) { + dev_err(dev, "Unable to allocate failover_netdev!\n"); + return ERR_PTR(-ENOMEM); + } + + dev_net_set(failover_dev, dev_net(standby_dev)); + SET_NETDEV_DEV(failover_dev, dev); + + failover_dev->netdev_ops = &failover_dev_ops; + failover_dev->ethtool_ops = &failover_ethtool_ops; + + /* Initialize the device options */ + failover_dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE; + failover_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | + IFF_TX_SKB_SHARING); + + /* don't acquire failover netdev's netif_tx_lock when transmitting */ + failover_dev->features |= NETIF_F_LLTX; + + /* Don't allow failover devices to change network namespaces. */ + failover_dev->features |= NETIF_F_NETNS_LOCAL; + + failover_dev->hw_features = FAILOVER_VLAN_FEATURES | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER; + + failover_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; + failover_dev->features |= failover_dev->hw_features; + + memcpy(failover_dev->dev_addr, standby_dev->dev_addr, + failover_dev->addr_len); + + failover_dev->min_mtu = standby_dev->min_mtu; + failover_dev->max_mtu = standby_dev->max_mtu; + + err = register_netdev(failover_dev); + if (err) { + dev_err(dev, "Unable to register failover_dev!\n"); + goto err_register_netdev; + } + + netif_carrier_off(failover_dev); + + failover = failover_register(failover_dev, &net_failover_ops); + if (IS_ERR(failover)) + goto err_failover_register; + + return failover; + +err_failover_register: + unregister_netdev(failover_dev); +err_register_netdev: + free_netdev(failover_dev); + + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(net_failover_create); + +/** + * net_failover_destroy - Destroy a failover instance + * + * @failover: pointer to failover instance + * + * Unregisters any slave netdevs associated with the failover instance by + * calling failover_slave_unregister(). + * unregisters the failover instance itself and finally frees the failover + * netdev. Used by paravirtual drivers that use 3-netdev model. + * + */ +void net_failover_destroy(struct failover *failover) +{ + struct net_failover_info *nfo_info; + struct net_device *failover_dev; + struct net_device *slave_dev; + + if (!failover) + return; + + failover_dev = rcu_dereference(failover->failover_dev); + nfo_info = netdev_priv(failover_dev); + + netif_device_detach(failover_dev); + + rtnl_lock(); + + slave_dev = rtnl_dereference(nfo_info->primary_dev); + if (slave_dev) + failover_slave_unregister(slave_dev); + + slave_dev = rtnl_dereference(nfo_info->standby_dev); + if (slave_dev) + failover_slave_unregister(slave_dev); + + failover_unregister(failover); + + unregister_netdevice(failover_dev); + + rtnl_unlock(); + + free_netdev(failover_dev); +} +EXPORT_SYMBOL_GPL(net_failover_destroy); + +static __init int +net_failover_init(void) +{ + return 0; +} +module_init(net_failover_init); + +static __exit +void net_failover_exit(void) +{ +} +module_exit(net_failover_exit); + +MODULE_DESCRIPTION("Failover driver for Paravirtual drivers"); +MODULE_LICENSE("GPL v2"); diff --git a/include/net/net_failover.h b/include/net/net_failover.h new file mode 100644 index 000000000000..b12a1c469d1c --- /dev/null +++ b/include/net/net_failover.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018, Intel Corporation. */ + +#ifndef _NET_FAILOVER_H +#define _NET_FAILOVER_H + +#include + +/* failover state */ +struct net_failover_info { + /* primary netdev with same MAC */ + struct net_device __rcu *primary_dev; + + /* standby netdev */ + struct net_device __rcu *standby_dev; + + /* primary netdev stats */ + struct rtnl_link_stats64 primary_stats; + + /* standby netdev stats */ + struct rtnl_link_stats64 standby_stats; + + /* aggregated stats */ + struct rtnl_link_stats64 failover_stats; + + /* spinlock while updating stats */ + spinlock_t stats_lock; +}; + +struct failover *net_failover_create(struct net_device *standby_dev); +void net_failover_destroy(struct failover *failover); + +#define FAILOVER_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ + NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ + NETIF_F_HIGHDMA | NETIF_F_LRO) + +#define FAILOVER_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ + NETIF_F_RXCSUM | NETIF_F_ALL_TSO) + +#endif /* _NET_FAILOVER_H */ -- cgit v1.2.3-58-ga151 From 0c3a4cf84fb9ab17a4c9d3b34cfd6098887dd998 Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Tue, 29 May 2018 11:47:44 +0800 Subject: MAINTAINERS: add myself as maintainer for QorIQ PTP clock driver Added myself as maintainer for QorIQ PTP clock driver. Since gianfar_ptp.c was renamed to ptp_qoriq.c, let's maintain it under QorIQ PTP clock driver. Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- MAINTAINERS | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index 1831ff5863a1..e7396119ce58 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5628,7 +5628,6 @@ M: Claudiu Manoil L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/freescale/gianfar* -X: drivers/net/ethernet/freescale/gianfar_ptp.c F: Documentation/devicetree/bindings/net/fsl-tsec-phy.txt FREESCALE GPMI NAND DRIVER @@ -5675,6 +5674,14 @@ S: Maintained F: drivers/net/ethernet/freescale/fman F: Documentation/devicetree/bindings/powerpc/fsl/fman.txt +FREESCALE QORIQ PTP CLOCK DRIVER +M: Yangbo Lu +L: netdev@vger.kernel.org +S: Maintained +F: drivers/ptp/ptp_qoriq.c +F: include/linux/fsl/ptp_qoriq.h +F: Documentation/devicetree/bindings/ptp/ptp-qoriq.txt + FREESCALE QUAD SPI DRIVER M: Han Xu L: linux-mtd@lists.infradead.org @@ -11421,7 +11428,6 @@ S: Maintained W: http://linuxptp.sourceforge.net/ F: Documentation/ABI/testing/sysfs-ptp F: Documentation/ptp/* -F: drivers/net/ethernet/freescale/gianfar_ptp.c F: drivers/net/phy/dp83640* F: drivers/ptp/* F: include/linux/ptp_cl* -- cgit v1.2.3-58-ga151 From 10a76564ae865cbf30ed30e8cbdc1a047e0559ae Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 2 Jun 2018 23:06:41 +0200 Subject: bpf, doc: add missing patchwork url and libbpf to maintainers Add missing bits under tools/lib/bpf/ and also Q: entry in order to make it easier for people to retrieve current patch queue. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index f492431b239b..2fd51db09fa4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2722,6 +2722,7 @@ L: netdev@vger.kernel.org L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git +Q: https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147 S: Supported F: arch/x86/net/bpf_jit* F: Documentation/networking/filter.txt @@ -2740,6 +2741,7 @@ F: net/sched/act_bpf.c F: net/sched/cls_bpf.c F: samples/bpf/ F: tools/bpf/ +F: tools/lib/bpf/ F: tools/testing/selftests/bpf/ BROADCOM B44 10/100 ETHERNET DRIVER -- cgit v1.2.3-58-ga151 From d3adce9d0334fcd5de1e9aa8749c8953ffc9b5a7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 4 Jun 2018 06:50:29 -0700 Subject: MAINTAINERS: TCP gets its first maintainer Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- MAINTAINERS | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'MAINTAINERS') diff --git a/MAINTAINERS b/MAINTAINERS index 0ae0dbf0e15e..70d61c2b1be4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9862,6 +9862,19 @@ F: net/ipv6/calipso.c F: net/netfilter/xt_CONNSECMARK.c F: net/netfilter/xt_SECMARK.c +NETWORKING [TCP] +M: Eric Dumazet +L: netdev@vger.kernel.org +S: Maintained +F: net/ipv4/tcp*.c +F: net/ipv4/syncookies.c +F: net/ipv6/tcp*.c +F: net/ipv6/syncookies.c +F: include/uapi/linux/tcp.h +F: include/net/tcp.h +F: include/linux/tcp.h +F: include/trace/events/tcp.h + NETWORKING [TLS] M: Boris Pismenny M: Aviad Yehezkel -- cgit v1.2.3-58-ga151 From 85d63445f41125dafeddda74e5b13b7eefac9407 Mon Sep 17 00:00:00 2001 From: Jeff Kirsher Date: Thu, 10 May 2018 12:20:13 -0700 Subject: Documentation: e100: Update the Intel 10/100 driver doc Over the years, several of the links have changed or are no longer valid so update them. In addition, the default values were incorrect for a couple of parameters. Converted the text file to the reStructuredText (RST) format, since the Linux kernel documentation now uses this format for documentation. Signed-off-by: Jeff Kirsher Tested-by: Aaron Brown --- Documentation/networking/e100.rst | 177 +++++++++++++++++++++++++++++++++++ Documentation/networking/e100.txt | 183 ------------------------------------- Documentation/networking/index.rst | 1 + MAINTAINERS | 2 +- 4 files changed, 179 insertions(+), 184 deletions(-) create mode 100644 Documentation/networking/e100.rst delete mode 100644 Documentation/networking/e100.txt (limited to 'MAINTAINERS') diff --git a/Documentation/networking/e100.rst b/Documentation/networking/e100.rst new file mode 100644 index 000000000000..d4d837027925 --- /dev/null +++ b/Documentation/networking/e100.rst @@ -0,0 +1,177 @@ +Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters +============================================================== + +June 1, 2018 + +Contents +======== + +- In This Release +- Identifying Your Adapter +- Building and Installation +- Driver Configuration Parameters +- Additional Configurations +- Known Issues +- Support + + +In This Release +=============== + +This file describes the Linux* Base Driver for the Intel(R) PRO/100 Family of +Adapters. This driver includes support for Itanium(R)2-based systems. + +For questions related to hardware requirements, refer to the documentation +supplied with your Intel PRO/100 adapter. + +The following features are now available in supported kernels: + - Native VLANs + - Channel Bonding (teaming) + - SNMP + +Channel Bonding documentation can be found in the Linux kernel source: +/Documentation/networking/bonding.txt + + +Identifying Your Adapter +======================== + +For information on how to identify your adapter, and for the latest Intel +network drivers, refer to the Intel Support website: +http://www.intel.com/support + +Driver Configuration Parameters +=============================== + +The default value for each parameter is generally the recommended setting, +unless otherwise noted. + +Rx Descriptors: Number of receive descriptors. A receive descriptor is a data + structure that describes a receive buffer and its attributes to the network + controller. The data in the descriptor is used by the controller to write + data from the controller to host memory. In the 3.x.x driver the valid range + for this parameter is 64-256. The default value is 256. This parameter can be + changed using the command:: + + ethtool -G eth? rx n + + Where n is the number of desired Rx descriptors. + +Tx Descriptors: Number of transmit descriptors. A transmit descriptor is a data + structure that describes a transmit buffer and its attributes to the network + controller. The data in the descriptor is used by the controller to read + data from the host memory to the controller. In the 3.x.x driver the valid + range for this parameter is 64-256. The default value is 128. This parameter + can be changed using the command:: + + ethtool -G eth? tx n + + Where n is the number of desired Tx descriptors. + +Speed/Duplex: The driver auto-negotiates the link speed and duplex settings by + default. The ethtool utility can be used as follows to force speed/duplex.:: + + ethtool -s eth? autoneg off speed {10|100} duplex {full|half} + + NOTE: setting the speed/duplex to incorrect values will cause the link to + fail. + +Event Log Message Level: The driver uses the message level flag to log events + to syslog. The message level can be set at driver load time. It can also be + set using the command:: + + ethtool -s eth? msglvl n + + +Additional Configurations +========================= + + Configuring the Driver on Different Distributions + ------------------------------------------------- + + Configuring a network driver to load properly when the system is started is + distribution dependent. Typically, the configuration process involves adding + an alias line to /etc/modprobe.d/*.conf as well as editing other system + startup scripts and/or configuration files. Many popular Linux + distributions ship with tools to make these changes for you. To learn the + proper way to configure a network device for your system, refer to your + distribution documentation. If during this process you are asked for the + driver or module name, the name for the Linux Base Driver for the Intel + PRO/100 Family of Adapters is e100. + + As an example, if you install the e100 driver for two PRO/100 adapters + (eth0 and eth1), add the following to a configuration file in /etc/modprobe.d/ + + alias eth0 e100 + alias eth1 e100 + + Viewing Link Messages + --------------------- + In order to see link messages and other Intel driver information on your + console, you must set the dmesg level up to six. This can be done by + entering the following on the command line before loading the e100 driver:: + + dmesg -n 6 + + If you wish to see all messages issued by the driver, including debug + messages, set the dmesg level to eight. + + NOTE: This setting is not saved across reboots. + + + ethtool + ------- + + The driver utilizes the ethtool interface for driver configuration and + diagnostics, as well as displaying statistical information. The ethtool + version 1.6 or later is required for this functionality. + + The latest release of ethtool can be found from + https://www.kernel.org/pub/software/network/ethtool/ + + Enabling Wake on LAN* (WoL) + --------------------------- + WoL is provided through the ethtool* utility. For instructions on enabling + WoL with ethtool, refer to the ethtool man page. + + WoL will be enabled on the system during the next shut down or reboot. For + this driver version, in order to enable WoL, the e100 driver must be + loaded when shutting down or rebooting the system. + + NAPI + ---- + + NAPI (Rx polling mode) is supported in the e100 driver. + + See https://wiki.linuxfoundation.org/networking/napi for more information + on NAPI. + + Multiple Interfaces on Same Ethernet Broadcast Network + ------------------------------------------------------ + + Due to the default ARP behavior on Linux, it is not possible to have + one system on two IP networks in the same Ethernet broadcast domain + (non-partitioned switch) behave as expected. All Ethernet interfaces + will respond to IP traffic for any IP address assigned to the system. + This results in unbalanced receive traffic. + + If you have multiple interfaces in a server, either turn on ARP + filtering by + + (1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter + (this only works if your kernel's version is higher than 2.4.5), or + + (2) installing the interfaces in separate broadcast domains (either + in different switches or in a switch partitioned to VLANs). + + +Support +======= +For general information, go to the Intel support website at: +http://www.intel.com/support/ + +or the Intel Wired Networking project hosted by Sourceforge at: +http://sourceforge.net/projects/e1000 +If an issue is identified with the released source code on a supported kernel +with a supported adapter, email the specific information related to the issue +to e1000-devel@lists.sf.net. diff --git a/Documentation/networking/e100.txt b/Documentation/networking/e100.txt deleted file mode 100644 index 54810b82c01a..000000000000 --- a/Documentation/networking/e100.txt +++ /dev/null @@ -1,183 +0,0 @@ -Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters -============================================================== - -March 15, 2011 - -Contents -======== - -- In This Release -- Identifying Your Adapter -- Building and Installation -- Driver Configuration Parameters -- Additional Configurations -- Known Issues -- Support - - -In This Release -=============== - -This file describes the Linux* Base Driver for the Intel(R) PRO/100 Family of -Adapters. This driver includes support for Itanium(R)2-based systems. - -For questions related to hardware requirements, refer to the documentation -supplied with your Intel PRO/100 adapter. - -The following features are now available in supported kernels: - - Native VLANs - - Channel Bonding (teaming) - - SNMP - -Channel Bonding documentation can be found in the Linux kernel source: -/Documentation/networking/bonding.txt - - -Identifying Your Adapter -======================== - -For more information on how to identify your adapter, go to the Adapter & -Driver ID Guide at: - - http://support.intel.com/support/network/adapter/pro100/21397.htm - -For the latest Intel network drivers for Linux, refer to the following -website. In the search field, enter your adapter name or type, or use the -networking link on the left to search for your adapter: - - http://downloadfinder.intel.com/scripts-df/support_intel.asp - -Driver Configuration Parameters -=============================== - -The default value for each parameter is generally the recommended setting, -unless otherwise noted. - -Rx Descriptors: Number of receive descriptors. A receive descriptor is a data - structure that describes a receive buffer and its attributes to the network - controller. The data in the descriptor is used by the controller to write - data from the controller to host memory. In the 3.x.x driver the valid range - for this parameter is 64-256. The default value is 64. This parameter can be - changed using the command: - - ethtool -G eth? rx n, where n is the number of desired rx descriptors. - -Tx Descriptors: Number of transmit descriptors. A transmit descriptor is a data - structure that describes a transmit buffer and its attributes to the network - controller. The data in the descriptor is used by the controller to read - data from the host memory to the controller. In the 3.x.x driver the valid - range for this parameter is 64-256. The default value is 64. This parameter - can be changed using the command: - - ethtool -G eth? tx n, where n is the number of desired tx descriptors. - -Speed/Duplex: The driver auto-negotiates the link speed and duplex settings by - default. The ethtool utility can be used as follows to force speed/duplex. - - ethtool -s eth? autoneg off speed {10|100} duplex {full|half} - - NOTE: setting the speed/duplex to incorrect values will cause the link to - fail. - -Event Log Message Level: The driver uses the message level flag to log events - to syslog. The message level can be set at driver load time. It can also be - set using the command: - - ethtool -s eth? msglvl n - - -Additional Configurations -========================= - - Configuring the Driver on Different Distributions - ------------------------------------------------- - - Configuring a network driver to load properly when the system is started is - distribution dependent. Typically, the configuration process involves adding - an alias line to /etc/modprobe.d/*.conf as well as editing other system - startup scripts and/or configuration files. Many popular Linux - distributions ship with tools to make these changes for you. To learn the - proper way to configure a network device for your system, refer to your - distribution documentation. If during this process you are asked for the - driver or module name, the name for the Linux Base Driver for the Intel - PRO/100 Family of Adapters is e100. - - As an example, if you install the e100 driver for two PRO/100 adapters - (eth0 and eth1), add the following to a configuration file in /etc/modprobe.d/ - - alias eth0 e100 - alias eth1 e100 - - Viewing Link Messages - --------------------- - In order to see link messages and other Intel driver information on your - console, you must set the dmesg level up to six. This can be done by - entering the following on the command line before loading the e100 driver: - - dmesg -n 8 - - If you wish to see all messages issued by the driver, including debug - messages, set the dmesg level to eight. - - NOTE: This setting is not saved across reboots. - - - ethtool - ------- - - The driver utilizes the ethtool interface for driver configuration and - diagnostics, as well as displaying statistical information. The ethtool - version 1.6 or later is required for this functionality. - - The latest release of ethtool can be found from - https://www.kernel.org/pub/software/network/ethtool/ - - Enabling Wake on LAN* (WoL) - --------------------------- - WoL is provided through the ethtool* utility. For instructions on enabling - WoL with ethtool, refer to the ethtool man page. - - WoL will be enabled on the system during the next shut down or reboot. For - this driver version, in order to enable WoL, the e100 driver must be - loaded when shutting down or rebooting the system. - - NAPI - ---- - - NAPI (Rx polling mode) is supported in the e100 driver. - - See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI. - - Multiple Interfaces on Same Ethernet Broadcast Network - ------------------------------------------------------ - - Due to the default ARP behavior on Linux, it is not possible to have - one system on two IP networks in the same Ethernet broadcast domain - (non-partitioned switch) behave as expected. All Ethernet interfaces - will respond to IP traffic for any IP address assigned to the system. - This results in unbalanced receive traffic. - - If you have multiple interfaces in a server, either turn on ARP - filtering by - - (1) entering: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter - (this only works if your kernel's version is higher than 2.4.5), or - - (2) installing the interfaces in separate broadcast domains (either - in different switches or in a switch partitioned to VLANs). - - -Support -======= - -For general information, go to the Intel support website at: - - http://support.intel.com - - or the Intel Wired Networking project hosted by Sourceforge at: - - http://sourceforge.net/projects/e1000 - -If an issue is identified with the released source code on the supported -kernel with a supported adapter, email the specific information related to the -issue to e1000-devel@lists.sourceforge.net. diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index cbd9bdd4a79e..d11a62977edd 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -10,6 +10,7 @@ Contents: batman-adv can dpaa2/index + e100 kapi z8530book msg_zerocopy diff --git a/MAINTAINERS b/MAINTAINERS index 0ae0dbf0e15e..d68981ca9896 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7089,7 +7089,7 @@ Q: http://patchwork.ozlabs.org/project/intel-wired-lan/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git S: Supported -F: Documentation/networking/e100.txt +F: Documentation/networking/e100.rst F: Documentation/networking/e1000.txt F: Documentation/networking/e1000e.txt F: Documentation/networking/igb.txt -- cgit v1.2.3-58-ga151 From 228046e76189ce542f15321b760e380551468017 Mon Sep 17 00:00:00 2001 From: Jeff Kirsher Date: Thu, 10 May 2018 12:55:38 -0700 Subject: Documentation: e1000: Update kernel documentation Updated the e1000.txt kernel documentation with the latest information. Also convert the text file to reStructuredText (RST) format, since the Linux kernel documentation now uses this format for documentation. Signed-off-by: Jeff Kirsher Tested-by: Aaron Brown --- Documentation/networking/e1000.rst | 422 +++++++++++++++++++++++++++++++++ Documentation/networking/e1000.txt | 461 ------------------------------------- Documentation/networking/index.rst | 1 + MAINTAINERS | 2 +- 4 files changed, 424 insertions(+), 462 deletions(-) create mode 100644 Documentation/networking/e1000.rst delete mode 100644 Documentation/networking/e1000.txt (limited to 'MAINTAINERS') diff --git a/Documentation/networking/e1000.rst b/Documentation/networking/e1000.rst new file mode 100644 index 000000000000..616848940e63 --- /dev/null +++ b/Documentation/networking/e1000.rst @@ -0,0 +1,422 @@ +Linux* Base Driver for Intel(R) Ethernet Network Connection +=========================================================== + +Intel Gigabit Linux driver. +Copyright(c) 1999 - 2013 Intel Corporation. + +Contents +======== + +- Identifying Your Adapter +- Command Line Parameters +- Speed and Duplex Configuration +- Additional Configurations +- Support + +Identifying Your Adapter +======================== + +For more information on how to identify your adapter, go to the Adapter & +Driver ID Guide at: + + http://support.intel.com/support/go/network/adapter/idguide.htm + +For the latest Intel network drivers for Linux, refer to the following +website. In the search field, enter your adapter name or type, or use the +networking link on the left to search for your adapter: + + http://support.intel.com/support/go/network/adapter/home.htm + +Command Line Parameters +======================= + +The default value for each parameter is generally the recommended setting, +unless otherwise noted. + +NOTES: For more information about the AutoNeg, Duplex, and Speed + parameters, see the "Speed and Duplex Configuration" section in + this document. + + For more information about the InterruptThrottleRate, + RxIntDelay, TxIntDelay, RxAbsIntDelay, and TxAbsIntDelay + parameters, see the application note at: + http://www.intel.com/design/network/applnots/ap450.htm + +AutoNeg +------- +(Supported only on adapters with copper connections) +Valid Range: 0x01-0x0F, 0x20-0x2F +Default Value: 0x2F + +This parameter is a bit-mask that specifies the speed and duplex settings +advertised by the adapter. When this parameter is used, the Speed and +Duplex parameters must not be specified. + +NOTE: Refer to the Speed and Duplex section of this readme for more + information on the AutoNeg parameter. + +Duplex +------ +(Supported only on adapters with copper connections) +Valid Range: 0-2 (0=auto-negotiate, 1=half, 2=full) +Default Value: 0 + +This defines the direction in which data is allowed to flow. Can be +either one or two-directional. If both Duplex and the link partner are +set to auto-negotiate, the board auto-detects the correct duplex. If the +link partner is forced (either full or half), Duplex defaults to half- +duplex. + +FlowControl +----------- +Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx) +Default Value: Reads flow control settings from the EEPROM + +This parameter controls the automatic generation(Tx) and response(Rx) +to Ethernet PAUSE frames. + +InterruptThrottleRate +--------------------- +(not supported on Intel(R) 82542, 82543 or 82544-based adapters) +Valid Range: 0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative, + 4=simplified balancing) +Default Value: 3 + +The driver can limit the amount of interrupts per second that the adapter +will generate for incoming packets. It does this by writing a value to the +adapter that is based on the maximum amount of interrupts that the adapter +will generate per second. + +Setting InterruptThrottleRate to a value greater or equal to 100 +will program the adapter to send out a maximum of that many interrupts +per second, even if more packets have come in. This reduces interrupt +load on the system and can lower CPU utilization under heavy load, +but will increase latency as packets are not processed as quickly. + +The default behaviour of the driver previously assumed a static +InterruptThrottleRate value of 8000, providing a good fallback value for +all traffic types,but lacking in small packet performance and latency. +The hardware can handle many more small packets per second however, and +for this reason an adaptive interrupt moderation algorithm was implemented. + +Since 7.3.x, the driver has two adaptive modes (setting 1 or 3) in which +it dynamically adjusts the InterruptThrottleRate value based on the traffic +that it receives. After determining the type of incoming traffic in the last +timeframe, it will adjust the InterruptThrottleRate to an appropriate value +for that traffic. + +The algorithm classifies the incoming traffic every interval into +classes. Once the class is determined, the InterruptThrottleRate value is +adjusted to suit that traffic type the best. There are three classes defined: +"Bulk traffic", for large amounts of packets of normal size; "Low latency", +for small amounts of traffic and/or a significant percentage of small +packets; and "Lowest latency", for almost completely small packets or +minimal traffic. + +In dynamic conservative mode, the InterruptThrottleRate value is set to 4000 +for traffic that falls in class "Bulk traffic". If traffic falls in the "Low +latency" or "Lowest latency" class, the InterruptThrottleRate is increased +stepwise to 20000. This default mode is suitable for most applications. + +For situations where low latency is vital such as cluster or +grid computing, the algorithm can reduce latency even more when +InterruptThrottleRate is set to mode 1. In this mode, which operates +the same as mode 3, the InterruptThrottleRate will be increased stepwise to +70000 for traffic in class "Lowest latency". + +In simplified mode the interrupt rate is based on the ratio of TX and +RX traffic. If the bytes per second rate is approximately equal, the +interrupt rate will drop as low as 2000 interrupts per second. If the +traffic is mostly transmit or mostly receive, the interrupt rate could +be as high as 8000. + +Setting InterruptThrottleRate to 0 turns off any interrupt moderation +and may improve small packet latency, but is generally not suitable +for bulk throughput traffic. + +NOTE: InterruptThrottleRate takes precedence over the TxAbsIntDelay and + RxAbsIntDelay parameters. In other words, minimizing the receive + and/or transmit absolute delays does not force the controller to + generate more interrupts than what the Interrupt Throttle Rate + allows. + +CAUTION: If you are using the Intel(R) PRO/1000 CT Network Connection + (controller 82547), setting InterruptThrottleRate to a value + greater than 75,000, may hang (stop transmitting) adapters + under certain network conditions. If this occurs a NETDEV + WATCHDOG message is logged in the system event log. In + addition, the controller is automatically reset, restoring + the network connection. To eliminate the potential for the + hang, ensure that InterruptThrottleRate is set no greater + than 75,000 and is not set to 0. + +NOTE: When e1000 is loaded with default settings and multiple adapters + are in use simultaneously, the CPU utilization may increase non- + linearly. In order to limit the CPU utilization without impacting + the overall throughput, we recommend that you load the driver as + follows:: + + modprobe e1000 InterruptThrottleRate=3000,3000,3000 + + This sets the InterruptThrottleRate to 3000 interrupts/sec for + the first, second, and third instances of the driver. The range + of 2000 to 3000 interrupts per second works on a majority of + systems and is a good starting point, but the optimal value will + be platform-specific. If CPU utilization is not a concern, use + RX_POLLING (NAPI) and default driver settings. + +RxDescriptors +------------- +Valid Range: 48-256 for 82542 and 82543-based adapters + 48-4096 for all other supported adapters +Default Value: 256 + +This value specifies the number of receive buffer descriptors allocated +by the driver. Increasing this value allows the driver to buffer more +incoming packets, at the expense of increased system memory utilization. + +Each descriptor is 16 bytes. A receive buffer is also allocated for each +descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending +on the MTU setting. The maximum MTU size is 16110. + +NOTE: MTU designates the frame size. It only needs to be set for Jumbo + Frames. Depending on the available system resources, the request + for a higher number of receive descriptors may be denied. In this + case, use a lower number. + +RxIntDelay +---------- +Valid Range: 0-65535 (0=off) +Default Value: 0 + +This value delays the generation of receive interrupts in units of 1.024 +microseconds. Receive interrupt reduction can improve CPU efficiency if +properly tuned for specific network traffic. Increasing this value adds +extra latency to frame reception and can end up decreasing the throughput +of TCP traffic. If the system is reporting dropped receives, this value +may be set too high, causing the driver to run out of available receive +descriptors. + +CAUTION: When setting RxIntDelay to a value other than 0, adapters may + hang (stop transmitting) under certain network conditions. If + this occurs a NETDEV WATCHDOG message is logged in the system + event log. In addition, the controller is automatically reset, + restoring the network connection. To eliminate the potential + for the hang ensure that RxIntDelay is set to 0. + +RxAbsIntDelay +------------- +(This parameter is supported only on 82540, 82545 and later adapters.) +Valid Range: 0-65535 (0=off) +Default Value: 128 + +This value, in units of 1.024 microseconds, limits the delay in which a +receive interrupt is generated. Useful only if RxIntDelay is non-zero, +this value ensures that an interrupt is generated after the initial +packet is received within the set amount of time. Proper tuning, +along with RxIntDelay, may improve traffic throughput in specific network +conditions. + +Speed +----- +(This parameter is supported only on adapters with copper connections.) +Valid Settings: 0, 10, 100, 1000 +Default Value: 0 (auto-negotiate at all supported speeds) + +Speed forces the line speed to the specified value in megabits per second +(Mbps). If this parameter is not specified or is set to 0 and the link +partner is set to auto-negotiate, the board will auto-detect the correct +speed. Duplex should also be set when Speed is set to either 10 or 100. + +TxDescriptors +------------- +Valid Range: 48-256 for 82542 and 82543-based adapters + 48-4096 for all other supported adapters +Default Value: 256 + +This value is the number of transmit descriptors allocated by the driver. +Increasing this value allows the driver to queue more transmits. Each +descriptor is 16 bytes. + +NOTE: Depending on the available system resources, the request for a + higher number of transmit descriptors may be denied. In this case, + use a lower number. + +TxIntDelay +---------- +Valid Range: 0-65535 (0=off) +Default Value: 8 + +This value delays the generation of transmit interrupts in units of +1.024 microseconds. Transmit interrupt reduction can improve CPU +efficiency if properly tuned for specific network traffic. If the +system is reporting dropped transmits, this value may be set too high +causing the driver to run out of available transmit descriptors. + +TxAbsIntDelay +------------- +(This parameter is supported only on 82540, 82545 and later adapters.) +Valid Range: 0-65535 (0=off) +Default Value: 32 + +This value, in units of 1.024 microseconds, limits the delay in which a +transmit interrupt is generated. Useful only if TxIntDelay is non-zero, +this value ensures that an interrupt is generated after the initial +packet is sent on the wire within the set amount of time. Proper tuning, +along with TxIntDelay, may improve traffic throughput in specific +network conditions. + +XsumRX +------ +(This parameter is NOT supported on the 82542-based adapter.) +Valid Range: 0-1 +Default Value: 1 + +A value of '1' indicates that the driver should enable IP checksum +offload for received packets (both UDP and TCP) to the adapter hardware. + +Copybreak +--------- +Valid Range: 0-xxxxxxx (0=off) +Default Value: 256 +Usage: modprobe e1000.ko copybreak=128 + +Driver copies all packets below or equaling this size to a fresh RX +buffer before handing it up the stack. + +This parameter is different than other parameters, in that it is a +single (not 1,1,1 etc.) parameter applied to all driver instances and +it is also available during runtime at +/sys/module/e1000/parameters/copybreak + +SmartPowerDownEnable +-------------------- +Valid Range: 0-1 +Default Value: 0 (disabled) + +Allows PHY to turn off in lower power states. The user can turn off +this parameter in supported chipsets. + +Speed and Duplex Configuration +============================== + +Three keywords are used to control the speed and duplex configuration. +These keywords are Speed, Duplex, and AutoNeg. + +If the board uses a fiber interface, these keywords are ignored, and the +fiber interface board only links at 1000 Mbps full-duplex. + +For copper-based boards, the keywords interact as follows: + + The default operation is auto-negotiate. The board advertises all + supported speed and duplex combinations, and it links at the highest + common speed and duplex mode IF the link partner is set to auto-negotiate. + + If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps + is advertised (The 1000BaseT spec requires auto-negotiation.) + + If Speed = 10 or 100, then both Speed and Duplex should be set. Auto- + negotiation is disabled, and the AutoNeg parameter is ignored. Partner + SHOULD also be forced. + +The AutoNeg parameter is used when more control is required over the +auto-negotiation process. It should be used when you wish to control which +speed and duplex combinations are advertised during the auto-negotiation +process. + +The parameter may be specified as either a decimal or hexadecimal value as +determined by the bitmap below. + +Bit position 7 6 5 4 3 2 1 0 +Decimal Value 128 64 32 16 8 4 2 1 +Hex value 80 40 20 10 8 4 2 1 +Speed (Mbps) N/A N/A 1000 N/A 100 100 10 10 +Duplex Full Full Half Full Half + +Some examples of using AutoNeg: + + modprobe e1000 AutoNeg=0x01 (Restricts autonegotiation to 10 Half) + modprobe e1000 AutoNeg=1 (Same as above) + modprobe e1000 AutoNeg=0x02 (Restricts autonegotiation to 10 Full) + modprobe e1000 AutoNeg=0x03 (Restricts autonegotiation to 10 Half or 10 Full) + modprobe e1000 AutoNeg=0x04 (Restricts autonegotiation to 100 Half) + modprobe e1000 AutoNeg=0x05 (Restricts autonegotiation to 10 Half or 100 + Half) + modprobe e1000 AutoNeg=0x020 (Restricts autonegotiation to 1000 Full) + modprobe e1000 AutoNeg=32 (Same as above) + +Note that when this parameter is used, Speed and Duplex must not be specified. + +If the link partner is forced to a specific speed and duplex, then this +parameter should not be used. Instead, use the Speed and Duplex parameters +previously mentioned to force the adapter to the same speed and duplex. + +Additional Configurations +========================= + + Jumbo Frames + ------------ + Jumbo Frames support is enabled by changing the MTU to a value larger than + the default of 1500. Use the ifconfig command to increase the MTU size. + For example:: + + ifconfig eth mtu 9000 up + + This setting is not saved across reboots. It can be made permanent if + you add:: + + MTU=9000 + + to the file /etc/sysconfig/network-scripts/ifcfg-eth. This example + applies to the Red Hat distributions; other distributions may store this + setting in a different location. + + Notes: + Degradation in throughput performance may be observed in some Jumbo frames + environments. If this is observed, increasing the application's socket buffer + size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help. + See the specific application manual and /usr/src/linux*/Documentation/ + networking/ip-sysctl.txt for more details. + + - The maximum MTU setting for Jumbo Frames is 16110. This value coincides + with the maximum Jumbo Frames size of 16128. + + - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in + poor performance or loss of link. + + - Adapters based on the Intel(R) 82542 and 82573V/E controller do not + support Jumbo Frames. These correspond to the following product names: + Intel(R) PRO/1000 Gigabit Server Adapter + Intel(R) PRO/1000 PM Network Connection + + ethtool + ------- + The driver utilizes the ethtool interface for driver configuration and + diagnostics, as well as displaying statistical information. The ethtool + version 1.6 or later is required for this functionality. + + The latest release of ethtool can be found from + https://www.kernel.org/pub/software/network/ethtool/ + + Enabling Wake on LAN* (WoL) + --------------------------- + WoL is configured through the ethtool* utility. + + WoL will be enabled on the system during the next shut down or reboot. + For this driver version, in order to enable WoL, the e1000 driver must be + loaded when shutting down or rebooting the system. + +Support +======= + +For general information, go to the Intel support website at: + + http://support.intel.com + +or the Intel Wired Networking project hosted by Sourceforge at: + + http://sourceforge.net/projects/e1000 + +If an issue is identified with the released source code on the supported +kernel with a supported adapter, email the specific information related +to the issue to e1000-devel@lists.sf.net diff --git a/Documentation/networking/e1000.txt b/Documentation/networking/e1000.txt deleted file mode 100644 index 1f6ed848363d..000000000000 --- a/Documentation/networking/e1000.txt +++ /dev/null @@ -1,461 +0,0 @@ -Linux* Base Driver for Intel(R) Ethernet Network Connection -=========================================================== - -Intel Gigabit Linux driver. -Copyright(c) 1999 - 2013 Intel Corporation. - -Contents -======== - -- Identifying Your Adapter -- Command Line Parameters -- Speed and Duplex Configuration -- Additional Configurations -- Support - -Identifying Your Adapter -======================== - -For more information on how to identify your adapter, go to the Adapter & -Driver ID Guide at: - - http://support.intel.com/support/go/network/adapter/idguide.htm - -For the latest Intel network drivers for Linux, refer to the following -website. In the search field, enter your adapter name or type, or use the -networking link on the left to search for your adapter: - - http://support.intel.com/support/go/network/adapter/home.htm - -Command Line Parameters -======================= - -The default value for each parameter is generally the recommended setting, -unless otherwise noted. - -NOTES: For more information about the AutoNeg, Duplex, and Speed - parameters, see the "Speed and Duplex Configuration" section in - this document. - - For more information about the InterruptThrottleRate, - RxIntDelay, TxIntDelay, RxAbsIntDelay, and TxAbsIntDelay - parameters, see the application note at: - http://www.intel.com/design/network/applnots/ap450.htm - -AutoNeg -------- -(Supported only on adapters with copper connections) -Valid Range: 0x01-0x0F, 0x20-0x2F -Default Value: 0x2F - -This parameter is a bit-mask that specifies the speed and duplex settings -advertised by the adapter. When this parameter is used, the Speed and -Duplex parameters must not be specified. - -NOTE: Refer to the Speed and Duplex section of this readme for more - information on the AutoNeg parameter. - -Duplex ------- -(Supported only on adapters with copper connections) -Valid Range: 0-2 (0=auto-negotiate, 1=half, 2=full) -Default Value: 0 - -This defines the direction in which data is allowed to flow. Can be -either one or two-directional. If both Duplex and the link partner are -set to auto-negotiate, the board auto-detects the correct duplex. If the -link partner is forced (either full or half), Duplex defaults to half- -duplex. - -FlowControl ------------ -Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx) -Default Value: Reads flow control settings from the EEPROM - -This parameter controls the automatic generation(Tx) and response(Rx) -to Ethernet PAUSE frames. - -InterruptThrottleRate ---------------------- -(not supported on Intel(R) 82542, 82543 or 82544-based adapters) -Valid Range: 0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative, - 4=simplified balancing) -Default Value: 3 - -The driver can limit the amount of interrupts per second that the adapter -will generate for incoming packets. It does this by writing a value to the -adapter that is based on the maximum amount of interrupts that the adapter -will generate per second. - -Setting InterruptThrottleRate to a value greater or equal to 100 -will program the adapter to send out a maximum of that many interrupts -per second, even if more packets have come in. This reduces interrupt -load on the system and can lower CPU utilization under heavy load, -but will increase latency as packets are not processed as quickly. - -The default behaviour of the driver previously assumed a static -InterruptThrottleRate value of 8000, providing a good fallback value for -all traffic types,but lacking in small packet performance and latency. -The hardware can handle many more small packets per second however, and -for this reason an adaptive interrupt moderation algorithm was implemented. - -Since 7.3.x, the driver has two adaptive modes (setting 1 or 3) in which -it dynamically adjusts the InterruptThrottleRate value based on the traffic -that it receives. After determining the type of incoming traffic in the last -timeframe, it will adjust the InterruptThrottleRate to an appropriate value -for that traffic. - -The algorithm classifies the incoming traffic every interval into -classes. Once the class is determined, the InterruptThrottleRate value is -adjusted to suit that traffic type the best. There are three classes defined: -"Bulk traffic", for large amounts of packets of normal size; "Low latency", -for small amounts of traffic and/or a significant percentage of small -packets; and "Lowest latency", for almost completely small packets or -minimal traffic. - -In dynamic conservative mode, the InterruptThrottleRate value is set to 4000 -for traffic that falls in class "Bulk traffic". If traffic falls in the "Low -latency" or "Lowest latency" class, the InterruptThrottleRate is increased -stepwise to 20000. This default mode is suitable for most applications. - -For situations where low latency is vital such as cluster or -grid computing, the algorithm can reduce latency even more when -InterruptThrottleRate is set to mode 1. In this mode, which operates -the same as mode 3, the InterruptThrottleRate will be increased stepwise to -70000 for traffic in class "Lowest latency". - -In simplified mode the interrupt rate is based on the ratio of TX and -RX traffic. If the bytes per second rate is approximately equal, the -interrupt rate will drop as low as 2000 interrupts per second. If the -traffic is mostly transmit or mostly receive, the interrupt rate could -be as high as 8000. - -Setting InterruptThrottleRate to 0 turns off any interrupt moderation -and may improve small packet latency, but is generally not suitable -for bulk throughput traffic. - -NOTE: InterruptThrottleRate takes precedence over the TxAbsIntDelay and - RxAbsIntDelay parameters. In other words, minimizing the receive - and/or transmit absolute delays does not force the controller to - generate more interrupts than what the Interrupt Throttle Rate - allows. - -CAUTION: If you are using the Intel(R) PRO/1000 CT Network Connection - (controller 82547), setting InterruptThrottleRate to a value - greater than 75,000, may hang (stop transmitting) adapters - under certain network conditions. If this occurs a NETDEV - WATCHDOG message is logged in the system event log. In - addition, the controller is automatically reset, restoring - the network connection. To eliminate the potential for the - hang, ensure that InterruptThrottleRate is set no greater - than 75,000 and is not set to 0. - -NOTE: When e1000 is loaded with default settings and multiple adapters - are in use simultaneously, the CPU utilization may increase non- - linearly. In order to limit the CPU utilization without impacting - the overall throughput, we recommend that you load the driver as - follows: - - modprobe e1000 InterruptThrottleRate=3000,3000,3000 - - This sets the InterruptThrottleRate to 3000 interrupts/sec for - the first, second, and third instances of the driver. The range - of 2000 to 3000 interrupts per second works on a majority of - systems and is a good starting point, but the optimal value will - be platform-specific. If CPU utilization is not a concern, use - RX_POLLING (NAPI) and default driver settings. - -RxDescriptors -------------- -Valid Range: 80-256 for 82542 and 82543-based adapters - 80-4096 for all other supported adapters -Default Value: 256 - -This value specifies the number of receive buffer descriptors allocated -by the driver. Increasing this value allows the driver to buffer more -incoming packets, at the expense of increased system memory utilization. - -Each descriptor is 16 bytes. A receive buffer is also allocated for each -descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending -on the MTU setting. The maximum MTU size is 16110. - -NOTE: MTU designates the frame size. It only needs to be set for Jumbo - Frames. Depending on the available system resources, the request - for a higher number of receive descriptors may be denied. In this - case, use a lower number. - -RxIntDelay ----------- -Valid Range: 0-65535 (0=off) -Default Value: 0 - -This value delays the generation of receive interrupts in units of 1.024 -microseconds. Receive interrupt reduction can improve CPU efficiency if -properly tuned for specific network traffic. Increasing this value adds -extra latency to frame reception and can end up decreasing the throughput -of TCP traffic. If the system is reporting dropped receives, this value -may be set too high, causing the driver to run out of available receive -descriptors. - -CAUTION: When setting RxIntDelay to a value other than 0, adapters may - hang (stop transmitting) under certain network conditions. If - this occurs a NETDEV WATCHDOG message is logged in the system - event log. In addition, the controller is automatically reset, - restoring the network connection. To eliminate the potential - for the hang ensure that RxIntDelay is set to 0. - -RxAbsIntDelay -------------- -(This parameter is supported only on 82540, 82545 and later adapters.) -Valid Range: 0-65535 (0=off) -Default Value: 128 - -This value, in units of 1.024 microseconds, limits the delay in which a -receive interrupt is generated. Useful only if RxIntDelay is non-zero, -this value ensures that an interrupt is generated after the initial -packet is received within the set amount of time. Proper tuning, -along with RxIntDelay, may improve traffic throughput in specific network -conditions. - -Speed ------ -(This parameter is supported only on adapters with copper connections.) -Valid Settings: 0, 10, 100, 1000 -Default Value: 0 (auto-negotiate at all supported speeds) - -Speed forces the line speed to the specified value in megabits per second -(Mbps). If this parameter is not specified or is set to 0 and the link -partner is set to auto-negotiate, the board will auto-detect the correct -speed. Duplex should also be set when Speed is set to either 10 or 100. - -TxDescriptors -------------- -Valid Range: 80-256 for 82542 and 82543-based adapters - 80-4096 for all other supported adapters -Default Value: 256 - -This value is the number of transmit descriptors allocated by the driver. -Increasing this value allows the driver to queue more transmits. Each -descriptor is 16 bytes. - -NOTE: Depending on the available system resources, the request for a - higher number of transmit descriptors may be denied. In this case, - use a lower number. - -TxDescriptorStep ----------------- -Valid Range: 1 (use every Tx Descriptor) - 4 (use every 4th Tx Descriptor) - -Default Value: 1 (use every Tx Descriptor) - -On certain non-Intel architectures, it has been observed that intense TX -traffic bursts of short packets may result in an improper descriptor -writeback. If this occurs, the driver will report a "TX Timeout" and reset -the adapter, after which the transmit flow will restart, though data may -have stalled for as much as 10 seconds before it resumes. - -The improper writeback does not occur on the first descriptor in a system -memory cache-line, which is typically 32 bytes, or 4 descriptors long. - -Setting TxDescriptorStep to a value of 4 will ensure that all TX descriptors -are aligned to the start of a system memory cache line, and so this problem -will not occur. - -NOTES: Setting TxDescriptorStep to 4 effectively reduces the number of - TxDescriptors available for transmits to 1/4 of the normal allocation. - This has a possible negative performance impact, which may be - compensated for by allocating more descriptors using the TxDescriptors - module parameter. - - There are other conditions which may result in "TX Timeout", which will - not be resolved by the use of the TxDescriptorStep parameter. As the - issue addressed by this parameter has never been observed on Intel - Architecture platforms, it should not be used on Intel platforms. - -TxIntDelay ----------- -Valid Range: 0-65535 (0=off) -Default Value: 64 - -This value delays the generation of transmit interrupts in units of -1.024 microseconds. Transmit interrupt reduction can improve CPU -efficiency if properly tuned for specific network traffic. If the -system is reporting dropped transmits, this value may be set too high -causing the driver to run out of available transmit descriptors. - -TxAbsIntDelay -------------- -(This parameter is supported only on 82540, 82545 and later adapters.) -Valid Range: 0-65535 (0=off) -Default Value: 64 - -This value, in units of 1.024 microseconds, limits the delay in which a -transmit interrupt is generated. Useful only if TxIntDelay is non-zero, -this value ensures that an interrupt is generated after the initial -packet is sent on the wire within the set amount of time. Proper tuning, -along with TxIntDelay, may improve traffic throughput in specific -network conditions. - -XsumRX ------- -(This parameter is NOT supported on the 82542-based adapter.) -Valid Range: 0-1 -Default Value: 1 - -A value of '1' indicates that the driver should enable IP checksum -offload for received packets (both UDP and TCP) to the adapter hardware. - -Copybreak ---------- -Valid Range: 0-xxxxxxx (0=off) -Default Value: 256 -Usage: insmod e1000.ko copybreak=128 - -Driver copies all packets below or equaling this size to a fresh RX -buffer before handing it up the stack. - -This parameter is different than other parameters, in that it is a -single (not 1,1,1 etc.) parameter applied to all driver instances and -it is also available during runtime at -/sys/module/e1000/parameters/copybreak - -SmartPowerDownEnable --------------------- -Valid Range: 0-1 -Default Value: 0 (disabled) - -Allows PHY to turn off in lower power states. The user can turn off -this parameter in supported chipsets. - -KumeranLockLoss ---------------- -Valid Range: 0-1 -Default Value: 1 (enabled) - -This workaround skips resetting the PHY at shutdown for the initial -silicon releases of ICH8 systems. - -Speed and Duplex Configuration -============================== - -Three keywords are used to control the speed and duplex configuration. -These keywords are Speed, Duplex, and AutoNeg. - -If the board uses a fiber interface, these keywords are ignored, and the -fiber interface board only links at 1000 Mbps full-duplex. - -For copper-based boards, the keywords interact as follows: - - The default operation is auto-negotiate. The board advertises all - supported speed and duplex combinations, and it links at the highest - common speed and duplex mode IF the link partner is set to auto-negotiate. - - If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps - is advertised (The 1000BaseT spec requires auto-negotiation.) - - If Speed = 10 or 100, then both Speed and Duplex should be set. Auto- - negotiation is disabled, and the AutoNeg parameter is ignored. Partner - SHOULD also be forced. - -The AutoNeg parameter is used when more control is required over the -auto-negotiation process. It should be used when you wish to control which -speed and duplex combinations are advertised during the auto-negotiation -process. - -The parameter may be specified as either a decimal or hexadecimal value as -determined by the bitmap below. - -Bit position 7 6 5 4 3 2 1 0 -Decimal Value 128 64 32 16 8 4 2 1 -Hex value 80 40 20 10 8 4 2 1 -Speed (Mbps) N/A N/A 1000 N/A 100 100 10 10 -Duplex Full Full Half Full Half - -Some examples of using AutoNeg: - - modprobe e1000 AutoNeg=0x01 (Restricts autonegotiation to 10 Half) - modprobe e1000 AutoNeg=1 (Same as above) - modprobe e1000 AutoNeg=0x02 (Restricts autonegotiation to 10 Full) - modprobe e1000 AutoNeg=0x03 (Restricts autonegotiation to 10 Half or 10 Full) - modprobe e1000 AutoNeg=0x04 (Restricts autonegotiation to 100 Half) - modprobe e1000 AutoNeg=0x05 (Restricts autonegotiation to 10 Half or 100 - Half) - modprobe e1000 AutoNeg=0x020 (Restricts autonegotiation to 1000 Full) - modprobe e1000 AutoNeg=32 (Same as above) - -Note that when this parameter is used, Speed and Duplex must not be specified. - -If the link partner is forced to a specific speed and duplex, then this -parameter should not be used. Instead, use the Speed and Duplex parameters -previously mentioned to force the adapter to the same speed and duplex. - -Additional Configurations -========================= - - Jumbo Frames - ------------ - Jumbo Frames support is enabled by changing the MTU to a value larger than - the default of 1500. Use the ifconfig command to increase the MTU size. - For example: - - ifconfig eth mtu 9000 up - - This setting is not saved across reboots. It can be made permanent if - you add: - - MTU=9000 - - to the file /etc/sysconfig/network-scripts/ifcfg-eth. This example - applies to the Red Hat distributions; other distributions may store this - setting in a different location. - - Notes: - Degradation in throughput performance may be observed in some Jumbo frames - environments. If this is observed, increasing the application's socket buffer - size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help. - See the specific application manual and /usr/src/linux*/Documentation/ - networking/ip-sysctl.txt for more details. - - - The maximum MTU setting for Jumbo Frames is 16110. This value coincides - with the maximum Jumbo Frames size of 16128. - - - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in - poor performance or loss of link. - - - Adapters based on the Intel(R) 82542 and 82573V/E controller do not - support Jumbo Frames. These correspond to the following product names: - Intel(R) PRO/1000 Gigabit Server Adapter - Intel(R) PRO/1000 PM Network Connection - - ethtool - ------- - The driver utilizes the ethtool interface for driver configuration and - diagnostics, as well as displaying statistical information. The ethtool - version 1.6 or later is required for this functionality. - - The latest release of ethtool can be found from - https://www.kernel.org/pub/software/network/ethtool/ - - Enabling Wake on LAN* (WoL) - --------------------------- - WoL is configured through the ethtool* utility. - - WoL will be enabled on the system during the next shut down or reboot. - For this driver version, in order to enable WoL, the e1000 driver must be - loaded when shutting down or rebooting the system. - -Support -======= - -For general information, go to the Intel support website at: - - http://support.intel.com - -or the Intel Wired Networking project hosted by Sourceforge at: - - http://sourceforge.net/projects/e1000 - -If an issue is identified with the released source code on the supported -kernel with a supported adapter, email the specific information related -to the issue to e1000-devel@lists.sf.net diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index d11a62977edd..fec8588a588e 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -11,6 +11,7 @@ Contents: can dpaa2/index e100 + e1000 kapi z8530book msg_zerocopy diff --git a/MAINTAINERS b/MAINTAINERS index d68981ca9896..32472fbf4d6e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7090,7 +7090,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git S: Supported F: Documentation/networking/e100.rst -F: Documentation/networking/e1000.txt +F: Documentation/networking/e1000.rst F: Documentation/networking/e1000e.txt F: Documentation/networking/igb.txt F: Documentation/networking/igbvf.txt -- cgit v1.2.3-58-ga151