diff options
297 files changed, 10604 insertions, 4904 deletions
diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt index 41b3f3f864e8..5d88f37480b6 100644 --- a/Documentation/devicetree/bindings/net/ethernet.txt +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -25,7 +25,11 @@ The following properties are common to the Ethernet controllers: flow control thresholds. - tx-fifo-depth: the size of the controller's transmit fifo in bytes. This is used for components that can have configurable fifo sizes. +- managed: string, specifies the PHY management type. Supported values are: + "auto", "in-band-status". "auto" is the default, it usess MDIO for + management if fixed-link is not specified. Child nodes of the Ethernet controller are typically the individual PHY devices connected via the MDIO bus (sometimes the MDIO bus controller is separate). They are described in the phy.txt file in this same directory. +For non-MDIO PHY management see fixed-link.txt. diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 5fae7704daab..1a5ab21bcca5 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1435,6 +1435,11 @@ mtu - INTEGER Default Maximum Transfer Unit Default: 1280 (IPv6 required minimum) +ip_nonlocal_bind - BOOLEAN + If set, allows processes to bind() to non-local IPv6 addresses, + which can be quite useful - but may break some applications. + Default: 0 + router_probe_interval - INTEGER Minimum interval (in seconds) between Router Probing described in RFC4191. @@ -1455,6 +1460,13 @@ router_solicitations - INTEGER routers are present. Default: 3 +use_oif_addrs_only - BOOLEAN + When enabled, the candidate source addresses for destinations + routed via this interface are restricted to the set of addresses + configured on this interface (vis. RFC 6724, section 4). + + Default: false + use_tempaddr - INTEGER Preference for Privacy Extensions (RFC3041). <= 0 : disable Privacy Extensions diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt index e655e2453c98..5fddefa69baf 100644 --- a/Documentation/networking/stmmac.txt +++ b/Documentation/networking/stmmac.txt @@ -139,8 +139,6 @@ struct plat_stmmacenet_data { void (*free)(struct platform_device *pdev, void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); - void *custom_cfg; - void *custom_data; void *bsp_priv; }; @@ -186,8 +184,6 @@ Where: which will be stored in bsp_priv, and then passed to init and exit callbacks. init/exit callbacks should not use or modify platform data. - o custom_cfg/custom_data: this is a custom configuration that can be passed - while initializing the resources. o bsp_priv: another private pointer. For MDIO bus The we have: diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index c5d7ade10ff2..9825f32a8634 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -279,8 +279,18 @@ and unknown unicast packets to all ports in domain, if allowed by port's current STP state. The switch driver, knowing which ports are within which vlan L2 domain, can program the switch device for flooding. The packet should also be sent to the port netdev for processing by the bridge driver. The -bridge should not reflood the packet to the same ports the device flooded. -XXX: the mechanism to avoid duplicate flood packets is being discuseed. +bridge should not reflood the packet to the same ports the device flooded, +otherwise there will be duplicate packets on the wire. + +To avoid duplicate packets, the device/driver should mark a packet as already +forwarded using skb->offload_fwd_mark. The same mark is set on the device +ports in the domain using dev->offload_fwd_mark. If the skb->offload_fwd_mark +is non-zero and matches the forwarding egress port's dev->skb_mark, the kernel +will drop the skb right before transmit on the egress port, with the +understanding that the device already forwarded the packet on same egress port. +The driver can use switchdev_port_fwd_mark_set() to set a globally unique mark +for port's dev->offload_fwd_mark, based on the port's parent ID (switch ID) and +a group ifindex. It is possible for the switch device to not handle flooding and push the packets up to the bridge driver for flooding. This is not ideal as the number diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 5f0922613f1a..a977339fbe0a 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -359,6 +359,13 @@ the requested fine-grained filtering for incoming packets is not supported, the driver may time stamp more than just the requested types of packets. +Drivers are free to use a more permissive configuration than the requested +configuration. It is expected that drivers should only implement directly the +most generic mode that can be supported. For example if the hardware can +support HWTSTAMP_FILTER_V2_EVENT, then it should generally always upscale +HWTSTAMP_FILTER_V2_L2_SYNC_MESSAGE, and so forth, as HWTSTAMP_FILTER_V2_EVENT +is more generic (and more useful to applications). + A driver which supports hardware time stamping shall update the struct with the actual, possibly more permissive configuration. If the requested packets cannot be time stamped, then nothing should be diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index fee782acc2ee..79c731e8d178 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -973,6 +973,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i */ const u64 func = (u64)__bpf_call_base + imm; + if (bpf_helper_changes_skb_data((void *)func)) + /* TODO reload skb->data, hlen */ + return -1; + REG_SET_SEEN(BPF_REG_5); jit->seen |= SEEN_FUNC; /* lg %w1,<d(imm)>(%l) */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 579a8fd74be0..6c335a8fc086 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -315,6 +315,26 @@ static void emit_bpf_tail_call(u8 **pprog) *pprog = prog; } + +static void emit_load_skb_data_hlen(u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + + /* r9d = skb->len - skb->data_len (headlen) + * r10 = skb->data + */ + /* mov %r9d, off32(%rdi) */ + EMIT3_off32(0x44, 0x8b, 0x8f, offsetof(struct sk_buff, len)); + + /* sub %r9d, off32(%rdi) */ + EMIT3_off32(0x44, 0x2b, 0x8f, offsetof(struct sk_buff, data_len)); + + /* mov %r10, off32(%rdi) */ + EMIT3_off32(0x4c, 0x8b, 0x97, offsetof(struct sk_buff, data)); + *pprog = prog; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int oldproglen, struct jit_context *ctx) { @@ -329,36 +349,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, emit_prologue(&prog); - if (seen_ld_abs) { - /* r9d : skb->len - skb->data_len (headlen) - * r10 : skb->data - */ - if (is_imm8(offsetof(struct sk_buff, len))) - /* mov %r9d, off8(%rdi) */ - EMIT4(0x44, 0x8b, 0x4f, - offsetof(struct sk_buff, len)); - else - /* mov %r9d, off32(%rdi) */ - EMIT3_off32(0x44, 0x8b, 0x8f, - offsetof(struct sk_buff, len)); - - if (is_imm8(offsetof(struct sk_buff, data_len))) - /* sub %r9d, off8(%rdi) */ - EMIT4(0x44, 0x2b, 0x4f, - offsetof(struct sk_buff, data_len)); - else - EMIT3_off32(0x44, 0x2b, 0x8f, - offsetof(struct sk_buff, data_len)); - - if (is_imm8(offsetof(struct sk_buff, data))) - /* mov %r10, off8(%rdi) */ - EMIT4(0x4c, 0x8b, 0x57, - offsetof(struct sk_buff, data)); - else - /* mov %r10, off32(%rdi) */ - EMIT3_off32(0x4c, 0x8b, 0x97, - offsetof(struct sk_buff, data)); - } + if (seen_ld_abs) + emit_load_skb_data_hlen(&prog); for (i = 0; i < insn_cnt; i++, insn++) { const s32 imm32 = insn->imm; @@ -367,6 +359,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 b1 = 0, b2 = 0, b3 = 0; s64 jmp_offset; u8 jmp_cond; + bool reload_skb_data; int ilen; u8 *func; @@ -818,12 +811,18 @@ xadd: if (is_imm8(insn->off)) func = (u8 *) __bpf_call_base + imm32; jmp_offset = func - (image + addrs[i]); if (seen_ld_abs) { - EMIT2(0x41, 0x52); /* push %r10 */ - EMIT2(0x41, 0x51); /* push %r9 */ - /* need to adjust jmp offset, since - * pop %r9, pop %r10 take 4 bytes after call insn - */ - jmp_offset += 4; + reload_skb_data = bpf_helper_changes_skb_data(func); + if (reload_skb_data) { + EMIT1(0x57); /* push %rdi */ + jmp_offset += 22; /* pop, mov, sub, mov */ + } else { + EMIT2(0x41, 0x52); /* push %r10 */ + EMIT2(0x41, 0x51); /* push %r9 */ + /* need to adjust jmp offset, since + * pop %r9, pop %r10 take 4 bytes after call insn + */ + jmp_offset += 4; + } } if (!imm32 || !is_simm32(jmp_offset)) { pr_err("unsupported bpf func %d addr %p image %p\n", @@ -832,8 +831,13 @@ xadd: if (is_imm8(insn->off)) } EMIT1_off32(0xE8, jmp_offset); if (seen_ld_abs) { - EMIT2(0x41, 0x59); /* pop %r9 */ - EMIT2(0x41, 0x5A); /* pop %r10 */ + if (reload_skb_data) { + EMIT1(0x5F); /* pop %rdi */ + emit_load_skb_data_hlen(&prog); + } else { + EMIT2(0x41, 0x59); /* pop %r9 */ + EMIT2(0x41, 0x5A); /* pop %r10 */ + } } break; diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 7fde4d5c2b28..3c45358844eb 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1870,8 +1870,6 @@ static void ad_marker_info_received(struct bond_marker *marker_info, static void ad_marker_response_received(struct bond_marker *marker, struct port *port) { - marker = NULL; - port = NULL; /* DO NOTHING, SINCE WE DECIDED NOT TO IMPLEMENT THIS FEATURE FOR NOW */ } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e1ccefce9a9d..0c627b4733ca 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3779,7 +3779,6 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) struct slave *slave; struct list_head *iter; struct bond_up_slave *new_arr, *old_arr; - int slaves_in_agg; int agg_id = 0; int ret = 0; @@ -3810,7 +3809,6 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) } goto out; } - slaves_in_agg = ad_info.ports; agg_id = ad_info.aggregator_id; } bond_for_each_slave(bond, slave, iter) { diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index 7ad0a4d8e475..4c483d937481 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -46,13 +46,13 @@ config NET_DSA_MV88E6171 ethernet switches chips. config NET_DSA_MV88E6352 - tristate "Marvell 88E6172/88E6176/88E6352 ethernet switch chip support" + tristate "Marvell 88E6172/6176/6320/6321/6352 ethernet switch chip support" depends on NET_DSA select NET_DSA_MV88E6XXX select NET_DSA_TAG_EDSA ---help--- - This enables support for the Marvell 88E6172, 88E6176 and 88E6352 - ethernet switch chips. + This enables support for the Marvell 88E6172, 88E6176, 88E6320, + 88E6321 and 88E6352 ethernet switch chips. config NET_DSA_BCM_SF2 tristate "Broadcom Starfighter 2 Ethernet switch support" diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 079897b3a955..289e20443d83 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -901,15 +901,11 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, struct fixed_phy_status *status) { struct bcm_sf2_priv *priv = ds_to_priv(ds); - u32 duplex, pause, speed; + u32 duplex, pause; u32 reg; duplex = core_readl(priv, CORE_DUPSTS); pause = core_readl(priv, CORE_PAUSESTS); - speed = core_readl(priv, CORE_SPDSTS); - - speed >>= (port * SPDSTS_SHIFT); - speed &= SPDSTS_MASK; status->link = 0; @@ -944,18 +940,6 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, reg &= ~LINK_STS; core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(port)); - switch (speed) { - case SPDSTS_10: - status->speed = SPEED_10; - break; - case SPDSTS_100: - status->speed = SPEED_100; - break; - case SPDSTS_1000: - status->speed = SPEED_1000; - break; - } - if ((pause & (1 << port)) && (pause & (1 << (port + PAUSESTS_TX_PAUSE_SHIFT)))) { status->asym_pause = 1; diff --git a/drivers/net/dsa/mv88e6352.c b/drivers/net/dsa/mv88e6352.c index 632815c10a40..cfece5ae9d5f 100644 --- a/drivers/net/dsa/mv88e6352.c +++ b/drivers/net/dsa/mv88e6352.c @@ -36,6 +36,18 @@ static char *mv88e6352_probe(struct device *host_dev, int sw_addr) return "Marvell 88E6172"; if ((ret & 0xfff0) == PORT_SWITCH_ID_6176) return "Marvell 88E6176"; + if (ret == PORT_SWITCH_ID_6320_A1) + return "Marvell 88E6320 (A1)"; + if (ret == PORT_SWITCH_ID_6320_A2) + return "Marvell 88e6320 (A2)"; + if ((ret & 0xfff0) == PORT_SWITCH_ID_6320) + return "Marvell 88E6320"; + if (ret == PORT_SWITCH_ID_6321_A1) + return "Marvell 88E6321 (A1)"; + if (ret == PORT_SWITCH_ID_6321_A2) + return "Marvell 88e6321 (A2)"; + if ((ret & 0xfff0) == PORT_SWITCH_ID_6321) + return "Marvell 88E6321"; if (ret == PORT_SWITCH_ID_6352_A0) return "Marvell 88E6352 (A0)"; if (ret == PORT_SWITCH_ID_6352_A1) @@ -84,11 +96,12 @@ static int mv88e6352_setup_global(struct dsa_switch *ds) static int mv88e6352_get_temp(struct dsa_switch *ds, int *temp) { + int phy = mv88e6xxx_6320_family(ds) ? 3 : 0; int ret; *temp = 0; - ret = mv88e6xxx_phy_page_read(ds, 0, 6, 27); + ret = mv88e6xxx_phy_page_read(ds, phy, 6, 27); if (ret < 0) return ret; @@ -99,11 +112,12 @@ static int mv88e6352_get_temp(struct dsa_switch *ds, int *temp) static int mv88e6352_get_temp_limit(struct dsa_switch *ds, int *temp) { + int phy = mv88e6xxx_6320_family(ds) ? 3 : 0; int ret; *temp = 0; - ret = mv88e6xxx_phy_page_read(ds, 0, 6, 26); + ret = mv88e6xxx_phy_page_read(ds, phy, 6, 26); if (ret < 0) return ret; @@ -114,23 +128,25 @@ static int mv88e6352_get_temp_limit(struct dsa_switch *ds, int *temp) static int mv88e6352_set_temp_limit(struct dsa_switch *ds, int temp) { + int phy = mv88e6xxx_6320_family(ds) ? 3 : 0; int ret; - ret = mv88e6xxx_phy_page_read(ds, 0, 6, 26); + ret = mv88e6xxx_phy_page_read(ds, phy, 6, 26); if (ret < 0) return ret; temp = clamp_val(DIV_ROUND_CLOSEST(temp, 5) + 5, 0, 0x1f); - return mv88e6xxx_phy_page_write(ds, 0, 6, 26, + return mv88e6xxx_phy_page_write(ds, phy, 6, 26, (ret & 0xe0ff) | (temp << 8)); } static int mv88e6352_get_temp_alarm(struct dsa_switch *ds, bool *alarm) { + int phy = mv88e6xxx_6320_family(ds) ? 3 : 0; int ret; *alarm = false; - ret = mv88e6xxx_phy_page_read(ds, 0, 6, 26); + ret = mv88e6xxx_phy_page_read(ds, phy, 6, 26); if (ret < 0) return ret; @@ -394,5 +410,8 @@ struct dsa_switch_driver mv88e6352_switch_driver = { .fdb_getnext = mv88e6xxx_port_fdb_getnext, }; -MODULE_ALIAS("platform:mv88e6352"); MODULE_ALIAS("platform:mv88e6172"); +MODULE_ALIAS("platform:mv88e6176"); +MODULE_ALIAS("platform:mv88e6320"); +MODULE_ALIAS("platform:mv88e6321"); +MODULE_ALIAS("platform:mv88e6352"); diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 561342466076..5158375b7abd 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -517,6 +517,18 @@ static bool mv88e6xxx_6185_family(struct dsa_switch *ds) return false; } +bool mv88e6xxx_6320_family(struct dsa_switch *ds) +{ + struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + + switch (ps->id) { + case PORT_SWITCH_ID_6320: + case PORT_SWITCH_ID_6321: + return true; + } + return false; +} + static bool mv88e6xxx_6351_family(struct dsa_switch *ds) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); @@ -565,7 +577,7 @@ static int _mv88e6xxx_stats_snapshot(struct dsa_switch *ds, int port) { int ret; - if (mv88e6xxx_6352_family(ds)) + if (mv88e6xxx_6320_family(ds) || mv88e6xxx_6352_family(ds)) port = (port + 1) << 5; /* Snapshot the hardware statistics counters for this port. */ @@ -1377,7 +1389,7 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) || mv88e6xxx_6185_family(ds) || mv88e6xxx_6095_family(ds) || - mv88e6xxx_6065_family(ds)) { + mv88e6xxx_6065_family(ds) || mv88e6xxx_6320_family(ds)) { /* MAC Forcing register: don't force link, speed, * duplex or flow control state to any particular * values on physical ports, but force the CPU port @@ -1423,7 +1435,7 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) || mv88e6xxx_6095_family(ds) || mv88e6xxx_6065_family(ds) || - mv88e6xxx_6185_family(ds)) + mv88e6xxx_6185_family(ds) || mv88e6xxx_6320_family(ds)) reg = PORT_CONTROL_IGMP_MLD_SNOOP | PORT_CONTROL_USE_TAG | PORT_CONTROL_USE_IP | PORT_CONTROL_STATE_FORWARDING; @@ -1431,7 +1443,8 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) if (mv88e6xxx_6095_family(ds) || mv88e6xxx_6185_family(ds)) reg |= PORT_CONTROL_DSA_TAG; if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || - mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds)) { + mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) || + mv88e6xxx_6320_family(ds)) { if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA) reg |= PORT_CONTROL_FRAME_ETHER_TYPE_DSA; else @@ -1441,14 +1454,15 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) || mv88e6xxx_6095_family(ds) || mv88e6xxx_6065_family(ds) || - mv88e6xxx_6185_family(ds)) { + mv88e6xxx_6185_family(ds) || mv88e6xxx_6320_family(ds)) { if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA) reg |= PORT_CONTROL_EGRESS_ADD_TAG; } } if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) || - mv88e6xxx_6095_family(ds) || mv88e6xxx_6065_family(ds)) { + mv88e6xxx_6095_family(ds) || mv88e6xxx_6065_family(ds) || + mv88e6xxx_6320_family(ds)) { if (ds->dsa_port_mask & (1 << port)) reg |= PORT_CONTROL_FRAME_MODE_DSA; if (port == dsa_upstream_port(ds)) @@ -1473,11 +1487,11 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) reg = 0; if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) || - mv88e6xxx_6095_family(ds)) + mv88e6xxx_6095_family(ds) || mv88e6xxx_6320_family(ds)) reg = PORT_CONTROL_2_MAP_DA; if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || - mv88e6xxx_6165_family(ds)) + mv88e6xxx_6165_family(ds) || mv88e6xxx_6320_family(ds)) reg |= PORT_CONTROL_2_JUMBO_10240; if (mv88e6xxx_6095_family(ds) || mv88e6xxx_6185_family(ds)) { @@ -1514,7 +1528,8 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) goto abort; if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || - mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds)) { + mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) || + mv88e6xxx_6320_family(ds)) { /* Do not limit the period of time that this port can * be paused for by the remote end or the period of * time that this port can pause the remote end. @@ -1564,7 +1579,8 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) || - mv88e6xxx_6185_family(ds) || mv88e6xxx_6095_family(ds)) { + mv88e6xxx_6185_family(ds) || mv88e6xxx_6095_family(ds) || + mv88e6xxx_6320_family(ds)) { /* Rate Control: disable ingress rate limiting. */ ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), PORT_RATE_CONTROL, 0x0001); @@ -1976,7 +1992,8 @@ int mv88e6xxx_setup_global(struct dsa_switch *ds) (i << GLOBAL2_TRUNK_MAPPING_ID_SHIFT)); if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || - mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds)) { + mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) || + mv88e6xxx_6320_family(ds)) { /* Send all frames with destination addresses matching * 01:80:c2:00:00:2x to the CPU port. */ @@ -1995,7 +2012,8 @@ int mv88e6xxx_setup_global(struct dsa_switch *ds) if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) || - mv88e6xxx_6185_family(ds) || mv88e6xxx_6095_family(ds)) { + mv88e6xxx_6185_family(ds) || mv88e6xxx_6095_family(ds) || + mv88e6xxx_6320_family(ds)) { /* Disable ingress rate limiting by resetting all * ingress rate limit registers to their initial * state. diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index a650b2656de9..64786cb89a93 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -89,7 +89,12 @@ #define PORT_SWITCH_ID_6182 0x1a60 #define PORT_SWITCH_ID_6185 0x1a70 #define PORT_SWITCH_ID_6240 0x2400 -#define PORT_SWITCH_ID_6320 0x1250 +#define PORT_SWITCH_ID_6320 0x1150 +#define PORT_SWITCH_ID_6320_A1 0x1151 +#define PORT_SWITCH_ID_6320_A2 0x1152 +#define PORT_SWITCH_ID_6321 0x3100 +#define PORT_SWITCH_ID_6321_A1 0x3101 +#define PORT_SWITCH_ID_6321_A2 0x3102 #define PORT_SWITCH_ID_6350 0x3710 #define PORT_SWITCH_ID_6351 0x3750 #define PORT_SWITCH_ID_6352 0x3520 @@ -410,6 +415,7 @@ int mv88e6xxx_port_fdb_getnext(struct dsa_switch *ds, int port, int mv88e6xxx_phy_page_read(struct dsa_switch *ds, int port, int page, int reg); int mv88e6xxx_phy_page_write(struct dsa_switch *ds, int port, int page, int reg, int val); +bool mv88e6xxx_6320_family(struct dsa_switch *ds); extern struct dsa_switch_driver mv88e6131_switch_driver; extern struct dsa_switch_driver mv88e6123_61_65_switch_driver; extern struct dsa_switch_driver mv88e6352_switch_driver; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index cd4ae76bbff2..a1f9785f0209 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1,6 +1,8 @@ -/* bnx2x.h: Broadcom Everest network driver. +/* bnx2x.h: QLogic Everest network driver. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -30,7 +32,7 @@ * (you will need to reboot afterwards) */ /* #define BNX2X_STOP_ON_ERROR */ -#define DRV_MODULE_VERSION "1.710.51-0" +#define DRV_MODULE_VERSION "1.712.30-0" #define DRV_MODULE_RELDATE "2014/02/10" #define BNX2X_BC_VER 0x040200 @@ -1422,6 +1424,7 @@ enum { SUB_MF_MODE_UNKNOWN = 0, SUB_MF_MODE_UFP, SUB_MF_MODE_NPAR1_DOT_5, + SUB_MF_MODE_BD, }; struct bnx2x { @@ -1636,6 +1639,8 @@ struct bnx2x { u8 mf_sub_mode; #define IS_MF_UFP(bp) (IS_MF_SD(bp) && \ bp->mf_sub_mode == SUB_MF_MODE_UFP) +#define IS_MF_BD(bp) (IS_MF_SD(bp) && \ + bp->mf_sub_mode == SUB_MF_MODE_BD) u8 wol; @@ -2577,6 +2582,8 @@ void bnx2x_set_local_cmng(struct bnx2x *bp); void bnx2x_update_mng_version(struct bnx2x *bp); +void bnx2x_update_mfw_dump(struct bnx2x *bp); + #define MCPR_SCRATCH_BASE(bp) \ (CHIP_IS_E1x(bp) ? MCP_REG_MCPR_SCRATCH : MCP_A_REG_MCPR_SCRATCH) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index a90d7364334f..6088c86c4872 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1,6 +1,8 @@ -/* bnx2x_cmn.c: Broadcom Everest network driver. +/* bnx2x_cmn.c: QLogic Everest network driver. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -2103,9 +2105,14 @@ int bnx2x_rss(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj, if (rss_obj->udp_rss_v6) __set_bit(BNX2X_RSS_IPV6_UDP, ¶ms.rss_flags); - if (!CHIP_IS_E1x(bp)) + if (!CHIP_IS_E1x(bp)) { + /* valid only for TUNN_MODE_VXLAN tunnel mode */ + __set_bit(BNX2X_RSS_IPV4_VXLAN, ¶ms.rss_flags); + __set_bit(BNX2X_RSS_IPV6_VXLAN, ¶ms.rss_flags); + /* valid only for TUNN_MODE_GRE tunnel mode */ - __set_bit(BNX2X_RSS_GRE_INNER_HDRS, ¶ms.rss_flags); + __set_bit(BNX2X_RSS_TUNN_INNER_HDRS, ¶ms.rss_flags); + } } else { __set_bit(BNX2X_RSS_MODE_DISABLED, ¶ms.rss_flags); } @@ -2510,6 +2517,20 @@ static void bnx2x_bz_fp(struct bnx2x *bp, int index) fp->mode = TPA_MODE_DISABLED; } +void bnx2x_set_os_driver_state(struct bnx2x *bp, u32 state) +{ + u32 cur; + + if (!IS_MF_BD(bp) || !SHMEM2_HAS(bp, os_driver_state) || IS_VF(bp)) + return; + + cur = SHMEM2_RD(bp, os_driver_state[BP_FW_MB_IDX(bp)]); + DP(NETIF_MSG_IFUP, "Driver state %08x-->%08x\n", + cur, state); + + SHMEM2_WR(bp, os_driver_state[BP_FW_MB_IDX(bp)], state); +} + int bnx2x_load_cnic(struct bnx2x *bp) { int i, rc, port = BP_PORT(bp); @@ -2873,6 +2894,8 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) /* mark driver is loaded in shmem2 */ u32 val; val = SHMEM2_RD(bp, drv_capabilities_flag[BP_FW_MB_IDX(bp)]); + val &= ~DRV_FLAGS_MTU_MASK; + val |= (bp->dev->mtu << DRV_FLAGS_MTU_SHIFT); SHMEM2_WR(bp, drv_capabilities_flag[BP_FW_MB_IDX(bp)], val | DRV_FLAGS_CAPABILITIES_LOADED_SUPPORTED | DRV_FLAGS_CAPABILITIES_LOADED_L2); @@ -2885,10 +2908,17 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) return -EBUSY; } + /* Update driver data for On-Chip MFW dump. */ + if (IS_PF(bp)) + bnx2x_update_mfw_dump(bp); + /* If PMF - send ADMIN DCBX msg to MFW to initiate DCBX FSM */ if (bp->port.pmf && (bp->state != BNX2X_STATE_DIAG)) bnx2x_dcbx_init(bp, false); + if (!IS_MF_SD_STORAGE_PERSONALITY_ONLY(bp)) + bnx2x_set_os_driver_state(bp, OS_DRIVER_STATE_ACTIVE); + DP(NETIF_MSG_IFUP, "Ending successfully NIC load\n"); return 0; @@ -2956,6 +2986,9 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link) DP(NETIF_MSG_IFUP, "Starting NIC unload\n"); + if (!IS_MF_SD_STORAGE_PERSONALITY_ONLY(bp)) + bnx2x_set_os_driver_state(bp, OS_DRIVER_STATE_DISABLED); + /* mark driver is unloaded in shmem2 */ if (IS_PF(bp) && SHMEM2_HAS(bp, drv_capabilities_flag)) { u32 val; @@ -3677,7 +3710,7 @@ static void bnx2x_update_pbds_gso_enc(struct sk_buff *skb, pbd2->fw_ip_hdr_to_payload_w = hlen_w - ((sizeof(struct ipv6hdr)) >> 1); pbd_e2->data.tunnel_data.flags |= - ETH_TUNNEL_DATA_IP_HDR_TYPE_OUTER; + ETH_TUNNEL_DATA_IPV6_OUTER; } pbd2->tcp_send_seq = bswab32(inner_tcp_hdr(skb)->seq); @@ -4184,6 +4217,41 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } +void bnx2x_get_c2s_mapping(struct bnx2x *bp, u8 *c2s_map, u8 *c2s_default) +{ + int mfw_vn = BP_FW_MB_IDX(bp); + u32 tmp; + + /* If the shmem shouldn't affect configuration, reflect */ + if (!IS_MF_BD(bp)) { + int i; + + for (i = 0; i < BNX2X_MAX_PRIORITY; i++) + c2s_map[i] = i; + *c2s_default = 0; + + return; + } + + tmp = SHMEM2_RD(bp, c2s_pcp_map_lower[mfw_vn]); + tmp = (__force u32)be32_to_cpu((__force __be32)tmp); + c2s_map[0] = tmp & 0xff; + c2s_map[1] = (tmp >> 8) & 0xff; + c2s_map[2] = (tmp >> 16) & 0xff; + c2s_map[3] = (tmp >> 24) & 0xff; + + tmp = SHMEM2_RD(bp, c2s_pcp_map_upper[mfw_vn]); + tmp = (__force u32)be32_to_cpu((__force __be32)tmp); + c2s_map[4] = tmp & 0xff; + c2s_map[5] = (tmp >> 8) & 0xff; + c2s_map[6] = (tmp >> 16) & 0xff; + c2s_map[7] = (tmp >> 24) & 0xff; + + tmp = SHMEM2_RD(bp, c2s_pcp_map_default[mfw_vn]); + tmp = (__force u32)be32_to_cpu((__force __be32)tmp); + *c2s_default = (tmp >> (8 * mfw_vn)) & 0xff; +} + /** * bnx2x_setup_tc - routine to configure net_device for multi tc * @@ -4194,8 +4262,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) */ int bnx2x_setup_tc(struct net_device *dev, u8 num_tc) { - int cos, prio, count, offset; struct bnx2x *bp = netdev_priv(dev); + u8 c2s_map[BNX2X_MAX_PRIORITY], c2s_def; + int cos, prio, count, offset; /* setup tc must be called under rtnl lock */ ASSERT_RTNL(); @@ -4219,12 +4288,16 @@ int bnx2x_setup_tc(struct net_device *dev, u8 num_tc) return -EINVAL; } + bnx2x_get_c2s_mapping(bp, c2s_map, &c2s_def); + /* configure priority to traffic class mapping */ for (prio = 0; prio < BNX2X_MAX_PRIORITY; prio++) { - netdev_set_prio_tc_map(dev, prio, bp->prio_to_cos[prio]); + int outer_prio = c2s_map[prio]; + + netdev_set_prio_tc_map(dev, prio, bp->prio_to_cos[outer_prio]); DP(BNX2X_MSG_SP | NETIF_MSG_IFUP, "mapping priority %d to tc %d\n", - prio, bp->prio_to_cos[prio]); + outer_prio, bp->prio_to_cos[outer_prio]); } /* Use this configuration to differentiate tc0 from other COSes @@ -4278,6 +4351,9 @@ int bnx2x_change_mac_addr(struct net_device *dev, void *p) if (netif_running(dev)) rc = bnx2x_set_eth_mac(bp, true); + if (IS_PF(bp) && SHMEM2_HAS(bp, curr_cfg)) + SHMEM2_WR(bp, curr_cfg, CURR_CFG_MET_OS); + return rc; } @@ -4831,6 +4907,9 @@ int bnx2x_change_mtu(struct net_device *dev, int new_mtu) */ dev->mtu = new_mtu; + if (IS_PF(bp) && SHMEM2_HAS(bp, curr_cfg)) + SHMEM2_WR(bp, curr_cfg, CURR_CFG_MET_OS); + return bnx2x_reload_if_running(dev); } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 03b7404d5b9b..821346ce50eb 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -1,6 +1,8 @@ -/* bnx2x_cmn.h: Broadcom Everest network driver. +/* bnx2x_cmn.h: QLogic Everest network driver. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -620,6 +622,14 @@ int bnx2x_set_features(struct net_device *dev, netdev_features_t features); */ void bnx2x_tx_timeout(struct net_device *dev); +/** bnx2x_get_c2s_mapping - read inner-to-outer vlan configuration + * c2s_map should have BNX2X_MAX_PRIORITY entries. + * @bp: driver handle + * @c2s_map: should have BNX2X_MAX_PRIORITY entries for mapping + * @c2s_default: entry for non-tagged configuration + */ +void bnx2x_get_c2s_mapping(struct bnx2x *bp, u8 *c2s_map, u8 *c2s_default); + /*********************** Inlines **********************************/ /*********************** Fast path ********************************/ static inline void bnx2x_update_fpsb_idx(struct bnx2x_fastpath *fp) @@ -931,14 +941,33 @@ static inline int bnx2x_func_start(struct bnx2x *bp) start_params->mf_mode = bp->mf_mode; start_params->sd_vlan_tag = bp->mf_ov; + /* Configure Ethertype for BD mode */ + if (IS_MF_BD(bp)) { + DP(NETIF_MSG_IFUP, "Configuring ethertype 0x88a8 for BD\n"); + start_params->sd_vlan_eth_type = ETH_P_8021AD; + REG_WR(bp, PRS_REG_VLAN_TYPE_0, ETH_P_8021AD); + REG_WR(bp, PBF_REG_VLAN_TYPE_0, ETH_P_8021AD); + REG_WR(bp, NIG_REG_LLH_E1HOV_TYPE_1, ETH_P_8021AD); + + bnx2x_get_c2s_mapping(bp, start_params->c2s_pri, + &start_params->c2s_pri_default); + start_params->c2s_pri_valid = 1; + + DP(NETIF_MSG_IFUP, + "Inner-to-Outer priority: %02x %02x %02x %02x %02x %02x %02x %02x [Default %02x]\n", + start_params->c2s_pri[0], start_params->c2s_pri[1], + start_params->c2s_pri[2], start_params->c2s_pri[3], + start_params->c2s_pri[4], start_params->c2s_pri[5], + start_params->c2s_pri[6], start_params->c2s_pri[7], + start_params->c2s_pri_default); + } + if (CHIP_IS_E2(bp) || CHIP_IS_E3(bp)) start_params->network_cos_mode = STATIC_COS; else /* CHIP_IS_E1X */ start_params->network_cos_mode = FW_WRR; - start_params->tunnel_mode = TUNN_MODE_GRE; - start_params->gre_tunnel_type = IPGRE_TUNNEL; - start_params->inner_gre_rss_en = 1; + start_params->inner_rss = 1; if (IS_MF_UFP(bp) && BNX2X_IS_MF_SD_PROTOCOL_FCOE(bp)) { start_params->class_fail_ethtype = ETH_P_FIP; @@ -1339,4 +1368,11 @@ void bnx2x_squeeze_objects(struct bnx2x *bp); void bnx2x_schedule_sp_rtnl(struct bnx2x*, enum sp_rtnl_flag, u32 verbose); +/** + * bnx2x_set_os_driver_state - write driver state for management FW usage + * + * @bp: driver handle + * @state: OS_DRIVER_STATE_* value reflecting current driver state + */ +void bnx2x_set_os_driver_state(struct bnx2x *bp, u32 state); #endif /* BNX2X_CMN_H */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c index 6e4294ed1fc9..7ccf6684e0a3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c @@ -1,15 +1,17 @@ -/* bnx2x_dcb.c: Broadcom Everest network driver. +/* bnx2x_dcb.c: QLogic Everest network driver. * * Copyright 2009-2013 Broadcom Corporation + * Copyright 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and QLogic execute a separate written software license * agreement governing use of this software, this software is licensed to you * under the terms of the GNU General Public License version 2, available * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). * * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written + * software in any way with any other QLogic software provided under a + * license other than the GPL, without QLogic's express prior written * consent. * * Maintained by: Ariel Elior <ariel.elior@qlogic.com> @@ -1850,6 +1852,8 @@ static void bnx2x_dcbx_fw_struct(struct bnx2x *bp, if (bp->dcbx_port_params.ets.cos_params[cos]. pri_bitmask & pri_bit) tt2cos[pri].cos = cos; + + pfc_fw_cfg->dcb_outer_pri[pri] = ttp[pri]; } /* we never want the FW to add a 0 vlan tag */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h index c6939ecb02c5..9a9517c0f703 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h @@ -1,15 +1,17 @@ -/* bnx2x_dcb.h: Broadcom Everest network driver. +/* bnx2x_dcb.h: QLogic Everest network driver. * * Copyright 2009-2013 Broadcom Corporation + * Copyright 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and QLogic execute a separate written software license * agreement governing use of this software, this software is licensed to you * under the terms of the GNU General Public License version 2, available * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). * * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written + * software in any way with any other QLogic software provided under a + * license other than the GPL, without QLogic's express prior written * consent. * * Maintained by: Ariel Elior <ariel.elior@qlogic.com> diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dump.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dump.h index 741aa130c19f..eccfa13b0f2d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dump.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dump.h @@ -1,15 +1,17 @@ -/* bnx2x_dump.h: Broadcom Everest network driver. +/* bnx2x_dump.h: QLogic Everest network driver. * * Copyright (c) 2012-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and QLogic execute a separate written software license * agreement governing use of this software, this software is licensed to you * under the terms of the GNU General Public License version 2, available * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). * * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written + * software in any way with any other QLogic software provided under a + * license other than the GPL, without QLogic's express prior written * consent. */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 76b9052a961c..6b2050a198df 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1,6 +1,8 @@ -/* bnx2x_ethtool.c: Broadcom Everest network driver. +/* bnx2x_ethtool.c: QLogic Everest network driver. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -1129,6 +1131,9 @@ static int bnx2x_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) } else bp->wol = 0; + if (SHMEM2_HAS(bp, curr_cfg)) + SHMEM2_WR(bp, curr_cfg, CURR_CFG_MET_OS); + return 0; } @@ -3562,17 +3567,8 @@ static int bnx2x_get_ts_info(struct net_device *dev, info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ); + (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); info->tx_types = (1 << HWTSTAMP_TX_OFF)|(1 << HWTSTAMP_TX_ON); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h index 7636e3c18771..226ab29f4cb6 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h @@ -1,6 +1,8 @@ -/* bnx2x_fw_defs.h: Broadcom Everest network driver. +/* bnx2x_fw_defs.h: Qlogic Everest network driver. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -372,7 +374,7 @@ #define MAX_COS_NUMBER 4 #define MAX_TRAFFIC_TYPES 8 #define MAX_PFC_PRIORITIES 8 - +#define MAX_VLAN_PRIORITIES 8 /* used by array traffic_type_to_priority[] to mark traffic type \ that is not mapped to priority*/ #define LLFC_TRAFFIC_TYPE_TO_PRIORITY_UNMAPPED 0xFF diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_file_hdr.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_file_hdr.h index 8aafd9b5d6a2..9e3b5a1e9f4f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_file_hdr.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_file_hdr.h @@ -1,6 +1,8 @@ /* bnx2x_fw_file_hdr.h: FW binary file header structure. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index 058bc7328220..08a08fa49caa 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -1,6 +1,8 @@ -/* bnx2x_hsi.h: Broadcom Everest network driver. +/* bnx2x_hsi.h: Qlogic Everest network driver. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -729,6 +731,7 @@ struct port_hw_cfg { /* port 0: 0x12c port 1: 0x2bc */ #define PORT_HW_CFG_XGXS_EXT_PHY2_TYPE_BCM8722 0x00000f00 #define PORT_HW_CFG_XGXS_EXT_PHY2_TYPE_BCM54616 0x00001000 #define PORT_HW_CFG_XGXS_EXT_PHY2_TYPE_BCM84834 0x00001100 + #define PORT_HW_CFG_XGXS_EXT_PHY2_TYPE_BCM84858 0x00001200 #define PORT_HW_CFG_XGXS_EXT_PHY2_TYPE_FAILURE 0x0000fd00 #define PORT_HW_CFG_XGXS_EXT_PHY2_TYPE_NOT_CONN 0x0000ff00 @@ -786,6 +789,7 @@ struct port_hw_cfg { /* port 0: 0x12c port 1: 0x2bc */ #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8722 0x00000f00 #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54616 0x00001000 #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834 0x00001100 + #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858 0x00001200 #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_DIRECT_WC 0x0000fc00 #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_FAILURE 0x0000fd00 #define PORT_HW_CFG_XGXS_EXT_PHY_TYPE_NOT_CONN 0x0000ff00 @@ -864,6 +868,7 @@ struct shared_feat_cfg { /* NVRAM Offset */ #define SHARED_FEAT_CFG_FORCE_SF_MODE_SPIO4 0x00000200 #define SHARED_FEAT_CFG_FORCE_SF_MODE_SWITCH_INDEPT 0x00000300 #define SHARED_FEAT_CFG_FORCE_SF_MODE_AFEX_MODE 0x00000400 + #define SHARED_FEAT_CFG_FORCE_SF_MODE_BD_MODE 0x00000500 #define SHARED_FEAT_CFG_FORCE_SF_MODE_UFP_MODE 0x00000600 #define SHARED_FEAT_CFG_FORCE_SF_MODE_EXTENDED_MODE 0x00000700 @@ -2064,6 +2069,26 @@ struct ncsi_oem_fcoe_features { #define FCOE_FEATURES4_FEATURE_SETTINGS_OFFSET 0 }; +enum curr_cfg_method_e { + CURR_CFG_MET_NONE = 0, /* default config */ + CURR_CFG_MET_OS = 1, + CURR_CFG_MET_VENDOR_SPEC = 2,/* e.g. Option ROM, NPAR, O/S Cfg Utils */ +}; + +struct mdump_driver_info { + u32 epoc; + u32 drv_ver; + u32 fw_ver; + + u32 valid_dump; + #define FIRST_DUMP_VALID (1 << 0) + #define SECOND_DUMP_VALID (1 << 1) + + u32 flags; + #define ENABLE_ALL_TRIGGERS (0x7fffffff) + #define TRIGGER_MDUMP_ONCE (1 << 31) +}; + struct ncsi_oem_data { u32 driver_version[4]; struct ncsi_oem_fcoe_features ncsi_oem_fcoe_features; @@ -2187,6 +2212,8 @@ struct shmem2_region { #define DRV_FLAGS_CAPABILITIES_LOADED_L2 0x00000002 #define DRV_FLAGS_CAPABILITIES_LOADED_FCOE 0x00000004 #define DRV_FLAGS_CAPABILITIES_LOADED_ISCSI 0x00000008 +#define DRV_FLAGS_MTU_MASK 0xffff0000 +#define DRV_FLAGS_MTU_SHIFT 16 u32 extended_dev_info_shared_cfg_size; @@ -2251,6 +2278,7 @@ struct shmem2_region { u32 reserved4; /* Offset 0x150 */ u32 link_attr_sync[PORT_MAX]; /* Offset 0x154 */ #define LINK_ATTR_SYNC_KR2_ENABLE 0x00000001 + #define LINK_ATTR_84858 0x00000002 #define LINK_SFP_EEPROM_COMP_CODE_MASK 0x0000ff00 #define LINK_SFP_EEPROM_COMP_CODE_SHIFT 8 #define LINK_SFP_EEPROM_COMP_CODE_SR 0x00001000 @@ -2268,6 +2296,74 @@ struct shmem2_region { /* We use indication for each PF (0..3) */ #define MFW_DRV_IND_READ_DONE_OFFSET(_pf_) (1 << (_pf_)) + union { /* For various OEMs */ /* Offset 0x1a0 */ + u8 storage_boot_prog[E2_FUNC_MAX]; + #define STORAGE_BOOT_PROG_MASK 0x000000FF + #define STORAGE_BOOT_PROG_NONE 0x00000000 + #define STORAGE_BOOT_PROG_ISCSI_IP_ACQUIRED 0x00000002 + #define STORAGE_BOOT_PROG_FCOE_FABRIC_LOGIN_SUCCESS 0x00000002 + #define STORAGE_BOOT_PROG_TARGET_FOUND 0x00000004 + #define STORAGE_BOOT_PROG_ISCSI_CHAP_SUCCESS 0x00000008 + #define STORAGE_BOOT_PROG_FCOE_LUN_FOUND 0x00000008 + #define STORAGE_BOOT_PROG_LOGGED_INTO_TGT 0x00000010 + #define STORAGE_BOOT_PROG_IMG_DOWNLOADED 0x00000020 + #define STORAGE_BOOT_PROG_OS_HANDOFF 0x00000040 + #define STORAGE_BOOT_PROG_COMPLETED 0x00000080 + + u32 oem_i2c_data_addr; + }; + + /* 9 entires for the C2S PCP map for each inner VLAN PCP + 1 default */ + /* For PCP values 0-3 use the map lower */ + /* 0xFF000000 - PCP 0, 0x00FF0000 - PCP 1, + * 0x0000FF00 - PCP 2, 0x000000FF PCP 3 + */ + u32 c2s_pcp_map_lower[E2_FUNC_MAX]; /* 0x1a4 */ + + /* For PCP values 4-7 use the map upper */ + /* 0xFF000000 - PCP 4, 0x00FF0000 - PCP 5, + * 0x0000FF00 - PCP 6, 0x000000FF PCP 7 + */ + u32 c2s_pcp_map_upper[E2_FUNC_MAX]; /* 0x1b4 */ + + /* For PCP default value get the MSB byte of the map default */ + u32 c2s_pcp_map_default[E2_FUNC_MAX]; /* 0x1c4 */ + + /* FC_NPIV table offset in NVRAM */ + u32 fc_npiv_nvram_tbl_addr[PORT_MAX]; /* 0x1d4 */ + + /* Shows last method that changed configuration of this device */ + enum curr_cfg_method_e curr_cfg; /* 0x1dc */ + + /* Storm FW version, shold be kept in the format 0xMMmmbbdd: + * MM - Major, mm - Minor, bb - Build ,dd - Drop + */ + u32 netproc_fw_ver; /* 0x1e0 */ + + /* Option ROM SMASH CLP version */ + u32 clp_ver; /* 0x1e4 */ + + u32 pcie_bus_num; /* 0x1e8 */ + + u32 sriov_switch_mode; /* 0x1ec */ + #define SRIOV_SWITCH_MODE_NONE 0x0 + #define SRIOV_SWITCH_MODE_VEB 0x1 + #define SRIOV_SWITCH_MODE_VEPA 0x2 + + u8 rsrv2[E2_FUNC_MAX]; /* 0x1f0 */ + + u32 img_inv_table_addr; /* Address to INV_TABLE_P */ /* 0x1f4 */ + + u32 mtu_size[E2_FUNC_MAX]; /* 0x1f8 */ + + u32 os_driver_state[E2_FUNC_MAX]; /* 0x208 */ + #define OS_DRIVER_STATE_NOT_LOADED 0 /* not installed */ + #define OS_DRIVER_STATE_LOADING 1 /* transition state */ + #define OS_DRIVER_STATE_DISABLED 2 /* installed but disabled */ + #define OS_DRIVER_STATE_ACTIVE 3 /* installed and active */ + + /* mini dump driver info */ + struct mdump_driver_info drv_info; /* 0x218 */ }; @@ -2898,8 +2994,8 @@ struct afex_stats { }; #define BCM_5710_FW_MAJOR_VERSION 7 -#define BCM_5710_FW_MINOR_VERSION 10 -#define BCM_5710_FW_REVISION_VERSION 51 +#define BCM_5710_FW_MINOR_VERSION 12 +#define BCM_5710_FW_REVISION_VERSION 30 #define BCM_5710_FW_ENGINEERING_VERSION 0 #define BCM_5710_FW_COMPILE_FLAGS 1 @@ -3901,7 +3997,11 @@ struct eth_fast_path_rx_cqe { __le16 len_on_bd; struct parsing_flags pars_flags; union eth_sgl_or_raw_data sgl_or_raw_data; - __le32 reserved1[7]; + u8 tunn_type; + u8 tunn_inner_hdrs_offset; + __le16 reserved1; + __le32 tunn_tenant_id; + __le32 padding[5]; u32 marker; }; @@ -4012,8 +4112,8 @@ struct eth_tunnel_data { __le16 pseudo_csum; u8 ip_hdr_start_inner_w; u8 flags; -#define ETH_TUNNEL_DATA_IP_HDR_TYPE_OUTER (0x1<<0) -#define ETH_TUNNEL_DATA_IP_HDR_TYPE_OUTER_SHIFT 0 +#define ETH_TUNNEL_DATA_IPV6_OUTER (0x1<<0) +#define ETH_TUNNEL_DATA_IPV6_OUTER_SHIFT 0 #define ETH_TUNNEL_DATA_RESERVED (0x7F<<1) #define ETH_TUNNEL_DATA_RESERVED_SHIFT 1 }; @@ -4120,16 +4220,12 @@ struct eth_rss_update_ramrod_data { #define ETH_RSS_UPDATE_RAMROD_DATA_IPV6_UDP_CAPABILITY_SHIFT 6 #define ETH_RSS_UPDATE_RAMROD_DATA_IPV6_VXLAN_CAPABILITY (0x1<<7) #define ETH_RSS_UPDATE_RAMROD_DATA_IPV6_VXLAN_CAPABILITY_SHIFT 7 -#define ETH_RSS_UPDATE_RAMROD_DATA_EN_5_TUPLE_CAPABILITY (0x1<<8) -#define ETH_RSS_UPDATE_RAMROD_DATA_EN_5_TUPLE_CAPABILITY_SHIFT 8 -#define ETH_RSS_UPDATE_RAMROD_DATA_NVGRE_KEY_ENTROPY_CAPABILITY (0x1<<9) -#define ETH_RSS_UPDATE_RAMROD_DATA_NVGRE_KEY_ENTROPY_CAPABILITY_SHIFT 9 -#define ETH_RSS_UPDATE_RAMROD_DATA_GRE_INNER_HDRS_CAPABILITY (0x1<<10) -#define ETH_RSS_UPDATE_RAMROD_DATA_GRE_INNER_HDRS_CAPABILITY_SHIFT 10 -#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY (0x1<<11) -#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY_SHIFT 11 -#define ETH_RSS_UPDATE_RAMROD_DATA_RESERVED (0xF<<12) -#define ETH_RSS_UPDATE_RAMROD_DATA_RESERVED_SHIFT 12 +#define ETH_RSS_UPDATE_RAMROD_DATA_TUNN_INNER_HDRS_CAPABILITY (0x1<<8) +#define ETH_RSS_UPDATE_RAMROD_DATA_TUNN_INNER_HDRS_CAPABILITY_SHIFT 8 +#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY (0x1<<9) +#define ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY_SHIFT 9 +#define ETH_RSS_UPDATE_RAMROD_DATA_RESERVED (0x3F<<10) +#define ETH_RSS_UPDATE_RAMROD_DATA_RESERVED_SHIFT 10 u8 rss_result_mask; u8 reserved3; __le16 reserved4; @@ -4314,6 +4410,18 @@ enum eth_tunnel_non_lso_csum_location { MAX_ETH_TUNNEL_NON_LSO_CSUM_LOCATION }; +enum eth_tunn_type { + TUNN_TYPE_NONE, + TUNN_TYPE_VXLAN, + TUNN_TYPE_L2_GRE, + TUNN_TYPE_IPV4_GRE, + TUNN_TYPE_IPV6_GRE, + TUNN_TYPE_L2_GENEVE, + TUNN_TYPE_IPV4_GENEVE, + TUNN_TYPE_IPV6_GENEVE, + MAX_ETH_TUNN_TYPE +}; + /* * Tx regular BD structure */ @@ -4758,6 +4866,9 @@ struct afex_vif_list_ramrod_data { __le16 reserved1; }; +struct c2s_pri_trans_table_entry { + u8 val[MAX_VLAN_PRIORITIES]; +}; /* * cfc delete event data @@ -5246,6 +5357,7 @@ struct flow_control_configuration { u8 dont_add_pri_0_en; u8 reserved1; __le32 reserved2; + u8 dcb_outer_pri[MAX_TRAFFIC_TYPES]; }; @@ -5260,18 +5372,25 @@ struct function_start_data { u8 path_id; u8 network_cos_mode; u8 dmae_cmd_id; - u8 tunnel_mode; - u8 gre_tunnel_type; - u8 tunn_clss_en; - u8 inner_gre_rss_en; - u8 sd_accept_mf_clss_fail; + u8 no_added_tags; + __le16 reserved0; + __le32 reserved1; + u8 inner_clss_vxlan; + u8 inner_clss_l2gre; + u8 inner_clss_l2geneve; + u8 inner_rss; __le16 vxlan_dst_port; + __le16 geneve_dst_port; + u8 sd_accept_mf_clss_fail; + u8 sd_accept_mf_clss_fail_match_ethtype; __le16 sd_accept_mf_clss_fail_ethtype; __le16 sd_vlan_eth_type; u8 sd_vlan_force_pri_flg; u8 sd_vlan_force_pri_val; - u8 sd_accept_mf_clss_fail_match_ethtype; - u8 no_added_tags; + u8 c2s_pri_tt_valid; + u8 c2s_pri_default; + u8 reserved2[6]; + struct c2s_pri_trans_table_entry c2s_pri_trans_table; }; struct function_update_data { @@ -5289,11 +5408,12 @@ struct function_update_data { u8 tx_switch_suspend; u8 echo; u8 update_tunn_cfg_flg; - u8 tunnel_mode; - u8 gre_tunnel_type; - u8 tunn_clss_en; - u8 inner_gre_rss_en; + u8 inner_clss_vxlan; + u8 inner_clss_l2gre; + u8 inner_clss_l2geneve; + u8 inner_rss; __le16 vxlan_dst_port; + __le16 geneve_dst_port; u8 sd_vlan_force_pri_change_flg; u8 sd_vlan_force_pri_flg; u8 sd_vlan_force_pri_val; @@ -5302,6 +5422,8 @@ struct function_update_data { u8 reserved1; __le16 sd_vlan_tag; __le16 sd_vlan_eth_type; + __le16 reserved0; + __le32 reserved2; }; /* @@ -5330,15 +5452,6 @@ struct fw_version { #define __FW_VERSION_RESERVED_SHIFT 4 }; - -/* GRE Tunnel Mode */ -enum gre_tunnel_type { - NVGRE_TUNNEL, - L2GRE_TUNNEL, - IPGRE_TUNNEL, - MAX_GRE_TUNNEL_TYPE -}; - /* * Dynamic Host-Coalescing - Driver(host) counters */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h index d6e1975b7b69..46ee2c01f4c5 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h @@ -1,7 +1,9 @@ -/* bnx2x_init.h: Broadcom Everest network driver. +/* bnx2x_init.h: Qlogic Everest network driver. * Structures and macroes needed during the initialization. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h index 5669ed2e87d0..1835d2e451c0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h @@ -1,8 +1,10 @@ -/* bnx2x_init_ops.h: Broadcom Everest network driver. +/* bnx2x_init_ops.h: Qlogic Everest network driver. * Static functions needed during the initialization. * This file is "included" in bnx2x_main.c. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index a0b03c27e0a3..d946bba43726 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -1,13 +1,15 @@ /* Copyright 2008-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and QLogic execute a separate written software license * agreement governing use of this software, this software is licensed to you * under the terms of the GNU General Public License version 2, available - * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). + * at http://www.gnu.org/licenses/gpl-2.0.html (the "GPL"). * * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written + * software in any way with any other Qlogic software provided under a + * license other than the GPL, without Qlogic's express prior written * consent. * * Written by Yaniv Rosner @@ -9652,6 +9654,13 @@ static void bnx2x_8727_link_reset(struct bnx2x_phy *phy, /******************************************************************/ /* BCM8481/BCM84823/BCM84833 PHY SECTION */ /******************************************************************/ +static int bnx2x_is_8483x_8485x(struct bnx2x_phy *phy) +{ + return ((phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) || + (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834) || + (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858)); +} + static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy, struct bnx2x *bp, u8 port) @@ -9666,8 +9675,7 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy, }; u16 fw_ver1; - if ((phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) || - (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834)) { + if (bnx2x_is_8483x_8485x(phy)) { bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, 0x400f, &fw_ver1); bnx2x_save_spirom_version(bp, port, fw_ver1 & 0xfff, phy->ver_addr); @@ -9749,8 +9757,7 @@ static void bnx2x_848xx_set_led(struct bnx2x *bp, bnx2x_cl45_write(bp, phy, reg_set[i].devad, reg_set[i].reg, reg_set[i].val); - if ((phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) || - (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834)) + if (bnx2x_is_8483x_8485x(phy)) offset = MDIO_PMA_REG_84833_CTL_LED_CTL_1; else offset = MDIO_PMA_REG_84823_CTL_LED_CTL_1; @@ -9768,8 +9775,7 @@ static void bnx2x_848xx_specific_func(struct bnx2x_phy *phy, struct bnx2x *bp = params->bp; switch (action) { case PHY_INIT: - if ((phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) && - (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834)) { + if (!bnx2x_is_8483x_8485x(phy)) { /* Save spirom version */ bnx2x_save_848xx_spirom_version(phy, bp, params->port); } @@ -9901,8 +9907,7 @@ static int bnx2x_848xx_cmn_config_init(struct bnx2x_phy *phy, /* Always write this if this is not 84833/4. * For 84833/4, write it only when it's a forced speed. */ - if (((phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) && - (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834)) || + if (!bnx2x_is_8483x_8485x(phy) || ((autoneg_val & (1<<12)) == 0)) bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, @@ -9949,8 +9954,86 @@ static int bnx2x_8481_config_init(struct bnx2x_phy *phy, return bnx2x_848xx_cmn_config_init(phy, params, vars); } -#define PHY84833_CMDHDLR_WAIT 300 -#define PHY84833_CMDHDLR_MAX_ARGS 5 +#define PHY848xx_CMDHDLR_WAIT 300 +#define PHY848xx_CMDHDLR_MAX_ARGS 5 + +static int bnx2x_84858_cmd_hdlr(struct bnx2x_phy *phy, + struct link_params *params, + u16 fw_cmd, + u16 cmd_args[], int argc) +{ + int idx; + u16 val; + struct bnx2x *bp = params->bp; + + /* Step 1: Poll the STATUS register to see whether the previous command + * is in progress or the system is busy (CMD_IN_PROGRESS or + * SYSTEM_BUSY). If previous command is in progress or system is busy, + * check again until the previous command finishes execution and the + * system is available for taking command + */ + + for (idx = 0; idx < PHY848xx_CMDHDLR_WAIT; idx++) { + bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, + MDIO_848xx_CMD_HDLR_STATUS, &val); + if ((val != PHY84858_STATUS_CMD_IN_PROGRESS) && + (val != PHY84858_STATUS_CMD_SYSTEM_BUSY)) + break; + usleep_range(1000, 2000); + } + if (idx >= PHY848xx_CMDHDLR_WAIT) { + DP(NETIF_MSG_LINK, "FW cmd: FW not ready.\n"); + return -EINVAL; + } + + /* Step2: If any parameters are required for the function, write them + * to the required DATA registers + */ + + for (idx = 0; idx < argc; idx++) { + bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, + MDIO_848xx_CMD_HDLR_DATA1 + idx, + cmd_args[idx]); + } + + /* Step3: When the firmware is ready for commands, write the 'Command + * code' to the CMD register + */ + bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, + MDIO_848xx_CMD_HDLR_COMMAND, fw_cmd); + + /* Step4: Once the command has been written, poll the STATUS register + * to check whether the command has completed (CMD_COMPLETED_PASS/ + * CMD_FOR_CMDS or CMD_COMPLETED_ERROR). + */ + + for (idx = 0; idx < PHY848xx_CMDHDLR_WAIT; idx++) { + bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, + MDIO_848xx_CMD_HDLR_STATUS, &val); + if ((val == PHY84858_STATUS_CMD_COMPLETE_PASS) || + (val == PHY84858_STATUS_CMD_COMPLETE_ERROR)) + break; + usleep_range(1000, 2000); + } + if ((idx >= PHY848xx_CMDHDLR_WAIT) || + (val == PHY84858_STATUS_CMD_COMPLETE_ERROR)) { + DP(NETIF_MSG_LINK, "FW cmd failed.\n"); + return -EINVAL; + } + /* Step5: Once the command has completed, read the specficied DATA + * registers for any saved results for the command, if applicable + */ + + /* Gather returning data */ + for (idx = 0; idx < argc; idx++) { + bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, + MDIO_848xx_CMD_HDLR_DATA1 + idx, + &cmd_args[idx]); + } + + return 0; +} + static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy, struct link_params *params, u16 fw_cmd, u16 cmd_args[], int argc) @@ -9960,16 +10043,16 @@ static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy, struct bnx2x *bp = params->bp; /* Write CMD_OPEN_OVERRIDE to STATUS reg */ bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, - MDIO_84833_CMD_HDLR_STATUS, + MDIO_848xx_CMD_HDLR_STATUS, PHY84833_STATUS_CMD_OPEN_OVERRIDE); - for (idx = 0; idx < PHY84833_CMDHDLR_WAIT; idx++) { + for (idx = 0; idx < PHY848xx_CMDHDLR_WAIT; idx++) { bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, - MDIO_84833_CMD_HDLR_STATUS, &val); + MDIO_848xx_CMD_HDLR_STATUS, &val); if (val == PHY84833_STATUS_CMD_OPEN_FOR_CMDS) break; usleep_range(1000, 2000); } - if (idx >= PHY84833_CMDHDLR_WAIT) { + if (idx >= PHY848xx_CMDHDLR_WAIT) { DP(NETIF_MSG_LINK, "FW cmd: FW not ready.\n"); return -EINVAL; } @@ -9977,42 +10060,62 @@ static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy, /* Prepare argument(s) and issue command */ for (idx = 0; idx < argc; idx++) { bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, - MDIO_84833_CMD_HDLR_DATA1 + idx, + MDIO_848xx_CMD_HDLR_DATA1 + idx, cmd_args[idx]); } bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, - MDIO_84833_CMD_HDLR_COMMAND, fw_cmd); - for (idx = 0; idx < PHY84833_CMDHDLR_WAIT; idx++) { + MDIO_848xx_CMD_HDLR_COMMAND, fw_cmd); + for (idx = 0; idx < PHY848xx_CMDHDLR_WAIT; idx++) { bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, - MDIO_84833_CMD_HDLR_STATUS, &val); + MDIO_848xx_CMD_HDLR_STATUS, &val); if ((val == PHY84833_STATUS_CMD_COMPLETE_PASS) || - (val == PHY84833_STATUS_CMD_COMPLETE_ERROR)) + (val == PHY84833_STATUS_CMD_COMPLETE_ERROR)) break; usleep_range(1000, 2000); } - if ((idx >= PHY84833_CMDHDLR_WAIT) || - (val == PHY84833_STATUS_CMD_COMPLETE_ERROR)) { + if ((idx >= PHY848xx_CMDHDLR_WAIT) || + (val == PHY84833_STATUS_CMD_COMPLETE_ERROR)) { DP(NETIF_MSG_LINK, "FW cmd failed.\n"); return -EINVAL; } /* Gather returning data */ for (idx = 0; idx < argc; idx++) { bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, - MDIO_84833_CMD_HDLR_DATA1 + idx, + MDIO_848xx_CMD_HDLR_DATA1 + idx, &cmd_args[idx]); } bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, - MDIO_84833_CMD_HDLR_STATUS, + MDIO_848xx_CMD_HDLR_STATUS, PHY84833_STATUS_CMD_CLEAR_COMPLETE); return 0; } -static int bnx2x_84833_pair_swap_cfg(struct bnx2x_phy *phy, - struct link_params *params, - struct link_vars *vars) +static int bnx2x_848xx_cmd_hdlr(struct bnx2x_phy *phy, + struct link_params *params, + u16 fw_cmd, + u16 cmd_args[], int argc) +{ + struct bnx2x *bp = params->bp; + + if ((phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) || + (REG_RD(bp, params->shmem2_base + + offsetof(struct shmem2_region, + link_attr_sync[params->port])) & + LINK_ATTR_84858)) { + return bnx2x_84858_cmd_hdlr(phy, params, fw_cmd, cmd_args, + argc); + } else { + return bnx2x_84833_cmd_hdlr(phy, params, fw_cmd, cmd_args, + argc); + } +} + +static int bnx2x_848xx_pair_swap_cfg(struct bnx2x_phy *phy, + struct link_params *params, + struct link_vars *vars) { u32 pair_swap; - u16 data[PHY84833_CMDHDLR_MAX_ARGS]; + u16 data[PHY848xx_CMDHDLR_MAX_ARGS]; int status; struct bnx2x *bp = params->bp; @@ -10028,8 +10131,9 @@ static int bnx2x_84833_pair_swap_cfg(struct bnx2x_phy *phy, /* Only the second argument is used for this command */ data[1] = (u16)pair_swap; - status = bnx2x_84833_cmd_hdlr(phy, params, - PHY84833_CMD_SET_PAIR_SWAP, data, PHY84833_CMDHDLR_MAX_ARGS); + status = bnx2x_848xx_cmd_hdlr(phy, params, + PHY848xx_CMD_SET_PAIR_SWAP, data, + PHY848xx_CMDHDLR_MAX_ARGS); if (status == 0) DP(NETIF_MSG_LINK, "Pairswap OK, val=0x%x\n", data[1]); @@ -10118,8 +10222,8 @@ static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "Don't Advertise 10GBase-T EEE\n"); /* Prevent Phy from working in EEE and advertising it */ - rc = bnx2x_84833_cmd_hdlr(phy, params, - PHY84833_CMD_SET_EEE_MODE, &cmd_args, 1); + rc = bnx2x_848xx_cmd_hdlr(phy, params, + PHY848xx_CMD_SET_EEE_MODE, &cmd_args, 1); if (rc) { DP(NETIF_MSG_LINK, "EEE disable failed.\n"); return rc; @@ -10136,8 +10240,8 @@ static int bnx2x_8483x_enable_eee(struct bnx2x_phy *phy, struct bnx2x *bp = params->bp; u16 cmd_args = 1; - rc = bnx2x_84833_cmd_hdlr(phy, params, - PHY84833_CMD_SET_EEE_MODE, &cmd_args, 1); + rc = bnx2x_848xx_cmd_hdlr(phy, params, + PHY848xx_CMD_SET_EEE_MODE, &cmd_args, 1); if (rc) { DP(NETIF_MSG_LINK, "EEE enable failed.\n"); return rc; @@ -10155,7 +10259,7 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy, u8 port, initialize = 1; u16 val; u32 actual_phy_selection; - u16 cmd_args[PHY84833_CMDHDLR_MAX_ARGS]; + u16 cmd_args[PHY848xx_CMDHDLR_MAX_ARGS]; int rc = 0; usleep_range(1000, 2000); @@ -10180,8 +10284,7 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy, /* Wait for GPHY to come out of reset */ msleep(50); - if ((phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) && - (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834)) { + if (!bnx2x_is_8483x_8485x(phy)) { /* BCM84823 requires that XGXS links up first @ 10G for normal * behavior. */ @@ -10192,7 +10295,19 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy, bnx2x_program_serdes(¶ms->phy[INT_PHY], params, vars); vars->line_speed = temp; } + /* Check if this is actually BCM84858 */ + if (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) { + u16 hw_rev; + bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, + MDIO_AN_REG_848xx_ID_MSB, &hw_rev); + if (hw_rev == BCM84858_PHY_ID) { + params->link_attr_sync |= LINK_ATTR_84858; + bnx2x_update_link_attr(params, params->link_attr_sync); + } + } + + /* Set dual-media configuration according to configuration */ bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, MDIO_CTL_REG_84823_MEDIA, &val); val &= ~(MDIO_CTL_REG_84823_MEDIA_MAC_MASK | @@ -10237,18 +10352,17 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "Multi_phy config = 0x%x, Media control = 0x%x\n", params->multi_phy_config, val); - if ((phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) || - (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834)) { - bnx2x_84833_pair_swap_cfg(phy, params, vars); + if (bnx2x_is_8483x_8485x(phy)) { + bnx2x_848xx_pair_swap_cfg(phy, params, vars); /* Keep AutogrEEEn disabled. */ cmd_args[0] = 0x0; cmd_args[1] = 0x0; cmd_args[2] = PHY84833_CONSTANT_LATENCY + 1; cmd_args[3] = PHY84833_CONSTANT_LATENCY; - rc = bnx2x_84833_cmd_hdlr(phy, params, - PHY84833_CMD_SET_EEE_MODE, cmd_args, - PHY84833_CMDHDLR_MAX_ARGS); + rc = bnx2x_848xx_cmd_hdlr(phy, params, + PHY848xx_CMD_SET_EEE_MODE, cmd_args, + PHY848xx_CMDHDLR_MAX_ARGS); if (rc) DP(NETIF_MSG_LINK, "Cfg AutogrEEEn failed.\n"); } @@ -10302,8 +10416,7 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy, vars->eee_status &= ~SHMEM_EEE_SUPPORTED_MASK; } - if ((phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) || - (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834)) { + if (bnx2x_is_8483x_8485x(phy)) { /* Bring PHY out of super isolate mode as the final step. */ bnx2x_cl45_read_and_write(bp, phy, MDIO_CTL_DEVAD, @@ -10435,8 +10548,7 @@ static u8 bnx2x_848xx_read_status(struct bnx2x_phy *phy, LINK_STATUS_LINK_PARTNER_10GXFD_CAPABLE; /* Determine if EEE was negotiated */ - if ((phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) || - (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834)) + if (bnx2x_is_8483x_8485x(phy)) bnx2x_eee_an_resolve(phy, params, vars); } @@ -11842,6 +11954,40 @@ static const struct bnx2x_phy phy_84834 = { .phy_specific_func = (phy_specific_func_t)bnx2x_848xx_specific_func }; +static const struct bnx2x_phy phy_84858 = { + .type = PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858, + .addr = 0xff, + .def_md_devad = 0, + .flags = FLAGS_FAN_FAILURE_DET_REQ | + FLAGS_REARM_LATCH_SIGNAL, + .rx_preemphasis = {0xffff, 0xffff, 0xffff, 0xffff}, + .tx_preemphasis = {0xffff, 0xffff, 0xffff, 0xffff}, + .mdio_ctrl = 0, + .supported = (SUPPORTED_100baseT_Half | + SUPPORTED_100baseT_Full | + SUPPORTED_1000baseT_Full | + SUPPORTED_10000baseT_Full | + SUPPORTED_TP | + SUPPORTED_Autoneg | + SUPPORTED_Pause | + SUPPORTED_Asym_Pause), + .media_type = ETH_PHY_BASE_T, + .ver_addr = 0, + .req_flow_ctrl = 0, + .req_line_speed = 0, + .speed_cap_mask = 0, + .req_duplex = 0, + .rsrv = 0, + .config_init = (config_init_t)bnx2x_848x3_config_init, + .read_status = (read_status_t)bnx2x_848xx_read_status, + .link_reset = (link_reset_t)bnx2x_848x3_link_reset, + .config_loopback = (config_loopback_t)NULL, + .format_fw_ver = (format_fw_ver_t)bnx2x_848xx_format_ver, + .hw_reset = (hw_reset_t)bnx2x_84833_hw_reset_phy, + .set_link_led = (set_link_led_t)bnx2x_848xx_set_link_led, + .phy_specific_func = (phy_specific_func_t)bnx2x_848xx_specific_func +}; + static const struct bnx2x_phy phy_54618se = { .type = PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE, .addr = 0xff, @@ -12128,6 +12274,9 @@ static int bnx2x_populate_ext_phy(struct bnx2x *bp, case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834: *phy = phy_84834; break; + case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858: + *phy = phy_84858; + break; case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54616: case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM54618SE: *phy = phy_54618se; @@ -12184,9 +12333,7 @@ static int bnx2x_populate_ext_phy(struct bnx2x *bp, } phy->mdio_ctrl = bnx2x_get_emac_base(bp, mdc_mdio_access, port); - if (((phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) || - (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834)) && - (phy->ver_addr)) { + if (bnx2x_is_8483x_8485x(phy) && (phy->ver_addr)) { /* Remove 100Mb link supported for BCM84833/4 when phy fw * version lower than or equal to 1.39 */ @@ -13281,6 +13428,7 @@ static int bnx2x_ext_phy_common_init(struct bnx2x *bp, u32 shmem_base_path[], break; case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833: case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834: + case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858: /* GPIO3's are linked, and so both need to be toggled * to obtain required 2us pulse. */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h index d9cce4c3899b..b7d251108c19 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h @@ -1,13 +1,15 @@ /* Copyright 2008-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and QLogic execute a separate written software license * agreement governing use of this software, this software is licensed to you * under the terms of the GNU General Public License version 2, available - * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). + * at http://www.gnu.org/licenses/gpl-2.0.html (the "GPL"). * * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written + * software in any way with any other Qlogic software provided under a + * license other than the GPL, without Qlogic's express prior written * consent. * * Written by Yaniv Rosner diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index c27af12314ed..78e55fe616e3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -1,6 +1,8 @@ -/* bnx2x_main.c: Broadcom Everest network driver. +/* bnx2x_main.c: QLogic Everest network driver. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -81,11 +83,11 @@ #define TX_TIMEOUT (5*HZ) static char version[] = - "Broadcom NetXtreme II 5771x/578xx 10/20-Gigabit Ethernet Driver " + "QLogic 5771x/578xx 10/20-Gigabit Ethernet Driver " DRV_MODULE_NAME " " DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; MODULE_AUTHOR("Eliezer Tamir"); -MODULE_DESCRIPTION("Broadcom NetXtreme II " +MODULE_DESCRIPTION("QLogic " "BCM57710/57711/57711E/" "57712/57712_MF/57800/57800_MF/57810/57810_MF/" "57840/57840_MF Driver"); @@ -163,27 +165,27 @@ enum bnx2x_board_type { static struct { char *name; } board_info[] = { - [BCM57710] = { "Broadcom NetXtreme II BCM57710 10 Gigabit PCIe [Everest]" }, - [BCM57711] = { "Broadcom NetXtreme II BCM57711 10 Gigabit PCIe" }, - [BCM57711E] = { "Broadcom NetXtreme II BCM57711E 10 Gigabit PCIe" }, - [BCM57712] = { "Broadcom NetXtreme II BCM57712 10 Gigabit Ethernet" }, - [BCM57712_MF] = { "Broadcom NetXtreme II BCM57712 10 Gigabit Ethernet Multi Function" }, - [BCM57712_VF] = { "Broadcom NetXtreme II BCM57712 10 Gigabit Ethernet Virtual Function" }, - [BCM57800] = { "Broadcom NetXtreme II BCM57800 10 Gigabit Ethernet" }, - [BCM57800_MF] = { "Broadcom NetXtreme II BCM57800 10 Gigabit Ethernet Multi Function" }, - [BCM57800_VF] = { "Broadcom NetXtreme II BCM57800 10 Gigabit Ethernet Virtual Function" }, - [BCM57810] = { "Broadcom NetXtreme II BCM57810 10 Gigabit Ethernet" }, - [BCM57810_MF] = { "Broadcom NetXtreme II BCM57810 10 Gigabit Ethernet Multi Function" }, - [BCM57810_VF] = { "Broadcom NetXtreme II BCM57810 10 Gigabit Ethernet Virtual Function" }, - [BCM57840_4_10] = { "Broadcom NetXtreme II BCM57840 10 Gigabit Ethernet" }, - [BCM57840_2_20] = { "Broadcom NetXtreme II BCM57840 20 Gigabit Ethernet" }, - [BCM57840_MF] = { "Broadcom NetXtreme II BCM57840 10/20 Gigabit Ethernet Multi Function" }, - [BCM57840_VF] = { "Broadcom NetXtreme II BCM57840 10/20 Gigabit Ethernet Virtual Function" }, - [BCM57811] = { "Broadcom NetXtreme II BCM57811 10 Gigabit Ethernet" }, - [BCM57811_MF] = { "Broadcom NetXtreme II BCM57811 10 Gigabit Ethernet Multi Function" }, - [BCM57840_O] = { "Broadcom NetXtreme II BCM57840 10/20 Gigabit Ethernet" }, - [BCM57840_MFO] = { "Broadcom NetXtreme II BCM57840 10/20 Gigabit Ethernet Multi Function" }, - [BCM57811_VF] = { "Broadcom NetXtreme II BCM57840 10/20 Gigabit Ethernet Virtual Function" } + [BCM57710] = { "QLogic BCM57710 10 Gigabit PCIe [Everest]" }, + [BCM57711] = { "QLogic BCM57711 10 Gigabit PCIe" }, + [BCM57711E] = { "QLogic BCM57711E 10 Gigabit PCIe" }, + [BCM57712] = { "QLogic BCM57712 10 Gigabit Ethernet" }, + [BCM57712_MF] = { "QLogic BCM57712 10 Gigabit Ethernet Multi Function" }, + [BCM57712_VF] = { "QLogic BCM57712 10 Gigabit Ethernet Virtual Function" }, + [BCM57800] = { "QLogic BCM57800 10 Gigabit Ethernet" }, + [BCM57800_MF] = { "QLogic BCM57800 10 Gigabit Ethernet Multi Function" }, + [BCM57800_VF] = { "QLogic BCM57800 10 Gigabit Ethernet Virtual Function" }, + [BCM57810] = { "QLogic BCM57810 10 Gigabit Ethernet" }, + [BCM57810_MF] = { "QLogic BCM57810 10 Gigabit Ethernet Multi Function" }, + [BCM57810_VF] = { "QLogic BCM57810 10 Gigabit Ethernet Virtual Function" }, + [BCM57840_4_10] = { "QLogic BCM57840 10 Gigabit Ethernet" }, + [BCM57840_2_20] = { "QLogic BCM57840 20 Gigabit Ethernet" }, + [BCM57840_MF] = { "QLogic BCM57840 10/20 Gigabit Ethernet Multi Function" }, + [BCM57840_VF] = { "QLogic BCM57840 10/20 Gigabit Ethernet Virtual Function" }, + [BCM57811] = { "QLogic BCM57811 10 Gigabit Ethernet" }, + [BCM57811_MF] = { "QLogic BCM57811 10 Gigabit Ethernet Multi Function" }, + [BCM57840_O] = { "QLogic BCM57840 10/20 Gigabit Ethernet" }, + [BCM57840_MFO] = { "QLogic BCM57840 10/20 Gigabit Ethernet Multi Function" }, + [BCM57811_VF] = { "QLogic BCM57840 10/20 Gigabit Ethernet Virtual Function" } }; #ifndef PCI_DEVICE_ID_NX2_57710 @@ -2916,7 +2918,7 @@ static void bnx2x_handle_update_svid_cmd(struct bnx2x *bp) func_params.f_obj = &bp->func_obj; func_params.cmd = BNX2X_F_CMD_SWITCH_UPDATE; - if (IS_MF_UFP(bp)) { + if (IS_MF_UFP(bp) || IS_MF_BD(bp)) { int func = BP_ABS_FUNC(bp); u32 val; @@ -2943,16 +2945,16 @@ static void bnx2x_handle_update_svid_cmd(struct bnx2x *bp) BNX2X_ERR("Failed to configure FW of S-tag Change to %02x\n", bp->mf_ov); goto fail; + } else { + DP(BNX2X_MSG_MCP, "Configured S-tag %02x\n", + bp->mf_ov); } - - DP(BNX2X_MSG_MCP, "Configured S-tag %02x\n", bp->mf_ov); - - bnx2x_fw_command(bp, DRV_MSG_CODE_OEM_UPDATE_SVID_OK, 0); - - return; + } else { + goto fail; } - /* not supported by SW yet */ + bnx2x_fw_command(bp, DRV_MSG_CODE_OEM_UPDATE_SVID_OK, 0); + return; fail: bnx2x_fw_command(bp, DRV_MSG_CODE_OEM_UPDATE_SVID_FAILURE, 0); } @@ -3707,6 +3709,34 @@ out: ethver, iscsiver, fcoever); } +void bnx2x_update_mfw_dump(struct bnx2x *bp) +{ + struct timeval epoc; + u32 drv_ver; + u32 valid_dump; + + if (!SHMEM2_HAS(bp, drv_info)) + return; + + /* Update Driver load time */ + do_gettimeofday(&epoc); + SHMEM2_WR(bp, drv_info.epoc, epoc.tv_sec); + + drv_ver = bnx2x_update_mng_version_utility(DRV_MODULE_VERSION, true); + SHMEM2_WR(bp, drv_info.drv_ver, drv_ver); + + SHMEM2_WR(bp, drv_info.fw_ver, REG_RD(bp, XSEM_REG_PRAM)); + + /* Check & notify On-Chip dump. */ + valid_dump = SHMEM2_RD(bp, drv_info.valid_dump); + + if (valid_dump & FIRST_DUMP_VALID) + DP(NETIF_MSG_IFUP, "A valid On-Chip MFW dump found on 1st partition\n"); + + if (valid_dump & SECOND_DUMP_VALID) + DP(NETIF_MSG_IFUP, "A valid On-Chip MFW dump found on 2nd partition\n"); +} + static void bnx2x_oem_event(struct bnx2x *bp, u32 event) { u32 cmd_ok, cmd_fail; @@ -5568,6 +5598,8 @@ static void bnx2x_eq_int(struct bnx2x *bp) BNX2X_STATE_OPEN): case (EVENT_RING_OPCODE_RSS_UPDATE_RULES | BNX2X_STATE_OPENING_WAIT4_PORT): + case (EVENT_RING_OPCODE_RSS_UPDATE_RULES | + BNX2X_STATE_CLOSING_WAIT4_HALT): cid = elem->message.data.eth_event.echo & BNX2X_SWCID_MASK; DP(BNX2X_MSG_SP, "got RSS_UPDATE ramrod. CID %d\n", @@ -7429,6 +7461,9 @@ static int bnx2x_init_hw_common(struct bnx2x *bp) } else BNX2X_ERR("Bootcode is missing - can not initialize link\n"); + if (SHMEM2_HAS(bp, netproc_fw_ver)) + SHMEM2_WR(bp, netproc_fw_ver, REG_RD(bp, XSEM_REG_PRAM)); + return 0; } @@ -11678,7 +11713,7 @@ static void validate_set_si_mode(struct bnx2x *bp) static int bnx2x_get_hwinfo(struct bnx2x *bp) { int /*abs*/func = BP_ABS_FUNC(bp); - int vn; + int vn, mfw_vn; u32 val = 0, val2 = 0; int rc = 0; @@ -11768,6 +11803,7 @@ static int bnx2x_get_hwinfo(struct bnx2x *bp) bp->mf_mode = 0; bp->mf_sub_mode = 0; vn = BP_VN(bp); + mfw_vn = BP_FW_MB_IDX(bp); if (!CHIP_IS_E1(bp) && !BP_NOMCP(bp)) { BNX2X_DEV_INFO("shmem2base 0x%x, size %d, mfcfg offset %d\n", @@ -11824,6 +11860,31 @@ static int bnx2x_get_hwinfo(struct bnx2x *bp) } else BNX2X_DEV_INFO("illegal OV for SD\n"); break; + case SHARED_FEAT_CFG_FORCE_SF_MODE_BD_MODE: + bp->mf_mode = MULTI_FUNCTION_SD; + bp->mf_sub_mode = SUB_MF_MODE_BD; + bp->mf_config[vn] = + MF_CFG_RD(bp, + func_mf_config[func].config); + + if (SHMEM2_HAS(bp, mtu_size)) { + int mtu_idx = BP_FW_MB_IDX(bp); + u16 mtu_size; + u32 mtu; + + mtu = SHMEM2_RD(bp, mtu_size[mtu_idx]); + mtu_size = (u16)mtu; + DP(NETIF_MSG_IFUP, "Read MTU size %04x [%08x]\n", + mtu_size, mtu); + + /* if valid: update device mtu */ + if (((mtu_size + ETH_HLEN) >= + ETH_MIN_PACKET_SIZE) && + (mtu_size <= + ETH_MAX_JUMBO_PACKET_SIZE)) + bp->dev->mtu = mtu_size; + } + break; case SHARED_FEAT_CFG_FORCE_SF_MODE_UFP_MODE: bp->mf_mode = MULTI_FUNCTION_SD; bp->mf_sub_mode = SUB_MF_MODE_UFP; @@ -11871,9 +11932,10 @@ static int bnx2x_get_hwinfo(struct bnx2x *bp) BNX2X_DEV_INFO("MF OV for func %d is %d (0x%04x)\n", func, bp->mf_ov, bp->mf_ov); - } else if (bp->mf_sub_mode == SUB_MF_MODE_UFP) { + } else if ((bp->mf_sub_mode == SUB_MF_MODE_UFP) || + (bp->mf_sub_mode == SUB_MF_MODE_BD)) { dev_err(&bp->pdev->dev, - "Unexpected - no valid MF OV for func %d in UFP mode\n", + "Unexpected - no valid MF OV for func %d in UFP/BD mode\n", func); bp->path_has_ovlan = true; } else { @@ -13561,6 +13623,9 @@ static int bnx2x_init_one(struct pci_dev *pdev, bnx2x_register_phc(bp); + if (!IS_MF_SD_STORAGE_PERSONALITY_ONLY(bp)) + bnx2x_set_os_driver_state(bp, OS_DRIVER_STATE_DISABLED); + return 0; init_one_exit: @@ -13623,6 +13688,7 @@ static void __bnx2x_remove(struct pci_dev *pdev, /* Power on: we can't let PCI layer write to us while we are in D3 */ if (IS_PF(bp)) { bnx2x_set_power_state(bp, PCI_D0); + bnx2x_set_os_driver_state(bp, OS_DRIVER_STATE_NOT_LOADED); /* Set endianity registers to reset values in case next driver * boots in different endianty environment. diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_mfw_req.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_mfw_req.h index caf1aef651eb..a91ccbf36345 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_mfw_req.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_mfw_req.h @@ -1,6 +1,8 @@ -/* bnx2x_mfw_req.h: Broadcom Everest network driver. +/* bnx2x_mfw_req.h: Qlogic Everest network driver. * * Copyright (c) 2012-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h index 49d511092c82..4dead49bd5cb 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h @@ -1,6 +1,8 @@ -/* bnx2x_reg.h: Broadcom Everest network driver. +/* bnx2x_reg.h: Qlogic Everest network driver. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -2137,6 +2139,10 @@ /* [RW 1] When this bit is set; the LLH will expect all packets to be with e1hov */ #define NIG_REG_LLH_E1HOV_MODE 0x160d8 +/* [RW 16] Outer VLAN type identifier for multi-function mode. In non + * multi-function mode; it will hold the inner VLAN type. Typically 0x8100. + */ +#define NIG_REG_LLH_E1HOV_TYPE_1 0x16028 /* [RW 1] When this bit is set; the LLH will classify the packet before sending it to the BRB or calculating WoL on it. */ #define NIG_REG_LLH_MF_MODE 0x16024 @@ -2953,7 +2959,12 @@ #define PBF_REG_TQ_OCCUPANCY_Q0 0x1403ac /* [R 13] Number of 8 bytes lines occupied in the task queue of queue 1. */ #define PBF_REG_TQ_OCCUPANCY_Q1 0x1403b0 -#define PB_REG_CONTROL 0 +/* [RW 16] One of 8 values that should be compared to type in Ethernet + * parsing. If there is a match; the field after Ethernet is the first VLAN. + * Reset value is 0x8100 which is the standard VLAN type. Note that when + * checking second VLAN; type is compared only to 0x8100. + */ +#define PBF_REG_VLAN_TYPE_0 0x15c06c /* [RW 2] Interrupt mask register #0 read/write */ #define PB_REG_PB_INT_MASK 0x28 /* [R 2] Interrupt register #0 read */ @@ -3372,6 +3383,12 @@ #define PRS_REG_TCM_CURRENT_CREDIT 0x40160 /* [R 8] debug only: TSDM current credit. Transaction based. */ #define PRS_REG_TSDM_CURRENT_CREDIT 0x4015c +/* [RW 16] One of 8 values that should be compared to type in Ethernet + * parsing. If there is a match; the field after Ethernet is the first VLAN. + * Reset value is 0x8100 which is the standard VLAN type. Note that when + * checking second VLAN; type is compared only to 0x8100. + */ +#define PRS_REG_VLAN_TYPE_0 0x401a8 #define PXP2_PXP2_INT_MASK_0_REG_PGL_CPL_AFT (0x1<<19) #define PXP2_PXP2_INT_MASK_0_REG_PGL_CPL_OF (0x1<<20) #define PXP2_PXP2_INT_MASK_0_REG_PGL_PCIE_ATTN (0x1<<22) @@ -7240,6 +7257,9 @@ Theotherbitsarereservedandshouldbezero*/ #define MDIO_AN_REG_8481_LEGACY_MII_CTRL 0xffe0 #define MDIO_AN_REG_8481_MII_CTRL_FORCE_1G 0x40 #define MDIO_AN_REG_8481_LEGACY_MII_STATUS 0xffe1 +#define MDIO_AN_REG_848xx_ID_MSB 0xffe2 +#define BCM84858_PHY_ID 0x600d +#define MDIO_AN_REG_848xx_ID_LSB 0xffe3 #define MDIO_AN_REG_8481_LEGACY_AN_ADV 0xffe4 #define MDIO_AN_REG_8481_LEGACY_AN_EXPANSION 0xffe6 #define MDIO_AN_REG_8481_1000T_CTRL 0xffe9 @@ -7283,31 +7303,31 @@ Theotherbitsarereservedandshouldbezero*/ #define MDIO_84833_TOP_CFG_FW_NO_EEE 0x1f81 #define MDIO_84833_TOP_CFG_XGPHY_STRAP1 0x401a #define MDIO_84833_SUPER_ISOLATE 0x8000 -/* These are mailbox register set used by 84833. */ -#define MDIO_84833_TOP_CFG_SCRATCH_REG0 0x4005 -#define MDIO_84833_TOP_CFG_SCRATCH_REG1 0x4006 -#define MDIO_84833_TOP_CFG_SCRATCH_REG2 0x4007 -#define MDIO_84833_TOP_CFG_SCRATCH_REG3 0x4008 -#define MDIO_84833_TOP_CFG_SCRATCH_REG4 0x4009 -#define MDIO_84833_TOP_CFG_SCRATCH_REG26 0x4037 -#define MDIO_84833_TOP_CFG_SCRATCH_REG27 0x4038 -#define MDIO_84833_TOP_CFG_SCRATCH_REG28 0x4039 -#define MDIO_84833_TOP_CFG_SCRATCH_REG29 0x403a -#define MDIO_84833_TOP_CFG_SCRATCH_REG30 0x403b -#define MDIO_84833_TOP_CFG_SCRATCH_REG31 0x403c -#define MDIO_84833_CMD_HDLR_COMMAND MDIO_84833_TOP_CFG_SCRATCH_REG0 -#define MDIO_84833_CMD_HDLR_STATUS MDIO_84833_TOP_CFG_SCRATCH_REG26 -#define MDIO_84833_CMD_HDLR_DATA1 MDIO_84833_TOP_CFG_SCRATCH_REG27 -#define MDIO_84833_CMD_HDLR_DATA2 MDIO_84833_TOP_CFG_SCRATCH_REG28 -#define MDIO_84833_CMD_HDLR_DATA3 MDIO_84833_TOP_CFG_SCRATCH_REG29 -#define MDIO_84833_CMD_HDLR_DATA4 MDIO_84833_TOP_CFG_SCRATCH_REG30 -#define MDIO_84833_CMD_HDLR_DATA5 MDIO_84833_TOP_CFG_SCRATCH_REG31 +/* These are mailbox register set used by 84833/84858. */ +#define MDIO_848xx_TOP_CFG_SCRATCH_REG0 0x4005 +#define MDIO_848xx_TOP_CFG_SCRATCH_REG1 0x4006 +#define MDIO_848xx_TOP_CFG_SCRATCH_REG2 0x4007 +#define MDIO_848xx_TOP_CFG_SCRATCH_REG3 0x4008 +#define MDIO_848xx_TOP_CFG_SCRATCH_REG4 0x4009 +#define MDIO_848xx_TOP_CFG_SCRATCH_REG26 0x4037 +#define MDIO_848xx_TOP_CFG_SCRATCH_REG27 0x4038 +#define MDIO_848xx_TOP_CFG_SCRATCH_REG28 0x4039 +#define MDIO_848xx_TOP_CFG_SCRATCH_REG29 0x403a +#define MDIO_848xx_TOP_CFG_SCRATCH_REG30 0x403b +#define MDIO_848xx_TOP_CFG_SCRATCH_REG31 0x403c +#define MDIO_848xx_CMD_HDLR_COMMAND (MDIO_848xx_TOP_CFG_SCRATCH_REG0) +#define MDIO_848xx_CMD_HDLR_STATUS (MDIO_848xx_TOP_CFG_SCRATCH_REG26) +#define MDIO_848xx_CMD_HDLR_DATA1 (MDIO_848xx_TOP_CFG_SCRATCH_REG27) +#define MDIO_848xx_CMD_HDLR_DATA2 (MDIO_848xx_TOP_CFG_SCRATCH_REG28) +#define MDIO_848xx_CMD_HDLR_DATA3 (MDIO_848xx_TOP_CFG_SCRATCH_REG29) +#define MDIO_848xx_CMD_HDLR_DATA4 (MDIO_848xx_TOP_CFG_SCRATCH_REG30) +#define MDIO_848xx_CMD_HDLR_DATA5 (MDIO_848xx_TOP_CFG_SCRATCH_REG31) -/* Mailbox command set used by 84833. */ -#define PHY84833_CMD_SET_PAIR_SWAP 0x8001 -#define PHY84833_CMD_GET_EEE_MODE 0x8008 -#define PHY84833_CMD_SET_EEE_MODE 0x8009 -/* Mailbox status set used by 84833. */ +/* Mailbox command set used by 84833/84858 */ +#define PHY848xx_CMD_SET_PAIR_SWAP 0x8001 +#define PHY848xx_CMD_GET_EEE_MODE 0x8008 +#define PHY848xx_CMD_SET_EEE_MODE 0x8009 +/* Mailbox status set used by 84833 only */ #define PHY84833_STATUS_CMD_RECEIVED 0x0001 #define PHY84833_STATUS_CMD_IN_PROGRESS 0x0002 #define PHY84833_STATUS_CMD_COMPLETE_PASS 0x0004 @@ -7318,6 +7338,13 @@ Theotherbitsarereservedandshouldbezero*/ #define PHY84833_STATUS_CMD_CLEAR_COMPLETE 0x0080 #define PHY84833_STATUS_CMD_OPEN_OVERRIDE 0xa5a5 +/* Mailbox status set used by 84858 only */ +#define PHY84858_STATUS_CMD_RECEIVED 0x0001 +#define PHY84858_STATUS_CMD_IN_PROGRESS 0x0002 +#define PHY84858_STATUS_CMD_COMPLETE_PASS 0x0004 +#define PHY84858_STATUS_CMD_COMPLETE_ERROR 0x0008 +#define PHY84858_STATUS_CMD_SYSTEM_BUSY 0xbbbb + /* Warpcore clause 45 addressing */ #define MDIO_WC_DEVAD 0x3 diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index 4ad415ac8cfe..265fe0a90adc 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -1,15 +1,17 @@ -/* bnx2x_sp.c: Broadcom Everest network driver. +/* bnx2x_sp.c: Qlogic Everest network driver. * - * Copyright (c) 2011-2013 Broadcom Corporation + * Copyright 2011-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and Qlogic execute a separate written software license * agreement governing use of this software, this software is licensed to you * under the terms of the GNU General Public License version 2, available - * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). + * at http://www.gnu.org/licenses/gpl-2.0.html (the "GPL"). * * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written + * software in any way with any other Qlogic software provided under a + * license other than the GPL, without Qlogic's express prior written * consent. * * Maintained by: Ariel Elior <ariel.elior@qlogic.com> @@ -4060,8 +4062,14 @@ static int bnx2x_setup_rss(struct bnx2x *bp, if (test_bit(BNX2X_RSS_IPV6_UDP, &p->rss_flags)) caps |= ETH_RSS_UPDATE_RAMROD_DATA_IPV6_UDP_CAPABILITY; - if (test_bit(BNX2X_RSS_GRE_INNER_HDRS, &p->rss_flags)) - caps |= ETH_RSS_UPDATE_RAMROD_DATA_GRE_INNER_HDRS_CAPABILITY; + if (test_bit(BNX2X_RSS_IPV4_VXLAN, &p->rss_flags)) + caps |= ETH_RSS_UPDATE_RAMROD_DATA_IPV4_VXLAN_CAPABILITY; + + if (test_bit(BNX2X_RSS_IPV6_VXLAN, &p->rss_flags)) + caps |= ETH_RSS_UPDATE_RAMROD_DATA_IPV6_VXLAN_CAPABILITY; + + if (test_bit(BNX2X_RSS_TUNN_INNER_HDRS, &p->rss_flags)) + caps |= ETH_RSS_UPDATE_RAMROD_DATA_TUNN_INNER_HDRS_CAPABILITY; /* RSS keys */ if (test_bit(BNX2X_RSS_SET_SRCH, &p->rss_flags)) { @@ -5669,10 +5677,14 @@ static inline int bnx2x_func_send_start(struct bnx2x *bp, rdata->sd_vlan_tag = cpu_to_le16(start_params->sd_vlan_tag); rdata->path_id = BP_PATH(bp); rdata->network_cos_mode = start_params->network_cos_mode; - rdata->tunnel_mode = start_params->tunnel_mode; - rdata->gre_tunnel_type = start_params->gre_tunnel_type; - rdata->inner_gre_rss_en = start_params->inner_gre_rss_en; - rdata->vxlan_dst_port = cpu_to_le16(4789); + + rdata->vxlan_dst_port = cpu_to_le16(start_params->vxlan_dst_port); + rdata->geneve_dst_port = cpu_to_le16(start_params->geneve_dst_port); + rdata->inner_clss_l2gre = start_params->inner_clss_l2gre; + rdata->inner_clss_l2geneve = start_params->inner_clss_l2geneve; + rdata->inner_clss_vxlan = start_params->inner_clss_vxlan; + rdata->inner_rss = start_params->inner_rss; + rdata->sd_accept_mf_clss_fail = start_params->class_fail; if (start_params->class_fail_ethtype) { rdata->sd_accept_mf_clss_fail_match_ethtype = 1; @@ -5690,6 +5702,14 @@ static inline int bnx2x_func_send_start(struct bnx2x *bp, cpu_to_le16(0x8100); rdata->no_added_tags = start_params->no_added_tags; + + rdata->c2s_pri_tt_valid = start_params->c2s_pri_valid; + if (rdata->c2s_pri_tt_valid) { + memcpy(rdata->c2s_pri_trans_table.val, + start_params->c2s_pri, + MAX_VLAN_PRIORITIES); + rdata->c2s_pri_default = start_params->c2s_pri_default; + } /* No need for an explicit memory barrier here as long we would * need to ensure the ordering of writing to the SPQ element * and updating of the SPQ producer which involves a memory @@ -5750,15 +5770,22 @@ static inline int bnx2x_func_send_switch_update(struct bnx2x *bp, if (test_bit(BNX2X_F_UPDATE_TUNNEL_CFG_CHNG, &switch_update_params->changes)) { rdata->update_tunn_cfg_flg = 1; - if (test_bit(BNX2X_F_UPDATE_TUNNEL_CLSS_EN, + if (test_bit(BNX2X_F_UPDATE_TUNNEL_INNER_CLSS_L2GRE, + &switch_update_params->changes)) + rdata->inner_clss_l2gre = 1; + if (test_bit(BNX2X_F_UPDATE_TUNNEL_INNER_CLSS_VXLAN, + &switch_update_params->changes)) + rdata->inner_clss_vxlan = 1; + if (test_bit(BNX2X_F_UPDATE_TUNNEL_INNER_CLSS_L2GENEVE, &switch_update_params->changes)) - rdata->tunn_clss_en = 1; - if (test_bit(BNX2X_F_UPDATE_TUNNEL_INNER_GRE_RSS_EN, + rdata->inner_clss_l2geneve = 1; + if (test_bit(BNX2X_F_UPDATE_TUNNEL_INNER_RSS, &switch_update_params->changes)) - rdata->inner_gre_rss_en = 1; - rdata->tunnel_mode = switch_update_params->tunnel_mode; - rdata->gre_tunnel_type = switch_update_params->gre_tunnel_type; - rdata->vxlan_dst_port = cpu_to_le16(4789); + rdata->inner_rss = 1; + rdata->vxlan_dst_port = + cpu_to_le16(switch_update_params->vxlan_dst_port); + rdata->geneve_dst_port = + cpu_to_le16(switch_update_params->geneve_dst_port); } rdata->echo = SWITCH_UPDATE; @@ -5885,6 +5912,8 @@ static inline int bnx2x_func_send_tx_start(struct bnx2x *bp, rdata->traffic_type_to_priority_cos[i] = tx_start_params->traffic_type_to_priority_cos[i]; + for (i = 0; i < MAX_TRAFFIC_TYPES; i++) + rdata->dcb_outer_pri[i] = tx_start_params->dcb_outer_pri[i]; /* No need for an explicit memory barrier here as long as we * ensure the ordering of writing to the SPQ element * and updating of the SPQ producer which involves a memory diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h index 86baecb7c60c..324e9f986314 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h @@ -1,15 +1,17 @@ -/* bnx2x_sp.h: Broadcom Everest network driver. +/* bnx2x_sp.h: Qlogic Everest network driver. * - * Copyright (c) 2011-2013 Broadcom Corporation + * Copyright 2011-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and Qlogic execute a separate written software license * agreement governing use of this software, this software is licensed to you * under the terms of the GNU General Public License version 2, available - * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). + * at http://www.gnu.org/licenses/gpl-2.0.html (the "GPL"). * * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written + * software in any way with any other Qlogic software provided under a + * license other than the GPL, without Qlogic's express prior written * consent. * * Maintained by: Ariel Elior <ariel.elior@qlogic.com> @@ -711,7 +713,10 @@ enum { BNX2X_RSS_IPV6, BNX2X_RSS_IPV6_TCP, BNX2X_RSS_IPV6_UDP, - BNX2X_RSS_GRE_INNER_HDRS, + + BNX2X_RSS_IPV4_VXLAN, + BNX2X_RSS_IPV6_VXLAN, + BNX2X_RSS_TUNN_INNER_HDRS, }; struct bnx2x_config_rss_params { @@ -1105,8 +1110,10 @@ enum { BNX2X_F_UPDATE_VLAN_FORCE_PRIO_CHNG, BNX2X_F_UPDATE_VLAN_FORCE_PRIO_FLAG, BNX2X_F_UPDATE_TUNNEL_CFG_CHNG, - BNX2X_F_UPDATE_TUNNEL_CLSS_EN, - BNX2X_F_UPDATE_TUNNEL_INNER_GRE_RSS_EN, + BNX2X_F_UPDATE_TUNNEL_INNER_CLSS_L2GRE, + BNX2X_F_UPDATE_TUNNEL_INNER_CLSS_VXLAN, + BNX2X_F_UPDATE_TUNNEL_INNER_CLSS_L2GENEVE, + BNX2X_F_UPDATE_TUNNEL_INNER_RSS, }; /* Allowed Function states */ @@ -1171,19 +1178,23 @@ struct bnx2x_func_start_params { /* Function cos mode */ u8 network_cos_mode; - /* TUNN_MODE_NONE/TUNN_MODE_VXLAN/TUNN_MODE_GRE */ - u8 tunnel_mode; + /* UDP dest port for VXLAN */ + u16 vxlan_dst_port; - /* tunneling classification enablement */ - u8 tunn_clss_en; + /* UDP dest port for Geneve */ + u16 geneve_dst_port; - /* NVGRE_TUNNEL/L2GRE_TUNNEL/IPGRE_TUNNEL */ - u8 gre_tunnel_type; + /* Enable inner Rx classifications for L2GRE packets */ + u8 inner_clss_l2gre; - /* Enables Inner GRE RSS on the function, depends on the client RSS - * capailities - */ - u8 inner_gre_rss_en; + /* Enable inner Rx classifications for L2-Geneve packets */ + u8 inner_clss_l2geneve; + + /* Enable inner Rx classification for vxlan packets */ + u8 inner_clss_vxlan; + + /* Enable RSS according to inner header */ + u8 inner_rss; /* Allows accepting of packets failing MF classification, possibly * only matching a given ethertype @@ -1200,6 +1211,11 @@ struct bnx2x_func_start_params { /* Prevent inner vlans from being added by FW */ u8 no_added_tags; + + /* Inner-to-Outer vlan priority mapping */ + u8 c2s_pri[MAX_VLAN_PRIORITIES]; + u8 c2s_pri_default; + u8 c2s_pri_valid; }; struct bnx2x_func_switch_update_params { @@ -1207,8 +1223,8 @@ struct bnx2x_func_switch_update_params { u16 vlan; u16 vlan_eth_type; u8 vlan_force_prio; - u8 tunnel_mode; - u8 gre_tunnel_type; + u16 vxlan_dst_port; + u16 geneve_dst_port; }; struct bnx2x_func_afex_update_params { @@ -1229,6 +1245,7 @@ struct bnx2x_func_tx_start_params { u8 dcb_enabled; u8 dcb_version; u8 dont_add_pri_0_en; + u8 dcb_outer_pri[MAX_TRAFFIC_TYPES]; }; struct bnx2x_func_set_timesync_params { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index f67348d16966..5b243bcec3fa 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1,15 +1,17 @@ -/* bnx2x_sriov.c: Broadcom Everest network driver. +/* bnx2x_sriov.c: QLogic Everest network driver. * * Copyright 2009-2013 Broadcom Corporation + * Copyright 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and QLogic execute a separate written software license * agreement governing use of this software, this software is licensed to you * under the terms of the GNU General Public License version 2, available * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). * * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written + * software in any way with any other QLogic software provided under a + * license other than the GPL, without QLogic's express prior written * consent. * * Maintained by: Ariel Elior <ariel.elior@qlogic.com> @@ -1338,6 +1340,9 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param, mutex_init(&bp->vfdb->bulletin_mutex); + if (SHMEM2_HAS(bp, sriov_switch_mode)) + SHMEM2_WR(bp, sriov_switch_mode, SRIOV_SWITCH_MODE_VEB); + return 0; failed: DP(BNX2X_MSG_IOV, "Failed err=%d\n", err); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index 66ee62a0401a..2011205ec8d4 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -1,15 +1,17 @@ -/* bnx2x_sriov.h: Broadcom Everest network driver. +/* bnx2x_sriov.h: QLogic Everest network driver. * * Copyright 2009-2013 Broadcom Corporation + * Copyright 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and QLogic execute a separate written software license * agreement governing use of this software, this software is licensed to you * under the terms of the GNU General Public License version 2, available * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). * * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written + * software in any way with any other QLogic software provided under a + * license other than the GPL, without QLogic's express prior written * consent. * * Maintained by: Ariel Elior <ariel.elior@qlogic.com> diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c index 69d699f0730a..7e0919aa450e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c @@ -1,6 +1,8 @@ -/* bnx2x_stats.c: Broadcom Everest network driver. +/* bnx2x_stats.c: QLogic Everest network driver. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h index 965539a9dabe..b2644ed13d06 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h @@ -1,6 +1,8 @@ -/* bnx2x_stats.h: Broadcom Everest network driver. +/* bnx2x_stats.h: QLogic Everest network driver. * * Copyright (c) 2007-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 06b8c0d8fd3b..31b79bd13292 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -1,15 +1,17 @@ -/* bnx2x_vfpf.c: Broadcom Everest network driver. +/* bnx2x_vfpf.c: QLogic Everest network driver. * * Copyright 2009-2013 Broadcom Corporation + * Copyright 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and QLogic execute a separate written software license * agreement governing use of this software, this software is licensed to you * under the terms of the GNU General Public License version 2, available * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). * * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written + * software in any way with any other QLogic software provided under a + * license other than the GPL, without QLogic's express prior written * consent. * * Maintained by: Ariel Elior <ariel.elior@qlogic.com> diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h index b86479fc0d2f..f0110f4bd0a3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h @@ -1,16 +1,22 @@ -/* bnx2x_vfpf.h: Broadcom Everest network driver. +/* bnx2x_vfpf.h: Qlogic Everest network driver. * * Copyright (c) 2011-2013 Broadcom Corporation + * Copyright (c) 2014 QLogic Corporation + * All rights reserved * - * Unless you and Broadcom execute a separate written software license + * Unless you and Qlogic execute a separate written software license * agreement governing use of this software, this software is licensed to you - * under the terms of the GNU General Public License version 2, available - * at http://www.gnu.org/licenses/old-licenses/gpl-2.0.html (the "GPL"). + * under the terms of the GNU General Public License version 2 (the “GPL”), + * available at http://www.gnu.org/licenses/gpl-2.0.html, with the following + * added to such license: * - * Notwithstanding the above, under no circumstances may you combine this - * software in any way with any other Broadcom software provided under a - * license other than the GPL, without Broadcom's express prior written - * consent. + * As a special exception, the copyright holders of this software give you + * permission to link this software with independent modules, and to copy and + * distribute the resulting executable under terms of your choice, provided that + * you also meet, for each linked independent module, the terms and conditions + * of the license of that module. An independent module is a module which is + * not derived from this software. The special exception does not apply to any + * modifications of the software. * * Maintained by: Ariel Elior <ariel.elior@qlogic.com> * Written by: Ariel Elior <ariel.elior@qlogic.com> diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 64c1e9db6b0b..5bf7ce0ae221 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -907,9 +907,8 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv, } bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - if (mode == GENET_POWER_PASSIVE) - bcmgenet_mii_reset(priv->dev); + bcmgenet_phy_power_set(priv->dev, true); } /* ioctl handle special commands that are not present in ethtool. */ @@ -1725,7 +1724,7 @@ static int init_umac(struct bcmgenet_priv *priv) int0_enable |= UMAC_IRQ_TXDMA_DONE; /* Monitor cable plug/unplugged event for internal PHY */ - if (phy_is_internal(priv->phydev)) { + if (priv->internal_phy) { int0_enable |= UMAC_IRQ_LINK_EVENT; } else if (priv->ext_phy) { int0_enable |= UMAC_IRQ_LINK_EVENT; @@ -2632,7 +2631,7 @@ static int bcmgenet_open(struct net_device *dev) /* If this is an internal GPHY, power it back on now, before UniMAC is * brought out of reset as absolutely no UniMAC activity is allowed */ - if (phy_is_internal(priv->phydev)) + if (priv->internal_phy) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); /* take MAC out of reset */ @@ -2651,7 +2650,7 @@ static int bcmgenet_open(struct net_device *dev) bcmgenet_set_hw_addr(priv, dev->dev_addr); - if (phy_is_internal(priv->phydev)) { + if (priv->internal_phy) { reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); reg |= EXT_ENERGY_DET_MASK; bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); @@ -2687,18 +2686,20 @@ static int bcmgenet_open(struct net_device *dev) goto err_irq0; } - /* Re-configure the port multiplexer towards the PHY device */ - bcmgenet_mii_config(priv->dev, false); - - phy_connect_direct(dev, priv->phydev, bcmgenet_mii_setup, - priv->phy_interface); + ret = bcmgenet_mii_probe(dev); + if (ret) { + netdev_err(dev, "failed to connect to PHY\n"); + goto err_irq1; + } bcmgenet_netif_start(dev); return 0; +err_irq1: + free_irq(priv->irq1, priv); err_irq0: - free_irq(priv->irq0, dev); + free_irq(priv->irq0, priv); err_fini_dma: bcmgenet_fini_dma(priv); err_clk_disable: @@ -2757,7 +2758,7 @@ static int bcmgenet_close(struct net_device *dev) free_irq(priv->irq0, priv); free_irq(priv->irq1, priv); - if (phy_is_internal(priv->phydev)) + if (priv->internal_phy) ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE); if (!IS_ERR(priv->clk)) @@ -3319,7 +3320,7 @@ static int bcmgenet_suspend(struct device *d) if (device_may_wakeup(d) && priv->wolopts) { ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC); clk_prepare_enable(priv->clk_wol); - } else if (phy_is_internal(priv->phydev)) { + } else if (priv->internal_phy) { ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE); } @@ -3348,7 +3349,7 @@ static int bcmgenet_resume(struct device *d) /* If this is an internal GPHY, power it back on now, before UniMAC is * brought out of reset as absolutely no UniMAC activity is allowed */ - if (phy_is_internal(priv->phydev)) + if (priv->internal_phy) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); bcmgenet_umac_reset(priv); @@ -3363,14 +3364,14 @@ static int bcmgenet_resume(struct device *d) phy_init_hw(priv->phydev); /* Speed settings must be restored */ - bcmgenet_mii_config(priv->dev, false); + bcmgenet_mii_config(priv->dev); /* disable ethernet MAC while updating its registers */ umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, false); bcmgenet_set_hw_addr(priv, dev->dev_addr); - if (phy_is_internal(priv->phydev)) { + if (priv->internal_phy) { reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); reg |= EXT_ENERGY_DET_MASK; bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 6159deab8c98..7299d1075422 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -593,6 +593,7 @@ struct bcmgenet_priv { /* MDIO bus variables */ wait_queue_head_t wq; struct phy_device *phydev; + bool internal_phy; struct device_node *phy_dn; struct device_node *mdio_dn; struct mii_bus *mii_bus; @@ -670,9 +671,9 @@ GENET_IO_MACRO(rbuf, GENET_RBUF_OFF); /* MDIO routines */ int bcmgenet_mii_init(struct net_device *dev); -int bcmgenet_mii_config(struct net_device *dev, bool init); +int bcmgenet_mii_config(struct net_device *dev); +int bcmgenet_mii_probe(struct net_device *dev); void bcmgenet_mii_exit(struct net_device *dev); -void bcmgenet_mii_reset(struct net_device *dev); void bcmgenet_phy_power_set(struct net_device *dev, bool enable); void bcmgenet_mii_setup(struct net_device *dev); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index adf23d2ac488..0802cd9d2424 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -163,16 +163,6 @@ void bcmgenet_mii_setup(struct net_device *dev) phy_print_status(phydev); } -void bcmgenet_mii_reset(struct net_device *dev) -{ - struct bcmgenet_priv *priv = netdev_priv(dev); - - if (priv->phydev) { - phy_init_hw(priv->phydev); - phy_start_aneg(priv->phydev); - } -} - void bcmgenet_phy_power_set(struct net_device *dev, bool enable) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -215,7 +205,6 @@ static void bcmgenet_internal_phy_setup(struct net_device *dev) reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); reg |= EXT_PWR_DN_EN_LD; bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); - bcmgenet_mii_reset(dev); } static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv) @@ -228,7 +217,7 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv) bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL); } -int bcmgenet_mii_config(struct net_device *dev, bool init) +int bcmgenet_mii_config(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); struct phy_device *phydev = priv->phydev; @@ -238,10 +227,10 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) u32 port_ctrl; u32 reg; - priv->ext_phy = !phy_is_internal(priv->phydev) && + priv->ext_phy = !priv->internal_phy && (priv->phy_interface != PHY_INTERFACE_MODE_MOCA); - if (phy_is_internal(priv->phydev)) + if (priv->internal_phy) priv->phy_interface = PHY_INTERFACE_MODE_NA; switch (priv->phy_interface) { @@ -259,7 +248,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) bcmgenet_sys_writel(priv, port_ctrl, SYS_PORT_CTRL); - if (phy_is_internal(priv->phydev)) { + if (priv->internal_phy) { phy_name = "internal PHY"; bcmgenet_internal_phy_setup(dev); } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { @@ -321,13 +310,12 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); } - if (init) - dev_info(kdev, "configuring instance for %s\n", phy_name); + dev_info_once(kdev, "configuring instance for %s\n", phy_name); return 0; } -static int bcmgenet_mii_probe(struct net_device *dev) +int bcmgenet_mii_probe(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); struct device_node *dn = priv->pdev->dev.of_node; @@ -345,22 +333,6 @@ static int bcmgenet_mii_probe(struct net_device *dev) priv->old_pause = -1; if (dn) { - if (priv->phydev) { - pr_info("PHY already attached\n"); - return 0; - } - - /* In the case of a fixed PHY, the DT node associated - * to the PHY is the Ethernet MAC DT node. - */ - if (!priv->phy_dn && of_phy_is_fixed_link(dn)) { - ret = of_phy_register_fixed_link(dn); - if (ret) - return ret; - - priv->phy_dn = of_node_get(dn); - } - phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup, phy_flags, priv->phy_interface); if (!phydev) { @@ -386,7 +358,7 @@ static int bcmgenet_mii_probe(struct net_device *dev) * PHY speed which is needed for bcmgenet_mii_config() to configure * things appropriately. */ - ret = bcmgenet_mii_config(dev, true); + ret = bcmgenet_mii_config(dev); if (ret) { phy_disconnect(priv->phydev); return ret; @@ -397,14 +369,11 @@ static int bcmgenet_mii_probe(struct net_device *dev) /* The internal PHY has its link interrupts routed to the * Ethernet MAC ISRs */ - if (phy_is_internal(priv->phydev)) + if (priv->internal_phy) priv->mii_bus->irq[phydev->addr] = PHY_IGNORE_INTERRUPT; else priv->mii_bus->irq[phydev->addr] = PHY_POLL; - pr_info("attached PHY at address %d [%s]\n", - phydev->addr, phydev->drv->name); - return 0; } @@ -490,7 +459,9 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) { struct device_node *dn = priv->pdev->dev.of_node; struct device *kdev = &priv->pdev->dev; + const char *phy_mode_str = NULL; char *compat; + int phy_mode; int ret; compat = kasprintf(GFP_KERNEL, "brcm,genet-mdio-v%d", priv->version); @@ -513,8 +484,36 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) /* Fetch the PHY phandle */ priv->phy_dn = of_parse_phandle(dn, "phy-handle", 0); + /* In the case of a fixed PHY, the DT node associated + * to the PHY is the Ethernet MAC DT node. + */ + if (!priv->phy_dn && of_phy_is_fixed_link(dn)) { + ret = of_phy_register_fixed_link(dn); + if (ret) + return ret; + + priv->phy_dn = of_node_get(dn); + } + /* Get the link mode */ - priv->phy_interface = of_get_phy_mode(dn); + phy_mode = of_get_phy_mode(dn); + priv->phy_interface = phy_mode; + + /* We need to specifically look up whether this PHY interface is internal + * or not *before* we even try to probe the PHY driver over MDIO as we + * may have shut down the internal PHY for power saving purposes. + */ + if (phy_mode < 0) { + ret = of_property_read_string(dn, "phy-mode", &phy_mode_str); + if (ret < 0) { + dev_err(kdev, "invalid PHY mode property\n"); + return ret; + } + + priv->phy_interface = PHY_INTERFACE_MODE_NA; + if (!strcasecmp(phy_mode_str, "internal")) + priv->internal_phy = true; + } return 0; } @@ -615,10 +614,6 @@ int bcmgenet_mii_init(struct net_device *dev) ret = bcmgenet_mii_bus_init(priv); if (ret) - goto out_free; - - ret = bcmgenet_mii_probe(dev); - if (ret) goto out; return 0; @@ -626,7 +621,6 @@ int bcmgenet_mii_init(struct net_device *dev) out: of_node_put(priv->phy_dn); mdiobus_unregister(priv->mii_bus); -out_free: kfree(priv->mii_bus->irq); mdiobus_free(priv->mii_bus); return ret; diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index caeb39561567..a4e3f8655cb8 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -2741,8 +2741,7 @@ static const struct macb_config emac_config = { static const struct macb_config zynqmp_config = { - .caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE | - MACB_CAPS_JUMBO, + .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, @@ -2750,8 +2749,7 @@ static const struct macb_config zynqmp_config = { }; static const struct macb_config zynq_config = { - .caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE | - MACB_CAPS_NO_GIGABIT_HALF, + .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 629f75d70353..58de4443eac0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -767,6 +767,7 @@ struct adapter { bool tid_release_task_busy; struct dentry *debugfs_root; + u32 use_bd; /* Use SGE Back Door intfc for reading SGE Contexts */ spinlock_t stats_lock; spinlock_t win0_lock ____cacheline_aligned_in_smp; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c index 6074680bc985..052c660aca80 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c @@ -31,6 +31,15 @@ static const char * const dcb_ver_array[] = { "Auto Negotiated" }; +static inline bool cxgb4_dcb_state_synced(enum cxgb4_dcb_state state) +{ + if (state == CXGB4_DCB_STATE_FW_ALLSYNCED || + state == CXGB4_DCB_STATE_HOST) + return true; + else + return false; +} + /* Initialize a port's Data Center Bridging state. Typically used after a * Link Down event. */ @@ -603,7 +612,7 @@ static void cxgb4_getpfccfg(struct net_device *dev, int priority, u8 *pfccfg) struct port_info *pi = netdev2pinfo(dev); struct port_dcb_info *dcb = &pi->dcb; - if (dcb->state != CXGB4_DCB_STATE_FW_ALLSYNCED || + if (!cxgb4_dcb_state_synced(dcb->state) || priority >= CXGB4_MAX_PRIORITY) *pfccfg = 0; else @@ -620,7 +629,7 @@ static void cxgb4_setpfccfg(struct net_device *dev, int priority, u8 pfccfg) struct adapter *adap = pi->adapter; int err; - if (pi->dcb.state != CXGB4_DCB_STATE_FW_ALLSYNCED || + if (!cxgb4_dcb_state_synced(pi->dcb.state) || priority >= CXGB4_MAX_PRIORITY) return; @@ -732,7 +741,7 @@ static u8 cxgb4_getpfcstate(struct net_device *dev) { struct port_info *pi = netdev2pinfo(dev); - if (pi->dcb.state != CXGB4_DCB_STATE_FW_ALLSYNCED) + if (!cxgb4_dcb_state_synced(pi->dcb.state)) return false; return pi->dcb.pfcen != 0; @@ -756,7 +765,7 @@ static int __cxgb4_getapp(struct net_device *dev, u8 app_idtype, u16 app_id, struct adapter *adap = pi->adapter; int i; - if (pi->dcb.state != CXGB4_DCB_STATE_FW_ALLSYNCED) + if (!cxgb4_dcb_state_synced(pi->dcb.state)) return 0; for (i = 0; i < CXGB4_MAX_DCBX_APP_SUPPORTED; i++) { @@ -794,7 +803,9 @@ static int __cxgb4_getapp(struct net_device *dev, u8 app_idtype, u16 app_id, */ static int cxgb4_getapp(struct net_device *dev, u8 app_idtype, u16 app_id) { - return __cxgb4_getapp(dev, app_idtype, app_id, 0); + /* Convert app_idtype to firmware format before querying */ + return __cxgb4_getapp(dev, app_idtype == DCB_APP_IDTYPE_ETHTYPE ? + app_idtype : 3, app_id, 0); } /* Write a new Application User Priority Map for the specified Application ID @@ -808,7 +819,7 @@ static int __cxgb4_setapp(struct net_device *dev, u8 app_idtype, u16 app_id, int i, err; - if (pi->dcb.state != CXGB4_DCB_STATE_FW_ALLSYNCED) + if (!cxgb4_dcb_state_synced(pi->dcb.state)) return -EINVAL; /* DCB info gets thrown away on link up */ @@ -896,10 +907,11 @@ cxgb4_ieee_negotiation_complete(struct net_device *dev, struct port_info *pi = netdev2pinfo(dev); struct port_dcb_info *dcb = &pi->dcb; - if (dcb_subtype && !(dcb->msgs & dcb_subtype)) - return 0; + if (dcb->state == CXGB4_DCB_STATE_FW_ALLSYNCED) + if (dcb_subtype && !(dcb->msgs & dcb_subtype)) + return 0; - return (dcb->state == CXGB4_DCB_STATE_FW_ALLSYNCED && + return (cxgb4_dcb_state_synced(dcb->state) && (dcb->supported & DCB_CAP_DCBX_VER_IEEE)); } @@ -1057,7 +1069,7 @@ static u8 cxgb4_setdcbx(struct net_device *dev, u8 dcb_request) /* Can't enable DCB if we haven't successfully negotiated it. */ - if (pi->dcb.state != CXGB4_DCB_STATE_FW_ALLSYNCED) + if (!cxgb4_dcb_state_synced(pi->dcb.state)) return 1; /* There's currently no mechanism to allow for the firmware DCBX @@ -1080,7 +1092,7 @@ static int cxgb4_getpeer_app(struct net_device *dev, struct adapter *adap = pi->adapter; int i, err = 0; - if (pi->dcb.state != CXGB4_DCB_STATE_FW_ALLSYNCED) + if (!cxgb4_dcb_state_synced(pi->dcb.state)) return 1; info->willing = 0; @@ -1114,7 +1126,7 @@ static int cxgb4_getpeerapp_tbl(struct net_device *dev, struct dcb_app *table) struct adapter *adap = pi->adapter; int i, err = 0; - if (pi->dcb.state != CXGB4_DCB_STATE_FW_ALLSYNCED) + if (!cxgb4_dcb_state_synced(pi->dcb.state)) return 1; for (i = 0; i < CXGB4_MAX_DCBX_APP_SUPPORTED; i++) { @@ -1133,7 +1145,7 @@ static int cxgb4_getpeerapp_tbl(struct net_device *dev, struct dcb_app *table) if (!pcmd.u.dcb.app_priority.protocolid) break; - table[i].selector = pcmd.u.dcb.app_priority.sel_field; + table[i].selector = (pcmd.u.dcb.app_priority.sel_field + 1); table[i].protocol = be16_to_cpu(pcmd.u.dcb.app_priority.protocolid); table[i].priority = @@ -1181,6 +1193,8 @@ static int cxgb4_cee_peer_getpg(struct net_device *dev, struct cee_pg *pg) for (i = 0; i < CXGB4_MAX_PRIORITY; i++) pg->pg_bw[i] = pcmd.u.dcb.pgrate.pgrate[i]; + pg->tcs_supported = pcmd.u.dcb.pgrate.num_tcs_supported; + return 0; } @@ -1198,6 +1212,8 @@ static int cxgb4_cee_peer_getpfc(struct net_device *dev, struct cee_pfc *pfc) */ pfc->pfc_en = bitswap_1(pi->dcb.pfcen); + pfc->tcs_supported = pi->dcb.pfc_num_tcs_supported; + return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index a11485fbb33f..f701a6f20c6a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -151,6 +151,45 @@ static int cim_la_show_3in1(struct seq_file *seq, void *v, int idx) return 0; } +static int cim_la_show_t6(struct seq_file *seq, void *v, int idx) +{ + if (v == SEQ_START_TOKEN) { + seq_puts(seq, "Status Inst Data PC LS0Stat " + "LS0Addr LS0Data LS1Stat LS1Addr LS1Data\n"); + } else { + const u32 *p = v; + + seq_printf(seq, " %02x %04x%04x %04x%04x %04x%04x %08x %08x %08x %08x %08x %08x\n", + (p[9] >> 16) & 0xff, /* Status */ + p[9] & 0xffff, p[8] >> 16, /* Inst */ + p[8] & 0xffff, p[7] >> 16, /* Data */ + p[7] & 0xffff, p[6] >> 16, /* PC */ + p[2], p[1], p[0], /* LS0 Stat, Addr and Data */ + p[5], p[4], p[3]); /* LS1 Stat, Addr and Data */ + } + return 0; +} + +static int cim_la_show_pc_t6(struct seq_file *seq, void *v, int idx) +{ + if (v == SEQ_START_TOKEN) { + seq_puts(seq, "Status Inst Data PC\n"); + } else { + const u32 *p = v; + + seq_printf(seq, " %02x %08x %08x %08x\n", + p[3] & 0xff, p[2], p[1], p[0]); + seq_printf(seq, " %02x %02x%06x %02x%06x %02x%06x\n", + (p[6] >> 8) & 0xff, p[6] & 0xff, p[5] >> 8, + p[5] & 0xff, p[4] >> 8, p[4] & 0xff, p[3] >> 8); + seq_printf(seq, " %02x %04x%04x %04x%04x %04x%04x\n", + (p[9] >> 16) & 0xff, p[9] & 0xffff, p[8] >> 16, + p[8] & 0xffff, p[7] >> 16, p[7] & 0xffff, + p[6] >> 16); + } + return 0; +} + static int cim_la_open(struct inode *inode, struct file *file) { int ret; @@ -162,9 +201,18 @@ static int cim_la_open(struct inode *inode, struct file *file) if (ret) return ret; - p = seq_open_tab(file, adap->params.cim_la_size / 8, 8 * sizeof(u32), 1, - cfg & UPDBGLACAPTPCONLY_F ? - cim_la_show_3in1 : cim_la_show); + if (is_t6(adap->params.chip)) { + /* +1 to account for integer division of CIMLA_SIZE/10 */ + p = seq_open_tab(file, (adap->params.cim_la_size / 10) + 1, + 10 * sizeof(u32), 1, + cfg & UPDBGLACAPTPCONLY_F ? + cim_la_show_pc_t6 : cim_la_show_t6); + } else { + p = seq_open_tab(file, adap->params.cim_la_size / 8, + 8 * sizeof(u32), 1, + cfg & UPDBGLACAPTPCONLY_F ? cim_la_show_3in1 : + cim_la_show); + } if (!p) return -ENOMEM; @@ -2340,6 +2388,8 @@ int t4_setup_debugfs(struct adapter *adap) de = debugfs_create_file_size("flash", S_IRUSR, adap->debugfs_root, adap, &flash_debugfs_fops, adap->params.sf_size); + debugfs_create_bool("use_backdoor", S_IWUSR | S_IRUSR, + adap->debugfs_root, &adap->use_bd); return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 351f3b1bf800..d582e175dfb6 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -4757,7 +4757,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ cfg_queues(adapter); - adapter->l2t = t4_init_l2t(); + adapter->l2t = t4_init_l2t(adapter->l2t_start, adapter->l2t_end); if (!adapter->l2t) { /* We tolerate a lack of L2T, giving up some functionality */ dev_warn(&pdev->dev, "could not allocate L2T, continuing\n"); diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c index 252efc29321f..ac27898c6ab0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c @@ -51,24 +51,17 @@ #define VLAN_NONE 0xfff /* identifies sync vs async L2T_WRITE_REQs */ -#define F_SYNC_WR (1 << 12) - -enum { - L2T_STATE_VALID, /* entry is up to date */ - L2T_STATE_STALE, /* entry may be used but needs revalidation */ - L2T_STATE_RESOLVING, /* entry needs address resolution */ - L2T_STATE_SYNC_WRITE, /* synchronous write of entry underway */ - - /* when state is one of the below the entry is not hashed */ - L2T_STATE_SWITCHING, /* entry is being used by a switching filter */ - L2T_STATE_UNUSED /* entry not in use */ -}; +#define SYNC_WR_S 12 +#define SYNC_WR_V(x) ((x) << SYNC_WR_S) +#define SYNC_WR_F SYNC_WR_V(1) struct l2t_data { + unsigned int l2t_start; /* start index of our piece of the L2T */ + unsigned int l2t_size; /* number of entries in l2tab */ rwlock_t lock; atomic_t nfree; /* number of free entries */ struct l2t_entry *rover; /* starting point for next allocation */ - struct l2t_entry l2tab[L2T_SIZE]; + struct l2t_entry l2tab[0]; /* MUST BE LAST */ }; static inline unsigned int vlan_prio(const struct l2t_entry *e) @@ -85,29 +78,36 @@ static inline void l2t_hold(struct l2t_data *d, struct l2t_entry *e) /* * To avoid having to check address families we do not allow v4 and v6 * neighbors to be on the same hash chain. We keep v4 entries in the first - * half of available hash buckets and v6 in the second. + * half of available hash buckets and v6 in the second. We need at least two + * entries in our L2T for this scheme to work. */ enum { - L2T_SZ_HALF = L2T_SIZE / 2, - L2T_HASH_MASK = L2T_SZ_HALF - 1 + L2T_MIN_HASH_BUCKETS = 2, }; -static inline unsigned int arp_hash(const u32 *key, int ifindex) +static inline unsigned int arp_hash(struct l2t_data *d, const u32 *key, + int ifindex) { - return jhash_2words(*key, ifindex, 0) & L2T_HASH_MASK; + unsigned int l2t_size_half = d->l2t_size / 2; + + return jhash_2words(*key, ifindex, 0) % l2t_size_half; } -static inline unsigned int ipv6_hash(const u32 *key, int ifindex) +static inline unsigned int ipv6_hash(struct l2t_data *d, const u32 *key, + int ifindex) { + unsigned int l2t_size_half = d->l2t_size / 2; u32 xor = key[0] ^ key[1] ^ key[2] ^ key[3]; - return L2T_SZ_HALF + (jhash_2words(xor, ifindex, 0) & L2T_HASH_MASK); + return (l2t_size_half + + (jhash_2words(xor, ifindex, 0) % l2t_size_half)); } -static unsigned int addr_hash(const u32 *addr, int addr_len, int ifindex) +static unsigned int addr_hash(struct l2t_data *d, const u32 *addr, + int addr_len, int ifindex) { - return addr_len == 4 ? arp_hash(addr, ifindex) : - ipv6_hash(addr, ifindex); + return addr_len == 4 ? arp_hash(d, addr, ifindex) : + ipv6_hash(d, addr, ifindex); } /* @@ -139,6 +139,8 @@ static void neigh_replace(struct l2t_entry *e, struct neighbour *n) */ static int write_l2e(struct adapter *adap, struct l2t_entry *e, int sync) { + struct l2t_data *d = adap->l2t; + unsigned int l2t_idx = e->idx + d->l2t_start; struct sk_buff *skb; struct cpl_l2t_write_req *req; @@ -150,10 +152,10 @@ static int write_l2e(struct adapter *adap, struct l2t_entry *e, int sync) INIT_TP_WR(req, 0); OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_L2T_WRITE_REQ, - e->idx | (sync ? F_SYNC_WR : 0) | + l2t_idx | (sync ? SYNC_WR_F : 0) | TID_QID_V(adap->sge.fw_evtq.abs_id))); req->params = htons(L2T_W_PORT_V(e->lport) | L2T_W_NOREPLY_V(!sync)); - req->l2t_idx = htons(e->idx); + req->l2t_idx = htons(l2t_idx); req->vlan = htons(e->vlan); if (e->neigh && !(e->neigh->dev->flags & IFF_LOOPBACK)) memcpy(e->dmac, e->neigh->ha, sizeof(e->dmac)); @@ -190,18 +192,19 @@ static void send_pending(struct adapter *adap, struct l2t_entry *e) */ void do_l2t_write_rpl(struct adapter *adap, const struct cpl_l2t_write_rpl *rpl) { + struct l2t_data *d = adap->l2t; unsigned int tid = GET_TID(rpl); - unsigned int idx = tid & (L2T_SIZE - 1); + unsigned int l2t_idx = tid % L2T_SIZE; if (unlikely(rpl->status != CPL_ERR_NONE)) { dev_err(adap->pdev_dev, "Unexpected L2T_WRITE_RPL status %u for entry %u\n", - rpl->status, idx); + rpl->status, l2t_idx); return; } - if (tid & F_SYNC_WR) { - struct l2t_entry *e = &adap->l2t->l2tab[idx]; + if (tid & SYNC_WR_F) { + struct l2t_entry *e = &d->l2tab[l2t_idx - d->l2t_start]; spin_lock(&e->lock); if (e->state != L2T_STATE_SWITCHING) { @@ -276,7 +279,7 @@ static struct l2t_entry *alloc_l2e(struct l2t_data *d) return NULL; /* there's definitely a free entry */ - for (e = d->rover, end = &d->l2tab[L2T_SIZE]; e != end; ++e) + for (e = d->rover, end = &d->l2tab[d->l2t_size]; e != end; ++e) if (atomic_read(&e->refcnt) == 0) goto found; @@ -368,7 +371,7 @@ struct l2t_entry *cxgb4_l2t_get(struct l2t_data *d, struct neighbour *neigh, int addr_len = neigh->tbl->key_len; u32 *addr = (u32 *)neigh->primary_key; int ifidx = neigh->dev->ifindex; - int hash = addr_hash(addr, addr_len, ifidx); + int hash = addr_hash(d, addr, addr_len, ifidx); if (neigh->dev->flags & IFF_LOOPBACK) lport = netdev2pinfo(physdev)->tx_chan + 4; @@ -481,7 +484,7 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh) int addr_len = neigh->tbl->key_len; u32 *addr = (u32 *) neigh->primary_key; int ifidx = neigh->dev->ifindex; - int hash = addr_hash(addr, addr_len, ifidx); + int hash = addr_hash(d, addr, addr_len, ifidx); read_lock_bh(&d->lock); for (e = d->l2tab[hash].first; e; e = e->next) @@ -554,20 +557,30 @@ int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan, return write_l2e(adap, e, 0); } -struct l2t_data *t4_init_l2t(void) +struct l2t_data *t4_init_l2t(unsigned int l2t_start, unsigned int l2t_end) { + unsigned int l2t_size; int i; struct l2t_data *d; - d = t4_alloc_mem(sizeof(*d)); + if (l2t_start >= l2t_end || l2t_end >= L2T_SIZE) + return NULL; + l2t_size = l2t_end - l2t_start + 1; + if (l2t_size < L2T_MIN_HASH_BUCKETS) + return NULL; + + d = t4_alloc_mem(sizeof(*d) + l2t_size * sizeof(struct l2t_entry)); if (!d) return NULL; + d->l2t_start = l2t_start; + d->l2t_size = l2t_size; + d->rover = d->l2tab; - atomic_set(&d->nfree, L2T_SIZE); + atomic_set(&d->nfree, l2t_size); rwlock_init(&d->lock); - for (i = 0; i < L2T_SIZE; ++i) { + for (i = 0; i < d->l2t_size; ++i) { d->l2tab[i].idx = i; d->l2tab[i].state = L2T_STATE_UNUSED; spin_lock_init(&d->l2tab[i].lock); @@ -578,9 +591,9 @@ struct l2t_data *t4_init_l2t(void) static inline void *l2t_get_idx(struct seq_file *seq, loff_t pos) { - struct l2t_entry *l2tab = seq->private; + struct l2t_data *d = seq->private; - return pos >= L2T_SIZE ? NULL : &l2tab[pos]; + return pos >= d->l2t_size ? NULL : &d->l2tab[pos]; } static void *l2t_seq_start(struct seq_file *seq, loff_t *pos) @@ -620,6 +633,7 @@ static int l2t_seq_show(struct seq_file *seq, void *v) "Ethernet address VLAN/P LP State Users Port\n"); else { char ip[60]; + struct l2t_data *d = seq->private; struct l2t_entry *e = v; spin_lock_bh(&e->lock); @@ -628,7 +642,7 @@ static int l2t_seq_show(struct seq_file *seq, void *v) else sprintf(ip, e->v6 ? "%pI6c" : "%pI4", e->addr); seq_printf(seq, "%4u %-25s %17pM %4d %u %2u %c %5u %s\n", - e->idx, ip, e->dmac, + e->idx + d->l2t_start, ip, e->dmac, e->vlan & VLAN_VID_MASK, vlan_prio(e), e->lport, l2e_state(e), atomic_read(&e->refcnt), e->neigh ? e->neigh->dev->name : ""); @@ -652,7 +666,7 @@ static int l2t_seq_open(struct inode *inode, struct file *file) struct adapter *adap = inode->i_private; struct seq_file *seq = file->private_data; - seq->private = adap->l2t->l2tab; + seq->private = adap->l2t; } return rc; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.h b/drivers/net/ethernet/chelsio/cxgb4/l2t.h index a30126ce90cb..b38dc526aad5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.h +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.h @@ -39,6 +39,20 @@ #include <linux/if_ether.h> #include <linux/atomic.h> +enum { L2T_SIZE = 4096 }; /* # of L2T entries */ + +enum { + L2T_STATE_VALID, /* entry is up to date */ + L2T_STATE_STALE, /* entry may be used but needs revalidation */ + L2T_STATE_RESOLVING, /* entry needs address resolution */ + L2T_STATE_SYNC_WRITE, /* synchronous write of entry underway */ + L2T_STATE_NOARP, /* Netdev down or removed*/ + + /* when state is one of the below the entry is not hashed */ + L2T_STATE_SWITCHING, /* entry is being used by a switching filter */ + L2T_STATE_UNUSED /* entry not in use */ +}; + struct adapter; struct l2t_data; struct neighbour; @@ -56,7 +70,7 @@ struct cpl_l2t_write_rpl; */ struct l2t_entry { u16 state; /* entry state */ - u16 idx; /* entry index */ + u16 idx; /* entry index within in-memory table */ u32 addr[4]; /* next hop IP or IPv6 address */ int ifindex; /* neighbor's net_device's ifindex */ struct neighbour *neigh; /* associated neighbour */ @@ -104,7 +118,7 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh); struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d); int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan, u8 port, u8 *eth_addr); -struct l2t_data *t4_init_l2t(void); +struct l2t_data *t4_init_l2t(unsigned int l2t_start, unsigned int l2t_end); void do_l2t_write_rpl(struct adapter *p, const struct cpl_l2t_write_rpl *rpl); extern const struct file_operations t4_l2t_fops; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 942db078f33a..d4248d74f560 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -1137,7 +1137,7 @@ cxgb_fcoe_offload(struct sk_buff *skb, struct adapter *adap, */ netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev) { - u32 wr_mid; + u32 wr_mid, ctrl0; u64 cntrl, *end; int qidx, credits; unsigned int flits, ndesc; @@ -1274,9 +1274,15 @@ out_free: dev_kfree_skb_any(skb); #endif /* CONFIG_CHELSIO_T4_FCOE */ } - cpl->ctrl0 = htonl(TXPKT_OPCODE_V(CPL_TX_PKT_XT) | - TXPKT_INTF_V(pi->tx_chan) | - TXPKT_PF_V(adap->pf)); + ctrl0 = TXPKT_OPCODE_V(CPL_TX_PKT_XT) | TXPKT_INTF_V(pi->tx_chan) | + TXPKT_PF_V(adap->pf); +#ifdef CONFIG_CHELSIO_T4_DCB + if (is_t4(adap->params.chip)) + ctrl0 |= TXPKT_OVLAN_IDX_V(q->dcb_prio); + else + ctrl0 |= TXPKT_T5_OVLAN_IDX_V(q->dcb_prio); +#endif + cpl->ctrl0 = htonl(ctrl0); cpl->pack = htons(0); cpl->len = htons(skb->len); cpl->ctrl1 = cpu_to_be64(cntrl); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 2b52aae7ec86..800bd489dd75 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -1345,9 +1345,9 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x5a80, 0x5a9c, 0x5b94, 0x5bfc, 0x5c10, 0x5ec0, - 0x5ec8, 0x5ec8, + 0x5ec8, 0x5ecc, 0x6000, 0x6040, - 0x6058, 0x6154, + 0x6058, 0x615c, 0x7700, 0x7798, 0x77c0, 0x7880, 0x78cc, 0x78fc, @@ -1371,20 +1371,22 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x9f00, 0x9f6c, 0x9f80, 0xa020, 0xd004, 0xd03c, + 0xd100, 0xd118, + 0xd200, 0xd31c, 0xdfc0, 0xdfe0, 0xe000, 0xf008, 0x11000, 0x11014, 0x11048, 0x11110, 0x11118, 0x1117c, - 0x11190, 0x11260, + 0x11190, 0x11264, 0x11300, 0x1130c, - 0x12000, 0x1205c, + 0x12000, 0x1206c, 0x19040, 0x1906c, 0x19078, 0x19080, 0x1908c, 0x19124, 0x19150, 0x191b0, 0x191d0, 0x191e8, - 0x19238, 0x192b8, + 0x19238, 0x192bc, 0x193f8, 0x19474, 0x19490, 0x194cc, 0x194f0, 0x194f8, @@ -1466,7 +1468,7 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x30200, 0x30318, 0x30400, 0x3052c, 0x30540, 0x3061c, - 0x30800, 0x3088c, + 0x30800, 0x30890, 0x308c0, 0x30908, 0x30910, 0x309b8, 0x30a00, 0x30a04, @@ -1544,7 +1546,7 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x34200, 0x34318, 0x34400, 0x3452c, 0x34540, 0x3461c, - 0x34800, 0x3488c, + 0x34800, 0x34890, 0x348c0, 0x34908, 0x34910, 0x349b8, 0x34a00, 0x34a04, @@ -3687,6 +3689,11 @@ int t4_read_rss(struct adapter *adapter, u16 *map) return 0; } +static unsigned int t4_use_ldst(struct adapter *adap) +{ + return (adap->flags & FW_OK) || !adap->use_bd; +} + /** * t4_fw_tp_pio_rw - Access TP PIO through LDST * @adap: the adapter @@ -3730,7 +3737,7 @@ static void t4_fw_tp_pio_rw(struct adapter *adap, u32 *vals, unsigned int nregs, */ void t4_read_rss_key(struct adapter *adap, u32 *key) { - if (adap->flags & FW_OK) + if (t4_use_ldst(adap)) t4_fw_tp_pio_rw(adap, key, 10, TP_RSS_SECRET_KEY0_A, 1); else t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10, @@ -3760,7 +3767,7 @@ void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx) (vrt & KEYEXTEND_F) && (KEYMODE_G(vrt) == 3)) rss_key_addr_cnt = 32; - if (adap->flags & FW_OK) + if (t4_use_ldst(adap)) t4_fw_tp_pio_rw(adap, (void *)key, 10, TP_RSS_SECRET_KEY0_A, 0); else t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10, @@ -3789,7 +3796,7 @@ void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx) void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index, u32 *valp) { - if (adapter->flags & FW_OK) + if (t4_use_ldst(adapter)) t4_fw_tp_pio_rw(adapter, valp, 1, TP_RSS_PF0_CONFIG_A + index, 1); else @@ -3829,7 +3836,7 @@ void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index, /* Grab the VFL/VFH values ... */ - if (adapter->flags & FW_OK) { + if (t4_use_ldst(adapter)) { t4_fw_tp_pio_rw(adapter, vfl, 1, TP_RSS_VFL_CONFIG_A, 1); t4_fw_tp_pio_rw(adapter, vfh, 1, TP_RSS_VFH_CONFIG_A, 1); } else { @@ -3850,7 +3857,7 @@ u32 t4_read_rss_pf_map(struct adapter *adapter) { u32 pfmap; - if (adapter->flags & FW_OK) + if (t4_use_ldst(adapter)) t4_fw_tp_pio_rw(adapter, &pfmap, 1, TP_RSS_PF_MAP_A, 1); else t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, @@ -3868,7 +3875,7 @@ u32 t4_read_rss_pf_mask(struct adapter *adapter) { u32 pfmask; - if (adapter->flags & FW_OK) + if (t4_use_ldst(adapter)) t4_fw_tp_pio_rw(adapter, &pfmask, 1, TP_RSS_PF_MSK_A, 1); else t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A, @@ -3924,43 +3931,25 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4, */ void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st) { - /* T6 and later has 2 channels */ - if (adap->params.arch.nchan == NCHAN) { - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->mac_in_errs, 12, TP_MIB_MAC_IN_ERR_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tnl_cong_drops, 8, - TP_MIB_TNL_CNG_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tnl_tx_drops, 4, - TP_MIB_TNL_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->ofld_vlan_drops, 4, - TP_MIB_OFD_VLN_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tcp6_in_errs, 4, - TP_MIB_TCP_V6IN_ERR_0_A); - } else { - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->mac_in_errs, 2, TP_MIB_MAC_IN_ERR_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->hdr_in_errs, 2, TP_MIB_HDR_IN_ERR_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tcp_in_errs, 2, TP_MIB_TCP_IN_ERR_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tnl_cong_drops, 2, - TP_MIB_TNL_CNG_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->ofld_chan_drops, 2, - TP_MIB_OFD_CHN_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tnl_tx_drops, 2, TP_MIB_TNL_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->ofld_vlan_drops, 2, - TP_MIB_OFD_VLN_DROP_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, - st->tcp6_in_errs, 2, TP_MIB_TCP_V6IN_ERR_0_A); - } + int nchan = adap->params.arch.nchan; + + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->mac_in_errs, nchan, TP_MIB_MAC_IN_ERR_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->hdr_in_errs, nchan, TP_MIB_HDR_IN_ERR_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tcp_in_errs, nchan, TP_MIB_TCP_IN_ERR_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tnl_cong_drops, nchan, TP_MIB_TNL_CNG_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->ofld_chan_drops, nchan, TP_MIB_OFD_CHN_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tnl_tx_drops, nchan, TP_MIB_TNL_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->ofld_vlan_drops, nchan, TP_MIB_OFD_VLN_DROP_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, + st->tcp6_in_errs, nchan, TP_MIB_TCP_V6IN_ERR_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->ofld_no_neigh, 2, TP_MIB_OFD_ARP_DROP_A); } @@ -3974,16 +3963,13 @@ void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st) */ void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st) { - /* T6 and later has 2 channels */ - if (adap->params.arch.nchan == NCHAN) { - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->req, - 8, TP_MIB_CPL_IN_REQ_0_A); - } else { - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->req, - 2, TP_MIB_CPL_IN_REQ_0_A); - t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->rsp, - 2, TP_MIB_CPL_OUT_RSP_0_A); - } + int nchan = adap->params.arch.nchan; + + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->req, + nchan, TP_MIB_CPL_IN_REQ_0_A); + t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->rsp, + nchan, TP_MIB_CPL_OUT_RSP_0_A); + } /** @@ -6294,7 +6280,7 @@ int t4_init_tp_params(struct adapter *adap) /* Cache the adapter's Compressed Filter Mode and global Incress * Configuration. */ - if (adap->flags & FW_OK) { + if (t4_use_ldst(adap)) { t4_fw_tp_pio_rw(adap, &adap->params.tp.vlan_pri_map, 1, TP_VLAN_PRI_MAP_A, 1); t4_fw_tp_pio_rw(adap, &adap->params.tp.ingress_config, 1, diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h index c8488f430d19..640369df8b3a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h @@ -47,7 +47,6 @@ enum { TCB_SIZE = 128, /* TCB size */ NMTUS = 16, /* size of MTU table */ NCCTRL_WIN = 32, /* # of congestion control windows */ - L2T_SIZE = 4096, /* # of L2T entries */ PM_NSTATS = 5, /* # of PM stats */ MBOX_LEN = 64, /* mailbox size in bytes */ TRACE_LEN = 112, /* length of trace data and mask */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index 132cb8fc0bf7..b99144afd4ec 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -660,6 +660,9 @@ struct cpl_tx_pkt { #define TXPKT_OVLAN_IDX_S 12 #define TXPKT_OVLAN_IDX_V(x) ((x) << TXPKT_OVLAN_IDX_S) +#define TXPKT_T5_OVLAN_IDX_S 12 +#define TXPKT_T5_OVLAN_IDX_V(x) ((x) << TXPKT_T5_OVLAN_IDX_S) + #define TXPKT_INTF_S 16 #define TXPKT_INTF_V(x) ((x) << TXPKT_INTF_S) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index d7ca106927b0..8353a6cbfcc2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -142,6 +142,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x5013), /* T580-chr */ CH_PCI_ID_TABLE_FENTRY(0x5014), /* T580-so */ CH_PCI_ID_TABLE_FENTRY(0x5015), /* T502-bt */ + CH_PCI_ID_TABLE_FENTRY(0x5016), /* T580-OCP-SO */ + CH_PCI_ID_TABLE_FENTRY(0x5017), /* T520-OCP-SO */ CH_PCI_ID_TABLE_FENTRY(0x5080), /* Custom T540-cr */ CH_PCI_ID_TABLE_FENTRY(0x5081), /* Custom T540-LL-cr */ CH_PCI_ID_TABLE_FENTRY(0x5082), /* Custom T504-cr */ @@ -155,6 +157,22 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x5090), /* Custom T540-CR */ CH_PCI_ID_TABLE_FENTRY(0x5091), /* Custom T522-CR */ CH_PCI_ID_TABLE_FENTRY(0x5092), /* Custom T520-CR */ + + /* T6 adapters: + */ + CH_PCI_ID_TABLE_FENTRY(0x6001), + CH_PCI_ID_TABLE_FENTRY(0x6002), + CH_PCI_ID_TABLE_FENTRY(0x6003), + CH_PCI_ID_TABLE_FENTRY(0x6004), + CH_PCI_ID_TABLE_FENTRY(0x6005), + CH_PCI_ID_TABLE_FENTRY(0x6006), + CH_PCI_ID_TABLE_FENTRY(0x6007), + CH_PCI_ID_TABLE_FENTRY(0x6009), + CH_PCI_ID_TABLE_FENTRY(0x600d), + CH_PCI_ID_TABLE_FENTRY(0x6010), + CH_PCI_ID_TABLE_FENTRY(0x6011), + CH_PCI_ID_TABLE_FENTRY(0x6014), + CH_PCI_ID_TABLE_FENTRY(0x6015), CH_PCI_DEVICE_ID_TABLE_DEFINE_END; #endif /* __T4_PCI_ID_TBL_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index ad53e5ad2acd..1d5e77a566e1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -1898,7 +1898,10 @@ static int napi_rx_handler(struct napi_struct *napi, int budget) rspq->unhandled_irqs++; val = CIDXINC_V(work_done) | SEINTARM_V(intr_params); - if (is_t4(rspq->adapter->params.chip)) { + /* If we don't have access to the new User GTS (T5+), use the old + * doorbell mechanism; otherwise use the new BAR2 mechanism. + */ + if (unlikely(!rspq->bar2_addr)) { t4_write_reg(rspq->adapter, T4VF_SGE_BASE_ADDR + SGE_VF_GTS, val | INGRESSQID_V((u32)rspq->cntxt_id)); @@ -1998,10 +2001,13 @@ static unsigned int process_intrq(struct adapter *adapter) } val = CIDXINC_V(work_done) | SEINTARM_V(intrq->intr_params); - if (is_t4(adapter->params.chip)) + /* If we don't have access to the new User GTS (T5+), use the old + * doorbell mechanism; otherwise use the new BAR2 mechanism. + */ + if (unlikely(!intrq->bar2_addr)) { t4_write_reg(adapter, T4VF_SGE_BASE_ADDR + SGE_VF_GTS, val | INGRESSQID_V(intrq->cntxt_id)); - else { + } else { writel(val | INGRESSQID_V(intrq->bar2_qid), intrq->bar2_addr + SGE_UDB_GTS); wmb(); diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c index f3f1601a76f3..f44a39c40642 100644 --- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -224,7 +224,8 @@ static int enic_get_coalesce(struct net_device *netdev, struct enic *enic = netdev_priv(netdev); struct enic_rx_coal *rxcoal = &enic->rx_coalesce_setting; - ecmd->tx_coalesce_usecs = enic->tx_coalesce_usecs; + if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX) + ecmd->tx_coalesce_usecs = enic->tx_coalesce_usecs; ecmd->rx_coalesce_usecs = enic->rx_coalesce_usecs; if (rxcoal->use_adaptive_rx_coalesce) ecmd->use_adaptive_rx_coalesce = 1; @@ -234,6 +235,53 @@ static int enic_get_coalesce(struct net_device *netdev, return 0; } +static int enic_coalesce_valid(struct enic *enic, + struct ethtool_coalesce *ec) +{ + u32 coalesce_usecs_max = vnic_dev_get_intr_coal_timer_max(enic->vdev); + u32 rx_coalesce_usecs_high = min_t(u32, coalesce_usecs_max, + ec->rx_coalesce_usecs_high); + u32 rx_coalesce_usecs_low = min_t(u32, coalesce_usecs_max, + ec->rx_coalesce_usecs_low); + + if (ec->rx_max_coalesced_frames || + ec->rx_coalesce_usecs_irq || + ec->rx_max_coalesced_frames_irq || + ec->tx_max_coalesced_frames || + ec->tx_coalesce_usecs_irq || + ec->tx_max_coalesced_frames_irq || + ec->stats_block_coalesce_usecs || + ec->use_adaptive_tx_coalesce || + ec->pkt_rate_low || + ec->rx_max_coalesced_frames_low || + ec->tx_coalesce_usecs_low || + ec->tx_max_coalesced_frames_low || + ec->pkt_rate_high || + ec->rx_max_coalesced_frames_high || + ec->tx_coalesce_usecs_high || + ec->tx_max_coalesced_frames_high || + ec->rate_sample_interval) + return -EINVAL; + + if ((vnic_dev_get_intr_mode(enic->vdev) != VNIC_DEV_INTR_MODE_MSIX) && + ec->tx_coalesce_usecs) + return -EINVAL; + + if ((ec->tx_coalesce_usecs > coalesce_usecs_max) || + (ec->rx_coalesce_usecs > coalesce_usecs_max) || + (ec->rx_coalesce_usecs_low > coalesce_usecs_max) || + (ec->rx_coalesce_usecs_high > coalesce_usecs_max)) + netdev_info(enic->netdev, "ethtool_set_coalesce: adaptor supports max coalesce value of %d. Setting max value.\n", + coalesce_usecs_max); + + if (ec->rx_coalesce_usecs_high && + (rx_coalesce_usecs_high < + rx_coalesce_usecs_low + ENIC_AIC_LARGE_PKT_DIFF)) + return -EINVAL; + + return 0; +} + static int enic_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecmd) { @@ -244,8 +292,12 @@ static int enic_set_coalesce(struct net_device *netdev, u32 rx_coalesce_usecs_high; u32 coalesce_usecs_max; unsigned int i, intr; + int ret; struct enic_rx_coal *rxcoal = &enic->rx_coalesce_setting; + ret = enic_coalesce_valid(enic, ecmd); + if (ret) + return ret; coalesce_usecs_max = vnic_dev_get_intr_coal_timer_max(enic->vdev); tx_coalesce_usecs = min_t(u32, ecmd->tx_coalesce_usecs, coalesce_usecs_max); @@ -257,59 +309,24 @@ static int enic_set_coalesce(struct net_device *netdev, rx_coalesce_usecs_high = min_t(u32, ecmd->rx_coalesce_usecs_high, coalesce_usecs_max); - switch (vnic_dev_get_intr_mode(enic->vdev)) { - case VNIC_DEV_INTR_MODE_INTX: - if (tx_coalesce_usecs != rx_coalesce_usecs) - return -EINVAL; - if (ecmd->use_adaptive_rx_coalesce || - ecmd->rx_coalesce_usecs_low || - ecmd->rx_coalesce_usecs_high) - return -EINVAL; - - intr = enic_legacy_io_intr(); - vnic_intr_coalescing_timer_set(&enic->intr[intr], - tx_coalesce_usecs); - break; - case VNIC_DEV_INTR_MODE_MSI: - if (tx_coalesce_usecs != rx_coalesce_usecs) - return -EINVAL; - if (ecmd->use_adaptive_rx_coalesce || - ecmd->rx_coalesce_usecs_low || - ecmd->rx_coalesce_usecs_high) - return -EINVAL; - - vnic_intr_coalescing_timer_set(&enic->intr[0], - tx_coalesce_usecs); - break; - case VNIC_DEV_INTR_MODE_MSIX: - if (ecmd->rx_coalesce_usecs_high && - (rx_coalesce_usecs_high < - rx_coalesce_usecs_low + ENIC_AIC_LARGE_PKT_DIFF)) - return -EINVAL; - + if (vnic_dev_get_intr_mode(enic->vdev) == VNIC_DEV_INTR_MODE_MSIX) { for (i = 0; i < enic->wq_count; i++) { intr = enic_msix_wq_intr(enic, i); vnic_intr_coalescing_timer_set(&enic->intr[intr], - tx_coalesce_usecs); - } - - rxcoal->use_adaptive_rx_coalesce = - !!ecmd->use_adaptive_rx_coalesce; - if (!rxcoal->use_adaptive_rx_coalesce) - enic_intr_coal_set_rx(enic, rx_coalesce_usecs); - - if (ecmd->rx_coalesce_usecs_high) { - rxcoal->range_end = rx_coalesce_usecs_high; - rxcoal->small_pkt_range_start = rx_coalesce_usecs_low; - rxcoal->large_pkt_range_start = rx_coalesce_usecs_low + - ENIC_AIC_LARGE_PKT_DIFF; + tx_coalesce_usecs); } - break; - default: - break; + enic->tx_coalesce_usecs = tx_coalesce_usecs; + } + rxcoal->use_adaptive_rx_coalesce = !!ecmd->use_adaptive_rx_coalesce; + if (!rxcoal->use_adaptive_rx_coalesce) + enic_intr_coal_set_rx(enic, rx_coalesce_usecs); + if (ecmd->rx_coalesce_usecs_high) { + rxcoal->range_end = rx_coalesce_usecs_high; + rxcoal->small_pkt_range_start = rx_coalesce_usecs_low; + rxcoal->large_pkt_range_start = rx_coalesce_usecs_low + + ENIC_AIC_LARGE_PKT_DIFF; } - enic->tx_coalesce_usecs = tx_coalesce_usecs; enic->rx_coalesce_usecs = rx_coalesce_usecs; return 0; diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 918a8e42139b..8f646e4e968b 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1149,6 +1149,64 @@ static int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, return 0; } +static void enic_set_int_moderation(struct enic *enic, struct vnic_rq *rq) +{ + unsigned int intr = enic_msix_rq_intr(enic, rq->index); + struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)]; + u32 timer = cq->tobe_rx_coal_timeval; + + if (cq->tobe_rx_coal_timeval != cq->cur_rx_coal_timeval) { + vnic_intr_coalescing_timer_set(&enic->intr[intr], timer); + cq->cur_rx_coal_timeval = cq->tobe_rx_coal_timeval; + } +} + +static void enic_calc_int_moderation(struct enic *enic, struct vnic_rq *rq) +{ + struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting; + struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)]; + struct vnic_rx_bytes_counter *pkt_size_counter = &cq->pkt_size_counter; + int index; + u32 timer; + u32 range_start; + u32 traffic; + u64 delta; + ktime_t now = ktime_get(); + + delta = ktime_us_delta(now, cq->prev_ts); + if (delta < ENIC_AIC_TS_BREAK) + return; + cq->prev_ts = now; + + traffic = pkt_size_counter->large_pkt_bytes_cnt + + pkt_size_counter->small_pkt_bytes_cnt; + /* The table takes Mbps + * traffic *= 8 => bits + * traffic *= (10^6 / delta) => bps + * traffic /= 10^6 => Mbps + * + * Combining, traffic *= (8 / delta) + */ + + traffic <<= 3; + traffic = delta > UINT_MAX ? 0 : traffic / (u32)delta; + + for (index = 0; index < ENIC_MAX_COALESCE_TIMERS; index++) + if (traffic < mod_table[index].rx_rate) + break; + range_start = (pkt_size_counter->small_pkt_bytes_cnt > + pkt_size_counter->large_pkt_bytes_cnt << 1) ? + rx_coal->small_pkt_range_start : + rx_coal->large_pkt_range_start; + timer = range_start + ((rx_coal->range_end - range_start) * + mod_table[index].range_percent / 100); + /* Damping */ + cq->tobe_rx_coal_timeval = (timer + cq->tobe_rx_coal_timeval) >> 1; + + pkt_size_counter->large_pkt_bytes_cnt = 0; + pkt_size_counter->small_pkt_bytes_cnt = 0; +} + static int enic_poll(struct napi_struct *napi, int budget) { struct net_device *netdev = napi->dev; @@ -1199,6 +1257,11 @@ static int enic_poll(struct napi_struct *napi, int budget) if (err) rq_work_done = rq_work_to_do; + if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce) + /* Call the function which refreshes the intr coalescing timer + * value based on the traffic. + */ + enic_calc_int_moderation(enic, &enic->rq[0]); if (rq_work_done < rq_work_to_do) { @@ -1207,70 +1270,14 @@ static int enic_poll(struct napi_struct *napi, int budget) */ napi_complete(napi); + if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce) + enic_set_int_moderation(enic, &enic->rq[0]); vnic_intr_unmask(&enic->intr[intr]); } return rq_work_done; } -static void enic_set_int_moderation(struct enic *enic, struct vnic_rq *rq) -{ - unsigned int intr = enic_msix_rq_intr(enic, rq->index); - struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)]; - u32 timer = cq->tobe_rx_coal_timeval; - - if (cq->tobe_rx_coal_timeval != cq->cur_rx_coal_timeval) { - vnic_intr_coalescing_timer_set(&enic->intr[intr], timer); - cq->cur_rx_coal_timeval = cq->tobe_rx_coal_timeval; - } -} - -static void enic_calc_int_moderation(struct enic *enic, struct vnic_rq *rq) -{ - struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting; - struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)]; - struct vnic_rx_bytes_counter *pkt_size_counter = &cq->pkt_size_counter; - int index; - u32 timer; - u32 range_start; - u32 traffic; - u64 delta; - ktime_t now = ktime_get(); - - delta = ktime_us_delta(now, cq->prev_ts); - if (delta < ENIC_AIC_TS_BREAK) - return; - cq->prev_ts = now; - - traffic = pkt_size_counter->large_pkt_bytes_cnt + - pkt_size_counter->small_pkt_bytes_cnt; - /* The table takes Mbps - * traffic *= 8 => bits - * traffic *= (10^6 / delta) => bps - * traffic /= 10^6 => Mbps - * - * Combining, traffic *= (8 / delta) - */ - - traffic <<= 3; - traffic = delta > UINT_MAX ? 0 : traffic / (u32)delta; - - for (index = 0; index < ENIC_MAX_COALESCE_TIMERS; index++) - if (traffic < mod_table[index].rx_rate) - break; - range_start = (pkt_size_counter->small_pkt_bytes_cnt > - pkt_size_counter->large_pkt_bytes_cnt << 1) ? - rx_coal->small_pkt_range_start : - rx_coal->large_pkt_range_start; - timer = range_start + ((rx_coal->range_end - range_start) * - mod_table[index].range_percent / 100); - /* Damping */ - cq->tobe_rx_coal_timeval = (timer + cq->tobe_rx_coal_timeval) >> 1; - - pkt_size_counter->large_pkt_bytes_cnt = 0; - pkt_size_counter->small_pkt_bytes_cnt = 0; -} - #ifdef CONFIG_RFS_ACCEL static void enic_free_rx_cpu_rmap(struct enic *enic) { @@ -1407,10 +1414,8 @@ static int enic_poll_msix_rq(struct napi_struct *napi, int budget) if (err) work_done = work_to_do; if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce) - /* Call the function which refreshes - * the intr coalescing timer value based on - * the traffic. This is supported only in - * the case of MSI-x mode + /* Call the function which refreshes the intr coalescing timer + * value based on the traffic. */ enic_calc_int_moderation(enic, &enic->rq[rq]); @@ -1569,12 +1574,6 @@ static void enic_set_rx_coal_setting(struct enic *enic) int index = -1; struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting; - /* If intr mode is not MSIX, do not do adaptive coalescing */ - if (VNIC_DEV_INTR_MODE_MSIX != vnic_dev_get_intr_mode(enic->vdev)) { - netdev_info(enic->netdev, "INTR mode is not MSIX, Not initializing adaptive coalescing"); - return; - } - /* 1. Read the link speed from fw * 2. Pick the default range for the speed * 3. Update it in enic->rx_coalesce_setting diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c index d1017509b08a..f7b42483921c 100644 --- a/drivers/net/ethernet/ec_bhf.c +++ b/drivers/net/ethernet/ec_bhf.c @@ -604,19 +604,7 @@ static struct pci_driver pci_driver = { .probe = ec_bhf_probe, .remove = ec_bhf_remove, }; - -static int __init ec_bhf_init(void) -{ - return pci_register_driver(&pci_driver); -} - -static void __exit ec_bhf_exit(void) -{ - pci_unregister_driver(&pci_driver); -} - -module_init(ec_bhf_init); -module_exit(ec_bhf_exit); +module_pci_driver(pci_driver); module_param(polling_frequency, long, S_IRUGO); MODULE_PARM_DESC(polling_frequency, "Polling timer frequency in ns"); diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 8d12b41b3b19..cb5777bb7429 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -37,7 +37,7 @@ #include "be_hw.h" #include "be_roce.h" -#define DRV_VER "10.6.0.2" +#define DRV_VER "10.6.0.3" #define DRV_NAME "be2net" #define BE_NAME "Emulex BladeEngine2" #define BE3_NAME "Emulex BladeEngine3" diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 9eac3227d2ca..ecad46f79653 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -88,19 +88,21 @@ static inline void *embedded_payload(struct be_mcc_wrb *wrb) return wrb->payload.embedded_payload; } -static void be_mcc_notify(struct be_adapter *adapter) +static int be_mcc_notify(struct be_adapter *adapter) { struct be_queue_info *mccq = &adapter->mcc_obj.q; u32 val = 0; if (be_check_error(adapter, BE_ERROR_ANY)) - return; + return -EIO; val |= mccq->id & DB_MCCQ_RING_ID_MASK; val |= 1 << DB_MCCQ_NUM_POSTED_SHIFT; wmb(); iowrite32(val, adapter->db + DB_MCCQ_OFFSET); + + return 0; } /* To check if valid bit is set, check the entire word as we don't know @@ -170,6 +172,12 @@ static void be_async_cmd_process(struct be_adapter *adapter, return; } + if (opcode == OPCODE_LOWLEVEL_SET_LOOPBACK_MODE && + subsystem == CMD_SUBSYSTEM_LOWLEVEL) { + complete(&adapter->et_cmd_compl); + return; + } + if ((opcode == OPCODE_COMMON_WRITE_FLASHROM || opcode == OPCODE_COMMON_WRITE_OBJECT) && subsystem == CMD_SUBSYSTEM_COMMON) { @@ -541,7 +549,9 @@ static int be_mcc_notify_wait(struct be_adapter *adapter) resp = be_decode_resp_hdr(wrb->tag0, wrb->tag1); - be_mcc_notify(adapter); + status = be_mcc_notify(adapter); + if (status) + goto out; status = be_mcc_wait_compl(adapter); if (status == -EIO) @@ -1547,7 +1557,10 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd) else hdr->version = 2; - be_mcc_notify(adapter); + status = be_mcc_notify(adapter); + if (status) + goto err; + adapter->stats_cmd_sent = true; err: @@ -1583,7 +1596,10 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter, req->cmd_params.params.pport_num = cpu_to_le16(adapter->hba_port_num); req->cmd_params.params.reset_stats = 0; - be_mcc_notify(adapter); + status = be_mcc_notify(adapter); + if (status) + goto err; + adapter->stats_cmd_sent = true; err: @@ -1687,8 +1703,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter) OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES, sizeof(*req), wrb, NULL); - be_mcc_notify(adapter); - + status = be_mcc_notify(adapter); err: spin_unlock_bh(&adapter->mcc_lock); return status; @@ -1860,7 +1875,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter, cpu_to_le32(set_eqd[i].delay_multiplier); } - be_mcc_notify(adapter); + status = be_mcc_notify(adapter); err: spin_unlock_bh(&adapter->mcc_lock); return status; @@ -1953,7 +1968,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value) memcpy(req->mcast_mac[i++].byte, ha->addr, ETH_ALEN); } - status = be_mcc_notify_wait(adapter); + status = be_mcc_notify(adapter); err: spin_unlock_bh(&adapter->mcc_lock); return status; @@ -2320,7 +2335,10 @@ int lancer_cmd_write_object(struct be_adapter *adapter, struct be_dma_mem *cmd, req->addr_high = cpu_to_le32(upper_32_bits(cmd->dma + sizeof(struct lancer_cmd_req_write_object))); - be_mcc_notify(adapter); + status = be_mcc_notify(adapter); + if (status) + goto err_unlock; + spin_unlock_bh(&adapter->mcc_lock); if (!wait_for_completion_timeout(&adapter->et_cmd_compl, @@ -2491,7 +2509,10 @@ int be_cmd_write_flashrom(struct be_adapter *adapter, struct be_dma_mem *cmd, req->params.op_code = cpu_to_le32(flash_opcode); req->params.data_buf_size = cpu_to_le32(buf_size); - be_mcc_notify(adapter); + status = be_mcc_notify(adapter); + if (status) + goto err_unlock; + spin_unlock_bh(&adapter->mcc_lock); if (!wait_for_completion_timeout(&adapter->et_cmd_compl, @@ -2585,7 +2606,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num, wrb = wrb_from_mccq(adapter); if (!wrb) { status = -EBUSY; - goto err; + goto err_unlock; } req = embedded_payload(wrb); @@ -2599,8 +2620,19 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num, req->loopback_type = loopback_type; req->loopback_state = enable; - status = be_mcc_notify_wait(adapter); -err: + status = be_mcc_notify(adapter); + if (status) + goto err_unlock; + + spin_unlock_bh(&adapter->mcc_lock); + + if (!wait_for_completion_timeout(&adapter->et_cmd_compl, + msecs_to_jiffies(SET_LB_MODE_TIMEOUT))) + status = -ETIMEDOUT; + + return status; + +err_unlock: spin_unlock_bh(&adapter->mcc_lock); return status; } @@ -2636,7 +2668,9 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num, req->num_pkts = cpu_to_le32(num_pkts); req->loopback_type = cpu_to_le32(loopback_type); - be_mcc_notify(adapter); + status = be_mcc_notify(adapter); + if (status) + goto err; spin_unlock_bh(&adapter->mcc_lock); diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 2716e6f30d9a..a4479f7488d3 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -1495,6 +1495,8 @@ struct be_cmd_resp_acpi_wol_magic_config_v1 { #define BE_PME_D3COLD_CAP 0x80 /********************** LoopBack test *********************/ +#define SET_LB_MODE_TIMEOUT 12000 + struct be_cmd_req_loopback_test { struct be_cmd_req_hdr hdr; u32 loopback_type; @@ -1758,6 +1760,7 @@ struct be_cmd_req_set_mac_list { /*********************** HSW Config ***********************/ #define PORT_FWD_TYPE_VEPA 0x3 #define PORT_FWD_TYPE_VEB 0x2 +#define PORT_FWD_TYPE_PASSTHRU 0x1 #define ENABLE_MAC_SPOOFCHK 0x2 #define DISABLE_MAC_SPOOFCHK 0x3 diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index b2476dbfd103..d20ff054c1f7 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -847,10 +847,21 @@ err: static u64 be_loopback_test(struct be_adapter *adapter, u8 loopback_type, u64 *status) { - be_cmd_set_loopback(adapter, adapter->hba_port_num, loopback_type, 1); + int ret; + + ret = be_cmd_set_loopback(adapter, adapter->hba_port_num, + loopback_type, 1); + if (ret) + return ret; + *status = be_cmd_loopback_test(adapter, adapter->hba_port_num, loopback_type, 1500, 2, 0xabc); - be_cmd_set_loopback(adapter, adapter->hba_port_num, BE_NO_LOOPBACK, 1); + + ret = be_cmd_set_loopback(adapter, adapter->hba_port_num, + BE_NO_LOOPBACK, 1); + if (ret) + return ret; + return *status; } diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 6f642426308c..c996dd76f546 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1254,7 +1254,7 @@ static bool be_send_pkt_to_bmc(struct be_adapter *adapter, if (is_udp_pkt((*skb))) { struct udphdr *udp = udp_hdr((*skb)); - switch (udp->dest) { + switch (ntohs(udp->dest)) { case DHCP_CLIENT_PORT: os2bmc = is_dhcp_client_filt_enabled(adapter); goto done; @@ -3529,15 +3529,15 @@ err: static int be_setup_wol(struct be_adapter *adapter, bool enable) { + struct device *dev = &adapter->pdev->dev; struct be_dma_mem cmd; - int status = 0; u8 mac[ETH_ALEN]; + int status; eth_zero_addr(mac); cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config); - cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma, - GFP_KERNEL); + cmd.va = dma_zalloc_coherent(dev, cmd.size, &cmd.dma, GFP_KERNEL); if (!cmd.va) return -ENOMEM; @@ -3546,24 +3546,18 @@ static int be_setup_wol(struct be_adapter *adapter, bool enable) PCICFG_PM_CONTROL_OFFSET, PCICFG_PM_CONTROL_MASK); if (status) { - dev_err(&adapter->pdev->dev, - "Could not enable Wake-on-lan\n"); - dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, - cmd.dma); - return status; + dev_err(dev, "Could not enable Wake-on-lan\n"); + goto err; } - status = be_cmd_enable_magic_wol(adapter, - adapter->netdev->dev_addr, - &cmd); - pci_enable_wake(adapter->pdev, PCI_D3hot, 1); - pci_enable_wake(adapter->pdev, PCI_D3cold, 1); } else { - status = be_cmd_enable_magic_wol(adapter, mac, &cmd); - pci_enable_wake(adapter->pdev, PCI_D3hot, 0); - pci_enable_wake(adapter->pdev, PCI_D3cold, 0); + ether_addr_copy(mac, adapter->netdev->dev_addr); } - dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma); + status = be_cmd_enable_magic_wol(adapter, mac, &cmd); + pci_enable_wake(adapter->pdev, PCI_D3hot, enable); + pci_enable_wake(adapter->pdev, PCI_D3cold, enable); +err: + dma_free_coherent(dev, cmd.size, cmd.va, cmd.dma); return status; } @@ -4924,7 +4918,7 @@ static bool be_check_ufi_compatibility(struct be_adapter *adapter, { if (!fhdr) { dev_err(&adapter->pdev->dev, "Invalid FW UFI file"); - return -1; + return false; } /* First letter of the build version is used to identify @@ -5079,9 +5073,6 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, int status = 0; u8 hsw_mode; - if (!sriov_enabled(adapter)) - return 0; - /* BE and Lancer chips support VEB mode only */ if (BEx_chip(adapter) || lancer_chip(adapter)) { hsw_mode = PORT_FWD_TYPE_VEB; @@ -5091,6 +5082,9 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, NULL); if (status) return 0; + + if (hsw_mode == PORT_FWD_TYPE_PASSTHRU) + return 0; } return ndo_dflt_bridge_getlink(skb, pid, seq, dev, @@ -5813,7 +5807,6 @@ static int be_pci_resume(struct pci_dev *pdev) if (status) return status; - pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); status = be_resume(adapter); @@ -5893,7 +5886,6 @@ static pci_ers_result_t be_eeh_reset(struct pci_dev *pdev) return PCI_ERS_RESULT_DISCONNECT; pci_set_master(pdev); - pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); /* Check if card is ok and fw is ready */ diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index a15663ad7f5e..7a8386a8244d 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -506,12 +506,6 @@ int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr) break; default: - /* - * register RXMTRL must be set in order to do V1 packets, - * therefore it is not possible to time stamp both V1 Sync and - * Delay_Req messages and hardware does not support - * timestamping all packets => return error - */ fep->hwts_rx_en = 1; config.rx_filter = HWTSTAMP_FILTER_ALL; break; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index ff875028fdff..648ca85c5859 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -109,15 +109,15 @@ #define TX_TIMEOUT (1*HZ) -const char gfar_driver_version[] = "1.3"; +const char gfar_driver_version[] = "2.0"; static int gfar_enet_open(struct net_device *dev); static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev); static void gfar_reset_task(struct work_struct *work); static void gfar_timeout(struct net_device *dev); static int gfar_close(struct net_device *dev); -static struct sk_buff *gfar_new_skb(struct net_device *dev, - dma_addr_t *bufaddr); +static void gfar_alloc_rx_buffs(struct gfar_priv_rx_q *rx_queue, + int alloc_cnt); static int gfar_set_mac_address(struct net_device *dev); static int gfar_change_mtu(struct net_device *dev, int new_mtu); static irqreturn_t gfar_error(int irq, void *dev_id); @@ -141,8 +141,7 @@ static void gfar_netpoll(struct net_device *dev); #endif int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit); static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue); -static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb, - int amount_pull, struct napi_struct *napi); +static void gfar_process_frame(struct net_device *ndev, struct sk_buff *skb); static void gfar_halt_nodisable(struct gfar_private *priv); static void gfar_clear_exact_match(struct net_device *dev); static void gfar_set_mac_for_addr(struct net_device *dev, int num, @@ -169,17 +168,15 @@ static void gfar_init_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp, bdp->lstatus = cpu_to_be32(lstatus); } -static int gfar_init_bds(struct net_device *ndev) +static void gfar_init_bds(struct net_device *ndev) { struct gfar_private *priv = netdev_priv(ndev); struct gfar __iomem *regs = priv->gfargrp[0].regs; struct gfar_priv_tx_q *tx_queue = NULL; struct gfar_priv_rx_q *rx_queue = NULL; struct txbd8 *txbdp; - struct rxbd8 *rxbdp; u32 __iomem *rfbptr; int i, j; - dma_addr_t bufaddr; for (i = 0; i < priv->num_tx_queues; i++) { tx_queue = priv->tx_queue[i]; @@ -207,40 +204,26 @@ static int gfar_init_bds(struct net_device *ndev) rfbptr = ®s->rfbptr0; for (i = 0; i < priv->num_rx_queues; i++) { rx_queue = priv->rx_queue[i]; - rx_queue->cur_rx = rx_queue->rx_bd_base; - rx_queue->skb_currx = 0; - rxbdp = rx_queue->rx_bd_base; - for (j = 0; j < rx_queue->rx_ring_size; j++) { - struct sk_buff *skb = rx_queue->rx_skbuff[j]; + rx_queue->next_to_clean = 0; + rx_queue->next_to_use = 0; + rx_queue->next_to_alloc = 0; - if (skb) { - bufaddr = be32_to_cpu(rxbdp->bufPtr); - } else { - skb = gfar_new_skb(ndev, &bufaddr); - if (!skb) { - netdev_err(ndev, "Can't allocate RX buffers\n"); - return -ENOMEM; - } - rx_queue->rx_skbuff[j] = skb; - } - - gfar_init_rxbdp(rx_queue, rxbdp, bufaddr); - rxbdp++; - } + /* make sure next_to_clean != next_to_use after this + * by leaving at least 1 unused descriptor + */ + gfar_alloc_rx_buffs(rx_queue, gfar_rxbd_unused(rx_queue)); rx_queue->rfbptr = rfbptr; rfbptr += 2; } - - return 0; } static int gfar_alloc_skb_resources(struct net_device *ndev) { void *vaddr; dma_addr_t addr; - int i, j, k; + int i, j; struct gfar_private *priv = netdev_priv(ndev); struct device *dev = priv->dev; struct gfar_priv_tx_q *tx_queue = NULL; @@ -279,7 +262,8 @@ static int gfar_alloc_skb_resources(struct net_device *ndev) rx_queue = priv->rx_queue[i]; rx_queue->rx_bd_base = vaddr; rx_queue->rx_bd_dma_base = addr; - rx_queue->dev = ndev; + rx_queue->ndev = ndev; + rx_queue->dev = dev; addr += sizeof(struct rxbd8) * rx_queue->rx_ring_size; vaddr += sizeof(struct rxbd8) * rx_queue->rx_ring_size; } @@ -294,25 +278,20 @@ static int gfar_alloc_skb_resources(struct net_device *ndev) if (!tx_queue->tx_skbuff) goto cleanup; - for (k = 0; k < tx_queue->tx_ring_size; k++) - tx_queue->tx_skbuff[k] = NULL; + for (j = 0; j < tx_queue->tx_ring_size; j++) + tx_queue->tx_skbuff[j] = NULL; } for (i = 0; i < priv->num_rx_queues; i++) { rx_queue = priv->rx_queue[i]; - rx_queue->rx_skbuff = - kmalloc_array(rx_queue->rx_ring_size, - sizeof(*rx_queue->rx_skbuff), - GFP_KERNEL); - if (!rx_queue->rx_skbuff) + rx_queue->rx_buff = kcalloc(rx_queue->rx_ring_size, + sizeof(*rx_queue->rx_buff), + GFP_KERNEL); + if (!rx_queue->rx_buff) goto cleanup; - - for (j = 0; j < rx_queue->rx_ring_size; j++) - rx_queue->rx_skbuff[j] = NULL; } - if (gfar_init_bds(ndev)) - goto cleanup; + gfar_init_bds(ndev); return 0; @@ -354,10 +333,8 @@ static void gfar_init_rqprm(struct gfar_private *priv) } } -static void gfar_rx_buff_size_config(struct gfar_private *priv) +static void gfar_rx_offload_en(struct gfar_private *priv) { - int frame_size = priv->ndev->mtu + ETH_HLEN + ETH_FCS_LEN; - /* set this when rx hw offload (TOE) functions are being used */ priv->uses_rxfcb = 0; @@ -366,16 +343,6 @@ static void gfar_rx_buff_size_config(struct gfar_private *priv) if (priv->hwts_rx_en) priv->uses_rxfcb = 1; - - if (priv->uses_rxfcb) - frame_size += GMAC_FCB_LEN; - - frame_size += priv->padding; - - frame_size = (frame_size & ~(INCREMENTAL_BUFFER_SIZE - 1)) + - INCREMENTAL_BUFFER_SIZE; - - priv->rx_buffer_size = frame_size; } static void gfar_mac_rx_config(struct gfar_private *priv) @@ -609,9 +576,8 @@ static int gfar_alloc_rx_queues(struct gfar_private *priv) if (!priv->rx_queue[i]) return -ENOMEM; - priv->rx_queue[i]->rx_skbuff = NULL; priv->rx_queue[i]->qindex = i; - priv->rx_queue[i]->dev = priv->ndev; + priv->rx_queue[i]->ndev = priv->ndev; } return 0; } @@ -1203,12 +1169,11 @@ void gfar_mac_reset(struct gfar_private *priv) udelay(3); - /* Compute rx_buff_size based on config flags */ - gfar_rx_buff_size_config(priv); + gfar_rx_offload_en(priv); /* Initialize the max receive frame/buffer lengths */ - gfar_write(®s->maxfrm, priv->rx_buffer_size); - gfar_write(®s->mrblr, priv->rx_buffer_size); + gfar_write(®s->maxfrm, GFAR_JUMBO_FRAME_SIZE); + gfar_write(®s->mrblr, GFAR_RXB_SIZE); /* Initialize the Minimum Frame Length Register */ gfar_write(®s->minflr, MINFLR_INIT_SETTINGS); @@ -1216,12 +1181,11 @@ void gfar_mac_reset(struct gfar_private *priv) /* Initialize MACCFG2. */ tempval = MACCFG2_INIT_SETTINGS; - /* If the mtu is larger than the max size for standard - * ethernet frames (ie, a jumbo frame), then set maccfg2 - * to allow huge frames, and to check the length + /* eTSEC74 erratum: Rx frames of length MAXFRM or MAXFRM-1 + * are marked as truncated. Avoid this by MACCFG2[Huge Frame]=1, + * and by checking RxBD[LG] and discarding larger than MAXFRM. */ - if (priv->rx_buffer_size > DEFAULT_RX_BUFFER_SIZE || - gfar_has_errata(priv, GFAR_ERRATA_74)) + if (gfar_has_errata(priv, GFAR_ERRATA_74)) tempval |= MACCFG2_HUGEFRAME | MACCFG2_LENGTHCHECK; gfar_write(®s->maccfg2, tempval); @@ -1432,8 +1396,6 @@ static int gfar_probe(struct platform_device *ofdev) priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) dev->needed_headroom = GMAC_FCB_LEN; - priv->rx_buffer_size = DEFAULT_RX_BUFFER_SIZE; - /* Initializing some of the rx/tx queue level parameters */ for (i = 0; i < priv->num_tx_queues; i++) { priv->tx_queue[i]->tx_ring_size = DEFAULT_TX_RING_SIZE; @@ -1639,10 +1601,7 @@ static int gfar_restore(struct device *dev) return 0; } - if (gfar_init_bds(ndev)) { - free_skb_resources(priv); - return -ENOMEM; - } + gfar_init_bds(ndev); gfar_mac_reset(priv); @@ -1933,26 +1892,32 @@ static void free_skb_tx_queue(struct gfar_priv_tx_q *tx_queue) static void free_skb_rx_queue(struct gfar_priv_rx_q *rx_queue) { - struct rxbd8 *rxbdp; - struct gfar_private *priv = netdev_priv(rx_queue->dev); int i; - rxbdp = rx_queue->rx_bd_base; + struct rxbd8 *rxbdp = rx_queue->rx_bd_base; + + if (rx_queue->skb) + dev_kfree_skb(rx_queue->skb); for (i = 0; i < rx_queue->rx_ring_size; i++) { - if (rx_queue->rx_skbuff[i]) { - dma_unmap_single(priv->dev, be32_to_cpu(rxbdp->bufPtr), - priv->rx_buffer_size, - DMA_FROM_DEVICE); - dev_kfree_skb_any(rx_queue->rx_skbuff[i]); - rx_queue->rx_skbuff[i] = NULL; - } + struct gfar_rx_buff *rxb = &rx_queue->rx_buff[i]; + rxbdp->lstatus = 0; rxbdp->bufPtr = 0; rxbdp++; + + if (!rxb->page) + continue; + + dma_unmap_single(rx_queue->dev, rxb->dma, + PAGE_SIZE, DMA_FROM_DEVICE); + __free_page(rxb->page); + + rxb->page = NULL; } - kfree(rx_queue->rx_skbuff); - rx_queue->rx_skbuff = NULL; + + kfree(rx_queue->rx_buff); + rx_queue->rx_buff = NULL; } /* If there are any tx skbs or rx skbs still around, free them. @@ -1977,7 +1942,7 @@ static void free_skb_resources(struct gfar_private *priv) for (i = 0; i < priv->num_rx_queues; i++) { rx_queue = priv->rx_queue[i]; - if (rx_queue->rx_skbuff) + if (rx_queue->rx_buff) free_skb_rx_queue(rx_queue); } @@ -2535,7 +2500,7 @@ static int gfar_change_mtu(struct net_device *dev, int new_mtu) struct gfar_private *priv = netdev_priv(dev); int frame_size = new_mtu + ETH_HLEN; - if ((frame_size < 64) || (frame_size > JUMBO_FRAME_SIZE)) { + if ((frame_size < 64) || (frame_size > GFAR_JUMBO_FRAME_SIZE)) { netif_err(priv, drv, dev, "Invalid MTU setting\n"); return -EINVAL; } @@ -2589,15 +2554,6 @@ static void gfar_timeout(struct net_device *dev) schedule_work(&priv->reset_task); } -static void gfar_align_skb(struct sk_buff *skb) -{ - /* We need the data buffer to be aligned properly. We will reserve - * as many bytes as needed to align the data properly - */ - skb_reserve(skb, RXBUF_ALIGNMENT - - (((unsigned long) skb->data) & (RXBUF_ALIGNMENT - 1))); -} - /* Interrupt Handler for Transmit complete */ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) { @@ -2704,49 +2660,85 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) netdev_tx_completed_queue(txq, howmany, bytes_sent); } -static struct sk_buff *gfar_alloc_skb(struct net_device *dev) +static bool gfar_new_page(struct gfar_priv_rx_q *rxq, struct gfar_rx_buff *rxb) { - struct gfar_private *priv = netdev_priv(dev); - struct sk_buff *skb; + struct page *page; + dma_addr_t addr; - skb = netdev_alloc_skb(dev, priv->rx_buffer_size + RXBUF_ALIGNMENT); - if (!skb) - return NULL; + page = dev_alloc_page(); + if (unlikely(!page)) + return false; - gfar_align_skb(skb); + addr = dma_map_page(rxq->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(rxq->dev, addr))) { + __free_page(page); - return skb; + return false; + } + + rxb->dma = addr; + rxb->page = page; + rxb->page_offset = 0; + + return true; } -static struct sk_buff *gfar_new_skb(struct net_device *dev, dma_addr_t *bufaddr) +static void gfar_rx_alloc_err(struct gfar_priv_rx_q *rx_queue) { - struct gfar_private *priv = netdev_priv(dev); - struct sk_buff *skb; - dma_addr_t addr; + struct gfar_private *priv = netdev_priv(rx_queue->ndev); + struct gfar_extra_stats *estats = &priv->extra_stats; - skb = gfar_alloc_skb(dev); - if (!skb) - return NULL; + netdev_err(rx_queue->ndev, "Can't alloc RX buffers\n"); + atomic64_inc(&estats->rx_alloc_err); +} - addr = dma_map_single(priv->dev, skb->data, - priv->rx_buffer_size, DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(priv->dev, addr))) { - dev_kfree_skb_any(skb); - return NULL; +static void gfar_alloc_rx_buffs(struct gfar_priv_rx_q *rx_queue, + int alloc_cnt) +{ + struct rxbd8 *bdp; + struct gfar_rx_buff *rxb; + int i; + + i = rx_queue->next_to_use; + bdp = &rx_queue->rx_bd_base[i]; + rxb = &rx_queue->rx_buff[i]; + + while (alloc_cnt--) { + /* try reuse page */ + if (unlikely(!rxb->page)) { + if (unlikely(!gfar_new_page(rx_queue, rxb))) { + gfar_rx_alloc_err(rx_queue); + break; + } + } + + /* Setup the new RxBD */ + gfar_init_rxbdp(rx_queue, bdp, + rxb->dma + rxb->page_offset + RXBUF_ALIGNMENT); + + /* Update to the next pointer */ + bdp++; + rxb++; + + if (unlikely(++i == rx_queue->rx_ring_size)) { + i = 0; + bdp = rx_queue->rx_bd_base; + rxb = rx_queue->rx_buff; + } } - *bufaddr = addr; - return skb; + rx_queue->next_to_use = i; + rx_queue->next_to_alloc = i; } -static inline void count_errors(unsigned short status, struct net_device *dev) +static void count_errors(u32 lstatus, struct net_device *ndev) { - struct gfar_private *priv = netdev_priv(dev); - struct net_device_stats *stats = &dev->stats; + struct gfar_private *priv = netdev_priv(ndev); + struct net_device_stats *stats = &ndev->stats; struct gfar_extra_stats *estats = &priv->extra_stats; /* If the packet was truncated, none of the other errors matter */ - if (status & RXBD_TRUNCATED) { + if (lstatus & BD_LFLAG(RXBD_TRUNCATED)) { stats->rx_length_errors++; atomic64_inc(&estats->rx_trunc); @@ -2754,25 +2746,25 @@ static inline void count_errors(unsigned short status, struct net_device *dev) return; } /* Count the errors, if there were any */ - if (status & (RXBD_LARGE | RXBD_SHORT)) { + if (lstatus & BD_LFLAG(RXBD_LARGE | RXBD_SHORT)) { stats->rx_length_errors++; - if (status & RXBD_LARGE) + if (lstatus & BD_LFLAG(RXBD_LARGE)) atomic64_inc(&estats->rx_large); else atomic64_inc(&estats->rx_short); } - if (status & RXBD_NONOCTET) { + if (lstatus & BD_LFLAG(RXBD_NONOCTET)) { stats->rx_frame_errors++; atomic64_inc(&estats->rx_nonoctet); } - if (status & RXBD_CRCERR) { + if (lstatus & BD_LFLAG(RXBD_CRCERR)) { atomic64_inc(&estats->rx_crcerr); stats->rx_crc_errors++; } - if (status & RXBD_OVERRUN) { + if (lstatus & BD_LFLAG(RXBD_OVERRUN)) { atomic64_inc(&estats->rx_overrun); - stats->rx_crc_errors++; + stats->rx_over_errors++; } } @@ -2823,6 +2815,93 @@ static irqreturn_t gfar_transmit(int irq, void *grp_id) return IRQ_HANDLED; } +static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus, + struct sk_buff *skb, bool first) +{ + unsigned int size = lstatus & BD_LENGTH_MASK; + struct page *page = rxb->page; + + /* Remove the FCS from the packet length */ + if (likely(lstatus & BD_LFLAG(RXBD_LAST))) + size -= ETH_FCS_LEN; + + if (likely(first)) + skb_put(skb, size); + else + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + rxb->page_offset + RXBUF_ALIGNMENT, + size, GFAR_RXB_TRUESIZE); + + /* try reuse page */ + if (unlikely(page_count(page) != 1)) + return false; + + /* change offset to the other half */ + rxb->page_offset ^= GFAR_RXB_TRUESIZE; + + atomic_inc(&page->_count); + + return true; +} + +static void gfar_reuse_rx_page(struct gfar_priv_rx_q *rxq, + struct gfar_rx_buff *old_rxb) +{ + struct gfar_rx_buff *new_rxb; + u16 nta = rxq->next_to_alloc; + + new_rxb = &rxq->rx_buff[nta]; + + /* find next buf that can reuse a page */ + nta++; + rxq->next_to_alloc = (nta < rxq->rx_ring_size) ? nta : 0; + + /* copy page reference */ + *new_rxb = *old_rxb; + + /* sync for use by the device */ + dma_sync_single_range_for_device(rxq->dev, old_rxb->dma, + old_rxb->page_offset, + GFAR_RXB_TRUESIZE, DMA_FROM_DEVICE); +} + +static struct sk_buff *gfar_get_next_rxbuff(struct gfar_priv_rx_q *rx_queue, + u32 lstatus, struct sk_buff *skb) +{ + struct gfar_rx_buff *rxb = &rx_queue->rx_buff[rx_queue->next_to_clean]; + struct page *page = rxb->page; + bool first = false; + + if (likely(!skb)) { + void *buff_addr = page_address(page) + rxb->page_offset; + + skb = build_skb(buff_addr, GFAR_SKBFRAG_SIZE); + if (unlikely(!skb)) { + gfar_rx_alloc_err(rx_queue); + return NULL; + } + skb_reserve(skb, RXBUF_ALIGNMENT); + first = true; + } + + dma_sync_single_range_for_cpu(rx_queue->dev, rxb->dma, rxb->page_offset, + GFAR_RXB_TRUESIZE, DMA_FROM_DEVICE); + + if (gfar_add_rx_frag(rxb, lstatus, skb, first)) { + /* reuse the free half of the page */ + gfar_reuse_rx_page(rx_queue, rxb); + } else { + /* page cannot be reused, unmap it */ + dma_unmap_page(rx_queue->dev, rxb->dma, + PAGE_SIZE, DMA_FROM_DEVICE); + } + + /* clear rxb content */ + rxb->page = NULL; + + return skb; +} + static inline void gfar_rx_checksum(struct sk_buff *skb, struct rxfcb *fcb) { /* If valid headers were found, and valid sums @@ -2837,10 +2916,9 @@ static inline void gfar_rx_checksum(struct sk_buff *skb, struct rxfcb *fcb) } /* gfar_process_frame() -- handle one incoming packet if skb isn't NULL. */ -static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb, - int amount_pull, struct napi_struct *napi) +static void gfar_process_frame(struct net_device *ndev, struct sk_buff *skb) { - struct gfar_private *priv = netdev_priv(dev); + struct gfar_private *priv = netdev_priv(ndev); struct rxfcb *fcb = NULL; /* fcb is at the beginning if exists */ @@ -2849,10 +2927,8 @@ static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb, /* Remove the FCB from the skb * Remove the padded bytes, if there are any */ - if (amount_pull) { - skb_record_rx_queue(skb, fcb->rq); - skb_pull(skb, amount_pull); - } + if (priv->uses_rxfcb) + skb_pull(skb, GMAC_FCB_LEN); /* Get receive timestamp from the skb */ if (priv->hwts_rx_en) { @@ -2866,24 +2942,20 @@ static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb, if (priv->padding) skb_pull(skb, priv->padding); - if (dev->features & NETIF_F_RXCSUM) + if (ndev->features & NETIF_F_RXCSUM) gfar_rx_checksum(skb, fcb); /* Tell the skb what kind of packet this is */ - skb->protocol = eth_type_trans(skb, dev); + skb->protocol = eth_type_trans(skb, ndev); /* There's need to check for NETIF_F_HW_VLAN_CTAG_RX here. * Even if vlan rx accel is disabled, on some chips * RXFCB_VLN is pseudo randomly set. */ - if (dev->features & NETIF_F_HW_VLAN_CTAG_RX && + if (ndev->features & NETIF_F_HW_VLAN_CTAG_RX && be16_to_cpu(fcb->flags) & RXFCB_VLN) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(fcb->vlctl)); - - /* Send the packet up the stack */ - napi_gro_receive(napi, skb); - } /* gfar_clean_rx_ring() -- Processes each frame in the rx ring @@ -2892,91 +2964,88 @@ static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb, */ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit) { - struct net_device *dev = rx_queue->dev; - struct rxbd8 *bdp, *base; - struct sk_buff *skb; - int pkt_len; - int amount_pull; - int howmany = 0; - struct gfar_private *priv = netdev_priv(dev); + struct net_device *ndev = rx_queue->ndev; + struct gfar_private *priv = netdev_priv(ndev); + struct rxbd8 *bdp; + int i, howmany = 0; + struct sk_buff *skb = rx_queue->skb; + int cleaned_cnt = gfar_rxbd_unused(rx_queue); + unsigned int total_bytes = 0, total_pkts = 0; /* Get the first full descriptor */ - bdp = rx_queue->cur_rx; - base = rx_queue->rx_bd_base; + i = rx_queue->next_to_clean; - amount_pull = priv->uses_rxfcb ? GMAC_FCB_LEN : 0; + while (rx_work_limit--) { + u32 lstatus; - while (!(be16_to_cpu(bdp->status) & RXBD_EMPTY) && rx_work_limit--) { - struct sk_buff *newskb; - dma_addr_t bufaddr; + if (cleaned_cnt >= GFAR_RX_BUFF_ALLOC) { + gfar_alloc_rx_buffs(rx_queue, cleaned_cnt); + cleaned_cnt = 0; + } + + bdp = &rx_queue->rx_bd_base[i]; + lstatus = be32_to_cpu(bdp->lstatus); + if (lstatus & BD_LFLAG(RXBD_EMPTY)) + break; + /* order rx buffer descriptor reads */ rmb(); - /* Add another skb for the future */ - newskb = gfar_new_skb(dev, &bufaddr); + /* fetch next to clean buffer from the ring */ + skb = gfar_get_next_rxbuff(rx_queue, lstatus, skb); + if (unlikely(!skb)) + break; - skb = rx_queue->rx_skbuff[rx_queue->skb_currx]; + cleaned_cnt++; + howmany++; - dma_unmap_single(priv->dev, be32_to_cpu(bdp->bufPtr), - priv->rx_buffer_size, DMA_FROM_DEVICE); - - if (unlikely(!(be16_to_cpu(bdp->status) & RXBD_ERR) && - be16_to_cpu(bdp->length) > priv->rx_buffer_size)) - bdp->status = cpu_to_be16(RXBD_LARGE); - - /* We drop the frame if we failed to allocate a new buffer */ - if (unlikely(!newskb || - !(be16_to_cpu(bdp->status) & RXBD_LAST) || - be16_to_cpu(bdp->status) & RXBD_ERR)) { - count_errors(be16_to_cpu(bdp->status), dev); - - if (unlikely(!newskb)) { - newskb = skb; - bufaddr = be32_to_cpu(bdp->bufPtr); - } else if (skb) - dev_kfree_skb(skb); - } else { - /* Increment the number of packets */ - rx_queue->stats.rx_packets++; - howmany++; - - if (likely(skb)) { - pkt_len = be16_to_cpu(bdp->length) - - ETH_FCS_LEN; - /* Remove the FCS from the packet length */ - skb_put(skb, pkt_len); - rx_queue->stats.rx_bytes += pkt_len; - skb_record_rx_queue(skb, rx_queue->qindex); - gfar_process_frame(dev, skb, amount_pull, - &rx_queue->grp->napi_rx); + if (unlikely(++i == rx_queue->rx_ring_size)) + i = 0; - } else { - netif_warn(priv, rx_err, dev, "Missing skb!\n"); - rx_queue->stats.rx_dropped++; - atomic64_inc(&priv->extra_stats.rx_skbmissing); - } + rx_queue->next_to_clean = i; + + /* fetch next buffer if not the last in frame */ + if (!(lstatus & BD_LFLAG(RXBD_LAST))) + continue; + if (unlikely(lstatus & BD_LFLAG(RXBD_ERR))) { + count_errors(lstatus, ndev); + + /* discard faulty buffer */ + dev_kfree_skb(skb); + skb = NULL; + rx_queue->stats.rx_dropped++; + continue; } - rx_queue->rx_skbuff[rx_queue->skb_currx] = newskb; + /* Increment the number of packets */ + total_pkts++; + total_bytes += skb->len; - /* Setup the new bdp */ - gfar_init_rxbdp(rx_queue, bdp, bufaddr); + skb_record_rx_queue(skb, rx_queue->qindex); - /* Update Last Free RxBD pointer for LFC */ - if (unlikely(rx_queue->rfbptr && priv->tx_actual_en)) - gfar_write(rx_queue->rfbptr, (u32)bdp); + gfar_process_frame(ndev, skb); - /* Update to the next pointer */ - bdp = next_bd(bdp, base, rx_queue->rx_ring_size); + /* Send the packet up the stack */ + napi_gro_receive(&rx_queue->grp->napi_rx, skb); - /* update to point at the next skb */ - rx_queue->skb_currx = (rx_queue->skb_currx + 1) & - RX_RING_MOD_MASK(rx_queue->rx_ring_size); + skb = NULL; } - /* Update the current rxbd pointer to be the next one */ - rx_queue->cur_rx = bdp; + /* Store incomplete frames for completion */ + rx_queue->skb = skb; + + rx_queue->stats.rx_packets += total_pkts; + rx_queue->stats.rx_bytes += total_bytes; + + if (cleaned_cnt) + gfar_alloc_rx_buffs(rx_queue, cleaned_cnt); + + /* Update Last Free RxBD pointer for LFC */ + if (unlikely(priv->tx_actual_en)) { + bdp = gfar_rxbd_lastfree(rx_queue); + gfar_write(rx_queue->rfbptr, (u32)bdp); + } return howmany; } @@ -3552,14 +3621,8 @@ static noinline void gfar_update_link_state(struct gfar_private *priv) if ((tempval1 & MACCFG1_TX_FLOW) && !tx_flow_oldval) { for (i = 0; i < priv->num_rx_queues; i++) { rx_queue = priv->rx_queue[i]; - bdp = rx_queue->cur_rx; - /* skip to previous bd */ - bdp = skip_bd(bdp, rx_queue->rx_ring_size - 1, - rx_queue->rx_bd_base, - rx_queue->rx_ring_size); - - if (rx_queue->rfbptr) - gfar_write(rx_queue->rfbptr, (u32)bdp); + bdp = gfar_rxbd_lastfree(rx_queue); + gfar_write(rx_queue->rfbptr, (u32)bdp); } priv->tx_actual_en = 1; diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index daa1d37de642..44021243c187 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -71,11 +71,6 @@ struct ethtool_rx_list { /* Number of bytes to align the rx bufs to */ #define RXBUF_ALIGNMENT 64 -/* The number of bytes which composes a unit for the purpose of - * allocating data buffers. ie-for any given MTU, the data buffer - * will be the next highest multiple of 512 bytes. */ -#define INCREMENTAL_BUFFER_SIZE 512 - #define PHY_INIT_TIMEOUT 100000 #define DRV_NAME "gfar-enet" @@ -92,6 +87,8 @@ extern const char gfar_driver_version[]; #define DEFAULT_TX_RING_SIZE 256 #define DEFAULT_RX_RING_SIZE 256 +#define GFAR_RX_BUFF_ALLOC 16 + #define GFAR_RX_MAX_RING_SIZE 256 #define GFAR_TX_MAX_RING_SIZE 256 @@ -103,11 +100,14 @@ extern const char gfar_driver_version[]; #define DEFAULT_RX_LFC_THR 16 #define DEFAULT_LFC_PTVVAL 4 -#define DEFAULT_RX_BUFFER_SIZE 1536 +#define GFAR_RXB_SIZE 1536 +#define GFAR_SKBFRAG_SIZE (RXBUF_ALIGNMENT + GFAR_RXB_SIZE \ + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) +#define GFAR_RXB_TRUESIZE 2048 + #define TX_RING_MOD_MASK(size) (size-1) #define RX_RING_MOD_MASK(size) (size-1) -#define JUMBO_BUFFER_SIZE 9728 -#define JUMBO_FRAME_SIZE 9600 +#define GFAR_JUMBO_FRAME_SIZE 9600 #define DEFAULT_FIFO_TX_THR 0x100 #define DEFAULT_FIFO_TX_STARVE 0x40 @@ -640,6 +640,7 @@ struct rmon_mib }; struct gfar_extra_stats { + atomic64_t rx_alloc_err; atomic64_t rx_large; atomic64_t rx_short; atomic64_t rx_nonoctet; @@ -651,7 +652,6 @@ struct gfar_extra_stats { atomic64_t eberr; atomic64_t tx_babt; atomic64_t tx_underrun; - atomic64_t rx_skbmissing; atomic64_t tx_timeout; }; @@ -1012,34 +1012,42 @@ struct rx_q_stats { unsigned long rx_dropped; }; +struct gfar_rx_buff { + dma_addr_t dma; + struct page *page; + unsigned int page_offset; +}; + /** * struct gfar_priv_rx_q - per rx queue structure - * @rx_skbuff: skb pointers - * @skb_currx: currently use skb pointer + * @rx_buff: Array of buffer info metadata structs * @rx_bd_base: First rx buffer descriptor - * @cur_rx: Next free rx ring entry + * @next_to_use: index of the next buffer to be alloc'd + * @next_to_clean: index of the next buffer to be cleaned * @qindex: index of this queue - * @dev: back pointer to the dev structure + * @ndev: back pointer to net_device * @rx_ring_size: Rx ring size * @rxcoalescing: enable/disable rx-coalescing * @rxic: receive interrupt coalescing vlaue */ struct gfar_priv_rx_q { - struct sk_buff **rx_skbuff __aligned(SMP_CACHE_BYTES); - dma_addr_t rx_bd_dma_base; + struct gfar_rx_buff *rx_buff __aligned(SMP_CACHE_BYTES); struct rxbd8 *rx_bd_base; - struct rxbd8 *cur_rx; - struct net_device *dev; - struct gfar_priv_grp *grp; + struct net_device *ndev; + struct device *dev; + u16 rx_ring_size; + u16 qindex; + struct gfar_priv_grp *grp; + u16 next_to_clean; + u16 next_to_use; + u16 next_to_alloc; + struct sk_buff *skb; struct rx_q_stats stats; - u16 skb_currx; - u16 qindex; - unsigned int rx_ring_size; - /* RX Coalescing values */ + u32 __iomem *rfbptr; unsigned char rxcoalescing; unsigned long rxic; - u32 __iomem *rfbptr; + dma_addr_t rx_bd_dma_base; }; enum gfar_irqinfo_id { @@ -1109,7 +1117,6 @@ struct gfar_private { struct device *dev; struct net_device *ndev; enum gfar_errata errata; - unsigned int rx_buffer_size; u16 uses_rxfcb; u16 padding; @@ -1295,6 +1302,23 @@ static inline void gfar_clear_txbd_status(struct txbd8 *bdp) bdp->lstatus = cpu_to_be32(lstatus); } +static inline int gfar_rxbd_unused(struct gfar_priv_rx_q *rxq) +{ + if (rxq->next_to_clean > rxq->next_to_use) + return rxq->next_to_clean - rxq->next_to_use - 1; + + return rxq->rx_ring_size + rxq->next_to_clean - rxq->next_to_use - 1; +} + +static inline struct rxbd8 *gfar_rxbd_lastfree(struct gfar_priv_rx_q *rxq) +{ + int i; + + i = rxq->next_to_use ? rxq->next_to_use - 1 : rxq->rx_ring_size - 1; + + return &rxq->rx_bd_base[i]; +} + irqreturn_t gfar_receive(int irq, void *dev_id); int startup_gfar(struct net_device *dev); void stop_gfar(struct net_device *dev); diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index fda12fb32ec7..3020aaabf0e4 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -61,6 +61,8 @@ static void gfar_gdrvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo); static const char stat_gstrings[][ETH_GSTRING_LEN] = { + /* extra stats */ + "rx-allocation-errors", "rx-large-frame-errors", "rx-short-frame-errors", "rx-non-octet-errors", @@ -72,8 +74,8 @@ static const char stat_gstrings[][ETH_GSTRING_LEN] = { "ethernet-bus-error", "tx-babbling-errors", "tx-underrun-errors", - "rx-skb-missing-errors", "tx-timeout-errors", + /* rmon stats */ "tx-rx-64-frames", "tx-rx-65-127-frames", "tx-rx-128-255-frames", diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index d49bee38cd31..cc2d8b4b18e3 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -965,7 +965,6 @@ static struct platform_driver hip04_mac_driver = { .remove = hip04_remove, .driver = { .name = DRV_NAME, - .owner = THIS_MODULE, .of_match_table = hip04_mac_match, }, }; diff --git a/drivers/net/ethernet/hisilicon/hip04_mdio.c b/drivers/net/ethernet/hisilicon/hip04_mdio.c index b3bac25db99c..fca0a5be1f0f 100644 --- a/drivers/net/ethernet/hisilicon/hip04_mdio.c +++ b/drivers/net/ethernet/hisilicon/hip04_mdio.c @@ -174,7 +174,6 @@ static struct platform_driver hip04_mdio_driver = { .remove = hip04_mdio_remove, .driver = { .name = "hip04-mdio", - .owner = THIS_MODULE, .of_match_table = hip04_mdio_match, }, }; diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 29bbb628d712..7af870a3c549 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -79,6 +79,11 @@ static unsigned int rx_flush __read_mostly = 0; module_param(rx_flush, uint, 0644); MODULE_PARM_DESC(rx_flush, "Flush receive buffers before use"); +static bool old_large_send __read_mostly; +module_param(old_large_send, bool, S_IRUGO); +MODULE_PARM_DESC(old_large_send, + "Use old large send method on firmware that supports the new method"); + struct ibmveth_stat { char name[ETH_GSTRING_LEN]; int offset; @@ -101,7 +106,8 @@ struct ibmveth_stat ibmveth_stats[] = { { "fw_enabled_ipv4_csum", IBMVETH_STAT_OFF(fw_ipv4_csum_support) }, { "fw_enabled_ipv6_csum", IBMVETH_STAT_OFF(fw_ipv6_csum_support) }, { "tx_large_packets", IBMVETH_STAT_OFF(tx_large_packets) }, - { "rx_large_packets", IBMVETH_STAT_OFF(rx_large_packets) } + { "rx_large_packets", IBMVETH_STAT_OFF(rx_large_packets) }, + { "fw_enabled_large_send", IBMVETH_STAT_OFF(fw_large_send_support) } }; /* simple methods of getting data from the current rxq entry */ @@ -848,25 +854,91 @@ static int ibmveth_set_csum_offload(struct net_device *dev, u32 data) return rc1 ? rc1 : rc2; } +static int ibmveth_set_tso(struct net_device *dev, u32 data) +{ + struct ibmveth_adapter *adapter = netdev_priv(dev); + unsigned long set_attr, clr_attr, ret_attr; + long ret1, ret2; + int rc1 = 0, rc2 = 0; + int restart = 0; + + if (netif_running(dev)) { + restart = 1; + adapter->pool_config = 1; + ibmveth_close(dev); + adapter->pool_config = 0; + } + + set_attr = 0; + clr_attr = 0; + + if (data) + set_attr = IBMVETH_ILLAN_LRG_SR_ENABLED; + else + clr_attr = IBMVETH_ILLAN_LRG_SR_ENABLED; + + ret1 = h_illan_attributes(adapter->vdev->unit_address, 0, 0, &ret_attr); + + if (ret1 == H_SUCCESS && (ret_attr & IBMVETH_ILLAN_LRG_SND_SUPPORT) && + !old_large_send) { + ret2 = h_illan_attributes(adapter->vdev->unit_address, clr_attr, + set_attr, &ret_attr); + + if (ret2 != H_SUCCESS) { + netdev_err(dev, "unable to change tso settings. %d rc=%ld\n", + data, ret2); + + h_illan_attributes(adapter->vdev->unit_address, + set_attr, clr_attr, &ret_attr); + + if (data == 1) + dev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6); + rc1 = -EIO; + + } else { + adapter->fw_large_send_support = data; + adapter->large_send = data; + } + } else { + /* Older firmware version of large send offload does not + * support tcp6/ipv6 + */ + if (data == 1) { + dev->features &= ~NETIF_F_TSO6; + netdev_info(dev, "TSO feature requires all partitions to have updated driver"); + } + adapter->large_send = data; + } + + if (restart) + rc2 = ibmveth_open(dev); + + return rc1 ? rc1 : rc2; +} + static int ibmveth_set_features(struct net_device *dev, netdev_features_t features) { struct ibmveth_adapter *adapter = netdev_priv(dev); int rx_csum = !!(features & NETIF_F_RXCSUM); - int rc; - netdev_features_t changed = features ^ dev->features; - - if (features & NETIF_F_TSO & changed) - netdev_info(dev, "TSO feature requires all partitions to have updated driver"); + int large_send = !!(features & (NETIF_F_TSO | NETIF_F_TSO6)); + int rc1 = 0, rc2 = 0; - if (rx_csum == adapter->rx_csum) - return 0; + if (rx_csum != adapter->rx_csum) { + rc1 = ibmveth_set_csum_offload(dev, rx_csum); + if (rc1 && !adapter->rx_csum) + dev->features = + features & ~(NETIF_F_ALL_CSUM | NETIF_F_RXCSUM); + } - rc = ibmveth_set_csum_offload(dev, rx_csum); - if (rc && !adapter->rx_csum) - dev->features = features & ~(NETIF_F_ALL_CSUM | NETIF_F_RXCSUM); + if (large_send != adapter->large_send) { + rc2 = ibmveth_set_tso(dev, large_send); + if (rc2 && !adapter->large_send) + dev->features = + features & ~(NETIF_F_TSO | NETIF_F_TSO6); + } - return rc; + return rc1 ? rc1 : rc2; } static void ibmveth_get_strings(struct net_device *dev, u32 stringset, u8 *data) @@ -917,7 +989,7 @@ static int ibmveth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) #define page_offset(v) ((unsigned long)(v) & ((1 << 12) - 1)) static int ibmveth_send(struct ibmveth_adapter *adapter, - union ibmveth_buf_desc *descs) + union ibmveth_buf_desc *descs, unsigned long mss) { unsigned long correlator; unsigned int retry_count; @@ -934,7 +1006,8 @@ static int ibmveth_send(struct ibmveth_adapter *adapter, descs[0].desc, descs[1].desc, descs[2].desc, descs[3].desc, descs[4].desc, descs[5].desc, - correlator, &correlator); + correlator, &correlator, mss, + adapter->fw_large_send_support); } while ((ret == H_BUSY) && (retry_count--)); if (ret != H_SUCCESS && ret != H_DROPPED) { @@ -955,6 +1028,7 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb, int last, i; int force_bounce = 0; dma_addr_t dma_addr; + unsigned long mss = 0; /* * veth handles a maximum of 6 segments including the header, so @@ -980,6 +1054,9 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb, desc_flags = IBMVETH_BUF_VALID; + if (skb_is_gso(skb) && adapter->fw_large_send_support) + desc_flags |= IBMVETH_BUF_LRG_SND; + if (skb->ip_summed == CHECKSUM_PARTIAL) { unsigned char *buf = skb_transport_header(skb) + skb->csum_offset; @@ -1007,7 +1084,7 @@ retry_bounce: descs[0].fields.flags_len = desc_flags | skb->len; descs[0].fields.address = adapter->bounce_buffer_dma; - if (ibmveth_send(adapter, descs)) { + if (ibmveth_send(adapter, descs, 0)) { adapter->tx_send_failed++; netdev->stats.tx_dropped++; } else { @@ -1041,16 +1118,23 @@ retry_bounce: descs[i+1].fields.address = dma_addr; } - if (skb_is_gso(skb) && !skb_is_gso_v6(skb)) { - /* Put -1 in the IP checksum to tell phyp it - * is a largesend packet and put the mss in the TCP checksum. - */ - ip_hdr(skb)->check = 0xffff; - tcp_hdr(skb)->check = cpu_to_be16(skb_shinfo(skb)->gso_size); - adapter->tx_large_packets++; + if (skb_is_gso(skb)) { + if (adapter->fw_large_send_support) { + mss = (unsigned long)skb_shinfo(skb)->gso_size; + adapter->tx_large_packets++; + } else if (!skb_is_gso_v6(skb)) { + /* Put -1 in the IP checksum to tell phyp it + * is a largesend packet. Put the mss in + * the TCP checksum. + */ + ip_hdr(skb)->check = 0xffff; + tcp_hdr(skb)->check = + cpu_to_be16(skb_shinfo(skb)->gso_size); + adapter->tx_large_packets++; + } } - if (ibmveth_send(adapter, descs)) { + if (ibmveth_send(adapter, descs, mss)) { adapter->tx_send_failed++; netdev->stats.tx_dropped++; } else { @@ -1401,6 +1485,8 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) struct ibmveth_adapter *adapter; unsigned char *mac_addr_p; unsigned int *mcastFilterSize_p; + long ret; + unsigned long ret_attr; dev_dbg(&dev->dev, "entering ibmveth_probe for UA 0x%x\n", dev->unit_address); @@ -1449,10 +1535,19 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) SET_NETDEV_DEV(netdev, &dev->dev); netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + netdev->features |= netdev->hw_features; - /* TSO is disabled by default */ - netdev->hw_features |= NETIF_F_TSO; + ret = h_illan_attributes(adapter->vdev->unit_address, 0, 0, &ret_attr); + + /* If running older firmware, TSO should not be enabled by default */ + if (ret == H_SUCCESS && (ret_attr & IBMVETH_ILLAN_LRG_SND_SUPPORT) && + !old_large_send) { + netdev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; + netdev->features |= netdev->hw_features; + } else { + netdev->hw_features |= NETIF_F_TSO; + } memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN); diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index 41dedb1fb2ae..4eade67fe30c 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -40,6 +40,8 @@ #define IbmVethMcastRemoveFilter 0x2UL #define IbmVethMcastClearFilterTable 0x3UL +#define IBMVETH_ILLAN_LRG_SR_ENABLED 0x0000000000010000UL +#define IBMVETH_ILLAN_LRG_SND_SUPPORT 0x0000000000008000UL #define IBMVETH_ILLAN_PADDED_PKT_CSUM 0x0000000000002000UL #define IBMVETH_ILLAN_TRUNK_PRI_MASK 0x0000000000000F00UL #define IBMVETH_ILLAN_IPV6_TCP_CSUM 0x0000000000000004UL @@ -59,13 +61,20 @@ static inline long h_send_logical_lan(unsigned long unit_address, unsigned long desc1, unsigned long desc2, unsigned long desc3, unsigned long desc4, unsigned long desc5, unsigned long desc6, - unsigned long corellator_in, unsigned long *corellator_out) + unsigned long corellator_in, unsigned long *corellator_out, + unsigned long mss, unsigned long large_send_support) { long rc; unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; - rc = plpar_hcall9(H_SEND_LOGICAL_LAN, retbuf, unit_address, desc1, - desc2, desc3, desc4, desc5, desc6, corellator_in); + if (large_send_support) + rc = plpar_hcall9(H_SEND_LOGICAL_LAN, retbuf, unit_address, + desc1, desc2, desc3, desc4, desc5, desc6, + corellator_in, mss); + else + rc = plpar_hcall9(H_SEND_LOGICAL_LAN, retbuf, unit_address, + desc1, desc2, desc3, desc4, desc5, desc6, + corellator_in); *corellator_out = retbuf[0]; @@ -147,11 +156,13 @@ struct ibmveth_adapter { struct ibmveth_rx_q rx_queue; int pool_config; int rx_csum; + int large_send; void *bounce_buffer; dma_addr_t bounce_buffer_dma; u64 fw_ipv6_csum_support; u64 fw_ipv4_csum_support; + u64 fw_large_send_support; /* adapter specific stats */ u64 replenish_task_cycles; u64 replenish_no_mem; @@ -182,6 +193,7 @@ struct ibmveth_buf_desc_fields { #endif #define IBMVETH_BUF_VALID 0x80000000 #define IBMVETH_BUF_TOGGLE 0x40000000 +#define IBMVETH_BUF_LRG_SND 0x04000000 #define IBMVETH_BUF_NO_CSUM 0x02000000 #define IBMVETH_BUF_CSUM_GOOD 0x01000000 #define IBMVETH_BUF_LEN_MASK 0x00FFFFFF diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 929e3d72a01e..9101f5c00f37 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -34,7 +34,7 @@ */ #define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR 0x0002 +#define I40E_FW_API_VERSION_MINOR 0x0004 struct i40e_aq_desc { __le16 flags; @@ -132,12 +132,7 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_list_func_capabilities = 0x000A, i40e_aqc_opc_list_dev_capabilities = 0x000B, - i40e_aqc_opc_set_cppm_configuration = 0x0103, - i40e_aqc_opc_set_arp_proxy_entry = 0x0104, - i40e_aqc_opc_set_ns_proxy_entry = 0x0105, - /* LAA */ - i40e_aqc_opc_mng_laa = 0x0106, /* AQ obsolete */ i40e_aqc_opc_mac_address_read = 0x0107, i40e_aqc_opc_mac_address_write = 0x0108, @@ -262,7 +257,6 @@ enum i40e_admin_queue_opc { /* Tunnel commands */ i40e_aqc_opc_add_udp_tunnel = 0x0B00, i40e_aqc_opc_del_udp_tunnel = 0x0B01, - i40e_aqc_opc_tunnel_key_structure = 0x0B10, /* Async Events */ i40e_aqc_opc_event_lan_overflow = 0x1001, @@ -274,8 +268,6 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_oem_ocbb_initialize = 0xFE03, /* debug commands */ - i40e_aqc_opc_debug_get_deviceid = 0xFF00, - i40e_aqc_opc_debug_set_mode = 0xFF01, i40e_aqc_opc_debug_read_reg = 0xFF03, i40e_aqc_opc_debug_write_reg = 0xFF04, i40e_aqc_opc_debug_modify_reg = 0xFF07, @@ -509,7 +501,8 @@ struct i40e_aqc_mac_address_read { #define I40E_AQC_SAN_ADDR_VALID 0x20 #define I40E_AQC_PORT_ADDR_VALID 0x40 #define I40E_AQC_WOL_ADDR_VALID 0x80 -#define I40E_AQC_ADDR_VALID_MASK 0xf0 +#define I40E_AQC_MC_MAG_EN_VALID 0x100 +#define I40E_AQC_ADDR_VALID_MASK 0x1F0 u8 reserved[6]; __le32 addr_high; __le32 addr_low; @@ -532,7 +525,9 @@ struct i40e_aqc_mac_address_write { #define I40E_AQC_WRITE_TYPE_LAA_ONLY 0x0000 #define I40E_AQC_WRITE_TYPE_LAA_WOL 0x4000 #define I40E_AQC_WRITE_TYPE_PORT 0x8000 -#define I40E_AQC_WRITE_TYPE_MASK 0xc000 +#define I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG 0xC000 +#define I40E_AQC_WRITE_TYPE_MASK 0xC000 + __le16 mac_sah; __le32 mac_sal; u8 reserved[8]; @@ -1068,6 +1063,7 @@ struct i40e_aqc_set_vsi_promiscuous_modes { __le16 seid; #define I40E_AQC_VSI_PROM_CMD_SEID_MASK 0x3FF __le16 vlan_tag; +#define I40E_AQC_SET_VSI_VLAN_MASK 0x0FFF #define I40E_AQC_SET_VSI_VLAN_VALID 0x8000 u8 reserved[8]; }; @@ -2064,6 +2060,12 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_start); #define I40E_AQC_CEE_PFC_STATUS_MASK (0x7 << I40E_AQC_CEE_PFC_STATUS_SHIFT) #define I40E_AQC_CEE_APP_STATUS_SHIFT 0x8 #define I40E_AQC_CEE_APP_STATUS_MASK (0x7 << I40E_AQC_CEE_APP_STATUS_SHIFT) +#define I40E_AQC_CEE_FCOE_STATUS_SHIFT 0x8 +#define I40E_AQC_CEE_FCOE_STATUS_MASK (0x7 << I40E_AQC_CEE_FCOE_STATUS_SHIFT) +#define I40E_AQC_CEE_ISCSI_STATUS_SHIFT 0xA +#define I40E_AQC_CEE_ISCSI_STATUS_MASK (0x7 << I40E_AQC_CEE_ISCSI_STATUS_SHIFT) +#define I40E_AQC_CEE_FIP_STATUS_SHIFT 0x10 +#define I40E_AQC_CEE_FIP_STATUS_MASK (0x7 << I40E_AQC_CEE_FIP_STATUS_SHIFT) struct i40e_aqc_get_cee_dcb_cfg_v1_resp { u8 reserved1; u8 oper_num_tc; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 0bae22da014d..07032229ee60 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -2391,7 +2391,7 @@ i40e_aq_erase_nvm_exit: #define I40E_DEV_FUNC_CAP_MSIX_VF 0x44 #define I40E_DEV_FUNC_CAP_FLOW_DIRECTOR 0x45 #define I40E_DEV_FUNC_CAP_IEEE_1588 0x46 -#define I40E_DEV_FUNC_CAP_MFP_MODE_1 0xF1 +#define I40E_DEV_FUNC_CAP_FLEX10 0xF1 #define I40E_DEV_FUNC_CAP_CEM 0xF2 #define I40E_DEV_FUNC_CAP_IWARP 0x51 #define I40E_DEV_FUNC_CAP_LED 0x61 @@ -2416,6 +2416,7 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, u32 valid_functions, num_functions; u32 number, logical_id, phys_id; struct i40e_hw_capabilities *p; + u8 major_rev; u32 i = 0; u16 id; @@ -2433,6 +2434,7 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, number = le32_to_cpu(cap->number); logical_id = le32_to_cpu(cap->logical_id); phys_id = le32_to_cpu(cap->phys_id); + major_rev = cap->major_rev; switch (id) { case I40E_DEV_FUNC_CAP_SWITCH_MODE: @@ -2507,9 +2509,21 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, case I40E_DEV_FUNC_CAP_MSIX_VF: p->num_msix_vectors_vf = number; break; - case I40E_DEV_FUNC_CAP_MFP_MODE_1: - if (number == 1) - p->mfp_mode_1 = true; + case I40E_DEV_FUNC_CAP_FLEX10: + if (major_rev == 1) { + if (number == 1) { + p->flex10_enable = true; + p->flex10_capable = true; + } + } else { + /* Capability revision >= 2 */ + if (number & 1) + p->flex10_enable = true; + if (number & 2) + p->flex10_capable = true; + } + p->flex10_mode = logical_id; + p->flex10_status = phys_id; break; case I40E_DEV_FUNC_CAP_CEM: if (number == 1) @@ -2557,7 +2571,7 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, /* Software override ensuring FCoE is disabled if npar or mfp * mode because it is not supported in these modes. */ - if (p->npar_enable || p->mfp_mode_1) + if (p->npar_enable || p->flex10_enable) p->fcoe = false; /* count the enabled ports (aka the "not disabled" ports) */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 9a68c65b17ea..f2075d5b800c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -148,7 +148,9 @@ static struct i40e_stats i40e_gstrings_stats[] = { I40E_PF_STAT("fdir_flush_cnt", fd_flush_cnt), I40E_PF_STAT("fdir_atr_match", stats.fd_atr_match), I40E_PF_STAT("fdir_atr_tunnel_match", stats.fd_atr_tunnel_match), + I40E_PF_STAT("fdir_atr_status", stats.fd_atr_status), I40E_PF_STAT("fdir_sb_match", stats.fd_sb_match), + I40E_PF_STAT("fdir_sb_status", stats.fd_sb_status), /* LPI stats */ I40E_PF_STAT("tx_lpi_status", stats.tx_lpi_status), @@ -1465,17 +1467,8 @@ static int i40e_get_ts_info(struct net_device *dev, info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON); info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | - (1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ); + (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c index 9b987ccc9e82..b89856a5e313 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c @@ -116,6 +116,7 @@ exit: * @hw: pointer to our HW structure * @hmc_info: pointer to the HMC configuration information structure * @pd_index: which page descriptor index to manipulate + * @rsrc_pg: if not NULL, use preallocated page instead of allocating new one. * * This function: * 1. Initializes the pd entry @@ -129,12 +130,14 @@ exit: **/ i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw, struct i40e_hmc_info *hmc_info, - u32 pd_index) + u32 pd_index, + struct i40e_dma_mem *rsrc_pg) { i40e_status ret_code = 0; struct i40e_hmc_pd_table *pd_table; struct i40e_hmc_pd_entry *pd_entry; struct i40e_dma_mem mem; + struct i40e_dma_mem *page = &mem; u32 sd_idx, rel_pd_idx; u64 *pd_addr; u64 page_desc; @@ -155,18 +158,24 @@ i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw, pd_table = &hmc_info->sd_table.sd_entry[sd_idx].u.pd_table; pd_entry = &pd_table->pd_entry[rel_pd_idx]; if (!pd_entry->valid) { - /* allocate a 4K backing page */ - ret_code = i40e_allocate_dma_mem(hw, &mem, i40e_mem_bp, - I40E_HMC_PAGED_BP_SIZE, - I40E_HMC_PD_BP_BUF_ALIGNMENT); - if (ret_code) - goto exit; + if (rsrc_pg) { + pd_entry->rsrc_pg = true; + page = rsrc_pg; + } else { + /* allocate a 4K backing page */ + ret_code = i40e_allocate_dma_mem(hw, page, i40e_mem_bp, + I40E_HMC_PAGED_BP_SIZE, + I40E_HMC_PD_BP_BUF_ALIGNMENT); + if (ret_code) + goto exit; + pd_entry->rsrc_pg = false; + } - pd_entry->bp.addr = mem; + pd_entry->bp.addr = *page; pd_entry->bp.sd_pd_index = pd_index; pd_entry->bp.entry_type = I40E_SD_TYPE_PAGED; /* Set page address and valid bit */ - page_desc = mem.pa | 0x1; + page_desc = page->pa | 0x1; pd_addr = (u64 *)pd_table->pd_page_addr.va; pd_addr += rel_pd_idx; @@ -240,7 +249,8 @@ i40e_status i40e_remove_pd_bp(struct i40e_hw *hw, I40E_INVALIDATE_PF_HMC_PD(hw, sd_idx, idx); /* free memory here */ - ret_code = i40e_free_dma_mem(hw, &(pd_entry->bp.addr)); + if (!pd_entry->rsrc_pg) + ret_code = i40e_free_dma_mem(hw, &pd_entry->bp.addr); if (ret_code) goto exit; if (!pd_table->ref_cnt) diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_hmc.h index 732a02660330..386416bf7267 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.h @@ -62,6 +62,7 @@ struct i40e_hmc_bp { struct i40e_hmc_pd_entry { struct i40e_hmc_bp bp; u32 sd_index; + bool rsrc_pg; bool valid; }; @@ -218,7 +219,8 @@ i40e_status i40e_add_sd_table_entry(struct i40e_hw *hw, i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw, struct i40e_hmc_info *hmc_info, - u32 pd_index); + u32 pd_index, + struct i40e_dma_mem *rsrc_pg); i40e_status i40e_remove_pd_bp(struct i40e_hw *hw, struct i40e_hmc_info *hmc_info, u32 idx); diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c index 0079ad7bcd0e..d399eaf5aad5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c @@ -387,7 +387,7 @@ static i40e_status i40e_create_lan_hmc_object(struct i40e_hw *hw, /* update the pd table entry */ ret_code = i40e_add_pd_table_entry(hw, info->hmc_info, - i); + i, NULL); if (ret_code) { pd_error = true; break; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 48a52b35b614..6ce9086e558a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -39,7 +39,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 3 -#define DRV_VERSION_BUILD 4 +#define DRV_VERSION_BUILD 6 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -1123,6 +1123,18 @@ static void i40e_update_pf_stats(struct i40e_pf *pf) pf->stat_offsets_loaded, &osd->rx_lpi_count, &nsd->rx_lpi_count); + if (pf->flags & I40E_FLAG_FD_SB_ENABLED && + !(pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) + nsd->fd_sb_status = true; + else + nsd->fd_sb_status = false; + + if (pf->flags & I40E_FLAG_FD_ATR_ENABLED && + !(pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) + nsd->fd_atr_status = true; + else + nsd->fd_atr_status = false; + pf->stat_offsets_loaded = true; } @@ -7673,7 +7685,7 @@ static int i40e_sw_init(struct i40e_pf *pf) } /* MFP mode enabled */ - if (pf->hw.func_caps.npar_enable || pf->hw.func_caps.mfp_mode_1) { + if (pf->hw.func_caps.npar_enable || pf->hw.func_caps.flex10_enable) { pf->flags |= I40E_FLAG_MFP_ENABLED; dev_info(&pf->pdev->dev, "MFP mode Enabled\n"); if (i40e_get_npar_bw_setting(pf)) @@ -7981,7 +7993,6 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return err; } -#ifdef HAVE_BRIDGE_ATTRIBS /** * i40e_ndo_bridge_setlink - Set the hardware bridge mode * @dev: the netdev being configured @@ -7995,7 +8006,8 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], * bridge mode enabled. **/ static int i40e_ndo_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh) + struct nlmsghdr *nlh, + u16 flags) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; @@ -8066,14 +8078,9 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, * Return the mode in which the hardware bridge is operating in * i.e VEB or VEPA. **/ -#ifdef HAVE_BRIDGE_FILTER static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) -#else -static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, int nlflags) -#endif /* HAVE_BRIDGE_FILTER */ { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; @@ -8097,7 +8104,25 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, return ndo_dflt_bridge_getlink(skb, pid, seq, dev, veb->bridge_mode, nlflags, 0, 0, filter_mask, NULL); } -#endif /* HAVE_BRIDGE_ATTRIBS */ + +#define I40E_MAX_TUNNEL_HDR_LEN 80 +/** + * i40e_features_check - Validate encapsulated packet conforms to limits + * @skb: skb buff + * @netdev: This physical port's netdev + * @features: Offload features that the stack believes apply + **/ +static netdev_features_t i40e_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + if (skb->encapsulation && + (skb_inner_mac_header(skb) - skb_transport_header(skb) > + I40E_MAX_TUNNEL_HDR_LEN)) + return features & ~(NETIF_F_ALL_CSUM | NETIF_F_GSO_MASK); + + return features; +} static const struct net_device_ops i40e_netdev_ops = { .ndo_open = i40e_open, @@ -8133,10 +8158,9 @@ static const struct net_device_ops i40e_netdev_ops = { #endif .ndo_get_phys_port_id = i40e_get_phys_port_id, .ndo_fdb_add = i40e_ndo_fdb_add, -#ifdef HAVE_BRIDGE_ATTRIBS + .ndo_features_check = i40e_features_check, .ndo_bridge_getlink = i40e_ndo_bridge_getlink, .ndo_bridge_setlink = i40e_ndo_bridge_setlink, -#endif /* HAVE_BRIDGE_ATTRIBS */ }; /** @@ -9743,7 +9767,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = i40e_init_shared_code(hw); if (err) { - dev_info(&pdev->dev, "init_shared_code failed: %d\n", err); + dev_warn(&pdev->dev, "unidentified MAC or BLANK NVM: %d\n", + err); goto err_pf_reset; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 9a4f2bc70cd2..1fe230d2be5d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2616,6 +2616,8 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index))) writel(i, tx_ring->tail); + else + prefetchw(tx_desc + 1); return; diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 9a5a75b1e2bc..220371ece7c4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -213,7 +213,17 @@ struct i40e_hw_capabilities { bool dcb; bool fcoe; bool iscsi; /* Indicates iSCSI enabled */ - bool mfp_mode_1; + bool flex10_enable; + bool flex10_capable; + u32 flex10_mode; +#define I40E_FLEX10_MODE_UNKNOWN 0x0 +#define I40E_FLEX10_MODE_DCC 0x1 +#define I40E_FLEX10_MODE_DCI 0x2 + + u32 flex10_status; +#define I40E_FLEX10_STATUS_DCC_ERROR 0x1 +#define I40E_FLEX10_STATUS_VC_MODE 0x2 + bool mgmt_cem; bool ieee_1588; bool iwarp; @@ -1134,6 +1144,8 @@ struct i40e_hw_port_stats { u64 fd_atr_match; u64 fd_sb_match; u64 fd_atr_tunnel_match; + u32 fd_atr_status; + u32 fd_sb_status; /* EEE LPI */ u32 tx_lpi_status; u32 rx_lpi_status; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 23f95cdbdfcc..fdd7f5e3a66b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -160,13 +160,8 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) **/ static inline void i40e_vc_disable_vf(struct i40e_pf *pf, struct i40e_vf *vf) { - struct i40e_hw *hw = &pf->hw; - u32 reg; - - reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id)); - reg |= I40E_VPGEN_VFRTRIG_VFSWR_MASK; - wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg); - i40e_flush(hw); + i40e_vc_notify_vf_reset(vf); + i40e_reset_vf(vf, false); } /** @@ -542,11 +537,13 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) if (vf->port_vlan_id) i40e_vsi_add_pvid(vsi, vf->port_vlan_id); f = i40e_add_filter(vsi, vf->default_lan_addr.addr, - vf->port_vlan_id, true, false); + vf->port_vlan_id ? vf->port_vlan_id : -1, + true, false); if (!f) dev_info(&pf->pdev->dev, "Could not allocate VF MAC addr\n"); - f = i40e_add_filter(vsi, brdcast, vf->port_vlan_id, + f = i40e_add_filter(vsi, brdcast, + vf->port_vlan_id ? vf->port_vlan_id : -1, true, false); if (!f) dev_info(&pf->pdev->dev, @@ -835,6 +832,7 @@ complete_reset: i40e_alloc_vf_res(vf); i40e_enable_vf_mappings(vf); set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states); + clear_bit(I40E_VF_STAT_DISABLED, &vf->vf_states); /* tell the VF the reset is done */ wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE); @@ -2023,7 +2021,8 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) } /* delete the temporary mac address */ - i40e_del_filter(vsi, vf->default_lan_addr.addr, vf->port_vlan_id, + i40e_del_filter(vsi, vf->default_lan_addr.addr, + vf->port_vlan_id ? vf->port_vlan_id : -1, true, false); /* Delete all the filters for this VSI - we're going to kill it @@ -2088,6 +2087,10 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, goto error_pvid; } + if (vsi->info.pvid == (vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT))) + /* duplicate request, so just return success */ + goto error_pvid; + if (vsi->info.pvid == 0 && i40e_is_vsi_in_vlan(vsi)) { dev_err(&pf->pdev->dev, "VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n", diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index e715bccfb5d2..d5bd6f066921 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -34,7 +34,7 @@ */ #define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR 0x0002 +#define I40E_FW_API_VERSION_MINOR 0x0004 #define I40E_FW_API_VERSION_A0_MINOR 0x0000 struct i40e_aq_desc { @@ -133,12 +133,7 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_list_func_capabilities = 0x000A, i40e_aqc_opc_list_dev_capabilities = 0x000B, - i40e_aqc_opc_set_cppm_configuration = 0x0103, - i40e_aqc_opc_set_arp_proxy_entry = 0x0104, - i40e_aqc_opc_set_ns_proxy_entry = 0x0105, - /* LAA */ - i40e_aqc_opc_mng_laa = 0x0106, /* AQ obsolete */ i40e_aqc_opc_mac_address_read = 0x0107, i40e_aqc_opc_mac_address_write = 0x0108, @@ -260,7 +255,6 @@ enum i40e_admin_queue_opc { /* Tunnel commands */ i40e_aqc_opc_add_udp_tunnel = 0x0B00, i40e_aqc_opc_del_udp_tunnel = 0x0B01, - i40e_aqc_opc_tunnel_key_structure = 0x0B10, /* Async Events */ i40e_aqc_opc_event_lan_overflow = 0x1001, @@ -272,8 +266,6 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_oem_ocbb_initialize = 0xFE03, /* debug commands */ - i40e_aqc_opc_debug_get_deviceid = 0xFF00, - i40e_aqc_opc_debug_set_mode = 0xFF01, i40e_aqc_opc_debug_read_reg = 0xFF03, i40e_aqc_opc_debug_write_reg = 0xFF04, i40e_aqc_opc_debug_modify_reg = 0xFF07, @@ -507,7 +499,8 @@ struct i40e_aqc_mac_address_read { #define I40E_AQC_SAN_ADDR_VALID 0x20 #define I40E_AQC_PORT_ADDR_VALID 0x40 #define I40E_AQC_WOL_ADDR_VALID 0x80 -#define I40E_AQC_ADDR_VALID_MASK 0xf0 +#define I40E_AQC_MC_MAG_EN_VALID 0x100 +#define I40E_AQC_ADDR_VALID_MASK 0x1F0 u8 reserved[6]; __le32 addr_high; __le32 addr_low; @@ -530,7 +523,9 @@ struct i40e_aqc_mac_address_write { #define I40E_AQC_WRITE_TYPE_LAA_ONLY 0x0000 #define I40E_AQC_WRITE_TYPE_LAA_WOL 0x4000 #define I40E_AQC_WRITE_TYPE_PORT 0x8000 -#define I40E_AQC_WRITE_TYPE_MASK 0xc000 +#define I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG 0xC000 +#define I40E_AQC_WRITE_TYPE_MASK 0xC000 + __le16 mac_sah; __le32 mac_sal; u8 reserved[8]; @@ -1066,6 +1061,7 @@ struct i40e_aqc_set_vsi_promiscuous_modes { __le16 seid; #define I40E_AQC_VSI_PROM_CMD_SEID_MASK 0x3FF __le16 vlan_tag; +#define I40E_AQC_SET_VSI_VLAN_MASK 0x0FFF #define I40E_AQC_SET_VSI_VLAN_VALID 0x8000 u8 reserved[8]; }; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h index 931c88044300..adc6f71f40a8 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h @@ -62,6 +62,7 @@ struct i40e_hmc_bp { struct i40e_hmc_pd_entry { struct i40e_hmc_bp bp; u32 sd_index; + bool rsrc_pg; bool valid; }; @@ -218,7 +219,8 @@ i40e_status i40e_add_sd_table_entry(struct i40e_hw *hw, i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw, struct i40e_hmc_info *hmc_info, - u32 pd_index); + u32 pd_index, + struct i40e_dma_mem *rsrc_pg); i40e_status i40e_remove_pd_bp(struct i40e_hw *hw, struct i40e_hmc_info *hmc_info, u32 idx); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 395f32f226c0..0f0e185b5c66 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -1841,6 +1841,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index))) writel(i, tx_ring->tail); + else + prefetchw(tx_desc + 1); return; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index c463ec41579c..3969c6548af0 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -213,7 +213,17 @@ struct i40e_hw_capabilities { bool dcb; bool fcoe; bool iscsi; /* Indicates iSCSI enabled */ - bool mfp_mode_1; + bool flex10_enable; + bool flex10_capable; + u32 flex10_mode; +#define I40E_FLEX10_MODE_UNKNOWN 0x0 +#define I40E_FLEX10_MODE_DCC 0x1 +#define I40E_FLEX10_MODE_DCI 0x2 + + u32 flex10_status; +#define I40E_FLEX10_STATUS_DCC_ERROR 0x1 +#define I40E_FLEX10_STATUS_VC_MODE 0x2 + bool mgmt_cem; bool ieee_1588; bool iwarp; @@ -1109,6 +1119,8 @@ struct i40e_hw_port_stats { u64 fd_atr_match; u64 fd_sb_match; u64 fd_atr_tunnel_match; + u32 fd_atr_status; + u32 fd_sb_status; /* EEE LPI */ u32 tx_lpi_status; u32 rx_lpi_status; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 4ab4ebba07a1..c698523923e4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -34,7 +34,7 @@ char i40evf_driver_name[] = "i40evf"; static const char i40evf_driver_string[] = "Intel(R) XL710/X710 Virtual Function Network Driver"; -#define DRV_VERSION "1.2.25" +#define DRV_VERSION "1.3.2" const char i40evf_driver_version[] = DRV_VERSION; static const char i40evf_copyright[] = "Copyright (c) 2013 - 2014 Intel Corporation."; @@ -406,7 +406,7 @@ static int i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) /* The ideal configuration... * We have enough vectors to map one per queue. */ - if (q_vectors == (rxr_remaining * 2)) { + if (q_vectors >= (rxr_remaining * 2)) { for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++) i40evf_map_vector_to_rxq(adapter, v_start, rxr_idx); @@ -892,8 +892,10 @@ static void i40evf_set_rx_mode(struct net_device *netdev) break; } } + if (ether_addr_equal(f->macaddr, adapter->hw.mac.addr)) + found = true; } - if (found) { + if (!found) { f->remove = true; adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; } @@ -1856,6 +1858,7 @@ static int i40evf_open(struct net_device *netdev) if (err) goto err_req_irq; + i40evf_add_filter(adapter, adapter->hw.mac.addr); i40evf_configure(adapter); err = i40evf_up_complete(adapter); @@ -1996,7 +1999,6 @@ static void i40evf_init_task(struct work_struct *work) struct i40evf_adapter, init_task.work); struct net_device *netdev = adapter->netdev; - struct i40evf_mac_filter *f; struct i40e_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; int i, err, bufsz; @@ -2130,16 +2132,6 @@ static void i40evf_init_task(struct work_struct *work) ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); - f = kzalloc(sizeof(*f), GFP_ATOMIC); - if (!f) - goto err_sw_init; - - ether_addr_copy(f->macaddr, adapter->hw.mac.addr); - f->add = true; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; - - list_add(&f->list, &adapter->mac_filter_list); - init_timer(&adapter->watchdog_timer); adapter->watchdog_timer.function = &i40evf_watchdog_timer; adapter->watchdog_timer.data = (unsigned long)adapter; diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index b0182dd31346..d19256994e5c 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -139,10 +139,6 @@ static s32 igb_check_for_link_media_swap(struct e1000_hw *hw) if (ret_val) return ret_val; - /* reset page to 0 */ - ret_val = phy->ops.write_reg(hw, E1000_M88E1112_PAGE_ADDR, 0); - if (ret_val) - return ret_val; if (data & E1000_M88E1112_STATUS_LINK) port = E1000_MEDIA_PORT_OTHER; @@ -151,8 +147,20 @@ static s32 igb_check_for_link_media_swap(struct e1000_hw *hw) if (port && (hw->dev_spec._82575.media_port != port)) { hw->dev_spec._82575.media_port = port; hw->dev_spec._82575.media_changed = true; + } + + if (port == E1000_MEDIA_PORT_COPPER) { + /* reset page to 0 */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1112_PAGE_ADDR, 0); + if (ret_val) + return ret_val; + igb_check_for_link_82575(hw); } else { - ret_val = igb_check_for_link_82575(hw); + igb_check_for_link_82575(hw); + /* reset page to 0 */ + ret_val = phy->ops.write_reg(hw, E1000_M88E1112_PAGE_ADDR, 0); + if (ret_val) + return ret_val; } return 0; diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index d5673eb90c54..109cad928e71 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2396,10 +2396,6 @@ static int igb_get_ts_info(struct net_device *dev, info->rx_filters |= (1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | (1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); return 0; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 2f70a9b152bd..fc7729e78f3d 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6621,22 +6621,25 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, struct sk_buff *skb) { struct page *page = rx_buffer->page; + unsigned char *va = page_address(page) + rx_buffer->page_offset; unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); #if (PAGE_SIZE < 8192) unsigned int truesize = IGB_RX_BUFSZ; #else - unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); + unsigned int truesize = SKB_DATA_ALIGN(size); #endif + unsigned int pull_len; - if ((size <= IGB_RX_HDR_LEN) && !skb_is_nonlinear(skb)) { - unsigned char *va = page_address(page) + rx_buffer->page_offset; + if (unlikely(skb_is_nonlinear(skb))) + goto add_tail_frag; - if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); - va += IGB_TS_HDR_LEN; - size -= IGB_TS_HDR_LEN; - } + if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) { + igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); + va += IGB_TS_HDR_LEN; + size -= IGB_TS_HDR_LEN; + } + if (likely(size <= IGB_RX_HDR_LEN)) { memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); /* page is not reserved, we can reuse buffer as-is */ @@ -6648,8 +6651,21 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, return false; } + /* we need the header to contain the greater of either ETH_HLEN or + * 60 bytes if the skb->len is less than 60 for skb_pad. + */ + pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN); + + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); + + /* update all of the pointers */ + va += pull_len; + size -= pull_len; + +add_tail_frag: skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - rx_buffer->page_offset, size, truesize); + (unsigned long)va & ~PAGE_MASK, size, truesize); return igb_can_reuse_rx_page(rx_buffer, page, truesize); } @@ -6791,62 +6807,6 @@ static bool igb_is_non_eop(struct igb_ring *rx_ring, } /** - * igb_pull_tail - igb specific version of skb_pull_tail - * @rx_ring: rx descriptor ring packet is being transacted on - * @rx_desc: pointer to the EOP Rx descriptor - * @skb: pointer to current skb being adjusted - * - * This function is an igb specific version of __pskb_pull_tail. The - * main difference between this version and the original function is that - * this function can make several assumptions about the state of things - * that allow for significant optimizations versus the standard function. - * As a result we can do things like drop a frag and maintain an accurate - * truesize for the skb. - */ -static void igb_pull_tail(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) -{ - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; - unsigned char *va; - unsigned int pull_len; - - /* it is valid to use page_address instead of kmap since we are - * working with pages allocated out of the lomem pool per - * alloc_page(GFP_ATOMIC) - */ - va = skb_frag_address(frag); - - if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - /* retrieve timestamp from buffer */ - igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); - - /* update pointers to remove timestamp header */ - skb_frag_size_sub(frag, IGB_TS_HDR_LEN); - frag->page_offset += IGB_TS_HDR_LEN; - skb->data_len -= IGB_TS_HDR_LEN; - skb->len -= IGB_TS_HDR_LEN; - - /* move va to start of packet data */ - va += IGB_TS_HDR_LEN; - } - - /* we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN); - - /* align pull length to size of long to optimize memcpy performance */ - skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); - - /* update all of the pointers */ - skb_frag_size_sub(frag, pull_len); - frag->page_offset += pull_len; - skb->data_len -= pull_len; - skb->tail += pull_len; -} - -/** * igb_cleanup_headers - Correct corrupted or empty headers * @rx_ring: rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor @@ -6873,10 +6833,6 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, } } - /* place header in linear portion of buffer */ - if (skb_is_nonlinear(skb)) - igb_pull_tail(rx_ring, rx_desc, skb); - /* if eth_skb_pad returns an error the skb was freed */ if (eth_skb_pad(skb)) return true; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index 6b87d9634614..b1e364d26aa7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1394,14 +1394,12 @@ s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 fdirctrl) /* * Continue setup of fdirctrl register bits: * Turn perfect match filtering on - * Report hash in RSS field of Rx wb descriptor * Initialize the drop queue * Move the flexible bytes to use the ethertype - shift 6 words * Set the maximum length per hash bucket to 0xA filters * Send interrupt when 64 (0x4 * 16) filters are left */ fdirctrl |= IXGBE_FDIRCTRL_PERFECT_MATCH | - IXGBE_FDIRCTRL_REPORT_STATUS | (IXGBE_FDIR_DROP_QUEUE << IXGBE_FDIRCTRL_DROP_Q_SHIFT) | (0x6 << IXGBE_FDIRCTRL_FLEX_SHIFT) | (0xA << IXGBE_FDIRCTRL_MAX_LENGTH_SHIFT) | diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index ec7b2324b77b..f7aeb560a504 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2938,14 +2938,6 @@ static int ixgbe_get_ts_info(struct net_device *dev, (1 << HWTSTAMP_FILTER_NONE) | (1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | (1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); break; default: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 9aa6104e34ea..3e6a9319c718 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1360,14 +1360,31 @@ static int __ixgbe_notify_dca(struct device *dev, void *data) } #endif /* CONFIG_IXGBE_DCA */ + +#define IXGBE_RSS_L4_TYPES_MASK \ + ((1ul << IXGBE_RXDADV_RSSTYPE_IPV4_TCP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV4_UDP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_TCP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_UDP)) + static inline void ixgbe_rx_hash(struct ixgbe_ring *ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { - if (ring->netdev->features & NETIF_F_RXHASH) - skb_set_hash(skb, - le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), - PKT_HASH_TYPE_L3); + u16 rss_type; + + if (!(ring->netdev->features & NETIF_F_RXHASH)) + return; + + rss_type = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.pkt_info) & + IXGBE_RXDADV_RSSTYPE_MASK; + + if (!rss_type) + return; + + skb_set_hash(skb, le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), + (IXGBE_RSS_L4_TYPES_MASK & (1ul << rss_type)) ? + PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3); } #ifdef IXGBE_FCOE diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h index 770e21a64388..58434584b16d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/defines.h +++ b/drivers/net/ethernet/intel/ixgbevf/defines.h @@ -161,6 +161,18 @@ typedef u32 ixgbe_link_speed; #define IXGBE_RXDADV_SPLITHEADER_EN 0x00001000 #define IXGBE_RXDADV_SPH 0x8000 +/* RSS Hash results */ +#define IXGBE_RXDADV_RSSTYPE_NONE 0x00000000 +#define IXGBE_RXDADV_RSSTYPE_IPV4_TCP 0x00000001 +#define IXGBE_RXDADV_RSSTYPE_IPV4 0x00000002 +#define IXGBE_RXDADV_RSSTYPE_IPV6_TCP 0x00000003 +#define IXGBE_RXDADV_RSSTYPE_IPV6_EX 0x00000004 +#define IXGBE_RXDADV_RSSTYPE_IPV6 0x00000005 +#define IXGBE_RXDADV_RSSTYPE_IPV6_TCP_EX 0x00000006 +#define IXGBE_RXDADV_RSSTYPE_IPV4_UDP 0x00000007 +#define IXGBE_RXDADV_RSSTYPE_IPV6_UDP 0x00000008 +#define IXGBE_RXDADV_RSSTYPE_IPV6_UDP_EX 0x00000009 + #define IXGBE_RXD_ERR_FRAME_ERR_MASK ( \ IXGBE_RXD_ERR_CE | \ IXGBE_RXD_ERR_LE | \ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index e71cdde9cb01..b2c86f1b8a9f 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -457,6 +457,32 @@ static void ixgbevf_rx_skb(struct ixgbevf_q_vector *q_vector, napi_gro_receive(&q_vector->napi, skb); } +#define IXGBE_RSS_L4_TYPES_MASK \ + ((1ul << IXGBE_RXDADV_RSSTYPE_IPV4_TCP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV4_UDP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_TCP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_UDP)) + +static inline void ixgbevf_rx_hash(struct ixgbevf_ring *ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + u16 rss_type; + + if (!(ring->netdev->features & NETIF_F_RXHASH)) + return; + + rss_type = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.pkt_info) & + IXGBE_RXDADV_RSSTYPE_MASK; + + if (!rss_type) + return; + + skb_set_hash(skb, le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), + (IXGBE_RSS_L4_TYPES_MASK & (1ul << rss_type)) ? + PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3); +} + /** * ixgbevf_rx_checksum - indicate in skb if hw indicated a good cksum * @ring: structure containig ring specific data @@ -506,6 +532,7 @@ static void ixgbevf_process_skb_fields(struct ixgbevf_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { + ixgbevf_rx_hash(rx_ring, rx_desc, skb); ixgbevf_rx_checksum(rx_ring, rx_desc, skb); if (ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) { @@ -649,46 +676,6 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring, } /** - * ixgbevf_pull_tail - ixgbevf specific version of skb_pull_tail - * @rx_ring: rx descriptor ring packet is being transacted on - * @skb: pointer to current skb being adjusted - * - * This function is an ixgbevf specific version of __pskb_pull_tail. The - * main difference between this version and the original function is that - * this function can make several assumptions about the state of things - * that allow for significant optimizations versus the standard function. - * As a result we can do things like drop a frag and maintain an accurate - * truesize for the skb. - **/ -static void ixgbevf_pull_tail(struct ixgbevf_ring *rx_ring, - struct sk_buff *skb) -{ - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; - unsigned char *va; - unsigned int pull_len; - - /* it is valid to use page_address instead of kmap since we are - * working with pages allocated out of the lomem pool per - * alloc_page(GFP_ATOMIC) - */ - va = skb_frag_address(frag); - - /* we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, IXGBEVF_RX_HDR_SIZE); - - /* align pull length to size of long to optimize memcpy performance */ - skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); - - /* update all of the pointers */ - skb_frag_size_sub(frag, pull_len); - frag->page_offset += pull_len; - skb->data_len -= pull_len; - skb->tail += pull_len; -} - -/** * ixgbevf_cleanup_headers - Correct corrupted or empty headers * @rx_ring: rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor @@ -721,10 +708,6 @@ static bool ixgbevf_cleanup_headers(struct ixgbevf_ring *rx_ring, } } - /* place header in linear portion of buffer */ - if (skb_is_nonlinear(skb)) - ixgbevf_pull_tail(rx_ring, skb); - /* if eth_skb_pad returns an error the skb was freed */ if (eth_skb_pad(skb)) return true; @@ -789,16 +772,19 @@ static bool ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring, struct sk_buff *skb) { struct page *page = rx_buffer->page; + unsigned char *va = page_address(page) + rx_buffer->page_offset; unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); #if (PAGE_SIZE < 8192) unsigned int truesize = IXGBEVF_RX_BUFSZ; #else unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); #endif + unsigned int pull_len; - if ((size <= IXGBEVF_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) { - unsigned char *va = page_address(page) + rx_buffer->page_offset; + if (unlikely(skb_is_nonlinear(skb))) + goto add_tail_frag; + if (likely(size <= IXGBEVF_RX_HDR_SIZE)) { memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); /* page is not reserved, we can reuse buffer as is */ @@ -810,8 +796,21 @@ static bool ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring, return false; } + /* we need the header to contain the greater of either ETH_HLEN or + * 60 bytes if the skb->len is less than 60 for skb_pad. + */ + pull_len = eth_get_headlen(va, IXGBEVF_RX_HDR_SIZE); + + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); + + /* update all of the pointers */ + va += pull_len; + size -= pull_len; + +add_tail_frag: skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - rx_buffer->page_offset, size, truesize); + (unsigned long)va & ~PAGE_MASK, size, truesize); /* avoid re-using remote pages */ if (unlikely(ixgbevf_page_is_reserved(page))) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 62e48bc0cb23..fe2299ac4f5c 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3027,8 +3027,8 @@ static int mvneta_probe(struct platform_device *pdev) const char *dt_mac_addr; char hw_mac_addr[ETH_ALEN]; const char *mac_from; + const char *managed; int phy_mode; - int fixed_phy = 0; int err; /* Our multiqueue support is not complete, so for now, only @@ -3062,7 +3062,6 @@ static int mvneta_probe(struct platform_device *pdev) dev_err(&pdev->dev, "cannot register fixed PHY\n"); goto err_free_irq; } - fixed_phy = 1; /* In the case of a fixed PHY, the DT node associated * to the PHY is the Ethernet MAC DT node. @@ -3086,8 +3085,10 @@ static int mvneta_probe(struct platform_device *pdev) pp = netdev_priv(dev); pp->phy_node = phy_node; pp->phy_interface = phy_mode; - pp->use_inband_status = (phy_mode == PHY_INTERFACE_MODE_SGMII) && - fixed_phy; + + err = of_property_read_string(dn, "managed", &managed); + pp->use_inband_status = (err == 0 && + strcmp(managed, "in-band-status") == 0); pp->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(pp->clk)) { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 7a4f20bb7fcb..12c65e1ad6a9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -917,7 +917,9 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud if (dev->features & NETIF_F_RXHASH) skb_set_hash(gro_skb, be32_to_cpu(cqe->immed_rss_invalid), - PKT_HASH_TYPE_L3); + (ip_summed == CHECKSUM_UNNECESSARY) ? + PKT_HASH_TYPE_L4 : + PKT_HASH_TYPE_L3); skb_record_rx_queue(gro_skb, cq->ring); skb_mark_napi_id(gro_skb, &cq->napi); @@ -963,7 +965,9 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud if (dev->features & NETIF_F_RXHASH) skb_set_hash(skb, be32_to_cpu(cqe->immed_rss_invalid), - PKT_HASH_TYPE_L3); + (ip_summed == CHECKSUM_UNNECESSARY) ? + PKT_HASH_TYPE_L4 : + PKT_HASH_TYPE_L3); if ((be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_VLAN_PRESENT_MASK) && diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 12fbfcb44d8a..d76f4257e305 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2907,6 +2907,8 @@ static u64 mlx4_enable_sriov(struct mlx4_dev *dev, struct pci_dev *pdev, { u64 dev_flags = dev->flags; int err = 0; + int fw_enabled_sriov_vfs = min(pci_sriov_get_totalvfs(pdev), + MLX4_MAX_NUM_VF); if (reset_flow) { dev->dev_vfs = kcalloc(total_vfs, sizeof(*dev->dev_vfs), @@ -2932,6 +2934,12 @@ static u64 mlx4_enable_sriov(struct mlx4_dev *dev, struct pci_dev *pdev, } if (!(dev->flags & MLX4_FLAG_SRIOV)) { + if (total_vfs > fw_enabled_sriov_vfs) { + mlx4_err(dev, "requested vfs (%d) > available vfs (%d). Continuing without SR_IOV\n", + total_vfs, fw_enabled_sriov_vfs); + err = -ENOMEM; + goto disable_sriov; + } mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", total_vfs); err = pci_enable_sriov(pdev, total_vfs); } @@ -3413,20 +3421,20 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data, goto err_disable_pdev; } } - if (total_vfs >= MLX4_MAX_NUM_VF) { + if (total_vfs > MLX4_MAX_NUM_VF) { dev_err(&pdev->dev, - "Requested more VF's (%d) than allowed (%d)\n", - total_vfs, MLX4_MAX_NUM_VF - 1); + "Requested more VF's (%d) than allowed by hw (%d)\n", + total_vfs, MLX4_MAX_NUM_VF); err = -EINVAL; goto err_disable_pdev; } for (i = 0; i < MLX4_MAX_PORTS; i++) { - if (nvfs[i] + nvfs[2] >= MLX4_MAX_NUM_VF_P_PORT) { + if (nvfs[i] + nvfs[2] > MLX4_MAX_NUM_VF_P_PORT) { dev_err(&pdev->dev, - "Requested more VF's (%d) for port (%d) than allowed (%d)\n", + "Requested more VF's (%d) for port (%d) than allowed by driver (%d)\n", nvfs[i] + nvfs[2], i + 1, - MLX4_MAX_NUM_VF_P_PORT - 1); + MLX4_MAX_NUM_VF_P_PORT); err = -EINVAL; goto err_disable_pdev; } diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index c28111749e1f..2d1b94274079 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -8226,31 +8226,7 @@ static void s2io_rem_nic(struct pci_dev *pdev) pci_disable_device(pdev); } -/** - * s2io_starter - Entry point for the driver - * Description: This function is the entry point for the driver. It verifies - * the module loadable parameters and initializes PCI configuration space. - */ - -static int __init s2io_starter(void) -{ - return pci_register_driver(&s2io_driver); -} - -/** - * s2io_closer - Cleanup routine for the driver - * Description: This function is the cleanup routine for the driver. It - * unregisters the driver. - */ - -static __exit void s2io_closer(void) -{ - pci_unregister_driver(&s2io_driver); - DBG_PRINT(INIT_DBG, "cleanup done\n"); -} - -module_init(s2io_starter); -module_exit(s2io_closer); +module_pci_driver(s2io_driver); static int check_L2_lro_capable(u8 *buffer, struct iphdr **ip, struct tcphdr **tcp, struct RxD_t *rxdp, diff --git a/drivers/net/ethernet/neterion/s2io.h b/drivers/net/ethernet/neterion/s2io.h index d89b6ed82c51..6c5997dc8afc 100644 --- a/drivers/net/ethernet/neterion/s2io.h +++ b/drivers/net/ethernet/neterion/s2io.h @@ -1085,8 +1085,6 @@ static void s2io_txpic_intr_handle(struct s2io_nic *sp); static void tx_intr_handler(struct fifo_info *fifo_data); static void s2io_handle_errors(void * dev_id); -static int s2io_starter(void); -static void s2io_closer(void); static void s2io_tx_watchdog(struct net_device *dev); static void s2io_set_multicast(struct net_device *dev); static int rx_osm_handler(struct ring_info *ring_data, struct RxD_t * rxdp); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 2f6cc423ab1d..7dbab3c20db5 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -2403,7 +2403,6 @@ int qlcnic_alloc_tx_rings(struct qlcnic_adapter *adapter, qlcnic_free_tx_rings(adapter); return -ENOMEM; } - memset(cmd_buf_arr, 0, TX_BUFF_RINGSIZE(tx_ring)); tx_ring->cmd_buf_arr = cmd_buf_arr; spin_lock_init(&tx_ring->tx_clean_lock); } diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 78849dd4ef8e..779bb58a068e 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -223,9 +223,9 @@ static void ravb_ring_free(struct net_device *ndev, int q) static void ravb_ring_format(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); - struct ravb_ex_rx_desc *rx_desc = NULL; - struct ravb_tx_desc *tx_desc = NULL; - struct ravb_desc *desc = NULL; + struct ravb_ex_rx_desc *rx_desc; + struct ravb_tx_desc *tx_desc; + struct ravb_desc *desc; int rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q]; int tx_ring_size = sizeof(*tx_desc) * priv->num_tx_ring[q]; dma_addr_t dma_addr; @@ -439,7 +439,7 @@ static int ravb_tx_free(struct net_device *ndev, int q) struct net_device_stats *stats = &priv->stats[q]; struct ravb_tx_desc *desc; int free_num = 0; - int entry = 0; + int entry; u32 size; for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) { @@ -512,8 +512,8 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) struct sk_buff *skb; dma_addr_t dma_addr; struct timespec64 ts; - u16 pkt_len = 0; u8 desc_status; + u16 pkt_len; int limit; boguscnt = min(boguscnt, *quota); @@ -1277,8 +1277,8 @@ static void ravb_tx_timeout_work(struct work_struct *work) static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); - struct ravb_tstamp_skb *ts_skb = NULL; u16 q = skb_get_queue_mapping(skb); + struct ravb_tstamp_skb *ts_skb; struct ravb_tx_desc *desc; unsigned long flags; u32 dma_addr; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 2d8578cade03..7b4c3474acfe 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -202,6 +202,7 @@ enum { ROCKER_CTRL_IPV4_MCAST, ROCKER_CTRL_IPV6_MCAST, ROCKER_CTRL_DFLT_BRIDGING, + ROCKER_CTRL_DFLT_OVS, ROCKER_CTRL_MAX, }; @@ -321,9 +322,21 @@ static u16 rocker_port_vlan_to_vid(const struct rocker_port *rocker_port, return ntohs(vlan_id); } +static bool rocker_port_is_slave(const struct rocker_port *rocker_port, + const char *kind) +{ + return rocker_port->bridge_dev && + !strcmp(rocker_port->bridge_dev->rtnl_link_ops->kind, kind); +} + static bool rocker_port_is_bridged(const struct rocker_port *rocker_port) { - return !!rocker_port->bridge_dev; + return rocker_port_is_slave(rocker_port, "bridge"); +} + +static bool rocker_port_is_ovsed(const struct rocker_port *rocker_port) +{ + return rocker_port_is_slave(rocker_port, "openvswitch"); } #define ROCKER_OP_FLAG_REMOVE BIT(0) @@ -1818,6 +1831,30 @@ rocker_cmd_set_port_settings_macaddr_prep(const struct rocker_port *rocker_port, } static int +rocker_cmd_set_port_settings_mtu_prep(const struct rocker_port *rocker_port, + struct rocker_desc_info *desc_info, + void *priv) +{ + int mtu = *(int *)priv; + struct rocker_tlv *cmd_info; + + if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE, + ROCKER_TLV_CMD_TYPE_SET_PORT_SETTINGS)) + return -EMSGSIZE; + cmd_info = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO); + if (!cmd_info) + return -EMSGSIZE; + if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_PPORT, + rocker_port->pport)) + return -EMSGSIZE; + if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_MTU, + mtu)) + return -EMSGSIZE; + rocker_tlv_nest_end(desc_info, cmd_info); + return 0; +} + +static int rocker_cmd_set_port_learning_prep(const struct rocker_port *rocker_port, struct rocker_desc_info *desc_info, void *priv) @@ -1874,6 +1911,14 @@ static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port, macaddr, NULL, NULL); } +static int rocker_cmd_set_port_settings_mtu(struct rocker_port *rocker_port, + int mtu) +{ + return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0, + rocker_cmd_set_port_settings_mtu_prep, + &mtu, NULL, NULL); +} + static int rocker_port_set_learning(struct rocker_port *rocker_port, enum switchdev_trans trans) { @@ -3243,6 +3288,12 @@ static struct rocker_ctrl { .bridge = true, .copy_to_cpu = true, }, + [ROCKER_CTRL_DFLT_OVS] = { + /* pass all pkts up to CPU */ + .eth_dst = zero_mac, + .eth_dst_mask = zero_mac, + .acl = true, + }, }; static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, @@ -3755,11 +3806,14 @@ static int rocker_port_stp_update(struct rocker_port *rocker_port, break; case BR_STATE_LEARNING: case BR_STATE_FORWARDING: - want[ROCKER_CTRL_LINK_LOCAL_MCAST] = true; + if (!rocker_port_is_ovsed(rocker_port)) + want[ROCKER_CTRL_LINK_LOCAL_MCAST] = true; want[ROCKER_CTRL_IPV4_MCAST] = true; want[ROCKER_CTRL_IPV6_MCAST] = true; if (rocker_port_is_bridged(rocker_port)) want[ROCKER_CTRL_DFLT_BRIDGING] = true; + else if (rocker_port_is_ovsed(rocker_port)) + want[ROCKER_CTRL_DFLT_OVS] = true; else want[ROCKER_CTRL_LOCAL_ARP] = true; break; @@ -3983,7 +4037,8 @@ static int rocker_port_open(struct net_device *dev) napi_enable(&rocker_port->napi_tx); napi_enable(&rocker_port->napi_rx); - rocker_port_set_enable(rocker_port, true); + if (!dev->proto_down) + rocker_port_set_enable(rocker_port, true); netif_start_queue(dev); return 0; @@ -4152,6 +4207,34 @@ static int rocker_port_set_mac_address(struct net_device *dev, void *p) return 0; } +static int rocker_port_change_mtu(struct net_device *dev, int new_mtu) +{ + struct rocker_port *rocker_port = netdev_priv(dev); + int running = netif_running(dev); + int err; + +#define ROCKER_PORT_MIN_MTU 68 +#define ROCKER_PORT_MAX_MTU 9000 + + if (new_mtu < ROCKER_PORT_MIN_MTU || new_mtu > ROCKER_PORT_MAX_MTU) + return -EINVAL; + + if (running) + rocker_port_stop(dev); + + netdev_info(dev, "MTU change from %d to %d\n", dev->mtu, new_mtu); + dev->mtu = new_mtu; + + err = rocker_cmd_set_port_settings_mtu(rocker_port, new_mtu); + if (err) + return err; + + if (running) + err = rocker_port_open(dev); + + return err; +} + static int rocker_port_get_phys_port_name(struct net_device *dev, char *buf, size_t len) { @@ -4167,11 +4250,23 @@ static int rocker_port_get_phys_port_name(struct net_device *dev, return err ? -EOPNOTSUPP : 0; } +static int rocker_port_change_proto_down(struct net_device *dev, + bool proto_down) +{ + struct rocker_port *rocker_port = netdev_priv(dev); + + if (rocker_port->dev->flags & IFF_UP) + rocker_port_set_enable(rocker_port, !proto_down); + rocker_port->dev->proto_down = proto_down; + return 0; +} + static const struct net_device_ops rocker_port_netdev_ops = { .ndo_open = rocker_port_open, .ndo_stop = rocker_port_stop, .ndo_start_xmit = rocker_port_xmit, .ndo_set_mac_address = rocker_port_set_mac_address, + .ndo_change_mtu = rocker_port_change_mtu, .ndo_bridge_getlink = switchdev_port_bridge_getlink, .ndo_bridge_setlink = switchdev_port_bridge_setlink, .ndo_bridge_dellink = switchdev_port_bridge_dellink, @@ -4179,6 +4274,7 @@ static const struct net_device_ops rocker_port_netdev_ops = { .ndo_fdb_del = switchdev_port_fdb_del, .ndo_fdb_dump = switchdev_port_fdb_dump, .ndo_get_phys_port_name = rocker_port_get_phys_port_name, + .ndo_change_proto_down = rocker_port_change_proto_down, }; /******************** @@ -4726,6 +4822,7 @@ static int rocker_port_rx_proc(const struct rocker *rocker, const struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1]; struct sk_buff *skb = rocker_desc_cookie_ptr_get(desc_info); size_t rx_len; + u16 rx_flags = 0; if (!skb) return -ENOENT; @@ -4733,6 +4830,8 @@ static int rocker_port_rx_proc(const struct rocker *rocker, rocker_tlv_parse_desc(attrs, ROCKER_TLV_RX_MAX, desc_info); if (!attrs[ROCKER_TLV_RX_FRAG_LEN]) return -EINVAL; + if (attrs[ROCKER_TLV_RX_FLAGS]) + rx_flags = rocker_tlv_get_u16(attrs[ROCKER_TLV_RX_FLAGS]); rocker_dma_rx_ring_skb_unmap(rocker, attrs); @@ -4740,6 +4839,9 @@ static int rocker_port_rx_proc(const struct rocker *rocker, skb_put(skb, rx_len); skb->protocol = eth_type_trans(skb, rocker_port->dev); + if (rx_flags & ROCKER_RX_FLAGS_FWD_OFFLOAD) + skb->offload_fwd_mark = rocker_port->dev->offload_fwd_mark; + rocker_port->dev->stats.rx_packets++; rocker_port->dev->stats.rx_bytes += skb->len; @@ -4877,6 +4979,8 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) } rocker->ports[port_number] = rocker_port; + switchdev_port_fwd_mark_set(rocker_port->dev, NULL, false); + rocker_port_set_learning(rocker_port, SWITCHDEV_TRANS_NONE); err = rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE, 0); @@ -5156,6 +5260,7 @@ static int rocker_port_bridge_join(struct rocker_port *rocker_port, rocker_port_internal_vlan_id_get(rocker_port, bridge->ifindex); rocker_port->bridge_dev = bridge; + switchdev_port_fwd_mark_set(rocker_port->dev, bridge, true); return rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE, untagged_vid, 0); @@ -5176,6 +5281,8 @@ static int rocker_port_bridge_leave(struct rocker_port *rocker_port) rocker_port_internal_vlan_id_get(rocker_port, rocker_port->dev->ifindex); + switchdev_port_fwd_mark_set(rocker_port->dev, rocker_port->bridge_dev, + false); rocker_port->bridge_dev = NULL; err = rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE, @@ -5190,23 +5297,39 @@ static int rocker_port_bridge_leave(struct rocker_port *rocker_port) return err; } + +static int rocker_port_ovs_changed(struct rocker_port *rocker_port, + struct net_device *master) +{ + int err; + + rocker_port->bridge_dev = master; + + err = rocker_port_fwd_disable(rocker_port, SWITCHDEV_TRANS_NONE, 0); + if (err) + return err; + err = rocker_port_fwd_enable(rocker_port, SWITCHDEV_TRANS_NONE, 0); + + return err; +} + static int rocker_port_master_changed(struct net_device *dev) { struct rocker_port *rocker_port = netdev_priv(dev); struct net_device *master = netdev_master_upper_dev_get(dev); int err = 0; - /* There are currently three cases handled here: - * 1. Joining a bridge - * 2. Leaving a previously joined bridge - * 3. Other, e.g. being added to or removed from a bond or openvswitch, - * in which case nothing is done - */ - if (master && master->rtnl_link_ops && - !strcmp(master->rtnl_link_ops->kind, "bridge")) - err = rocker_port_bridge_join(rocker_port, master); - else if (rocker_port_is_bridged(rocker_port)) + /* N.B: Do nothing if the type of master is not supported */ + if (master && master->rtnl_link_ops) { + if (!strcmp(master->rtnl_link_ops->kind, "bridge")) + err = rocker_port_bridge_join(rocker_port, master); + else if (!strcmp(master->rtnl_link_ops->kind, "openvswitch")) + err = rocker_port_ovs_changed(rocker_port, master); + } else if (rocker_port_is_bridged(rocker_port)) { err = rocker_port_bridge_leave(rocker_port); + } else if (rocker_port_is_ovsed(rocker_port)) { + err = rocker_port_ovs_changed(rocker_port, NULL); + } return err; } diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h index c61fbf968036..12490b2f6504 100644 --- a/drivers/net/ethernet/rocker/rocker.h +++ b/drivers/net/ethernet/rocker/rocker.h @@ -159,6 +159,7 @@ enum { ROCKER_TLV_CMD_PORT_SETTINGS_MODE, /* u8 */ ROCKER_TLV_CMD_PORT_SETTINGS_LEARNING, /* u8 */ ROCKER_TLV_CMD_PORT_SETTINGS_PHYS_NAME, /* binary */ + ROCKER_TLV_CMD_PORT_SETTINGS_MTU, /* u16 */ __ROCKER_TLV_CMD_PORT_SETTINGS_MAX, ROCKER_TLV_CMD_PORT_SETTINGS_MAX = @@ -245,6 +246,7 @@ enum { #define ROCKER_RX_FLAGS_TCP BIT(5) #define ROCKER_RX_FLAGS_UDP BIT(6) #define ROCKER_RX_FLAGS_TCP_UDP_CSUM_GOOD BIT(7) +#define ROCKER_RX_FLAGS_FWD_OFFLOAD BIT(8) enum { ROCKER_TLV_TX_UNSPEC, diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 605cc8948594..8505d82290cb 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -49,6 +49,12 @@ enum { */ #define HUNT_FILTER_TBL_ROWS 8192 +#define EFX_EF10_FILTER_ID_INVALID 0xffff +struct efx_ef10_dev_addr { + u8 addr[ETH_ALEN]; + u16 id; +}; + struct efx_ef10_filter_table { /* The RX match field masks supported by this fw & hw, in order of priority */ enum efx_filter_match_flags rx_match_flags[ @@ -69,13 +75,14 @@ struct efx_ef10_filter_table { /* Shadow of net_device address lists, guarded by mac_lock */ #define EFX_EF10_FILTER_DEV_UC_MAX 32 #define EFX_EF10_FILTER_DEV_MC_MAX 256 - struct { - u8 addr[ETH_ALEN]; - u16 id; - } dev_uc_list[EFX_EF10_FILTER_DEV_UC_MAX], - dev_mc_list[EFX_EF10_FILTER_DEV_MC_MAX]; - int dev_uc_count; /* negative for PROMISC */ - int dev_mc_count; /* negative for PROMISC/ALLMULTI */ + struct efx_ef10_dev_addr dev_uc_list[EFX_EF10_FILTER_DEV_UC_MAX]; + struct efx_ef10_dev_addr dev_mc_list[EFX_EF10_FILTER_DEV_MC_MAX]; + int dev_uc_count; + int dev_mc_count; +/* Indices (like efx_ef10_dev_addr.id) for promisc/allmulti filters */ + u16 ucdef_id; + u16 bcast_id; + u16 mcdef_id; }; /* An arbitrary search limit for the software hash table */ @@ -387,7 +394,7 @@ static int efx_ef10_probe(struct efx_nic *efx) * First try to enable it, then if we get EPERM, just * ask if it's already enabled */ - rc = efx_mcdi_set_workaround(efx, MC_CMD_WORKAROUND_BUG35388, true); + rc = efx_mcdi_set_workaround(efx, MC_CMD_WORKAROUND_BUG35388, true, NULL); if (rc == 0) { nic_data->workaround_35388 = true; } else if (rc == -EPERM) { @@ -2197,6 +2204,29 @@ static int efx_ef10_ev_probe(struct efx_channel *channel) GFP_KERNEL); } +static void efx_ef10_ev_fini(struct efx_channel *channel) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_EVQ_IN_LEN); + MCDI_DECLARE_BUF_ERR(outbuf); + struct efx_nic *efx = channel->efx; + size_t outlen; + int rc; + + MCDI_SET_DWORD(inbuf, FINI_EVQ_IN_INSTANCE, channel->channel); + + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_EVQ, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + + if (rc && rc != -EALREADY) + goto fail; + + return; + +fail: + efx_mcdi_display_error(efx, MC_CMD_FINI_EVQ, MC_CMD_FINI_EVQ_IN_LEN, + outbuf, outlen, rc); +} + static int efx_ef10_ev_init(struct efx_channel *channel) { MCDI_DECLARE_BUF(inbuf, @@ -2208,6 +2238,7 @@ static int efx_ef10_ev_init(struct efx_channel *channel) struct efx_ef10_nic_data *nic_data; bool supports_rx_merge; size_t inlen, outlen; + unsigned int enabled, implemented; dma_addr_t dma_addr; int rc; int i; @@ -2248,30 +2279,52 @@ static int efx_ef10_ev_init(struct efx_channel *channel) rc = efx_mcdi_rpc(efx, MC_CMD_INIT_EVQ, inbuf, inlen, outbuf, sizeof(outbuf), &outlen); /* IRQ return is ignored */ - return rc; -} - -static void efx_ef10_ev_fini(struct efx_channel *channel) -{ - MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_EVQ_IN_LEN); - MCDI_DECLARE_BUF_ERR(outbuf); - struct efx_nic *efx = channel->efx; - size_t outlen; - int rc; - - MCDI_SET_DWORD(inbuf, FINI_EVQ_IN_INSTANCE, channel->channel); - - rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_EVQ, inbuf, sizeof(inbuf), - outbuf, sizeof(outbuf), &outlen); + if (channel->channel || rc) + return rc; - if (rc && rc != -EALREADY) + /* Successfully created event queue on channel 0 */ + rc = efx_mcdi_get_workarounds(efx, &implemented, &enabled); + if (rc == -ENOSYS) { + /* GET_WORKAROUNDS was implemented before the bug26807 + * workaround, thus the latter must be unavailable in this fw + */ + nic_data->workaround_26807 = false; + rc = 0; + } else if (rc) { goto fail; + } else { + nic_data->workaround_26807 = + !!(enabled & MC_CMD_GET_WORKAROUNDS_OUT_BUG26807); + + if (implemented & MC_CMD_GET_WORKAROUNDS_OUT_BUG26807 && + !nic_data->workaround_26807) { + unsigned int flags; + + rc = efx_mcdi_set_workaround(efx, + MC_CMD_WORKAROUND_BUG26807, + true, &flags); + + if (!rc) { + if (flags & + 1 << MC_CMD_WORKAROUND_EXT_OUT_FLR_DONE_LBN) { + netif_info(efx, drv, efx->net_dev, + "other functions on NIC have been reset\n"); + /* MC's boot count has incremented */ + ++nic_data->warm_boot_count; + } + nic_data->workaround_26807 = true; + } else if (rc == -EPERM) { + rc = 0; + } + } + } - return; + if (!rc) + return 0; fail: - efx_mcdi_display_error(efx, MC_CMD_FINI_EVQ, MC_CMD_FINI_EVQ_IN_LEN, - outbuf, outlen, rc); + efx_ef10_ev_fini(channel); + return rc; } static void efx_ef10_ev_remove(struct efx_channel *channel) @@ -3225,6 +3278,19 @@ static int efx_ef10_filter_remove_safe(struct efx_nic *efx, filter_id, false); } +static u32 efx_ef10_filter_get_unsafe_id(struct efx_nic *efx, u32 filter_id) +{ + return filter_id % HUNT_FILTER_TBL_ROWS; +} + +static int efx_ef10_filter_remove_unsafe(struct efx_nic *efx, + enum efx_filter_priority priority, + u32 filter_id) +{ + return efx_ef10_filter_remove_internal(efx, 1U << priority, + filter_id, true); +} + static int efx_ef10_filter_get_safe(struct efx_nic *efx, enum efx_filter_priority priority, u32 filter_id, struct efx_filter_spec *spec) @@ -3598,6 +3664,10 @@ static int efx_ef10_filter_table_probe(struct efx_nic *efx) goto fail; } + table->ucdef_id = EFX_EF10_FILTER_ID_INVALID; + table->bcast_id = EFX_EF10_FILTER_ID_INVALID; + table->mcdef_id = EFX_EF10_FILTER_ID_INVALID; + efx->filter_state = table; init_waitqueue_head(&table->waitq); return 0; @@ -3700,145 +3770,233 @@ static void efx_ef10_filter_table_remove(struct efx_nic *efx) kfree(table); } -/* Caller must hold efx->filter_sem for read if race against - * efx_ef10_filter_table_remove() is possible - */ -static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx) +#define EFX_EF10_FILTER_DO_MARK_OLD(id) \ + if (id != EFX_EF10_FILTER_ID_INVALID) { \ + filter_idx = efx_ef10_filter_get_unsafe_id(efx, id); \ + WARN_ON(!table->entry[filter_idx].spec); \ + table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD; \ + } +static void efx_ef10_filter_mark_old(struct efx_nic *efx) { struct efx_ef10_filter_table *table = efx->filter_state; - struct net_device *net_dev = efx->net_dev; - struct efx_filter_spec spec; - bool remove_failed = false; - struct netdev_hw_addr *uc; - struct netdev_hw_addr *mc; - unsigned int filter_idx; - int i, n, rc; - - if (!efx_dev_registered(efx)) - return; + unsigned int filter_idx, i; if (!table) return; /* Mark old filters that may need to be removed */ spin_lock_bh(&efx->filter_lock); - n = table->dev_uc_count < 0 ? 1 : table->dev_uc_count; - for (i = 0; i < n; i++) { - filter_idx = table->dev_uc_list[i].id % HUNT_FILTER_TBL_ROWS; - table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD; - } - n = table->dev_mc_count < 0 ? 1 : table->dev_mc_count; - for (i = 0; i < n; i++) { - filter_idx = table->dev_mc_list[i].id % HUNT_FILTER_TBL_ROWS; - table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD; - } + for (i = 0; i < table->dev_uc_count; i++) + EFX_EF10_FILTER_DO_MARK_OLD(table->dev_uc_list[i].id); + for (i = 0; i < table->dev_mc_count; i++) + EFX_EF10_FILTER_DO_MARK_OLD(table->dev_mc_list[i].id); + EFX_EF10_FILTER_DO_MARK_OLD(table->ucdef_id); + EFX_EF10_FILTER_DO_MARK_OLD(table->bcast_id); + EFX_EF10_FILTER_DO_MARK_OLD(table->mcdef_id); spin_unlock_bh(&efx->filter_lock); +} +#undef EFX_EF10_FILTER_DO_MARK_OLD - /* Copy/convert the address lists; add the primary station - * address and broadcast address - */ - netif_addr_lock_bh(net_dev); - if (net_dev->flags & IFF_PROMISC || - netdev_uc_count(net_dev) >= EFX_EF10_FILTER_DEV_UC_MAX) { - table->dev_uc_count = -1; - } else { - table->dev_uc_count = 1 + netdev_uc_count(net_dev); - ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr); - i = 1; - netdev_for_each_uc_addr(uc, net_dev) { - ether_addr_copy(table->dev_uc_list[i].addr, uc->addr); - i++; +static void efx_ef10_filter_uc_addr_list(struct efx_nic *efx, bool *promisc) +{ + struct efx_ef10_filter_table *table = efx->filter_state; + struct net_device *net_dev = efx->net_dev; + struct netdev_hw_addr *uc; + int addr_count; + unsigned int i; + + table->ucdef_id = EFX_EF10_FILTER_ID_INVALID; + addr_count = netdev_uc_count(net_dev); + if (net_dev->flags & IFF_PROMISC) + *promisc = true; + table->dev_uc_count = 1 + addr_count; + ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr); + i = 1; + netdev_for_each_uc_addr(uc, net_dev) { + if (i >= EFX_EF10_FILTER_DEV_UC_MAX) { + *promisc = true; + break; } + ether_addr_copy(table->dev_uc_list[i].addr, uc->addr); + table->dev_uc_list[i].id = EFX_EF10_FILTER_ID_INVALID; + i++; } - if (net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI) || - netdev_mc_count(net_dev) >= EFX_EF10_FILTER_DEV_MC_MAX) { - table->dev_mc_count = -1; - } else { - table->dev_mc_count = 1 + netdev_mc_count(net_dev); - eth_broadcast_addr(table->dev_mc_list[0].addr); - i = 1; - netdev_for_each_mc_addr(mc, net_dev) { - ether_addr_copy(table->dev_mc_list[i].addr, mc->addr); - i++; +} + +static void efx_ef10_filter_mc_addr_list(struct efx_nic *efx, bool *promisc) +{ + struct efx_ef10_filter_table *table = efx->filter_state; + struct net_device *net_dev = efx->net_dev; + struct netdev_hw_addr *mc; + unsigned int i, addr_count; + + table->mcdef_id = EFX_EF10_FILTER_ID_INVALID; + table->bcast_id = EFX_EF10_FILTER_ID_INVALID; + if (net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) + *promisc = true; + + addr_count = netdev_mc_count(net_dev); + i = 0; + netdev_for_each_mc_addr(mc, net_dev) { + if (i >= EFX_EF10_FILTER_DEV_MC_MAX) { + *promisc = true; + break; } + ether_addr_copy(table->dev_mc_list[i].addr, mc->addr); + table->dev_mc_list[i].id = EFX_EF10_FILTER_ID_INVALID; + i++; } - netif_addr_unlock_bh(net_dev); - /* Insert/renew unicast filters */ - if (table->dev_uc_count >= 0) { - for (i = 0; i < table->dev_uc_count; i++) { - efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, - EFX_FILTER_FLAG_RX_RSS, - 0); - efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, - table->dev_uc_list[i].addr); - rc = efx_ef10_filter_insert(efx, &spec, true); - if (rc < 0) { - /* Fall back to unicast-promisc */ - while (i--) - efx_ef10_filter_remove_safe( + table->dev_mc_count = i; +} + +static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx, + bool multicast, bool rollback) +{ + struct efx_ef10_filter_table *table = efx->filter_state; + struct efx_ef10_dev_addr *addr_list; + struct efx_filter_spec spec; + u8 baddr[ETH_ALEN]; + unsigned int i, j; + int addr_count; + int rc; + + if (multicast) { + addr_list = table->dev_mc_list; + addr_count = table->dev_mc_count; + } else { + addr_list = table->dev_uc_list; + addr_count = table->dev_uc_count; + } + + /* Insert/renew filters */ + for (i = 0; i < addr_count; i++) { + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, + EFX_FILTER_FLAG_RX_RSS, + 0); + efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, + addr_list[i].addr); + rc = efx_ef10_filter_insert(efx, &spec, true); + if (rc < 0) { + if (rollback) { + netif_info(efx, drv, efx->net_dev, + "efx_ef10_filter_insert failed rc=%d\n", + rc); + /* Fall back to promiscuous */ + for (j = 0; j < i; j++) { + if (addr_list[j].id == EFX_EF10_FILTER_ID_INVALID) + continue; + efx_ef10_filter_remove_unsafe( efx, EFX_FILTER_PRI_AUTO, - table->dev_uc_list[i].id); - table->dev_uc_count = -1; - break; + addr_list[j].id); + addr_list[j].id = EFX_EF10_FILTER_ID_INVALID; + } + return rc; + } else { + /* mark as not inserted, and carry on */ + rc = EFX_EF10_FILTER_ID_INVALID; } - table->dev_uc_list[i].id = rc; } + addr_list[i].id = efx_ef10_filter_get_unsafe_id(efx, rc); } - if (table->dev_uc_count < 0) { + + if (multicast && rollback) { + /* Also need an Ethernet broadcast filter */ efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, EFX_FILTER_FLAG_RX_RSS, 0); - efx_filter_set_uc_def(&spec); + eth_broadcast_addr(baddr); + efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, baddr); rc = efx_ef10_filter_insert(efx, &spec, true); if (rc < 0) { - WARN_ON(1); - table->dev_uc_count = 0; + netif_warn(efx, drv, efx->net_dev, + "Broadcast filter insert failed rc=%d\n", rc); + /* Fall back to promiscuous */ + for (j = 0; j < i; j++) { + if (addr_list[j].id == EFX_EF10_FILTER_ID_INVALID) + continue; + efx_ef10_filter_remove_unsafe( + efx, EFX_FILTER_PRI_AUTO, + addr_list[j].id); + addr_list[j].id = EFX_EF10_FILTER_ID_INVALID; + } + return rc; } else { - table->dev_uc_list[0].id = rc; + table->bcast_id = efx_ef10_filter_get_unsafe_id(efx, rc); } } - /* Insert/renew multicast filters */ - if (table->dev_mc_count >= 0) { - for (i = 0; i < table->dev_mc_count; i++) { + return 0; +} + +static int efx_ef10_filter_insert_def(struct efx_nic *efx, bool multicast, + bool rollback) +{ + struct efx_ef10_filter_table *table = efx->filter_state; + struct efx_ef10_nic_data *nic_data = efx->nic_data; + struct efx_filter_spec spec; + u8 baddr[ETH_ALEN]; + int rc; + + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, + EFX_FILTER_FLAG_RX_RSS, + 0); + + if (multicast) + efx_filter_set_mc_def(&spec); + else + efx_filter_set_uc_def(&spec); + + rc = efx_ef10_filter_insert(efx, &spec, true); + if (rc < 0) { + netif_warn(efx, drv, efx->net_dev, + "%scast mismatch filter insert failed rc=%d\n", + multicast ? "Multi" : "Uni", rc); + } else if (multicast) { + table->mcdef_id = efx_ef10_filter_get_unsafe_id(efx, rc); + if (!nic_data->workaround_26807) { + /* Also need an Ethernet broadcast filter */ efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, EFX_FILTER_FLAG_RX_RSS, 0); + eth_broadcast_addr(baddr); efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, - table->dev_mc_list[i].addr); + baddr); rc = efx_ef10_filter_insert(efx, &spec, true); if (rc < 0) { - /* Fall back to multicast-promisc */ - while (i--) - efx_ef10_filter_remove_safe( - efx, EFX_FILTER_PRI_AUTO, - table->dev_mc_list[i].id); - table->dev_mc_count = -1; - break; + netif_warn(efx, drv, efx->net_dev, + "Broadcast filter insert failed rc=%d\n", + rc); + if (rollback) { + /* Roll back the mc_def filter */ + efx_ef10_filter_remove_unsafe( + efx, EFX_FILTER_PRI_AUTO, + table->mcdef_id); + table->mcdef_id = EFX_EF10_FILTER_ID_INVALID; + return rc; + } + } else { + table->bcast_id = efx_ef10_filter_get_unsafe_id(efx, rc); } - table->dev_mc_list[i].id = rc; - } - } - if (table->dev_mc_count < 0) { - efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, - EFX_FILTER_FLAG_RX_RSS, - 0); - efx_filter_set_mc_def(&spec); - rc = efx_ef10_filter_insert(efx, &spec, true); - if (rc < 0) { - WARN_ON(1); - table->dev_mc_count = 0; - } else { - table->dev_mc_list[0].id = rc; } + rc = 0; + } else { + table->ucdef_id = rc; + rc = 0; } + return rc; +} + +/* Remove filters that weren't renewed. Since nothing else changes the AUTO_OLD + * flag or removes these filters, we don't need to hold the filter_lock while + * scanning for these filters. + */ +static void efx_ef10_filter_remove_old(struct efx_nic *efx) +{ + struct efx_ef10_filter_table *table = efx->filter_state; + bool remove_failed = false; + int i; - /* Remove filters that weren't renewed. Since nothing else - * changes the AUTO_OLD flag or removes these filters, we - * don't need to hold the filter_lock while scanning for - * these filters. - */ for (i = 0; i < HUNT_FILTER_TBL_ROWS; i++) { if (ACCESS_ONCE(table->entry[i].spec) & EFX_EF10_FILTER_FLAG_AUTO_OLD) { @@ -3917,6 +4075,87 @@ reset_nic: return rc ? rc : rc2; } +/* Caller must hold efx->filter_sem for read if race against + * efx_ef10_filter_table_remove() is possible + */ +static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx) +{ + struct efx_ef10_filter_table *table = efx->filter_state; + struct efx_ef10_nic_data *nic_data = efx->nic_data; + struct net_device *net_dev = efx->net_dev; + bool uc_promisc = false, mc_promisc = false; + + if (!efx_dev_registered(efx)) + return; + + if (!table) + return; + + efx_ef10_filter_mark_old(efx); + + /* Copy/convert the address lists; add the primary station + * address and broadcast address + */ + netif_addr_lock_bh(net_dev); + efx_ef10_filter_uc_addr_list(efx, &uc_promisc); + efx_ef10_filter_mc_addr_list(efx, &mc_promisc); + netif_addr_unlock_bh(net_dev); + + /* Insert/renew unicast filters */ + if (uc_promisc) { + efx_ef10_filter_insert_def(efx, false, false); + efx_ef10_filter_insert_addr_list(efx, false, false); + } else { + /* If any of the filters failed to insert, fall back to + * promiscuous mode - add in the uc_def filter. But keep + * our individual unicast filters. + */ + if (efx_ef10_filter_insert_addr_list(efx, false, false)) + efx_ef10_filter_insert_def(efx, false, false); + } + + /* Insert/renew multicast filters */ + /* If changing promiscuous state with cascaded multicast filters, remove + * old filters first, so that packets are dropped rather than duplicated + */ + if (nic_data->workaround_26807 && efx->mc_promisc != mc_promisc) + efx_ef10_filter_remove_old(efx); + if (mc_promisc) { + if (nic_data->workaround_26807) { + /* If we failed to insert promiscuous filters, rollback + * and fall back to individual multicast filters + */ + if (efx_ef10_filter_insert_def(efx, true, true)) { + /* Changing promisc state, so remove old filters */ + efx_ef10_filter_remove_old(efx); + efx_ef10_filter_insert_addr_list(efx, true, false); + } + } else { + /* If we failed to insert promiscuous filters, don't + * rollback. Regardless, also insert the mc_list + */ + efx_ef10_filter_insert_def(efx, true, false); + efx_ef10_filter_insert_addr_list(efx, true, false); + } + } else { + /* If any filters failed to insert, rollback and fall back to + * promiscuous mode - mc_def filter and maybe broadcast. If + * that fails, roll back again and insert as many of our + * individual multicast filters as we can. + */ + if (efx_ef10_filter_insert_addr_list(efx, true, true)) { + /* Changing promisc state, so remove old filters */ + if (nic_data->workaround_26807) + efx_ef10_filter_remove_old(efx); + if (efx_ef10_filter_insert_def(efx, true, true)) + efx_ef10_filter_insert_addr_list(efx, true, false); + } + } + + efx_ef10_filter_remove_old(efx); + efx->mc_promisc = mc_promisc; +} + static int efx_ef10_set_mac_address(struct efx_nic *efx) { MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_SET_MAC_IN_LEN); diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 81640f8bb811..98d172b04f71 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -1779,15 +1779,31 @@ int efx_mcdi_wol_filter_reset(struct efx_nic *efx) return rc; } -int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled) +int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled, + unsigned int *flags) { MCDI_DECLARE_BUF(inbuf, MC_CMD_WORKAROUND_IN_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_WORKAROUND_EXT_OUT_LEN); + size_t outlen; + int rc; BUILD_BUG_ON(MC_CMD_WORKAROUND_OUT_LEN != 0); MCDI_SET_DWORD(inbuf, WORKAROUND_IN_TYPE, type); MCDI_SET_DWORD(inbuf, WORKAROUND_IN_ENABLED, enabled); - return efx_mcdi_rpc(efx, MC_CMD_WORKAROUND, inbuf, sizeof(inbuf), - NULL, 0, NULL); + rc = efx_mcdi_rpc(efx, MC_CMD_WORKAROUND, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (rc) + return rc; + + if (!flags) + return 0; + + if (outlen >= MC_CMD_WORKAROUND_EXT_OUT_LEN) + *flags = MCDI_DWORD(outbuf, WORKAROUND_EXT_OUT_FLAGS); + else + *flags = 0; + + return 0; } int efx_mcdi_get_workarounds(struct efx_nic *efx, unsigned int *impl_out, @@ -1816,7 +1832,11 @@ int efx_mcdi_get_workarounds(struct efx_nic *efx, unsigned int *impl_out, return 0; fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); + /* Older firmware lacks GET_WORKAROUNDS and this isn't especially + * terrifying. The call site will have to deal with it though. + */ + netif_printk(efx, hw, rc == -ENOSYS ? KERN_DEBUG : KERN_ERR, + efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index 1838afe2da92..025d504c472b 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -346,7 +346,8 @@ void efx_mcdi_mac_pull_stats(struct efx_nic *efx); bool efx_mcdi_mac_check_fault(struct efx_nic *efx); enum reset_type efx_mcdi_map_reset_reason(enum reset_type reason); int efx_mcdi_reset(struct efx_nic *efx, enum reset_type method); -int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled); +int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled, + unsigned int *flags); int efx_mcdi_get_workarounds(struct efx_nic *efx, unsigned int *impl_out, unsigned int *enabled_out); diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h index 45fca9fc66b7..4cc772164a79 100644 --- a/drivers/net/ethernet/sfc/mcdi_pcol.h +++ b/drivers/net/ethernet/sfc/mcdi_pcol.h @@ -26,6 +26,10 @@ * Unlike a warm boot, assume DMEM has been reloaded, so that * the MC persistent data must be reinitialised. */ #define MC_FW_TEPID_BOOT_OK (16) +/* We have entered the main firmware via recovery mode. This + * means that MC persistent data must be reinitialised, but that + * we shouldn't touch PCIe config. */ +#define MC_FW_RECOVERY_MODE_PCIE_INIT_OK (32) /* BIST state has been initialized */ #define MC_FW_BIST_INIT_OK (128) @@ -169,6 +173,8 @@ #define MC_CMD_ERR_EINTR 4 /* I/O failure */ #define MC_CMD_ERR_EIO 5 +/* Already exists */ +#define MC_CMD_ERR_EEXIST 6 /* Try again */ #define MC_CMD_ERR_EAGAIN 11 /* Out of memory */ @@ -181,6 +187,10 @@ #define MC_CMD_ERR_ENODEV 19 /* Invalid argument to target */ #define MC_CMD_ERR_EINVAL 22 +/* Broken pipe */ +#define MC_CMD_ERR_EPIPE 32 +/* Read-only */ +#define MC_CMD_ERR_EROFS 30 /* Out of range */ #define MC_CMD_ERR_ERANGE 34 /* Non-recursive resource is already acquired */ @@ -226,6 +236,43 @@ #define MC_CMD_ERR_SLAVE_NOT_PRESENT 0x100a /* The datapath is disabled. */ #define MC_CMD_ERR_DATAPATH_DISABLED 0x100b +/* The requesting client is not a function */ +#define MC_CMD_ERR_CLIENT_NOT_FN 0x100c +/* The requested operation might require the + command to be passed between MCs, and the + transport doesn't support that. Should + only ever been seen over the UART. */ +#define MC_CMD_ERR_TRANSPORT_NOPROXY 0x100d +/* VLAN tag(s) exists */ +#define MC_CMD_ERR_VLAN_EXIST 0x100e +/* No MAC address assigned to an EVB port */ +#define MC_CMD_ERR_NO_MAC_ADDR 0x100f +/* Notifies the driver that the request has been relayed + * to an admin function for authorization. The driver should + * wait for a PROXY_RESPONSE event and then resend its request. + * This error code is followed by a 32-bit handle that + * helps matching it with the respective PROXY_RESPONSE event. */ +#define MC_CMD_ERR_PROXY_PENDING 0x1010 +#define MC_CMD_ERR_PROXY_PENDING_HANDLE_OFST 4 +/* The request cannot be passed for authorization because + * another request from the same function is currently being + * authorized. The drvier should try again later. */ +#define MC_CMD_ERR_PROXY_INPROGRESS 0x1011 +/* Returned by MC_CMD_PROXY_COMPLETE if the caller is not the function + * that has enabled proxying or BLOCK_INDEX points to a function that + * doesn't await an authorization. */ +#define MC_CMD_ERR_PROXY_UNEXPECTED 0x1012 +/* This code is currently only used internally in FW. Its meaning is that + * an operation failed due to lack of SR-IOV privilege. + * Normally it is translated to EPERM by send_cmd_err(), + * but it may also be used to trigger some special mechanism + * for handling such case, e.g. to relay the failed request + * to a designated admin function for authorization. */ +#define MC_CMD_ERR_NO_PRIVILEGE 0x1013 +/* Workaround 26807 could not be turned on/off because some functions + * have already installed filters. See the comment at + * MC_CMD_WORKAROUND_BUG26807. */ +#define MC_CMD_ERR_FILTERS_PRESENT 0x1014 #define MC_CMD_ERR_CODE_OFST 0 @@ -275,6 +322,11 @@ MC_CMD_DBIWROP_TYPEDEF_VALUE_OFST + \ (n) * MC_CMD_DBIWROP_TYPEDEF_LEN) +/* This may be ORed with an EVB_PORT_ID_xxx constant to pass a non-default + * stack ID (which must be in the range 1-255) along with an EVB port ID. + */ +#define EVB_STACK_ID(n) (((n) & 0xff) << 16) + /* Version 2 adds an optional argument to error returns: the errno value * may be followed by the (0-based) number of the first argument that @@ -394,6 +446,8 @@ #define MCDI_EVENT_AOE_BYTEBLASTER 0x9 /* enum: DDR ECC status update */ #define MCDI_EVENT_AOE_DDR_ECC_STATUS 0xa +/* enum: PTP status update */ +#define MCDI_EVENT_AOE_PTP_STATUS 0xb #define MCDI_EVENT_AOE_ERR_DATA_LBN 8 #define MCDI_EVENT_AOE_ERR_DATA_WIDTH 8 #define MCDI_EVENT_RX_ERR_RXQ_LBN 0 @@ -408,6 +462,16 @@ #define MCDI_EVENT_RX_FLUSH_RXQ_WIDTH 12 #define MCDI_EVENT_MC_REBOOT_COUNT_LBN 0 #define MCDI_EVENT_MC_REBOOT_COUNT_WIDTH 16 +#define MCDI_EVENT_MUM_ERR_TYPE_LBN 0 +#define MCDI_EVENT_MUM_ERR_TYPE_WIDTH 8 +/* enum: MUM failed to load - no valid image? */ +#define MCDI_EVENT_MUM_NO_LOAD 0x1 +/* enum: MUM f/w reported an exception */ +#define MCDI_EVENT_MUM_ASSERT 0x2 +/* enum: MUM not kicking watchdog */ +#define MCDI_EVENT_MUM_WATCHDOG 0x3 +#define MCDI_EVENT_MUM_ERR_DATA_LBN 8 +#define MCDI_EVENT_MUM_ERR_DATA_WIDTH 8 #define MCDI_EVENT_DATA_LBN 0 #define MCDI_EVENT_DATA_WIDTH 32 #define MCDI_EVENT_SRC_LBN 36 @@ -416,6 +480,8 @@ #define MCDI_EVENT_EV_CODE_WIDTH 4 #define MCDI_EVENT_CODE_LBN 44 #define MCDI_EVENT_CODE_WIDTH 8 +/* enum: Event generated by host software */ +#define MCDI_EVENT_SW_EVENT 0x0 /* enum: Bad assert. */ #define MCDI_EVENT_CODE_BADSSERT 0x1 /* enum: PM Notice. */ @@ -470,6 +536,14 @@ #define MCDI_EVENT_CODE_MC_BIST 0x19 /* enum: PTP tick event providing current NIC time */ #define MCDI_EVENT_CODE_PTP_TIME 0x1a +/* enum: MUM fault */ +#define MCDI_EVENT_CODE_MUM 0x1b +/* enum: notify the designated PF of a new authorization request */ +#define MCDI_EVENT_CODE_PROXY_REQUEST 0x1c +/* enum: notify a function that awaits an authorization that its request has + * been processed and it may now resend the command + */ +#define MCDI_EVENT_CODE_PROXY_RESPONSE 0x1d /* enum: Artificial event generated by host and posted via MC for test * purposes. */ @@ -537,6 +611,33 @@ /* For CODE_PTP_TIME events, bits 19-26 of the minor value of the PTP clock */ #define MCDI_EVENT_PTP_TIME_MINOR_26_19_LBN 36 #define MCDI_EVENT_PTP_TIME_MINOR_26_19_WIDTH 8 +/* For CODE_PTP_TIME events where report sync status is enabled, indicates + * whether the NIC clock has ever been set + */ +#define MCDI_EVENT_PTP_TIME_NIC_CLOCK_VALID_LBN 36 +#define MCDI_EVENT_PTP_TIME_NIC_CLOCK_VALID_WIDTH 1 +/* For CODE_PTP_TIME events where report sync status is enabled, indicates + * whether the NIC and System clocks are in sync + */ +#define MCDI_EVENT_PTP_TIME_HOST_NIC_IN_SYNC_LBN 37 +#define MCDI_EVENT_PTP_TIME_HOST_NIC_IN_SYNC_WIDTH 1 +/* For CODE_PTP_TIME events where report sync status is enabled, bits 21-26 of + * the minor value of the PTP clock + */ +#define MCDI_EVENT_PTP_TIME_MINOR_26_21_LBN 38 +#define MCDI_EVENT_PTP_TIME_MINOR_26_21_WIDTH 6 +#define MCDI_EVENT_PROXY_REQUEST_BUFF_INDEX_OFST 0 +#define MCDI_EVENT_PROXY_REQUEST_BUFF_INDEX_LBN 0 +#define MCDI_EVENT_PROXY_REQUEST_BUFF_INDEX_WIDTH 32 +#define MCDI_EVENT_PROXY_RESPONSE_HANDLE_OFST 0 +#define MCDI_EVENT_PROXY_RESPONSE_HANDLE_LBN 0 +#define MCDI_EVENT_PROXY_RESPONSE_HANDLE_WIDTH 32 +/* Zero means that the request has been completed or authorized, and the driver + * should resend it. A non-zero value means that the authorization has been + * denied, and gives the reason. Typically it will be EPERM. + */ +#define MCDI_EVENT_PROXY_RESPONSE_RC_LBN 36 +#define MCDI_EVENT_PROXY_RESPONSE_RC_WIDTH 8 /* FCDI_EVENT structuredef */ #define FCDI_EVENT_LEN 8 @@ -581,6 +682,10 @@ #define FCDI_EVENT_CODE_PTP_TICK 0x7 /* enum: ECC error counters */ #define FCDI_EVENT_CODE_DDR_ECC_STATUS 0x8 +/* enum: Current status of PTP */ +#define FCDI_EVENT_CODE_PTP_STATUS 0x9 +/* enum: Port id config to map MC-FC port idx */ +#define FCDI_EVENT_CODE_PORT_CONFIG 0xa #define FCDI_EVENT_ASSERT_INSTR_ADDRESS_OFST 0 #define FCDI_EVENT_ASSERT_INSTR_ADDRESS_LBN 0 #define FCDI_EVENT_ASSERT_INSTR_ADDRESS_WIDTH 32 @@ -594,11 +699,24 @@ #define FCDI_EVENT_LINK_STATE_DATA_OFST 0 #define FCDI_EVENT_LINK_STATE_DATA_LBN 0 #define FCDI_EVENT_LINK_STATE_DATA_WIDTH 32 +#define FCDI_EVENT_PTP_STATE_OFST 0 +#define FCDI_EVENT_PTP_UNDEFINED 0x0 /* enum */ +#define FCDI_EVENT_PTP_SETUP_FAILED 0x1 /* enum */ +#define FCDI_EVENT_PTP_OPERATIONAL 0x2 /* enum */ +#define FCDI_EVENT_PTP_STATE_LBN 0 +#define FCDI_EVENT_PTP_STATE_WIDTH 32 #define FCDI_EVENT_DDR_ECC_STATUS_BANK_ID_LBN 36 #define FCDI_EVENT_DDR_ECC_STATUS_BANK_ID_WIDTH 8 #define FCDI_EVENT_DDR_ECC_STATUS_STATUS_OFST 0 #define FCDI_EVENT_DDR_ECC_STATUS_STATUS_LBN 0 #define FCDI_EVENT_DDR_ECC_STATUS_STATUS_WIDTH 32 +/* Index of MC port being referred to */ +#define FCDI_EVENT_PORT_CONFIG_SRC_LBN 36 +#define FCDI_EVENT_PORT_CONFIG_SRC_WIDTH 8 +/* FC Port index that matches the MC port index in SRC */ +#define FCDI_EVENT_PORT_CONFIG_DATA_OFST 0 +#define FCDI_EVENT_PORT_CONFIG_DATA_LBN 0 +#define FCDI_EVENT_PORT_CONFIG_DATA_WIDTH 32 /* FCDI_EXTENDED_EVENT_PPS structuredef: Extended FCDI event to send PPS events * to the MC. Note that this structure | is overlayed over a normal FCDI event @@ -631,6 +749,90 @@ #define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LBN 64 #define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_WIDTH 64 +/* MUM_EVENT structuredef */ +#define MUM_EVENT_LEN 8 +#define MUM_EVENT_CONT_LBN 32 +#define MUM_EVENT_CONT_WIDTH 1 +#define MUM_EVENT_LEVEL_LBN 33 +#define MUM_EVENT_LEVEL_WIDTH 3 +/* enum: Info. */ +#define MUM_EVENT_LEVEL_INFO 0x0 +/* enum: Warning. */ +#define MUM_EVENT_LEVEL_WARN 0x1 +/* enum: Error. */ +#define MUM_EVENT_LEVEL_ERR 0x2 +/* enum: Fatal. */ +#define MUM_EVENT_LEVEL_FATAL 0x3 +#define MUM_EVENT_DATA_OFST 0 +#define MUM_EVENT_SENSOR_ID_LBN 0 +#define MUM_EVENT_SENSOR_ID_WIDTH 8 +/* Enum values, see field(s): */ +/* MC_CMD_SENSOR_INFO/MC_CMD_SENSOR_INFO_OUT/MASK */ +#define MUM_EVENT_SENSOR_STATE_LBN 8 +#define MUM_EVENT_SENSOR_STATE_WIDTH 8 +#define MUM_EVENT_PORT_PHY_READY_LBN 0 +#define MUM_EVENT_PORT_PHY_READY_WIDTH 1 +#define MUM_EVENT_PORT_PHY_LINK_UP_LBN 1 +#define MUM_EVENT_PORT_PHY_LINK_UP_WIDTH 1 +#define MUM_EVENT_PORT_PHY_TX_LOL_LBN 2 +#define MUM_EVENT_PORT_PHY_TX_LOL_WIDTH 1 +#define MUM_EVENT_PORT_PHY_RX_LOL_LBN 3 +#define MUM_EVENT_PORT_PHY_RX_LOL_WIDTH 1 +#define MUM_EVENT_PORT_PHY_TX_LOS_LBN 4 +#define MUM_EVENT_PORT_PHY_TX_LOS_WIDTH 1 +#define MUM_EVENT_PORT_PHY_RX_LOS_LBN 5 +#define MUM_EVENT_PORT_PHY_RX_LOS_WIDTH 1 +#define MUM_EVENT_PORT_PHY_TX_FAULT_LBN 6 +#define MUM_EVENT_PORT_PHY_TX_FAULT_WIDTH 1 +#define MUM_EVENT_DATA_LBN 0 +#define MUM_EVENT_DATA_WIDTH 32 +#define MUM_EVENT_SRC_LBN 36 +#define MUM_EVENT_SRC_WIDTH 8 +#define MUM_EVENT_EV_CODE_LBN 60 +#define MUM_EVENT_EV_CODE_WIDTH 4 +#define MUM_EVENT_CODE_LBN 44 +#define MUM_EVENT_CODE_WIDTH 8 +/* enum: The MUM was rebooted. */ +#define MUM_EVENT_CODE_REBOOT 0x1 +/* enum: Bad assert. */ +#define MUM_EVENT_CODE_ASSERT 0x2 +/* enum: Sensor failure. */ +#define MUM_EVENT_CODE_SENSOR 0x3 +/* enum: Link fault has been asserted, or has cleared. */ +#define MUM_EVENT_CODE_QSFP_LASI_INTERRUPT 0x4 +#define MUM_EVENT_SENSOR_DATA_OFST 0 +#define MUM_EVENT_SENSOR_DATA_LBN 0 +#define MUM_EVENT_SENSOR_DATA_WIDTH 32 +#define MUM_EVENT_PORT_PHY_FLAGS_OFST 0 +#define MUM_EVENT_PORT_PHY_FLAGS_LBN 0 +#define MUM_EVENT_PORT_PHY_FLAGS_WIDTH 32 +#define MUM_EVENT_PORT_PHY_COPPER_LEN_OFST 0 +#define MUM_EVENT_PORT_PHY_COPPER_LEN_LBN 0 +#define MUM_EVENT_PORT_PHY_COPPER_LEN_WIDTH 32 +#define MUM_EVENT_PORT_PHY_CAPS_OFST 0 +#define MUM_EVENT_PORT_PHY_CAPS_LBN 0 +#define MUM_EVENT_PORT_PHY_CAPS_WIDTH 32 +#define MUM_EVENT_PORT_PHY_TECH_OFST 0 +#define MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_UNKNOWN 0x0 /* enum */ +#define MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_OPTICAL 0x1 /* enum */ +#define MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_PASSIVE 0x2 /* enum */ +#define MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_PASSIVE_EQUALIZED 0x3 /* enum */ +#define MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_ACTIVE_LIMITING 0x4 /* enum */ +#define MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_ACTIVE_LINEAR 0x5 /* enum */ +#define MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_BASE_T 0x6 /* enum */ +#define MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_LOOPBACK_PASSIVE 0x7 /* enum */ +#define MUM_EVENT_PORT_PHY_TECH_LBN 0 +#define MUM_EVENT_PORT_PHY_TECH_WIDTH 32 +#define MUM_EVENT_PORT_PHY_SRC_DATA_ID_LBN 36 +#define MUM_EVENT_PORT_PHY_SRC_DATA_ID_WIDTH 4 +#define MUM_EVENT_PORT_PHY_SRC_DATA_ID_FLAGS 0x0 /* enum */ +#define MUM_EVENT_PORT_PHY_SRC_DATA_ID_COPPER_LEN 0x1 /* enum */ +#define MUM_EVENT_PORT_PHY_SRC_DATA_ID_CAPS 0x2 /* enum */ +#define MUM_EVENT_PORT_PHY_SRC_DATA_ID_TECH 0x3 /* enum */ +#define MUM_EVENT_PORT_PHY_SRC_DATA_ID_MAX 0x4 /* enum */ +#define MUM_EVENT_PORT_PHY_SRC_PORT_NO_LBN 40 +#define MUM_EVENT_PORT_PHY_SRC_PORT_NO_WIDTH 4 + /***********************************/ /* MC_CMD_READ32 @@ -687,24 +889,34 @@ /* MC_CMD_COPYCODE_IN msgrequest */ #define MC_CMD_COPYCODE_IN_LEN 16 -/* Source address */ -#define MC_CMD_COPYCODE_IN_SRC_ADDR_OFST 0 -/* enum: The main image should be entered via a copy of a single word from and - * to this address when none of the other magic behaviours are required. +/* Source address + * + * The main image should be entered via a copy of a single word from and to a + * magic address, which controls various aspects of the boot. The magic address + * is a bitfield, with each bit as documented below. */ +#define MC_CMD_COPYCODE_IN_SRC_ADDR_OFST 0 +/* enum: Deprecated; equivalent to setting BOOT_MAGIC_PRESENT (see below) */ #define MC_CMD_COPYCODE_HUNT_NO_MAGIC_ADDR 0x10000 -/* enum: Entering the main image via a copy of a single word from and to this - * address indicates that it should not attempt to start the datapath CPUs. - * This is useful for certain soft rebooting scenarios. (Huntington only) +/* enum: Deprecated; equivalent to setting BOOT_MAGIC_PRESENT and + * BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED (see below) */ #define MC_CMD_COPYCODE_HUNT_NO_DATAPATH_MAGIC_ADDR 0x1d0d0 -/* enum: Entering the main image via a copy of a single word from and to this - * address indicates that it should not attempt to parse any configuration from - * flash. (In addition, the datapath CPUs will not be started, as for - * MC_CMD_COPYCODE_HUNT_NO_DATAPATH_MAGIC_ADDR above.) This is useful for - * certain soft rebooting scenarios. (Huntington only) +/* enum: Deprecated; equivalent to setting BOOT_MAGIC_PRESENT, + * BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED and BOOT_MAGIC_IGNORE_CONFIG (see + * below) */ #define MC_CMD_COPYCODE_HUNT_IGNORE_CONFIG_MAGIC_ADDR 0x1badc +#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_PRESENT_LBN 17 +#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_PRESENT_WIDTH 1 +#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED_LBN 2 +#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED_WIDTH 1 +#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_IGNORE_CONFIG_LBN 3 +#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_IGNORE_CONFIG_WIDTH 1 +#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_SKIP_BOOT_ICORE_SYNC_LBN 4 +#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_SKIP_BOOT_ICORE_SYNC_WIDTH 1 +#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_FORCE_STANDALONE_LBN 5 +#define MC_CMD_COPYCODE_IN_BOOT_MAGIC_FORCE_STANDALONE_WIDTH 1 /* Destination address */ #define MC_CMD_COPYCODE_IN_DEST_ADDR_OFST 4 #define MC_CMD_COPYCODE_IN_NUMWORDS_OFST 8 @@ -795,6 +1007,10 @@ #define MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_OFST 8 #define MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_LEN 4 #define MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_NUM 31 +/* enum: A magic value hinting that the value in this register at the time of + * the failure has likely been lost. + */ +#define MC_CMD_GET_ASSERTS_REG_NO_DATA 0xda7a1057 /* Failing thread address */ #define MC_CMD_GET_ASSERTS_OUT_THREAD_OFFS_OFST 132 #define MC_CMD_GET_ASSERTS_OUT_RESERVED_OFST 136 @@ -802,7 +1018,8 @@ /***********************************/ /* MC_CMD_LOG_CTRL - * Configure the output stream for various events and messages. + * Configure the output stream for log events such as link state changes, + * sensor notifications and MCDI completions */ #define MC_CMD_LOG_CTRL 0x7 @@ -816,6 +1033,7 @@ #define MC_CMD_LOG_CTRL_IN_LOG_DEST_UART 0x1 /* enum: Event queue. */ #define MC_CMD_LOG_CTRL_IN_LOG_DEST_EVQ 0x2 +/* Legacy argument. Must be zero. */ #define MC_CMD_LOG_CTRL_IN_LOG_DEST_EVQ_OFST 4 /* MC_CMD_LOG_CTRL_OUT msgresponse */ @@ -955,8 +1173,12 @@ * input on the same NIC. */ #define MC_CMD_PTP_OP_MANFTEST_PPS 0x1a +/* enum: Set the PTP sync status. Status is used by firmware to report to event + * subscribers. + */ +#define MC_CMD_PTP_OP_SET_SYNC_STATUS 0x1b /* enum: Above this for future use. */ -#define MC_CMD_PTP_OP_MAX 0x1b +#define MC_CMD_PTP_OP_MAX 0x1c /* MC_CMD_PTP_IN_ENABLE msgrequest */ #define MC_CMD_PTP_IN_ENABLE_LEN 16 @@ -1191,8 +1413,12 @@ #define MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_LEN 12 /* MC_CMD_PTP_IN_CMD_OFST 0 */ /* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */ -/* Event queue to send PTP time events to */ +/* Original field containing queue ID. Now extended to include flags. */ #define MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_QUEUE_OFST 8 +#define MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_QUEUE_ID_LBN 0 +#define MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_QUEUE_ID_WIDTH 16 +#define MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_REPORT_SYNC_STATUS_LBN 31 +#define MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_REPORT_SYNC_STATUS_WIDTH 1 /* MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE msgrequest */ #define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_LEN 16 @@ -1214,6 +1440,23 @@ /* 1 to enable PPS test mode, 0 to disable and return result. */ #define MC_CMD_PTP_IN_MANFTEST_PPS_TEST_ENABLE_OFST 8 +/* MC_CMD_PTP_IN_SET_SYNC_STATUS msgrequest */ +#define MC_CMD_PTP_IN_SET_SYNC_STATUS_LEN 24 +/* MC_CMD_PTP_IN_CMD_OFST 0 */ +/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */ +/* NIC - Host System Clock Synchronization status */ +#define MC_CMD_PTP_IN_SET_SYNC_STATUS_STATUS_OFST 8 +/* enum: Host System clock and NIC clock are not in sync */ +#define MC_CMD_PTP_IN_SET_SYNC_STATUS_NOT_IN_SYNC 0x0 +/* enum: Host System clock and NIC clock are synchronized */ +#define MC_CMD_PTP_IN_SET_SYNC_STATUS_IN_SYNC 0x1 +/* If synchronized, number of seconds until clocks should be considered to be + * no longer in sync. + */ +#define MC_CMD_PTP_IN_SET_SYNC_STATUS_TIMEOUT_OFST 12 +#define MC_CMD_PTP_IN_SET_SYNC_STATUS_RESERVED0_OFST 16 +#define MC_CMD_PTP_IN_SET_SYNC_STATUS_RESERVED1_OFST 20 + /* MC_CMD_PTP_OUT msgresponse */ #define MC_CMD_PTP_OUT_LEN 0 @@ -1375,7 +1618,7 @@ #define MC_CMD_PTP_OUT_GET_TIME_FORMAT_SECONDS_27FRACTION 0x2 /* MC_CMD_PTP_OUT_GET_ATTRIBUTES msgresponse */ -#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_LEN 8 +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_LEN 24 /* Time format required/used by for this NIC. Applies to all PTP MCDI * operations that pass times between the host and firmware. If this operation * is not supported (older firmware) a format of seconds and nanoseconds should @@ -1396,6 +1639,13 @@ * end and start times minus the time that the MC waited for host end. */ #define MC_CMD_PTP_OUT_GET_ATTRIBUTES_SYNC_WINDOW_MIN_OFST 4 +/* Various PTP capabilities */ +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_CAPABILITIES_OFST 8 +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_REPORT_SYNC_STATUS_LBN 0 +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_REPORT_SYNC_STATUS_WIDTH 1 +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_RESERVED0_OFST 12 +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_RESERVED1_OFST 16 +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_RESERVED2_OFST 20 /* MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS msgresponse */ #define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_LEN 16 @@ -1415,6 +1665,9 @@ /* Enum values, see field(s): */ /* MC_CMD_PTP_OUT_MANFTEST_BASIC/TEST_RESULT */ +/* MC_CMD_PTP_OUT_SET_SYNC_STATUS msgresponse */ +#define MC_CMD_PTP_OUT_SET_SYNC_STATUS_LEN 0 + /***********************************/ /* MC_CMD_CSR_READ32 @@ -1915,6 +2168,14 @@ #define MC_CMD_FW_FULL_FEATURED 0x0 /* enum: Prefer to use firmware with fewer features but lower latency */ #define MC_CMD_FW_LOW_LATENCY 0x1 +/* enum: Prefer to use firmware for SolarCapture packed stream mode */ +#define MC_CMD_FW_PACKED_STREAM 0x2 +/* enum: Prefer to use firmware with fewer features and simpler TX event + * batching but higher TX packet rate + */ +#define MC_CMD_FW_HIGH_TX_RATE 0x3 +/* enum: Reserved value */ +#define MC_CMD_FW_PACKED_STREAM_HASH_MODE_1 0x4 /* enum: Only this option is allowed for non-admin functions */ #define MC_CMD_FW_DONT_CARE 0xffffffff @@ -2481,6 +2742,12 @@ #define MC_CMD_LOOPBACK_SD_FES_WS 0x22 /* enum: Near side of AOE Siena side port */ #define MC_CMD_LOOPBACK_AOE_INT_NEAR 0x23 +/* enum: Medford Wireside datapath loopback */ +#define MC_CMD_LOOPBACK_DATA_WS 0x24 +/* enum: Force link up without setting up any physical loopback (snapper use + * only) + */ +#define MC_CMD_LOOPBACK_FORCE_EXT_LINK 0x25 /* Supported loopbacks. */ #define MC_CMD_GET_LOOPBACK_MODES_OUT_1G_OFST 8 #define MC_CMD_GET_LOOPBACK_MODES_OUT_1G_LEN 8 @@ -2552,12 +2819,8 @@ #define MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_WIDTH 1 /* This returns the negotiated flow control value. */ #define MC_CMD_GET_LINK_OUT_FCNTL_OFST 20 -/* enum: Flow control is off. */ -#define MC_CMD_FCNTL_OFF 0x0 -/* enum: Respond to flow control. */ -#define MC_CMD_FCNTL_RESPOND 0x1 -/* enum: Respond to and Issue flow control. */ -#define MC_CMD_FCNTL_BIDIR 0x2 +/* Enum values, see field(s): */ +/* MC_CMD_SET_MAC/MC_CMD_SET_MAC_IN/FCNTL */ #define MC_CMD_GET_LINK_OUT_MAC_FAULT_OFST 24 #define MC_CMD_MAC_FAULT_XGMII_LOCAL_LBN 0 #define MC_CMD_MAC_FAULT_XGMII_LOCAL_WIDTH 1 @@ -2632,7 +2895,7 @@ #define MC_CMD_0x2c_PRIVILEGE_CTG SRIOV_CTG_LINK /* MC_CMD_SET_MAC_IN msgrequest */ -#define MC_CMD_SET_MAC_IN_LEN 24 +#define MC_CMD_SET_MAC_IN_LEN 28 /* The MTU is the MTU programmed directly into the XMAC/GMAC (inclusive of * EtherII, VLAN, bug16011 padding). */ @@ -2649,13 +2912,20 @@ #define MC_CMD_SET_MAC_IN_REJECT_BRDCST_WIDTH 1 #define MC_CMD_SET_MAC_IN_FCNTL_OFST 20 /* enum: Flow control is off. */ -/* MC_CMD_FCNTL_OFF 0x0 */ +#define MC_CMD_FCNTL_OFF 0x0 /* enum: Respond to flow control. */ -/* MC_CMD_FCNTL_RESPOND 0x1 */ +#define MC_CMD_FCNTL_RESPOND 0x1 /* enum: Respond to and Issue flow control. */ -/* MC_CMD_FCNTL_BIDIR 0x2 */ +#define MC_CMD_FCNTL_BIDIR 0x2 /* enum: Auto neg flow control. */ #define MC_CMD_FCNTL_AUTO 0x3 +/* enum: Priority flow control (eftest builds only). */ +#define MC_CMD_FCNTL_QBB 0x4 +/* enum: Issue flow control. */ +#define MC_CMD_FCNTL_GENERATE 0x5 +#define MC_CMD_SET_MAC_IN_FLAGS_OFST 24 +#define MC_CMD_SET_MAC_IN_FLAG_INCLUDE_FCS_LBN 0 +#define MC_CMD_SET_MAC_IN_FLAG_INCLUDE_FCS_WIDTH 1 /* MC_CMD_SET_MAC_OUT msgresponse */ #define MC_CMD_SET_MAC_OUT_LEN 0 @@ -2748,7 +3018,8 @@ * guarantee consistent results. If the DMA_ADDR is 0, then no DMA is * performed, and the statistics may be read from the message response. If * DMA_ADDR != 0, then the statistics are dmad to that (page-aligned location). - * Locks required: None. Returns: 0, ETIME + * Locks required: None. The PERIODIC_CLEAR option is not used and now has no + * effect. Returns: 0, ETIME */ #define MC_CMD_MAC_STATS 0x2e @@ -2791,6 +3062,7 @@ #define MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_HI_OFST 4 #define MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS #define MC_CMD_MAC_GENERATION_START 0x0 /* enum */ +#define MC_CMD_MAC_DMABUF_START 0x1 /* enum */ #define MC_CMD_MAC_TX_PKTS 0x1 /* enum */ #define MC_CMD_MAC_TX_PAUSE_PKTS 0x2 /* enum */ #define MC_CMD_MAC_TX_CONTROL_PKTS 0x3 /* enum */ @@ -2890,8 +3162,8 @@ * PM_AND_RXDP_COUNTERS capability only. */ #define MC_CMD_MAC_RXDP_STREAMING_PKTS 0x46 -/* enum: RXDP counter: Number of times an emergency descriptor fetch was - * performed. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only. +/* enum: RXDP counter: Number of times an hlb descriptor fetch was performed. + * Valid for EF10 with PM_AND_RXDP_COUNTERS capability only. */ #define MC_CMD_MAC_RXDP_HLB_FETCH_CONDITIONS 0x47 /* enum: RXDP counter: Number of times the DPCPU waited for an existing @@ -3213,6 +3485,8 @@ #define MC_CMD_NVRAM_TYPE_LICENSE 0x12 /* enum: FC Log. */ #define MC_CMD_NVRAM_TYPE_FC_LOG 0x13 +/* enum: Additional flash on FPGA. */ +#define MC_CMD_NVRAM_TYPE_FC_EXTRA 0x14 /***********************************/ @@ -3407,6 +3681,8 @@ */ #define MC_CMD_SCHEDINFO 0x3e +#define MC_CMD_0x3e_PRIVILEGE_CTG SRIOV_CTG_ADMIN + /* MC_CMD_SCHEDINFO_IN msgrequest */ #define MC_CMD_SCHEDINFO_IN_LEN 0 @@ -3593,6 +3869,68 @@ #define MC_CMD_SENSOR_VDD08D_VSS08D_CSR_EXTADC 0x2c /* enum: Hotpoint temperature: degC */ #define MC_CMD_SENSOR_HOTPOINT_TEMP 0x2d +/* enum: Port 0 PHY power switch over-current: bool */ +#define MC_CMD_SENSOR_PHY_POWER_PORT0 0x2e +/* enum: Port 1 PHY power switch over-current: bool */ +#define MC_CMD_SENSOR_PHY_POWER_PORT1 0x2f +/* enum: Mop-up microcontroller reference voltage (millivolts) */ +#define MC_CMD_SENSOR_MUM_VCC 0x30 +/* enum: 0.9v power phase A voltage: mV */ +#define MC_CMD_SENSOR_IN_0V9_A 0x31 +/* enum: 0.9v power phase A current: mA */ +#define MC_CMD_SENSOR_IN_I0V9_A 0x32 +/* enum: 0.9V voltage regulator phase A temperature: degC */ +#define MC_CMD_SENSOR_VREG_0V9_A_TEMP 0x33 +/* enum: 0.9v power phase B voltage: mV */ +#define MC_CMD_SENSOR_IN_0V9_B 0x34 +/* enum: 0.9v power phase B current: mA */ +#define MC_CMD_SENSOR_IN_I0V9_B 0x35 +/* enum: 0.9V voltage regulator phase B temperature: degC */ +#define MC_CMD_SENSOR_VREG_0V9_B_TEMP 0x36 +/* enum: CCOM AVREG 1v2 supply (interval ADC): mV */ +#define MC_CMD_SENSOR_CCOM_AVREG_1V2_SUPPLY 0x37 +/* enum: CCOM AVREG 1v2 supply (external ADC): mV */ +#define MC_CMD_SENSOR_CCOM_AVREG_1V2_SUPPLY_EXTADC 0x38 +/* enum: CCOM AVREG 1v8 supply (interval ADC): mV */ +#define MC_CMD_SENSOR_CCOM_AVREG_1V8_SUPPLY 0x39 +/* enum: CCOM AVREG 1v8 supply (external ADC): mV */ +#define MC_CMD_SENSOR_CCOM_AVREG_1V8_SUPPLY_EXTADC 0x3a +/* enum: Not a sensor: reserved for the next page flag */ +#define MC_CMD_SENSOR_PAGE1_NEXT 0x3f +/* enum: controller internal temperature sensor voltage on master core + * (internal ADC): mV + */ +#define MC_CMD_SENSOR_CONTROLLER_MASTER_VPTAT 0x40 +/* enum: controller internal temperature on master core (internal ADC): degC */ +#define MC_CMD_SENSOR_CONTROLLER_MASTER_INTERNAL_TEMP 0x41 +/* enum: controller internal temperature sensor voltage on master core + * (external ADC): mV + */ +#define MC_CMD_SENSOR_CONTROLLER_MASTER_VPTAT_EXTADC 0x42 +/* enum: controller internal temperature on master core (external ADC): degC */ +#define MC_CMD_SENSOR_CONTROLLER_MASTER_INTERNAL_TEMP_EXTADC 0x43 +/* enum: controller internal temperature on slave core sensor voltage (internal + * ADC): mV + */ +#define MC_CMD_SENSOR_CONTROLLER_SLAVE_VPTAT 0x44 +/* enum: controller internal temperature on slave core (internal ADC): degC */ +#define MC_CMD_SENSOR_CONTROLLER_SLAVE_INTERNAL_TEMP 0x45 +/* enum: controller internal temperature on slave core sensor voltage (external + * ADC): mV + */ +#define MC_CMD_SENSOR_CONTROLLER_SLAVE_VPTAT_EXTADC 0x46 +/* enum: controller internal temperature on slave core (external ADC): degC */ +#define MC_CMD_SENSOR_CONTROLLER_SLAVE_INTERNAL_TEMP_EXTADC 0x47 +/* enum: Voltage supplied to the SODIMMs from their power supply: mV */ +#define MC_CMD_SENSOR_SODIMM_VOUT 0x49 +/* enum: Temperature of SODIMM 0 (if installed): degC */ +#define MC_CMD_SENSOR_SODIMM_0_TEMP 0x4a +/* enum: Temperature of SODIMM 1 (if installed): degC */ +#define MC_CMD_SENSOR_SODIMM_1_TEMP 0x4b +/* enum: Voltage supplied to the QSFP #0 from their power supply: mV */ +#define MC_CMD_SENSOR_PHY0_VCC 0x4c +/* enum: Voltage supplied to the QSFP #1 from their power supply: mV */ +#define MC_CMD_SENSOR_PHY1_VCC 0x4d /* MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF */ #define MC_CMD_SENSOR_ENTRY_OFST 4 #define MC_CMD_SENSOR_ENTRY_LEN 8 @@ -3701,6 +4039,8 @@ #define MC_CMD_SENSOR_STATE_BROKEN 0x3 /* enum: Sensor is working but does not currently have a reading. */ #define MC_CMD_SENSOR_STATE_NO_READING 0x4 +/* enum: Sensor initialisation failed. */ +#define MC_CMD_SENSOR_STATE_INIT_FAILED 0x5 #define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_STATE_LBN 16 #define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_STATE_WIDTH 8 #define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_TYPE_OFST 3 @@ -3870,6 +4210,7 @@ /* MC_CMD_WORKAROUND_IN msgrequest */ #define MC_CMD_WORKAROUND_IN_LEN 8 +/* The enums here must correspond with those in MC_CMD_GET_WORKAROUND. */ #define MC_CMD_WORKAROUND_IN_TYPE_OFST 0 /* enum: Bug 17230 work around. */ #define MC_CMD_WORKAROUND_BUG17230 0x1 @@ -3877,11 +4218,38 @@ #define MC_CMD_WORKAROUND_BUG35388 0x2 /* enum: Bug35017 workaround (A64 tables must be identity map) */ #define MC_CMD_WORKAROUND_BUG35017 0x3 +/* enum: Bug 41750 present (MC_CMD_TRIGGER_INTERRUPT won't work) */ +#define MC_CMD_WORKAROUND_BUG41750 0x4 +/* enum: Bug 42008 present (Interrupts can overtake associated events). Caution + * - before adding code that queries this workaround, remember that there's + * released Monza firmware that doesn't understand MC_CMD_WORKAROUND_BUG42008, + * and will hence (incorrectly) report that the bug doesn't exist. + */ +#define MC_CMD_WORKAROUND_BUG42008 0x5 +/* enum: Bug 26807 features present in firmware (multicast filter chaining) + * This feature cannot be turned on/off while there are any filters already + * present. The behaviour in such case depends on the acting client's privilege + * level. If the client has the admin privilege, then all functions that have + * filters installed will be FLRed and the FLR_DONE flag will be set. Otherwise + * the command will fail with MC_CMD_ERR_FILTERS_PRESENT. + */ +#define MC_CMD_WORKAROUND_BUG26807 0x6 +/* 0 = disable the workaround indicated by TYPE; any non-zero value = enable + * the workaround + */ #define MC_CMD_WORKAROUND_IN_ENABLED_OFST 4 /* MC_CMD_WORKAROUND_OUT msgresponse */ #define MC_CMD_WORKAROUND_OUT_LEN 0 +/* MC_CMD_WORKAROUND_EXT_OUT msgresponse: This response format will be used + * when (TYPE == MC_CMD_WORKAROUND_BUG26807) + */ +#define MC_CMD_WORKAROUND_EXT_OUT_LEN 4 +#define MC_CMD_WORKAROUND_EXT_OUT_FLAGS_OFST 0 +#define MC_CMD_WORKAROUND_EXT_OUT_FLR_DONE_LBN 0 +#define MC_CMD_WORKAROUND_EXT_OUT_FLR_DONE_WIDTH 1 + /***********************************/ /* MC_CMD_GET_PHY_MEDIA_INFO @@ -4093,7 +4461,7 @@ /***********************************/ /* MC_CMD_GET_MAC_ADDRESSES - * Returns the base MAC, count and stride for the requestiong function + * Returns the base MAC, count and stride for the requesting function */ #define MC_CMD_GET_MAC_ADDRESSES 0x55 @@ -4115,6 +4483,527 @@ /* Spacing of allocated MAC addresses */ #define MC_CMD_GET_MAC_ADDRESSES_OUT_MAC_STRIDE_OFST 12 + +/***********************************/ +/* MC_CMD_CLP + * Perform a CLP related operation + */ +#define MC_CMD_CLP 0x56 + +#define MC_CMD_0x56_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_CLP_IN msgrequest */ +#define MC_CMD_CLP_IN_LEN 4 +/* Sub operation */ +#define MC_CMD_CLP_IN_OP_OFST 0 +/* enum: Return to factory default settings */ +#define MC_CMD_CLP_OP_DEFAULT 0x1 +/* enum: Set MAC address */ +#define MC_CMD_CLP_OP_SET_MAC 0x2 +/* enum: Get MAC address */ +#define MC_CMD_CLP_OP_GET_MAC 0x3 +/* enum: Set UEFI/GPXE boot mode */ +#define MC_CMD_CLP_OP_SET_BOOT 0x4 +/* enum: Get UEFI/GPXE boot mode */ +#define MC_CMD_CLP_OP_GET_BOOT 0x5 + +/* MC_CMD_CLP_OUT msgresponse */ +#define MC_CMD_CLP_OUT_LEN 0 + +/* MC_CMD_CLP_IN_DEFAULT msgrequest */ +#define MC_CMD_CLP_IN_DEFAULT_LEN 4 +/* MC_CMD_CLP_IN_OP_OFST 0 */ + +/* MC_CMD_CLP_OUT_DEFAULT msgresponse */ +#define MC_CMD_CLP_OUT_DEFAULT_LEN 0 + +/* MC_CMD_CLP_IN_SET_MAC msgrequest */ +#define MC_CMD_CLP_IN_SET_MAC_LEN 12 +/* MC_CMD_CLP_IN_OP_OFST 0 */ +/* MAC address assigned to port */ +#define MC_CMD_CLP_IN_SET_MAC_ADDR_OFST 4 +#define MC_CMD_CLP_IN_SET_MAC_ADDR_LEN 6 +/* Padding */ +#define MC_CMD_CLP_IN_SET_MAC_RESERVED_OFST 10 +#define MC_CMD_CLP_IN_SET_MAC_RESERVED_LEN 2 + +/* MC_CMD_CLP_OUT_SET_MAC msgresponse */ +#define MC_CMD_CLP_OUT_SET_MAC_LEN 0 + +/* MC_CMD_CLP_IN_GET_MAC msgrequest */ +#define MC_CMD_CLP_IN_GET_MAC_LEN 4 +/* MC_CMD_CLP_IN_OP_OFST 0 */ + +/* MC_CMD_CLP_OUT_GET_MAC msgresponse */ +#define MC_CMD_CLP_OUT_GET_MAC_LEN 8 +/* MAC address assigned to port */ +#define MC_CMD_CLP_OUT_GET_MAC_ADDR_OFST 0 +#define MC_CMD_CLP_OUT_GET_MAC_ADDR_LEN 6 +/* Padding */ +#define MC_CMD_CLP_OUT_GET_MAC_RESERVED_OFST 6 +#define MC_CMD_CLP_OUT_GET_MAC_RESERVED_LEN 2 + +/* MC_CMD_CLP_IN_SET_BOOT msgrequest */ +#define MC_CMD_CLP_IN_SET_BOOT_LEN 5 +/* MC_CMD_CLP_IN_OP_OFST 0 */ +/* Boot flag */ +#define MC_CMD_CLP_IN_SET_BOOT_FLAG_OFST 4 +#define MC_CMD_CLP_IN_SET_BOOT_FLAG_LEN 1 + +/* MC_CMD_CLP_OUT_SET_BOOT msgresponse */ +#define MC_CMD_CLP_OUT_SET_BOOT_LEN 0 + +/* MC_CMD_CLP_IN_GET_BOOT msgrequest */ +#define MC_CMD_CLP_IN_GET_BOOT_LEN 4 +/* MC_CMD_CLP_IN_OP_OFST 0 */ + +/* MC_CMD_CLP_OUT_GET_BOOT msgresponse */ +#define MC_CMD_CLP_OUT_GET_BOOT_LEN 4 +/* Boot flag */ +#define MC_CMD_CLP_OUT_GET_BOOT_FLAG_OFST 0 +#define MC_CMD_CLP_OUT_GET_BOOT_FLAG_LEN 1 +/* Padding */ +#define MC_CMD_CLP_OUT_GET_BOOT_RESERVED_OFST 1 +#define MC_CMD_CLP_OUT_GET_BOOT_RESERVED_LEN 3 + + +/***********************************/ +/* MC_CMD_MUM + * Perform a MUM operation + */ +#define MC_CMD_MUM 0x57 + +#define MC_CMD_0x57_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_MUM_IN msgrequest */ +#define MC_CMD_MUM_IN_LEN 4 +#define MC_CMD_MUM_IN_OP_HDR_OFST 0 +#define MC_CMD_MUM_IN_OP_LBN 0 +#define MC_CMD_MUM_IN_OP_WIDTH 8 +/* enum: NULL MCDI command to MUM */ +#define MC_CMD_MUM_OP_NULL 0x1 +/* enum: Get MUM version */ +#define MC_CMD_MUM_OP_GET_VERSION 0x2 +/* enum: Issue raw I2C command to MUM */ +#define MC_CMD_MUM_OP_RAW_CMD 0x3 +/* enum: Read from registers on devices connected to MUM. */ +#define MC_CMD_MUM_OP_READ 0x4 +/* enum: Write to registers on devices connected to MUM. */ +#define MC_CMD_MUM_OP_WRITE 0x5 +/* enum: Control UART logging. */ +#define MC_CMD_MUM_OP_LOG 0x6 +/* enum: Operations on MUM GPIO lines */ +#define MC_CMD_MUM_OP_GPIO 0x7 +/* enum: Get sensor readings from MUM */ +#define MC_CMD_MUM_OP_READ_SENSORS 0x8 +/* enum: Initiate clock programming on the MUM */ +#define MC_CMD_MUM_OP_PROGRAM_CLOCKS 0x9 +/* enum: Initiate FPGA load from flash on the MUM */ +#define MC_CMD_MUM_OP_FPGA_LOAD 0xa +/* enum: Request sensor reading from MUM ADC resulting from earlier request via + * MUM ATB + */ +#define MC_CMD_MUM_OP_READ_ATB_SENSOR 0xb +/* enum: Send commands relating to the QSFP ports via the MUM for PHY + * operations + */ +#define MC_CMD_MUM_OP_QSFP 0xc + +/* MC_CMD_MUM_IN_NULL msgrequest */ +#define MC_CMD_MUM_IN_NULL_LEN 4 +/* MUM cmd header */ +#define MC_CMD_MUM_IN_CMD_OFST 0 + +/* MC_CMD_MUM_IN_GET_VERSION msgrequest */ +#define MC_CMD_MUM_IN_GET_VERSION_LEN 4 +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ + +/* MC_CMD_MUM_IN_READ msgrequest */ +#define MC_CMD_MUM_IN_READ_LEN 16 +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +/* ID of (device connected to MUM) to read from registers of */ +#define MC_CMD_MUM_IN_READ_DEVICE_OFST 4 +/* enum: Hittite HMC1035 clock generator on Sorrento board */ +#define MC_CMD_MUM_DEV_HITTITE 0x1 +/* enum: Hittite HMC1035 clock generator for NIC-side on Sorrento board */ +#define MC_CMD_MUM_DEV_HITTITE_NIC 0x2 +/* 32-bit address to read from */ +#define MC_CMD_MUM_IN_READ_ADDR_OFST 8 +/* Number of words to read. */ +#define MC_CMD_MUM_IN_READ_NUMWORDS_OFST 12 + +/* MC_CMD_MUM_IN_WRITE msgrequest */ +#define MC_CMD_MUM_IN_WRITE_LENMIN 16 +#define MC_CMD_MUM_IN_WRITE_LENMAX 252 +#define MC_CMD_MUM_IN_WRITE_LEN(num) (12+4*(num)) +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +/* ID of (device connected to MUM) to write to registers of */ +#define MC_CMD_MUM_IN_WRITE_DEVICE_OFST 4 +/* enum: Hittite HMC1035 clock generator on Sorrento board */ +/* MC_CMD_MUM_DEV_HITTITE 0x1 */ +/* 32-bit address to write to */ +#define MC_CMD_MUM_IN_WRITE_ADDR_OFST 8 +/* Words to write */ +#define MC_CMD_MUM_IN_WRITE_BUFFER_OFST 12 +#define MC_CMD_MUM_IN_WRITE_BUFFER_LEN 4 +#define MC_CMD_MUM_IN_WRITE_BUFFER_MINNUM 1 +#define MC_CMD_MUM_IN_WRITE_BUFFER_MAXNUM 60 + +/* MC_CMD_MUM_IN_RAW_CMD msgrequest */ +#define MC_CMD_MUM_IN_RAW_CMD_LENMIN 17 +#define MC_CMD_MUM_IN_RAW_CMD_LENMAX 252 +#define MC_CMD_MUM_IN_RAW_CMD_LEN(num) (16+1*(num)) +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +/* MUM I2C cmd code */ +#define MC_CMD_MUM_IN_RAW_CMD_CMD_CODE_OFST 4 +/* Number of bytes to write */ +#define MC_CMD_MUM_IN_RAW_CMD_NUM_WRITE_OFST 8 +/* Number of bytes to read */ +#define MC_CMD_MUM_IN_RAW_CMD_NUM_READ_OFST 12 +/* Bytes to write */ +#define MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_OFST 16 +#define MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_LEN 1 +#define MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_MINNUM 1 +#define MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_MAXNUM 236 + +/* MC_CMD_MUM_IN_LOG msgrequest */ +#define MC_CMD_MUM_IN_LOG_LEN 8 +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_LOG_OP_OFST 4 +#define MC_CMD_MUM_IN_LOG_OP_UART 0x1 /* enum */ + +/* MC_CMD_MUM_IN_LOG_OP_UART msgrequest */ +#define MC_CMD_MUM_IN_LOG_OP_UART_LEN 12 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +/* MC_CMD_MUM_IN_LOG_OP_OFST 4 */ +/* Enable/disable debug output to UART */ +#define MC_CMD_MUM_IN_LOG_OP_UART_ENABLE_OFST 8 + +/* MC_CMD_MUM_IN_GPIO msgrequest */ +#define MC_CMD_MUM_IN_GPIO_LEN 8 +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_HDR_OFST 4 +#define MC_CMD_MUM_IN_GPIO_OPCODE_LBN 0 +#define MC_CMD_MUM_IN_GPIO_OPCODE_WIDTH 8 +#define MC_CMD_MUM_IN_GPIO_IN_READ 0x0 /* enum */ +#define MC_CMD_MUM_IN_GPIO_OUT_WRITE 0x1 /* enum */ +#define MC_CMD_MUM_IN_GPIO_OUT_READ 0x2 /* enum */ +#define MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE 0x3 /* enum */ +#define MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ 0x4 /* enum */ +#define MC_CMD_MUM_IN_GPIO_OP 0x5 /* enum */ + +/* MC_CMD_MUM_IN_GPIO_IN_READ msgrequest */ +#define MC_CMD_MUM_IN_GPIO_IN_READ_LEN 8 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_IN_READ_HDR_OFST 4 + +/* MC_CMD_MUM_IN_GPIO_OUT_WRITE msgrequest */ +#define MC_CMD_MUM_IN_GPIO_OUT_WRITE_LEN 16 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_OUT_WRITE_HDR_OFST 4 +/* The first 32-bit word to be written to the GPIO OUT register. */ +#define MC_CMD_MUM_IN_GPIO_OUT_WRITE_GPIOMASK1_OFST 8 +/* The second 32-bit word to be written to the GPIO OUT register. */ +#define MC_CMD_MUM_IN_GPIO_OUT_WRITE_GPIOMASK2_OFST 12 + +/* MC_CMD_MUM_IN_GPIO_OUT_READ msgrequest */ +#define MC_CMD_MUM_IN_GPIO_OUT_READ_LEN 8 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_OUT_READ_HDR_OFST 4 + +/* MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE msgrequest */ +#define MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_LEN 16 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_HDR_OFST 4 +/* The first 32-bit word to be written to the GPIO OUT ENABLE register. */ +#define MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_GPIOMASK1_OFST 8 +/* The second 32-bit word to be written to the GPIO OUT ENABLE register. */ +#define MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_GPIOMASK2_OFST 12 + +/* MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ msgrequest */ +#define MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ_LEN 8 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ_HDR_OFST 4 + +/* MC_CMD_MUM_IN_GPIO_OP msgrequest */ +#define MC_CMD_MUM_IN_GPIO_OP_LEN 8 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_OP_HDR_OFST 4 +#define MC_CMD_MUM_IN_GPIO_OP_BITWISE_OP_LBN 8 +#define MC_CMD_MUM_IN_GPIO_OP_BITWISE_OP_WIDTH 8 +#define MC_CMD_MUM_IN_GPIO_OP_OUT_READ 0x0 /* enum */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE 0x1 /* enum */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG 0x2 /* enum */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE 0x3 /* enum */ +#define MC_CMD_MUM_IN_GPIO_OP_GPIO_NUMBER_LBN 16 +#define MC_CMD_MUM_IN_GPIO_OP_GPIO_NUMBER_WIDTH 8 + +/* MC_CMD_MUM_IN_GPIO_OP_OUT_READ msgrequest */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_READ_LEN 8 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_READ_HDR_OFST 4 + +/* MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE msgrequest */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_LEN 8 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_HDR_OFST 4 +#define MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_WRITEBIT_LBN 24 +#define MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_WRITEBIT_WIDTH 8 + +/* MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG msgrequest */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_LEN 8 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_HDR_OFST 4 +#define MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_CFG_LBN 24 +#define MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_CFG_WIDTH 8 + +/* MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE msgrequest */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_LEN 8 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_HDR_OFST 4 +#define MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_ENABLEBIT_LBN 24 +#define MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_ENABLEBIT_WIDTH 8 + +/* MC_CMD_MUM_IN_READ_SENSORS msgrequest */ +#define MC_CMD_MUM_IN_READ_SENSORS_LEN 8 +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_READ_SENSORS_PARAMS_OFST 4 +#define MC_CMD_MUM_IN_READ_SENSORS_SENSOR_ID_LBN 0 +#define MC_CMD_MUM_IN_READ_SENSORS_SENSOR_ID_WIDTH 8 +#define MC_CMD_MUM_IN_READ_SENSORS_NUM_SENSORS_LBN 8 +#define MC_CMD_MUM_IN_READ_SENSORS_NUM_SENSORS_WIDTH 8 + +/* MC_CMD_MUM_IN_PROGRAM_CLOCKS msgrequest */ +#define MC_CMD_MUM_IN_PROGRAM_CLOCKS_LEN 12 +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +/* Bit-mask of clocks to be programmed */ +#define MC_CMD_MUM_IN_PROGRAM_CLOCKS_MASK_OFST 4 +#define MC_CMD_MUM_CLOCK_ID_FPGA 0x0 /* enum */ +#define MC_CMD_MUM_CLOCK_ID_DDR 0x1 /* enum */ +#define MC_CMD_MUM_CLOCK_ID_NIC 0x2 /* enum */ +/* Control flags for clock programming */ +#define MC_CMD_MUM_IN_PROGRAM_CLOCKS_FLAGS_OFST 8 +#define MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_LBN 0 +#define MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_WIDTH 1 + +/* MC_CMD_MUM_IN_FPGA_LOAD msgrequest */ +#define MC_CMD_MUM_IN_FPGA_LOAD_LEN 8 +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +/* Enable/Disable FPGA config from flash */ +#define MC_CMD_MUM_IN_FPGA_LOAD_ENABLE_OFST 4 + +/* MC_CMD_MUM_IN_READ_ATB_SENSOR msgrequest */ +#define MC_CMD_MUM_IN_READ_ATB_SENSOR_LEN 4 +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ + +/* MC_CMD_MUM_IN_QSFP msgrequest */ +#define MC_CMD_MUM_IN_QSFP_LEN 12 +/* MUM cmd header */ +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_QSFP_HDR_OFST 4 +#define MC_CMD_MUM_IN_QSFP_OPCODE_LBN 0 +#define MC_CMD_MUM_IN_QSFP_OPCODE_WIDTH 4 +#define MC_CMD_MUM_IN_QSFP_INIT 0x0 /* enum */ +#define MC_CMD_MUM_IN_QSFP_RECONFIGURE 0x1 /* enum */ +#define MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP 0x2 /* enum */ +#define MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO 0x3 /* enum */ +#define MC_CMD_MUM_IN_QSFP_FILL_STATS 0x4 /* enum */ +#define MC_CMD_MUM_IN_QSFP_POLL_BIST 0x5 /* enum */ +#define MC_CMD_MUM_IN_QSFP_IDX_OFST 8 + +/* MC_CMD_MUM_IN_QSFP_INIT msgrequest */ +#define MC_CMD_MUM_IN_QSFP_INIT_LEN 16 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_QSFP_INIT_HDR_OFST 4 +#define MC_CMD_MUM_IN_QSFP_INIT_IDX_OFST 8 +#define MC_CMD_MUM_IN_QSFP_INIT_CAGE_OFST 12 + +/* MC_CMD_MUM_IN_QSFP_RECONFIGURE msgrequest */ +#define MC_CMD_MUM_IN_QSFP_RECONFIGURE_LEN 24 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_QSFP_RECONFIGURE_HDR_OFST 4 +#define MC_CMD_MUM_IN_QSFP_RECONFIGURE_IDX_OFST 8 +#define MC_CMD_MUM_IN_QSFP_RECONFIGURE_TX_DISABLE_OFST 12 +#define MC_CMD_MUM_IN_QSFP_RECONFIGURE_PORT_LANES_OFST 16 +#define MC_CMD_MUM_IN_QSFP_RECONFIGURE_PORT_LINK_SPEED_OFST 20 + +/* MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP msgrequest */ +#define MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_LEN 12 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_HDR_OFST 4 +#define MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_IDX_OFST 8 + +/* MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO msgrequest */ +#define MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_LEN 16 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_HDR_OFST 4 +#define MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_IDX_OFST 8 +#define MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_PAGE_OFST 12 + +/* MC_CMD_MUM_IN_QSFP_FILL_STATS msgrequest */ +#define MC_CMD_MUM_IN_QSFP_FILL_STATS_LEN 12 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_QSFP_FILL_STATS_HDR_OFST 4 +#define MC_CMD_MUM_IN_QSFP_FILL_STATS_IDX_OFST 8 + +/* MC_CMD_MUM_IN_QSFP_POLL_BIST msgrequest */ +#define MC_CMD_MUM_IN_QSFP_POLL_BIST_LEN 12 +/* MC_CMD_MUM_IN_CMD_OFST 0 */ +#define MC_CMD_MUM_IN_QSFP_POLL_BIST_HDR_OFST 4 +#define MC_CMD_MUM_IN_QSFP_POLL_BIST_IDX_OFST 8 + +/* MC_CMD_MUM_OUT msgresponse */ +#define MC_CMD_MUM_OUT_LEN 0 + +/* MC_CMD_MUM_OUT_NULL msgresponse */ +#define MC_CMD_MUM_OUT_NULL_LEN 0 + +/* MC_CMD_MUM_OUT_GET_VERSION msgresponse */ +#define MC_CMD_MUM_OUT_GET_VERSION_LEN 12 +#define MC_CMD_MUM_OUT_GET_VERSION_FIRMWARE_OFST 0 +#define MC_CMD_MUM_OUT_GET_VERSION_VERSION_OFST 4 +#define MC_CMD_MUM_OUT_GET_VERSION_VERSION_LEN 8 +#define MC_CMD_MUM_OUT_GET_VERSION_VERSION_LO_OFST 4 +#define MC_CMD_MUM_OUT_GET_VERSION_VERSION_HI_OFST 8 + +/* MC_CMD_MUM_OUT_RAW_CMD msgresponse */ +#define MC_CMD_MUM_OUT_RAW_CMD_LENMIN 1 +#define MC_CMD_MUM_OUT_RAW_CMD_LENMAX 252 +#define MC_CMD_MUM_OUT_RAW_CMD_LEN(num) (0+1*(num)) +/* returned data */ +#define MC_CMD_MUM_OUT_RAW_CMD_DATA_OFST 0 +#define MC_CMD_MUM_OUT_RAW_CMD_DATA_LEN 1 +#define MC_CMD_MUM_OUT_RAW_CMD_DATA_MINNUM 1 +#define MC_CMD_MUM_OUT_RAW_CMD_DATA_MAXNUM 252 + +/* MC_CMD_MUM_OUT_READ msgresponse */ +#define MC_CMD_MUM_OUT_READ_LENMIN 4 +#define MC_CMD_MUM_OUT_READ_LENMAX 252 +#define MC_CMD_MUM_OUT_READ_LEN(num) (0+4*(num)) +#define MC_CMD_MUM_OUT_READ_BUFFER_OFST 0 +#define MC_CMD_MUM_OUT_READ_BUFFER_LEN 4 +#define MC_CMD_MUM_OUT_READ_BUFFER_MINNUM 1 +#define MC_CMD_MUM_OUT_READ_BUFFER_MAXNUM 63 + +/* MC_CMD_MUM_OUT_WRITE msgresponse */ +#define MC_CMD_MUM_OUT_WRITE_LEN 0 + +/* MC_CMD_MUM_OUT_LOG msgresponse */ +#define MC_CMD_MUM_OUT_LOG_LEN 0 + +/* MC_CMD_MUM_OUT_LOG_OP_UART msgresponse */ +#define MC_CMD_MUM_OUT_LOG_OP_UART_LEN 0 + +/* MC_CMD_MUM_OUT_GPIO_IN_READ msgresponse */ +#define MC_CMD_MUM_OUT_GPIO_IN_READ_LEN 8 +/* The first 32-bit word read from the GPIO IN register. */ +#define MC_CMD_MUM_OUT_GPIO_IN_READ_GPIOMASK1_OFST 0 +/* The second 32-bit word read from the GPIO IN register. */ +#define MC_CMD_MUM_OUT_GPIO_IN_READ_GPIOMASK2_OFST 4 + +/* MC_CMD_MUM_OUT_GPIO_OUT_WRITE msgresponse */ +#define MC_CMD_MUM_OUT_GPIO_OUT_WRITE_LEN 0 + +/* MC_CMD_MUM_OUT_GPIO_OUT_READ msgresponse */ +#define MC_CMD_MUM_OUT_GPIO_OUT_READ_LEN 8 +/* The first 32-bit word read from the GPIO OUT register. */ +#define MC_CMD_MUM_OUT_GPIO_OUT_READ_GPIOMASK1_OFST 0 +/* The second 32-bit word read from the GPIO OUT register. */ +#define MC_CMD_MUM_OUT_GPIO_OUT_READ_GPIOMASK2_OFST 4 + +/* MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_WRITE msgresponse */ +#define MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_WRITE_LEN 0 + +/* MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ msgresponse */ +#define MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_LEN 8 +#define MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_GPIOMASK1_OFST 0 +#define MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_GPIOMASK2_OFST 4 + +/* MC_CMD_MUM_OUT_GPIO_OP_OUT_READ msgresponse */ +#define MC_CMD_MUM_OUT_GPIO_OP_OUT_READ_LEN 4 +#define MC_CMD_MUM_OUT_GPIO_OP_OUT_READ_BIT_READ_OFST 0 + +/* MC_CMD_MUM_OUT_GPIO_OP_OUT_WRITE msgresponse */ +#define MC_CMD_MUM_OUT_GPIO_OP_OUT_WRITE_LEN 0 + +/* MC_CMD_MUM_OUT_GPIO_OP_OUT_CONFIG msgresponse */ +#define MC_CMD_MUM_OUT_GPIO_OP_OUT_CONFIG_LEN 0 + +/* MC_CMD_MUM_OUT_GPIO_OP_OUT_ENABLE msgresponse */ +#define MC_CMD_MUM_OUT_GPIO_OP_OUT_ENABLE_LEN 0 + +/* MC_CMD_MUM_OUT_READ_SENSORS msgresponse */ +#define MC_CMD_MUM_OUT_READ_SENSORS_LENMIN 4 +#define MC_CMD_MUM_OUT_READ_SENSORS_LENMAX 252 +#define MC_CMD_MUM_OUT_READ_SENSORS_LEN(num) (0+4*(num)) +#define MC_CMD_MUM_OUT_READ_SENSORS_DATA_OFST 0 +#define MC_CMD_MUM_OUT_READ_SENSORS_DATA_LEN 4 +#define MC_CMD_MUM_OUT_READ_SENSORS_DATA_MINNUM 1 +#define MC_CMD_MUM_OUT_READ_SENSORS_DATA_MAXNUM 63 +#define MC_CMD_MUM_OUT_READ_SENSORS_READING_LBN 0 +#define MC_CMD_MUM_OUT_READ_SENSORS_READING_WIDTH 16 +#define MC_CMD_MUM_OUT_READ_SENSORS_STATE_LBN 16 +#define MC_CMD_MUM_OUT_READ_SENSORS_STATE_WIDTH 8 +#define MC_CMD_MUM_OUT_READ_SENSORS_TYPE_LBN 24 +#define MC_CMD_MUM_OUT_READ_SENSORS_TYPE_WIDTH 8 + +/* MC_CMD_MUM_OUT_PROGRAM_CLOCKS msgresponse */ +#define MC_CMD_MUM_OUT_PROGRAM_CLOCKS_LEN 4 +#define MC_CMD_MUM_OUT_PROGRAM_CLOCKS_OK_MASK_OFST 0 + +/* MC_CMD_MUM_OUT_FPGA_LOAD msgresponse */ +#define MC_CMD_MUM_OUT_FPGA_LOAD_LEN 0 + +/* MC_CMD_MUM_OUT_READ_ATB_SENSOR msgresponse */ +#define MC_CMD_MUM_OUT_READ_ATB_SENSOR_LEN 4 +#define MC_CMD_MUM_OUT_READ_ATB_SENSOR_RESULT_OFST 0 + +/* MC_CMD_MUM_OUT_QSFP_INIT msgresponse */ +#define MC_CMD_MUM_OUT_QSFP_INIT_LEN 0 + +/* MC_CMD_MUM_OUT_QSFP_RECONFIGURE msgresponse */ +#define MC_CMD_MUM_OUT_QSFP_RECONFIGURE_LEN 8 +#define MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LP_CAP_OFST 0 +#define MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_FLAGS_OFST 4 +#define MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_READY_LBN 0 +#define MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_READY_WIDTH 1 +#define MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LINK_UP_LBN 1 +#define MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LINK_UP_WIDTH 1 + +/* MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP msgresponse */ +#define MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP_LEN 4 +#define MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP_PORT_PHY_LP_CAP_OFST 0 + +/* MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO msgresponse */ +#define MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LENMIN 5 +#define MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LENMAX 252 +#define MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LEN(num) (4+1*(num)) +/* in bytes */ +#define MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATALEN_OFST 0 +#define MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_OFST 4 +#define MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_LEN 1 +#define MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_MINNUM 1 +#define MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_MAXNUM 248 + +/* MC_CMD_MUM_OUT_QSFP_FILL_STATS msgresponse */ +#define MC_CMD_MUM_OUT_QSFP_FILL_STATS_LEN 8 +#define MC_CMD_MUM_OUT_QSFP_FILL_STATS_PORT_PHY_STATS_PMA_PMD_LINK_UP_OFST 0 +#define MC_CMD_MUM_OUT_QSFP_FILL_STATS_PORT_PHY_STATS_PCS_LINK_UP_OFST 4 + +/* MC_CMD_MUM_OUT_QSFP_POLL_BIST msgresponse */ +#define MC_CMD_MUM_OUT_QSFP_POLL_BIST_LEN 4 +#define MC_CMD_MUM_OUT_QSFP_POLL_BIST_TEST_OFST 0 + /* MC_CMD_RESOURCE_SPECIFIER enum */ /* enum: Any */ #define MC_CMD_RESOURCE_INSTANCE_ANY 0xffffffff @@ -4203,6 +5092,30 @@ #define NVRAM_PARTITION_TYPE_PHY_MIN 0xa00 /* enum: End of range used for PHY partitions (low 8 bits are the PHY ID) */ #define NVRAM_PARTITION_TYPE_PHY_MAX 0xaff +/* enum: Primary FPGA partition */ +#define NVRAM_PARTITION_TYPE_FPGA 0xb00 +/* enum: Secondary FPGA partition */ +#define NVRAM_PARTITION_TYPE_FPGA_BACKUP 0xb01 +/* enum: FC firmware partition */ +#define NVRAM_PARTITION_TYPE_FC_FIRMWARE 0xb02 +/* enum: FC License partition */ +#define NVRAM_PARTITION_TYPE_FC_LICENSE 0xb03 +/* enum: Non-volatile log output partition for FC */ +#define NVRAM_PARTITION_TYPE_FC_LOG 0xb04 +/* enum: MUM firmware partition */ +#define NVRAM_PARTITION_TYPE_MUM_FIRMWARE 0xc00 +/* enum: MUM Non-volatile log output partition. */ +#define NVRAM_PARTITION_TYPE_MUM_LOG 0xc01 +/* enum: MUM Application table partition. */ +#define NVRAM_PARTITION_TYPE_MUM_APPTABLE 0xc02 +/* enum: MUM boot rom partition. */ +#define NVRAM_PARTITION_TYPE_MUM_BOOT_ROM 0xc03 +/* enum: MUM production signatures & calibration rom partition. */ +#define NVRAM_PARTITION_TYPE_MUM_PROD_ROM 0xc04 +/* enum: MUM user signatures & calibration rom partition. */ +#define NVRAM_PARTITION_TYPE_MUM_USER_ROM 0xc05 +/* enum: MUM fuses and lockbits partition. */ +#define NVRAM_PARTITION_TYPE_MUM_FUSELOCK 0xc06 /* enum: Start of reserved value range (firmware may use for any purpose) */ #define NVRAM_PARTITION_TYPE_RESERVED_VALUES_MIN 0xff00 /* enum: End of reserved value range (firmware may use for any purpose) */ @@ -4218,66 +5131,69 @@ #define LICENSED_APP_ID_LEN 4 #define LICENSED_APP_ID_ID_OFST 0 /* enum: OpenOnload */ -#define LICENSED_APP_ID_ONLOAD 0x1 +#define LICENSED_APP_ID_ONLOAD 0x1 /* enum: PTP timestamping */ -#define LICENSED_APP_ID_PTP 0x2 +#define LICENSED_APP_ID_PTP 0x2 /* enum: SolarCapture Pro */ -#define LICENSED_APP_ID_SOLARCAPTURE_PRO 0x4 +#define LICENSED_APP_ID_SOLARCAPTURE_PRO 0x4 +/* enum: SolarSecure filter engine */ +#define LICENSED_APP_ID_SOLARSECURE 0x8 +/* enum: Performance monitor */ +#define LICENSED_APP_ID_PERF_MONITOR 0x10 +/* enum: SolarCapture Live */ +#define LICENSED_APP_ID_SOLARCAPTURE_LIVE 0x20 +/* enum: Capture SolarSystem */ +#define LICENSED_APP_ID_CAPTURE_SOLARSYSTEM 0x40 +/* enum: Network Access Control */ +#define LICENSED_APP_ID_NETWORK_ACCESS_CONTROL 0x80 #define LICENSED_APP_ID_ID_LBN 0 #define LICENSED_APP_ID_ID_WIDTH 32 - -/***********************************/ -/* MC_CMD_GET_WORKAROUNDS - * Read the list of all implemented and all currently enabled workarounds. The - * enums here must correspond with those in MC_CMD_WORKAROUND. - */ -#define MC_CMD_GET_WORKAROUNDS 0x59 - -/* MC_CMD_GET_WORKAROUNDS_OUT msgresponse */ -#define MC_CMD_GET_WORKAROUNDS_OUT_LEN 8 -/* Each workaround is represented by a single bit according to the enums below. - */ -#define MC_CMD_GET_WORKAROUNDS_OUT_IMPLEMENTED_OFST 0 -#define MC_CMD_GET_WORKAROUNDS_OUT_ENABLED_OFST 4 -/* enum: Bug 17230 work around. */ -#define MC_CMD_GET_WORKAROUNDS_OUT_BUG17230 0x2 -/* enum: Bug 35388 work around (unsafe EVQ writes). */ -#define MC_CMD_GET_WORKAROUNDS_OUT_BUG35388 0x4 -/* enum: Bug35017 workaround (A64 tables must be identity map) */ -#define MC_CMD_GET_WORKAROUNDS_OUT_BUG35017 0x8 - - -/***********************************/ -/* MC_CMD_LINK_STATE_MODE - * Read/set link state mode of a VF - */ -#define MC_CMD_LINK_STATE_MODE 0x5c - -#define MC_CMD_0x5c_PRIVILEGE_CTG SRIOV_CTG_GENERAL - -/* MC_CMD_LINK_STATE_MODE_IN msgrequest */ -#define MC_CMD_LINK_STATE_MODE_IN_LEN 8 -/* The target function to have its link state mode read or set, must be a VF - * e.g. VF 1,3 = 0x00030001 - */ -#define MC_CMD_LINK_STATE_MODE_IN_FUNCTION_OFST 0 -#define MC_CMD_LINK_STATE_MODE_IN_FUNCTION_PF_LBN 0 -#define MC_CMD_LINK_STATE_MODE_IN_FUNCTION_PF_WIDTH 16 -#define MC_CMD_LINK_STATE_MODE_IN_FUNCTION_VF_LBN 16 -#define MC_CMD_LINK_STATE_MODE_IN_FUNCTION_VF_WIDTH 16 -/* New link state mode to be set */ -#define MC_CMD_LINK_STATE_MODE_IN_NEW_MODE_OFST 4 -#define MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_AUTO 0x0 /* enum */ -#define MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_UP 0x1 /* enum */ -#define MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_DOWN 0x2 /* enum */ -/* enum: Use this value to just read the existing setting without modifying it. - */ -#define MC_CMD_LINK_STATE_MODE_IN_DO_NOT_CHANGE 0xffffffff - -/* MC_CMD_LINK_STATE_MODE_OUT msgresponse */ -#define MC_CMD_LINK_STATE_MODE_OUT_LEN 4 -#define MC_CMD_LINK_STATE_MODE_OUT_OLD_MODE_OFST 0 +/* TX_TIMESTAMP_EVENT structuredef */ +#define TX_TIMESTAMP_EVENT_LEN 6 +/* lower 16 bits of timestamp data */ +#define TX_TIMESTAMP_EVENT_TSTAMP_DATA_LO_OFST 0 +#define TX_TIMESTAMP_EVENT_TSTAMP_DATA_LO_LEN 2 +#define TX_TIMESTAMP_EVENT_TSTAMP_DATA_LO_LBN 0 +#define TX_TIMESTAMP_EVENT_TSTAMP_DATA_LO_WIDTH 16 +/* Type of TX event, ordinary TX completion, low or high part of TX timestamp + */ +#define TX_TIMESTAMP_EVENT_TX_EV_TYPE_OFST 3 +#define TX_TIMESTAMP_EVENT_TX_EV_TYPE_LEN 1 +/* enum: This is a TX completion event, not a timestamp */ +#define TX_TIMESTAMP_EVENT_TX_EV_COMPLETION 0x0 +/* enum: This is the low part of a TX timestamp event */ +#define TX_TIMESTAMP_EVENT_TX_EV_TSTAMP_LO 0x51 +/* enum: This is the high part of a TX timestamp event */ +#define TX_TIMESTAMP_EVENT_TX_EV_TSTAMP_HI 0x52 +#define TX_TIMESTAMP_EVENT_TX_EV_TYPE_LBN 24 +#define TX_TIMESTAMP_EVENT_TX_EV_TYPE_WIDTH 8 +/* upper 16 bits of timestamp data */ +#define TX_TIMESTAMP_EVENT_TSTAMP_DATA_HI_OFST 4 +#define TX_TIMESTAMP_EVENT_TSTAMP_DATA_HI_LEN 2 +#define TX_TIMESTAMP_EVENT_TSTAMP_DATA_HI_LBN 32 +#define TX_TIMESTAMP_EVENT_TSTAMP_DATA_HI_WIDTH 16 + +/* RSS_MODE structuredef */ +#define RSS_MODE_LEN 1 +/* The RSS mode for a particular packet type is a value from 0 - 15 which can + * be considered as 4 bits selecting which fields are included in the hash. (A + * value 0 effectively disables RSS spreading for the packet type.) The YAML + * generation tools require this structure to be a whole number of bytes wide, + * but only 4 bits are relevant. + */ +#define RSS_MODE_HASH_SELECTOR_OFST 0 +#define RSS_MODE_HASH_SELECTOR_LEN 1 +#define RSS_MODE_HASH_SRC_ADDR_LBN 0 +#define RSS_MODE_HASH_SRC_ADDR_WIDTH 1 +#define RSS_MODE_HASH_DST_ADDR_LBN 1 +#define RSS_MODE_HASH_DST_ADDR_WIDTH 1 +#define RSS_MODE_HASH_SRC_PORT_LBN 2 +#define RSS_MODE_HASH_SRC_PORT_WIDTH 1 +#define RSS_MODE_HASH_DST_PORT_LBN 3 +#define RSS_MODE_HASH_DST_PORT_WIDTH 1 +#define RSS_MODE_HASH_SELECTOR_LBN 0 +#define RSS_MODE_HASH_SELECTOR_WIDTH 8 /***********************************/ @@ -4413,7 +5329,9 @@ #define MC_CMD_0x81_PRIVILEGE_CTG SRIOV_CTG_GENERAL -/* MC_CMD_INIT_RXQ_IN msgrequest */ +/* MC_CMD_INIT_RXQ_IN msgrequest: Legacy RXQ_INIT request. Use extended version + * in new code. + */ #define MC_CMD_INIT_RXQ_IN_LENMIN 36 #define MC_CMD_INIT_RXQ_IN_LENMAX 252 #define MC_CMD_INIT_RXQ_IN_LEN(num) (28+8*(num)) @@ -4456,9 +5374,73 @@ #define MC_CMD_INIT_RXQ_IN_DMA_ADDR_MINNUM 1 #define MC_CMD_INIT_RXQ_IN_DMA_ADDR_MAXNUM 28 +/* MC_CMD_INIT_RXQ_EXT_IN msgrequest: Extended RXQ_INIT with additional mode + * flags + */ +#define MC_CMD_INIT_RXQ_EXT_IN_LEN 544 +/* Size, in entries */ +#define MC_CMD_INIT_RXQ_EXT_IN_SIZE_OFST 0 +/* The EVQ to send events to. This is an index originally specified to INIT_EVQ + */ +#define MC_CMD_INIT_RXQ_EXT_IN_TARGET_EVQ_OFST 4 +/* The value to put in the event data. Check hardware spec. for valid range. */ +#define MC_CMD_INIT_RXQ_EXT_IN_LABEL_OFST 8 +/* Desired instance. Must be set to a specific instance, which is a function + * local queue index. + */ +#define MC_CMD_INIT_RXQ_EXT_IN_INSTANCE_OFST 12 +/* There will be more flags here. */ +#define MC_CMD_INIT_RXQ_EXT_IN_FLAGS_OFST 16 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_BUFF_MODE_LBN 0 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_BUFF_MODE_WIDTH 1 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_HDR_SPLIT_LBN 1 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_HDR_SPLIT_WIDTH 1 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_TIMESTAMP_LBN 2 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_TIMESTAMP_WIDTH 1 +#define MC_CMD_INIT_RXQ_EXT_IN_CRC_MODE_LBN 3 +#define MC_CMD_INIT_RXQ_EXT_IN_CRC_MODE_WIDTH 4 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_CHAIN_LBN 7 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_CHAIN_WIDTH 1 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_PREFIX_LBN 8 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_PREFIX_WIDTH 1 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_DISABLE_SCATTER_LBN 9 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_DISABLE_SCATTER_WIDTH 1 +#define MC_CMD_INIT_RXQ_EXT_IN_DMA_MODE_LBN 10 +#define MC_CMD_INIT_RXQ_EXT_IN_DMA_MODE_WIDTH 4 +/* enum: One packet per descriptor (for normal networking) */ +#define MC_CMD_INIT_RXQ_EXT_IN_SINGLE_PACKET 0x0 +/* enum: Pack multiple packets into large descriptors (for SolarCapture) */ +#define MC_CMD_INIT_RXQ_EXT_IN_PACKED_STREAM 0x1 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_SNAPSHOT_MODE_LBN 14 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_SNAPSHOT_MODE_WIDTH 1 +#define MC_CMD_INIT_RXQ_EXT_IN_PACKED_STREAM_BUFF_SIZE_LBN 15 +#define MC_CMD_INIT_RXQ_EXT_IN_PACKED_STREAM_BUFF_SIZE_WIDTH 3 +#define MC_CMD_INIT_RXQ_EXT_IN_PS_BUFF_1M 0x0 /* enum */ +#define MC_CMD_INIT_RXQ_EXT_IN_PS_BUFF_512K 0x1 /* enum */ +#define MC_CMD_INIT_RXQ_EXT_IN_PS_BUFF_256K 0x2 /* enum */ +#define MC_CMD_INIT_RXQ_EXT_IN_PS_BUFF_128K 0x3 /* enum */ +#define MC_CMD_INIT_RXQ_EXT_IN_PS_BUFF_64K 0x4 /* enum */ +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_WANT_OUTER_CLASSES_LBN 18 +#define MC_CMD_INIT_RXQ_EXT_IN_FLAG_WANT_OUTER_CLASSES_WIDTH 1 +/* Owner ID to use if in buffer mode (zero if physical) */ +#define MC_CMD_INIT_RXQ_EXT_IN_OWNER_ID_OFST 20 +/* The port ID associated with the v-adaptor which should contain this DMAQ. */ +#define MC_CMD_INIT_RXQ_EXT_IN_PORT_ID_OFST 24 +/* 64-bit address of 4k of 4k-aligned host memory buffer */ +#define MC_CMD_INIT_RXQ_EXT_IN_DMA_ADDR_OFST 28 +#define MC_CMD_INIT_RXQ_EXT_IN_DMA_ADDR_LEN 8 +#define MC_CMD_INIT_RXQ_EXT_IN_DMA_ADDR_LO_OFST 28 +#define MC_CMD_INIT_RXQ_EXT_IN_DMA_ADDR_HI_OFST 32 +#define MC_CMD_INIT_RXQ_EXT_IN_DMA_ADDR_NUM 64 +/* Maximum length of packet to receive, if SNAPSHOT_MODE flag is set */ +#define MC_CMD_INIT_RXQ_EXT_IN_SNAPSHOT_LENGTH_OFST 540 + /* MC_CMD_INIT_RXQ_OUT msgresponse */ #define MC_CMD_INIT_RXQ_OUT_LEN 0 +/* MC_CMD_INIT_RXQ_EXT_OUT msgresponse */ +#define MC_CMD_INIT_RXQ_EXT_OUT_LEN 0 + /***********************************/ /* MC_CMD_INIT_TXQ @@ -4467,7 +5449,9 @@ #define MC_CMD_0x82_PRIVILEGE_CTG SRIOV_CTG_GENERAL -/* MC_CMD_INIT_TXQ_IN msgrequest */ +/* MC_CMD_INIT_TXQ_IN msgrequest: Legacy INIT_TXQ request. Use extended version + * in new code. + */ #define MC_CMD_INIT_TXQ_IN_LENMIN 36 #define MC_CMD_INIT_TXQ_IN_LENMAX 252 #define MC_CMD_INIT_TXQ_IN_LEN(num) (28+8*(num)) @@ -4499,6 +5483,10 @@ #define MC_CMD_INIT_TXQ_IN_FLAG_TIMESTAMP_WIDTH 1 #define MC_CMD_INIT_TXQ_IN_FLAG_PACER_BYPASS_LBN 9 #define MC_CMD_INIT_TXQ_IN_FLAG_PACER_BYPASS_WIDTH 1 +#define MC_CMD_INIT_TXQ_IN_FLAG_INNER_IP_CSUM_EN_LBN 10 +#define MC_CMD_INIT_TXQ_IN_FLAG_INNER_IP_CSUM_EN_WIDTH 1 +#define MC_CMD_INIT_TXQ_IN_FLAG_INNER_TCP_CSUM_EN_LBN 11 +#define MC_CMD_INIT_TXQ_IN_FLAG_INNER_TCP_CSUM_EN_WIDTH 1 /* Owner ID to use if in buffer mode (zero if physical) */ #define MC_CMD_INIT_TXQ_IN_OWNER_ID_OFST 20 /* The port ID associated with the v-adaptor which should contain this DMAQ. */ @@ -4511,6 +5499,60 @@ #define MC_CMD_INIT_TXQ_IN_DMA_ADDR_MINNUM 1 #define MC_CMD_INIT_TXQ_IN_DMA_ADDR_MAXNUM 28 +/* MC_CMD_INIT_TXQ_EXT_IN msgrequest: Extended INIT_TXQ with additional mode + * flags + */ +#define MC_CMD_INIT_TXQ_EXT_IN_LEN 544 +/* Size, in entries */ +#define MC_CMD_INIT_TXQ_EXT_IN_SIZE_OFST 0 +/* The EVQ to send events to. This is an index originally specified to + * INIT_EVQ. + */ +#define MC_CMD_INIT_TXQ_EXT_IN_TARGET_EVQ_OFST 4 +/* The value to put in the event data. Check hardware spec. for valid range. */ +#define MC_CMD_INIT_TXQ_EXT_IN_LABEL_OFST 8 +/* Desired instance. Must be set to a specific instance, which is a function + * local queue index. + */ +#define MC_CMD_INIT_TXQ_EXT_IN_INSTANCE_OFST 12 +/* There will be more flags here. */ +#define MC_CMD_INIT_TXQ_EXT_IN_FLAGS_OFST 16 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_BUFF_MODE_LBN 0 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_BUFF_MODE_WIDTH 1 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_IP_CSUM_DIS_LBN 1 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_IP_CSUM_DIS_WIDTH 1 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_TCP_CSUM_DIS_LBN 2 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_TCP_CSUM_DIS_WIDTH 1 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_TCP_UDP_ONLY_LBN 3 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_TCP_UDP_ONLY_WIDTH 1 +#define MC_CMD_INIT_TXQ_EXT_IN_CRC_MODE_LBN 4 +#define MC_CMD_INIT_TXQ_EXT_IN_CRC_MODE_WIDTH 4 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_TIMESTAMP_LBN 8 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_TIMESTAMP_WIDTH 1 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_PACER_BYPASS_LBN 9 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_PACER_BYPASS_WIDTH 1 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_IP_CSUM_EN_LBN 10 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_IP_CSUM_EN_WIDTH 1 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_TCP_CSUM_EN_LBN 11 +#define MC_CMD_INIT_TXQ_EXT_IN_FLAG_INNER_TCP_CSUM_EN_WIDTH 1 +/* Owner ID to use if in buffer mode (zero if physical) */ +#define MC_CMD_INIT_TXQ_EXT_IN_OWNER_ID_OFST 20 +/* The port ID associated with the v-adaptor which should contain this DMAQ. */ +#define MC_CMD_INIT_TXQ_EXT_IN_PORT_ID_OFST 24 +/* 64-bit address of 4k of 4k-aligned host memory buffer */ +#define MC_CMD_INIT_TXQ_EXT_IN_DMA_ADDR_OFST 28 +#define MC_CMD_INIT_TXQ_EXT_IN_DMA_ADDR_LEN 8 +#define MC_CMD_INIT_TXQ_EXT_IN_DMA_ADDR_LO_OFST 28 +#define MC_CMD_INIT_TXQ_EXT_IN_DMA_ADDR_HI_OFST 32 +#define MC_CMD_INIT_TXQ_EXT_IN_DMA_ADDR_MINNUM 1 +#define MC_CMD_INIT_TXQ_EXT_IN_DMA_ADDR_MAXNUM 64 +/* Flags related to Qbb flow control mode. */ +#define MC_CMD_INIT_TXQ_EXT_IN_QBB_FLAGS_OFST 540 +#define MC_CMD_INIT_TXQ_EXT_IN_QBB_ENABLE_LBN 0 +#define MC_CMD_INIT_TXQ_EXT_IN_QBB_ENABLE_WIDTH 1 +#define MC_CMD_INIT_TXQ_EXT_IN_QBB_PRIORITY_LBN 1 +#define MC_CMD_INIT_TXQ_EXT_IN_QBB_PRIORITY_WIDTH 3 + /* MC_CMD_INIT_TXQ_OUT msgresponse */ #define MC_CMD_INIT_TXQ_OUT_LEN 0 @@ -4617,6 +5659,132 @@ /* MC_CMD_PROXY_CMD_OUT msgresponse */ #define MC_CMD_PROXY_CMD_OUT_LEN 0 +/* MC_PROXY_STATUS_BUFFER structuredef: Host memory status buffer used to + * manage proxied requests + */ +#define MC_PROXY_STATUS_BUFFER_LEN 16 +/* Handle allocated by the firmware for this proxy transaction */ +#define MC_PROXY_STATUS_BUFFER_HANDLE_OFST 0 +/* enum: An invalid handle. */ +#define MC_PROXY_STATUS_BUFFER_HANDLE_INVALID 0x0 +#define MC_PROXY_STATUS_BUFFER_HANDLE_LBN 0 +#define MC_PROXY_STATUS_BUFFER_HANDLE_WIDTH 32 +/* The requesting physical function number */ +#define MC_PROXY_STATUS_BUFFER_PF_OFST 4 +#define MC_PROXY_STATUS_BUFFER_PF_LEN 2 +#define MC_PROXY_STATUS_BUFFER_PF_LBN 32 +#define MC_PROXY_STATUS_BUFFER_PF_WIDTH 16 +/* The requesting virtual function number. Set to VF_NULL if the target is a + * PF. + */ +#define MC_PROXY_STATUS_BUFFER_VF_OFST 6 +#define MC_PROXY_STATUS_BUFFER_VF_LEN 2 +#define MC_PROXY_STATUS_BUFFER_VF_LBN 48 +#define MC_PROXY_STATUS_BUFFER_VF_WIDTH 16 +/* The target function RID. */ +#define MC_PROXY_STATUS_BUFFER_RID_OFST 8 +#define MC_PROXY_STATUS_BUFFER_RID_LEN 2 +#define MC_PROXY_STATUS_BUFFER_RID_LBN 64 +#define MC_PROXY_STATUS_BUFFER_RID_WIDTH 16 +/* The status of the proxy as described in MC_CMD_PROXY_COMPLETE. */ +#define MC_PROXY_STATUS_BUFFER_STATUS_OFST 10 +#define MC_PROXY_STATUS_BUFFER_STATUS_LEN 2 +#define MC_PROXY_STATUS_BUFFER_STATUS_LBN 80 +#define MC_PROXY_STATUS_BUFFER_STATUS_WIDTH 16 +/* If a request is authorized rather than carried out by the host, this is the + * elevated privilege mask granted to the requesting function. + */ +#define MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_OFST 12 +#define MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_LBN 96 +#define MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_WIDTH 32 + + +/***********************************/ +/* MC_CMD_PROXY_CONFIGURE + * Enable/disable authorization of MCDI requests from unprivileged functions by + * a designated admin function + */ +#define MC_CMD_PROXY_CONFIGURE 0x58 + +#define MC_CMD_0x58_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_PROXY_CONFIGURE_IN msgrequest */ +#define MC_CMD_PROXY_CONFIGURE_IN_LEN 108 +#define MC_CMD_PROXY_CONFIGURE_IN_FLAGS_OFST 0 +#define MC_CMD_PROXY_CONFIGURE_IN_ENABLE_LBN 0 +#define MC_CMD_PROXY_CONFIGURE_IN_ENABLE_WIDTH 1 +/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS + * of blocks, each of the size REQUEST_BLOCK_SIZE. + */ +#define MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_OFST 4 +#define MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LEN 8 +#define MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LO_OFST 4 +#define MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_HI_OFST 8 +/* Must be a power of 2 */ +#define MC_CMD_PROXY_CONFIGURE_IN_STATUS_BLOCK_SIZE_OFST 12 +/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS + * of blocks, each of the size REPLY_BLOCK_SIZE. + */ +#define MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_OFST 16 +#define MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LEN 8 +#define MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LO_OFST 16 +#define MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_HI_OFST 20 +/* Must be a power of 2 */ +#define MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BLOCK_SIZE_OFST 24 +/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS + * of blocks, each of the size STATUS_BLOCK_SIZE. This buffer is only needed if + * host intends to complete proxied operations by using MC_CMD_PROXY_CMD. + */ +#define MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_OFST 28 +#define MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LEN 8 +#define MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LO_OFST 28 +#define MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_HI_OFST 32 +/* Must be a power of 2, or zero if this buffer is not provided */ +#define MC_CMD_PROXY_CONFIGURE_IN_REPLY_BLOCK_SIZE_OFST 36 +/* Applies to all three buffers */ +#define MC_CMD_PROXY_CONFIGURE_IN_NUM_BLOCKS_OFST 40 +/* A bit mask defining which MCDI operations may be proxied */ +#define MC_CMD_PROXY_CONFIGURE_IN_ALLOWED_MCDI_MASK_OFST 44 +#define MC_CMD_PROXY_CONFIGURE_IN_ALLOWED_MCDI_MASK_LEN 64 + +/* MC_CMD_PROXY_CONFIGURE_OUT msgresponse */ +#define MC_CMD_PROXY_CONFIGURE_OUT_LEN 0 + + +/***********************************/ +/* MC_CMD_PROXY_COMPLETE + * Tells FW that a requested proxy operation has either been completed (by + * using MC_CMD_PROXY_CMD) or authorized/declined. May only be sent by the + * function that enabled proxying/authorization (by using + * MC_CMD_PROXY_CONFIGURE). + */ +#define MC_CMD_PROXY_COMPLETE 0x5f + +#define MC_CMD_0x5f_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_PROXY_COMPLETE_IN msgrequest */ +#define MC_CMD_PROXY_COMPLETE_IN_LEN 12 +#define MC_CMD_PROXY_COMPLETE_IN_BLOCK_INDEX_OFST 0 +#define MC_CMD_PROXY_COMPLETE_IN_STATUS_OFST 4 +/* enum: The operation has been completed by using MC_CMD_PROXY_CMD, the reply + * is stored in the REPLY_BUFF. + */ +#define MC_CMD_PROXY_COMPLETE_IN_COMPLETE 0x0 +/* enum: The operation has been authorized. The originating function may now + * try again. + */ +#define MC_CMD_PROXY_COMPLETE_IN_AUTHORIZED 0x1 +/* enum: The operation has been declined. */ +#define MC_CMD_PROXY_COMPLETE_IN_DECLINED 0x2 +/* enum: The authorization failed because the relevant application did not + * respond in time. + */ +#define MC_CMD_PROXY_COMPLETE_IN_TIMEDOUT 0x3 +#define MC_CMD_PROXY_COMPLETE_IN_HANDLE_OFST 8 + +/* MC_CMD_PROXY_COMPLETE_OUT msgresponse */ +#define MC_CMD_PROXY_COMPLETE_OUT_LEN 0 + /***********************************/ /* MC_CMD_ALLOC_BUFTBL_CHUNK @@ -4688,6 +5856,44 @@ /* MC_CMD_FREE_BUFTBL_CHUNK_OUT msgresponse */ #define MC_CMD_FREE_BUFTBL_CHUNK_OUT_LEN 0 +/* PORT_CONFIG_ENTRY structuredef */ +#define PORT_CONFIG_ENTRY_LEN 16 +/* External port number (label) */ +#define PORT_CONFIG_ENTRY_EXT_NUMBER_OFST 0 +#define PORT_CONFIG_ENTRY_EXT_NUMBER_LEN 1 +#define PORT_CONFIG_ENTRY_EXT_NUMBER_LBN 0 +#define PORT_CONFIG_ENTRY_EXT_NUMBER_WIDTH 8 +/* Port core location */ +#define PORT_CONFIG_ENTRY_CORE_OFST 1 +#define PORT_CONFIG_ENTRY_CORE_LEN 1 +#define PORT_CONFIG_ENTRY_STANDALONE 0x0 /* enum */ +#define PORT_CONFIG_ENTRY_MASTER 0x1 /* enum */ +#define PORT_CONFIG_ENTRY_SLAVE 0x2 /* enum */ +#define PORT_CONFIG_ENTRY_CORE_LBN 8 +#define PORT_CONFIG_ENTRY_CORE_WIDTH 8 +/* Internal number (HW resource) relative to the core */ +#define PORT_CONFIG_ENTRY_INT_NUMBER_OFST 2 +#define PORT_CONFIG_ENTRY_INT_NUMBER_LEN 1 +#define PORT_CONFIG_ENTRY_INT_NUMBER_LBN 16 +#define PORT_CONFIG_ENTRY_INT_NUMBER_WIDTH 8 +/* Reserved */ +#define PORT_CONFIG_ENTRY_RSVD_OFST 3 +#define PORT_CONFIG_ENTRY_RSVD_LEN 1 +#define PORT_CONFIG_ENTRY_RSVD_LBN 24 +#define PORT_CONFIG_ENTRY_RSVD_WIDTH 8 +/* Bitmask of KR lanes used by the port */ +#define PORT_CONFIG_ENTRY_LANES_OFST 4 +#define PORT_CONFIG_ENTRY_LANES_LBN 32 +#define PORT_CONFIG_ENTRY_LANES_WIDTH 32 +/* Port capabilities (MC_CMD_PHY_CAP_*) */ +#define PORT_CONFIG_ENTRY_SUPPORTED_CAPS_OFST 8 +#define PORT_CONFIG_ENTRY_SUPPORTED_CAPS_LBN 64 +#define PORT_CONFIG_ENTRY_SUPPORTED_CAPS_WIDTH 32 +/* Reserved (align to 16 bytes) */ +#define PORT_CONFIG_ENTRY_RSVD2_OFST 12 +#define PORT_CONFIG_ENTRY_RSVD2_LBN 96 +#define PORT_CONFIG_ENTRY_RSVD2_WIDTH 32 + /***********************************/ /* MC_CMD_FILTER_OP @@ -4759,9 +5965,9 @@ #define MC_CMD_FILTER_OP_IN_RX_DEST_HOST 0x1 /* enum: receive to MC */ #define MC_CMD_FILTER_OP_IN_RX_DEST_MC 0x2 -/* enum: loop back to port 0 TX MAC */ +/* enum: loop back to TXDP 0 */ #define MC_CMD_FILTER_OP_IN_RX_DEST_TX0 0x3 -/* enum: loop back to port 1 TX MAC */ +/* enum: loop back to TXDP 1 */ #define MC_CMD_FILTER_OP_IN_RX_DEST_TX1 0x4 /* receive queue handle (for multiple queue modes, this is the base queue) */ #define MC_CMD_FILTER_OP_IN_RX_QUEUE_OFST 24 @@ -4778,9 +5984,7 @@ #define MC_CMD_FILTER_OP_IN_RX_MODE_TEST_NEVER_MATCH 0x80000000 /* RSS context (for RX_MODE_RSS) or .1p mapping handle (for * RX_MODE_DOT1P_MAPPING), as returned by MC_CMD_RSS_CONTEXT_ALLOC or - * MC_CMD_DOT1P_MAPPING_ALLOC. Note that these handles should be considered - * opaque to the host, although a value of 0xFFFFFFFF is guaranteed never to be - * a valid handle. + * MC_CMD_DOT1P_MAPPING_ALLOC. */ #define MC_CMD_FILTER_OP_IN_RX_CONTEXT_OFST 32 /* transmit domain (reserved; set to 0) */ @@ -4835,6 +6039,235 @@ #define MC_CMD_FILTER_OP_IN_DST_IP_OFST 92 #define MC_CMD_FILTER_OP_IN_DST_IP_LEN 16 +/* MC_CMD_FILTER_OP_EXT_IN msgrequest: Extension to MC_CMD_FILTER_OP_IN to + * include handling of VXLAN/NVGRE encapsulated frame filtering (which is + * supported on Medford only). + */ +#define MC_CMD_FILTER_OP_EXT_IN_LEN 172 +/* identifies the type of operation requested */ +#define MC_CMD_FILTER_OP_EXT_IN_OP_OFST 0 +/* Enum values, see field(s): */ +/* MC_CMD_FILTER_OP_IN/OP */ +/* filter handle (for remove / unsubscribe operations) */ +#define MC_CMD_FILTER_OP_EXT_IN_HANDLE_OFST 4 +#define MC_CMD_FILTER_OP_EXT_IN_HANDLE_LEN 8 +#define MC_CMD_FILTER_OP_EXT_IN_HANDLE_LO_OFST 4 +#define MC_CMD_FILTER_OP_EXT_IN_HANDLE_HI_OFST 8 +/* The port ID associated with the v-adaptor which should contain this filter. + */ +#define MC_CMD_FILTER_OP_EXT_IN_PORT_ID_OFST 12 +/* fields to include in match criteria */ +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_FIELDS_OFST 16 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_SRC_IP_LBN 0 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_SRC_IP_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_DST_IP_LBN 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_DST_IP_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_SRC_MAC_LBN 2 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_SRC_MAC_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_SRC_PORT_LBN 3 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_SRC_PORT_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_DST_MAC_LBN 4 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_DST_MAC_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_DST_PORT_LBN 5 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_DST_PORT_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_ETHER_TYPE_LBN 6 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_ETHER_TYPE_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_INNER_VLAN_LBN 7 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_INNER_VLAN_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_OUTER_VLAN_LBN 8 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_OUTER_VLAN_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IP_PROTO_LBN 9 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IP_PROTO_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_FWDEF0_LBN 10 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_FWDEF0_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_VNI_OR_VSID_LBN 11 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_VNI_OR_VSID_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_SRC_IP_LBN 12 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_SRC_IP_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_DST_IP_LBN 13 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_DST_IP_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_SRC_MAC_LBN 14 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_SRC_MAC_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_SRC_PORT_LBN 15 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_SRC_PORT_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_DST_MAC_LBN 16 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_DST_MAC_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_DST_PORT_LBN 17 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_DST_PORT_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_ETHER_TYPE_LBN 18 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_ETHER_TYPE_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_INNER_VLAN_LBN 19 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_INNER_VLAN_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_OUTER_VLAN_LBN 20 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_OUTER_VLAN_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_IP_PROTO_LBN 21 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_IP_PROTO_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_FWDEF0_LBN 22 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_FWDEF0_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_FWDEF1_LBN 23 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_FWDEF1_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_UNKNOWN_MCAST_DST_LBN 24 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_UNKNOWN_MCAST_DST_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_UNKNOWN_UCAST_DST_LBN 25 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_IFRM_UNKNOWN_UCAST_DST_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_UNKNOWN_MCAST_DST_LBN 30 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_UNKNOWN_MCAST_DST_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_UNKNOWN_UCAST_DST_LBN 31 +#define MC_CMD_FILTER_OP_EXT_IN_MATCH_UNKNOWN_UCAST_DST_WIDTH 1 +/* receive destination */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_DEST_OFST 20 +/* enum: drop packets */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_DEST_DROP 0x0 +/* enum: receive to host */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_DEST_HOST 0x1 +/* enum: receive to MC */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_DEST_MC 0x2 +/* enum: loop back to TXDP 0 */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_DEST_TX0 0x3 +/* enum: loop back to TXDP 1 */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_DEST_TX1 0x4 +/* receive queue handle (for multiple queue modes, this is the base queue) */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_QUEUE_OFST 24 +/* receive mode */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_MODE_OFST 28 +/* enum: receive to just the specified queue */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_MODE_SIMPLE 0x0 +/* enum: receive to multiple queues using RSS context */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_MODE_RSS 0x1 +/* enum: receive to multiple queues using .1p mapping */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_MODE_DOT1P_MAPPING 0x2 +/* enum: install a filter entry that will never match; for test purposes only + */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_MODE_TEST_NEVER_MATCH 0x80000000 +/* RSS context (for RX_MODE_RSS) or .1p mapping handle (for + * RX_MODE_DOT1P_MAPPING), as returned by MC_CMD_RSS_CONTEXT_ALLOC or + * MC_CMD_DOT1P_MAPPING_ALLOC. + */ +#define MC_CMD_FILTER_OP_EXT_IN_RX_CONTEXT_OFST 32 +/* transmit domain (reserved; set to 0) */ +#define MC_CMD_FILTER_OP_EXT_IN_TX_DOMAIN_OFST 36 +/* transmit destination (either set the MAC and/or PM bits for explicit + * control, or set this field to TX_DEST_DEFAULT for sensible default + * behaviour) + */ +#define MC_CMD_FILTER_OP_EXT_IN_TX_DEST_OFST 40 +/* enum: request default behaviour (based on filter type) */ +#define MC_CMD_FILTER_OP_EXT_IN_TX_DEST_DEFAULT 0xffffffff +#define MC_CMD_FILTER_OP_EXT_IN_TX_DEST_MAC_LBN 0 +#define MC_CMD_FILTER_OP_EXT_IN_TX_DEST_MAC_WIDTH 1 +#define MC_CMD_FILTER_OP_EXT_IN_TX_DEST_PM_LBN 1 +#define MC_CMD_FILTER_OP_EXT_IN_TX_DEST_PM_WIDTH 1 +/* source MAC address to match (as bytes in network order) */ +#define MC_CMD_FILTER_OP_EXT_IN_SRC_MAC_OFST 44 +#define MC_CMD_FILTER_OP_EXT_IN_SRC_MAC_LEN 6 +/* source port to match (as bytes in network order) */ +#define MC_CMD_FILTER_OP_EXT_IN_SRC_PORT_OFST 50 +#define MC_CMD_FILTER_OP_EXT_IN_SRC_PORT_LEN 2 +/* destination MAC address to match (as bytes in network order) */ +#define MC_CMD_FILTER_OP_EXT_IN_DST_MAC_OFST 52 +#define MC_CMD_FILTER_OP_EXT_IN_DST_MAC_LEN 6 +/* destination port to match (as bytes in network order) */ +#define MC_CMD_FILTER_OP_EXT_IN_DST_PORT_OFST 58 +#define MC_CMD_FILTER_OP_EXT_IN_DST_PORT_LEN 2 +/* Ethernet type to match (as bytes in network order) */ +#define MC_CMD_FILTER_OP_EXT_IN_ETHER_TYPE_OFST 60 +#define MC_CMD_FILTER_OP_EXT_IN_ETHER_TYPE_LEN 2 +/* Inner VLAN tag to match (as bytes in network order) */ +#define MC_CMD_FILTER_OP_EXT_IN_INNER_VLAN_OFST 62 +#define MC_CMD_FILTER_OP_EXT_IN_INNER_VLAN_LEN 2 +/* Outer VLAN tag to match (as bytes in network order) */ +#define MC_CMD_FILTER_OP_EXT_IN_OUTER_VLAN_OFST 64 +#define MC_CMD_FILTER_OP_EXT_IN_OUTER_VLAN_LEN 2 +/* IP protocol to match (in low byte; set high byte to 0) */ +#define MC_CMD_FILTER_OP_EXT_IN_IP_PROTO_OFST 66 +#define MC_CMD_FILTER_OP_EXT_IN_IP_PROTO_LEN 2 +/* Firmware defined register 0 to match (reserved; set to 0) */ +#define MC_CMD_FILTER_OP_EXT_IN_FWDEF0_OFST 68 +/* VNI (for VXLAN/Geneve, when IP protocol is UDP) or VSID (for NVGRE, when IP + * protocol is GRE) to match (as bytes in network order; set last byte to 0 for + * VXLAN/NVGRE, or 1 for Geneve) + */ +#define MC_CMD_FILTER_OP_EXT_IN_VNI_OR_VSID_OFST 72 +#define MC_CMD_FILTER_OP_EXT_IN_VNI_VALUE_LBN 0 +#define MC_CMD_FILTER_OP_EXT_IN_VNI_VALUE_WIDTH 24 +#define MC_CMD_FILTER_OP_EXT_IN_VNI_TYPE_LBN 24 +#define MC_CMD_FILTER_OP_EXT_IN_VNI_TYPE_WIDTH 8 +/* enum: Match VXLAN traffic with this VNI */ +#define MC_CMD_FILTER_OP_EXT_IN_VNI_TYPE_VXLAN 0x0 +/* enum: Match Geneve traffic with this VNI */ +#define MC_CMD_FILTER_OP_EXT_IN_VNI_TYPE_GENEVE 0x1 +/* enum: Reserved for experimental development use */ +#define MC_CMD_FILTER_OP_EXT_IN_VNI_TYPE_EXPERIMENTAL 0xfe +#define MC_CMD_FILTER_OP_EXT_IN_VSID_VALUE_LBN 0 +#define MC_CMD_FILTER_OP_EXT_IN_VSID_VALUE_WIDTH 24 +#define MC_CMD_FILTER_OP_EXT_IN_VSID_TYPE_LBN 24 +#define MC_CMD_FILTER_OP_EXT_IN_VSID_TYPE_WIDTH 8 +/* enum: Match NVGRE traffic with this VSID */ +#define MC_CMD_FILTER_OP_EXT_IN_VSID_TYPE_NVGRE 0x0 +/* source IP address to match (as bytes in network order; set last 12 bytes to + * 0 for IPv4 address) + */ +#define MC_CMD_FILTER_OP_EXT_IN_SRC_IP_OFST 76 +#define MC_CMD_FILTER_OP_EXT_IN_SRC_IP_LEN 16 +/* destination IP address to match (as bytes in network order; set last 12 + * bytes to 0 for IPv4 address) + */ +#define MC_CMD_FILTER_OP_EXT_IN_DST_IP_OFST 92 +#define MC_CMD_FILTER_OP_EXT_IN_DST_IP_LEN 16 +/* VXLAN/NVGRE inner frame source MAC address to match (as bytes in network + * order) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_SRC_MAC_OFST 108 +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_SRC_MAC_LEN 6 +/* VXLAN/NVGRE inner frame source port to match (as bytes in network order) */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_SRC_PORT_OFST 114 +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_SRC_PORT_LEN 2 +/* VXLAN/NVGRE inner frame destination MAC address to match (as bytes in + * network order) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_DST_MAC_OFST 116 +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_DST_MAC_LEN 6 +/* VXLAN/NVGRE inner frame destination port to match (as bytes in network + * order) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_DST_PORT_OFST 122 +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_DST_PORT_LEN 2 +/* VXLAN/NVGRE inner frame Ethernet type to match (as bytes in network order) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_ETHER_TYPE_OFST 124 +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_ETHER_TYPE_LEN 2 +/* VXLAN/NVGRE inner frame Inner VLAN tag to match (as bytes in network order) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_INNER_VLAN_OFST 126 +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_INNER_VLAN_LEN 2 +/* VXLAN/NVGRE inner frame Outer VLAN tag to match (as bytes in network order) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_OUTER_VLAN_OFST 128 +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_OUTER_VLAN_LEN 2 +/* VXLAN/NVGRE inner frame IP protocol to match (in low byte; set high byte to + * 0) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_IP_PROTO_OFST 130 +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_IP_PROTO_LEN 2 +/* VXLAN/NVGRE inner frame Firmware defined register 0 to match (reserved; set + * to 0) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_FWDEF0_OFST 132 +/* VXLAN/NVGRE inner frame Firmware defined register 1 to match (reserved; set + * to 0) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_FWDEF1_OFST 136 +/* VXLAN/NVGRE inner frame source IP address to match (as bytes in network + * order; set last 12 bytes to 0 for IPv4 address) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_SRC_IP_OFST 140 +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_SRC_IP_LEN 16 +/* VXLAN/NVGRE inner frame destination IP address to match (as bytes in network + * order; set last 12 bytes to 0 for IPv4 address) + */ +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_DST_IP_OFST 156 +#define MC_CMD_FILTER_OP_EXT_IN_IFRM_DST_IP_LEN 16 + /* MC_CMD_FILTER_OP_OUT msgresponse */ #define MC_CMD_FILTER_OP_OUT_LEN 12 /* identifies the type of operation requested */ @@ -4849,6 +6282,27 @@ #define MC_CMD_FILTER_OP_OUT_HANDLE_LEN 8 #define MC_CMD_FILTER_OP_OUT_HANDLE_LO_OFST 4 #define MC_CMD_FILTER_OP_OUT_HANDLE_HI_OFST 8 +/* enum: guaranteed invalid filter handle (low 32 bits) */ +#define MC_CMD_FILTER_OP_OUT_HANDLE_LO_INVALID 0xffffffff +/* enum: guaranteed invalid filter handle (high 32 bits) */ +#define MC_CMD_FILTER_OP_OUT_HANDLE_HI_INVALID 0xffffffff + +/* MC_CMD_FILTER_OP_EXT_OUT msgresponse */ +#define MC_CMD_FILTER_OP_EXT_OUT_LEN 12 +/* identifies the type of operation requested */ +#define MC_CMD_FILTER_OP_EXT_OUT_OP_OFST 0 +/* Enum values, see field(s): */ +/* MC_CMD_FILTER_OP_EXT_IN/OP */ +/* Returned filter handle (for insert / subscribe operations). Note that these + * handles should be considered opaque to the host, although a value of + * 0xFFFFFFFF_FFFFFFFF is guaranteed never to be a valid handle. + */ +#define MC_CMD_FILTER_OP_EXT_OUT_HANDLE_OFST 4 +#define MC_CMD_FILTER_OP_EXT_OUT_HANDLE_LEN 8 +#define MC_CMD_FILTER_OP_EXT_OUT_HANDLE_LO_OFST 4 +#define MC_CMD_FILTER_OP_EXT_OUT_HANDLE_HI_OFST 8 +/* Enum values, see field(s): */ +/* MC_CMD_FILTER_OP_OUT/HANDLE */ /***********************************/ @@ -4865,6 +6319,10 @@ #define MC_CMD_GET_PARSER_DISP_INFO_IN_OP_OFST 0 /* enum: read the list of supported RX filter matches */ #define MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_RX_MATCHES 0x1 +/* enum: read flags indicating restrictions on filter insertion for the calling + * client + */ +#define MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_RESTRICTIONS 0x2 /* MC_CMD_GET_PARSER_DISP_INFO_OUT msgresponse */ #define MC_CMD_GET_PARSER_DISP_INFO_OUT_LENMIN 8 @@ -4884,6 +6342,17 @@ #define MC_CMD_GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES_MINNUM 0 #define MC_CMD_GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES_MAXNUM 61 +/* MC_CMD_GET_PARSER_DISP_RESTRICTIONS_OUT msgresponse */ +#define MC_CMD_GET_PARSER_DISP_RESTRICTIONS_OUT_LEN 8 +/* identifies the type of operation requested */ +#define MC_CMD_GET_PARSER_DISP_RESTRICTIONS_OUT_OP_OFST 0 +/* Enum values, see field(s): */ +/* MC_CMD_GET_PARSER_DISP_INFO_IN/OP */ +/* bitfield of filter insertion restrictions */ +#define MC_CMD_GET_PARSER_DISP_RESTRICTIONS_OUT_RESTRICTION_FLAGS_OFST 4 +#define MC_CMD_GET_PARSER_DISP_RESTRICTIONS_OUT_DST_IP_MCAST_ONLY_LBN 0 +#define MC_CMD_GET_PARSER_DISP_RESTRICTIONS_OUT_DST_IP_MCAST_ONLY_WIDTH 1 + /***********************************/ /* MC_CMD_PARSER_DISP_RW @@ -4901,8 +6370,10 @@ #define MC_CMD_PARSER_DISP_RW_IN_RX_DICPU 0x0 /* enum: TX dispatcher CPU */ #define MC_CMD_PARSER_DISP_RW_IN_TX_DICPU 0x1 -/* enum: Lookup engine */ +/* enum: Lookup engine (with original metadata format) */ #define MC_CMD_PARSER_DISP_RW_IN_LUE 0x2 +/* enum: Lookup engine (with requested metadata format) */ +#define MC_CMD_PARSER_DISP_RW_IN_LUE_VERSIONED_METADATA 0x3 /* identifies the type of operation requested */ #define MC_CMD_PARSER_DISP_RW_IN_OP_OFST 4 /* enum: read a word of DICPU DMEM or a LUE entry */ @@ -4919,6 +6390,8 @@ #define MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_XOR_VALUE_OFST 12 /* AND mask (for DMEM read-modify-writes: new = (old & mask) ^ value) */ #define MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_AND_MASK_OFST 16 +/* metadata format (for LUE reads using LUE_VERSIONED_METADATA) */ +#define MC_CMD_PARSER_DISP_RW_IN_LUE_READ_METADATA_VERSION_OFST 12 /* value to write (for LUE writes) */ #define MC_CMD_PARSER_DISP_RW_IN_LUE_WRITE_VALUE_OFST 12 #define MC_CMD_PARSER_DISP_RW_IN_LUE_WRITE_VALUE_LEN 20 @@ -5019,7 +6492,9 @@ /* The maximum number of VIs that would be useful */ #define MC_CMD_ALLOC_VIS_IN_MAX_VI_COUNT_OFST 4 -/* MC_CMD_ALLOC_VIS_OUT msgresponse */ +/* MC_CMD_ALLOC_VIS_OUT msgresponse: Huntington-compatible VI_ALLOC request. + * Use extended version in new code. + */ #define MC_CMD_ALLOC_VIS_OUT_LEN 8 /* The number of VIs allocated on this function */ #define MC_CMD_ALLOC_VIS_OUT_VI_COUNT_OFST 0 @@ -5028,6 +6503,17 @@ */ #define MC_CMD_ALLOC_VIS_OUT_VI_BASE_OFST 4 +/* MC_CMD_ALLOC_VIS_EXT_OUT msgresponse */ +#define MC_CMD_ALLOC_VIS_EXT_OUT_LEN 12 +/* The number of VIs allocated on this function */ +#define MC_CMD_ALLOC_VIS_EXT_OUT_VI_COUNT_OFST 0 +/* The base absolute VI number allocated to this function. Required to + * correctly interpret wakeup events. + */ +#define MC_CMD_ALLOC_VIS_EXT_OUT_VI_BASE_OFST 4 +/* Function's port vi_shift value (always 0 on Huntington) */ +#define MC_CMD_ALLOC_VIS_EXT_OUT_VI_SHIFT_OFST 8 + /***********************************/ /* MC_CMD_FREE_VIS @@ -5114,13 +6600,15 @@ #define MC_CMD_GET_VI_ALLOC_INFO_IN_LEN 0 /* MC_CMD_GET_VI_ALLOC_INFO_OUT msgresponse */ -#define MC_CMD_GET_VI_ALLOC_INFO_OUT_LEN 8 +#define MC_CMD_GET_VI_ALLOC_INFO_OUT_LEN 12 /* The number of VIs allocated on this function */ #define MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_COUNT_OFST 0 /* The base absolute VI number allocated to this function. Required to * correctly interpret wakeup events. */ #define MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_BASE_OFST 4 +/* Function's port vi_shift value (always 0 on Huntington) */ +#define MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_SHIFT_OFST 8 /***********************************/ @@ -5575,6 +7063,7 @@ #define MC_CMD_GET_CAPABILITIES 0xbe #define MC_CMD_0xbe_PRIVILEGE_CTG SRIOV_CTG_GENERAL + /* MC_CMD_GET_CAPABILITIES_IN msgrequest */ #define MC_CMD_GET_CAPABILITIES_IN_LEN 0 @@ -5582,6 +7071,20 @@ #define MC_CMD_GET_CAPABILITIES_OUT_LEN 20 /* First word of flags. */ #define MC_CMD_GET_CAPABILITIES_OUT_FLAGS1_OFST 0 +#define MC_CMD_GET_CAPABILITIES_OUT_TX_MAC_SECURITY_FILTERING_LBN 12 +#define MC_CMD_GET_CAPABILITIES_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_ADDITIONAL_RSS_MODES_LBN 13 +#define MC_CMD_GET_CAPABILITIES_OUT_ADDITIONAL_RSS_MODES_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_QBB_LBN 14 +#define MC_CMD_GET_CAPABILITIES_OUT_QBB_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15 +#define MC_CMD_GET_CAPABILITIES_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_RX_RSS_LIMITED_LBN 16 +#define MC_CMD_GET_CAPABILITIES_OUT_RX_RSS_LIMITED_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_RX_PACKED_STREAM_LBN 17 +#define MC_CMD_GET_CAPABILITIES_OUT_RX_PACKED_STREAM_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_RX_INCLUDE_FCS_LBN 18 +#define MC_CMD_GET_CAPABILITIES_OUT_RX_INCLUDE_FCS_WIDTH 1 #define MC_CMD_GET_CAPABILITIES_OUT_TX_VLAN_INSERTION_LBN 19 #define MC_CMD_GET_CAPABILITIES_OUT_TX_VLAN_INSERTION_WIDTH 1 #define MC_CMD_GET_CAPABILITIES_OUT_RX_VLAN_STRIPPING_LBN 20 @@ -5600,8 +7103,14 @@ #define MC_CMD_GET_CAPABILITIES_OUT_MCAST_FILTER_CHAINING_WIDTH 1 #define MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_LBN 27 #define MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_RX_DISABLE_SCATTER_LBN 28 +#define MC_CMD_GET_CAPABILITIES_OUT_RX_DISABLE_SCATTER_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29 +#define MC_CMD_GET_CAPABILITIES_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1 #define MC_CMD_GET_CAPABILITIES_OUT_EVB_LBN 30 #define MC_CMD_GET_CAPABILITIES_OUT_EVB_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_LBN 31 +#define MC_CMD_GET_CAPABILITIES_OUT_VXLAN_NVGRE_WIDTH 1 /* RxDPCPU firmware id. */ #define MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_OFST 4 #define MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_LEN 2 @@ -5609,6 +7118,10 @@ #define MC_CMD_GET_CAPABILITIES_OUT_RXDP 0x0 /* enum: Low latency RXDP firmware */ #define MC_CMD_GET_CAPABILITIES_OUT_RXDP_LOW_LATENCY 0x1 +/* enum: Packed stream RXDP firmware */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_PACKED_STREAM 0x2 +/* enum: BIST RXDP firmware */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_BIST 0x10a /* enum: RXDP Test firmware image 1 */ #define MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101 /* enum: RXDP Test firmware image 2 */ @@ -5632,6 +7145,10 @@ #define MC_CMD_GET_CAPABILITIES_OUT_TXDP 0x0 /* enum: Low latency TXDP firmware */ #define MC_CMD_GET_CAPABILITIES_OUT_TXDP_LOW_LATENCY 0x1 +/* enum: High packet rate TXDP firmware */ +#define MC_CMD_GET_CAPABILITIES_OUT_TXDP_HIGH_PACKET_RATE 0x3 +/* enum: BIST TXDP firmware */ +#define MC_CMD_GET_CAPABILITIES_OUT_TXDP_BIST 0x12d /* enum: TXDP Test firmware image 1 */ #define MC_CMD_GET_CAPABILITIES_OUT_TXDP_TEST_FW_TSO_EDIT 0x101 /* enum: TXDP Test firmware image 2 */ @@ -5642,22 +7159,69 @@ #define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_REV_WIDTH 12 #define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_TYPE_LBN 12 #define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4 -#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1 /* enum */ -#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2 /* enum */ -#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_VSWITCH 0x3 /* enum */ -#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4 /* enum */ -#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */ +/* enum: reserved value - do not use (may indicate alternative interpretation + * of REV field in future) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_RESERVED 0x0 +/* enum: Trivial RX PD firmware for early Huntington development (Huntington + * development only) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1 +/* enum: RX PD firmware with approximately Siena-compatible behaviour + * (Huntington development only) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2 +/* enum: Virtual switching (full feature) RX PD production firmware */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_VSWITCH 0x3 +/* enum: siena_compat variant RX PD firmware using PM rather than MAC + * (Huntington development only) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4 +/* enum: Low latency RX PD production firmware */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5 +/* enum: Packed stream RX PD production firmware */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6 +/* enum: RX PD firmware handling layer 2 only for high packet rate performance + * tests (Medford development only) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7 +/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe +/* enum: RX PD firmware parsing but not filtering network overlay tunnel + * encapsulations (Medford development only) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf #define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_OFST 10 #define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_LEN 2 #define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_REV_LBN 0 #define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_REV_WIDTH 12 #define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_TYPE_LBN 12 #define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4 -#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1 /* enum */ -#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2 /* enum */ -#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_VSWITCH 0x3 /* enum */ -#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4 /* enum */ +/* enum: reserved value - do not use (may indicate alternative interpretation + * of REV field in future) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_RESERVED 0x0 +/* enum: Trivial TX PD firmware for early Huntington development (Huntington + * development only) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1 +/* enum: TX PD firmware with approximately Siena-compatible behaviour + * (Huntington development only) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2 +/* enum: Virtual switching (full feature) TX PD production firmware */ +#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_VSWITCH 0x3 +/* enum: siena_compat variant TX PD firmware using PM rather than MAC + * (Huntington development only) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4 #define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */ +/* enum: TX PD firmware handling layer 2 only for high packet rate performance + * tests (Medford development only) + */ +#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7 +/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */ +#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe /* Hardware capabilities of NIC */ #define MC_CMD_GET_CAPABILITIES_OUT_HW_CAPABILITIES_OFST 12 /* Licensed capabilities */ @@ -5735,6 +7299,15 @@ /* the rate in mbps */ #define MC_CMD_TCM_BUCKET_INIT_IN_RATE_OFST 4 +/* MC_CMD_TCM_BUCKET_INIT_EXT_IN msgrequest */ +#define MC_CMD_TCM_BUCKET_INIT_EXT_IN_LEN 12 +/* the bucket id */ +#define MC_CMD_TCM_BUCKET_INIT_EXT_IN_BUCKET_OFST 0 +/* the rate in mbps */ +#define MC_CMD_TCM_BUCKET_INIT_EXT_IN_RATE_OFST 4 +/* the desired maximum fill level */ +#define MC_CMD_TCM_BUCKET_INIT_EXT_IN_MAX_FILL_OFST 8 + /* MC_CMD_TCM_BUCKET_INIT_OUT msgresponse */ #define MC_CMD_TCM_BUCKET_INIT_OUT_LEN 0 @@ -5753,8 +7326,14 @@ #define MC_CMD_TCM_TXQ_INIT_IN_QID_OFST 0 /* the static priority associated with the txq */ #define MC_CMD_TCM_TXQ_INIT_IN_LABEL_OFST 4 -/* bitmask of the priority queues this txq is inserted into */ +/* bitmask of the priority queues this txq is inserted into when inserted. */ #define MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAGS_OFST 8 +#define MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_GUARANTEED_LBN 0 +#define MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_GUARANTEED_WIDTH 1 +#define MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_NORMAL_LBN 1 +#define MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_NORMAL_WIDTH 1 +#define MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_LOW_LBN 2 +#define MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_LOW_WIDTH 1 /* the reaction point (RP) bucket */ #define MC_CMD_TCM_TXQ_INIT_IN_RP_BKT_OFST 12 /* an already reserved bucket (typically set to bucket associated with outer @@ -5768,6 +7347,35 @@ /* the min bucket (typically for ETS/minimum bandwidth) */ #define MC_CMD_TCM_TXQ_INIT_IN_MIN_BKT_OFST 24 +/* MC_CMD_TCM_TXQ_INIT_EXT_IN msgrequest */ +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_LEN 32 +/* the txq id */ +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_QID_OFST 0 +/* the static priority associated with the txq */ +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_LABEL_NORMAL_OFST 4 +/* bitmask of the priority queues this txq is inserted into when inserted. */ +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAGS_OFST 8 +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_GUARANTEED_LBN 0 +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_GUARANTEED_WIDTH 1 +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_NORMAL_LBN 1 +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_NORMAL_WIDTH 1 +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_LOW_LBN 2 +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_LOW_WIDTH 1 +/* the reaction point (RP) bucket */ +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_RP_BKT_OFST 12 +/* an already reserved bucket (typically set to bucket associated with outer + * vswitch) + */ +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_MAX_BKT1_OFST 16 +/* an already reserved bucket (typically set to bucket associated with inner + * vswitch) + */ +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_MAX_BKT2_OFST 20 +/* the min bucket (typically for ETS/minimum bandwidth) */ +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_MIN_BKT_OFST 24 +/* the static priority associated with the txq */ +#define MC_CMD_TCM_TXQ_INIT_EXT_IN_LABEL_GUARANTEED_OFST 28 + /* MC_CMD_TCM_TXQ_INIT_OUT msgresponse */ #define MC_CMD_TCM_TXQ_INIT_OUT_LEN 0 @@ -5826,13 +7434,23 @@ #define MC_CMD_VSWITCH_ALLOC_IN_VSWITCH_TYPE_VLAN 0x1 /* enum: VEB */ #define MC_CMD_VSWITCH_ALLOC_IN_VSWITCH_TYPE_VEB 0x2 -/* enum: VEPA */ +/* enum: VEPA (obsolete) */ #define MC_CMD_VSWITCH_ALLOC_IN_VSWITCH_TYPE_VEPA 0x3 +/* enum: MUX */ +#define MC_CMD_VSWITCH_ALLOC_IN_VSWITCH_TYPE_MUX 0x4 +/* enum: Snapper specific; semantics TBD */ +#define MC_CMD_VSWITCH_ALLOC_IN_VSWITCH_TYPE_TEST 0x5 /* Flags controlling v-port creation */ #define MC_CMD_VSWITCH_ALLOC_IN_FLAGS_OFST 8 #define MC_CMD_VSWITCH_ALLOC_IN_FLAG_AUTO_PORT_LBN 0 #define MC_CMD_VSWITCH_ALLOC_IN_FLAG_AUTO_PORT_WIDTH 1 -/* The number of VLAN tags to support. */ +/* The number of VLAN tags to allow for attached v-ports. For VLAN aggregators, + * this must be one or greated, and the attached v-ports must have exactly this + * number of tags. For other v-switch types, this must be zero of greater, and + * is an upper limit on the number of VLAN tags for attached v-ports. An error + * will be returned if existing configuration means we can't support attached + * v-ports with this number of tags. + */ #define MC_CMD_VSWITCH_ALLOC_IN_NUM_VLAN_TAGS_OFST 12 /* MC_CMD_VSWITCH_ALLOC_OUT msgresponse */ @@ -5892,7 +7510,10 @@ #define MC_CMD_VPORT_ALLOC_IN_FLAGS_OFST 8 #define MC_CMD_VPORT_ALLOC_IN_FLAG_AUTO_PORT_LBN 0 #define MC_CMD_VPORT_ALLOC_IN_FLAG_AUTO_PORT_WIDTH 1 -/* The number of VLAN tags to insert/remove. */ +/* The number of VLAN tags to insert/remove. An error will be returned if + * incompatible with the number of VLAN tags specified for the upstream + * v-switch. + */ #define MC_CMD_VPORT_ALLOC_IN_NUM_VLAN_TAGS_OFST 12 /* The actual VLAN tags to insert/remove */ #define MC_CMD_VPORT_ALLOC_IN_VLAN_TAGS_OFST 16 @@ -6136,8 +7757,13 @@ /* MC_CMD_RSS_CONTEXT_ALLOC_OUT msgresponse */ #define MC_CMD_RSS_CONTEXT_ALLOC_OUT_LEN 4 -/* The handle of the new RSS context */ +/* The handle of the new RSS context. This should be considered opaque to the + * host, although a value of 0xFFFFFFFF is guaranteed never to be a valid + * handle. + */ #define MC_CMD_RSS_CONTEXT_ALLOC_OUT_RSS_CONTEXT_ID_OFST 0 +/* enum: guaranteed invalid RSS context handle value */ +#define MC_CMD_RSS_CONTEXT_ALLOC_OUT_RSS_CONTEXT_ID_INVALID 0xffffffff /***********************************/ @@ -6249,7 +7875,11 @@ #define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_LEN 8 /* The handle of the RSS context */ #define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_RSS_CONTEXT_ID_OFST 0 -/* Hash control flags */ +/* Hash control flags. The _EN bits are always supported. The _MODE bits only + * work when the firmware reports ADDITIONAL_RSS_MODES in + * MC_CMD_GET_CAPABILITIES and override the _EN bits if any of them are not 0. + * See the RSS_MODE structure for the meaning of the mode bits. + */ #define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_FLAGS_OFST 4 #define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_IPV4_EN_LBN 0 #define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_IPV4_EN_WIDTH 1 @@ -6259,6 +7889,20 @@ #define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_IPV6_EN_WIDTH 1 #define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_TCPV6_EN_LBN 3 #define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_TCPV6_EN_WIDTH 1 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_RESERVED_LBN 4 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_RESERVED_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TCP_IPV4_RSS_MODE_LBN 8 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TCP_IPV4_RSS_MODE_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_UDP_IPV4_RSS_MODE_LBN 12 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_UDP_IPV4_RSS_MODE_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_OTHER_IPV4_RSS_MODE_LBN 16 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_OTHER_IPV4_RSS_MODE_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TCP_IPV6_RSS_MODE_LBN 20 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TCP_IPV6_RSS_MODE_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_UDP_IPV6_RSS_MODE_LBN 24 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_UDP_IPV6_RSS_MODE_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_OTHER_IPV6_RSS_MODE_LBN 28 +#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_OTHER_IPV6_RSS_MODE_WIDTH 4 /* MC_CMD_RSS_CONTEXT_SET_FLAGS_OUT msgresponse */ #define MC_CMD_RSS_CONTEXT_SET_FLAGS_OUT_LEN 0 @@ -6279,7 +7923,12 @@ /* MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT msgresponse */ #define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_LEN 8 -/* Hash control flags */ +/* Hash control flags. If any _MODE bits are non-zero (which will only be true + * when the firmware reports ADDITIONAL_RSS_MODES) then the _EN bits should be + * disregarded (but are guaranteed to be consistent with the _MODE bits if + * RSS_CONTEXT_SET_FLAGS has never been called for this context since it was + * allocated). + */ #define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_FLAGS_OFST 4 #define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV4_EN_LBN 0 #define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV4_EN_WIDTH 1 @@ -6289,6 +7938,20 @@ #define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV6_EN_WIDTH 1 #define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_TCPV6_EN_LBN 3 #define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_TCPV6_EN_WIDTH 1 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_RESERVED_LBN 4 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_RESERVED_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TCP_IPV4_RSS_MODE_LBN 8 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TCP_IPV4_RSS_MODE_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV4_RSS_MODE_LBN 12 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV4_RSS_MODE_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_OTHER_IPV4_RSS_MODE_LBN 16 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_OTHER_IPV4_RSS_MODE_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TCP_IPV6_RSS_MODE_LBN 20 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TCP_IPV6_RSS_MODE_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV6_RSS_MODE_LBN 24 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_UDP_IPV6_RSS_MODE_WIDTH 4 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_OTHER_IPV6_RSS_MODE_LBN 28 +#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_OTHER_IPV6_RSS_MODE_WIDTH 4 /***********************************/ @@ -6311,8 +7974,13 @@ /* MC_CMD_DOT1P_MAPPING_ALLOC_OUT msgresponse */ #define MC_CMD_DOT1P_MAPPING_ALLOC_OUT_LEN 4 -/* The handle of the new .1p mapping */ +/* The handle of the new .1p mapping. This should be considered opaque to the + * host, although a value of 0xFFFFFFFF is guaranteed never to be a valid + * handle. + */ #define MC_CMD_DOT1P_MAPPING_ALLOC_OUT_DOT1P_MAPPING_ID_OFST 0 +/* enum: guaranteed invalid .1p mapping handle value */ +#define MC_CMD_DOT1P_MAPPING_ALLOC_OUT_DOT1P_MAPPING_ID_INVALID 0xffffffff /***********************************/ @@ -6421,375 +8089,6 @@ /***********************************/ -/* MC_CMD_RMON_RX_CLASS_STATS - * Retrieve rmon rx class statistics - */ -#define MC_CMD_RMON_RX_CLASS_STATS 0xc3 - -/* MC_CMD_RMON_RX_CLASS_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_CLASS_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_CLASS_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_CLASS_STATS_IN_CLASS_LBN 0 -#define MC_CMD_RMON_RX_CLASS_STATS_IN_CLASS_WIDTH 8 -#define MC_CMD_RMON_RX_CLASS_STATS_IN_RST_LBN 8 -#define MC_CMD_RMON_RX_CLASS_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_CLASS_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_CLASS_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_CLASS_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_CLASS_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_CLASS_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_CLASS_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_CLASS_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_CLASS_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_TX_CLASS_STATS - * Retrieve rmon tx class statistics - */ -#define MC_CMD_RMON_TX_CLASS_STATS 0xc4 - -/* MC_CMD_RMON_TX_CLASS_STATS_IN msgrequest */ -#define MC_CMD_RMON_TX_CLASS_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_TX_CLASS_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_TX_CLASS_STATS_IN_CLASS_LBN 0 -#define MC_CMD_RMON_TX_CLASS_STATS_IN_CLASS_WIDTH 8 -#define MC_CMD_RMON_TX_CLASS_STATS_IN_RST_LBN 8 -#define MC_CMD_RMON_TX_CLASS_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_TX_CLASS_STATS_OUT msgresponse */ -#define MC_CMD_RMON_TX_CLASS_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_TX_CLASS_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_TX_CLASS_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_TX_CLASS_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_TX_CLASS_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_TX_CLASS_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_TX_CLASS_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_RX_SUPER_CLASS_STATS - * Retrieve rmon rx super_class statistics - */ -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS 0xc5 - -/* MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_SUPER_CLASS_LBN 0 -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_SUPER_CLASS_WIDTH 4 -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_RST_LBN 4 -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_TX_SUPER_CLASS_STATS - * Retrieve rmon tx super_class statistics - */ -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS 0xc6 - -/* MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN msgrequest */ -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_SUPER_CLASS_LBN 0 -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_SUPER_CLASS_WIDTH 4 -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_RST_LBN 4 -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT msgresponse */ -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_RX_ADD_QID_TO_CLASS - * Add qid to class for statistics collection - */ -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS 0xc7 - -/* MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN msgrequest */ -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_LEN 12 -/* class */ -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_CLASS_OFST 0 -/* qid */ -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_QID_OFST 4 -/* flags */ -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_FLAGS_OFST 8 -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_SUPER_CLASS_LBN 0 -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_SUPER_CLASS_WIDTH 4 -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_PE_DELTA_LBN 4 -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_PE_DELTA_WIDTH 4 -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_MTU_LBN 8 -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_MTU_WIDTH 14 - -/* MC_CMD_RMON_RX_ADD_QID_TO_CLASS_OUT msgresponse */ -#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_OUT_LEN 0 - - -/***********************************/ -/* MC_CMD_RMON_TX_ADD_QID_TO_CLASS - * Add qid to class for statistics collection - */ -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS 0xc8 - -/* MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN msgrequest */ -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_LEN 12 -/* class */ -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_CLASS_OFST 0 -/* qid */ -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_QID_OFST 4 -/* flags */ -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_FLAGS_OFST 8 -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_SUPER_CLASS_LBN 0 -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_SUPER_CLASS_WIDTH 4 -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_PE_DELTA_LBN 4 -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_PE_DELTA_WIDTH 4 -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_MTU_LBN 8 -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_MTU_WIDTH 14 - -/* MC_CMD_RMON_TX_ADD_QID_TO_CLASS_OUT msgresponse */ -#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_OUT_LEN 0 - - -/***********************************/ -/* MC_CMD_RMON_MC_ADD_QID_TO_CLASS - * Add qid to class for statistics collection - */ -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS 0xc9 - -/* MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN msgrequest */ -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_LEN 12 -/* class */ -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_CLASS_OFST 0 -/* qid */ -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_QID_OFST 4 -/* flags */ -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_FLAGS_OFST 8 -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_SUPER_CLASS_LBN 0 -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_SUPER_CLASS_WIDTH 4 -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_PE_DELTA_LBN 4 -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_PE_DELTA_WIDTH 4 -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_MTU_LBN 8 -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_MTU_WIDTH 14 - -/* MC_CMD_RMON_MC_ADD_QID_TO_CLASS_OUT msgresponse */ -#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_OUT_LEN 0 - - -/***********************************/ -/* MC_CMD_RMON_ALLOC_CLASS - * Allocate an rmon class - */ -#define MC_CMD_RMON_ALLOC_CLASS 0xca - -/* MC_CMD_RMON_ALLOC_CLASS_IN msgrequest */ -#define MC_CMD_RMON_ALLOC_CLASS_IN_LEN 0 - -/* MC_CMD_RMON_ALLOC_CLASS_OUT msgresponse */ -#define MC_CMD_RMON_ALLOC_CLASS_OUT_LEN 4 -/* class */ -#define MC_CMD_RMON_ALLOC_CLASS_OUT_CLASS_OFST 0 - - -/***********************************/ -/* MC_CMD_RMON_DEALLOC_CLASS - * Deallocate an rmon class - */ -#define MC_CMD_RMON_DEALLOC_CLASS 0xcb - -/* MC_CMD_RMON_DEALLOC_CLASS_IN msgrequest */ -#define MC_CMD_RMON_DEALLOC_CLASS_IN_LEN 4 -/* class */ -#define MC_CMD_RMON_DEALLOC_CLASS_IN_CLASS_OFST 0 - -/* MC_CMD_RMON_DEALLOC_CLASS_OUT msgresponse */ -#define MC_CMD_RMON_DEALLOC_CLASS_OUT_LEN 0 - - -/***********************************/ -/* MC_CMD_RMON_ALLOC_SUPER_CLASS - * Allocate an rmon super_class - */ -#define MC_CMD_RMON_ALLOC_SUPER_CLASS 0xcc - -/* MC_CMD_RMON_ALLOC_SUPER_CLASS_IN msgrequest */ -#define MC_CMD_RMON_ALLOC_SUPER_CLASS_IN_LEN 0 - -/* MC_CMD_RMON_ALLOC_SUPER_CLASS_OUT msgresponse */ -#define MC_CMD_RMON_ALLOC_SUPER_CLASS_OUT_LEN 4 -/* super_class */ -#define MC_CMD_RMON_ALLOC_SUPER_CLASS_OUT_SUPER_CLASS_OFST 0 - - -/***********************************/ -/* MC_CMD_RMON_DEALLOC_SUPER_CLASS - * Deallocate an rmon tx super_class - */ -#define MC_CMD_RMON_DEALLOC_SUPER_CLASS 0xcd - -/* MC_CMD_RMON_DEALLOC_SUPER_CLASS_IN msgrequest */ -#define MC_CMD_RMON_DEALLOC_SUPER_CLASS_IN_LEN 4 -/* super_class */ -#define MC_CMD_RMON_DEALLOC_SUPER_CLASS_IN_SUPER_CLASS_OFST 0 - -/* MC_CMD_RMON_DEALLOC_SUPER_CLASS_OUT msgresponse */ -#define MC_CMD_RMON_DEALLOC_SUPER_CLASS_OUT_LEN 0 - - -/***********************************/ -/* MC_CMD_RMON_RX_UP_CONV_STATS - * Retrieve up converter statistics - */ -#define MC_CMD_RMON_RX_UP_CONV_STATS 0xce - -/* MC_CMD_RMON_RX_UP_CONV_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_PORT_LBN 0 -#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_PORT_WIDTH 2 -#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_RST_LBN 2 -#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_UP_CONV_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_RX_IPI_STATS - * Retrieve rx ipi stats - */ -#define MC_CMD_RMON_RX_IPI_STATS 0xcf - -/* MC_CMD_RMON_RX_IPI_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_IPI_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_IPI_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_IPI_STATS_IN_VFIFO_LBN 0 -#define MC_CMD_RMON_RX_IPI_STATS_IN_VFIFO_WIDTH 5 -#define MC_CMD_RMON_RX_IPI_STATS_IN_RST_LBN 5 -#define MC_CMD_RMON_RX_IPI_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_IPI_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_IPI_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_IPI_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_IPI_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_IPI_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_IPI_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_IPI_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_IPI_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS - * Retrieve rx ipsec cntxt_ptr indexed stats - */ -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS 0xd0 - -/* MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_CNTXT_PTR_LBN 0 -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_CNTXT_PTR_WIDTH 9 -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_RST_LBN 9 -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_RX_IPSEC_PORT_STATS - * Retrieve rx ipsec port indexed stats - */ -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS 0xd1 - -/* MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_PORT_LBN 0 -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_PORT_WIDTH 2 -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_RST_LBN 2 -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_RX_IPSEC_OFLOW_STATS - * Retrieve tx ipsec overflow - */ -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS 0xd2 - -/* MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_PORT_LBN 0 -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_PORT_WIDTH 2 -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_RST_LBN 2 -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ /* MC_CMD_VPORT_ADD_MAC_ADDRESS * Add a MAC address to a v-port */ @@ -6877,7 +8176,7 @@ #define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LENMIN 12 #define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LENMAX 252 #define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LEN(num) (0+12*(num)) -/* Raw buffer table entries, laid out as BUFTBL_ENTRY. */ +/* Raw buffer table entries, layed out as BUFTBL_ENTRY. */ #define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_OFST 0 #define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_LEN 12 #define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_MINNUM 1 @@ -6921,354 +8220,6 @@ /***********************************/ -/* MC_CMD_RMON_RX_CLASS_DROPS_STATS - * Retrieve rx class drop stats - */ -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS 0xd3 - -/* MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_CLASS_LBN 0 -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_CLASS_WIDTH 8 -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_RST_LBN 8 -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS - * Retrieve rx super class drop stats - */ -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS 0xd4 - -/* MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_SUPER_CLASS_LBN 0 -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_SUPER_CLASS_WIDTH 4 -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_RST_LBN 4 -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_RX_ERRORS_STATS - * Retrieve rxdp errors - */ -#define MC_CMD_RMON_RX_ERRORS_STATS 0xd5 - -/* MC_CMD_RMON_RX_ERRORS_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_ERRORS_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_ERRORS_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_ERRORS_STATS_IN_QID_LBN 0 -#define MC_CMD_RMON_RX_ERRORS_STATS_IN_QID_WIDTH 11 -#define MC_CMD_RMON_RX_ERRORS_STATS_IN_RST_LBN 11 -#define MC_CMD_RMON_RX_ERRORS_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_ERRORS_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_RX_OVERFLOW_STATS - * Retrieve rxdp overflow - */ -#define MC_CMD_RMON_RX_OVERFLOW_STATS 0xd6 - -/* MC_CMD_RMON_RX_OVERFLOW_STATS_IN msgrequest */ -#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_CLASS_LBN 0 -#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_CLASS_WIDTH 8 -#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_RST_LBN 8 -#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_RX_OVERFLOW_STATS_OUT msgresponse */ -#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_TX_IPI_STATS - * Retrieve tx ipi stats - */ -#define MC_CMD_RMON_TX_IPI_STATS 0xd7 - -/* MC_CMD_RMON_TX_IPI_STATS_IN msgrequest */ -#define MC_CMD_RMON_TX_IPI_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_TX_IPI_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_TX_IPI_STATS_IN_VFIFO_LBN 0 -#define MC_CMD_RMON_TX_IPI_STATS_IN_VFIFO_WIDTH 5 -#define MC_CMD_RMON_TX_IPI_STATS_IN_RST_LBN 5 -#define MC_CMD_RMON_TX_IPI_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_TX_IPI_STATS_OUT msgresponse */ -#define MC_CMD_RMON_TX_IPI_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_TX_IPI_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_TX_IPI_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_TX_IPI_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_TX_IPI_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_TX_IPI_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_TX_IPI_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS - * Retrieve tx ipsec counters by cntxt_ptr - */ -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS 0xd8 - -/* MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN msgrequest */ -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_CNTXT_PTR_LBN 0 -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_CNTXT_PTR_WIDTH 9 -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_RST_LBN 9 -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT msgresponse */ -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_TX_IPSEC_PORT_STATS - * Retrieve tx ipsec counters by port - */ -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS 0xd9 - -/* MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN msgrequest */ -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_PORT_LBN 0 -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_PORT_WIDTH 2 -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_RST_LBN 2 -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT msgresponse */ -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_TX_IPSEC_OFLOW_STATS - * Retrieve tx ipsec overflow - */ -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS 0xda - -/* MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN msgrequest */ -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_PORT_LBN 0 -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_PORT_WIDTH 2 -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_RST_LBN 2 -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT msgresponse */ -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_TX_NOWHERE_STATS - * Retrieve tx nowhere stats - */ -#define MC_CMD_RMON_TX_NOWHERE_STATS 0xdb - -/* MC_CMD_RMON_TX_NOWHERE_STATS_IN msgrequest */ -#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_CLASS_LBN 0 -#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_CLASS_WIDTH 8 -#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_RST_LBN 8 -#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_TX_NOWHERE_STATS_OUT msgresponse */ -#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_TX_NOWHERE_QBB_STATS - * Retrieve tx nowhere qbb stats - */ -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS 0xdc - -/* MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN msgrequest */ -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_PRIORITY_LBN 0 -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_PRIORITY_WIDTH 3 -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_RST_LBN 3 -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT msgresponse */ -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_TX_ERRORS_STATS - * Retrieve rxdp errors - */ -#define MC_CMD_RMON_TX_ERRORS_STATS 0xdd - -/* MC_CMD_RMON_TX_ERRORS_STATS_IN msgrequest */ -#define MC_CMD_RMON_TX_ERRORS_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_TX_ERRORS_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_TX_ERRORS_STATS_IN_QID_LBN 0 -#define MC_CMD_RMON_TX_ERRORS_STATS_IN_QID_WIDTH 11 -#define MC_CMD_RMON_TX_ERRORS_STATS_IN_RST_LBN 11 -#define MC_CMD_RMON_TX_ERRORS_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_TX_ERRORS_STATS_OUT msgresponse */ -#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_TX_OVERFLOW_STATS - * Retrieve rxdp overflow - */ -#define MC_CMD_RMON_TX_OVERFLOW_STATS 0xde - -/* MC_CMD_RMON_TX_OVERFLOW_STATS_IN msgrequest */ -#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_LEN 4 -/* flags */ -#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_FLAGS_OFST 0 -#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_CLASS_LBN 0 -#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_CLASS_WIDTH 8 -#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_RST_LBN 8 -#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_RST_WIDTH 1 - -/* MC_CMD_RMON_TX_OVERFLOW_STATS_OUT msgresponse */ -#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_LENMIN 4 -#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_LENMAX 252 -#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_LEN(num) (0+4*(num)) -/* Array of stats */ -#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_BUFFER_OFST 0 -#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_BUFFER_LEN 4 -#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_BUFFER_MINNUM 1 -#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_BUFFER_MAXNUM 63 - - -/***********************************/ -/* MC_CMD_RMON_COLLECT_CLASS_STATS - * Explicitly collect class stats at the specified evb port - */ -#define MC_CMD_RMON_COLLECT_CLASS_STATS 0xdf - -/* MC_CMD_RMON_COLLECT_CLASS_STATS_IN msgrequest */ -#define MC_CMD_RMON_COLLECT_CLASS_STATS_IN_LEN 4 -/* The port id associated with the vport/pport at which to collect class stats - */ -#define MC_CMD_RMON_COLLECT_CLASS_STATS_IN_PORT_ID_OFST 0 - -/* MC_CMD_RMON_COLLECT_CLASS_STATS_OUT msgresponse */ -#define MC_CMD_RMON_COLLECT_CLASS_STATS_OUT_LEN 4 -/* class */ -#define MC_CMD_RMON_COLLECT_CLASS_STATS_OUT_CLASS_OFST 0 - - -/***********************************/ -/* MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS - * Explicitly collect class stats at the specified evb port - */ -#define MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS 0xe0 - -/* MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_IN msgrequest */ -#define MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_IN_LEN 4 -/* The port id associated with the vport/pport at which to collect class stats - */ -#define MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_IN_PORT_ID_OFST 0 - -/* MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_OUT msgresponse */ -#define MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_OUT_LEN 4 -/* super_class */ -#define MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_OUT_SUPER_CLASS_OFST 0 - - -/***********************************/ /* MC_CMD_GET_CLOCK * Return the system and PDCPU clock frequencies. */ @@ -7296,22 +8247,66 @@ #define MC_CMD_0xad_PRIVILEGE_CTG SRIOV_CTG_ADMIN /* MC_CMD_SET_CLOCK_IN msgrequest */ -#define MC_CMD_SET_CLOCK_IN_LEN 12 -/* Requested system frequency in MHz; 0 leaves unchanged. */ +#define MC_CMD_SET_CLOCK_IN_LEN 28 +/* Requested frequency in MHz for system clock domain */ #define MC_CMD_SET_CLOCK_IN_SYS_FREQ_OFST 0 -/* Requested inter-core frequency in MHz; 0 leaves unchanged. */ +/* enum: Leave the system clock domain frequency unchanged */ +#define MC_CMD_SET_CLOCK_IN_SYS_DOMAIN_DONT_CHANGE 0x0 +/* Requested frequency in MHz for inter-core clock domain */ #define MC_CMD_SET_CLOCK_IN_ICORE_FREQ_OFST 4 -/* Request DPCPU frequency in MHz; 0 leaves unchanged. */ +/* enum: Leave the inter-core clock domain frequency unchanged */ +#define MC_CMD_SET_CLOCK_IN_ICORE_DOMAIN_DONT_CHANGE 0x0 +/* Requested frequency in MHz for DPCPU clock domain */ #define MC_CMD_SET_CLOCK_IN_DPCPU_FREQ_OFST 8 +/* enum: Leave the DPCPU clock domain frequency unchanged */ +#define MC_CMD_SET_CLOCK_IN_DPCPU_DOMAIN_DONT_CHANGE 0x0 +/* Requested frequency in MHz for PCS clock domain */ +#define MC_CMD_SET_CLOCK_IN_PCS_FREQ_OFST 12 +/* enum: Leave the PCS clock domain frequency unchanged */ +#define MC_CMD_SET_CLOCK_IN_PCS_DOMAIN_DONT_CHANGE 0x0 +/* Requested frequency in MHz for MC clock domain */ +#define MC_CMD_SET_CLOCK_IN_MC_FREQ_OFST 16 +/* enum: Leave the MC clock domain frequency unchanged */ +#define MC_CMD_SET_CLOCK_IN_MC_DOMAIN_DONT_CHANGE 0x0 +/* Requested frequency in MHz for rmon clock domain */ +#define MC_CMD_SET_CLOCK_IN_RMON_FREQ_OFST 20 +/* enum: Leave the rmon clock domain frequency unchanged */ +#define MC_CMD_SET_CLOCK_IN_RMON_DOMAIN_DONT_CHANGE 0x0 +/* Requested frequency in MHz for vswitch clock domain */ +#define MC_CMD_SET_CLOCK_IN_VSWITCH_FREQ_OFST 24 +/* enum: Leave the vswitch clock domain frequency unchanged */ +#define MC_CMD_SET_CLOCK_IN_VSWITCH_DOMAIN_DONT_CHANGE 0x0 /* MC_CMD_SET_CLOCK_OUT msgresponse */ -#define MC_CMD_SET_CLOCK_OUT_LEN 12 +#define MC_CMD_SET_CLOCK_OUT_LEN 28 /* Resulting system frequency in MHz */ #define MC_CMD_SET_CLOCK_OUT_SYS_FREQ_OFST 0 +/* enum: The system clock domain doesn't exist */ +#define MC_CMD_SET_CLOCK_OUT_SYS_DOMAIN_UNSUPPORTED 0x0 /* Resulting inter-core frequency in MHz */ #define MC_CMD_SET_CLOCK_OUT_ICORE_FREQ_OFST 4 +/* enum: The inter-core clock domain doesn't exist / isn't used */ +#define MC_CMD_SET_CLOCK_OUT_ICORE_DOMAIN_UNSUPPORTED 0x0 /* Resulting DPCPU frequency in MHz */ #define MC_CMD_SET_CLOCK_OUT_DPCPU_FREQ_OFST 8 +/* enum: The dpcpu clock domain doesn't exist */ +#define MC_CMD_SET_CLOCK_OUT_DPCPU_DOMAIN_UNSUPPORTED 0x0 +/* Resulting PCS frequency in MHz */ +#define MC_CMD_SET_CLOCK_OUT_PCS_FREQ_OFST 12 +/* enum: The PCS clock domain doesn't exist / isn't controlled */ +#define MC_CMD_SET_CLOCK_OUT_PCS_DOMAIN_UNSUPPORTED 0x0 +/* Resulting MC frequency in MHz */ +#define MC_CMD_SET_CLOCK_OUT_MC_FREQ_OFST 16 +/* enum: The MC clock domain doesn't exist / isn't controlled */ +#define MC_CMD_SET_CLOCK_OUT_MC_DOMAIN_UNSUPPORTED 0x0 +/* Resulting rmon frequency in MHz */ +#define MC_CMD_SET_CLOCK_OUT_RMON_FREQ_OFST 20 +/* enum: The rmon clock domain doesn't exist / isn't controlled */ +#define MC_CMD_SET_CLOCK_OUT_RMON_DOMAIN_UNSUPPORTED 0x0 +/* Resulting vswitch frequency in MHz */ +#define MC_CMD_SET_CLOCK_OUT_VSWITCH_FREQ_OFST 24 +/* enum: The vswitch clock domain doesn't exist / isn't controlled */ +#define MC_CMD_SET_CLOCK_OUT_VSWITCH_DOMAIN_UNSUPPORTED 0x0 /***********************************/ @@ -7325,12 +8320,22 @@ /* MC_CMD_DPCPU_RPC_IN msgrequest */ #define MC_CMD_DPCPU_RPC_IN_LEN 36 #define MC_CMD_DPCPU_RPC_IN_CPU_OFST 0 -/* enum: RxDPCPU */ -#define MC_CMD_DPCPU_RPC_IN_DPCPU_RX 0x0 +/* enum: RxDPCPU0 */ +#define MC_CMD_DPCPU_RPC_IN_DPCPU_RX0 0x0 /* enum: TxDPCPU0 */ #define MC_CMD_DPCPU_RPC_IN_DPCPU_TX0 0x1 /* enum: TxDPCPU1 */ #define MC_CMD_DPCPU_RPC_IN_DPCPU_TX1 0x2 +/* enum: RxDPCPU1 (Medford only) */ +#define MC_CMD_DPCPU_RPC_IN_DPCPU_RX1 0x3 +/* enum: RxDPCPU (will be for the calling function; for now, just an alias of + * DPCPU_RX0) + */ +#define MC_CMD_DPCPU_RPC_IN_DPCPU_RX 0x80 +/* enum: TxDPCPU (will be for the calling function; for now, just an alias of + * DPCPU_TX0) + */ +#define MC_CMD_DPCPU_RPC_IN_DPCPU_TX 0x81 /* First 8 bits [39:32] of DATA are consumed by MC-DPCPU protocol and must be * initialised to zero */ @@ -7418,6 +8423,25 @@ /***********************************/ +/* MC_CMD_SHMBOOT_OP + * Special operations to support (for now) shmboot. + */ +#define MC_CMD_SHMBOOT_OP 0xe6 + +#define MC_CMD_0xe6_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_SHMBOOT_OP_IN msgrequest */ +#define MC_CMD_SHMBOOT_OP_IN_LEN 4 +/* Identifies the operation to perform */ +#define MC_CMD_SHMBOOT_OP_IN_SHMBOOT_OP_OFST 0 +/* enum: Copy slave_data section to the slave core. (Greenport only) */ +#define MC_CMD_SHMBOOT_OP_IN_PUSH_SLAVE_DATA 0x0 + +/* MC_CMD_SHMBOOT_OP_OUT msgresponse */ +#define MC_CMD_SHMBOOT_OP_OUT_LEN 0 + + +/***********************************/ /* MC_CMD_CAP_BLK_READ * Read multiple 64bit words from capture block memory */ @@ -7730,6 +8754,8 @@ * more data is returned. */ #define MC_CMD_KR_TUNE_IN_POLL_EYE_PLOT 0x6 +/* enum: Read Figure Of Merit (eye quality, higher is better). */ +#define MC_CMD_KR_TUNE_IN_READ_FOM 0x7 /* Align the arguments to 32 bits */ #define MC_CMD_KR_TUNE_IN_KR_TUNE_RSVD_OFST 1 #define MC_CMD_KR_TUNE_IN_KR_TUNE_RSVD_LEN 3 @@ -7762,20 +8788,32 @@ #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_MAXNUM 63 #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_ID_LBN 0 #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_ID_WIDTH 8 -/* enum: Attenuation (0-15) */ +/* enum: Attenuation (0-15, TBD for Medford) */ #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_ATT 0x0 -/* enum: CTLE Boost (0-15) */ +/* enum: CTLE Boost (0-15, TBD for Medford) */ #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_BOOST 0x1 -/* enum: Edge DFE Tap1 (0 - max negative, 64 - zero, 127 - max positive) */ +/* enum: Edge DFE Tap1 (0 - max negative, 64 - zero, 127 - max positive, TBD + * for Medford) + */ #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP1 0x2 -/* enum: Edge DFE Tap2 (0 - max negative, 32 - zero, 63 - max positive) */ +/* enum: Edge DFE Tap2 (0 - max negative, 32 - zero, 63 - max positive, TBD for + * Medford) + */ #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP2 0x3 -/* enum: Edge DFE Tap3 (0 - max negative, 32 - zero, 63 - max positive) */ +/* enum: Edge DFE Tap3 (0 - max negative, 32 - zero, 63 - max positive, TBD for + * Medford) + */ #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP3 0x4 -/* enum: Edge DFE Tap4 (0 - max negative, 32 - zero, 63 - max positive) */ +/* enum: Edge DFE Tap4 (0 - max negative, 32 - zero, 63 - max positive, TBD for + * Medford) + */ #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP4 0x5 -/* enum: Edge DFE Tap5 (0 - max negative, 32 - zero, 63 - max positive) */ +/* enum: Edge DFE Tap5 (0 - max negative, 32 - zero, 63 - max positive, TBD for + * Medford) + */ #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP5 0x6 +/* enum: Edge DFE DLEV (TBD for Medford) */ +#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_DLEV 0x7 #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_LANE_LBN 8 #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 3 #define MC_CMD_KR_TUNE_RXEQ_GET_OUT_LANE_0 0x0 /* enum */ @@ -7865,6 +8903,8 @@ #define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_PREDRV_DLY 0x7 /* enum: TX Slew Rate Fine control */ #define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_SR_SET 0x8 +/* enum: TX Termination Impedance control */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_RT_SET 0x9 #define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LANE_LBN 8 #define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LANE_WIDTH 3 #define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_0 0x0 /* enum */ @@ -7955,6 +8995,20 @@ #define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MINNUM 0 #define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MAXNUM 126 +/* MC_CMD_KR_TUNE_READ_FOM_IN msgrequest */ +#define MC_CMD_KR_TUNE_READ_FOM_IN_LEN 8 +/* Requested operation */ +#define MC_CMD_KR_TUNE_READ_FOM_IN_KR_TUNE_OP_OFST 0 +#define MC_CMD_KR_TUNE_READ_FOM_IN_KR_TUNE_OP_LEN 1 +/* Align the arguments to 32 bits */ +#define MC_CMD_KR_TUNE_READ_FOM_IN_KR_TUNE_RSVD_OFST 1 +#define MC_CMD_KR_TUNE_READ_FOM_IN_KR_TUNE_RSVD_LEN 3 +#define MC_CMD_KR_TUNE_READ_FOM_IN_LANE_OFST 4 + +/* MC_CMD_KR_TUNE_READ_FOM_OUT msgresponse */ +#define MC_CMD_KR_TUNE_READ_FOM_OUT_LEN 4 +#define MC_CMD_KR_TUNE_READ_FOM_OUT_FOM_OFST 0 + /***********************************/ /* MC_CMD_PCIE_TUNE @@ -8224,6 +9278,8 @@ #define MC_CMD_LICENSED_APP_OP_IN_OP_OFST 4 /* enum: validate application */ #define MC_CMD_LICENSED_APP_OP_IN_OP_VALIDATE 0x0 +/* enum: mask application */ +#define MC_CMD_LICENSED_APP_OP_IN_OP_MASK 0x1 /* arguments specific to this particular operation */ #define MC_CMD_LICENSED_APP_OP_IN_ARGS_OFST 8 #define MC_CMD_LICENSED_APP_OP_IN_ARGS_LEN 4 @@ -8258,10 +9314,22 @@ #define MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_RESPONSE_OFST 4 #define MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_RESPONSE_LEN 64 +/* MC_CMD_LICENSED_APP_OP_MASK_IN msgrequest */ +#define MC_CMD_LICENSED_APP_OP_MASK_IN_LEN 12 +/* application ID */ +#define MC_CMD_LICENSED_APP_OP_MASK_IN_APP_ID_OFST 0 +/* the type of operation requested */ +#define MC_CMD_LICENSED_APP_OP_MASK_IN_OP_OFST 4 +/* flag */ +#define MC_CMD_LICENSED_APP_OP_MASK_IN_FLAG_OFST 8 + +/* MC_CMD_LICENSED_APP_OP_MASK_OUT msgresponse */ +#define MC_CMD_LICENSED_APP_OP_MASK_OUT_LEN 0 + /***********************************/ /* MC_CMD_SET_PORT_SNIFF_CONFIG - * Configure port sniffing for the physical port associated with the calling + * Configure RX port sniffing for the physical port associated with the calling * function. Only a privileged function may change the port sniffing * configuration. A copy of all traffic delivered to the host (non-promiscuous * mode) or all traffic arriving at the port (promiscuous mode) may be @@ -8299,7 +9367,7 @@ /***********************************/ /* MC_CMD_GET_PORT_SNIFF_CONFIG - * Obtain the current port sniffing configuration for the physical port + * Obtain the current RX port sniffing configuration for the physical port * associated with the calling function. Only a privileged function may read * the configuration. */ @@ -8330,4 +9398,673 @@ #define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_OFST 12 +/***********************************/ +/* MC_CMD_SET_PARSER_DISP_CONFIG + * Change configuration related to the parser-dispatcher subsystem. + */ +#define MC_CMD_SET_PARSER_DISP_CONFIG 0xf9 + +#define MC_CMD_0xf9_PRIVILEGE_CTG SRIOV_CTG_GENERAL + +/* MC_CMD_SET_PARSER_DISP_CONFIG_IN msgrequest */ +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_LENMIN 12 +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_LENMAX 252 +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_LEN(num) (8+4*(num)) +/* the type of configuration setting to change */ +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_TYPE_OFST 0 +/* enum: Per-TXQ enable for multicast UDP destination lookup for possible + * internal loopback. (ENTITY is a queue handle, VALUE is a single boolean.) + */ +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_TXQ_MCAST_UDP_DST_LOOKUP_EN 0x0 +/* enum: Per-v-adaptor enable for suppression of self-transmissions on the + * internal loopback path. (ENTITY is an EVB_PORT_ID, VALUE is a single + * boolean.) + */ +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_VADAPTOR_SUPPRESS_SELF_TX 0x1 +/* handle for the entity to update: queue handle, EVB port ID, etc. depending + * on the type of configuration setting being changed + */ +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_ENTITY_OFST 4 +/* new value: the details depend on the type of configuration setting being + * changed + */ +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_VALUE_OFST 8 +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_VALUE_LEN 4 +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_VALUE_MINNUM 1 +#define MC_CMD_SET_PARSER_DISP_CONFIG_IN_VALUE_MAXNUM 61 + +/* MC_CMD_SET_PARSER_DISP_CONFIG_OUT msgresponse */ +#define MC_CMD_SET_PARSER_DISP_CONFIG_OUT_LEN 0 + + +/***********************************/ +/* MC_CMD_GET_PARSER_DISP_CONFIG + * Read configuration related to the parser-dispatcher subsystem. + */ +#define MC_CMD_GET_PARSER_DISP_CONFIG 0xfa + +#define MC_CMD_0xfa_PRIVILEGE_CTG SRIOV_CTG_GENERAL + +/* MC_CMD_GET_PARSER_DISP_CONFIG_IN msgrequest */ +#define MC_CMD_GET_PARSER_DISP_CONFIG_IN_LEN 8 +/* the type of configuration setting to read */ +#define MC_CMD_GET_PARSER_DISP_CONFIG_IN_TYPE_OFST 0 +/* Enum values, see field(s): */ +/* MC_CMD_SET_PARSER_DISP_CONFIG/MC_CMD_SET_PARSER_DISP_CONFIG_IN/TYPE */ +/* handle for the entity to query: queue handle, EVB port ID, etc. depending on + * the type of configuration setting being read + */ +#define MC_CMD_GET_PARSER_DISP_CONFIG_IN_ENTITY_OFST 4 + +/* MC_CMD_GET_PARSER_DISP_CONFIG_OUT msgresponse */ +#define MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LENMIN 4 +#define MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LENMAX 252 +#define MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LEN(num) (0+4*(num)) +/* current value: the details depend on the type of configuration setting being + * read + */ +#define MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_OFST 0 +#define MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_LEN 4 +#define MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_MINNUM 1 +#define MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_MAXNUM 63 + + +/***********************************/ +/* MC_CMD_SET_TX_PORT_SNIFF_CONFIG + * Configure TX port sniffing for the physical port associated with the calling + * function. Only a privileged function may change the port sniffing + * configuration. A copy of all traffic transmitted through the port may be + * delivered to a specific queue, or a set of queues with RSS. Note that these + * packets are delivered with transmit timestamps in the packet prefix, not + * receive timestamps, so it is likely that the queue(s) will need to be + * dedicated as TX sniff receivers. + */ +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG 0xfb + +#define MC_CMD_0xfb_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN msgrequest */ +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_LEN 16 +/* configuration flags */ +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_FLAGS_OFST 0 +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_ENABLE_LBN 0 +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_ENABLE_WIDTH 1 +/* receive queue handle (for RSS mode, this is the base queue) */ +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_QUEUE_OFST 4 +/* receive mode */ +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_OFST 8 +/* enum: receive to just the specified queue */ +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_SIMPLE 0x0 +/* enum: receive to multiple queues using RSS context */ +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_RSS 0x1 +/* RSS context (for RX_MODE_RSS) as returned by MC_CMD_RSS_CONTEXT_ALLOC. Note + * that these handles should be considered opaque to the host, although a value + * of 0xFFFFFFFF is guaranteed never to be a valid handle. + */ +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_OFST 12 + +/* MC_CMD_SET_TX_PORT_SNIFF_CONFIG_OUT msgresponse */ +#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG_OUT_LEN 0 + + +/***********************************/ +/* MC_CMD_GET_TX_PORT_SNIFF_CONFIG + * Obtain the current TX port sniffing configuration for the physical port + * associated with the calling function. Only a privileged function may read + * the configuration. + */ +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG 0xfc + +#define MC_CMD_0xfc_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_GET_TX_PORT_SNIFF_CONFIG_IN msgrequest */ +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG_IN_LEN 0 + +/* MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT msgresponse */ +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_LEN 16 +/* configuration flags */ +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_FLAGS_OFST 0 +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_ENABLE_LBN 0 +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_ENABLE_WIDTH 1 +/* receiving queue handle (for RSS mode, this is the base queue) */ +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_OFST 4 +/* receive mode */ +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_OFST 8 +/* enum: receiving to just the specified queue */ +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_SIMPLE 0x0 +/* enum: receiving to multiple queues using RSS context */ +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_RSS 0x1 +/* RSS context (for RX_MODE_RSS) */ +#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_OFST 12 + + +/***********************************/ +/* MC_CMD_RMON_STATS_RX_ERRORS + * Per queue rx error stats. + */ +#define MC_CMD_RMON_STATS_RX_ERRORS 0xfe + +#define MC_CMD_0xfe_PRIVILEGE_CTG SRIOV_CTG_GENERAL + +/* MC_CMD_RMON_STATS_RX_ERRORS_IN msgrequest */ +#define MC_CMD_RMON_STATS_RX_ERRORS_IN_LEN 8 +/* The rx queue to get stats for. */ +#define MC_CMD_RMON_STATS_RX_ERRORS_IN_RX_QUEUE_OFST 0 +#define MC_CMD_RMON_STATS_RX_ERRORS_IN_FLAGS_OFST 4 +#define MC_CMD_RMON_STATS_RX_ERRORS_IN_RST_LBN 0 +#define MC_CMD_RMON_STATS_RX_ERRORS_IN_RST_WIDTH 1 + +/* MC_CMD_RMON_STATS_RX_ERRORS_OUT msgresponse */ +#define MC_CMD_RMON_STATS_RX_ERRORS_OUT_LEN 16 +#define MC_CMD_RMON_STATS_RX_ERRORS_OUT_CRC_ERRORS_OFST 0 +#define MC_CMD_RMON_STATS_RX_ERRORS_OUT_TRUNC_ERRORS_OFST 4 +#define MC_CMD_RMON_STATS_RX_ERRORS_OUT_RX_NO_DESC_DROPS_OFST 8 +#define MC_CMD_RMON_STATS_RX_ERRORS_OUT_RX_ABORT_OFST 12 + + +/***********************************/ +/* MC_CMD_GET_PCIE_RESOURCE_INFO + * Find out about available PCIE resources + */ +#define MC_CMD_GET_PCIE_RESOURCE_INFO 0xfd + +/* MC_CMD_GET_PCIE_RESOURCE_INFO_IN msgrequest */ +#define MC_CMD_GET_PCIE_RESOURCE_INFO_IN_LEN 0 + +/* MC_CMD_GET_PCIE_RESOURCE_INFO_OUT msgresponse */ +#define MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_LEN 28 +/* The maximum number of PFs the device can expose */ +#define MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_PFS_OFST 0 +/* The maximum number of VFs the device can expose in total */ +#define MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VFS_OFST 4 +/* The maximum number of MSI-X vectors the device can provide in total */ +#define MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VECTORS_OFST 8 +/* the number of MSI-X vectors the device will allocate by default to each PF + */ +#define MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_DEFAULT_PF_VECTORS_OFST 12 +/* the number of MSI-X vectors the device will allocate by default to each VF + */ +#define MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_DEFAULT_VF_VECTORS_OFST 16 +/* the maximum number of MSI-X vectors the device can allocate to any one PF */ +#define MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_PF_VECTORS_OFST 20 +/* the maximum number of MSI-X vectors the device can allocate to any one VF */ +#define MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VF_VECTORS_OFST 24 + + +/***********************************/ +/* MC_CMD_GET_PORT_MODES + * Find out about available port modes + */ +#define MC_CMD_GET_PORT_MODES 0xff + +#define MC_CMD_0xff_PRIVILEGE_CTG SRIOV_CTG_GENERAL + +/* MC_CMD_GET_PORT_MODES_IN msgrequest */ +#define MC_CMD_GET_PORT_MODES_IN_LEN 0 + +/* MC_CMD_GET_PORT_MODES_OUT msgresponse */ +#define MC_CMD_GET_PORT_MODES_OUT_LEN 12 +/* Bitmask of port modes available on the board (indexed by TLV_PORT_MODE_*) */ +#define MC_CMD_GET_PORT_MODES_OUT_MODES_OFST 0 +/* Default (canonical) board mode */ +#define MC_CMD_GET_PORT_MODES_OUT_DEFAULT_MODE_OFST 4 +/* Current board mode */ +#define MC_CMD_GET_PORT_MODES_OUT_CURRENT_MODE_OFST 8 + + +/***********************************/ +/* MC_CMD_READ_ATB + * Sample voltages on the ATB + */ +#define MC_CMD_READ_ATB 0x100 + +#define MC_CMD_0x100_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_READ_ATB_IN msgrequest */ +#define MC_CMD_READ_ATB_IN_LEN 16 +#define MC_CMD_READ_ATB_IN_SIGNAL_BUS_OFST 0 +#define MC_CMD_READ_ATB_IN_BUS_CCOM 0x0 /* enum */ +#define MC_CMD_READ_ATB_IN_BUS_CKR 0x1 /* enum */ +#define MC_CMD_READ_ATB_IN_BUS_CPCIE 0x8 /* enum */ +#define MC_CMD_READ_ATB_IN_SIGNAL_EN_BITNO_OFST 4 +#define MC_CMD_READ_ATB_IN_SIGNAL_SEL_OFST 8 +#define MC_CMD_READ_ATB_IN_SETTLING_TIME_US_OFST 12 + +/* MC_CMD_READ_ATB_OUT msgresponse */ +#define MC_CMD_READ_ATB_OUT_LEN 4 +#define MC_CMD_READ_ATB_OUT_SAMPLE_MV_OFST 0 + + +/***********************************/ +/* MC_CMD_GET_WORKAROUNDS + * Read the list of all implemented and all currently enabled workarounds. The + * enums here must correspond with those in MC_CMD_WORKAROUND. + */ +#define MC_CMD_GET_WORKAROUNDS 0x59 + +#define MC_CMD_0x59_PRIVILEGE_CTG SRIOV_CTG_GENERAL + +/* MC_CMD_GET_WORKAROUNDS_OUT msgresponse */ +#define MC_CMD_GET_WORKAROUNDS_OUT_LEN 8 +/* Each workaround is represented by a single bit according to the enums below. + */ +#define MC_CMD_GET_WORKAROUNDS_OUT_IMPLEMENTED_OFST 0 +#define MC_CMD_GET_WORKAROUNDS_OUT_ENABLED_OFST 4 +/* enum: Bug 17230 work around. */ +#define MC_CMD_GET_WORKAROUNDS_OUT_BUG17230 0x2 +/* enum: Bug 35388 work around (unsafe EVQ writes). */ +#define MC_CMD_GET_WORKAROUNDS_OUT_BUG35388 0x4 +/* enum: Bug35017 workaround (A64 tables must be identity map) */ +#define MC_CMD_GET_WORKAROUNDS_OUT_BUG35017 0x8 +/* enum: Bug 41750 present (MC_CMD_TRIGGER_INTERRUPT won't work) */ +#define MC_CMD_GET_WORKAROUNDS_OUT_BUG41750 0x10 +/* enum: Bug 42008 present (Interrupts can overtake associated events). Caution + * - before adding code that queries this workaround, remember that there's + * released Monza firmware that doesn't understand MC_CMD_WORKAROUND_BUG42008, + * and will hence (incorrectly) report that the bug doesn't exist. + */ +#define MC_CMD_GET_WORKAROUNDS_OUT_BUG42008 0x20 +/* enum: Bug 26807 features present in firmware (multicast filter chaining) */ +#define MC_CMD_GET_WORKAROUNDS_OUT_BUG26807 0x40 + + +/***********************************/ +/* MC_CMD_PRIVILEGE_MASK + * Read/set privileges of an arbitrary PCIe function + */ +#define MC_CMD_PRIVILEGE_MASK 0x5a + +#define MC_CMD_0x5a_PRIVILEGE_CTG SRIOV_CTG_GENERAL + +/* MC_CMD_PRIVILEGE_MASK_IN msgrequest */ +#define MC_CMD_PRIVILEGE_MASK_IN_LEN 8 +/* The target function to have its mask read or set e.g. PF 0 = 0xFFFF0000, VF + * 1,3 = 0x00030001 + */ +#define MC_CMD_PRIVILEGE_MASK_IN_FUNCTION_OFST 0 +#define MC_CMD_PRIVILEGE_MASK_IN_FUNCTION_PF_LBN 0 +#define MC_CMD_PRIVILEGE_MASK_IN_FUNCTION_PF_WIDTH 16 +#define MC_CMD_PRIVILEGE_MASK_IN_FUNCTION_VF_LBN 16 +#define MC_CMD_PRIVILEGE_MASK_IN_FUNCTION_VF_WIDTH 16 +#define MC_CMD_PRIVILEGE_MASK_IN_VF_NULL 0xffff /* enum */ +/* New privilege mask to be set. The mask will only be changed if the MSB is + * set to 1. + */ +#define MC_CMD_PRIVILEGE_MASK_IN_NEW_MASK_OFST 4 +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_ADMIN 0x1 /* enum */ +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_LINK 0x2 /* enum */ +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_ONLOAD 0x4 /* enum */ +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_PTP 0x8 /* enum */ +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_INSECURE_FILTERS 0x10 /* enum */ +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_MAC_SPOOFING 0x20 /* enum */ +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_UNICAST 0x40 /* enum */ +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_MULTICAST 0x80 /* enum */ +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_BROADCAST 0x100 /* enum */ +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_ALL_MULTICAST 0x200 /* enum */ +#define MC_CMD_PRIVILEGE_MASK_IN_GRP_PROMISCUOUS 0x400 /* enum */ +/* enum: Set this bit to indicate that a new privilege mask is to be set, + * otherwise the command will only read the existing mask. + */ +#define MC_CMD_PRIVILEGE_MASK_IN_DO_CHANGE 0x80000000 + +/* MC_CMD_PRIVILEGE_MASK_OUT msgresponse */ +#define MC_CMD_PRIVILEGE_MASK_OUT_LEN 4 +/* For an admin function, always all the privileges are reported. */ +#define MC_CMD_PRIVILEGE_MASK_OUT_OLD_MASK_OFST 0 + + +/***********************************/ +/* MC_CMD_LINK_STATE_MODE + * Read/set link state mode of a VF + */ +#define MC_CMD_LINK_STATE_MODE 0x5c + +#define MC_CMD_0x5c_PRIVILEGE_CTG SRIOV_CTG_GENERAL + +/* MC_CMD_LINK_STATE_MODE_IN msgrequest */ +#define MC_CMD_LINK_STATE_MODE_IN_LEN 8 +/* The target function to have its link state mode read or set, must be a VF + * e.g. VF 1,3 = 0x00030001 + */ +#define MC_CMD_LINK_STATE_MODE_IN_FUNCTION_OFST 0 +#define MC_CMD_LINK_STATE_MODE_IN_FUNCTION_PF_LBN 0 +#define MC_CMD_LINK_STATE_MODE_IN_FUNCTION_PF_WIDTH 16 +#define MC_CMD_LINK_STATE_MODE_IN_FUNCTION_VF_LBN 16 +#define MC_CMD_LINK_STATE_MODE_IN_FUNCTION_VF_WIDTH 16 +/* New link state mode to be set */ +#define MC_CMD_LINK_STATE_MODE_IN_NEW_MODE_OFST 4 +#define MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_AUTO 0x0 /* enum */ +#define MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_UP 0x1 /* enum */ +#define MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_DOWN 0x2 /* enum */ +/* enum: Use this value to just read the existing setting without modifying it. + */ +#define MC_CMD_LINK_STATE_MODE_IN_DO_NOT_CHANGE 0xffffffff + +/* MC_CMD_LINK_STATE_MODE_OUT msgresponse */ +#define MC_CMD_LINK_STATE_MODE_OUT_LEN 4 +#define MC_CMD_LINK_STATE_MODE_OUT_OLD_MODE_OFST 0 + + +/***********************************/ +/* MC_CMD_GET_SNAPSHOT_LENGTH + * Obtain the curent range of allowable values for the SNAPSHOT_LENGTH + * parameter to MC_CMD_INIT_RXQ. + */ +#define MC_CMD_GET_SNAPSHOT_LENGTH 0x101 + +#define MC_CMD_0x101_PRIVILEGE_CTG SRIOV_CTG_GENERAL + +/* MC_CMD_GET_SNAPSHOT_LENGTH_IN msgrequest */ +#define MC_CMD_GET_SNAPSHOT_LENGTH_IN_LEN 0 + +/* MC_CMD_GET_SNAPSHOT_LENGTH_OUT msgresponse */ +#define MC_CMD_GET_SNAPSHOT_LENGTH_OUT_LEN 8 +/* Minimum acceptable snapshot length. */ +#define MC_CMD_GET_SNAPSHOT_LENGTH_OUT_RX_SNAPLEN_MIN_OFST 0 +/* Maximum acceptable snapshot length. */ +#define MC_CMD_GET_SNAPSHOT_LENGTH_OUT_RX_SNAPLEN_MAX_OFST 4 + + +/***********************************/ +/* MC_CMD_FUSE_DIAGS + * Additional fuse diagnostics + */ +#define MC_CMD_FUSE_DIAGS 0x102 + +#define MC_CMD_0x102_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_FUSE_DIAGS_IN msgrequest */ +#define MC_CMD_FUSE_DIAGS_IN_LEN 0 + +/* MC_CMD_FUSE_DIAGS_OUT msgresponse */ +#define MC_CMD_FUSE_DIAGS_OUT_LEN 48 +/* Total number of mismatched bits between pairs in area 0 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA0_MISMATCH_BITS_OFST 0 +/* Total number of unexpectedly clear (set in B but not A) bits in area 0 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA0_PAIR_A_BAD_BITS_OFST 4 +/* Total number of unexpectedly clear (set in A but not B) bits in area 0 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA0_PAIR_B_BAD_BITS_OFST 8 +/* Checksum of data after logical OR of pairs in area 0 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA0_CHECKSUM_OFST 12 +/* Total number of mismatched bits between pairs in area 1 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA1_MISMATCH_BITS_OFST 16 +/* Total number of unexpectedly clear (set in B but not A) bits in area 1 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA1_PAIR_A_BAD_BITS_OFST 20 +/* Total number of unexpectedly clear (set in A but not B) bits in area 1 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA1_PAIR_B_BAD_BITS_OFST 24 +/* Checksum of data after logical OR of pairs in area 1 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA1_CHECKSUM_OFST 28 +/* Total number of mismatched bits between pairs in area 2 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA2_MISMATCH_BITS_OFST 32 +/* Total number of unexpectedly clear (set in B but not A) bits in area 2 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA2_PAIR_A_BAD_BITS_OFST 36 +/* Total number of unexpectedly clear (set in A but not B) bits in area 2 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA2_PAIR_B_BAD_BITS_OFST 40 +/* Checksum of data after logical OR of pairs in area 2 */ +#define MC_CMD_FUSE_DIAGS_OUT_AREA2_CHECKSUM_OFST 44 + + +/***********************************/ +/* MC_CMD_PRIVILEGE_MODIFY + * Modify the privileges of a set of PCIe functions. Note that this operation + * only effects non-admin functions unless the admin privilege itself is + * included in one of the masks provided. + */ +#define MC_CMD_PRIVILEGE_MODIFY 0x60 + +#define MC_CMD_0x60_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_PRIVILEGE_MODIFY_IN msgrequest */ +#define MC_CMD_PRIVILEGE_MODIFY_IN_LEN 16 +/* The groups of functions to have their privilege masks modified. */ +#define MC_CMD_PRIVILEGE_MODIFY_IN_FN_GROUP_OFST 0 +#define MC_CMD_PRIVILEGE_MODIFY_IN_NONE 0x0 /* enum */ +#define MC_CMD_PRIVILEGE_MODIFY_IN_ALL 0x1 /* enum */ +#define MC_CMD_PRIVILEGE_MODIFY_IN_PFS_ONLY 0x2 /* enum */ +#define MC_CMD_PRIVILEGE_MODIFY_IN_VFS_ONLY 0x3 /* enum */ +#define MC_CMD_PRIVILEGE_MODIFY_IN_VFS_OF_PF 0x4 /* enum */ +#define MC_CMD_PRIVILEGE_MODIFY_IN_ONE 0x5 /* enum */ +/* For VFS_OF_PF specify the PF, for ONE specify the target function */ +#define MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_OFST 4 +#define MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_PF_LBN 0 +#define MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_PF_WIDTH 16 +#define MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_VF_LBN 16 +#define MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_VF_WIDTH 16 +/* Privileges to be added to the target functions. For privilege definitions + * refer to the command MC_CMD_PRIVILEGE_MASK + */ +#define MC_CMD_PRIVILEGE_MODIFY_IN_ADD_MASK_OFST 8 +/* Privileges to be removed from the target functions. For privilege + * definitions refer to the command MC_CMD_PRIVILEGE_MASK + */ +#define MC_CMD_PRIVILEGE_MODIFY_IN_REMOVE_MASK_OFST 12 + +/* MC_CMD_PRIVILEGE_MODIFY_OUT msgresponse */ +#define MC_CMD_PRIVILEGE_MODIFY_OUT_LEN 0 + + +/***********************************/ +/* MC_CMD_XPM_READ_BYTES + * Read XPM memory + */ +#define MC_CMD_XPM_READ_BYTES 0x103 + +#define MC_CMD_0x103_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_XPM_READ_BYTES_IN msgrequest */ +#define MC_CMD_XPM_READ_BYTES_IN_LEN 8 +/* Start address (byte) */ +#define MC_CMD_XPM_READ_BYTES_IN_ADDR_OFST 0 +/* Count (bytes) */ +#define MC_CMD_XPM_READ_BYTES_IN_COUNT_OFST 4 + +/* MC_CMD_XPM_READ_BYTES_OUT msgresponse */ +#define MC_CMD_XPM_READ_BYTES_OUT_LENMIN 0 +#define MC_CMD_XPM_READ_BYTES_OUT_LENMAX 252 +#define MC_CMD_XPM_READ_BYTES_OUT_LEN(num) (0+1*(num)) +/* Data */ +#define MC_CMD_XPM_READ_BYTES_OUT_DATA_OFST 0 +#define MC_CMD_XPM_READ_BYTES_OUT_DATA_LEN 1 +#define MC_CMD_XPM_READ_BYTES_OUT_DATA_MINNUM 0 +#define MC_CMD_XPM_READ_BYTES_OUT_DATA_MAXNUM 252 + + +/***********************************/ +/* MC_CMD_XPM_WRITE_BYTES + * Write XPM memory + */ +#define MC_CMD_XPM_WRITE_BYTES 0x104 + +#define MC_CMD_0x104_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_XPM_WRITE_BYTES_IN msgrequest */ +#define MC_CMD_XPM_WRITE_BYTES_IN_LENMIN 8 +#define MC_CMD_XPM_WRITE_BYTES_IN_LENMAX 252 +#define MC_CMD_XPM_WRITE_BYTES_IN_LEN(num) (8+1*(num)) +/* Start address (byte) */ +#define MC_CMD_XPM_WRITE_BYTES_IN_ADDR_OFST 0 +/* Count (bytes) */ +#define MC_CMD_XPM_WRITE_BYTES_IN_COUNT_OFST 4 +/* Data */ +#define MC_CMD_XPM_WRITE_BYTES_IN_DATA_OFST 8 +#define MC_CMD_XPM_WRITE_BYTES_IN_DATA_LEN 1 +#define MC_CMD_XPM_WRITE_BYTES_IN_DATA_MINNUM 0 +#define MC_CMD_XPM_WRITE_BYTES_IN_DATA_MAXNUM 244 + +/* MC_CMD_XPM_WRITE_BYTES_OUT msgresponse */ +#define MC_CMD_XPM_WRITE_BYTES_OUT_LEN 0 + + +/***********************************/ +/* MC_CMD_XPM_READ_SECTOR + * Read XPM sector + */ +#define MC_CMD_XPM_READ_SECTOR 0x105 + +#define MC_CMD_0x105_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_XPM_READ_SECTOR_IN msgrequest */ +#define MC_CMD_XPM_READ_SECTOR_IN_LEN 8 +/* Sector index */ +#define MC_CMD_XPM_READ_SECTOR_IN_INDEX_OFST 0 +/* Sector size */ +#define MC_CMD_XPM_READ_SECTOR_IN_SIZE_OFST 4 + +/* MC_CMD_XPM_READ_SECTOR_OUT msgresponse */ +#define MC_CMD_XPM_READ_SECTOR_OUT_LENMIN 4 +#define MC_CMD_XPM_READ_SECTOR_OUT_LENMAX 36 +#define MC_CMD_XPM_READ_SECTOR_OUT_LEN(num) (4+1*(num)) +/* Sector type */ +#define MC_CMD_XPM_READ_SECTOR_OUT_TYPE_OFST 0 +#define MC_CMD_XPM_READ_SECTOR_OUT_BLANK 0x0 /* enum */ +#define MC_CMD_XPM_READ_SECTOR_OUT_CRYPTO_KEY_128 0x1 /* enum */ +#define MC_CMD_XPM_READ_SECTOR_OUT_CRYPTO_KEY_256 0x2 /* enum */ +#define MC_CMD_XPM_READ_SECTOR_OUT_INVALID 0xff /* enum */ +/* Sector data */ +#define MC_CMD_XPM_READ_SECTOR_OUT_DATA_OFST 4 +#define MC_CMD_XPM_READ_SECTOR_OUT_DATA_LEN 1 +#define MC_CMD_XPM_READ_SECTOR_OUT_DATA_MINNUM 0 +#define MC_CMD_XPM_READ_SECTOR_OUT_DATA_MAXNUM 32 + + +/***********************************/ +/* MC_CMD_XPM_WRITE_SECTOR + * Write XPM sector + */ +#define MC_CMD_XPM_WRITE_SECTOR 0x106 + +#define MC_CMD_0x106_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_XPM_WRITE_SECTOR_IN msgrequest */ +#define MC_CMD_XPM_WRITE_SECTOR_IN_LENMIN 12 +#define MC_CMD_XPM_WRITE_SECTOR_IN_LENMAX 44 +#define MC_CMD_XPM_WRITE_SECTOR_IN_LEN(num) (12+1*(num)) +/* If writing fails due to an uncorrectable error, try up to RETRIES following + * sectors (or until no more space available). If 0, only one write attempt is + * made. Note that uncorrectable errors are unlikely, thanks to XPM self-repair + * mechanism. + */ +#define MC_CMD_XPM_WRITE_SECTOR_IN_RETRIES_OFST 0 +#define MC_CMD_XPM_WRITE_SECTOR_IN_RETRIES_LEN 1 +#define MC_CMD_XPM_WRITE_SECTOR_IN_RESERVED_OFST 1 +#define MC_CMD_XPM_WRITE_SECTOR_IN_RESERVED_LEN 3 +/* Sector type */ +#define MC_CMD_XPM_WRITE_SECTOR_IN_TYPE_OFST 4 +/* Enum values, see field(s): */ +/* MC_CMD_XPM_READ_SECTOR_OUT/TYPE */ +/* Sector size */ +#define MC_CMD_XPM_WRITE_SECTOR_IN_SIZE_OFST 8 +/* Sector data */ +#define MC_CMD_XPM_WRITE_SECTOR_IN_DATA_OFST 12 +#define MC_CMD_XPM_WRITE_SECTOR_IN_DATA_LEN 1 +#define MC_CMD_XPM_WRITE_SECTOR_IN_DATA_MINNUM 0 +#define MC_CMD_XPM_WRITE_SECTOR_IN_DATA_MAXNUM 32 + +/* MC_CMD_XPM_WRITE_SECTOR_OUT msgresponse */ +#define MC_CMD_XPM_WRITE_SECTOR_OUT_LEN 4 +/* New sector index */ +#define MC_CMD_XPM_WRITE_SECTOR_OUT_INDEX_OFST 0 + + +/***********************************/ +/* MC_CMD_XPM_INVALIDATE_SECTOR + * Invalidate XPM sector + */ +#define MC_CMD_XPM_INVALIDATE_SECTOR 0x107 + +#define MC_CMD_0x107_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_XPM_INVALIDATE_SECTOR_IN msgrequest */ +#define MC_CMD_XPM_INVALIDATE_SECTOR_IN_LEN 4 +/* Sector index */ +#define MC_CMD_XPM_INVALIDATE_SECTOR_IN_INDEX_OFST 0 + +/* MC_CMD_XPM_INVALIDATE_SECTOR_OUT msgresponse */ +#define MC_CMD_XPM_INVALIDATE_SECTOR_OUT_LEN 0 + + +/***********************************/ +/* MC_CMD_XPM_BLANK_CHECK + * Blank-check XPM memory and report bad locations + */ +#define MC_CMD_XPM_BLANK_CHECK 0x108 + +#define MC_CMD_0x108_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_XPM_BLANK_CHECK_IN msgrequest */ +#define MC_CMD_XPM_BLANK_CHECK_IN_LEN 8 +/* Start address (byte) */ +#define MC_CMD_XPM_BLANK_CHECK_IN_ADDR_OFST 0 +/* Count (bytes) */ +#define MC_CMD_XPM_BLANK_CHECK_IN_COUNT_OFST 4 + +/* MC_CMD_XPM_BLANK_CHECK_OUT msgresponse */ +#define MC_CMD_XPM_BLANK_CHECK_OUT_LENMIN 4 +#define MC_CMD_XPM_BLANK_CHECK_OUT_LENMAX 252 +#define MC_CMD_XPM_BLANK_CHECK_OUT_LEN(num) (4+2*(num)) +/* Total number of bad (non-blank) locations */ +#define MC_CMD_XPM_BLANK_CHECK_OUT_BAD_COUNT_OFST 0 +/* Addresses of bad locations (may be less than BAD_COUNT, if all cannot fit + * into MCDI response) + */ +#define MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_OFST 4 +#define MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_LEN 2 +#define MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_MINNUM 0 +#define MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_MAXNUM 124 + + +/***********************************/ +/* MC_CMD_XPM_REPAIR + * Blank-check and repair XPM memory + */ +#define MC_CMD_XPM_REPAIR 0x109 + +#define MC_CMD_0x109_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_XPM_REPAIR_IN msgrequest */ +#define MC_CMD_XPM_REPAIR_IN_LEN 8 +/* Start address (byte) */ +#define MC_CMD_XPM_REPAIR_IN_ADDR_OFST 0 +/* Count (bytes) */ +#define MC_CMD_XPM_REPAIR_IN_COUNT_OFST 4 + +/* MC_CMD_XPM_REPAIR_OUT msgresponse */ +#define MC_CMD_XPM_REPAIR_OUT_LEN 0 + + +/***********************************/ +/* MC_CMD_XPM_DECODER_TEST + * Test XPM memory address decoders for gross manufacturing defects. Can only + * be performed on an unprogrammed part. + */ +#define MC_CMD_XPM_DECODER_TEST 0x10a + +#define MC_CMD_0x10a_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_XPM_DECODER_TEST_IN msgrequest */ +#define MC_CMD_XPM_DECODER_TEST_IN_LEN 0 + +/* MC_CMD_XPM_DECODER_TEST_OUT msgresponse */ +#define MC_CMD_XPM_DECODER_TEST_OUT_LEN 0 + + +/***********************************/ +/* MC_CMD_XPM_WRITE_TEST + * XPM memory write test. Test XPM write logic for gross manufacturing defects + * by writing to a dedicated test row. There are 16 locations in the test row + * and the test can only be performed on locations that have not been + * previously used (i.e. can be run at most 16 times). The test will pick the + * first available location to use, or fail with ENOSPC if none left. + */ +#define MC_CMD_XPM_WRITE_TEST 0x10b + +#define MC_CMD_0x10b_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_XPM_WRITE_TEST_IN msgrequest */ +#define MC_CMD_XPM_WRITE_TEST_IN_LEN 0 + +/* MC_CMD_XPM_WRITE_TEST_OUT msgresponse */ +#define MC_CMD_XPM_WRITE_TEST_OUT_LEN 0 + + #endif /* MCDI_PCOL_H */ diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 47d1e3a96522..4d35313a239d 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -925,6 +925,7 @@ struct vfdi_status; * @stats_lock: Statistics update lock. Must be held when calling * efx_nic_type::{update,start,stop}_stats. * @n_rx_noskb_drops: Count of RX packets dropped due to failure to allocate an skb + * @mc_promisc: Whether in multicast promiscuous mode when last changed * * This is stored in the private area of the &struct net_device. */ @@ -1072,6 +1073,7 @@ struct efx_nic { int last_irq_cpu; spinlock_t stats_lock; atomic_t n_rx_noskb_drops; + bool mc_promisc; }; static inline int efx_dev_registered(struct efx_nic *efx) diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index 31ff9084d9a4..0b536e27d3b2 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -506,6 +506,7 @@ enum { * @rx_rss_context_exclusive: Whether our RSS context is exclusive or shared * @stats: Hardware statistics * @workaround_35388: Flag: firmware supports workaround for bug 35388 + * @workaround_26807: Flag: firmware supports workaround for bug 26807 * @must_check_datapath_caps: Flag: @datapath_caps needs to be revalidated * after MC reboot * @datapath_caps: Capabilities of datapath firmware (FLAGS1 field of @@ -535,6 +536,7 @@ struct efx_ef10_nic_data { bool rx_rss_context_exclusive; u64 stats[EF10_STAT_COUNT]; bool workaround_35388; + bool workaround_26807; bool must_check_datapath_caps; u32 datapath_caps; unsigned int rx_dpcpu_fw_id; diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c index b323b9167526..b2f886d90429 100644 --- a/drivers/net/ethernet/sfc/siena.c +++ b/drivers/net/ethernet/sfc/siena.c @@ -1042,9 +1042,5 @@ const struct efx_nic_type siena_a0_nic_type = { .max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS, .hwtstamp_filters = (1 << HWTSTAMP_FILTER_NONE | 1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT | - 1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC | - 1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ | - 1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT | - 1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC | - 1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ), + 1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT), }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c index cb888d3ebbdc..78e9d1861896 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c @@ -25,66 +25,53 @@ # define LPC18XX_CREG_CREG6_ETHMODE_MII 0x0 # define LPC18XX_CREG_CREG6_ETHMODE_RMII 0x4 -struct lpc18xx_dwmac_priv_data { +static int lpc18xx_dwmac_probe(struct platform_device *pdev) +{ + struct plat_stmmacenet_data *plat_dat; + struct stmmac_resources stmmac_res; struct regmap *reg; - int interface; -}; + u8 ethmode; + int ret; -static void *lpc18xx_dwmac_setup(struct platform_device *pdev) -{ - struct lpc18xx_dwmac_priv_data *dwmac; + ret = stmmac_get_platform_resources(pdev, &stmmac_res); + if (ret) + return ret; - dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return ERR_PTR(-ENOMEM); + plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac); + if (IS_ERR(plat_dat)) + return PTR_ERR(plat_dat); - dwmac->interface = of_get_phy_mode(pdev->dev.of_node); - if (dwmac->interface < 0) - return ERR_PTR(dwmac->interface); + plat_dat->has_gmac = true; - dwmac->reg = syscon_regmap_lookup_by_compatible("nxp,lpc1850-creg"); - if (IS_ERR(dwmac->reg)) { - dev_err(&pdev->dev, "Syscon lookup failed\n"); - return dwmac->reg; + reg = syscon_regmap_lookup_by_compatible("nxp,lpc1850-creg"); + if (IS_ERR(reg)) { + dev_err(&pdev->dev, "syscon lookup failed\n"); + return PTR_ERR(reg); } - return dwmac; -} - -static int lpc18xx_dwmac_init(struct platform_device *pdev, void *priv) -{ - struct lpc18xx_dwmac_priv_data *dwmac = priv; - u8 ethmode; - - if (dwmac->interface == PHY_INTERFACE_MODE_MII) { + if (plat_dat->interface == PHY_INTERFACE_MODE_MII) { ethmode = LPC18XX_CREG_CREG6_ETHMODE_MII; - } else if (dwmac->interface == PHY_INTERFACE_MODE_RMII) { + } else if (plat_dat->interface == PHY_INTERFACE_MODE_RMII) { ethmode = LPC18XX_CREG_CREG6_ETHMODE_RMII; } else { dev_err(&pdev->dev, "Only MII and RMII mode supported\n"); return -EINVAL; } - regmap_update_bits(dwmac->reg, LPC18XX_CREG_CREG6, + regmap_update_bits(reg, LPC18XX_CREG_CREG6, LPC18XX_CREG_CREG6_ETHMODE_MASK, ethmode); - return 0; + return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); } -static const struct stmmac_of_data lpc18xx_dwmac_data = { - .has_gmac = 1, - .setup = lpc18xx_dwmac_setup, - .init = lpc18xx_dwmac_init, -}; - static const struct of_device_id lpc18xx_dwmac_match[] = { - { .compatible = "nxp,lpc1850-dwmac", .data = &lpc18xx_dwmac_data }, + { .compatible = "nxp,lpc1850-dwmac" }, { } }; MODULE_DEVICE_TABLE(of, lpc18xx_dwmac_match); static struct platform_driver lpc18xx_dwmac_driver = { - .probe = stmmac_pltfr_probe, + .probe = lpc18xx_dwmac_probe, .remove = stmmac_pltfr_remove, .driver = { .name = "lpc18xx-dwmac", diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c index 61a324a87d09..c1bac1912b37 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c @@ -47,36 +47,45 @@ static void meson6_dwmac_fix_mac_speed(void *priv, unsigned int speed) writel(val, dwmac->reg); } -static void *meson6_dwmac_setup(struct platform_device *pdev) +static int meson6_dwmac_probe(struct platform_device *pdev) { + struct plat_stmmacenet_data *plat_dat; + struct stmmac_resources stmmac_res; struct meson_dwmac *dwmac; struct resource *res; + int ret; + + ret = stmmac_get_platform_resources(pdev, &stmmac_res); + if (ret) + return ret; + + plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac); + if (IS_ERR(plat_dat)) + return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); if (!dwmac) - return ERR_PTR(-ENOMEM); + return -ENOMEM; res = platform_get_resource(pdev, IORESOURCE_MEM, 1); dwmac->reg = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(dwmac->reg)) - return ERR_CAST(dwmac->reg); + return PTR_ERR(dwmac->reg); - return dwmac; -} + plat_dat->bsp_priv = dwmac; + plat_dat->fix_mac_speed = meson6_dwmac_fix_mac_speed; -static const struct stmmac_of_data meson6_dwmac_data = { - .setup = meson6_dwmac_setup, - .fix_mac_speed = meson6_dwmac_fix_mac_speed, -}; + return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); +} static const struct of_device_id meson6_dwmac_match[] = { - { .compatible = "amlogic,meson6-dwmac", .data = &meson6_dwmac_data}, + { .compatible = "amlogic,meson6-dwmac" }, { } }; MODULE_DEVICE_TABLE(of, meson6_dwmac_match); static struct platform_driver meson6_dwmac_driver = { - .probe = stmmac_pltfr_probe, + .probe = meson6_dwmac_probe, .remove = stmmac_pltfr_remove, .driver = { .name = "meson6-dwmac", diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index f3918c7e7eeb..eca0eb845241 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -104,18 +104,20 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries) * this function is to read the driver parameters from device-tree and * set some private fields that will be used by the main at runtime. */ -static int stmmac_probe_config_dt(struct platform_device *pdev, - struct plat_stmmacenet_data *plat, - const char **mac) +struct plat_stmmacenet_data * +stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) { struct device_node *np = pdev->dev.of_node; + struct plat_stmmacenet_data *plat; + const struct stmmac_of_data *data; struct stmmac_dma_cfg *dma_cfg; - const struct of_device_id *device; - struct device *dev = &pdev->dev; - device = of_match_device(dev->driver->of_match_table, dev); - if (device->data) { - const struct stmmac_of_data *data = device->data; + plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); + if (!plat) + return ERR_PTR(-ENOMEM); + + data = of_device_get_match_data(&pdev->dev); + if (data) { plat->has_gmac = data->has_gmac; plat->enh_desc = data->enh_desc; plat->tx_coe = data->tx_coe; @@ -151,7 +153,7 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, /* If phy-handle is not specified, check if we have a fixed-phy */ if (!plat->phy_node && of_phy_is_fixed_link(np)) { if ((of_phy_register_fixed_link(np) < 0)) - return -ENODEV; + return ERR_PTR(-ENODEV); plat->phy_node = of_node_get(np); } @@ -182,6 +184,12 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, */ plat->maxmtu = JUMBO_LEN; + /* Set default value for multicast hash bins */ + plat->multicast_filter_bins = HASH_TABLE_SIZE; + + /* Set default value for unicast filter entries */ + plat->unicast_filter_entries = 1; + /* * Currently only the properties needed on SPEAr600 * are provided. All other properties should be added @@ -222,7 +230,7 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, GFP_KERNEL); if (!dma_cfg) { of_node_put(np); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } plat->dma_cfg = dma_cfg; of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl); @@ -240,44 +248,34 @@ static int stmmac_probe_config_dt(struct platform_device *pdev, pr_warn("force_sf_dma_mode is ignored if force_thresh_dma_mode is set."); } - return 0; + return plat; } #else -static int stmmac_probe_config_dt(struct platform_device *pdev, - struct plat_stmmacenet_data *plat, - const char **mac) +struct plat_stmmacenet_data * +stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) { - return -ENOSYS; + return ERR_PTR(-ENOSYS); } #endif /* CONFIG_OF */ +EXPORT_SYMBOL_GPL(stmmac_probe_config_dt); -/** - * stmmac_pltfr_probe - platform driver probe. - * @pdev: platform device pointer - * Description: platform_device probe function. It is to allocate - * the necessary platform resources, invoke custom helper (if required) and - * invoke the main probe function. - */ -int stmmac_pltfr_probe(struct platform_device *pdev) +int stmmac_get_platform_resources(struct platform_device *pdev, + struct stmmac_resources *stmmac_res) { - struct stmmac_resources stmmac_res; - int ret = 0; struct resource *res; - struct device *dev = &pdev->dev; - struct plat_stmmacenet_data *plat_dat = NULL; - memset(&stmmac_res, 0, sizeof(stmmac_res)); + memset(stmmac_res, 0, sizeof(*stmmac_res)); /* Get IRQ information early to have an ability to ask for deferred * probe if needed before we went too far with resource allocation. */ - stmmac_res.irq = platform_get_irq_byname(pdev, "macirq"); - if (stmmac_res.irq < 0) { - if (stmmac_res.irq != -EPROBE_DEFER) { - dev_err(dev, + stmmac_res->irq = platform_get_irq_byname(pdev, "macirq"); + if (stmmac_res->irq < 0) { + if (stmmac_res->irq != -EPROBE_DEFER) { + dev_err(&pdev->dev, "MAC IRQ configuration information not found\n"); } - return stmmac_res.irq; + return stmmac_res->irq; } /* On some platforms e.g. SPEAr the wake up irq differs from the mac irq @@ -287,45 +285,61 @@ int stmmac_pltfr_probe(struct platform_device *pdev) * In case the wake up interrupt is not passed from the platform * so the driver will continue to use the mac irq (ndev->irq) */ - stmmac_res.wol_irq = platform_get_irq_byname(pdev, "eth_wake_irq"); - if (stmmac_res.wol_irq < 0) { - if (stmmac_res.wol_irq == -EPROBE_DEFER) + stmmac_res->wol_irq = platform_get_irq_byname(pdev, "eth_wake_irq"); + if (stmmac_res->wol_irq < 0) { + if (stmmac_res->wol_irq == -EPROBE_DEFER) return -EPROBE_DEFER; - stmmac_res.wol_irq = stmmac_res.irq; + stmmac_res->wol_irq = stmmac_res->irq; } - stmmac_res.lpi_irq = platform_get_irq_byname(pdev, "eth_lpi"); - if (stmmac_res.lpi_irq == -EPROBE_DEFER) + stmmac_res->lpi_irq = platform_get_irq_byname(pdev, "eth_lpi"); + if (stmmac_res->lpi_irq == -EPROBE_DEFER) return -EPROBE_DEFER; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - stmmac_res.addr = devm_ioremap_resource(dev, res); - if (IS_ERR(stmmac_res.addr)) - return PTR_ERR(stmmac_res.addr); - - plat_dat = dev_get_platdata(&pdev->dev); - - if (!plat_dat) - plat_dat = devm_kzalloc(&pdev->dev, - sizeof(struct plat_stmmacenet_data), - GFP_KERNEL); - if (!plat_dat) { - pr_err("%s: ERROR: no memory", __func__); - return -ENOMEM; - } + stmmac_res->addr = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(stmmac_res->addr)) + return PTR_ERR(stmmac_res->addr); - /* Set default value for multicast hash bins */ - plat_dat->multicast_filter_bins = HASH_TABLE_SIZE; + return 0; +} +EXPORT_SYMBOL_GPL(stmmac_get_platform_resources); - /* Set default value for unicast filter entries */ - plat_dat->unicast_filter_entries = 1; +/** + * stmmac_pltfr_probe - platform driver probe. + * @pdev: platform device pointer + * Description: platform_device probe function. It is to allocate + * the necessary platform resources, invoke custom helper (if required) and + * invoke the main probe function. + */ +int stmmac_pltfr_probe(struct platform_device *pdev) +{ + struct plat_stmmacenet_data *plat_dat; + struct stmmac_resources stmmac_res; + int ret; + + ret = stmmac_get_platform_resources(pdev, &stmmac_res); + if (ret) + return ret; if (pdev->dev.of_node) { - ret = stmmac_probe_config_dt(pdev, plat_dat, &stmmac_res.mac); - if (ret) { - pr_err("%s: main dt probe failed", __func__); - return ret; + plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac); + if (IS_ERR(plat_dat)) { + dev_err(&pdev->dev, "dt configuration failed\n"); + return PTR_ERR(plat_dat); + } + } else { + plat_dat = dev_get_platdata(&pdev->dev); + if (!plat_dat) { + dev_err(&pdev->dev, "no platform data provided\n"); + return -EINVAL; } + + /* Set default value for multicast hash bins */ + plat_dat->multicast_filter_bins = HASH_TABLE_SIZE; + + /* Set default value for unicast filter entries */ + plat_dat->unicast_filter_entries = 1; } /* Custom setup (if needed) */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h index 71da86d7bd00..84ceb5342686 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h @@ -19,6 +19,14 @@ #ifndef __STMMAC_PLATFORM_H__ #define __STMMAC_PLATFORM_H__ +#include "stmmac.h" + +struct plat_stmmacenet_data * +stmmac_probe_config_dt(struct platform_device *pdev, const char **mac); + +int stmmac_get_platform_resources(struct platform_device *pdev, + struct stmmac_resources *stmmac_res); + int stmmac_pltfr_probe(struct platform_device *pdev); int stmmac_pltfr_remove(struct platform_device *pdev); extern const struct dev_pm_ops stmmac_pltfr_pm_ops; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index ec8ed30196f3..3ca87f26582a 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -2142,7 +2142,6 @@ MODULE_DEVICE_TABLE(of, of_match); static struct platform_driver netcp_driver = { .driver = { .name = "netcp-1.0", - .owner = THIS_MODULE, .of_match_table = of_match, }, .probe = netcp_probe, diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index dd4544085db3..26cd14ccf4d5 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -589,6 +589,7 @@ struct nvsp_message { #define NETVSC_MTU 65536 +#define NETVSC_MTU_MIN 68 #define NETVSC_RECEIVE_BUFFER_SIZE (1024*1024*16) /* 16MB */ #define NETVSC_RECEIVE_BUFFER_SIZE_LEGACY (1024*1024*15) /* 15MB */ diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 358475ed9b59..7b36d5fecc1f 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -106,7 +106,7 @@ static int netvsc_open(struct net_device *net) return ret; } - netif_tx_start_all_queues(net); + netif_tx_wake_all_queues(net); nvdev = hv_get_drvdata(device_obj); rdev = nvdev->extension; @@ -120,15 +120,56 @@ static int netvsc_close(struct net_device *net) { struct net_device_context *net_device_ctx = netdev_priv(net); struct hv_device *device_obj = net_device_ctx->device_ctx; + struct netvsc_device *nvdev = hv_get_drvdata(device_obj); int ret; + u32 aread, awrite, i, msec = 10, retry = 0, retry_max = 20; + struct vmbus_channel *chn; netif_tx_disable(net); /* Make sure netvsc_set_multicast_list doesn't re-enable filter! */ cancel_work_sync(&net_device_ctx->work); ret = rndis_filter_close(device_obj); - if (ret != 0) + if (ret != 0) { netdev_err(net, "unable to close device (ret %d).\n", ret); + return ret; + } + + /* Ensure pending bytes in ring are read */ + while (true) { + aread = 0; + for (i = 0; i < nvdev->num_chn; i++) { + chn = nvdev->chn_table[i]; + if (!chn) + continue; + + hv_get_ringbuffer_availbytes(&chn->inbound, &aread, + &awrite); + + if (aread) + break; + + hv_get_ringbuffer_availbytes(&chn->outbound, &aread, + &awrite); + + if (aread) + break; + } + + retry++; + if (retry > retry_max || aread == 0) + break; + + msleep(msec); + + if (msec < 1000) + msec *= 2; + } + + if (aread) { + netdev_err(net, "Ring buffer not empty after closing rndis\n"); + ret = -ETIMEDOUT; + } return ret; } @@ -736,6 +777,7 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu) struct netvsc_device *nvdev = hv_get_drvdata(hdev); struct netvsc_device_info device_info; int limit = ETH_DATA_LEN; + int ret = 0; if (nvdev == NULL || nvdev->destroy) return -ENODEV; @@ -743,13 +785,14 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu) if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2) limit = NETVSC_MTU - ETH_HLEN; - /* Hyper-V hosts don't support MTU < ETH_DATA_LEN (1500) */ - if (mtu < ETH_DATA_LEN || mtu > limit) + if (mtu < NETVSC_MTU_MIN || mtu > limit) return -EINVAL; + ret = netvsc_close(ndev); + if (ret) + goto out; + nvdev->start_remove = true; - cancel_work_sync(&ndevctx->work); - netif_tx_disable(ndev); rndis_filter_device_remove(hdev); ndev->mtu = mtu; @@ -759,9 +802,11 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu) device_info.ring_size = ring_size; device_info.max_num_vrss_chns = max_num_vrss_chns; rndis_filter_device_add(hdev, &device_info); - netif_tx_wake_all_queues(ndev); - return 0; +out: + netvsc_open(ndev); + + return ret; } static struct rtnl_link_stats64 *netvsc_get_stats64(struct net_device *net, diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 236aeb76ef22..2e40417a8087 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1054,7 +1054,7 @@ int rndis_filter_device_add(struct hv_device *dev, ret = rndis_filter_query_device(rndis_device, RNDIS_OID_GEN_MAXIMUM_FRAME_SIZE, &mtu, &size); - if (ret == 0 && size == sizeof(u32)) + if (ret == 0 && size == sizeof(u32) && mtu < net_device->ndev->mtu) net_device->ndev->mtu = mtu; /* Get the mac address */ diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 94570aace241..cc56fac3c3f8 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -38,69 +38,68 @@ #include <net/net_namespace.h> #define TX_Q_LIMIT 32 -struct ifb_private { +struct ifb_q_private { + struct net_device *dev; struct tasklet_struct ifb_tasklet; - int tasklet_pending; - - struct u64_stats_sync rsync; + int tasklet_pending; + int txqnum; struct sk_buff_head rq; - u64 rx_packets; - u64 rx_bytes; + u64 rx_packets; + u64 rx_bytes; + struct u64_stats_sync rsync; struct u64_stats_sync tsync; + u64 tx_packets; + u64 tx_bytes; struct sk_buff_head tq; - u64 tx_packets; - u64 tx_bytes; -}; +} ____cacheline_aligned_in_smp; -static int numifbs = 2; +struct ifb_dev_private { + struct ifb_q_private *tx_private; +}; -static void ri_tasklet(unsigned long dev); static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev); static int ifb_open(struct net_device *dev); static int ifb_close(struct net_device *dev); -static void ri_tasklet(unsigned long dev) +static void ifb_ri_tasklet(unsigned long _txp) { - struct net_device *_dev = (struct net_device *)dev; - struct ifb_private *dp = netdev_priv(_dev); + struct ifb_q_private *txp = (struct ifb_q_private *)_txp; struct netdev_queue *txq; struct sk_buff *skb; - txq = netdev_get_tx_queue(_dev, 0); - if ((skb = skb_peek(&dp->tq)) == NULL) { - if (__netif_tx_trylock(txq)) { - skb_queue_splice_tail_init(&dp->rq, &dp->tq); - __netif_tx_unlock(txq); - } else { - /* reschedule */ + txq = netdev_get_tx_queue(txp->dev, txp->txqnum); + skb = skb_peek(&txp->tq); + if (!skb) { + if (!__netif_tx_trylock(txq)) goto resched; - } + skb_queue_splice_tail_init(&txp->rq, &txp->tq); + __netif_tx_unlock(txq); } - while ((skb = __skb_dequeue(&dp->tq)) != NULL) { + while ((skb = __skb_dequeue(&txp->tq)) != NULL) { u32 from = G_TC_FROM(skb->tc_verd); skb->tc_verd = 0; skb->tc_verd = SET_TC_NCLS(skb->tc_verd); - u64_stats_update_begin(&dp->tsync); - dp->tx_packets++; - dp->tx_bytes += skb->len; - u64_stats_update_end(&dp->tsync); + u64_stats_update_begin(&txp->tsync); + txp->tx_packets++; + txp->tx_bytes += skb->len; + u64_stats_update_end(&txp->tsync); rcu_read_lock(); - skb->dev = dev_get_by_index_rcu(dev_net(_dev), skb->skb_iif); + skb->dev = dev_get_by_index_rcu(dev_net(txp->dev), skb->skb_iif); if (!skb->dev) { rcu_read_unlock(); dev_kfree_skb(skb); - _dev->stats.tx_dropped++; - if (skb_queue_len(&dp->tq) != 0) + txp->dev->stats.tx_dropped++; + if (skb_queue_len(&txp->tq) != 0) goto resched; break; } rcu_read_unlock(); - skb->skb_iif = _dev->ifindex; + skb->skb_iif = txp->dev->ifindex; if (from & AT_EGRESS) { dev_queue_xmit(skb); @@ -112,10 +111,11 @@ static void ri_tasklet(unsigned long dev) } if (__netif_tx_trylock(txq)) { - if ((skb = skb_peek(&dp->rq)) == NULL) { - dp->tasklet_pending = 0; - if (netif_queue_stopped(_dev)) - netif_wake_queue(_dev); + skb = skb_peek(&txp->rq); + if (!skb) { + txp->tasklet_pending = 0; + if (netif_tx_queue_stopped(txq)) + netif_tx_wake_queue(txq); } else { __netif_tx_unlock(txq); goto resched; @@ -123,8 +123,8 @@ static void ri_tasklet(unsigned long dev) __netif_tx_unlock(txq); } else { resched: - dp->tasklet_pending = 1; - tasklet_schedule(&dp->ifb_tasklet); + txp->tasklet_pending = 1; + tasklet_schedule(&txp->ifb_tasklet); } } @@ -132,29 +132,58 @@ resched: static struct rtnl_link_stats64 *ifb_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { - struct ifb_private *dp = netdev_priv(dev); + struct ifb_dev_private *dp = netdev_priv(dev); + struct ifb_q_private *txp = dp->tx_private; unsigned int start; - - do { - start = u64_stats_fetch_begin_irq(&dp->rsync); - stats->rx_packets = dp->rx_packets; - stats->rx_bytes = dp->rx_bytes; - } while (u64_stats_fetch_retry_irq(&dp->rsync, start)); - - do { - start = u64_stats_fetch_begin_irq(&dp->tsync); - - stats->tx_packets = dp->tx_packets; - stats->tx_bytes = dp->tx_bytes; - - } while (u64_stats_fetch_retry_irq(&dp->tsync, start)); - + u64 packets, bytes; + int i; + + for (i = 0; i < dev->num_tx_queues; i++,txp++) { + do { + start = u64_stats_fetch_begin_irq(&txp->rsync); + packets = txp->rx_packets; + bytes = txp->rx_bytes; + } while (u64_stats_fetch_retry_irq(&txp->rsync, start)); + stats->rx_packets += packets; + stats->rx_bytes += bytes; + + do { + start = u64_stats_fetch_begin_irq(&txp->tsync); + packets = txp->tx_packets; + bytes = txp->tx_bytes; + } while (u64_stats_fetch_retry_irq(&txp->tsync, start)); + stats->tx_packets += packets; + stats->tx_bytes += bytes; + } stats->rx_dropped = dev->stats.rx_dropped; stats->tx_dropped = dev->stats.tx_dropped; return stats; } +static int ifb_dev_init(struct net_device *dev) +{ + struct ifb_dev_private *dp = netdev_priv(dev); + struct ifb_q_private *txp; + int i; + + txp = kcalloc(dev->num_tx_queues, sizeof(*txp), GFP_KERNEL); + if (!txp) + return -ENOMEM; + dp->tx_private = txp; + for (i = 0; i < dev->num_tx_queues; i++,txp++) { + txp->txqnum = i; + txp->dev = dev; + __skb_queue_head_init(&txp->rq); + __skb_queue_head_init(&txp->tq); + u64_stats_init(&txp->rsync); + u64_stats_init(&txp->tsync); + tasklet_init(&txp->ifb_tasklet, ifb_ri_tasklet, + (unsigned long)txp); + netif_tx_start_queue(netdev_get_tx_queue(dev, i)); + } + return 0; +} static const struct net_device_ops ifb_netdev_ops = { .ndo_open = ifb_open, @@ -162,6 +191,7 @@ static const struct net_device_ops ifb_netdev_ops = { .ndo_get_stats64 = ifb_stats64, .ndo_start_xmit = ifb_xmit, .ndo_validate_addr = eth_validate_addr, + .ndo_init = ifb_dev_init, }; #define IFB_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | \ @@ -169,10 +199,24 @@ static const struct net_device_ops ifb_netdev_ops = { NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_CTAG_TX | \ NETIF_F_HW_VLAN_STAG_TX) +static void ifb_dev_free(struct net_device *dev) +{ + struct ifb_dev_private *dp = netdev_priv(dev); + struct ifb_q_private *txp = dp->tx_private; + int i; + + for (i = 0; i < dev->num_tx_queues; i++,txp++) { + tasklet_kill(&txp->ifb_tasklet); + __skb_queue_purge(&txp->rq); + __skb_queue_purge(&txp->tq); + } + kfree(dp->tx_private); + free_netdev(dev); +} + static void ifb_setup(struct net_device *dev) { /* Initialize the device structure. */ - dev->destructor = free_netdev; dev->netdev_ops = &ifb_netdev_ops; /* Fill in device structure with ethernet-generic values. */ @@ -188,17 +232,19 @@ static void ifb_setup(struct net_device *dev) dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); eth_hw_addr_random(dev); + dev->destructor = ifb_dev_free; } static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) { - struct ifb_private *dp = netdev_priv(dev); + struct ifb_dev_private *dp = netdev_priv(dev); u32 from = G_TC_FROM(skb->tc_verd); + struct ifb_q_private *txp = dp->tx_private + skb_get_queue_mapping(skb); - u64_stats_update_begin(&dp->rsync); - dp->rx_packets++; - dp->rx_bytes += skb->len; - u64_stats_update_end(&dp->rsync); + u64_stats_update_begin(&txp->rsync); + txp->rx_packets++; + txp->rx_bytes += skb->len; + u64_stats_update_end(&txp->rsync); if (!(from & (AT_INGRESS|AT_EGRESS)) || !skb->skb_iif) { dev_kfree_skb(skb); @@ -206,14 +252,13 @@ static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - if (skb_queue_len(&dp->rq) >= dev->tx_queue_len) { - netif_stop_queue(dev); - } + if (skb_queue_len(&txp->rq) >= dev->tx_queue_len) + netif_tx_stop_queue(netdev_get_tx_queue(dev, txp->txqnum)); - __skb_queue_tail(&dp->rq, skb); - if (!dp->tasklet_pending) { - dp->tasklet_pending = 1; - tasklet_schedule(&dp->ifb_tasklet); + __skb_queue_tail(&txp->rq, skb); + if (!txp->tasklet_pending) { + txp->tasklet_pending = 1; + tasklet_schedule(&txp->ifb_tasklet); } return NETDEV_TX_OK; @@ -221,24 +266,13 @@ static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) static int ifb_close(struct net_device *dev) { - struct ifb_private *dp = netdev_priv(dev); - - tasklet_kill(&dp->ifb_tasklet); - netif_stop_queue(dev); - __skb_queue_purge(&dp->rq); - __skb_queue_purge(&dp->tq); + netif_tx_stop_all_queues(dev); return 0; } static int ifb_open(struct net_device *dev) { - struct ifb_private *dp = netdev_priv(dev); - - tasklet_init(&dp->ifb_tasklet, ri_tasklet, (unsigned long)dev); - __skb_queue_head_init(&dp->rq); - __skb_queue_head_init(&dp->tq); - netif_start_queue(dev); - + netif_tx_start_all_queues(dev); return 0; } @@ -255,31 +289,30 @@ static int ifb_validate(struct nlattr *tb[], struct nlattr *data[]) static struct rtnl_link_ops ifb_link_ops __read_mostly = { .kind = "ifb", - .priv_size = sizeof(struct ifb_private), + .priv_size = sizeof(struct ifb_dev_private), .setup = ifb_setup, .validate = ifb_validate, }; -/* Number of ifb devices to be set up by this module. */ +/* Number of ifb devices to be set up by this module. + * Note that these legacy devices have one queue. + * Prefer something like : ip link add ifb10 numtxqueues 8 type ifb + */ +static int numifbs = 2; module_param(numifbs, int, 0); MODULE_PARM_DESC(numifbs, "Number of ifb devices"); static int __init ifb_init_one(int index) { struct net_device *dev_ifb; - struct ifb_private *dp; int err; - dev_ifb = alloc_netdev(sizeof(struct ifb_private), "ifb%d", + dev_ifb = alloc_netdev(sizeof(struct ifb_dev_private), "ifb%d", NET_NAME_UNKNOWN, ifb_setup); if (!dev_ifb) return -ENOMEM; - dp = netdev_priv(dev_ifb); - u64_stats_init(&dp->rsync); - u64_stats_init(&dp->tsync); - dev_ifb->rtnl_link_ops = &ifb_link_ops; err = register_netdevice(dev_ifb); if (err < 0) diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index cb86d7a01542..d6aff873803c 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -54,6 +54,11 @@ config VITESSE_PHY ---help--- Currently supports the vsc8244 +config TERANETICS_PHY + tristate "Drivers for the Teranetics PHYs" + ---help--- + Currently supports the Teranetics TN2020 + config SMSC_PHY tristate "Drivers for SMSC PHYs" ---help--- diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index fcc25a0c45cd..16aac1c3e703 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_CICADA_PHY) += cicada.o obj-$(CONFIG_LXT_PHY) += lxt.o obj-$(CONFIG_QSEMI_PHY) += qsemi.o obj-$(CONFIG_SMSC_PHY) += smsc.o +obj-$(CONFIG_TERANETICS_PHY) += teranetics.o obj-$(CONFIG_VITESSE_PHY) += vitesse.o obj-$(CONFIG_BROADCOM_PHY) += broadcom.o obj-$(CONFIG_BCM63XX_PHY) += bcm63xx.o diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 00cb41e71312..185b03c08e16 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1449,17 +1449,9 @@ static int dp83640_ts_info(struct phy_device *dev, struct ethtool_ts_info *info) info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | - (1 << HWTSTAMP_FILTER_PTP_V2_EVENT) | - (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | - (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ); + (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); return 0; } diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 1960b46add65..479b93f9581c 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -52,6 +52,10 @@ static int fixed_phy_update_regs(struct fixed_phy *fp) u16 lpagb = 0; u16 lpa = 0; + if (!fp->status.link) + goto done; + bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE; + if (fp->status.duplex) { bmcr |= BMCR_FULLDPLX; @@ -96,15 +100,13 @@ static int fixed_phy_update_regs(struct fixed_phy *fp) } } - if (fp->status.link) - bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE; - if (fp->status.pause) lpa |= LPA_PAUSE_CAP; if (fp->status.asym_pause) lpa |= LPA_PAUSE_ASYM; +done: fp->regs[MII_PHYSID1] = 0; fp->regs[MII_PHYSID2] = 0; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index f721444c2b0a..3320a179ee36 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -48,6 +48,8 @@ #define MII_M1011_IMASK_CLEAR 0x0000 #define MII_M1011_PHY_SCR 0x10 +#define MII_M1011_PHY_SCR_MDI 0x0000 +#define MII_M1011_PHY_SCR_MDI_X 0x0020 #define MII_M1011_PHY_SCR_AUTO_CROSS 0x0060 #define MII_M1145_PHY_EXT_SR 0x1b @@ -159,6 +161,43 @@ static int marvell_config_intr(struct phy_device *phydev) return err; } +static int marvell_set_polarity(struct phy_device *phydev, int polarity) +{ + int reg; + int err; + int val; + + /* get the current settings */ + reg = phy_read(phydev, MII_M1011_PHY_SCR); + if (reg < 0) + return reg; + + val = reg; + val &= ~MII_M1011_PHY_SCR_AUTO_CROSS; + switch (polarity) { + case ETH_TP_MDI: + val |= MII_M1011_PHY_SCR_MDI; + break; + case ETH_TP_MDI_X: + val |= MII_M1011_PHY_SCR_MDI_X; + break; + case ETH_TP_MDI_AUTO: + case ETH_TP_MDI_INVALID: + default: + val |= MII_M1011_PHY_SCR_AUTO_CROSS; + break; + } + + if (val != reg) { + /* Set the new polarity value in the register */ + err = phy_write(phydev, MII_M1011_PHY_SCR, val); + if (err) + return err; + } + + return 0; +} + static int marvell_config_aneg(struct phy_device *phydev) { int err; @@ -191,8 +230,7 @@ static int marvell_config_aneg(struct phy_device *phydev) if (err < 0) return err; - err = phy_write(phydev, MII_M1011_PHY_SCR, - MII_M1011_PHY_SCR_AUTO_CROSS); + err = marvell_set_polarity(phydev, phydev->mdix); if (err < 0) return err; diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index b2197b506acb..84b1fba58ac3 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -353,6 +353,8 @@ int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd) phydev->duplex = cmd->duplex; + phydev->mdix = cmd->eth_tp_mdix_ctrl; + /* Restart the PHY */ phy_start_aneg(phydev); @@ -377,6 +379,7 @@ int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd) cmd->transceiver = phy_is_internal(phydev) ? XCVR_INTERNAL : XCVR_EXTERNAL; cmd->autoneg = phydev->autoneg; + cmd->eth_tp_mdix_ctrl = phydev->mdix; return 0; } diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c new file mode 100644 index 000000000000..7dcb5aada1c4 --- /dev/null +++ b/drivers/net/phy/teranetics.c @@ -0,0 +1,128 @@ +/* + * Driver for Teranetics PHY + * + * Author: Shaohui Xie <Shaohui.Xie@freescale.com> + * + * Copyright 2015 Freescale Semiconductor, Inc. + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mii.h> +#include <linux/ethtool.h> +#include <linux/mdio.h> +#include <linux/phy.h> + +MODULE_DESCRIPTION("Teranetics PHY driver"); +MODULE_AUTHOR("Shaohui Xie <Shaohui.Xie@freescale.com>"); +MODULE_LICENSE("GPL v2"); + +#define PHY_ID_TN2020 0x00a19410 +#define MDIO_PHYXS_LNSTAT_SYNC0 0x0001 +#define MDIO_PHYXS_LNSTAT_SYNC1 0x0002 +#define MDIO_PHYXS_LNSTAT_SYNC2 0x0004 +#define MDIO_PHYXS_LNSTAT_SYNC3 0x0008 +#define MDIO_PHYXS_LNSTAT_ALIGN 0x1000 + +#define MDIO_PHYXS_LANE_READY (MDIO_PHYXS_LNSTAT_SYNC0 | \ + MDIO_PHYXS_LNSTAT_SYNC1 | \ + MDIO_PHYXS_LNSTAT_SYNC2 | \ + MDIO_PHYXS_LNSTAT_SYNC3 | \ + MDIO_PHYXS_LNSTAT_ALIGN) + +static int teranetics_config_init(struct phy_device *phydev) +{ + phydev->supported = SUPPORTED_10000baseT_Full; + phydev->advertising = SUPPORTED_10000baseT_Full; + + return 0; +} + +static int teranetics_soft_reset(struct phy_device *phydev) +{ + return 0; +} + +static int teranetics_aneg_done(struct phy_device *phydev) +{ + int reg; + + reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1); + return (reg < 0) ? reg : (reg & BMSR_ANEGCOMPLETE); +} + +static int teranetics_config_aneg(struct phy_device *phydev) +{ + return 0; +} + +static int teranetics_read_status(struct phy_device *phydev) +{ + int reg; + + phydev->link = 1; + + phydev->speed = SPEED_10000; + phydev->duplex = DUPLEX_FULL; + + if (!phy_read_mmd(phydev, MDIO_MMD_VEND1, 93)) { + reg = phy_read_mmd(phydev, MDIO_MMD_PHYXS, MDIO_PHYXS_LNSTAT); + if (reg < 0 || + !((reg & MDIO_PHYXS_LANE_READY) == MDIO_PHYXS_LANE_READY)) { + phydev->link = 0; + return 0; + } + + reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1); + if (reg < 0 || !(reg & MDIO_STAT1_LSTATUS)) + phydev->link = 0; + } + + return 0; +} + +static int teranetics_match_phy_device(struct phy_device *phydev) +{ + return phydev->c45_ids.device_ids[3] == PHY_ID_TN2020; +} + +static struct phy_driver teranetics_driver[] = { +{ + .phy_id = PHY_ID_TN2020, + .phy_id_mask = 0xffffffff, + .name = "Teranetics TN2020", + .soft_reset = teranetics_soft_reset, + .aneg_done = teranetics_aneg_done, + .config_init = teranetics_config_init, + .config_aneg = teranetics_config_aneg, + .read_status = teranetics_read_status, + .match_phy_device = teranetics_match_phy_device, + .driver = { .owner = THIS_MODULE,}, +}, +}; + +static int __init teranetics_init(void) +{ + return phy_drivers_register(teranetics_driver, + ARRAY_SIZE(teranetics_driver)); +} + +static void __exit teranetics_exit(void) +{ + return phy_drivers_unregister(teranetics_driver, + ARRAY_SIZE(teranetics_driver)); +} + +module_init(teranetics_init); +module_exit(teranetics_exit); + +static struct mdio_device_id __maybe_unused teranetics_tbl[] = { + { PHY_ID_TN2020, 0xffffffff }, + { } +}; + +MODULE_DEVICE_TABLE(mdio, teranetics_tbl); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 9d43460ce3c7..1f7a7cd97e50 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -785,6 +785,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81a4, 8)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a8, 8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ + {QMI_FIXED_INTF(0x413c, 0x81b1, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x03f0, 0x581d, 4)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */ /* 4. Gobi 1000 devices */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 7f6419ebb5e1..57b72ecb5455 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -622,6 +622,7 @@ enum rtl_version { RTL_VER_03, RTL_VER_04, RTL_VER_05, + RTL_VER_06, RTL_VER_MAX }; @@ -2560,7 +2561,10 @@ static void r8153_hw_phy_cfg(struct r8152 *tp) u32 ocp_data; u16 data; - ocp_reg_write(tp, OCP_ADC_CFG, CKADSEL_L | ADC_EN | EN_EMI_L); + if (tp->version == RTL_VER_03 || tp->version == RTL_VER_04 || + tp->version == RTL_VER_05) + ocp_reg_write(tp, OCP_ADC_CFG, CKADSEL_L | ADC_EN | EN_EMI_L); + data = r8152_mdio_read(tp, MII_BMCR); if (data & BMCR_PDOWN) { data &= ~BMCR_PDOWN; @@ -3274,6 +3278,13 @@ static void r8153_init(struct r8152 *tp) else ocp_data |= DYNAMIC_BURST; ocp_write_byte(tp, MCU_TYPE_USB, USB_CSR_DUMMY1, ocp_data); + } else if (tp->version == RTL_VER_06) { + ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_CSR_DUMMY1); + if (ocp_read_word(tp, MCU_TYPE_USB, USB_BURST_SIZE) == 0) + ocp_data &= ~DYNAMIC_BURST; + else + ocp_data |= DYNAMIC_BURST; + ocp_write_byte(tp, MCU_TYPE_USB, USB_CSR_DUMMY1, ocp_data); } ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_CSR_DUMMY2); @@ -3908,6 +3919,10 @@ static void r8152b_get_version(struct r8152 *tp) tp->version = RTL_VER_05; tp->mii.supports_gmii = 1; break; + case 0x5c30: + tp->version = RTL_VER_06; + tp->mii.supports_gmii = 1; + break; default: netif_info(tp, probe, tp->netdev, "Unknown version 0x%04x\n", version); @@ -3953,6 +3968,7 @@ static int rtl_ops_init(struct r8152 *tp) case RTL_VER_03: case RTL_VER_04: case RTL_VER_05: + case RTL_VER_06: ops->init = r8153_init; ops->enable = rtl8153_enable; ops->disable = rtl8153_disable; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 34c519eb1db5..e9feefb41f0b 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -49,15 +49,12 @@ #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> #endif +#include <net/dst_metadata.h> #define VXLAN_VERSION "0.1" #define PORT_HASH_BITS 8 #define PORT_HASH_SIZE (1<<PORT_HASH_BITS) -#define VNI_HASH_BITS 10 -#define VNI_HASH_SIZE (1<<VNI_HASH_BITS) -#define FDB_HASH_BITS 8 -#define FDB_HASH_SIZE (1<<FDB_HASH_BITS) #define FDB_AGE_DEFAULT 300 /* 5 min */ #define FDB_AGE_INTERVAL (10 * HZ) /* rescan interval */ @@ -74,9 +71,13 @@ module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static int vxlan_net_id; +static struct rtnl_link_ops vxlan_link_ops; static const u8 all_zeros_mac[ETH_ALEN]; +static struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, + bool no_share, u32 flags); + /* per-network namespace private data for this module */ struct vxlan_net { struct list_head vxlan_list; @@ -84,21 +85,6 @@ struct vxlan_net { spinlock_t sock_lock; }; -union vxlan_addr { - struct sockaddr_in sin; - struct sockaddr_in6 sin6; - struct sockaddr sa; -}; - -struct vxlan_rdst { - union vxlan_addr remote_ip; - __be16 remote_port; - u32 remote_vni; - u32 remote_ifindex; - struct list_head list; - struct rcu_head rcu; -}; - /* Forwarding table entry */ struct vxlan_fdb { struct hlist_node hlist; /* linked list of entries */ @@ -106,40 +92,21 @@ struct vxlan_fdb { unsigned long updated; /* jiffies */ unsigned long used; struct list_head remotes; + u8 eth_addr[ETH_ALEN]; u16 state; /* see ndm_state */ u8 flags; /* see ndm_flags */ - u8 eth_addr[ETH_ALEN]; -}; - -/* Pseudo network device */ -struct vxlan_dev { - struct hlist_node hlist; /* vni hash table */ - struct list_head next; /* vxlan's per namespace list */ - struct vxlan_sock *vn_sock; /* listening socket */ - struct net_device *dev; - struct net *net; /* netns for packet i/o */ - struct vxlan_rdst default_dst; /* default destination */ - union vxlan_addr saddr; /* source address */ - __be16 dst_port; - __u16 port_min; /* source port range */ - __u16 port_max; - __u8 tos; /* TOS override */ - __u8 ttl; - u32 flags; /* VXLAN_F_* in vxlan.h */ - - unsigned long age_interval; - struct timer_list age_timer; - spinlock_t hash_lock; - unsigned int addrcnt; - unsigned int addrmax; - - struct hlist_head fdb_head[FDB_HASH_SIZE]; }; /* salt for hash table */ static u32 vxlan_salt __read_mostly; static struct workqueue_struct *vxlan_wq; +static inline bool vxlan_collect_metadata(struct vxlan_sock *vs) +{ + return vs->flags & VXLAN_F_COLLECT_METADATA || + ip_tunnel_collect_metadata(); +} + #if IS_ENABLED(CONFIG_IPV6) static inline bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b) @@ -345,7 +312,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip)) goto nla_put_failure; - if (rdst->remote_port && rdst->remote_port != vxlan->dst_port && + if (rdst->remote_port && rdst->remote_port != vxlan->cfg.dst_port && nla_put_be16(skb, NDA_PORT, rdst->remote_port)) goto nla_put_failure; if (rdst->remote_vni != vxlan->default_dst.remote_vni && @@ -749,7 +716,8 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, if (!(flags & NLM_F_CREATE)) return -ENOENT; - if (vxlan->addrmax && vxlan->addrcnt >= vxlan->addrmax) + if (vxlan->cfg.addrmax && + vxlan->addrcnt >= vxlan->cfg.addrmax) return -ENOSPC; /* Disallow replace to add a multicast entry */ @@ -835,7 +803,7 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, return -EINVAL; *port = nla_get_be16(tb[NDA_PORT]); } else { - *port = vxlan->dst_port; + *port = vxlan->cfg.dst_port; } if (tb[NDA_VNI]) { @@ -1021,7 +989,7 @@ static bool vxlan_snoop(struct net_device *dev, vxlan_fdb_create(vxlan, src_mac, src_ip, NUD_REACHABLE, NLM_F_EXCL|NLM_F_CREATE, - vxlan->dst_port, + vxlan->cfg.dst_port, vxlan->default_dst.remote_vni, 0, NTF_SELF); spin_unlock(&vxlan->hash_lock); @@ -1062,7 +1030,7 @@ static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev) return false; } -void vxlan_sock_release(struct vxlan_sock *vs) +static void vxlan_sock_release(struct vxlan_sock *vs) { struct sock *sk = vs->sock->sk; struct net *net = sock_net(sk); @@ -1078,7 +1046,6 @@ void vxlan_sock_release(struct vxlan_sock *vs) queue_work(vxlan_wq, &vs->del_work); } -EXPORT_SYMBOL_GPL(vxlan_sock_release); /* Update multicast group membership when first VNI on * multicast address is brought up @@ -1161,13 +1128,112 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh, return vh; } +static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, + struct vxlan_metadata *md, u32 vni, + struct metadata_dst *tun_dst) +{ + struct iphdr *oip = NULL; + struct ipv6hdr *oip6 = NULL; + struct vxlan_dev *vxlan; + struct pcpu_sw_netstats *stats; + union vxlan_addr saddr; + int err = 0; + union vxlan_addr *remote_ip; + + /* For flow based devices, map all packets to VNI 0 */ + if (vs->flags & VXLAN_F_FLOW_BASED) + vni = 0; + + /* Is this VNI defined? */ + vxlan = vxlan_vs_find_vni(vs, vni); + if (!vxlan) + goto drop; + + remote_ip = &vxlan->default_dst.remote_ip; + skb_reset_mac_header(skb); + skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev))); + skb->protocol = eth_type_trans(skb, vxlan->dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + + /* Ignore packet loops (and multicast echo) */ + if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) + goto drop; + + /* Re-examine inner Ethernet packet */ + if (remote_ip->sa.sa_family == AF_INET) { + oip = ip_hdr(skb); + saddr.sin.sin_addr.s_addr = oip->saddr; + saddr.sa.sa_family = AF_INET; +#if IS_ENABLED(CONFIG_IPV6) + } else { + oip6 = ipv6_hdr(skb); + saddr.sin6.sin6_addr = oip6->saddr; + saddr.sa.sa_family = AF_INET6; +#endif + } + + if (tun_dst) { + skb_dst_set(skb, (struct dst_entry *)tun_dst); + tun_dst = NULL; + } + + if ((vxlan->flags & VXLAN_F_LEARN) && + vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source)) + goto drop; + + skb_reset_network_header(skb); + /* In flow-based mode, GBP is carried in dst_metadata */ + if (!(vs->flags & VXLAN_F_FLOW_BASED)) + skb->mark = md->gbp; + + if (oip6) + err = IP6_ECN_decapsulate(oip6, skb); + if (oip) + err = IP_ECN_decapsulate(oip, skb); + + if (unlikely(err)) { + if (log_ecn_error) { + if (oip6) + net_info_ratelimited("non-ECT from %pI6\n", + &oip6->saddr); + if (oip) + net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", + &oip->saddr, oip->tos); + } + if (err > 1) { + ++vxlan->dev->stats.rx_frame_errors; + ++vxlan->dev->stats.rx_errors; + goto drop; + } + } + + stats = this_cpu_ptr(vxlan->dev->tstats); + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += skb->len; + u64_stats_update_end(&stats->syncp); + + netif_rx(skb); + + return; +drop: + if (tun_dst) + dst_release((struct dst_entry *)tun_dst); + + /* Consume bad packet */ + kfree_skb(skb); +} + /* Callback from net/ipv4/udp.c to receive packets */ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { + struct metadata_dst *tun_dst = NULL; + struct ip_tunnel_info *info; struct vxlan_sock *vs; struct vxlanhdr *vxh; u32 flags, vni; - struct vxlan_metadata md = {0}; + struct vxlan_metadata _md; + struct vxlan_metadata *md = &_md; /* Need Vxlan and inner Ethernet header to be present */ if (!pskb_may_pull(skb, VXLAN_HLEN)) @@ -1202,6 +1268,32 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) vni &= VXLAN_VNI_MASK; } + if (vxlan_collect_metadata(vs)) { + const struct iphdr *iph = ip_hdr(skb); + + tun_dst = metadata_dst_alloc(sizeof(*md), GFP_ATOMIC); + if (!tun_dst) + goto drop; + + info = &tun_dst->u.tun_info; + info->key.ipv4_src = iph->saddr; + info->key.ipv4_dst = iph->daddr; + info->key.ipv4_tos = iph->tos; + info->key.ipv4_ttl = iph->ttl; + info->key.tp_src = udp_hdr(skb)->source; + info->key.tp_dst = udp_hdr(skb)->dest; + + info->mode = IP_TUNNEL_INFO_RX; + info->key.tun_flags = TUNNEL_KEY; + info->key.tun_id = cpu_to_be64(vni >> 8); + if (udp_hdr(skb)->check != 0) + info->key.tun_flags |= TUNNEL_CSUM; + + md = ip_tunnel_info_opts(info, sizeof(*md)); + } else { + memset(md, 0, sizeof(*md)); + } + /* For backwards compatibility, only allow reserved fields to be * used by VXLAN extensions if explicitly requested. */ @@ -1209,13 +1301,16 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) struct vxlanhdr_gbp *gbp; gbp = (struct vxlanhdr_gbp *)vxh; - md.gbp = ntohs(gbp->policy_id); + md->gbp = ntohs(gbp->policy_id); + + if (tun_dst) + info->key.tun_flags |= TUNNEL_VXLAN_OPT; if (gbp->dont_learn) - md.gbp |= VXLAN_GBP_DONT_LEARN; + md->gbp |= VXLAN_GBP_DONT_LEARN; if (gbp->policy_applied) - md.gbp |= VXLAN_GBP_POLICY_APPLIED; + md->gbp |= VXLAN_GBP_POLICY_APPLIED; flags &= ~VXLAN_GBP_USED_BITS; } @@ -1233,8 +1328,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) goto bad_flags; } - md.vni = vxh->vx_vni; - vs->rcv(vs, skb, &md); + vxlan_rcv(vs, skb, md, vni >> 8, tun_dst); return 0; drop: @@ -1247,93 +1341,13 @@ bad_flags: ntohl(vxh->vx_flags), ntohl(vxh->vx_vni)); error: + if (tun_dst) + dst_release((struct dst_entry *)tun_dst); + /* Return non vxlan pkt */ return 1; } -static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, - struct vxlan_metadata *md) -{ - struct iphdr *oip = NULL; - struct ipv6hdr *oip6 = NULL; - struct vxlan_dev *vxlan; - struct pcpu_sw_netstats *stats; - union vxlan_addr saddr; - __u32 vni; - int err = 0; - union vxlan_addr *remote_ip; - - vni = ntohl(md->vni) >> 8; - /* Is this VNI defined? */ - vxlan = vxlan_vs_find_vni(vs, vni); - if (!vxlan) - goto drop; - - remote_ip = &vxlan->default_dst.remote_ip; - skb_reset_mac_header(skb); - skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev))); - skb->protocol = eth_type_trans(skb, vxlan->dev); - skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); - - /* Ignore packet loops (and multicast echo) */ - if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) - goto drop; - - /* Re-examine inner Ethernet packet */ - if (remote_ip->sa.sa_family == AF_INET) { - oip = ip_hdr(skb); - saddr.sin.sin_addr.s_addr = oip->saddr; - saddr.sa.sa_family = AF_INET; -#if IS_ENABLED(CONFIG_IPV6) - } else { - oip6 = ipv6_hdr(skb); - saddr.sin6.sin6_addr = oip6->saddr; - saddr.sa.sa_family = AF_INET6; -#endif - } - - if ((vxlan->flags & VXLAN_F_LEARN) && - vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source)) - goto drop; - - skb_reset_network_header(skb); - skb->mark = md->gbp; - - if (oip6) - err = IP6_ECN_decapsulate(oip6, skb); - if (oip) - err = IP_ECN_decapsulate(oip, skb); - - if (unlikely(err)) { - if (log_ecn_error) { - if (oip6) - net_info_ratelimited("non-ECT from %pI6\n", - &oip6->saddr); - if (oip) - net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", - &oip->saddr, oip->tos); - } - if (err > 1) { - ++vxlan->dev->stats.rx_frame_errors; - ++vxlan->dev->stats.rx_errors; - goto drop; - } - } - - stats = this_cpu_ptr(vxlan->dev->tstats); - u64_stats_update_begin(&stats->syncp); - stats->rx_packets++; - stats->rx_bytes += skb->len; - u64_stats_update_end(&stats->syncp); - - netif_rx(skb); - - return; -drop: - /* Consume bad packet */ - kfree_skb(skb); -} - static int arp_reduce(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); @@ -1672,7 +1686,7 @@ static int vxlan6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, - __be16 src_port, __be16 dst_port, + __be16 src_port, __be16 dst_port, __u32 vni, struct vxlan_metadata *md, bool xnet, u32 vxflags) { struct vxlanhdr *vxh; @@ -1722,7 +1736,7 @@ static int vxlan6_xmit_skb(struct dst_entry *dst, struct sock *sk, vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh)); vxh->vx_flags = htonl(VXLAN_HF_VNI); - vxh->vx_vni = md->vni; + vxh->vx_vni = vni; if (type & SKB_GSO_TUNNEL_REMCSUM) { u32 data = (skb_checksum_start_offset(skb) - hdrlen) >> @@ -1755,10 +1769,10 @@ err: } #endif -int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, - __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, - __be16 src_port, __be16 dst_port, - struct vxlan_metadata *md, bool xnet, u32 vxflags) +static int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, + __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, + __be16 src_port, __be16 dst_port, __u32 vni, + struct vxlan_metadata *md, bool xnet, u32 vxflags) { struct vxlanhdr *vxh; int min_headroom; @@ -1801,7 +1815,7 @@ int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh)); vxh->vx_flags = htonl(VXLAN_HF_VNI); - vxh->vx_vni = md->vni; + vxh->vx_vni = vni; if (type & SKB_GSO_TUNNEL_REMCSUM) { u32 data = (skb_checksum_start_offset(skb) - hdrlen) >> @@ -1828,7 +1842,6 @@ int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, ttl, df, src_port, dst_port, xnet, !(vxflags & VXLAN_F_UDP_CSUM)); } -EXPORT_SYMBOL_GPL(vxlan_xmit_skb); /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, @@ -1878,22 +1891,43 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct vxlan_rdst *rdst, bool did_rsc) { + struct ip_tunnel_info *info; struct vxlan_dev *vxlan = netdev_priv(dev); struct sock *sk = vxlan->vn_sock->sock->sk; struct rtable *rt = NULL; const struct iphdr *old_iph; struct flowi4 fl4; union vxlan_addr *dst; - struct vxlan_metadata md; + union vxlan_addr remote_ip; + struct vxlan_metadata _md; + struct vxlan_metadata *md = &_md; __be16 src_port = 0, dst_port; u32 vni; __be16 df = 0; __u8 tos, ttl; int err; + u32 flags = vxlan->flags; + + /* FIXME: Support IPv6 */ + info = skb_tunnel_info(skb, AF_INET); + + if (rdst) { + dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; + vni = rdst->remote_vni; + dst = &rdst->remote_ip; + } else { + if (!info) { + WARN_ONCE(1, "%s: Missing encapsulation instructions\n", + dev->name); + goto drop; + } - dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port; - vni = rdst->remote_vni; - dst = &rdst->remote_ip; + dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; + vni = be64_to_cpu(info->key.tun_id); + remote_ip.sin.sin_family = AF_INET; + remote_ip.sin.sin_addr.s_addr = info->key.ipv4_dst; + dst = &remote_ip; + } if (vxlan_addr_any(dst)) { if (did_rsc) { @@ -1906,25 +1940,42 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, old_iph = ip_hdr(skb); - ttl = vxlan->ttl; + ttl = vxlan->cfg.ttl; if (!ttl && vxlan_addr_multicast(dst)) ttl = 1; - tos = vxlan->tos; + tos = vxlan->cfg.tos; if (tos == 1) tos = ip_tunnel_get_dsfield(old_iph, skb); - src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->port_min, - vxlan->port_max, true); + src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, + vxlan->cfg.port_max, true); if (dst->sa.sa_family == AF_INET) { + if (info) { + if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + if (info->key.tun_flags & TUNNEL_CSUM) + flags |= VXLAN_F_UDP_CSUM; + else + flags &= ~VXLAN_F_UDP_CSUM; + + ttl = info->key.ipv4_ttl; + tos = info->key.ipv4_tos; + + if (info->options_len) + md = ip_tunnel_info_opts(info, sizeof(*md)); + } else { + md->gbp = skb->mark; + } + memset(&fl4, 0, sizeof(fl4)); - fl4.flowi4_oif = rdst->remote_ifindex; + fl4.flowi4_oif = rdst ? rdst->remote_ifindex : 0; fl4.flowi4_tos = RT_TOS(tos); fl4.flowi4_mark = skb->mark; fl4.flowi4_proto = IPPROTO_UDP; fl4.daddr = dst->sin.sin_addr.s_addr; - fl4.saddr = vxlan->saddr.sin.sin_addr.s_addr; + fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr; rt = ip_route_output_key(vxlan->net, &fl4); if (IS_ERR(rt)) { @@ -1958,14 +2009,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); - md.vni = htonl(vni << 8); - md.gbp = skb->mark; - err = vxlan_xmit_skb(rt, sk, skb, fl4.saddr, dst->sin.sin_addr.s_addr, tos, ttl, df, - src_port, dst_port, &md, + src_port, dst_port, htonl(vni << 8), md, !net_eq(vxlan->net, dev_net(vxlan->dev)), - vxlan->flags); + flags); if (err < 0) { /* skb is already freed. */ skb = NULL; @@ -1980,9 +2028,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, u32 flags; memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_oif = rdst->remote_ifindex; + fl6.flowi6_oif = rdst ? rdst->remote_ifindex : 0; fl6.daddr = dst->sin6.sin6_addr; - fl6.saddr = vxlan->saddr.sin6.sin6_addr; + fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr; fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = IPPROTO_UDP; @@ -2018,11 +2066,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } ttl = ttl ? : ip6_dst_hoplimit(ndst); - md.vni = htonl(vni << 8); - md.gbp = skb->mark; + md->gbp = skb->mark; err = vxlan6_xmit_skb(ndst, sk, skb, dev, &fl6.saddr, &fl6.daddr, - 0, ttl, src_port, dst_port, &md, + 0, ttl, src_port, dst_port, htonl(vni << 8), md, !net_eq(vxlan->net, dev_net(vxlan->dev)), vxlan->flags); #endif @@ -2051,11 +2098,15 @@ tx_free: static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); + const struct ip_tunnel_info *info; struct ethhdr *eth; bool did_rsc = false; struct vxlan_rdst *rdst, *fdst = NULL; struct vxlan_fdb *f; + /* FIXME: Support IPv6 */ + info = skb_tunnel_info(skb, AF_INET); + skb_reset_mac_header(skb); eth = eth_hdr(skb); @@ -2078,6 +2129,12 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) #endif } + if (vxlan->flags & VXLAN_F_FLOW_BASED && + info && info->mode == IP_TUNNEL_INFO_TX) { + vxlan_xmit_one(skb, dev, NULL, false); + return NETDEV_TX_OK; + } + f = vxlan_find_mac(vxlan, eth->h_dest); did_rsc = false; @@ -2143,7 +2200,7 @@ static void vxlan_cleanup(unsigned long arg) if (f->state & NUD_PERMANENT) continue; - timeout = f->used + vxlan->age_interval * HZ; + timeout = f->used + vxlan->cfg.age_interval * HZ; if (time_before_eq(timeout, jiffies)) { netdev_dbg(vxlan->dev, "garbage collect %pM\n", @@ -2207,8 +2264,8 @@ static int vxlan_open(struct net_device *dev) struct vxlan_sock *vs; int ret = 0; - vs = vxlan_sock_add(vxlan->net, vxlan->dst_port, vxlan_rcv, NULL, - false, vxlan->flags); + vs = vxlan_sock_add(vxlan->net, vxlan->cfg.dst_port, + vxlan->cfg.no_share, vxlan->flags); if (IS_ERR(vs)) return PTR_ERR(vs); @@ -2222,7 +2279,7 @@ static int vxlan_open(struct net_device *dev) } } - if (vxlan->age_interval) + if (vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL); return ret; @@ -2380,7 +2437,7 @@ static void vxlan_setup(struct net_device *dev) vxlan->age_timer.function = vxlan_cleanup; vxlan->age_timer.data = (unsigned long) vxlan; - vxlan->dst_port = htons(vxlan_port); + vxlan->cfg.dst_port = htons(vxlan_port); vxlan->dev = dev; @@ -2405,6 +2462,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_RSC] = { .type = NLA_U8 }, [IFLA_VXLAN_L2MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_L3MISS] = { .type = NLA_U8 }, + [IFLA_VXLAN_FLOWBASED] = { .type = NLA_U8 }, [IFLA_VXLAN_PORT] = { .type = NLA_U16 }, [IFLA_VXLAN_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, @@ -2500,7 +2558,6 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6, /* Create new listen socket if needed */ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, - vxlan_rcv_t *rcv, void *data, u32 flags) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); @@ -2529,8 +2586,6 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, vs->sock = sock; atomic_set(&vs->refcnt, 1); - vs->rcv = rcv; - vs->data = data; vs->flags = (flags & VXLAN_F_RCV_FLAGS); /* Initialize the vxlan udp offloads structure */ @@ -2554,9 +2609,8 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, return vs; } -struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, - vxlan_rcv_t *rcv, void *data, - bool no_share, u32 flags) +static struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, + bool no_share, u32 flags) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_sock *vs; @@ -2566,7 +2620,7 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, spin_lock(&vn->sock_lock); vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port, flags); - if (vs && vs->rcv == rcv) { + if (vs) { if (!atomic_add_unless(&vs->refcnt, 1, 0)) vs = ERR_PTR(-EBUSY); spin_unlock(&vn->sock_lock); @@ -2575,58 +2629,38 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, spin_unlock(&vn->sock_lock); } - return vxlan_socket_create(net, port, rcv, data, flags); + return vxlan_socket_create(net, port, flags); } -EXPORT_SYMBOL_GPL(vxlan_sock_add); -static int vxlan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) +static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, + struct vxlan_config *conf) { struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; - __u32 vni; int err; bool use_ipv6 = false; - - if (!data[IFLA_VXLAN_ID]) - return -EINVAL; + __be16 default_port = vxlan->cfg.dst_port; vxlan->net = src_net; - vni = nla_get_u32(data[IFLA_VXLAN_ID]); - dst->remote_vni = vni; - - /* Unless IPv6 is explicitly requested, assume IPv4 */ - dst->remote_ip.sa.sa_family = AF_INET; - if (data[IFLA_VXLAN_GROUP]) { - dst->remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); - } else if (data[IFLA_VXLAN_GROUP6]) { - if (!IS_ENABLED(CONFIG_IPV6)) - return -EPFNOSUPPORT; + dst->remote_vni = conf->vni; - dst->remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]); - dst->remote_ip.sa.sa_family = AF_INET6; - use_ipv6 = true; - } + memcpy(&dst->remote_ip, &conf->remote_ip, sizeof(conf->remote_ip)); - if (data[IFLA_VXLAN_LOCAL]) { - vxlan->saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]); - vxlan->saddr.sa.sa_family = AF_INET; - } else if (data[IFLA_VXLAN_LOCAL6]) { - if (!IS_ENABLED(CONFIG_IPV6)) - return -EPFNOSUPPORT; + /* Unless IPv6 is explicitly requested, assume IPv4 */ + if (!dst->remote_ip.sa.sa_family) + dst->remote_ip.sa.sa_family = AF_INET; - /* TODO: respect scope id */ - vxlan->saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]); - vxlan->saddr.sa.sa_family = AF_INET6; + if (dst->remote_ip.sa.sa_family == AF_INET6 || + vxlan->cfg.saddr.sa.sa_family == AF_INET6) use_ipv6 = true; - } - if (data[IFLA_VXLAN_LINK] && - (dst->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]))) { + if (conf->remote_ifindex) { struct net_device *lowerdev - = __dev_get_by_index(src_net, dst->remote_ifindex); + = __dev_get_by_index(src_net, conf->remote_ifindex); + + dst->remote_ifindex = conf->remote_ifindex; if (!lowerdev) { pr_info("ifindex %d does not exist\n", dst->remote_ifindex); @@ -2644,7 +2678,7 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, } #endif - if (!tb[IFLA_MTU]) + if (!conf->mtu) dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); dev->needed_headroom = lowerdev->hard_header_len + @@ -2652,101 +2686,188 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, } else if (use_ipv6) vxlan->flags |= VXLAN_F_IPV6; + memcpy(&vxlan->cfg, conf, sizeof(*conf)); + if (!vxlan->cfg.dst_port) + vxlan->cfg.dst_port = default_port; + vxlan->flags |= conf->flags; + + if (!vxlan->cfg.age_interval) + vxlan->cfg.age_interval = FDB_AGE_DEFAULT; + + if (vxlan_find_vni(src_net, conf->vni, use_ipv6 ? AF_INET6 : AF_INET, + vxlan->cfg.dst_port, vxlan->flags)) + return -EEXIST; + + dev->ethtool_ops = &vxlan_ethtool_ops; + + /* create an fdb entry for a valid default destination */ + if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) { + err = vxlan_fdb_create(vxlan, all_zeros_mac, + &vxlan->default_dst.remote_ip, + NUD_REACHABLE|NUD_PERMANENT, + NLM_F_EXCL|NLM_F_CREATE, + vxlan->cfg.dst_port, + vxlan->default_dst.remote_vni, + vxlan->default_dst.remote_ifindex, + NTF_SELF); + if (err) + return err; + } + + err = register_netdevice(dev); + if (err) { + vxlan_fdb_delete_default(vxlan); + return err; + } + + list_add(&vxlan->next, &vn->vxlan_list); + + return 0; +} + +struct net_device *vxlan_dev_create(struct net *net, const char *name, + u8 name_assign_type, struct vxlan_config *conf) +{ + struct nlattr *tb[IFLA_MAX+1]; + struct net_device *dev; + int err; + + memset(&tb, 0, sizeof(tb)); + + dev = rtnl_create_link(net, name, name_assign_type, + &vxlan_link_ops, tb); + if (IS_ERR(dev)) + return dev; + + err = vxlan_dev_configure(net, dev, conf); + if (err < 0) { + free_netdev(dev); + return ERR_PTR(err); + } + + return dev; +} +EXPORT_SYMBOL_GPL(vxlan_dev_create); + +static int vxlan_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct vxlan_config conf; + int err; + + if (!data[IFLA_VXLAN_ID]) + return -EINVAL; + + memset(&conf, 0, sizeof(conf)); + conf.vni = nla_get_u32(data[IFLA_VXLAN_ID]); + + if (data[IFLA_VXLAN_GROUP]) { + conf.remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); + } else if (data[IFLA_VXLAN_GROUP6]) { + if (!IS_ENABLED(CONFIG_IPV6)) + return -EPFNOSUPPORT; + + conf.remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]); + conf.remote_ip.sa.sa_family = AF_INET6; + } + + if (data[IFLA_VXLAN_LOCAL]) { + conf.saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]); + conf.saddr.sa.sa_family = AF_INET; + } else if (data[IFLA_VXLAN_LOCAL6]) { + if (!IS_ENABLED(CONFIG_IPV6)) + return -EPFNOSUPPORT; + + /* TODO: respect scope id */ + conf.saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]); + conf.saddr.sa.sa_family = AF_INET6; + } + + if (data[IFLA_VXLAN_LINK]) + conf.remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]); + if (data[IFLA_VXLAN_TOS]) - vxlan->tos = nla_get_u8(data[IFLA_VXLAN_TOS]); + conf.tos = nla_get_u8(data[IFLA_VXLAN_TOS]); if (data[IFLA_VXLAN_TTL]) - vxlan->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); + conf.ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); if (!data[IFLA_VXLAN_LEARNING] || nla_get_u8(data[IFLA_VXLAN_LEARNING])) - vxlan->flags |= VXLAN_F_LEARN; + conf.flags |= VXLAN_F_LEARN; if (data[IFLA_VXLAN_AGEING]) - vxlan->age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]); - else - vxlan->age_interval = FDB_AGE_DEFAULT; + conf.age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]); if (data[IFLA_VXLAN_PROXY] && nla_get_u8(data[IFLA_VXLAN_PROXY])) - vxlan->flags |= VXLAN_F_PROXY; + conf.flags |= VXLAN_F_PROXY; if (data[IFLA_VXLAN_RSC] && nla_get_u8(data[IFLA_VXLAN_RSC])) - vxlan->flags |= VXLAN_F_RSC; + conf.flags |= VXLAN_F_RSC; if (data[IFLA_VXLAN_L2MISS] && nla_get_u8(data[IFLA_VXLAN_L2MISS])) - vxlan->flags |= VXLAN_F_L2MISS; + conf.flags |= VXLAN_F_L2MISS; if (data[IFLA_VXLAN_L3MISS] && nla_get_u8(data[IFLA_VXLAN_L3MISS])) - vxlan->flags |= VXLAN_F_L3MISS; + conf.flags |= VXLAN_F_L3MISS; if (data[IFLA_VXLAN_LIMIT]) - vxlan->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]); + conf.addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]); + + if (data[IFLA_VXLAN_FLOWBASED] && + nla_get_u8(data[IFLA_VXLAN_FLOWBASED])) + conf.flags |= VXLAN_F_FLOW_BASED; if (data[IFLA_VXLAN_PORT_RANGE]) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); - vxlan->port_min = ntohs(p->low); - vxlan->port_max = ntohs(p->high); + conf.port_min = ntohs(p->low); + conf.port_max = ntohs(p->high); } if (data[IFLA_VXLAN_PORT]) - vxlan->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); + conf.dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); if (data[IFLA_VXLAN_UDP_CSUM] && nla_get_u8(data[IFLA_VXLAN_UDP_CSUM])) - vxlan->flags |= VXLAN_F_UDP_CSUM; + conf.flags |= VXLAN_F_UDP_CSUM; if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] && nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX])) - vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_TX; + conf.flags |= VXLAN_F_UDP_ZERO_CSUM6_TX; if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX] && nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX])) - vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX; + conf.flags |= VXLAN_F_UDP_ZERO_CSUM6_RX; if (data[IFLA_VXLAN_REMCSUM_TX] && nla_get_u8(data[IFLA_VXLAN_REMCSUM_TX])) - vxlan->flags |= VXLAN_F_REMCSUM_TX; + conf.flags |= VXLAN_F_REMCSUM_TX; if (data[IFLA_VXLAN_REMCSUM_RX] && nla_get_u8(data[IFLA_VXLAN_REMCSUM_RX])) - vxlan->flags |= VXLAN_F_REMCSUM_RX; + conf.flags |= VXLAN_F_REMCSUM_RX; if (data[IFLA_VXLAN_GBP]) - vxlan->flags |= VXLAN_F_GBP; + conf.flags |= VXLAN_F_GBP; if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) - vxlan->flags |= VXLAN_F_REMCSUM_NOPARTIAL; - - if (vxlan_find_vni(src_net, vni, use_ipv6 ? AF_INET6 : AF_INET, - vxlan->dst_port, vxlan->flags)) { - pr_info("duplicate VNI %u\n", vni); - return -EEXIST; - } + conf.flags |= VXLAN_F_REMCSUM_NOPARTIAL; - dev->ethtool_ops = &vxlan_ethtool_ops; + err = vxlan_dev_configure(src_net, dev, &conf); + switch (err) { + case -ENODEV: + pr_info("ifindex %d does not exist\n", conf.remote_ifindex); + break; - /* create an fdb entry for a valid default destination */ - if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) { - err = vxlan_fdb_create(vxlan, all_zeros_mac, - &vxlan->default_dst.remote_ip, - NUD_REACHABLE|NUD_PERMANENT, - NLM_F_EXCL|NLM_F_CREATE, - vxlan->dst_port, - vxlan->default_dst.remote_vni, - vxlan->default_dst.remote_ifindex, - NTF_SELF); - if (err) - return err; - } + case -EPERM: + pr_info("IPv6 is disabled via sysctl\n"); + break; - err = register_netdevice(dev); - if (err) { - vxlan_fdb_delete_default(vxlan); - return err; + case -EEXIST: + pr_info("duplicate VNI %u\n", conf.vni); + break; } - list_add(&vxlan->next, &vn->vxlan_list); - - return 0; + return err; } static void vxlan_dellink(struct net_device *dev, struct list_head *head) @@ -2777,6 +2898,7 @@ static size_t vxlan_get_size(const struct net_device *dev) nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L2MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L3MISS */ + nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_FLOWBASED */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_AGEING */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LIMIT */ nla_total_size(sizeof(struct ifla_vxlan_port_range)) + @@ -2794,8 +2916,8 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) const struct vxlan_dev *vxlan = netdev_priv(dev); const struct vxlan_rdst *dst = &vxlan->default_dst; struct ifla_vxlan_port_range ports = { - .low = htons(vxlan->port_min), - .high = htons(vxlan->port_max), + .low = htons(vxlan->cfg.port_min), + .high = htons(vxlan->cfg.port_max), }; if (nla_put_u32(skb, IFLA_VXLAN_ID, dst->remote_vni)) @@ -2818,22 +2940,22 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex)) goto nla_put_failure; - if (!vxlan_addr_any(&vxlan->saddr)) { - if (vxlan->saddr.sa.sa_family == AF_INET) { + if (!vxlan_addr_any(&vxlan->cfg.saddr)) { + if (vxlan->cfg.saddr.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_LOCAL, - vxlan->saddr.sin.sin_addr.s_addr)) + vxlan->cfg.saddr.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_LOCAL6, - &vxlan->saddr.sin6.sin6_addr)) + &vxlan->cfg.saddr.sin6.sin6_addr)) goto nla_put_failure; #endif } } - if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->ttl) || - nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->tos) || + if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || + nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, !!(vxlan->flags & VXLAN_F_LEARN)) || nla_put_u8(skb, IFLA_VXLAN_PROXY, @@ -2843,9 +2965,11 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) !!(vxlan->flags & VXLAN_F_L2MISS)) || nla_put_u8(skb, IFLA_VXLAN_L3MISS, !!(vxlan->flags & VXLAN_F_L3MISS)) || - nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->age_interval) || - nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->addrmax) || - nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->dst_port) || + nla_put_u8(skb, IFLA_VXLAN_FLOWBASED, + !!(vxlan->flags & VXLAN_F_FLOW_BASED)) || + nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->cfg.age_interval) || + nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) || + nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) || nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM, !!(vxlan->flags & VXLAN_F_UDP_CSUM)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 8a495b318b6f..c6cb85a85c89 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -325,9 +325,6 @@ static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue) queue->pending_prod + queue->pending_cons; } -/* Callback from stack when TX packet can be released */ -void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success); - irqreturn_t xenvif_interrupt(int irq, void *dev_id); extern bool separate_tx_rx_irq; diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index fdc60db60829..7c8c23cc6896 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -266,7 +266,8 @@ EXPORT_SYMBOL(of_phy_attach); bool of_phy_is_fixed_link(struct device_node *np) { struct device_node *dn; - int len; + int len, err; + const char *managed; /* New binding */ dn = of_get_child_by_name(np, "fixed-link"); @@ -275,6 +276,10 @@ bool of_phy_is_fixed_link(struct device_node *np) return true; } + err = of_property_read_string(np, "managed", &managed); + if (err == 0 && strcmp(managed, "auto") != 0) + return true; + /* Old binding */ if (of_get_property(np, "fixed-link", &len) && len == (5 * sizeof(__be32))) @@ -289,8 +294,18 @@ int of_phy_register_fixed_link(struct device_node *np) struct fixed_phy_status status = {}; struct device_node *fixed_link_node; const __be32 *fixed_link_prop; - int len; + int len, err; struct phy_device *phy; + const char *managed; + + err = of_property_read_string(np, "managed", &managed); + if (err == 0) { + if (strcmp(managed, "in-band-status") == 0) { + /* status is zeroed, namely its .link member */ + phy = fixed_phy_register(PHY_POLL, &status, np); + return IS_ERR(phy) ? PTR_ERR(phy) : 0; + } + } /* New binding */ fixed_link_node = of_get_child_by_name(np, "fixed-link"); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4383476a0d48..139d6d2e123f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -192,5 +192,7 @@ extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; +extern const struct bpf_func_proto bpf_skb_vlan_push_proto; +extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; #endif /* _LINUX_BPF_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 17724f6ea983..69d00555ce35 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -411,6 +411,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); void bpf_int_jit_compile(struct bpf_prog *fp); +bool bpf_helper_changes_skb_data(void *func); #ifdef CONFIG_BPF_JIT typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 82806c60aa42..06ed637225b8 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -57,6 +57,7 @@ struct ipv6_devconf { bool initialized; struct in6_addr secret; } stable_secret; + __s32 use_oif_addrs_only; void *sysctl; }; @@ -94,7 +95,6 @@ static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb) struct inet6_skb_parm { int iif; __be16 ra; - __u16 hop; __u16 dst0; __u16 srcrt; __u16 dst1; @@ -111,6 +111,7 @@ struct inet6_skb_parm { #define IP6SKB_REROUTED 4 #define IP6SKB_ROUTERALERT 8 #define IP6SKB_FRAGMENTED 16 +#define IP6SKB_HOPBYHOP 32 }; #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) diff --git a/include/linux/lwtunnel.h b/include/linux/lwtunnel.h new file mode 100644 index 000000000000..97f32f8b4ae1 --- /dev/null +++ b/include/linux/lwtunnel.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_LWTUNNEL_H_ +#define _LINUX_LWTUNNEL_H_ + +#include <uapi/linux/lwtunnel.h> + +#endif /* _LINUX_LWTUNNEL_H_ */ diff --git a/include/linux/mpls_iptunnel.h b/include/linux/mpls_iptunnel.h new file mode 100644 index 000000000000..ef29eb2d6dfd --- /dev/null +++ b/include/linux/mpls_iptunnel.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_MPLS_IPTUNNEL_H +#define _LINUX_MPLS_IPTUNNEL_H + +#include <uapi/linux/mpls_iptunnel.h> + +#endif /* _LINUX_MPLS_IPTUNNEL_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e20979dfd6a9..607b5f41f46f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -766,6 +766,13 @@ struct netdev_phys_item_id { unsigned char id_len; }; +static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, + struct netdev_phys_item_id *b) +{ + return a->id_len == b->id_len && + memcmp(a->id, b->id, a->id_len) == 0; +} + typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); @@ -1041,6 +1048,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. + * void (*ndo_change_proto_down)(struct net_device *dev, + * bool proto_down); + * This function is used to pass protocol port error state information + * to the switch driver. The switch driver can react to the proto_down + * by doing a phys down on the associated switch port. + * */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1211,6 +1224,8 @@ struct net_device_ops { int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); + int (*ndo_change_proto_down)(struct net_device *dev, + bool proto_down); }; /** @@ -1448,6 +1463,8 @@ enum netdev_priv_flags { * * @xps_maps: XXX: need comments on this one * + * @offload_fwd_mark: Offload device fwding mark + * * @trans_start: Time (in jiffies) of last Tx * @watchdog_timeo: Represents the timeout that is used by * the watchdog ( see dev_watchdog() ) @@ -1502,6 +1519,10 @@ enum netdev_priv_flags { * * @qdisc_tx_busylock: XXX: need comments on this one * + * @proto_down: protocol port state information can be sent to the + * switch driver and used to set the phys state of the + * switch port. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -1685,6 +1706,10 @@ struct net_device { struct xps_dev_maps __rcu *xps_maps; #endif +#ifdef CONFIG_NET_SWITCHDEV + u32 offload_fwd_mark; +#endif + /* These may be needed for future network-power-down code. */ /* @@ -1762,6 +1787,7 @@ struct net_device { #endif struct phy_device *phydev; struct lock_class_key *qdisc_tx_busylock; + bool proto_down; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2982,6 +3008,7 @@ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); +int dev_change_proto_down(struct net_device *dev, bool proto_down); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); diff --git a/include/linux/phy.h b/include/linux/phy.h index a26c3f84b8dd..e5fb1d415961 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -424,6 +424,8 @@ struct phy_device { struct net_device *attached_dev; + u8 mdix; + void (*adjust_link)(struct net_device *dev); }; #define to_phy_device(d) container_of(d, struct phy_device, dev) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d6cdd6e87d53..648a2c241993 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -506,6 +506,7 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @napi_id: id of the NAPI struct this skb came from * @secmark: security marking + * @offload_fwd_mark: fwding offload mark * @mark: Generic packet mark * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information @@ -650,9 +651,15 @@ struct sk_buff { unsigned int sender_cpu; }; #endif + union { #ifdef CONFIG_NETWORK_SECMARK - __u32 secmark; + __u32 secmark; +#endif +#ifdef CONFIG_NET_SWITCHDEV + __u32 offload_fwd_mark; #endif + }; + union { __u32 mark; __u32 reserved_tailroom; @@ -2671,12 +2678,6 @@ static inline void skb_frag_list_init(struct sk_buff *skb) skb_shinfo(skb)->frag_list = NULL; } -static inline void skb_frag_add_head(struct sk_buff *skb, struct sk_buff *frag) -{ - frag->next = skb_shinfo(skb)->frag_list; - skb_shinfo(skb)->frag_list = frag; -} - #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) @@ -3468,5 +3469,6 @@ static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) skb_network_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c735f5c91eea..c86a20047cb1 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -123,8 +123,6 @@ struct plat_stmmacenet_data { void (*free)(struct platform_device *pdev, void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); - void *custom_cfg; - void *custom_data; void *bsp_priv; }; diff --git a/include/net/act_api.h b/include/net/act_api.h index 3ee4c92afd1b..8d2a707a9e87 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -21,6 +21,8 @@ struct tcf_common { struct gnet_stats_rate_est64 tcfc_rate_est; spinlock_t tcfc_lock; struct rcu_head tcfc_rcu; + struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_queue __percpu *cpu_qstats; }; #define tcf_head common.tcfc_head #define tcf_index common.tcfc_index @@ -68,6 +70,17 @@ static inline void tcf_hashinfo_destroy(struct tcf_hashinfo *hf) kfree(hf->htab); } +/* Update lastuse only if needed, to avoid dirtying a cache line. + * We use a temp variable to avoid fetching jiffies twice. + */ +static inline void tcf_lastuse_update(struct tcf_t *tm) +{ + unsigned long now = jiffies; + + if (tm->lastuse != now) + tm->lastuse = now; +} + #ifdef CONFIG_NET_CLS_ACT #define ACT_P_CREATED 1 @@ -103,7 +116,7 @@ int tcf_hash_release(struct tc_action *a, int bind); u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo); int tcf_hash_check(u32 index, struct tc_action *a, int bind); int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, - int size, int bind); + int size, int bind, bool cpustats); void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est); void tcf_hash_insert(struct tc_action *a); diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index c15d39456e14..ccd6d8bffa4d 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -49,9 +49,38 @@ static inline void sock_update_classid(struct sock *sk) if (classid != sk->sk_classid) sk->sk_classid = classid; } + +static inline u32 task_get_classid(const struct sk_buff *skb) +{ + u32 classid = task_cls_state(current)->classid; + + /* Due to the nature of the classifier it is required to ignore all + * packets originating from softirq context as accessing `current' + * would lead to false results. + * + * This test assumes that all callers of dev_queue_xmit() explicitly + * disable bh. Knowing this, it is possible to detect softirq based + * calls by looking at the number of nested bh disable calls because + * softirqs always disables bh. + */ + if (in_serving_softirq()) { + /* If there is an sk_classid we'll use that. */ + if (!skb->sk) + return 0; + + classid = skb->sk->sk_classid; + } + + return classid; +} #else /* !CONFIG_CGROUP_NET_CLASSID */ static inline void sock_update_classid(struct sock *sk) { } + +static inline u32 task_get_classid(const struct sk_buff *skb) +{ + return 0; +} #endif /* CONFIG_CGROUP_NET_CLASSID */ #endif /* _NET_CLS_CGROUP_H */ diff --git a/include/net/dst.h b/include/net/dst.h index 2bc73f8a00a9..2578811cef51 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -57,6 +57,7 @@ struct dst_entry { #define DST_FAKE_RTABLE 0x0040 #define DST_XFRM_TUNNEL 0x0080 #define DST_XFRM_QUEUE 0x0100 +#define DST_METADATA 0x0200 unsigned short pending_confirm; @@ -356,6 +357,9 @@ static inline int dst_discard(struct sk_buff *skb) } void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, unsigned short flags); +void dst_init(struct dst_entry *dst, struct dst_ops *ops, + struct net_device *dev, int initial_ref, int initial_obsolete, + unsigned short flags); void __dst_free(struct dst_entry *dst); struct dst_entry *dst_destroy(struct dst_entry *dst); @@ -457,7 +461,7 @@ static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) return dst; } -void dst_init(void); +void dst_subsys_init(void); /* Flags for xfrm_lookup flags argument. */ enum { diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h new file mode 100644 index 000000000000..7b0306894663 --- /dev/null +++ b/include/net/dst_metadata.h @@ -0,0 +1,55 @@ +#ifndef __NET_DST_METADATA_H +#define __NET_DST_METADATA_H 1 + +#include <linux/skbuff.h> +#include <net/ip_tunnels.h> +#include <net/dst.h> + +struct metadata_dst { + struct dst_entry dst; + size_t opts_len; + union { + struct ip_tunnel_info tun_info; + } u; +}; + +static inline struct metadata_dst *skb_metadata_dst(struct sk_buff *skb) +{ + struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb); + + if (md_dst && md_dst->dst.flags & DST_METADATA) + return md_dst; + + return NULL; +} + +static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb, + int family) +{ + struct metadata_dst *md_dst = skb_metadata_dst(skb); + struct rtable *rt; + + if (md_dst) + return &md_dst->u.tun_info; + + switch (family) { + case AF_INET: + rt = (struct rtable *)skb_dst(skb); + if (rt && rt->rt_lwtstate) + return lwt_tun_info(rt->rt_lwtstate); + break; + } + + return NULL; +} + +static inline bool skb_valid_dst(const struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + + return dst && !(dst->flags & DST_METADATA); +} + +struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags); + +#endif /* __NET_DST_METADATA_H */ diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 903a55efbffe..4e8f804f4589 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -19,6 +19,7 @@ struct fib_rule { u8 action; /* 3 bytes hole, try to use */ u32 target; + __be64 tun_id; struct fib_rule __rcu *ctarget; struct net *fr_net; diff --git a/include/net/flow.h b/include/net/flow.h index 8109a159d1b3..3098ae33a178 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -19,6 +19,10 @@ #define LOOPBACK_IFINDEX 1 +struct flowi_tunnel { + __be64 tun_id; +}; + struct flowi_common { int flowic_oif; int flowic_iif; @@ -30,6 +34,7 @@ struct flowi_common { #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_KNOWN_NH 0x02 __u32 flowic_secid; + struct flowi_tunnel flowic_tun_key; }; union flowi_uli { @@ -66,6 +71,7 @@ struct flowi4 { #define flowi4_proto __fl_common.flowic_proto #define flowi4_flags __fl_common.flowic_flags #define flowi4_secid __fl_common.flowic_secid +#define flowi4_tun_key __fl_common.flowic_tun_key /* (saddr,daddr) must be grouped, same order as in IP header */ __be32 saddr; @@ -95,6 +101,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, fl4->flowi4_proto = proto; fl4->flowi4_flags = flags; fl4->flowi4_secid = 0; + fl4->flowi4_tun_key.tun_id = 0; fl4->daddr = daddr; fl4->saddr = saddr; fl4->fl4_dport = dport; @@ -165,6 +172,7 @@ struct flowi { #define flowi_proto u.__fl_common.flowic_proto #define flowi_flags u.__fl_common.flowic_flags #define flowi_secid u.__fl_common.flowic_secid +#define flowi_tun_key u.__fl_common.flowic_tun_key } __attribute__((__aligned__(BITS_PER_LONG/8))); static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4) diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index b73c88a19dd4..b07d126694a7 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -205,8 +205,8 @@ void inet_put_port(struct sock *sk); void inet_hashinfo_init(struct inet_hashinfo *h); -int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw); -int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw); +void __inet_hash_nolisten(struct sock *sk, struct sock *osk); +void __inet_hash(struct sock *sk, struct sock *osk); void inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 360c4802288d..879d6e5a973b 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -100,10 +100,8 @@ static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk) void inet_twsk_free(struct inet_timewait_sock *tw); void inet_twsk_put(struct inet_timewait_sock *tw); -int inet_twsk_unhash(struct inet_timewait_sock *tw); - -int inet_twsk_bind_unhash(struct inet_timewait_sock *tw, - struct inet_hashinfo *hashinfo); +void inet_twsk_bind_unhash(struct inet_timewait_sock *tw, + struct inet_hashinfo *hashinfo); struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, struct inet_timewait_death_row *dr, @@ -113,7 +111,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, struct inet_hashinfo *hashinfo); void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo); -void inet_twsk_deschedule(struct inet_timewait_sock *tw); +void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 3b76849c190f..276328e3daa6 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -51,6 +51,8 @@ struct fib6_config { struct nlattr *fc_mp; struct nl_info fc_nlinfo; + struct nlattr *fc_encap; + u16 fc_encap_type; }; struct fib6_node { @@ -131,6 +133,7 @@ struct rt6_info { /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; u8 rt6i_protocol; + struct lwtunnel_state *rt6i_lwtstate; }; static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 49c142bdf01e..5e0196084f1e 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -44,7 +44,9 @@ struct fib_config { u32 fc_flow; u32 fc_nlflags; struct nl_info fc_nlinfo; - }; + struct nlattr *fc_encap; + u16 fc_encap_type; +}; struct fib_info; struct rtable; @@ -89,6 +91,7 @@ struct fib_nh { struct rtable __rcu * __percpu *nh_pcpu_rth_output; struct rtable __rcu *nh_rth_input; struct fnhe_hash_bucket __rcu *nh_exceptions; + struct lwtunnel_state *nh_lwtstate; }; /* diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index d8214cb88bbc..d975b3ebd6c7 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -9,9 +9,9 @@ #include <net/dsfield.h> #include <net/gro_cells.h> #include <net/inet_ecn.h> -#include <net/ip.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> +#include <net/lwtunnel.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -22,6 +22,37 @@ /* Keep error state on tunnel for 30 sec */ #define IPTUNNEL_ERR_TIMEO (30*HZ) +/* Used to memset ip_tunnel padding. */ +#define IP_TUNNEL_KEY_SIZE \ + (offsetof(struct ip_tunnel_key, tp_dst) + \ + FIELD_SIZEOF(struct ip_tunnel_key, tp_dst)) + +struct ip_tunnel_key { + __be64 tun_id; + __be32 ipv4_src; + __be32 ipv4_dst; + __be16 tun_flags; + __u8 ipv4_tos; + __u8 ipv4_ttl; + __be16 tp_src; + __be16 tp_dst; +} __packed __aligned(4); /* Minimize padding. */ + +/* Indicates whether the tunnel info structure represents receive + * or transmit tunnel parameters. + */ +enum { + IP_TUNNEL_INFO_RX, + IP_TUNNEL_INFO_TX, +}; + +struct ip_tunnel_info { + struct ip_tunnel_key key; + const void *options; + u8 options_len; + u8 mode; +}; + /* 6rd prefix/relay information */ #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd_parm { @@ -136,6 +167,47 @@ int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op, int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, unsigned int num); +static inline void __ip_tunnel_info_init(struct ip_tunnel_info *tun_info, + __be32 saddr, __be32 daddr, + u8 tos, u8 ttl, + __be16 tp_src, __be16 tp_dst, + __be64 tun_id, __be16 tun_flags, + const void *opts, u8 opts_len) +{ + tun_info->key.tun_id = tun_id; + tun_info->key.ipv4_src = saddr; + tun_info->key.ipv4_dst = daddr; + tun_info->key.ipv4_tos = tos; + tun_info->key.ipv4_ttl = ttl; + tun_info->key.tun_flags = tun_flags; + + /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of + * the upper tunnel are used. + * E.g: GRE over IPSEC, the tp_src and tp_port are zero. + */ + tun_info->key.tp_src = tp_src; + tun_info->key.tp_dst = tp_dst; + + /* Clear struct padding. */ + if (sizeof(tun_info->key) != IP_TUNNEL_KEY_SIZE) + memset((unsigned char *)&tun_info->key + IP_TUNNEL_KEY_SIZE, + 0, sizeof(tun_info->key) - IP_TUNNEL_KEY_SIZE); + + tun_info->options = opts; + tun_info->options_len = opts_len; +} + +static inline void ip_tunnel_info_init(struct ip_tunnel_info *tun_info, + const struct iphdr *iph, + __be16 tp_src, __be16 tp_dst, + __be64 tun_id, __be16 tun_flags, + const void *opts, u8 opts_len) +{ + __ip_tunnel_info_init(tun_info, iph->saddr, iph->daddr, + iph->tos, iph->ttl, tp_src, tp_dst, + tun_id, tun_flags, opts, opts_len); +} + #ifdef CONFIG_INET int ip_tunnel_init(struct net_device *dev); @@ -221,6 +293,42 @@ static inline void iptunnel_xmit_stats(int err, } } +static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info, size_t n) +{ + return info + 1; +} + +static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) +{ + return (struct ip_tunnel_info *)lwtstate->data; +} + +extern struct static_key ip_tunnel_metadata_cnt; + +/* Returns > 0 if metadata should be collected */ +static inline int ip_tunnel_collect_metadata(void) +{ + return static_key_false(&ip_tunnel_metadata_cnt); +} + +void ip_tunnel_need_metadata(void); +void ip_tunnel_unneed_metadata(void); + +#else /* CONFIG_INET */ + +static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) +{ + return NULL; +} + +static inline void ip_tunnel_need_metadata(void) +{ +} + +static inline void ip_tunnel_unneed_metadata(void) +{ +} + #endif /* CONFIG_INET */ #endif /* __NET_IP_TUNNELS_H */ diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h new file mode 100644 index 000000000000..918e03c1dafa --- /dev/null +++ b/include/net/lwtunnel.h @@ -0,0 +1,144 @@ +#ifndef __NET_LWTUNNEL_H +#define __NET_LWTUNNEL_H 1 + +#include <linux/lwtunnel.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/types.h> +#include <net/route.h> + +#define LWTUNNEL_HASH_BITS 7 +#define LWTUNNEL_HASH_SIZE (1 << LWTUNNEL_HASH_BITS) + +/* lw tunnel state flags */ +#define LWTUNNEL_STATE_OUTPUT_REDIRECT 0x1 + +struct lwtunnel_state { + __u16 type; + __u16 flags; + atomic_t refcnt; + int len; + __u8 data[0]; +}; + +struct lwtunnel_encap_ops { + int (*build_state)(struct net_device *dev, struct nlattr *encap, + struct lwtunnel_state **ts); + int (*output)(struct sock *sk, struct sk_buff *skb); + int (*fill_encap)(struct sk_buff *skb, + struct lwtunnel_state *lwtstate); + int (*get_encap_size)(struct lwtunnel_state *lwtstate); + int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b); +}; + +extern const struct lwtunnel_encap_ops __rcu * + lwtun_encaps[LWTUNNEL_ENCAP_MAX+1]; + +#ifdef CONFIG_LWTUNNEL +static inline void lwtunnel_state_get(struct lwtunnel_state *lws) +{ + atomic_inc(&lws->refcnt); +} + +static inline void lwtunnel_state_put(struct lwtunnel_state *lws) +{ + if (!lws) + return; + + if (atomic_dec_and_test(&lws->refcnt)) + kfree(lws); +} + +static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate) +{ + if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_OUTPUT_REDIRECT)) + return true; + + return false; +} + +int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, + unsigned int num); +int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, + unsigned int num); +int lwtunnel_build_state(struct net_device *dev, u16 encap_type, + struct nlattr *encap, + struct lwtunnel_state **lws); +int lwtunnel_fill_encap(struct sk_buff *skb, + struct lwtunnel_state *lwtstate); +int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate); +struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len); +int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b); +int lwtunnel_output(struct sock *sk, struct sk_buff *skb); +int lwtunnel_output6(struct sock *sk, struct sk_buff *skb); + +#else + +static inline void lwtunnel_state_get(struct lwtunnel_state *lws) +{ +} + +static inline void lwtunnel_state_put(struct lwtunnel_state *lws) +{ +} + +static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate) +{ + return false; +} + +static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, + unsigned int num) +{ + return -EOPNOTSUPP; + +} + +static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, + unsigned int num) +{ + return -EOPNOTSUPP; +} + +static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type, + struct nlattr *encap, + struct lwtunnel_state **lws) +{ + return -EOPNOTSUPP; +} + +static inline int lwtunnel_fill_encap(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + return 0; +} + +static inline int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) +{ + return 0; +} + +static inline struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len) +{ + return NULL; +} + +static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a, + struct lwtunnel_state *b) +{ + return 0; +} + +static inline int lwtunnel_output(struct sock *sk, struct sk_buff *skb) +{ + return -EOPNOTSUPP; +} + +static inline int lwtunnel_output6(struct sock *sk, struct sk_buff *skb) +{ + return -EOPNOTSUPP; +} + +#endif + +#endif /* __NET_LWTUNNEL_H */ diff --git a/include/net/mpls_iptunnel.h b/include/net/mpls_iptunnel.h new file mode 100644 index 000000000000..4757997f76ed --- /dev/null +++ b/include/net/mpls_iptunnel.h @@ -0,0 +1,29 @@ +/* + * Copyright (c) 2015 Cumulus Networks, Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _NET_MPLS_IPTUNNEL_H +#define _NET_MPLS_IPTUNNEL_H 1 + +#define MAX_NEW_LABELS 2 + +struct mpls_iptunnel_encap { + u32 label[MAX_NEW_LABELS]; + u32 labels; +}; + +static inline struct mpls_iptunnel_encap *mpls_lwtunnel_encap(struct lwtunnel_state *lwtstate) +{ + return (struct mpls_iptunnel_encap *)lwtstate->data; +} + +#endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 8d93544a2d2b..c0368db6df54 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -31,6 +31,7 @@ struct netns_sysctl_ipv6 { int auto_flowlabels; int icmpv6_time; int anycast_src_echo_reply; + int ip_nonlocal_bind; int fwmark_reflect; int idgen_retries; int idgen_delay; diff --git a/include/net/route.h b/include/net/route.h index fe22d03afb6a..2d45f419477f 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -66,6 +66,7 @@ struct rtable { struct list_head rt_uncached; struct uncached_list *rt_uncached_list; + struct lwtunnel_state *rt_lwtstate; }; static inline bool rt_is_input_route(const struct rtable *rt) diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 343d922d15c2..18fdb98185ab 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -141,6 +141,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, unsigned char name_assign_type, const struct rtnl_link_ops *ops, struct nlattr *tb[]); +int rtnl_delete_link(struct net_device *dev); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm); int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 2738f6f87908..2eab08c38e32 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -513,17 +513,20 @@ static inline void bstats_update(struct gnet_stats_basic_packed *bstats, bstats->packets += skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1; } -static inline void qdisc_bstats_update_cpu(struct Qdisc *sch, - const struct sk_buff *skb) +static inline void bstats_cpu_update(struct gnet_stats_basic_cpu *bstats, + const struct sk_buff *skb) { - struct gnet_stats_basic_cpu *bstats = - this_cpu_ptr(sch->cpu_bstats); - u64_stats_update_begin(&bstats->syncp); bstats_update(&bstats->bstats, skb); u64_stats_update_end(&bstats->syncp); } +static inline void qdisc_bstats_cpu_update(struct Qdisc *sch, + const struct sk_buff *skb) +{ + bstats_cpu_update(this_cpu_ptr(sch->cpu_bstats), skb); +} + static inline void qdisc_bstats_update(struct Qdisc *sch, const struct sk_buff *skb) { @@ -547,16 +550,24 @@ static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count) sch->qstats.drops += count; } -static inline void qdisc_qstats_drop(struct Qdisc *sch) +static inline void qstats_drop_inc(struct gnet_stats_queue *qstats) { - sch->qstats.drops++; + qstats->drops++; } -static inline void qdisc_qstats_drop_cpu(struct Qdisc *sch) +static inline void qstats_overlimit_inc(struct gnet_stats_queue *qstats) { - struct gnet_stats_queue *qstats = this_cpu_ptr(sch->cpu_qstats); + qstats->overlimits++; +} - qstats->drops++; +static inline void qdisc_qstats_drop(struct Qdisc *sch) +{ + qstats_drop_inc(&sch->qstats); +} + +static inline void qdisc_qstats_cpu_drop(struct Qdisc *sch) +{ + qstats_drop_inc(this_cpu_ptr(sch->cpu_qstats)); } static inline void qdisc_qstats_overlimit(struct Qdisc *sch) diff --git a/include/net/sock.h b/include/net/sock.h index 05a8c1aea251..4353ef70bf48 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -429,7 +429,9 @@ struct sock { void *sk_security; #endif __u32 sk_mark; +#ifdef CONFIG_CGROUP_NET_CLASSID u32 sk_classid; +#endif struct cg_proto *sk_cgrp; void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d5671f118bfc..89da8934519b 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -157,6 +157,9 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int idx); +void switchdev_port_fwd_mark_set(struct net_device *dev, + struct net_device *group_dev, + bool joining); #else @@ -271,6 +274,12 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb, return -EOPNOTSUPP; } +static inline void switchdev_port_fwd_mark_set(struct net_device *dev, + struct net_device *group_dev, + bool joining) +{ +} + #endif #endif /* _LINUX_SWITCHDEV_H_ */ diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index 9fc9b578908a..592a6bc02b0b 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -6,9 +6,10 @@ struct tcf_gact { struct tcf_common common; #ifdef CONFIG_GACT_PROB - u16 tcfg_ptype; - u16 tcfg_pval; - int tcfg_paction; + u16 tcfg_ptype; + u16 tcfg_pval; + int tcfg_paction; + atomic_t packets; #endif }; #define to_gact(a) \ diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 4dd77a1c106b..dae96bae1c19 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -8,7 +8,7 @@ struct tcf_mirred { int tcfm_eaction; int tcfm_ifindex; int tcfm_ok_push; - struct net_device *tcfm_dev; + struct net_device __rcu *tcfm_dev; struct list_head tcfm_list; }; #define to_mirred(a) \ diff --git a/include/net/tcp.h b/include/net/tcp.h index 950cfecaad3c..364426a2be5a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -989,6 +989,11 @@ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) #define TCP_INFINITE_SSTHRESH 0x7fffffff +static inline bool tcp_in_slow_start(const struct tcp_sock *tp) +{ + return tp->snd_cwnd < tp->snd_ssthresh; +} + static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) { return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; @@ -1065,7 +1070,7 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); /* If in slow start, ensure cwnd grows to twice what was ACKed. */ - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) return tp->snd_cwnd < 2 * tp->max_packets_out; return tp->is_cwnd_limited; diff --git a/include/net/timewait_sock.h b/include/net/timewait_sock.h index 68f0ecad6c6e..1a47946f95ba 100644 --- a/include/net/timewait_sock.h +++ b/include/net/timewait_sock.h @@ -33,9 +33,6 @@ static inline int twsk_unique(struct sock *sk, struct sock *sktw, void *twp) static inline void twsk_destructor(struct sock *sk) { - BUG_ON(sk == NULL); - BUG_ON(sk->sk_prot == NULL); - BUG_ON(sk->sk_prot->twsk_prot == NULL); if (sk->sk_prot->twsk_prot->twsk_destructor != NULL) sk->sk_prot->twsk_prot->twsk_destructor(sk); } diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 0082b5d33d7d..eb8d721cdb67 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -7,6 +7,7 @@ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/udp.h> +#include <net/dst_metadata.h> #define VNI_HASH_BITS 10 #define VNI_HASH_SIZE (1<<VNI_HASH_BITS) @@ -94,20 +95,18 @@ struct vxlanhdr { #define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8) #define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) +#define VNI_HASH_BITS 10 +#define VNI_HASH_SIZE (1<<VNI_HASH_BITS) +#define FDB_HASH_BITS 8 +#define FDB_HASH_SIZE (1<<FDB_HASH_BITS) + struct vxlan_metadata { - __be32 vni; u32 gbp; }; -struct vxlan_sock; -typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb, - struct vxlan_metadata *md); - /* per UDP socket information */ struct vxlan_sock { struct hlist_node hlist; - vxlan_rcv_t *rcv; - void *data; struct work_struct del_work; struct socket *sock; struct rcu_head rcu; @@ -117,6 +116,57 @@ struct vxlan_sock { u32 flags; }; +union vxlan_addr { + struct sockaddr_in sin; + struct sockaddr_in6 sin6; + struct sockaddr sa; +}; + +struct vxlan_rdst { + union vxlan_addr remote_ip; + __be16 remote_port; + u32 remote_vni; + u32 remote_ifindex; + struct list_head list; + struct rcu_head rcu; +}; + +struct vxlan_config { + union vxlan_addr remote_ip; + union vxlan_addr saddr; + u32 vni; + int remote_ifindex; + int mtu; + __be16 dst_port; + __u16 port_min; + __u16 port_max; + __u8 tos; + __u8 ttl; + u32 flags; + unsigned long age_interval; + unsigned int addrmax; + bool no_share; +}; + +/* Pseudo network device */ +struct vxlan_dev { + struct hlist_node hlist; /* vni hash table */ + struct list_head next; /* vxlan's per namespace list */ + struct vxlan_sock *vn_sock; /* listening socket */ + struct net_device *dev; + struct net *net; /* netns for packet i/o */ + struct vxlan_rdst default_dst; /* default destination */ + u32 flags; /* VXLAN_F_* in vxlan.h */ + + struct timer_list age_timer; + spinlock_t hash_lock; + unsigned int addrcnt; + + struct vxlan_config cfg; + + struct hlist_head fdb_head[FDB_HASH_SIZE]; +}; + #define VXLAN_F_LEARN 0x01 #define VXLAN_F_PROXY 0x02 #define VXLAN_F_RSC 0x04 @@ -130,6 +180,8 @@ struct vxlan_sock { #define VXLAN_F_REMCSUM_RX 0x400 #define VXLAN_F_GBP 0x800 #define VXLAN_F_REMCSUM_NOPARTIAL 0x1000 +#define VXLAN_F_COLLECT_METADATA 0x2000 +#define VXLAN_F_FLOW_BASED 0x4000 /* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable @@ -137,18 +189,17 @@ struct vxlan_sock { #define VXLAN_F_RCV_FLAGS (VXLAN_F_GBP | \ VXLAN_F_UDP_ZERO_CSUM6_RX | \ VXLAN_F_REMCSUM_RX | \ - VXLAN_F_REMCSUM_NOPARTIAL) - -struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, - vxlan_rcv_t *rcv, void *data, - bool no_share, u32 flags); + VXLAN_F_REMCSUM_NOPARTIAL | \ + VXLAN_F_COLLECT_METADATA | \ + VXLAN_F_FLOW_BASED) -void vxlan_sock_release(struct vxlan_sock *vs); +struct net_device *vxlan_dev_create(struct net *net, const char *name, + u8 name_assign_type, struct vxlan_config *conf); -int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, - __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, - __be16 src_port, __be16 dst_port, struct vxlan_metadata *md, - bool xnet, u32 vxflags); +static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan) +{ + return inet_sk(vxlan->vn_sock->sock->sk)->inet_sport; +} static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, netdev_features_t features) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 29ef6f99e43d..2f6c83d714e9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -249,6 +249,15 @@ enum bpf_func_id { * Return: 0 on success */ BPF_FUNC_get_current_comm, + + /** + * bpf_get_cgroup_classid(skb) - retrieve a proc's classid + * @skb: pointer to skb + * Return: classid if != 0 + */ + BPF_FUNC_get_cgroup_classid, + BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */ + BPF_FUNC_skb_vlan_pop, /* bpf_skb_vlan_pop(skb) */ __BPF_FUNC_MAX_ID, }; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index cd67aec187d9..cd1629170103 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1093,6 +1093,11 @@ struct ethtool_sfeatures { * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values, * respectively. For example, if the device supports HWTSTAMP_TX_ON, * then (1 << HWTSTAMP_TX_ON) in 'tx_types' will be set. + * + * Drivers should only report the filters they actually support without + * upscaling in the SIOCSHWTSTAMP ioctl. If the SIOCSHWSTAMP request for + * HWTSTAMP_FILTER_V1_SYNC is supported by HWTSTAMP_FILTER_V1_EVENT, then the + * driver should only report HWTSTAMP_FILTER_V1_EVENT in this op. */ struct ethtool_ts_info { __u32 cmd; diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index 2b82d7e30974..96161b8202b5 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -43,7 +43,7 @@ enum { FRA_UNUSED5, FRA_FWMARK, /* mark */ FRA_FLOW, /* flow/class id */ - FRA_UNUSED6, + FRA_TUN_ID, FRA_SUPPRESS_IFGROUP, FRA_SUPPRESS_PREFIXLEN, FRA_TABLE, /* Extended table id */ diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index eaaea6208b42..3635b7797508 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -182,6 +182,7 @@ struct br_mdb_entry { #define MDB_TEMPORARY 0 #define MDB_PERMANENT 1 __u8 state; + __u16 vid; struct { union { __be32 ip4; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 2c7e8e3d3981..9eeb5d9cf8f0 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -148,6 +148,7 @@ enum { IFLA_PHYS_SWITCH_ID, IFLA_LINK_NETNSID, IFLA_PHYS_PORT_NAME, + IFLA_PROTO_DOWN, __IFLA_MAX }; @@ -381,6 +382,7 @@ enum { IFLA_VXLAN_REMCSUM_RX, IFLA_VXLAN_GBP, IFLA_VXLAN_REMCSUM_NOPARTIAL, + IFLA_VXLAN_FLOWBASED, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 5efa54ae567c..641a146ead7d 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -171,6 +171,7 @@ enum { DEVCONF_USE_OPTIMISTIC, DEVCONF_ACCEPT_RA_MTU, DEVCONF_STABLE_SECRET, + DEVCONF_USE_OIF_ADDRS_ONLY, DEVCONF_MAX }; diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h new file mode 100644 index 000000000000..31377bbea3f8 --- /dev/null +++ b/include/uapi/linux/lwtunnel.h @@ -0,0 +1,16 @@ +#ifndef _UAPI_LWTUNNEL_H_ +#define _UAPI_LWTUNNEL_H_ + +#include <linux/types.h> + +enum lwtunnel_encap_types { + LWTUNNEL_ENCAP_NONE, + LWTUNNEL_ENCAP_MPLS, + LWTUNNEL_ENCAP_IP, + __LWTUNNEL_ENCAP_MAX, +}; + +#define LWTUNNEL_ENCAP_MAX (__LWTUNNEL_ENCAP_MAX - 1) + + +#endif /* _UAPI_LWTUNNEL_H_ */ diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h new file mode 100644 index 000000000000..d80a0498f77e --- /dev/null +++ b/include/uapi/linux/mpls_iptunnel.h @@ -0,0 +1,28 @@ +/* + * mpls tunnel api + * + * Authors: + * Roopa Prabhu <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_MPLS_IPTUNNEL_H +#define _UAPI_LINUX_MPLS_IPTUNNEL_H + +/* MPLS tunnel attributes + * [RTA_ENCAP] = { + * [MPLS_IPTUNNEL_DST] + * } + */ +enum { + MPLS_IPTUNNEL_UNSPEC, + MPLS_IPTUNNEL_DST, + __MPLS_IPTUNNEL_MAX, +}; +#define MPLS_IPTUNNEL_MAX (__MPLS_IPTUNNEL_MAX - 1) + +#endif /* _UAPI_LINUX_MPLS_IPTUNNEL_H */ diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 1dab77601c21..d6b885460187 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -321,7 +321,7 @@ enum ovs_key_attr { * the accepted length of the array. */ #ifdef __KERNEL__ - OVS_KEY_ATTR_TUNNEL_INFO, /* struct ovs_tunnel_info */ + OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ #endif __OVS_KEY_ATTR_MAX }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index fdd8f07f1d34..47d24cb3fbc1 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -286,6 +286,21 @@ enum rt_class_t { /* Routing message attributes */ +enum ip_tunnel_t { + IP_TUN_UNSPEC, + IP_TUN_ID, + IP_TUN_DST, + IP_TUN_SRC, + IP_TUN_TTL, + IP_TUN_TOS, + IP_TUN_SPORT, + IP_TUN_DPORT, + IP_TUN_FLAGS, + __IP_TUN_MAX, +}; + +#define IP_TUN_MAX (__IP_TUN_MAX - 1) + enum rtattr_type_t { RTA_UNSPEC, RTA_DST, @@ -308,6 +323,8 @@ enum rtattr_type_t { RTA_VIA, RTA_NEWDST, RTA_PREF, + RTA_ENCAP_TYPE, + RTA_ENCAP, __RTA_MAX }; diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index eee8968407f0..25a9ad8bcef1 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -278,6 +278,8 @@ enum LINUX_MIB_TCPACKSKIPPEDCHALLENGE, /* TCPACKSkippedChallenge */ LINUX_MIB_TCPWINPROBE, /* TCPWinProbe */ LINUX_MIB_TCPKEEPALIVE, /* TCPKeepAlive */ + LINUX_MIB_TCPMTUPFAIL, /* TCPMTUPFail */ + LINUX_MIB_TCPMTUPSUCCESS, /* TCPMTUPSuccess */ __LINUX_MIB_MAX }; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c5bedc82bc1c..fafa74161445 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -177,6 +177,7 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return 0; } +EXPORT_SYMBOL_GPL(__bpf_call_base); /** * __bpf_prog_run - run eBPF program on a given context @@ -453,7 +454,11 @@ select_insn: if (unlikely(!prog)) goto out; - ARG1 = BPF_R1; + /* ARG1 at this point is guaranteed to point to CTX from + * the verifier side due to the fact that the tail call is + * handeled like a helper, that is, bpf_tail_call_proto, + * where arg1_type is ARG_PTR_TO_CTX. + */ insn = prog->insnsi; goto select_insn; out: diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 7f58c735d745..8b5e66f008b0 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -18,6 +18,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/filter.h> +#include <linux/bpf.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> @@ -355,6 +356,81 @@ static int bpf_fill_ja(struct bpf_test *self) return __bpf_fill_ja(self, 12, 9); } +static int bpf_fill_ld_abs_get_processor_id(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct sock_filter *insn; + int i; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + for (i = 0; i < len - 1; i += 2) { + insn[i] = __BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 0); + insn[i + 1] = __BPF_STMT(BPF_LD | BPF_W | BPF_ABS, + SKF_AD_OFF + SKF_AD_CPU); + } + + insn[len - 1] = __BPF_STMT(BPF_RET | BPF_K, 0xbee); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + +#define PUSH_CNT 68 +/* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */ +static int bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self) +{ + unsigned int len = BPF_MAXINSNS; + struct bpf_insn *insn; + int i = 0, j, k = 0; + + insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + insn[i++] = BPF_MOV64_REG(R6, R1); +loop: + for (j = 0; j < PUSH_CNT; j++) { + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2); + i++; + insn[i++] = BPF_MOV64_REG(R1, R6); + insn[i++] = BPF_MOV64_IMM(R2, 1); + insn[i++] = BPF_MOV64_IMM(R3, 2); + insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + bpf_skb_vlan_push_proto.func - __bpf_call_base); + insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2); + i++; + } + + for (j = 0; j < PUSH_CNT; j++) { + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2); + i++; + insn[i++] = BPF_MOV64_REG(R1, R6); + insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + bpf_skb_vlan_pop_proto.func - __bpf_call_base); + insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2); + i++; + } + if (++k < 5) + goto loop; + + for (; i < len - 1; i++) + insn[i] = BPF_ALU32_IMM(BPF_MOV, R0, 0xbef); + + insn[len - 1] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insn; + self->u.ptr.len = len; + + return 0; +} + static struct bpf_test tests[] = { { "TAX", @@ -3674,6 +3750,9 @@ static struct bpf_test tests[] = { .u.insns_int = { BPF_LD_IMM64(R0, 0x0123456789abcdefLL), BPF_ENDIAN(BPF_FROM_BE, R0, 32), + BPF_ALU64_REG(BPF_MOV, R1, R0), + BPF_ALU64_IMM(BPF_RSH, R1, 32), + BPF_ALU32_REG(BPF_ADD, R0, R1), /* R1 = 0 */ BPF_EXIT_INSN(), }, INTERNAL, @@ -3708,6 +3787,9 @@ static struct bpf_test tests[] = { .u.insns_int = { BPF_LD_IMM64(R0, 0x0123456789abcdefLL), BPF_ENDIAN(BPF_FROM_LE, R0, 32), + BPF_ALU64_REG(BPF_MOV, R1, R0), + BPF_ALU64_IMM(BPF_RSH, R1, 32), + BPF_ALU32_REG(BPF_ADD, R0, R1), /* R1 = 0 */ BPF_EXIT_INSN(), }, INTERNAL, @@ -4392,6 +4474,22 @@ static struct bpf_test tests[] = { { { 0, 0xababcbac } }, .fill_helper = bpf_fill_maxinsns11, }, + { + "BPF_MAXINSNS: ld_abs+get_processor_id", + { }, + CLASSIC, + { }, + { { 1, 0xbee } }, + .fill_helper = bpf_fill_ld_abs_get_processor_id, + }, + { + "BPF_MAXINSNS: ld_abs+vlan_push/pop", + { }, + INTERNAL, + { 0x34 }, + { { 1, 0xbef } }, + .fill_helper = bpf_fill_ld_abs_vlan_push_pop, + }, }; static struct net_device dev; @@ -4545,14 +4643,14 @@ static int __run_one(const struct bpf_prog *fp, const void *data, u64 start, finish; int ret = 0, i; - start = ktime_to_us(ktime_get()); + start = ktime_get_ns(); for (i = 0; i < runs; i++) ret = BPF_PROG_RUN(fp, data); - finish = ktime_to_us(ktime_get()); + finish = ktime_get_ns(); - *duration = (finish - start) * 1000ULL; + *duration = finish - start; do_div(*duration, runs); return ret; diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index c90777eae1f8..9af7cefb195d 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -20,6 +20,7 @@ #include <linux/rcupdate.h> #include <linux/rhashtable.h> #include <linux/slab.h> +#include <linux/sched.h> #define MAX_ENTRIES 1000000 #define TEST_INSERT_FAIL INT_MAX @@ -87,6 +88,8 @@ static int __init test_rht_lookup(struct rhashtable *ht) return -EINVAL; } } + + cond_resched_rcu(); } return 0; @@ -160,6 +163,8 @@ static s64 __init test_rhashtable(struct rhashtable *ht) } else if (err) { return err; } + + cond_resched(); } if (insert_fails) @@ -183,6 +188,8 @@ static s64 __init test_rhashtable(struct rhashtable *ht) rhashtable_remove_fast(ht, &obj->node, test_rht_params); } + + cond_resched(); } end = ktime_get_ns(); diff --git a/net/Kconfig b/net/Kconfig index 57a7c5af3175..7021c1bf44d6 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -374,6 +374,13 @@ source "net/caif/Kconfig" source "net/ceph/Kconfig" source "net/nfc/Kconfig" +config LWTUNNEL + bool "Network light weight tunnels" + ---help--- + This feature provides an infrastructure to support light weight + tunnels like mpls. There is no netdevice associated with a light + weight tunnel endpoint. Tunnel encapsulation parameters are stored + with light weight tunnel state associated with fib routes. endif # if NET diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index a538cb1199a3..45e4757c6fd2 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -281,6 +281,7 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) br_fdb_delete_by_port(br, NULL, 0, 1); br_vlan_flush(br); + br_multicast_dev_del(br); del_timer_sync(&br->gc_timer); br_sysfs_delbr(br->dev); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 1198a3dbad95..6a591e6e2d04 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -85,6 +85,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, memset(&e, 0, sizeof(e)); e.ifindex = port->dev->ifindex; e.state = p->state; + e.vid = p->addr.vid; if (p->addr.proto == htons(ETH_P_IP)) e.addr.u.ip4 = p->addr.u.ip4; #if IS_ENABLED(CONFIG_IPV6) @@ -230,7 +231,7 @@ errout: } void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, - struct br_ip *group, int type) + struct br_ip *group, int type, u8 state) { struct br_mdb_entry entry; @@ -241,6 +242,8 @@ void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, #if IS_ENABLED(CONFIG_IPV6) entry.addr.u.ip6 = group->u.ip6; #endif + entry.state = state; + entry.vid = group->vid; __br_mdb_notify(dev, &entry, type); } @@ -263,6 +266,8 @@ static bool is_valid_mdb_entry(struct br_mdb_entry *entry) return false; if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) return false; + if (entry->vid >= VLAN_VID_MASK) + return false; return true; } @@ -374,6 +379,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, return -EINVAL; memset(&ip, 0, sizeof(ip)); + ip.vid = entry->vid; ip.proto = entry->addr.proto; if (ip.proto == htons(ETH_P_IP)) ip.u.ip4 = entry->addr.u.ip4; @@ -421,6 +427,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) return -EINVAL; memset(&ip, 0, sizeof(ip)); + ip.vid = entry->vid; ip.proto = entry->addr.proto; if (ip.proto == htons(ETH_P_IP)) ip.u.ip4 = entry->addr.u.ip4; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 79db489cdade..ed5dc684a4ce 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -283,6 +283,8 @@ static void br_multicast_del_pg(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); + br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB, + p->state); call_rcu_bh(&p->rcu, br_multicast_free_pg); if (!mp->ports && !mp->mglist && @@ -704,7 +706,7 @@ static int br_multicast_add_group(struct net_bridge *br, if (unlikely(!p)) goto err; rcu_assign_pointer(*pp, p); - br_mdb_notify(br->dev, port, group, RTM_NEWMDB); + br_mdb_notify(br->dev, port, group, RTM_NEWMDB, MDB_TEMPORARY); found: mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -924,6 +926,15 @@ void br_multicast_add_port(struct net_bridge_port *port) void br_multicast_del_port(struct net_bridge_port *port) { + struct net_bridge *br = port->br; + struct net_bridge_port_group *pg; + struct hlist_node *n; + + /* Take care of the remaining groups, only perm ones should be left */ + spin_lock_bh(&br->multicast_lock); + hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) + br_multicast_del_pg(br, pg); + spin_unlock_bh(&br->multicast_lock); del_timer_sync(&port->multicast_router_timer); } @@ -963,7 +974,8 @@ void br_multicast_disable_port(struct net_bridge_port *port) spin_lock(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) - br_multicast_del_pg(br, pg); + if (pg->state == MDB_TEMPORARY) + br_multicast_del_pg(br, pg); if (!hlist_unhashed(&port->rlist)) hlist_del_init_rcu(&port->rlist); @@ -1462,8 +1474,9 @@ br_multicast_leave_group(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); + br_mdb_notify(br->dev, port, group, RTM_DELMDB, + p->state); call_rcu_bh(&p->rcu, br_multicast_free_pg); - br_mdb_notify(br->dev, port, group, RTM_DELMDB); if (!mp->ports && !mp->mglist && netif_running(br->dev)) @@ -1752,12 +1765,6 @@ void br_multicast_open(struct net_bridge *br) void br_multicast_stop(struct net_bridge *br) { - struct net_bridge_mdb_htable *mdb; - struct net_bridge_mdb_entry *mp; - struct hlist_node *n; - u32 ver; - int i; - del_timer_sync(&br->multicast_router_timer); del_timer_sync(&br->ip4_other_query.timer); del_timer_sync(&br->ip4_own_query.timer); @@ -1765,6 +1772,15 @@ void br_multicast_stop(struct net_bridge *br) del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif +} + +void br_multicast_dev_del(struct net_bridge *br) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct hlist_node *n; + u32 ver; + int i; spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 8b21146b24a0..3ad1290528af 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -466,6 +466,7 @@ void br_multicast_disable_port(struct net_bridge_port *port); void br_multicast_init(struct net_bridge *br); void br_multicast_open(struct net_bridge *br); void br_multicast_stop(struct net_bridge *br); +void br_multicast_dev_del(struct net_bridge *br); void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, struct sk_buff *skb); void br_multicast_forward(struct net_bridge_mdb_entry *mdst, @@ -488,7 +489,7 @@ br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group, void br_mdb_init(void); void br_mdb_uninit(void); void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, - struct br_ip *group, int type); + struct br_ip *group, int type, u8 state); #define mlock_dereference(X, br) \ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) @@ -565,6 +566,10 @@ static inline void br_multicast_stop(struct net_bridge *br) { } +static inline void br_multicast_dev_del(struct net_bridge *br) +{ +} + static inline void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, struct sk_buff *skb) { diff --git a/net/core/Makefile b/net/core/Makefile index fec0856dd6c0..086b01fbe1bd 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -23,3 +23,4 @@ obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o +obj-$(CONFIG_LWTUNNEL) += lwtunnel.o diff --git a/net/core/dev.c b/net/core/dev.c index a8e4dd430285..cb52cba30ae8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3061,6 +3061,16 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) else skb_dst_force(skb); +#ifdef CONFIG_NET_SWITCHDEV + /* Don't forward if offload device already forwarded */ + if (skb->offload_fwd_mark && + skb->offload_fwd_mark == dev->offload_fwd_mark) { + consume_skb(skb); + rc = NET_XMIT_SUCCESS; + goto out; + } +#endif + txq = netdev_pick_tx(dev, skb, accel_priv); q = rcu_dereference_bh(txq->qdisc); @@ -3645,7 +3655,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, qdisc_skb_cb(skb)->pkt_len = skb->len; skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); - qdisc_bstats_update_cpu(cl->q, skb); + qdisc_bstats_cpu_update(cl->q, skb); switch (tc_classify(skb, cl, &cl_res)) { case TC_ACT_OK: @@ -3653,7 +3663,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, skb->tc_index = TC_H_MIN(cl_res.classid); break; case TC_ACT_SHOT: - qdisc_qstats_drop_cpu(cl->q); + qdisc_qstats_cpu_drop(cl->q); case TC_ACT_STOLEN: case TC_ACT_QUEUED: kfree_skb(skb); @@ -6075,6 +6085,26 @@ int dev_get_phys_port_name(struct net_device *dev, EXPORT_SYMBOL(dev_get_phys_port_name); /** + * dev_change_proto_down - update protocol port state information + * @dev: device + * @proto_down: new value + * + * This info can be used by switch drivers to set the phys state of the + * port. + */ +int dev_change_proto_down(struct net_device *dev, bool proto_down) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_change_proto_down) + return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_change_proto_down(dev, proto_down); +} +EXPORT_SYMBOL(dev_change_proto_down); + +/** * dev_new_index - allocate an ifindex * @net: the applicable net namespace * @@ -7639,7 +7669,7 @@ static int __init net_dev_init(void) open_softirq(NET_RX_SOFTIRQ, net_rx_action); hotcpu_notifier(dev_cpu_callback, 0); - dst_init(); + dst_subsys_init(); rc = 0; out: return rc; diff --git a/net/core/dst.c b/net/core/dst.c index 002144bea935..76a617f6d60a 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -22,6 +22,7 @@ #include <linux/prefetch.h> #include <net/dst.h> +#include <net/dst_metadata.h> /* * Theory of operations: @@ -158,19 +159,10 @@ const u32 dst_default_metrics[RTAX_MAX + 1] = { [RTAX_MAX] = 0xdeadbeef, }; - -void *dst_alloc(struct dst_ops *ops, struct net_device *dev, - int initial_ref, int initial_obsolete, unsigned short flags) +void dst_init(struct dst_entry *dst, struct dst_ops *ops, + struct net_device *dev, int initial_ref, int initial_obsolete, + unsigned short flags) { - struct dst_entry *dst; - - if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { - if (ops->gc(ops)) - return NULL; - } - dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); - if (!dst) - return NULL; dst->child = NULL; dst->dev = dev; if (dev) @@ -200,6 +192,25 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst->next = NULL; if (!(flags & DST_NOCOUNT)) dst_entries_add(ops, 1); +} +EXPORT_SYMBOL(dst_init); + +void *dst_alloc(struct dst_ops *ops, struct net_device *dev, + int initial_ref, int initial_obsolete, unsigned short flags) +{ + struct dst_entry *dst; + + if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { + if (ops->gc(ops)) + return NULL; + } + + dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); + if (!dst) + return NULL; + + dst_init(dst, ops, dev, initial_ref, initial_obsolete, flags); + return dst; } EXPORT_SYMBOL(dst_alloc); @@ -248,7 +259,11 @@ again: dst->ops->destroy(dst); if (dst->dev) dev_put(dst->dev); - kmem_cache_free(dst->ops->kmem_cachep, dst); + + if (dst->flags & DST_METADATA) + kfree(dst); + else + kmem_cache_free(dst->ops->kmem_cachep, dst); dst = child; if (dst) { @@ -329,6 +344,47 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) } EXPORT_SYMBOL(__dst_destroy_metrics_generic); +static struct dst_ops md_dst_ops = { + .family = AF_UNSPEC, +}; + +static int dst_md_discard_sk(struct sock *sk, struct sk_buff *skb) +{ + WARN_ONCE(1, "Attempting to call output on metadata dst\n"); + kfree_skb(skb); + return 0; +} + +static int dst_md_discard(struct sk_buff *skb) +{ + WARN_ONCE(1, "Attempting to call input on metadata dst\n"); + kfree_skb(skb); + return 0; +} + +struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags) +{ + struct metadata_dst *md_dst; + struct dst_entry *dst; + + md_dst = kmalloc(sizeof(*md_dst) + optslen, flags); + if (!md_dst) + return ERR_PTR(-ENOMEM); + + dst = &md_dst->dst; + dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE, + DST_METADATA | DST_NOCACHE | DST_NOCOUNT); + + dst->input = dst_md_discard; + dst->output = dst_md_discard_sk; + + memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); + md_dst->opts_len = optslen; + + return md_dst; +} +EXPORT_SYMBOL_GPL(metadata_dst_alloc); + /* Dirty hack. We did it in 2.2 (in __dst_free), * we have _very_ good reasons not to repeat * this mistake in 2.3, but we have no choice @@ -393,7 +449,7 @@ static struct notifier_block dst_dev_notifier = { .priority = -10, /* must be called after other network notifiers */ }; -void __init dst_init(void) +void __init dst_subsys_init(void) { register_netdevice_notifier(&dst_dev_notifier); } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 9a12668f7d62..ae8306e7c56f 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -16,6 +16,7 @@ #include <net/net_namespace.h> #include <net/sock.h> #include <net/fib_rules.h> +#include <net/ip_tunnels.h> int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table, u32 flags) @@ -186,6 +187,9 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) goto out; + if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id)) + goto out; + ret = ops->match(rule, fl, flags); out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; @@ -330,6 +334,9 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) if (tb[FRA_FWMASK]) rule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); + if (tb[FRA_TUN_ID]) + rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); + rule->action = frh->action; rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); @@ -407,6 +414,9 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) if (unresolved) ops->unresolved_rules++; + if (rule->tun_id) + ip_tunnel_need_metadata(); + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); @@ -473,6 +483,10 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) (rule->mark_mask != nla_get_u32(tb[FRA_FWMASK]))) continue; + if (tb[FRA_TUN_ID] && + (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID]))) + continue; + if (!ops->compare(rule, frh, tb)) continue; @@ -487,6 +501,9 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) goto errout; } + if (rule->tun_id) + ip_tunnel_unneed_metadata(); + list_del_rcu(&rule->list); if (rule->action == FR_ACT_GOTO) { @@ -535,7 +552,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ - + nla_total_size(4); /* FRA_FWMASK */ + + nla_total_size(4) /* FRA_FWMASK */ + + nla_total_size(8); /* FRA_TUN_ID */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); @@ -591,7 +609,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, ((rule->mark_mask || rule->mark) && nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || (rule->target && - nla_put_u32(skb, FRA_GOTO, rule->target))) + nla_put_u32(skb, FRA_GOTO, rule->target)) || + (rule->tun_id && + nla_put_be64(skb, FRA_TUN_ID, rule->tun_id))) goto nla_put_failure; if (rule->suppress_ifgroup != -1) { diff --git a/net/core/filter.c b/net/core/filter.c index be3098fb65e4..786722a9c6f2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -47,6 +47,7 @@ #include <linux/if_vlan.h> #include <linux/bpf.h> #include <net/sch_generic.h> +#include <net/cls_cgroup.h> /** * sk_filter - run a packet through a socket filter @@ -1424,6 +1425,64 @@ const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; +static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return task_get_classid((struct sk_buff *) (unsigned long) r1); +} + +static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { + .func = bpf_get_cgroup_classid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + __be16 vlan_proto = (__force __be16) r2; + + if (unlikely(vlan_proto != htons(ETH_P_8021Q) && + vlan_proto != htons(ETH_P_8021AD))) + vlan_proto = htons(ETH_P_8021Q); + + return skb_vlan_push(skb, vlan_proto, vlan_tci); +} + +const struct bpf_func_proto bpf_skb_vlan_push_proto = { + .func = bpf_skb_vlan_push, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; +EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto); + +static u64 bpf_skb_vlan_pop(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + + return skb_vlan_pop(skb); +} + +const struct bpf_func_proto bpf_skb_vlan_pop_proto = { + .func = bpf_skb_vlan_pop, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; +EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto); + +bool bpf_helper_changes_skb_data(void *func) +{ + if (func == bpf_skb_vlan_push) + return true; + if (func == bpf_skb_vlan_pop) + return true; + return false; +} + static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id) { @@ -1461,6 +1520,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_l4_csum_replace_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_proto; + case BPF_FUNC_skb_vlan_push: + return &bpf_skb_vlan_push_proto; + case BPF_FUNC_skb_vlan_pop: + return &bpf_skb_vlan_pop_proto; default: return sk_filter_func_proto(func_id); } diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c new file mode 100644 index 000000000000..bb58826c708d --- /dev/null +++ b/net/core/lwtunnel.c @@ -0,0 +1,235 @@ +/* + * lwtunnel Infrastructure for light weight tunnels like mpls + * + * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <linux/capability.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/lwtunnel.h> +#include <linux/in.h> +#include <linux/init.h> +#include <linux/err.h> + +#include <net/lwtunnel.h> +#include <net/rtnetlink.h> +#include <net/ip6_fib.h> + +struct lwtunnel_state *lwtunnel_state_alloc(int encap_len) +{ + struct lwtunnel_state *lws; + + lws = kzalloc(sizeof(*lws) + encap_len, GFP_ATOMIC); + + return lws; +} +EXPORT_SYMBOL(lwtunnel_state_alloc); + +const struct lwtunnel_encap_ops __rcu * + lwtun_encaps[LWTUNNEL_ENCAP_MAX + 1] __read_mostly; + +int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *ops, + unsigned int num) +{ + if (num > LWTUNNEL_ENCAP_MAX) + return -ERANGE; + + return !cmpxchg((const struct lwtunnel_encap_ops **) + &lwtun_encaps[num], + NULL, ops) ? 0 : -1; +} +EXPORT_SYMBOL(lwtunnel_encap_add_ops); + +int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops, + unsigned int encap_type) +{ + int ret; + + if (encap_type == LWTUNNEL_ENCAP_NONE || + encap_type > LWTUNNEL_ENCAP_MAX) + return -ERANGE; + + ret = (cmpxchg((const struct lwtunnel_encap_ops **) + &lwtun_encaps[encap_type], + ops, NULL) == ops) ? 0 : -1; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_encap_del_ops); + +int lwtunnel_build_state(struct net_device *dev, u16 encap_type, + struct nlattr *encap, struct lwtunnel_state **lws) +{ + const struct lwtunnel_encap_ops *ops; + int ret = -EINVAL; + + if (encap_type == LWTUNNEL_ENCAP_NONE || + encap_type > LWTUNNEL_ENCAP_MAX) + return ret; + + ret = -EOPNOTSUPP; + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[encap_type]); + if (likely(ops && ops->build_state)) + ret = ops->build_state(dev, encap, lws); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_build_state); + +int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate) +{ + const struct lwtunnel_encap_ops *ops; + struct nlattr *nest; + int ret = -EINVAL; + + if (!lwtstate) + return 0; + + if (lwtstate->type == LWTUNNEL_ENCAP_NONE || + lwtstate->type > LWTUNNEL_ENCAP_MAX) + return 0; + + ret = -EOPNOTSUPP; + nest = nla_nest_start(skb, RTA_ENCAP); + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[lwtstate->type]); + if (likely(ops && ops->fill_encap)) + ret = ops->fill_encap(skb, lwtstate); + rcu_read_unlock(); + + if (ret) + goto nla_put_failure; + nla_nest_end(skb, nest); + ret = nla_put_u16(skb, RTA_ENCAP_TYPE, lwtstate->type); + if (ret) + goto nla_put_failure; + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + + return (ret == -EOPNOTSUPP ? 0 : ret); +} +EXPORT_SYMBOL(lwtunnel_fill_encap); + +int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) +{ + const struct lwtunnel_encap_ops *ops; + int ret = 0; + + if (!lwtstate) + return 0; + + if (lwtstate->type == LWTUNNEL_ENCAP_NONE || + lwtstate->type > LWTUNNEL_ENCAP_MAX) + return 0; + + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[lwtstate->type]); + if (likely(ops && ops->get_encap_size)) + ret = nla_total_size(ops->get_encap_size(lwtstate)); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_get_encap_size); + +int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + const struct lwtunnel_encap_ops *ops; + int ret = 0; + + if (!a && !b) + return 0; + + if (!a || !b) + return 1; + + if (a->type != b->type) + return 1; + + if (a->type == LWTUNNEL_ENCAP_NONE || + a->type > LWTUNNEL_ENCAP_MAX) + return 0; + + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[a->type]); + if (likely(ops && ops->cmp_encap)) + ret = ops->cmp_encap(a, b); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_cmp_encap); + +int __lwtunnel_output(struct sock *sk, struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + const struct lwtunnel_encap_ops *ops; + int ret = -EINVAL; + + if (!lwtstate) + goto drop; + + if (lwtstate->type == LWTUNNEL_ENCAP_NONE || + lwtstate->type > LWTUNNEL_ENCAP_MAX) + return 0; + + ret = -EOPNOTSUPP; + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[lwtstate->type]); + if (likely(ops && ops->output)) + ret = ops->output(sk, skb); + rcu_read_unlock(); + + if (ret == -EOPNOTSUPP) + goto drop; + + return ret; + +drop: + kfree(skb); + + return ret; +} + +int lwtunnel_output6(struct sock *sk, struct sk_buff *skb) +{ + struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + struct lwtunnel_state *lwtstate = NULL; + + if (rt) + lwtstate = rt->rt6i_lwtstate; + + return __lwtunnel_output(sk, skb, lwtstate); +} +EXPORT_SYMBOL(lwtunnel_output6); + +int lwtunnel_output(struct sock *sk, struct sk_buff *skb) +{ + struct rtable *rt = (struct rtable *)skb_dst(skb); + struct lwtunnel_state *lwtstate = NULL; + + if (rt) + lwtstate = rt->rt_lwtstate; + + return __lwtunnel_output(sk, skb, lwtstate); +} +EXPORT_SYMBOL(lwtunnel_output); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 18b34d771ed4..194c1d03b2b3 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -404,6 +404,19 @@ static ssize_t group_store(struct device *dev, struct device_attribute *attr, NETDEVICE_SHOW(group, fmt_dec); static DEVICE_ATTR(netdev_group, S_IRUGO | S_IWUSR, group_show, group_store); +static int change_proto_down(struct net_device *dev, unsigned long proto_down) +{ + return dev_change_proto_down(dev, (bool) proto_down); +} + +static ssize_t proto_down_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_proto_down); +} +NETDEVICE_SHOW_RW(proto_down, fmt_dec); + static ssize_t phys_port_id_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -501,6 +514,7 @@ static struct attribute *net_class_attrs[] = { &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, + &dev_attr_proto_down.attr, NULL, }; ATTRIBUTE_GROUPS(net_class); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index dc004b1e1f85..788ceed39463 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -896,7 +896,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ - + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(1); /* IFLA_PROTO_DOWN */ + } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -1082,7 +1084,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, (dev->ifalias && nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) || nla_put_u32(skb, IFLA_CARRIER_CHANGES, - atomic_read(&dev->carrier_changes))) + atomic_read(&dev->carrier_changes)) || + nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) goto nla_put_failure; if (1) { @@ -1319,6 +1322,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */ [IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, [IFLA_LINK_NETNSID] = { .type = NLA_S32 }, + [IFLA_PROTO_DOWN] = { .type = NLA_U8 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -1861,6 +1865,14 @@ static int do_setlink(const struct sk_buff *skb, } err = 0; + if (tb[IFLA_PROTO_DOWN]) { + err = dev_change_proto_down(dev, + nla_get_u8(tb[IFLA_PROTO_DOWN])); + if (err) + goto errout; + status |= DO_SETLINK_NOTIFY; + } + errout: if (status & DO_SETLINK_MODIFIED) { if (status & DO_SETLINK_NOTIFY) @@ -1951,16 +1963,30 @@ static int rtnl_group_dellink(const struct net *net, int group) return 0; } +int rtnl_delete_link(struct net_device *dev) +{ + const struct rtnl_link_ops *ops; + LIST_HEAD(list_kill); + + ops = dev->rtnl_link_ops; + if (!ops || !ops->dellink) + return -EOPNOTSUPP; + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + + return 0; +} +EXPORT_SYMBOL_GPL(rtnl_delete_link); + static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - const struct rtnl_link_ops *ops; struct net_device *dev; struct ifinfomsg *ifm; char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; int err; - LIST_HEAD(list_kill); err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) @@ -1982,13 +2008,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) if (!dev) return -ENODEV; - ops = dev->rtnl_link_ops; - if (!ops || !ops->dellink) - return -EOPNOTSUPP; - - ops->dellink(dev, &list_kill); - unregister_netdevice_many(&list_kill); - return 0; + return rtnl_delete_link(dev); } int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 43d3dd62fcc8..42689d5c468c 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -60,11 +60,15 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) struct phy_device *phydev; unsigned int type; + if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->drv) + return false; + if (skb_headroom(skb) < ETH_HLEN) return false; + __skb_push(skb, ETH_HLEN); - type = classify(skb); + type = ptp_classify_raw(skb); __skb_pull(skb, ETH_HLEN); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 933a92820d26..1d59e50ce8b7 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -291,6 +291,40 @@ static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); } +/* Create and send an arp packet. */ +static void arp_send_dst(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, + const unsigned char *dest_hw, + const unsigned char *src_hw, + const unsigned char *target_hw, struct sk_buff *oskb) +{ + struct sk_buff *skb; + + /* arp on this interface. */ + if (dev->flags & IFF_NOARP) + return; + + skb = arp_create(type, ptype, dest_ip, dev, src_ip, + dest_hw, src_hw, target_hw); + if (!skb) + return; + + if (oskb) + skb_dst_copy(skb, oskb); + + arp_xmit(skb); +} + +void arp_send(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, + const unsigned char *dest_hw, const unsigned char *src_hw, + const unsigned char *target_hw) +{ + arp_send_dst(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, + target_hw, NULL); +} +EXPORT_SYMBOL(arp_send); + static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { __be32 saddr = 0; @@ -346,8 +380,9 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } } - arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, - dst_hw, dev->dev_addr, NULL); + arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, + dst_hw, dev->dev_addr, NULL, + dev->priv_flags & IFF_XMIT_DST_RELEASE ? NULL : skb); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) @@ -597,32 +632,6 @@ void arp_xmit(struct sk_buff *skb) EXPORT_SYMBOL(arp_xmit); /* - * Create and send an arp packet. - */ -void arp_send(int type, int ptype, __be32 dest_ip, - struct net_device *dev, __be32 src_ip, - const unsigned char *dest_hw, const unsigned char *src_hw, - const unsigned char *target_hw) -{ - struct sk_buff *skb; - - /* - * No arp on this interface. - */ - - if (dev->flags&IFF_NOARP) - return; - - skb = arp_create(type, ptype, dest_ip, dev, src_ip, - dest_hw, src_hw, target_hw); - if (!skb) - return; - - arp_xmit(skb); -} -EXPORT_SYMBOL(arp_send); - -/* * Process an arp request. */ diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 6bbc54940eb4..6b98de0d7949 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -280,6 +280,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_scope = scope; fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0; + fl4.flowi4_tun_key.tun_id = 0; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); } else { @@ -313,6 +314,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.saddr = dst; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_tun_key.tun_id = 0; no_addr = idev->ifa_list == NULL; @@ -591,6 +593,8 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_FLOW] = { .type = NLA_U32 }, + [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, + [RTA_ENCAP] = { .type = NLA_NESTED }, }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, @@ -656,6 +660,12 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, case RTA_TABLE: cfg->fc_table = nla_get_u32(attr); break; + case RTA_ENCAP: + cfg->fc_encap = attr; + break; + case RTA_ENCAP_TYPE: + cfg->fc_encap_type = nla_get_u16(attr); + break; } } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index c7358ea4ae93..6754c64b2fe0 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -42,6 +42,7 @@ #include <net/ip_fib.h> #include <net/netlink.h> #include <net/nexthop.h> +#include <net/lwtunnel.h> #include "fib_lookup.h" @@ -208,6 +209,7 @@ static void free_fib_info_rcu(struct rcu_head *head) change_nexthops(fi) { if (nexthop_nh->nh_dev) dev_put(nexthop_nh->nh_dev); + lwtunnel_state_put(nexthop_nh->nh_lwtstate); free_nh_exceptions(nexthop_nh); rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output); rt_fibinfo_free(&nexthop_nh->nh_rth_input); @@ -266,6 +268,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) #ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid != onh->nh_tclassid || #endif + lwtunnel_cmp_encap(nh->nh_lwtstate, onh->nh_lwtstate) || ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_COMPARE_MASK)) return -1; onh++; @@ -366,6 +369,7 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) payload += nla_total_size((RTAX_MAX * nla_total_size(4))); if (fi->fib_nhs) { + size_t nh_encapsize = 0; /* Also handles the special case fib_nhs == 1 */ /* each nexthop is packed in an attribute */ @@ -374,8 +378,21 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) /* may contain flow and gateway attribute */ nhsize += 2 * nla_total_size(4); + /* grab encap info */ + for_nexthops(fi) { + if (nh->nh_lwtstate) { + /* RTA_ENCAP_TYPE */ + nh_encapsize += lwtunnel_get_encap_size( + nh->nh_lwtstate); + /* RTA_ENCAP */ + nh_encapsize += nla_total_size(2); + } + } endfor_nexthops(fi); + /* all nexthops are packed in a nested attribute */ - payload += nla_total_size(fi->fib_nhs * nhsize); + payload += nla_total_size((fi->fib_nhs * nhsize) + + nh_encapsize); + } return payload; @@ -452,6 +469,9 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, int remaining, struct fib_config *cfg) { + struct net *net = cfg->fc_nlinfo.nl_net; + int ret; + change_nexthops(fi) { int attrlen; @@ -475,18 +495,66 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (nexthop_nh->nh_tclassid) fi->fib_net->ipv4.fib_num_tclassid_users++; #endif + nla = nla_find(attrs, attrlen, RTA_ENCAP); + if (nla) { + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + struct nlattr *nla_entype; + + nla_entype = nla_find(attrs, attrlen, + RTA_ENCAP_TYPE); + if (!nla_entype) + goto err_inval; + if (cfg->fc_oif) + dev = __dev_get_by_index(net, cfg->fc_oif); + ret = lwtunnel_build_state(dev, nla_get_u16( + nla_entype), + nla, &lwtstate); + if (ret) + goto errout; + lwtunnel_state_get(lwtstate); + nexthop_nh->nh_lwtstate = lwtstate; + } } rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); return 0; + +err_inval: + ret = -EINVAL; + +errout: + return ret; } #endif +int fib_encap_match(struct net *net, u16 encap_type, + struct nlattr *encap, + int oif, const struct fib_nh *nh) +{ + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + int ret; + + if (encap_type == LWTUNNEL_ENCAP_NONE) + return 0; + + if (oif) + dev = __dev_get_by_index(net, oif); + ret = lwtunnel_build_state(dev, encap_type, + encap, &lwtstate); + if (!ret) + return lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate); + + return 0; +} + int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) { + struct net *net = cfg->fc_nlinfo.nl_net; #ifdef CONFIG_IP_ROUTE_MULTIPATH struct rtnexthop *rtnh; int remaining; @@ -496,6 +564,12 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) return 1; if (cfg->fc_oif || cfg->fc_gw) { + if (cfg->fc_encap) { + if (fib_encap_match(net, cfg->fc_encap_type, + cfg->fc_encap, cfg->fc_oif, + fi->fib_nh)) + return 1; + } if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) return 0; @@ -882,6 +956,22 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } else { struct fib_nh *nh = fi->fib_nh; + if (cfg->fc_encap) { + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + + if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) + goto err_inval; + if (cfg->fc_oif) + dev = __dev_get_by_index(net, cfg->fc_oif); + err = lwtunnel_build_state(dev, cfg->fc_encap_type, + cfg->fc_encap, &lwtstate); + if (err) + goto failure; + + lwtunnel_state_get(lwtstate); + nh->nh_lwtstate = lwtstate; + } nh->nh_oif = cfg->fc_oif; nh->nh_gw = cfg->fc_gw; nh->nh_flags = cfg->fc_flags; @@ -1055,6 +1145,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) goto nla_put_failure; #endif + if (fi->fib_nh->nh_lwtstate) + lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate); } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fi->fib_nhs > 1) { @@ -1090,6 +1182,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) goto nla_put_failure; #endif + if (nh->nh_lwtstate) + lwtunnel_fill_encap(skb, nh->nh_lwtstate); /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; } endfor_nexthops(fi); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index f5203fba6236..c0556f1e4bf0 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -496,6 +496,7 @@ static struct rtable *icmp_route_lookup(struct net *net, } /* Ugh! */ orefdst = skb_in->_skb_refdst; /* save old refdst */ + skb_dst_set(skb_in, NULL); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, RT_TOS(tos), rt2->dst.dev); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0cb9165421d4..89120196a949 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -343,7 +343,6 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; - int twrefcnt = 0; spin_lock(lock); @@ -371,21 +370,17 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { - twrefcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); - if (twrefcnt) - inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw); - - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); } return 0; @@ -403,13 +398,12 @@ static u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) +void __inet_hash_nolisten(struct sock *sk, struct sock *osk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; struct inet_ehash_bucket *head; spinlock_t *lock; - int twrefcnt = 0; WARN_ON(!sk_unhashed(sk)); @@ -420,23 +414,22 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) spin_lock(lock); __sk_nulls_add_node_rcu(sk, list); - if (tw) { - WARN_ON(sk->sk_hash != tw->tw_hash); - twrefcnt = inet_twsk_unhash(tw); + if (osk) { + WARN_ON(sk->sk_hash != osk->sk_hash); + sk_nulls_del_node_init_rcu(osk); } spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - return twrefcnt; } EXPORT_SYMBOL_GPL(__inet_hash_nolisten); -int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw) +void __inet_hash(struct sock *sk, struct sock *osk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_listen_hashbucket *ilb; if (sk->sk_state != TCP_LISTEN) - return __inet_hash_nolisten(sk, tw); + return __inet_hash_nolisten(sk, osk); WARN_ON(!sk_unhashed(sk)); ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; @@ -445,7 +438,6 @@ int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw) __sk_nulls_add_node_rcu(sk, &ilb->head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); spin_unlock(&ilb->lock); - return 0; } EXPORT_SYMBOL(__inet_hash); @@ -492,7 +484,6 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct inet_bind_bucket *tb; int ret; struct net *net = sock_net(sk); - int twrefcnt = 1; if (!snum) { int i, remaining, low, high, port; @@ -560,19 +551,14 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - twrefcnt += __inet_hash_nolisten(sk, tw); + __inet_hash_nolisten(sk, (struct sock *)tw); } if (tw) - twrefcnt += inet_twsk_bind_unhash(tw, hinfo); + inet_twsk_bind_unhash(tw, hinfo); spin_unlock(&head->lock); - if (tw) { - inet_twsk_deschedule(tw); - while (twrefcnt) { - twrefcnt--; - inet_twsk_put(tw); - } - } + if (tw) + inet_twsk_deschedule_put(tw); ret = 0; goto out; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 2ffbd16b79e0..ae22cc24fbe8 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -18,28 +18,6 @@ /** - * inet_twsk_unhash - unhash a timewait socket from established hash - * @tw: timewait socket - * - * unhash a timewait socket from established hash, if hashed. - * ehash lock must be held by caller. - * Returns 1 if caller should call inet_twsk_put() after lock release. - */ -int inet_twsk_unhash(struct inet_timewait_sock *tw) -{ - if (hlist_nulls_unhashed(&tw->tw_node)) - return 0; - - hlist_nulls_del_rcu(&tw->tw_node); - sk_nulls_node_init(&tw->tw_node); - /* - * We cannot call inet_twsk_put() ourself under lock, - * caller must call it for us. - */ - return 1; -} - -/** * inet_twsk_bind_unhash - unhash a timewait socket from bind hash * @tw: timewait socket * @hashinfo: hashinfo pointer @@ -48,35 +26,29 @@ int inet_twsk_unhash(struct inet_timewait_sock *tw) * bind hash lock must be held by caller. * Returns 1 if caller should call inet_twsk_put() after lock release. */ -int inet_twsk_bind_unhash(struct inet_timewait_sock *tw, +void inet_twsk_bind_unhash(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) { struct inet_bind_bucket *tb = tw->tw_tb; if (!tb) - return 0; + return; __hlist_del(&tw->tw_bind_node); tw->tw_tb = NULL; inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); - /* - * We cannot call inet_twsk_put() ourself under lock, - * caller must call it for us. - */ - return 1; + __sock_put((struct sock *)tw); } /* Must be called with locally disabled BHs. */ static void inet_twsk_kill(struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo; - struct inet_bind_hashbucket *bhead; - int refcnt; - /* Unlink from established hashes. */ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); + struct inet_bind_hashbucket *bhead; spin_lock(lock); - refcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); spin_unlock(lock); /* Disassociate with bind bucket. */ @@ -84,11 +56,9 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) hashinfo->bhash_size)]; spin_lock(&bhead->lock); - refcnt += inet_twsk_bind_unhash(tw, hashinfo); + inet_twsk_bind_unhash(tw, hashinfo); spin_unlock(&bhead->lock); - BUG_ON(refcnt >= atomic_read(&tw->tw_refcnt)); - atomic_sub(refcnt, &tw->tw_refcnt); atomic_dec(&tw->tw_dr->tw_count); inet_twsk_put(tw); } @@ -235,13 +205,17 @@ EXPORT_SYMBOL_GPL(inet_twsk_alloc); * tcp_input.c to verify this. */ -/* This is for handling early-kills of TIME_WAIT sockets. */ -void inet_twsk_deschedule(struct inet_timewait_sock *tw) +/* This is for handling early-kills of TIME_WAIT sockets. + * Warning : consume reference. + * Caller should not access tw anymore. + */ +void inet_twsk_deschedule_put(struct inet_timewait_sock *tw) { if (del_timer_sync(&tw->tw_timer)) inet_twsk_kill(tw); + inet_twsk_put(tw); } -EXPORT_SYMBOL(inet_twsk_deschedule); +EXPORT_SYMBOL(inet_twsk_deschedule_put); void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) { @@ -311,9 +285,8 @@ restart: rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule(tw); + inet_twsk_deschedule_put(tw); local_bh_enable(); - inet_twsk_put(tw); goto restart_rcu; } /* If the nulls value we got at the end of this lookup is diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 31f71b15cfba..f44bccc42494 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -522,7 +522,6 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, int len; int ihlen; int err; - int sum_truesize; u8 ecn; ipq_kill(qp); @@ -590,32 +589,19 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, add_frag_mem_limit(&qp->q, clone->truesize); } + skb_shinfo(head)->frag_list = head->next; skb_push(head, head->data - skb_network_header(head)); - sum_truesize = head->truesize; - for (fp = head->next; fp;) { - bool headstolen; - int delta; - struct sk_buff *next = fp->next; - - sum_truesize += fp->truesize; + for (fp=head->next; fp; fp = fp->next) { + head->data_len += fp->len; + head->len += fp->len; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); - - if (skb_try_coalesce(head, fp, &headstolen, &delta)) { - kfree_skb_partial(fp, headstolen); - } else { - if (!skb_shinfo(head)->frag_list) - skb_shinfo(head)->frag_list = fp; - head->data_len += fp->len; - head->len += fp->len; - head->truesize += fp->truesize; - } - fp = next; + head->truesize += fp->truesize; } - sub_frag_mem_limit(&qp->q, sum_truesize); + sub_frag_mem_limit(&qp->q, head->truesize); head->next = NULL; head->dev = dev; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 2db4c8773c1b..f4fc8a77aaa7 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -146,6 +146,7 @@ #include <net/xfrm.h> #include <linux/mroute.h> #include <linux/netlink.h> +#include <net/dst_metadata.h> /* * Process Router Attention IP option (RFC 2113) @@ -331,7 +332,7 @@ static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb) * Initialise the virtual path cache for the packet. It describes * how the packet travels inside Linux networking. */ - if (!skb_dst(skb)) { + if (!skb_valid_dst(skb)) { int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, iph->tos, skb->dev); if (unlikely(err)) { diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6a51a71a6c67..630e6d5712e8 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -32,6 +32,7 @@ #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> +#include <linux/static_key.h> #include <net/ip.h> #include <net/icmp.h> @@ -190,3 +191,132 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, return tot; } EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); + +static const struct nla_policy ip_tun_policy[IP_TUN_MAX + 1] = { + [IP_TUN_ID] = { .type = NLA_U64 }, + [IP_TUN_DST] = { .type = NLA_U32 }, + [IP_TUN_SRC] = { .type = NLA_U32 }, + [IP_TUN_TTL] = { .type = NLA_U8 }, + [IP_TUN_TOS] = { .type = NLA_U8 }, + [IP_TUN_SPORT] = { .type = NLA_U16 }, + [IP_TUN_DPORT] = { .type = NLA_U16 }, + [IP_TUN_FLAGS] = { .type = NLA_U16 }, +}; + +static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr, + struct lwtunnel_state **ts) +{ + struct ip_tunnel_info *tun_info; + struct lwtunnel_state *new_state; + struct nlattr *tb[IP_TUN_MAX + 1]; + int err; + + err = nla_parse_nested(tb, IP_TUN_MAX, attr, ip_tun_policy); + if (err < 0) + return err; + + new_state = lwtunnel_state_alloc(sizeof(*tun_info)); + if (!new_state) + return -ENOMEM; + + new_state->type = LWTUNNEL_ENCAP_IP; + + tun_info = lwt_tun_info(new_state); + + if (tb[IP_TUN_ID]) + tun_info->key.tun_id = nla_get_u64(tb[IP_TUN_ID]); + + if (tb[IP_TUN_DST]) + tun_info->key.ipv4_dst = nla_get_be32(tb[IP_TUN_DST]); + + if (tb[IP_TUN_SRC]) + tun_info->key.ipv4_src = nla_get_be32(tb[IP_TUN_SRC]); + + if (tb[IP_TUN_TTL]) + tun_info->key.ipv4_ttl = nla_get_u8(tb[IP_TUN_TTL]); + + if (tb[IP_TUN_TOS]) + tun_info->key.ipv4_tos = nla_get_u8(tb[IP_TUN_TOS]); + + if (tb[IP_TUN_SPORT]) + tun_info->key.tp_src = nla_get_be16(tb[IP_TUN_SPORT]); + + if (tb[IP_TUN_DPORT]) + tun_info->key.tp_dst = nla_get_be16(tb[IP_TUN_DPORT]); + + if (tb[IP_TUN_FLAGS]) + tun_info->key.tun_flags = nla_get_u16(tb[IP_TUN_FLAGS]); + + tun_info->mode = IP_TUNNEL_INFO_TX; + tun_info->options = NULL; + tun_info->options_len = 0; + + *ts = new_state; + + return 0; +} + +static int ip_tun_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); + + if (nla_put_u64(skb, IP_TUN_ID, tun_info->key.tun_id) || + nla_put_be32(skb, IP_TUN_DST, tun_info->key.ipv4_dst) || + nla_put_be32(skb, IP_TUN_SRC, tun_info->key.ipv4_src) || + nla_put_u8(skb, IP_TUN_TOS, tun_info->key.ipv4_tos) || + nla_put_u8(skb, IP_TUN_TTL, tun_info->key.ipv4_ttl) || + nla_put_u16(skb, IP_TUN_SPORT, tun_info->key.tp_src) || + nla_put_u16(skb, IP_TUN_DPORT, tun_info->key.tp_dst) || + nla_put_u16(skb, IP_TUN_FLAGS, tun_info->key.tun_flags)) + return -ENOMEM; + + return 0; +} + +static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + return nla_total_size(8) /* IP_TUN_ID */ + + nla_total_size(4) /* IP_TUN_DST */ + + nla_total_size(4) /* IP_TUN_SRC */ + + nla_total_size(1) /* IP_TUN_TOS */ + + nla_total_size(1) /* IP_TUN_TTL */ + + nla_total_size(2) /* IP_TUN_SPORT */ + + nla_total_size(2) /* IP_TUN_DPORT */ + + nla_total_size(2); /* IP_TUN_FLAGS */ +} + +static const struct lwtunnel_encap_ops ip_tun_lwt_ops = { + .build_state = ip_tun_build_state, + .fill_encap = ip_tun_fill_encap_info, + .get_encap_size = ip_tun_encap_nlsize, +}; + +static int __init ip_tunnel_core_init(void) +{ + lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP); + + return 0; +} +module_init(ip_tunnel_core_init); + +static void __exit ip_tunnel_core_exit(void) +{ + lwtunnel_encap_del_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP); +} +module_exit(ip_tunnel_core_exit); + +struct static_key ip_tunnel_metadata_cnt = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL(ip_tunnel_metadata_cnt); + +void ip_tunnel_need_metadata(void) +{ + static_key_slow_inc(&ip_tunnel_metadata_cnt); +} +EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata); + +void ip_tunnel_unneed_metadata(void) +{ + static_key_slow_dec(&ip_tunnel_metadata_cnt); +} +EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 05ff44b758df..e89094ab5ddb 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -363,7 +363,8 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, scoped); rcu_read_unlock(); - if (!(isk->freebind || isk->transparent || has_addr || + if (!(net->ipv6.sysctl.ip_nonlocal_bind || + isk->freebind || isk->transparent || has_addr || addr_type == IPV6_ADDR_ANY)) return -EADDRNOTAVAIL; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index da5d483e236a..3abd9d7a3adf 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -300,6 +300,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE), SNMP_MIB_ITEM("TCPWinProbe", LINUX_MIB_TCPWINPROBE), SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE), + SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL), + SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d0362a2de3d3..519ec232818d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -91,6 +91,7 @@ #include <linux/slab.h> #include <linux/jhash.h> #include <net/dst.h> +#include <net/dst_metadata.h> #include <net/net_namespace.h> #include <net/protocol.h> #include <net/ip.h> @@ -102,6 +103,7 @@ #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> +#include <net/lwtunnel.h> #include <net/netevent.h> #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL @@ -109,6 +111,7 @@ #include <linux/kmemleak.h> #endif #include <net/secure_seq.h> +#include <net/ip_tunnels.h> #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) @@ -1355,6 +1358,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst) list_del(&rt->rt_uncached); spin_unlock_bh(&ul->lock); } + lwtunnel_state_put(rt->rt_lwtstate); } void rt_flush_dev(struct net_device *dev) @@ -1403,6 +1407,12 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif + if (nh->nh_lwtstate) { + lwtunnel_state_get(nh->nh_lwtstate); + rt->rt_lwtstate = nh->nh_lwtstate; + } else { + rt->rt_lwtstate = NULL; + } if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr); else if (!(rt->dst.flags & DST_NOCACHE)) @@ -1488,6 +1498,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + rth->rt_lwtstate = NULL; if (our) { rth->dst.input= ip_local_deliver; rth->rt_flags |= RTCF_LOCAL; @@ -1546,7 +1557,6 @@ static int __mkroute_input(struct sk_buff *skb, struct rtable *rth; int err; struct in_device *out_dev; - unsigned int flags = 0; bool do_cache; u32 itag = 0; @@ -1610,7 +1620,7 @@ static int __mkroute_input(struct sk_buff *skb, } rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev)); - rth->rt_flags = flags; + rth->rt_flags = 0; rth->rt_type = res->type; rth->rt_is_input = 1; rth->rt_iif = 0; @@ -1618,12 +1628,15 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + rth->rt_lwtstate = NULL; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rth->dst.output = ip_output; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag); + if (lwtunnel_output_redirect(rth->rt_lwtstate)) + rth->dst.output = lwtunnel_output; skb_dst_set(skb, &rth->dst); out: err = 0; @@ -1662,6 +1675,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, { struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); + struct ip_tunnel_info *tun_info; struct flowi4 fl4; unsigned int flags = 0; u32 itag = 0; @@ -1679,6 +1693,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, by fib_lookup. */ + tun_info = skb_tunnel_info(skb, AF_INET); + if (tun_info && tun_info->mode == IP_TUNNEL_INFO_RX) + fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id; + else + fl4.flowi4_tun_key.tun_id = 0; + skb_dst_drop(skb); + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; @@ -1792,6 +1813,8 @@ local_input: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + rth->rt_lwtstate = NULL; + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; @@ -1981,7 +2004,7 @@ add: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); - + rth->rt_lwtstate = NULL; RT_CACHE_STAT_INC(out_slow_tot); if (flags & RTCF_LOCAL) @@ -2261,7 +2284,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_uses_gateway = ort->rt_uses_gateway; INIT_LIST_HEAD(&rt->rt_uncached); - + rt->rt_lwtstate = NULL; dst_free(new); } diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index c037644eafb7..fd1405d37c14 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -146,7 +146,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { bictcp_update(ca, tp->snd_cwnd); diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 8c6fd3d5e40f..167b6a3e1b98 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -264,7 +264,7 @@ static void tcp_cdg_cong_avoid(struct sock *sk, u32 ack, u32 acked) u32 prior_snd_cwnd; u32 incr; - if (tp->snd_cwnd < tp->snd_ssthresh && hystart_detect) + if (tcp_in_slow_start(tp) && hystart_detect) tcp_cdg_hystart_update(sk); if (after(ack, ca->rtt_seq) && ca->rtt.v64) { diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 84be008c945c..a2ed23c595cf 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -365,10 +365,8 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) */ u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { - u32 cwnd = tp->snd_cwnd + acked; + u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh); - if (cwnd > tp->snd_ssthresh) - cwnd = tp->snd_ssthresh + 1; acked -= cwnd - tp->snd_cwnd; tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp); @@ -413,7 +411,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; /* In "safe" area, increase. */ - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 06d3d665a9fd..28011fb1f4a2 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -320,7 +320,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { if (hystart && after(ack, ca->end_seq)) bictcp_hystart_reset(sk); acked = tcp_slow_start(tp, acked); @@ -439,7 +439,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) ca->delay_min = delay; /* hystart triggers when cwnd is larger than some threshold */ - if (hystart && tp->snd_cwnd <= tp->snd_ssthresh && + if (hystart && tcp_in_slow_start(tp) && tp->snd_cwnd >= hystart_low_window) hystart_update(sk, delay); } diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c index 882c08aae2f5..db7842495a64 100644 --- a/net/ipv4/tcp_highspeed.c +++ b/net/ipv4/tcp_highspeed.c @@ -116,7 +116,7 @@ static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { /* Update AIMD parameters. diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 58469fff6c18..82f0d9ed60f5 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -236,7 +236,7 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { /* In dangerous area, increase slowly. diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index f963b274f2b0..083831e359df 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -112,7 +112,7 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked) rho_fractions = ca->rho_3ls - (ca->rho << 3); - if (tp->snd_cwnd < tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { /* * slow start * INC = 2^RHO - 1 diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index f71002e4db0b..2ab9bbb6faff 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -268,7 +268,7 @@ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; /* In slow start */ - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 728f5b3d3c64..4e4d6bcd0ca9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -109,6 +109,7 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */ #define FLAG_DATA_SACKED 0x20 /* New SACK. */ #define FLAG_ECE 0x40 /* ECE in this ACK */ +#define FLAG_LOST_RETRANS 0x80 /* This ACK marks some retransmission lost */ #define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/ #define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ @@ -196,11 +197,13 @@ static void tcp_enter_quickack_mode(struct sock *sk) * and the session is not interactive. */ -static inline bool tcp_in_quickack_mode(const struct sock *sk) +static bool tcp_in_quickack_mode(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + const struct dst_entry *dst = __sk_dst_get(sk); - return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong; + return (dst && dst_metric(dst, RTAX_QUICKACK)) || + (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong); } static void tcp_ecn_queue_cwr(struct tcp_sock *tp) @@ -1037,7 +1040,7 @@ static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack, * highest SACK block). Also calculate the lowest snd_nxt among the remaining * retransmitted skbs to avoid some costly processing per ACKs. */ -static void tcp_mark_lost_retrans(struct sock *sk) +static void tcp_mark_lost_retrans(struct sock *sk, int *flag) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -1078,7 +1081,7 @@ static void tcp_mark_lost_retrans(struct sock *sk) if (after(received_upto, ack_seq)) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; tp->retrans_out -= tcp_skb_pcount(skb); - + *flag |= FLAG_LOST_RETRANS; tcp_skb_mark_lost_uncond_verify(tp, skb); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT); } else { @@ -1818,7 +1821,7 @@ advance_sp: ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) tcp_update_reordering(sk, tp->fackets_out - state->reord, 0); - tcp_mark_lost_retrans(sk); + tcp_mark_lost_retrans(sk, &state->flag); tcp_verify_left_out(tp); out: @@ -2474,15 +2477,14 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) return false; } -/* The cwnd reduction in CWR and Recovery use the PRR algorithm - * https://datatracker.ietf.org/doc/draft-ietf-tcpm-proportional-rate-reduction/ +/* The cwnd reduction in CWR and Recovery uses the PRR algorithm in RFC 6937. * It computes the number of packets to send (sndcnt) based on packets newly * delivered: * 1) If the packets in flight is larger than ssthresh, PRR spreads the * cwnd reductions across a full RTT. - * 2) If packets in flight is lower than ssthresh (such as due to excess - * losses and/or application stalls), do not perform any further cwnd - * reductions, but instead slow start up to ssthresh. + * 2) Otherwise PRR uses packet conservation to send as much as delivered. + * But when the retransmits are acked without further losses, PRR + * slow starts cwnd up to ssthresh to speed up the recovery. */ static void tcp_init_cwnd_reduction(struct sock *sk) { @@ -2499,7 +2501,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk) } static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, - int fast_rexmit) + int fast_rexmit, int flag) { struct tcp_sock *tp = tcp_sk(sk); int sndcnt = 0; @@ -2508,16 +2510,18 @@ static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, (tp->packets_out - tp->sacked_out); tp->prr_delivered += newly_acked_sacked; - if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { + if (delta < 0) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + tp->prior_cwnd - 1; sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; - } else { + } else if ((flag & FLAG_RETRANS_DATA_ACKED) && + !(flag & FLAG_LOST_RETRANS)) { sndcnt = min_t(int, delta, max_t(int, tp->prr_delivered - tp->prr_out, newly_acked_sacked) + 1); + } else { + sndcnt = min(delta, newly_acked_sacked); } - sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0)); tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; } @@ -2578,7 +2582,7 @@ static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked) if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { tcp_try_keep_open(sk); } else { - tcp_cwnd_reduction(sk, prior_unsacked, 0); + tcp_cwnd_reduction(sk, prior_unsacked, 0, flag); } } @@ -2588,6 +2592,7 @@ static void tcp_mtup_probe_failed(struct sock *sk) icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1; icsk->icsk_mtup.probe_size = 0; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMTUPFAIL); } static void tcp_mtup_probe_success(struct sock *sk) @@ -2607,6 +2612,7 @@ static void tcp_mtup_probe_success(struct sock *sk) icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; icsk->icsk_mtup.probe_size = 0; tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS); } /* Do a simple retransmit without using the backoff mechanisms in @@ -2675,7 +2681,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) tp->prior_ssthresh = 0; tcp_init_undo(tp); - if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { + if (!tcp_in_cwnd_reduction(sk)) { if (!ece_ack) tp->prior_ssthresh = tcp_current_ssthresh(sk); tcp_init_cwnd_reduction(sk); @@ -2735,7 +2741,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) /* Undo during fast recovery after partial ACK. */ static bool tcp_try_undo_partial(struct sock *sk, const int acked, - const int prior_unsacked) + const int prior_unsacked, int flag) { struct tcp_sock *tp = tcp_sk(sk); @@ -2751,7 +2757,7 @@ static bool tcp_try_undo_partial(struct sock *sk, const int acked, * mark more packets lost or retransmit more. */ if (tp->retrans_out) { - tcp_cwnd_reduction(sk, prior_unsacked, 0); + tcp_cwnd_reduction(sk, prior_unsacked, 0, flag); return true; } @@ -2838,7 +2844,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, if (tcp_is_reno(tp) && is_dupack) tcp_add_reno_sack(sk); } else { - if (tcp_try_undo_partial(sk, acked, prior_unsacked)) + if (tcp_try_undo_partial(sk, acked, prior_unsacked, flag)) return; /* Partial ACK arrived. Force fast retransmit. */ do_lost = tcp_is_reno(tp) || @@ -2851,9 +2857,10 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, break; case TCP_CA_Loss: tcp_process_loss(sk, flag, is_dupack); - if (icsk->icsk_ca_state != TCP_CA_Open) + if (icsk->icsk_ca_state != TCP_CA_Open && + !(flag & FLAG_LOST_RETRANS)) return; - /* Fall through to processing in Open state. */ + /* Change state if cwnd is undone or retransmits are lost */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) @@ -2888,7 +2895,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, if (do_lost) tcp_update_scoreboard(sk, fast_rexmit); - tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit); + tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit, flag); tcp_xmit_retransmit_queue(sk); } @@ -3562,10 +3569,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) &sack_state); acked -= tp->packets_out; - /* Advance cwnd if state allows */ - if (tcp_may_raise_cwnd(sk, flag)) - tcp_cong_avoid(sk, ack, acked); - if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, acked, prior_unsacked, @@ -3574,6 +3577,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); + /* Advance cwnd if state allows */ + if (tcp_may_raise_cwnd(sk, flag)) + tcp_cong_avoid(sk, ack, acked); + if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) { struct dst_entry *dst = __sk_dst_get(sk); if (dst) @@ -3947,7 +3954,6 @@ void tcp_reset(struct sock *sk) static void tcp_fin(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - const struct dst_entry *dst; inet_csk_schedule_ack(sk); @@ -3959,9 +3965,7 @@ static void tcp_fin(struct sock *sk) case TCP_ESTABLISHED: /* Move to CLOSE_WAIT */ tcp_set_state(sk, TCP_CLOSE_WAIT); - dst = __sk_dst_get(sk); - if (!dst || !dst_metric(dst, RTAX_QUICKACK)) - inet_csk(sk)->icsk_ack.pingpong = 1; + inet_csk(sk)->icsk_ack.pingpong = 1; break; case TCP_CLOSE_WAIT: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d7d4c2b79cf2..486ba96ae91a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1683,8 +1683,7 @@ do_time_wait: iph->daddr, th->dest, inet_iif(skb)); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk)); - inet_twsk_put(inet_twsk(sk)); + inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; goto process; } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index a51d63a43e33..b3d64f61d922 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -461,7 +461,7 @@ void tcp_update_metrics(struct sock *sk) tcp_metric_set(tm, TCP_METRIC_CWND, tp->snd_cwnd); } - } else if (tp->snd_cwnd > tp->snd_ssthresh && + } else if (!tcp_in_slow_start(tp) && icsk->icsk_ca_state == TCP_CA_Open) { /* Cong. avoidance phase, cwnd is reliable. */ if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4bc00cb79e60..6d8795b066ac 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -147,8 +147,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, if (!th->fin || TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) { kill_with_rst: - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); return TCP_TW_RST; } @@ -198,8 +197,7 @@ kill_with_rst: */ if (sysctl_tcp_rfc1337 == 0) { kill: - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; } } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b1c218df2c85..71057849593a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -163,7 +163,6 @@ static void tcp_event_data_sent(struct tcp_sock *tp, { struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_time_stamp; - const struct dst_entry *dst = __sk_dst_get(sk); if (sysctl_tcp_slow_start_after_idle && (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto)) @@ -174,9 +173,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp, /* If it is a reply for ato after last received * packet, enter pingpong mode. */ - if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato && - (!dst || !dst_metric(dst, RTAX_QUICKACK))) - icsk->icsk_ack.pingpong = 1; + if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) + icsk->icsk_ack.pingpong = 1; } /* Account for an ACK we sent. */ diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 333bcb2415ff..bf5ea9e9bbc1 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -22,7 +22,7 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT), diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 5b752f58a900..7149ebc820c7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -649,4 +649,3 @@ void tcp_init_xmit_timers(struct sock *sk) inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); } -EXPORT_SYMBOL(tcp_init_xmit_timers); diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index a6cea1d5e20d..13951c4087d4 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -225,7 +225,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) */ diff = tp->snd_cwnd * (rtt-vegas->baseRTT) / vegas->baseRTT; - if (diff > gamma && tp->snd_cwnd <= tp->snd_ssthresh) { + if (diff > gamma && tcp_in_slow_start(tp)) { /* Going too fast. Time to slow down * and switch to congestion avoidance. */ @@ -240,7 +240,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) tp->snd_cwnd = min(tp->snd_cwnd, (u32)target_cwnd+1); tp->snd_ssthresh = tcp_vegas_ssthresh(tp); - } else if (tp->snd_cwnd <= tp->snd_ssthresh) { + } else if (tcp_in_slow_start(tp)) { /* Slow start. */ tcp_slow_start(tp, acked); } else { @@ -281,7 +281,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) vegas->minRTT = 0x7fffffff; } /* Use normal slow start */ - else if (tp->snd_cwnd <= tp->snd_ssthresh) + else if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); } diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 112151eeee45..0d094b995cd9 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -150,7 +150,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked) veno->diff = (tp->snd_cwnd << V_PARAM_SHIFT) - target_cwnd; - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { /* Slow start. */ tcp_slow_start(tp, acked); } else { diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 438a73aa777c..643f61339e7b 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -5,16 +5,15 @@ # IPv6 as module will cause a CRASH if you try to unload it menuconfig IPV6 tristate "The IPv6 protocol" - default m + default y ---help--- - This is complemental support for the IP version 6. - You will still be able to do traditional IPv4 networking as well. + Support for IP version 6 (IPv6). For general information about IPv6, see <https://en.wikipedia.org/wiki/IPv6>. - For Linux IPv6 development information, see <http://www.linux-ipv6.org>. - For specific information about IPv6 under Linux, read the HOWTO at - <http://www.bieringer.de/linux/IPv6/>. + For specific information about IPv6 under Linux, see + Documentation/networking/ipv6.txt and read the HOWTO at + <http://www.tldp.org/HOWTO/Linux+IPv6-HOWTO/> To compile this protocol support as a module, choose M here: the module will be called ipv6. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 21c2c818df3b..eb0c6a3a8a00 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -211,7 +211,8 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_ra_mtu = 1, .stable_secret = { .initialized = false, - } + }, + .use_oif_addrs_only = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -253,6 +254,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .stable_secret = { .initialized = false, }, + .use_oif_addrs_only = 0, }; /* Check if a valid qdisc is available */ @@ -1358,15 +1360,96 @@ out: return ret; } +static int __ipv6_dev_get_saddr(struct net *net, + struct ipv6_saddr_dst *dst, + struct inet6_dev *idev, + struct ipv6_saddr_score *scores, + int hiscore_idx) +{ + struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx]; + + read_lock_bh(&idev->lock); + list_for_each_entry(score->ifa, &idev->addr_list, if_list) { + int i; + + /* + * - Tentative Address (RFC2462 section 5.4) + * - A tentative address is not considered + * "assigned to an interface" in the traditional + * sense, unless it is also flagged as optimistic. + * - Candidate Source Address (section 4) + * - In any case, anycast addresses, multicast + * addresses, and the unspecified address MUST + * NOT be included in a candidate set. + */ + if ((score->ifa->flags & IFA_F_TENTATIVE) && + (!(score->ifa->flags & IFA_F_OPTIMISTIC))) + continue; + + score->addr_type = __ipv6_addr_type(&score->ifa->addr); + + if (unlikely(score->addr_type == IPV6_ADDR_ANY || + score->addr_type & IPV6_ADDR_MULTICAST)) { + net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s", + idev->dev->name); + continue; + } + + score->rule = -1; + bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX); + + for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) { + int minihiscore, miniscore; + + minihiscore = ipv6_get_saddr_eval(net, hiscore, dst, i); + miniscore = ipv6_get_saddr_eval(net, score, dst, i); + + if (minihiscore > miniscore) { + if (i == IPV6_SADDR_RULE_SCOPE && + score->scopedist > 0) { + /* + * special case: + * each remaining entry + * has too small (not enough) + * scope, because ifa entries + * are sorted by their scope + * values. + */ + goto out; + } + break; + } else if (minihiscore < miniscore) { + if (hiscore->ifa) + in6_ifa_put(hiscore->ifa); + + in6_ifa_hold(score->ifa); + + swap(hiscore, score); + hiscore_idx = 1 - hiscore_idx; + + /* restore our iterator */ + score->ifa = hiscore->ifa; + + break; + } + } + } +out: + read_unlock_bh(&idev->lock); + return hiscore_idx; +} + int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, const struct in6_addr *daddr, unsigned int prefs, struct in6_addr *saddr) { - struct ipv6_saddr_score scores[2], - *score = &scores[0], *hiscore = &scores[1]; + struct ipv6_saddr_score scores[2], *hiscore; struct ipv6_saddr_dst dst; + struct inet6_dev *idev; struct net_device *dev; int dst_type; + bool use_oif_addr = false; + int hiscore_idx = 0; dst_type = __ipv6_addr_type(daddr); dst.addr = daddr; @@ -1375,105 +1458,50 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, dst.label = ipv6_addr_label(net, daddr, dst_type, dst.ifindex); dst.prefs = prefs; - hiscore->rule = -1; - hiscore->ifa = NULL; + scores[hiscore_idx].rule = -1; + scores[hiscore_idx].ifa = NULL; rcu_read_lock(); - for_each_netdev_rcu(net, dev) { - struct inet6_dev *idev; - - /* Candidate Source Address (section 4) - * - multicast and link-local destination address, - * the set of candidate source address MUST only - * include addresses assigned to interfaces - * belonging to the same link as the outgoing - * interface. - * (- For site-local destination addresses, the - * set of candidate source addresses MUST only - * include addresses assigned to interfaces - * belonging to the same site as the outgoing - * interface.) - */ - if (((dst_type & IPV6_ADDR_MULTICAST) || - dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL) && - dst.ifindex && dev->ifindex != dst.ifindex) - continue; - - idev = __in6_dev_get(dev); - if (!idev) - continue; - - read_lock_bh(&idev->lock); - list_for_each_entry(score->ifa, &idev->addr_list, if_list) { - int i; - - /* - * - Tentative Address (RFC2462 section 5.4) - * - A tentative address is not considered - * "assigned to an interface" in the traditional - * sense, unless it is also flagged as optimistic. - * - Candidate Source Address (section 4) - * - In any case, anycast addresses, multicast - * addresses, and the unspecified address MUST - * NOT be included in a candidate set. - */ - if ((score->ifa->flags & IFA_F_TENTATIVE) && - (!(score->ifa->flags & IFA_F_OPTIMISTIC))) - continue; - - score->addr_type = __ipv6_addr_type(&score->ifa->addr); + /* Candidate Source Address (section 4) + * - multicast and link-local destination address, + * the set of candidate source address MUST only + * include addresses assigned to interfaces + * belonging to the same link as the outgoing + * interface. + * (- For site-local destination addresses, the + * set of candidate source addresses MUST only + * include addresses assigned to interfaces + * belonging to the same site as the outgoing + * interface.) + * - "It is RECOMMENDED that the candidate source addresses + * be the set of unicast addresses assigned to the + * interface that will be used to send to the destination + * (the 'outgoing' interface)." (RFC 6724) + */ + if (dst_dev) { + idev = __in6_dev_get(dst_dev); + if ((dst_type & IPV6_ADDR_MULTICAST) || + dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL || + (idev && idev->cnf.use_oif_addrs_only)) { + use_oif_addr = true; + } + } - if (unlikely(score->addr_type == IPV6_ADDR_ANY || - score->addr_type & IPV6_ADDR_MULTICAST)) { - net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s", - dev->name); + if (use_oif_addr) { + if (idev) + hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx); + } else { + for_each_netdev_rcu(net, dev) { + idev = __in6_dev_get(dev); + if (!idev) continue; - } - - score->rule = -1; - bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX); - - for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) { - int minihiscore, miniscore; - - minihiscore = ipv6_get_saddr_eval(net, hiscore, &dst, i); - miniscore = ipv6_get_saddr_eval(net, score, &dst, i); - - if (minihiscore > miniscore) { - if (i == IPV6_SADDR_RULE_SCOPE && - score->scopedist > 0) { - /* - * special case: - * each remaining entry - * has too small (not enough) - * scope, because ifa entries - * are sorted by their scope - * values. - */ - goto try_nextdev; - } - break; - } else if (minihiscore < miniscore) { - if (hiscore->ifa) - in6_ifa_put(hiscore->ifa); - - in6_ifa_hold(score->ifa); - - swap(hiscore, score); - - /* restore our iterator */ - score->ifa = hiscore->ifa; - - break; - } - } + hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx); } -try_nextdev: - read_unlock_bh(&idev->lock); } rcu_read_unlock(); + hiscore = &scores[hiscore_idx]; if (!hiscore->ifa) return -EADDRNOTAVAIL; @@ -4586,6 +4614,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu; /* we omit DEVCONF_STABLE_SECRET for now */ + array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; } static inline size_t inet6_ifla6_size(void) @@ -5585,6 +5614,14 @@ static struct addrconf_sysctl_table .proc_handler = addrconf_sysctl_stable_secret, }, { + .procname = "use_oif_addrs_only", + .data = &ipv6_devconf.use_oif_addrs_only, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + + }, + { /* sentinel */ } }, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 7de52b65173f..7bc92ea4ae8f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -342,7 +342,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!(inet->freebind || inet->transparent) && + if (!net->ipv6.sysctl.ip_nonlocal_bind && + !(inet->freebind || inet->transparent) && !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; @@ -679,8 +680,8 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct ipv6_pinfo *np = inet6_sk(sk); if (np->rxopt.all) { - if ((opt->hop && (np->rxopt.bits.hopopts || - np->rxopt.bits.ohopopts)) || + if (((opt->flags & IP6SKB_HOPBYHOP) && + (np->rxopt.bits.hopopts || np->rxopt.bits.ohopopts)) || (ip6_flowinfo((struct ipv6hdr *) skb_network_header(skb)) && np->rxopt.bits.rxflow) || (opt->srcrt && (np->rxopt.bits.srcrt || diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index b10a88986a98..2572a324b345 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -568,8 +568,8 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } /* HbH is allowed only once */ - if (np->rxopt.bits.hopopts && opt->hop) { - u8 *ptr = nh + opt->hop; + if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) { + u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr); } @@ -630,8 +630,8 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } - if (np->rxopt.bits.ohopopts && opt->hop) { - u8 *ptr = nh + opt->hop; + if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) { + u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.odstopts && opt->dst0) { diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index a7bbbe45570b..ce203b0402be 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -632,7 +632,7 @@ int ipv6_parse_hopopts(struct sk_buff *skb) return -1; } - opt->hop = sizeof(struct ipv6hdr); + opt->flags |= IP6SKB_HOPBYHOP; if (ip6_parse_tlv(tlvprochopopt_lst, skb)) { skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; opt = IP6CB(skb); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b4fd96de97e6..6ac8dad0138a 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -207,7 +207,6 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; - int twrefcnt = 0; spin_lock(lock); @@ -234,21 +233,17 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { - twrefcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); - if (twrefcnt) - inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw); - - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); } return 0; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 55d19861ab20..d715f2e0c4e7 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -32,6 +32,7 @@ #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> +#include <net/lwtunnel.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> @@ -177,6 +178,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) static void rt6_release(struct rt6_info *rt) { if (atomic_dec_and_test(&rt->rt6i_ref)) { + lwtunnel_state_put(rt->rt6i_lwtstate); rt6_free_pcpu(rt); dst_free(&rt->dst); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d5f7716662db..c5fc85286ef6 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1023,6 +1023,8 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; + if (!fl6->flowi6_oif) + fl6->flowi6_oif = dst->dev->ifindex; return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ca4700cb26c4..fdbada1569a3 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -295,7 +295,8 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; - if (!(addr_type & IPV6_ADDR_MULTICAST)) { + if (!(addr_type & IPV6_ADDR_MULTICAST) && + !sock_net(sk)->ipv6.sysctl.ip_nonlocal_bind) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6090969937f8..7f2214f8fde7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -58,6 +58,7 @@ #include <net/netevent.h> #include <net/netlink.h> #include <net/nexthop.h> +#include <net/lwtunnel.h> #include <asm/uaccess.h> @@ -1770,6 +1771,18 @@ int ip6_route_add(struct fib6_config *cfg) rt->dst.output = ip6_output; + if (cfg->fc_encap) { + struct lwtunnel_state *lwtstate; + + err = lwtunnel_build_state(dev, cfg->fc_encap_type, + cfg->fc_encap, &lwtstate); + if (err) + goto out; + lwtunnel_state_get(lwtstate); + rt->rt6i_lwtstate = lwtstate; + rt->dst.output = lwtunnel_output6; + } + ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->rt6i_dst.plen = cfg->fc_dst_len; if (rt->rt6i_dst.plen == 128) @@ -2595,6 +2608,8 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PREF] = { .type = NLA_U8 }, + [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, + [RTA_ENCAP] = { .type = NLA_NESTED }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2689,6 +2704,12 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_flags |= RTF_PREF(pref); } + if (tb[RTA_ENCAP]) + cfg->fc_encap = tb[RTA_ENCAP]; + + if (tb[RTA_ENCAP_TYPE]) + cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); + err = 0; errout: return err; @@ -2721,6 +2742,10 @@ beginning: r_cfg.fc_gateway = nla_get_in6_addr(nla); r_cfg.fc_flags |= RTF_GATEWAY; } + r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); + nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); + if (nla) + r_cfg.fc_encap_type = nla_get_u16(nla); } err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg); if (err) { @@ -2783,7 +2808,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) return ip6_route_add(&cfg); } -static inline size_t rt6_nlmsg_size(void) +static inline size_t rt6_nlmsg_size(struct rt6_info *rt) { return NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(16) /* RTA_SRC */ @@ -2797,7 +2822,8 @@ static inline size_t rt6_nlmsg_size(void) + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ - + nla_total_size(1); /* RTA_PREF */ + + nla_total_size(1) /* RTA_PREF */ + + lwtunnel_get_encap_size(rt->rt6i_lwtstate); } static int rt6_fill_node(struct net *net, @@ -2945,6 +2971,8 @@ static int rt6_fill_node(struct net *net, if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags))) goto nla_put_failure; + lwtunnel_fill_encap(skb, rt->rt6i_lwtstate); + nlmsg_end(skb, nlh); return 0; @@ -3071,7 +3099,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; - skb = nlmsg_new(rt6_nlmsg_size(), gfp_any()); + skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (!skb) goto errout; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 4e705add4f18..db48aebd9c47 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -75,6 +75,13 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_nonlocal_bind", + .data = &init_net.ipv6.sysctl.ip_nonlocal_bind, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -117,6 +124,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries; ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay; ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges; + ipv6_table[8].data = &net->ipv6.sysctl.ip_nonlocal_bind; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6748c4277aff..d540846a1a79 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1481,8 +1481,7 @@ do_time_wait: ntohs(th->dest), tcp_v6_iif(skb)); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); sk = sk2; tcp_v6_restore_cb(skb); goto process; diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig index 17bde799c854..5c467ef97311 100644 --- a/net/mpls/Kconfig +++ b/net/mpls/Kconfig @@ -24,7 +24,13 @@ config NET_MPLS_GSO config MPLS_ROUTING tristate "MPLS: routing support" - help + ---help--- Add support for forwarding of mpls packets. +config MPLS_IPTUNNEL + tristate "MPLS: IP over MPLS tunnel support" + depends on LWTUNNEL && MPLS_ROUTING + ---help--- + mpls ip tunnel support. + endif # MPLS diff --git a/net/mpls/Makefile b/net/mpls/Makefile index 65bbe68c72e6..9ca923625016 100644 --- a/net/mpls/Makefile +++ b/net/mpls/Makefile @@ -3,5 +3,6 @@ # obj-$(CONFIG_NET_MPLS_GSO) += mpls_gso.o obj-$(CONFIG_MPLS_ROUTING) += mpls_router.o +obj-$(CONFIG_MPLS_IPTUNNEL) += mpls_iptunnel.o mpls_router-y := af_mpls.o diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 1f93a5978f2a..49f1b0e41bdf 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -15,6 +15,7 @@ #include <net/ip_fib.h> #include <net/netevent.h> #include <net/netns/generic.h> +#include <net/ip6_route.h> #include "internal.h" #define LABEL_NOT_SPECIFIED (1<<20) @@ -58,10 +59,11 @@ static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) return rcu_dereference_rtnl(dev->mpls_ptr); } -static bool mpls_output_possible(const struct net_device *dev) +bool mpls_output_possible(const struct net_device *dev) { return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev); } +EXPORT_SYMBOL_GPL(mpls_output_possible); static unsigned int mpls_rt_header_size(const struct mpls_route *rt) { @@ -69,13 +71,14 @@ static unsigned int mpls_rt_header_size(const struct mpls_route *rt) return rt->rt_labels * sizeof(struct mpls_shim_hdr); } -static unsigned int mpls_dev_mtu(const struct net_device *dev) +unsigned int mpls_dev_mtu(const struct net_device *dev) { /* The amount of data the layer 2 frame can hold */ return dev->mtu; } +EXPORT_SYMBOL_GPL(mpls_dev_mtu); -static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; @@ -85,6 +88,7 @@ static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) return true; } +EXPORT_SYMBOL_GPL(mpls_pkt_too_big); static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, struct mpls_entry_decoded dec) @@ -327,6 +331,70 @@ static unsigned find_free_label(struct net *net) return LABEL_NOT_SPECIFIED; } +static struct net_device *inet_fib_lookup_dev(struct net *net, void *addr) +{ + struct net_device *dev = NULL; + struct rtable *rt; + struct in_addr daddr; + + memcpy(&daddr, addr, sizeof(struct in_addr)); + rt = ip_route_output(net, daddr.s_addr, 0, 0, 0); + if (IS_ERR(rt)) + goto errout; + + dev = rt->dst.dev; + dev_hold(dev); + + ip_rt_put(rt); + +errout: + return dev; +} + +static struct net_device *inet6_fib_lookup_dev(struct net *net, void *addr) +{ + struct net_device *dev = NULL; + struct dst_entry *dst; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + memcpy(&fl6.daddr, addr, sizeof(struct in6_addr)); + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) + goto errout; + + dev = dst->dev; + dev_hold(dev); + +errout: + dst_release(dst); + + return dev; +} + +static struct net_device *find_outdev(struct net *net, + struct mpls_route_config *cfg) +{ + struct net_device *dev = NULL; + + if (!cfg->rc_ifindex) { + switch (cfg->rc_via_table) { + case NEIGH_ARP_TABLE: + dev = inet_fib_lookup_dev(net, cfg->rc_via); + break; + case NEIGH_ND_TABLE: + dev = inet6_fib_lookup_dev(net, cfg->rc_via); + break; + case NEIGH_LINK_TABLE: + break; + } + } else { + dev = dev_get_by_index(net, cfg->rc_ifindex); + } + + return dev; +} + static int mpls_route_add(struct mpls_route_config *cfg) { struct mpls_route __rcu **platform_label; @@ -358,7 +426,7 @@ static int mpls_route_add(struct mpls_route_config *cfg) goto errout; err = -ENODEV; - dev = dev_get_by_index(net, cfg->rc_ifindex); + dev = find_outdev(net, cfg); if (!dev) goto errout; @@ -626,6 +694,7 @@ int nla_put_labels(struct sk_buff *skb, int attrtype, return 0; } +EXPORT_SYMBOL_GPL(nla_put_labels); int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, u32 label[]) @@ -671,6 +740,7 @@ int nla_get_labels(const struct nlattr *nla, *labels = nla_labels; return 0; } +EXPORT_SYMBOL_GPL(nla_get_labels); static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct mpls_route_config *cfg) diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 8cabeb5a1cb9..2681a4ba6c37 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -50,7 +50,12 @@ static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr * return result; } -int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, const u32 label[]); -int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, u32 label[]); +int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, + const u32 label[]); +int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, + u32 label[]); +bool mpls_output_possible(const struct net_device *dev); +unsigned int mpls_dev_mtu(const struct net_device *dev); +bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu); #endif /* MPLS_INTERNAL_H */ diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c new file mode 100644 index 000000000000..276f8c992218 --- /dev/null +++ b/net/mpls/mpls_iptunnel.c @@ -0,0 +1,233 @@ +/* + * mpls tunnels An implementation mpls tunnels using the light weight tunnel + * infrastructure + * + * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/net.h> +#include <linux/module.h> +#include <linux/mpls.h> +#include <linux/vmalloc.h> +#include <net/ip.h> +#include <net/dst.h> +#include <net/lwtunnel.h> +#include <net/netevent.h> +#include <net/netns/generic.h> +#include <net/ip6_fib.h> +#include <net/route.h> +#include <net/mpls_iptunnel.h> +#include <linux/mpls_iptunnel.h> +#include "internal.h" + +static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = { + [MPLS_IPTUNNEL_DST] = { .type = NLA_U32 }, +}; + +static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en) +{ + /* The size of the layer 2.5 labels to be added for this route */ + return en->labels * sizeof(struct mpls_shim_hdr); +} + +int mpls_output(struct sock *sk, struct sk_buff *skb) +{ + struct mpls_iptunnel_encap *tun_encap_info; + struct mpls_shim_hdr *hdr; + struct net_device *out_dev; + unsigned int hh_len; + unsigned int new_header_size; + unsigned int mtu; + struct dst_entry *dst = skb_dst(skb); + struct rtable *rt = NULL; + struct rt6_info *rt6 = NULL; + struct lwtunnel_state *lwtstate = NULL; + int err = 0; + bool bos; + int i; + unsigned int ttl; + + /* Obtain the ttl */ + if (skb->protocol == htons(ETH_P_IP)) { + ttl = ip_hdr(skb)->ttl; + rt = (struct rtable *)dst; + lwtstate = rt->rt_lwtstate; + } else if (skb->protocol == htons(ETH_P_IPV6)) { + ttl = ipv6_hdr(skb)->hop_limit; + rt6 = (struct rt6_info *)dst; + lwtstate = rt6->rt6i_lwtstate; + } else { + goto drop; + } + + skb_orphan(skb); + + /* Find the output device */ + out_dev = dst->dev; + if (!mpls_output_possible(out_dev) || + !lwtstate || skb_warn_if_lro(skb)) + goto drop; + + skb_forward_csum(skb); + + tun_encap_info = mpls_lwtunnel_encap(lwtstate); + + /* Verify the destination can hold the packet */ + new_header_size = mpls_encap_size(tun_encap_info); + mtu = mpls_dev_mtu(out_dev); + if (mpls_pkt_too_big(skb, mtu - new_header_size)) + goto drop; + + hh_len = LL_RESERVED_SPACE(out_dev); + if (!out_dev->header_ops) + hh_len = 0; + + /* Ensure there is enough space for the headers in the skb */ + if (skb_cow(skb, hh_len + new_header_size)) + goto drop; + + skb_push(skb, new_header_size); + skb_reset_network_header(skb); + + skb->dev = out_dev; + skb->protocol = htons(ETH_P_MPLS_UC); + + /* Push the new labels */ + hdr = mpls_hdr(skb); + bos = true; + for (i = tun_encap_info->labels - 1; i >= 0; i--) { + hdr[i] = mpls_entry_encode(tun_encap_info->label[i], + ttl, 0, bos); + bos = false; + } + + if (rt) + err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway, + skb); + else if (rt6) + err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt6->rt6i_gateway, + skb); + if (err) + net_dbg_ratelimited("%s: packet transmission failed: %d\n", + __func__, err); + + return 0; + +drop: + kfree_skb(skb); + return -EINVAL; +} + +static int mpls_build_state(struct net_device *dev, struct nlattr *nla, + struct lwtunnel_state **ts) +{ + struct mpls_iptunnel_encap *tun_encap_info; + struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1]; + struct lwtunnel_state *newts; + int tun_encap_info_len; + int ret; + + ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla, + mpls_iptunnel_policy); + if (ret < 0) + return ret; + + if (!tb[MPLS_IPTUNNEL_DST]) + return -EINVAL; + + tun_encap_info_len = sizeof(*tun_encap_info); + + newts = lwtunnel_state_alloc(tun_encap_info_len); + if (!newts) + return -ENOMEM; + + newts->len = tun_encap_info_len; + tun_encap_info = mpls_lwtunnel_encap(newts); + ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], MAX_NEW_LABELS, + &tun_encap_info->labels, tun_encap_info->label); + if (ret) + goto errout; + newts->type = LWTUNNEL_ENCAP_MPLS; + newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + + *ts = newts; + + return 0; + +errout: + kfree(newts); + *ts = NULL; + + return ret; +} + +static int mpls_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct mpls_iptunnel_encap *tun_encap_info; + + tun_encap_info = mpls_lwtunnel_encap(lwtstate); + + if (nla_put_labels(skb, MPLS_IPTUNNEL_DST, tun_encap_info->labels, + tun_encap_info->label)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + struct mpls_iptunnel_encap *tun_encap_info; + + tun_encap_info = mpls_lwtunnel_encap(lwtstate); + + return nla_total_size(tun_encap_info->labels * 4); +} + +static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + struct mpls_iptunnel_encap *a_hdr = mpls_lwtunnel_encap(a); + struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b); + int l; + + if (a_hdr->labels != b_hdr->labels) + return 1; + + for (l = 0; l < MAX_NEW_LABELS; l++) + if (a_hdr->label[l] != b_hdr->label[l]) + return 1; + return 0; +} + +static const struct lwtunnel_encap_ops mpls_iptun_ops = { + .build_state = mpls_build_state, + .output = mpls_output, + .fill_encap = mpls_fill_encap_info, + .get_encap_size = mpls_encap_nlsize, + .cmp_encap = mpls_encap_cmp, +}; + +static int __init mpls_iptunnel_init(void) +{ + return lwtunnel_encap_add_ops(&mpls_iptun_ops, LWTUNNEL_ENCAP_MPLS); +} +module_init(mpls_iptunnel_init); + +static void __exit mpls_iptunnel_exit(void) +{ + lwtunnel_encap_del_ops(&mpls_iptun_ops, LWTUNNEL_ENCAP_MPLS); +} +module_exit(mpls_iptunnel_exit); + +MODULE_DESCRIPTION("MultiProtocol Label Switching IP Tunnels"); +MODULE_LICENSE("GPL v2"); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 52561e1c31e2..cb2f13ebb5a6 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -166,11 +166,13 @@ void nft_meta_get_eval(const struct nft_expr *expr, goto err; *dest = out->group; break; +#ifdef CONFIG_CGROUP_NET_CLASSID case NFT_META_CGROUP: if (skb->sk == NULL || !sk_fullsock(skb->sk)) goto err; *dest = skb->sk->sk_classid; break; +#endif default: WARN_ON(1); goto err; @@ -246,7 +248,9 @@ int nft_meta_get_init(const struct nft_ctx *ctx, case NFT_META_CPU: case NFT_META_IIFGROUP: case NFT_META_OIFGROUP: +#ifdef CONFIG_CGROUP_NET_CLASSID case NFT_META_CGROUP: +#endif len = sizeof(u32); break; case NFT_META_IIFNAME: diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index cca96cec1b68..d0c96c5ae29a 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -272,8 +272,7 @@ tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport, hp->source, lport ? lport : hp->dest, skb->dev, NFT_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk)); - inet_twsk_put(inet_twsk(sk)); + inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; } } @@ -437,8 +436,7 @@ tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, tgi->lport ? tgi->lport : hp->dest, skb->dev, NFT_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk)); - inet_twsk_put(inet_twsk(sk)); + inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; } } diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 15840401a2ce..1119f46b80b4 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -44,18 +44,6 @@ config OPENVSWITCH_GRE If unsure, say Y. -config OPENVSWITCH_VXLAN - tristate "Open vSwitch VXLAN tunneling support" - depends on OPENVSWITCH - depends on VXLAN - default OPENVSWITCH - ---help--- - If you say Y here, then the Open vSwitch will be able create vxlan vport. - - Say N to exclude this support and reduce the binary size. - - If unsure, say Y. - config OPENVSWITCH_GENEVE tristate "Open vSwitch Geneve tunneling support" depends on OPENVSWITCH diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile index 91b9478413ef..38e0e149c55e 100644 --- a/net/openvswitch/Makefile +++ b/net/openvswitch/Makefile @@ -16,5 +16,4 @@ openvswitch-y := \ vport-netdev.o obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o -obj-$(CONFIG_OPENVSWITCH_VXLAN) += vport-vxlan.o obj-$(CONFIG_OPENVSWITCH_GRE) += vport-gre.o diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 8a8c0b8b4f63..cf04c2f8b32a 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -611,7 +611,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, const struct nlattr *actions, int actions_len) { - struct ovs_tunnel_info info; + struct ip_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; @@ -733,7 +733,15 @@ static int execute_set_action(struct sk_buff *skb, { /* Only tunnel set execution is supported without a mask. */ if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) { - OVS_CB(skb)->egress_tun_info = nla_data(a); + struct ovs_tunnel_info *tun = nla_data(a); + + skb_dst_drop(skb); + dst_hold((struct dst_entry *)tun->tun_dst); + skb_dst_set(skb, (struct dst_entry *)tun->tun_dst); + + /* FIXME: Remove when all vports have been converted */ + OVS_CB(skb)->egress_tun_info = &tun->tun_dst->u.tun_info; + return 0; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index ff8c4a4c1609..ffe984f5b95c 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -176,7 +176,7 @@ static inline struct datapath *get_dp(struct net *net, int dp_ifindex) const char *ovs_dp_name(const struct datapath *dp) { struct vport *vport = ovs_vport_ovsl_rcu(dp, OVSP_LOCAL); - return vport->ops->get_name(vport); + return ovs_vport_name(vport); } static int get_dpifindex(const struct datapath *dp) @@ -188,7 +188,7 @@ static int get_dpifindex(const struct datapath *dp) local = ovs_vport_rcu(dp, OVSP_LOCAL); if (local) - ifindex = netdev_vport_priv(local)->dev->ifindex; + ifindex = local->dev->ifindex; else ifindex = 0; @@ -1018,7 +1018,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) } ovs_unlock(); - ovs_nla_free_flow_actions(old_acts); + ovs_nla_free_flow_actions_rcu(old_acts); ovs_flow_free(new_flow, false); } @@ -1030,7 +1030,7 @@ err_unlock_ovs: ovs_unlock(); kfree_skb(reply); err_kfree_acts: - kfree(acts); + ovs_nla_free_flow_actions(acts); err_kfree_flow: ovs_flow_free(new_flow, false); error: @@ -1157,7 +1157,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) if (reply) ovs_notify(&dp_flow_genl_family, reply, info); if (old_acts) - ovs_nla_free_flow_actions(old_acts); + ovs_nla_free_flow_actions_rcu(old_acts); return 0; @@ -1165,7 +1165,7 @@ err_unlock_ovs: ovs_unlock(); kfree_skb(reply); err_kfree_acts: - kfree(acts); + ovs_nla_free_flow_actions(acts); error: return error; } @@ -1800,7 +1800,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) || nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) || nla_put_string(skb, OVS_VPORT_ATTR_NAME, - vport->ops->get_name(vport))) + ovs_vport_name(vport))) goto nla_put_failure; ovs_vport_get_stats(vport, &vport_stats); @@ -2219,13 +2219,10 @@ static void __net_exit list_vports_from_net(struct net *net, struct net *dnet, struct vport *vport; hlist_for_each_entry(vport, &dp->ports[i], dp_hash_node) { - struct netdev_vport *netdev_vport; - if (vport->ops->type != OVS_VPORT_TYPE_INTERNAL) continue; - netdev_vport = netdev_vport_priv(vport); - if (dev_net(netdev_vport->dev) == dnet) + if (dev_net(vport->dev) == dnet) list_add(&vport->detach_list, head); } } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index cd691e935e08..6b28c5cedb23 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -25,6 +25,7 @@ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/u64_stats_sync.h> +#include <net/ip_tunnels.h> #include "flow.h" #include "flow_table.h" @@ -98,7 +99,7 @@ struct datapath { * when a packet is received by OVS. */ struct ovs_skb_cb { - struct ovs_tunnel_info *egress_tun_info; + struct ip_tunnel_info *egress_tun_info; struct vport *input_vport; }; #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb) @@ -114,7 +115,7 @@ struct ovs_skb_cb { * @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY. */ struct dp_upcall_info { - const struct ovs_tunnel_info *egress_tun_info; + const struct ip_tunnel_info *egress_tun_info; const struct nlattr *userdata; const struct nlattr *actions; int actions_len; diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index 2c631fe76be1..a7a80a6b77b0 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -58,13 +58,10 @@ void ovs_dp_notify_wq(struct work_struct *work) struct hlist_node *n; hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) { - struct netdev_vport *netdev_vport; - if (vport->ops->type != OVS_VPORT_TYPE_NETDEV) continue; - netdev_vport = netdev_vport_priv(vport); - if (!(netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH)) + if (!(vport->dev->priv_flags & IFF_OVS_DATAPATH)) dp_detach_port_notify(vport); } } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index bc7b0aba994a..8db22ef73626 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -682,12 +682,12 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key) return key_extract(skb, key); } -int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info, +int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key) { /* Extract metadata from packet. */ if (tun_info) { - memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key)); + memcpy(&key->tun_key, &tun_info->key, sizeof(key->tun_key)); if (tun_info->options) { BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) * diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index a076e445ccc2..b62cdb3e3589 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -32,31 +32,11 @@ #include <linux/time.h> #include <linux/flex_array.h> #include <net/inet_ecn.h> +#include <net/ip_tunnels.h> +#include <net/dst_metadata.h> struct sk_buff; -/* Used to memset ovs_key_ipv4_tunnel padding. */ -#define OVS_TUNNEL_KEY_SIZE \ - (offsetof(struct ovs_key_ipv4_tunnel, tp_dst) + \ - FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, tp_dst)) - -struct ovs_key_ipv4_tunnel { - __be64 tun_id; - __be32 ipv4_src; - __be32 ipv4_dst; - __be16 tun_flags; - u8 ipv4_tos; - u8 ipv4_ttl; - __be16 tp_src; - __be16 tp_dst; -} __packed __aligned(4); /* Minimize padding. */ - -struct ovs_tunnel_info { - struct ovs_key_ipv4_tunnel tunnel; - const void *options; - u8 options_len; -}; - /* Store options at the end of the array if they are less than the * maximum size. This allows us to get the benefits of variable length * matching for small options. @@ -66,54 +46,9 @@ struct ovs_tunnel_info { #define TUN_METADATA_OPTS(flow_key, opt_len) \ ((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len))) -static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, - __be32 saddr, __be32 daddr, - u8 tos, u8 ttl, - __be16 tp_src, - __be16 tp_dst, - __be64 tun_id, - __be16 tun_flags, - const void *opts, - u8 opts_len) -{ - tun_info->tunnel.tun_id = tun_id; - tun_info->tunnel.ipv4_src = saddr; - tun_info->tunnel.ipv4_dst = daddr; - tun_info->tunnel.ipv4_tos = tos; - tun_info->tunnel.ipv4_ttl = ttl; - tun_info->tunnel.tun_flags = tun_flags; - - /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of - * the upper tunnel are used. - * E.g: GRE over IPSEC, the tp_src and tp_port are zero. - */ - tun_info->tunnel.tp_src = tp_src; - tun_info->tunnel.tp_dst = tp_dst; - - /* Clear struct padding. */ - if (sizeof(tun_info->tunnel) != OVS_TUNNEL_KEY_SIZE) - memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, - 0, sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE); - - tun_info->options = opts; - tun_info->options_len = opts_len; -} - -static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, - const struct iphdr *iph, - __be16 tp_src, - __be16 tp_dst, - __be64 tun_id, - __be16 tun_flags, - const void *opts, - u8 opts_len) -{ - __ovs_flow_tun_info_init(tun_info, iph->saddr, iph->daddr, - iph->tos, iph->ttl, - tp_src, tp_dst, - tun_id, tun_flags, - opts, opts_len); -} +struct ovs_tunnel_info { + struct metadata_dst *tun_dst; +}; #define OVS_SW_FLOW_KEY_METADATA_SIZE \ (offsetof(struct sw_flow_key, recirc_id) + \ @@ -122,7 +57,7 @@ static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, struct sw_flow_key { u8 tun_opts[255]; u8 tun_opts_len; - struct ovs_key_ipv4_tunnel tun_key; /* Encapsulating tunnel key. */ + struct ip_tunnel_key tun_key; /* Encapsulating tunnel key. */ struct { u32 priority; /* Packet QoS priority. */ u32 skb_mark; /* SKB mark. */ @@ -273,7 +208,7 @@ void ovs_flow_stats_clear(struct sw_flow *); u64 ovs_flow_used_time(unsigned long flow_jiffies); int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key); -int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info, +int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key); /* Extract key from packet coming from userspace. */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 624e41c4267f..a6eb77ab1a64 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -47,9 +47,9 @@ #include <net/ipv6.h> #include <net/ndisc.h> #include <net/mpls.h> +#include <net/vxlan.h> #include "flow_netlink.h" -#include "vport-vxlan.h" struct ovs_len_tbl { int len; @@ -475,7 +475,7 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *a, { struct nlattr *tb[OVS_VXLAN_EXT_MAX+1]; unsigned long opt_key_offset; - struct ovs_vxlan_opts opts; + struct vxlan_metadata opts; int err; BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); @@ -626,7 +626,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, static int vxlan_opt_to_nlattr(struct sk_buff *skb, const void *tun_opts, int swkey_tun_opts_len) { - const struct ovs_vxlan_opts *opts = tun_opts; + const struct vxlan_metadata *opts = tun_opts; struct nlattr *nla; nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS); @@ -641,7 +641,7 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb, } static int __ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ovs_key_ipv4_tunnel *output, + const struct ip_tunnel_key *output, const void *tun_opts, int swkey_tun_opts_len) { if (output->tun_flags & TUNNEL_KEY && @@ -689,7 +689,7 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, } static int ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ovs_key_ipv4_tunnel *output, + const struct ip_tunnel_key *output, const void *tun_opts, int swkey_tun_opts_len) { struct nlattr *nla; @@ -708,9 +708,9 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, } int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb, - const struct ovs_tunnel_info *egress_tun_info) + const struct ip_tunnel_info *egress_tun_info) { - return __ipv4_tun_to_nlattr(skb, &egress_tun_info->tunnel, + return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key, egress_tun_info->options, egress_tun_info->options_len); } @@ -1548,11 +1548,48 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log) return sfa; } +static void ovs_nla_free_set_action(const struct nlattr *a) +{ + const struct nlattr *ovs_key = nla_data(a); + struct ovs_tunnel_info *ovs_tun; + + switch (nla_type(ovs_key)) { + case OVS_KEY_ATTR_TUNNEL_INFO: + ovs_tun = nla_data(ovs_key); + dst_release((struct dst_entry *)ovs_tun->tun_dst); + break; + } +} + +void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +{ + const struct nlattr *a; + int rem; + + if (!sf_acts) + return; + + nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) { + switch (nla_type(a)) { + case OVS_ACTION_ATTR_SET: + ovs_nla_free_set_action(a); + break; + } + } + + kfree(sf_acts); +} + +static void __ovs_nla_free_flow_actions(struct rcu_head *head) +{ + ovs_nla_free_flow_actions(container_of(head, struct sw_flow_actions, rcu)); +} + /* Schedules 'sf_acts' to be freed after the next RCU grace period. * The caller must hold rcu_read_lock for this to be sensible. */ -void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *sf_acts) { - kfree_rcu(sf_acts, rcu); + call_rcu(&sf_acts->rcu, __ovs_nla_free_flow_actions); } static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, @@ -1746,7 +1783,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, { struct sw_flow_match match; struct sw_flow_key key; - struct ovs_tunnel_info *tun_info; + struct metadata_dst *tun_dst; + struct ip_tunnel_info *tun_info; + struct ovs_tunnel_info *ovs_tun; struct nlattr *a; int err = 0, start, opts_type; @@ -1771,13 +1810,23 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, if (start < 0) return start; + tun_dst = metadata_dst_alloc(key.tun_opts_len, GFP_KERNEL); + if (!tun_dst) + return -ENOMEM; + a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL, - sizeof(*tun_info) + key.tun_opts_len, log); - if (IS_ERR(a)) + sizeof(*ovs_tun), log); + if (IS_ERR(a)) { + dst_release((struct dst_entry *)tun_dst); return PTR_ERR(a); + } + + ovs_tun = nla_data(a); + ovs_tun->tun_dst = tun_dst; - tun_info = nla_data(a); - tun_info->tunnel = key.tun_key; + tun_info = &tun_dst->u.tun_info; + tun_info->mode = IP_TUNNEL_INFO_TX; + tun_info->key = key.tun_key; tun_info->options_len = key.tun_opts_len; if (tun_info->options_len) { @@ -2177,7 +2226,7 @@ int ovs_nla_copy_actions(const struct nlattr *attr, err = __ovs_nla_copy_actions(attr, key, 0, sfa, key->eth.type, key->eth.tci, log); if (err) - kfree(*sfa); + ovs_nla_free_flow_actions(*sfa); return err; } @@ -2227,13 +2276,14 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) switch (key_type) { case OVS_KEY_ATTR_TUNNEL_INFO: { - struct ovs_tunnel_info *tun_info = nla_data(ovs_key); + struct ovs_tunnel_info *ovs_tun = nla_data(ovs_key); + struct ip_tunnel_info *tun_info = &ovs_tun->tun_dst->u.tun_info; start = nla_nest_start(skb, OVS_ACTION_ATTR_SET); if (!start) return -EMSGSIZE; - err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel, + err = ipv4_tun_to_nlattr(skb, &tun_info->key, tun_info->options_len ? tun_info->options : NULL, tun_info->options_len); diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 5c3d75bff310..acd074408f0a 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -55,7 +55,7 @@ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key, const struct nlattr *mask, bool log); int ovs_nla_put_egress_tunnel_key(struct sk_buff *, - const struct ovs_tunnel_info *); + const struct ip_tunnel_info *); bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log); int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid, @@ -69,5 +69,6 @@ int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb); void ovs_nla_free_flow_actions(struct sw_flow_actions *); +void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *); #endif /* flow_netlink.h */ diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 65523948fb95..3a9d1dde76ed 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -18,6 +18,7 @@ #include "flow.h" #include "datapath.h" +#include "flow_netlink.h" #include <linux/uaccess.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> @@ -143,7 +144,8 @@ static void flow_free(struct sw_flow *flow) if (ovs_identifier_is_key(&flow->id)) kfree(flow->id.unmasked_key); - kfree((struct sw_flow_actions __force *)flow->sf_acts); + if (flow->sf_acts) + ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts); for_each_node(node) if (flow->stats[node]) kmem_cache_free(flow_stats_cache, diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 208c576bd1b6..1da3a14d1010 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -77,7 +77,7 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb) struct vport *vport = gs->rcv_data; struct genevehdr *geneveh = geneve_hdr(skb); int opts_len; - struct ovs_tunnel_info tun_info; + struct ip_tunnel_info tun_info; __be64 key; __be16 flags; @@ -90,10 +90,9 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb) key = vni_to_tunnel_id(geneveh->vni); - ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), - udp_hdr(skb)->source, udp_hdr(skb)->dest, - key, flags, - geneveh->options, opts_len); + ip_tunnel_info_init(&tun_info, ip_hdr(skb), + udp_hdr(skb)->source, udp_hdr(skb)->dest, + key, flags, geneveh->options, opts_len); ovs_vport_receive(vport, skb, &tun_info); } @@ -165,8 +164,8 @@ error: static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) { - const struct ovs_key_ipv4_tunnel *tun_key; - struct ovs_tunnel_info *tun_info; + const struct ip_tunnel_key *tun_key; + struct ip_tunnel_info *tun_info; struct net *net = ovs_dp_get_net(vport->dp); struct geneve_port *geneve_port = geneve_vport(vport); __be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport; @@ -183,7 +182,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) goto error; } - tun_key = &tun_info->tunnel; + tun_key = &tun_info->key; rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP); if (IS_ERR(rt)) { err = PTR_ERR(rt); @@ -225,7 +224,7 @@ static const char *geneve_get_name(const struct vport *vport) } static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *egress_tun_info) + struct ip_tunnel_info *egress_tun_info) { struct geneve_port *geneve_port = geneve_vport(vport); struct net *net = ovs_dp_get_net(vport->dp); diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index f17ac9642f4e..b87656c66aaf 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -67,9 +67,9 @@ static struct sk_buff *__build_header(struct sk_buff *skb, int tunnel_hlen) { struct tnl_ptk_info tpi; - const struct ovs_key_ipv4_tunnel *tun_key; + const struct ip_tunnel_key *tun_key; - tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; + tun_key = &OVS_CB(skb)->egress_tun_info->key; skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM)); if (IS_ERR(skb)) @@ -97,7 +97,7 @@ static __be64 key_to_tunnel_id(__be32 key, __be32 seq) static int gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) { - struct ovs_tunnel_info tun_info; + struct ip_tunnel_info tun_info; struct ovs_net *ovs_net; struct vport *vport; __be64 key; @@ -108,8 +108,8 @@ static int gre_rcv(struct sk_buff *skb, return PACKET_REJECT; key = key_to_tunnel_id(tpi->key, tpi->seq); - ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), 0, 0, key, - filter_tnl_flags(tpi->flags), NULL, 0); + ip_tunnel_info_init(&tun_info, ip_hdr(skb), 0, 0, key, + filter_tnl_flags(tpi->flags), NULL, 0); ovs_vport_receive(vport, skb, &tun_info); return PACKET_RCVD; @@ -134,7 +134,7 @@ static int gre_err(struct sk_buff *skb, u32 info, static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) { struct net *net = ovs_dp_get_net(vport->dp); - const struct ovs_key_ipv4_tunnel *tun_key; + const struct ip_tunnel_key *tun_key; struct flowi4 fl; struct rtable *rt; int min_headroom; @@ -147,7 +147,7 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) goto err_free_skb; } - tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; + tun_key = &OVS_CB(skb)->egress_tun_info->key; rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_GRE); if (IS_ERR(rt)) { err = PTR_ERR(rt); @@ -277,7 +277,7 @@ static void gre_tnl_destroy(struct vport *vport) } static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *egress_tun_info) + struct ip_tunnel_info *egress_tun_info) { return ovs_tunnel_get_egress_info(egress_tun_info, ovs_dp_get_net(vport->dp), diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 6a55f7105505..c058bbf876c3 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -156,49 +156,44 @@ static void do_setup(struct net_device *netdev) static struct vport *internal_dev_create(const struct vport_parms *parms) { struct vport *vport; - struct netdev_vport *netdev_vport; struct internal_dev *internal_dev; int err; - vport = ovs_vport_alloc(sizeof(struct netdev_vport), - &ovs_internal_vport_ops, parms); + vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms); if (IS_ERR(vport)) { err = PTR_ERR(vport); goto error; } - netdev_vport = netdev_vport_priv(vport); - - netdev_vport->dev = alloc_netdev(sizeof(struct internal_dev), - parms->name, NET_NAME_UNKNOWN, - do_setup); - if (!netdev_vport->dev) { + vport->dev = alloc_netdev(sizeof(struct internal_dev), + parms->name, NET_NAME_UNKNOWN, do_setup); + if (!vport->dev) { err = -ENOMEM; goto error_free_vport; } - dev_net_set(netdev_vport->dev, ovs_dp_get_net(vport->dp)); - internal_dev = internal_dev_priv(netdev_vport->dev); + dev_net_set(vport->dev, ovs_dp_get_net(vport->dp)); + internal_dev = internal_dev_priv(vport->dev); internal_dev->vport = vport; /* Restrict bridge port to current netns. */ if (vport->port_no == OVSP_LOCAL) - netdev_vport->dev->features |= NETIF_F_NETNS_LOCAL; + vport->dev->features |= NETIF_F_NETNS_LOCAL; rtnl_lock(); - err = register_netdevice(netdev_vport->dev); + err = register_netdevice(vport->dev); if (err) goto error_free_netdev; - dev_set_promiscuity(netdev_vport->dev, 1); + dev_set_promiscuity(vport->dev, 1); rtnl_unlock(); - netif_start_queue(netdev_vport->dev); + netif_start_queue(vport->dev); return vport; error_free_netdev: rtnl_unlock(); - free_netdev(netdev_vport->dev); + free_netdev(vport->dev); error_free_vport: ovs_vport_free(vport); error: @@ -207,21 +202,19 @@ error: static void internal_dev_destroy(struct vport *vport) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - - netif_stop_queue(netdev_vport->dev); + netif_stop_queue(vport->dev); rtnl_lock(); - dev_set_promiscuity(netdev_vport->dev, -1); + dev_set_promiscuity(vport->dev, -1); /* unregister_netdevice() waits for an RCU grace period. */ - unregister_netdevice(netdev_vport->dev); + unregister_netdevice(vport->dev); rtnl_unlock(); } static int internal_dev_recv(struct vport *vport, struct sk_buff *skb) { - struct net_device *netdev = netdev_vport_priv(vport)->dev; + struct net_device *netdev = vport->dev; int len; if (unlikely(!(netdev->flags & IFF_UP))) { @@ -249,7 +242,6 @@ static struct vport_ops ovs_internal_vport_ops = { .type = OVS_VPORT_TYPE_INTERNAL, .create = internal_dev_create, .destroy = internal_dev_destroy, - .get_name = ovs_netdev_get_name, .send = internal_dev_recv, }; diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 33e6d6e2908f..68d0582fc001 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -27,9 +27,13 @@ #include <linux/skbuff.h> #include <linux/openvswitch.h> -#include <net/llc.h> +#include <net/udp.h> +#include <net/ip_tunnels.h> +#include <net/rtnetlink.h> +#include <net/vxlan.h> #include "datapath.h" +#include "vport.h" #include "vport-internal_dev.h" #include "vport-netdev.h" @@ -83,104 +87,93 @@ static struct net_device *get_dpdev(const struct datapath *dp) local = ovs_vport_ovsl(dp, OVSP_LOCAL); BUG_ON(!local); - return netdev_vport_priv(local)->dev; + return local->dev; } -static struct vport *netdev_create(const struct vport_parms *parms) +static struct vport *netdev_link(struct vport *vport, const char *name) { - struct vport *vport; - struct netdev_vport *netdev_vport; int err; - vport = ovs_vport_alloc(sizeof(struct netdev_vport), - &ovs_netdev_vport_ops, parms); - if (IS_ERR(vport)) { - err = PTR_ERR(vport); - goto error; - } - - netdev_vport = netdev_vport_priv(vport); - - netdev_vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), parms->name); - if (!netdev_vport->dev) { + vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), name); + if (!vport->dev) { err = -ENODEV; goto error_free_vport; } - if (netdev_vport->dev->flags & IFF_LOOPBACK || - netdev_vport->dev->type != ARPHRD_ETHER || - ovs_is_internal_dev(netdev_vport->dev)) { + if (vport->dev->flags & IFF_LOOPBACK || + vport->dev->type != ARPHRD_ETHER || + ovs_is_internal_dev(vport->dev)) { err = -EINVAL; goto error_put; } rtnl_lock(); - err = netdev_master_upper_dev_link(netdev_vport->dev, + err = netdev_master_upper_dev_link(vport->dev, get_dpdev(vport->dp)); if (err) goto error_unlock; - err = netdev_rx_handler_register(netdev_vport->dev, netdev_frame_hook, + err = netdev_rx_handler_register(vport->dev, netdev_frame_hook, vport); if (err) goto error_master_upper_dev_unlink; - dev_disable_lro(netdev_vport->dev); - dev_set_promiscuity(netdev_vport->dev, 1); - netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH; + dev_disable_lro(vport->dev); + dev_set_promiscuity(vport->dev, 1); + vport->dev->priv_flags |= IFF_OVS_DATAPATH; rtnl_unlock(); return vport; error_master_upper_dev_unlink: - netdev_upper_dev_unlink(netdev_vport->dev, get_dpdev(vport->dp)); + netdev_upper_dev_unlink(vport->dev, get_dpdev(vport->dp)); error_unlock: rtnl_unlock(); error_put: - dev_put(netdev_vport->dev); + dev_put(vport->dev); error_free_vport: ovs_vport_free(vport); -error: return ERR_PTR(err); } +static struct vport *netdev_create(const struct vport_parms *parms) +{ + struct vport *vport; + + vport = ovs_vport_alloc(0, &ovs_netdev_vport_ops, parms); + if (IS_ERR(vport)) + return vport; + + return netdev_link(vport, parms->name); +} + static void free_port_rcu(struct rcu_head *rcu) { - struct netdev_vport *netdev_vport = container_of(rcu, - struct netdev_vport, rcu); + struct vport *vport = container_of(rcu, struct vport, rcu); - dev_put(netdev_vport->dev); - ovs_vport_free(vport_from_priv(netdev_vport)); + if (vport->dev) + dev_put(vport->dev); + ovs_vport_free(vport); } void ovs_netdev_detach_dev(struct vport *vport) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - ASSERT_RTNL(); - netdev_vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; - netdev_rx_handler_unregister(netdev_vport->dev); - netdev_upper_dev_unlink(netdev_vport->dev, - netdev_master_upper_dev_get(netdev_vport->dev)); - dev_set_promiscuity(netdev_vport->dev, -1); + vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; + netdev_rx_handler_unregister(vport->dev); + netdev_upper_dev_unlink(vport->dev, + netdev_master_upper_dev_get(vport->dev)); + dev_set_promiscuity(vport->dev, -1); } static void netdev_destroy(struct vport *vport) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - rtnl_lock(); - if (netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH) + if (vport->dev->priv_flags & IFF_OVS_DATAPATH) ovs_netdev_detach_dev(vport); rtnl_unlock(); - call_rcu(&netdev_vport->rcu, free_port_rcu); -} - -const char *ovs_netdev_get_name(const struct vport *vport) -{ - const struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - return netdev_vport->dev->name; + call_rcu(&vport->rcu, free_port_rcu); } static unsigned int packet_length(const struct sk_buff *skb) @@ -195,18 +188,17 @@ static unsigned int packet_length(const struct sk_buff *skb) static int netdev_send(struct vport *vport, struct sk_buff *skb) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - int mtu = netdev_vport->dev->mtu; + int mtu = vport->dev->mtu; int len; if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) { net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n", - netdev_vport->dev->name, + vport->dev->name, packet_length(skb), mtu); goto drop; } - skb->dev = netdev_vport->dev; + skb->dev = vport->dev; len = skb->len; dev_queue_xmit(skb); @@ -231,16 +223,205 @@ static struct vport_ops ovs_netdev_vport_ops = { .type = OVS_VPORT_TYPE_NETDEV, .create = netdev_create, .destroy = netdev_destroy, - .get_name = ovs_netdev_get_name, .send = netdev_send, }; +/* Compat code for old userspace. */ +#if IS_ENABLED(CONFIG_VXLAN) +static struct vport_ops ovs_vxlan_netdev_vport_ops; + +static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) +{ + struct vxlan_dev *vxlan = netdev_priv(vport->dev); + __be16 dst_port = vxlan->cfg.dst_port; + + if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port))) + return -EMSGSIZE; + + if (vxlan->flags & VXLAN_F_GBP) { + struct nlattr *exts; + + exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION); + if (!exts) + return -EMSGSIZE; + + if (vxlan->flags & VXLAN_F_GBP && + nla_put_flag(skb, OVS_VXLAN_EXT_GBP)) + return -EMSGSIZE; + + nla_nest_end(skb, exts); + } + + return 0; +} + +static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX + 1] = { + [OVS_VXLAN_EXT_GBP] = { .type = NLA_FLAG, }, +}; + +static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr, + struct vxlan_config *conf) +{ + struct nlattr *exts[OVS_VXLAN_EXT_MAX + 1]; + int err; + + if (nla_len(attr) < sizeof(struct nlattr)) + return -EINVAL; + + err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy); + if (err < 0) + return err; + + if (exts[OVS_VXLAN_EXT_GBP]) + conf->flags |= VXLAN_F_GBP; + + return 0; +} + +static struct vport *vxlan_tnl_create(const struct vport_parms *parms) +{ + struct net *net = ovs_dp_get_net(parms->dp); + struct nlattr *options = parms->options; + struct net_device *dev; + struct vport *vport; + struct nlattr *a; + int err; + struct vxlan_config conf = { + .no_share = true, + .flags = VXLAN_F_FLOW_BASED | VXLAN_F_COLLECT_METADATA, + }; + + if (!options) { + err = -EINVAL; + goto error; + } + + a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT); + if (a && nla_len(a) == sizeof(u16)) { + conf.dst_port = htons(nla_get_u16(a)); + } else { + /* Require destination port from userspace. */ + err = -EINVAL; + goto error; + } + + vport = ovs_vport_alloc(0, &ovs_vxlan_netdev_vport_ops, parms); + if (IS_ERR(vport)) + return vport; + + a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION); + if (a) { + err = vxlan_configure_exts(vport, a, &conf); + if (err) { + ovs_vport_free(vport); + goto error; + } + } + + rtnl_lock(); + dev = vxlan_dev_create(net, parms->name, NET_NAME_USER, &conf); + if (IS_ERR(dev)) { + rtnl_unlock(); + ovs_vport_free(vport); + return ERR_CAST(dev); + } + + dev_change_flags(dev, dev->flags | IFF_UP); + rtnl_unlock(); + return vport; +error: + return ERR_PTR(err); +} + +static struct vport *vxlan_create(const struct vport_parms *parms) +{ + struct vport *vport; + + vport = vxlan_tnl_create(parms); + if (IS_ERR(vport)) + return vport; + + return netdev_link(vport, parms->name); +} + +static void vxlan_destroy(struct vport *vport) +{ + rtnl_lock(); + if (vport->dev->priv_flags & IFF_OVS_DATAPATH) + ovs_netdev_detach_dev(vport); + + /* Early release so we can unregister the device */ + dev_put(vport->dev); + rtnl_delete_link(vport->dev); + vport->dev = NULL; + rtnl_unlock(); + + call_rcu(&vport->rcu, free_port_rcu); +} + +static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, + struct ip_tunnel_info *egress_tun_info) +{ + struct vxlan_dev *vxlan = netdev_priv(vport->dev); + struct net *net = ovs_dp_get_net(vport->dp); + __be16 dst_port = vxlan_dev_dst_port(vxlan); + __be16 src_port; + int port_min; + int port_max; + + inet_get_local_port_range(net, &port_min, &port_max); + src_port = udp_flow_src_port(net, skb, 0, 0, true); + + return ovs_tunnel_get_egress_info(egress_tun_info, net, + OVS_CB(skb)->egress_tun_info, + IPPROTO_UDP, skb->mark, + src_port, dst_port); +} + +static struct vport_ops ovs_vxlan_netdev_vport_ops = { + .type = OVS_VPORT_TYPE_VXLAN, + .create = vxlan_create, + .destroy = vxlan_destroy, + .get_options = vxlan_get_options, + .send = netdev_send, + .get_egress_tun_info = vxlan_get_egress_tun_info, +}; + +static int vxlan_compat_init(void) +{ + return ovs_vport_ops_register(&ovs_vxlan_netdev_vport_ops); +} + +static void vxlan_compat_exit(void) +{ + ovs_vport_ops_unregister(&ovs_vxlan_netdev_vport_ops); +} +#else +static int vxlan_compat_init(void) +{ + return 0; +} + +static void vxlan_compat_exit(void) +{ +} +#endif + int __init ovs_netdev_init(void) { - return ovs_vport_ops_register(&ovs_netdev_vport_ops); + int err; + + err = ovs_vport_ops_register(&ovs_netdev_vport_ops); + if (err) + return err; + err = vxlan_compat_init(); + if (err) + vxlan_compat_exit(); + return err; } void ovs_netdev_exit(void) { ovs_vport_ops_unregister(&ovs_netdev_vport_ops); + vxlan_compat_exit(); } diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index 6f7038e79c52..684fb88723a4 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -26,19 +26,6 @@ struct vport *ovs_netdev_get_vport(struct net_device *dev); -struct netdev_vport { - struct rcu_head rcu; - - struct net_device *dev; -}; - -static inline struct netdev_vport * -netdev_vport_priv(const struct vport *vport) -{ - return vport_priv(vport); -} - -const char *ovs_netdev_get_name(const struct vport *); void ovs_netdev_detach_dev(struct vport *); int __init ovs_netdev_init(void); diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c deleted file mode 100644 index 6d39766e7828..000000000000 --- a/net/openvswitch/vport-vxlan.c +++ /dev/null @@ -1,322 +0,0 @@ -/* - * Copyright (c) 2014 Nicira, Inc. - * Copyright (c) 2013 Cisco Systems, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/net.h> -#include <linux/rculist.h> -#include <linux/udp.h> -#include <linux/module.h> - -#include <net/icmp.h> -#include <net/ip.h> -#include <net/udp.h> -#include <net/ip_tunnels.h> -#include <net/rtnetlink.h> -#include <net/route.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <net/net_namespace.h> -#include <net/netns/generic.h> -#include <net/vxlan.h> - -#include "datapath.h" -#include "vport.h" -#include "vport-vxlan.h" - -/** - * struct vxlan_port - Keeps track of open UDP ports - * @vs: vxlan_sock created for the port. - * @name: vport name. - */ -struct vxlan_port { - struct vxlan_sock *vs; - char name[IFNAMSIZ]; - u32 exts; /* VXLAN_F_* in <net/vxlan.h> */ -}; - -static struct vport_ops ovs_vxlan_vport_ops; - -static inline struct vxlan_port *vxlan_vport(const struct vport *vport) -{ - return vport_priv(vport); -} - -/* Called with rcu_read_lock and BH disabled. */ -static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, - struct vxlan_metadata *md) -{ - struct ovs_tunnel_info tun_info; - struct vxlan_port *vxlan_port; - struct vport *vport = vs->data; - struct iphdr *iph; - struct ovs_vxlan_opts opts = { - .gbp = md->gbp, - }; - __be64 key; - __be16 flags; - - flags = TUNNEL_KEY | (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0); - vxlan_port = vxlan_vport(vport); - if (vxlan_port->exts & VXLAN_F_GBP && md->gbp) - flags |= TUNNEL_VXLAN_OPT; - - /* Save outer tunnel values */ - iph = ip_hdr(skb); - key = cpu_to_be64(ntohl(md->vni) >> 8); - ovs_flow_tun_info_init(&tun_info, iph, - udp_hdr(skb)->source, udp_hdr(skb)->dest, - key, flags, &opts, sizeof(opts)); - - ovs_vport_receive(vport, skb, &tun_info); -} - -static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) -{ - struct vxlan_port *vxlan_port = vxlan_vport(vport); - __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport; - - if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port))) - return -EMSGSIZE; - - if (vxlan_port->exts) { - struct nlattr *exts; - - exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION); - if (!exts) - return -EMSGSIZE; - - if (vxlan_port->exts & VXLAN_F_GBP && - nla_put_flag(skb, OVS_VXLAN_EXT_GBP)) - return -EMSGSIZE; - - nla_nest_end(skb, exts); - } - - return 0; -} - -static void vxlan_tnl_destroy(struct vport *vport) -{ - struct vxlan_port *vxlan_port = vxlan_vport(vport); - - vxlan_sock_release(vxlan_port->vs); - - ovs_vport_deferred_free(vport); -} - -static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX+1] = { - [OVS_VXLAN_EXT_GBP] = { .type = NLA_FLAG, }, -}; - -static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr) -{ - struct nlattr *exts[OVS_VXLAN_EXT_MAX+1]; - struct vxlan_port *vxlan_port; - int err; - - if (nla_len(attr) < sizeof(struct nlattr)) - return -EINVAL; - - err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy); - if (err < 0) - return err; - - vxlan_port = vxlan_vport(vport); - - if (exts[OVS_VXLAN_EXT_GBP]) - vxlan_port->exts |= VXLAN_F_GBP; - - return 0; -} - -static struct vport *vxlan_tnl_create(const struct vport_parms *parms) -{ - struct net *net = ovs_dp_get_net(parms->dp); - struct nlattr *options = parms->options; - struct vxlan_port *vxlan_port; - struct vxlan_sock *vs; - struct vport *vport; - struct nlattr *a; - u16 dst_port; - int err; - - if (!options) { - err = -EINVAL; - goto error; - } - a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT); - if (a && nla_len(a) == sizeof(u16)) { - dst_port = nla_get_u16(a); - } else { - /* Require destination port from userspace. */ - err = -EINVAL; - goto error; - } - - vport = ovs_vport_alloc(sizeof(struct vxlan_port), - &ovs_vxlan_vport_ops, parms); - if (IS_ERR(vport)) - return vport; - - vxlan_port = vxlan_vport(vport); - strncpy(vxlan_port->name, parms->name, IFNAMSIZ); - - a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION); - if (a) { - err = vxlan_configure_exts(vport, a); - if (err) { - ovs_vport_free(vport); - goto error; - } - } - - vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, - vxlan_port->exts); - if (IS_ERR(vs)) { - ovs_vport_free(vport); - return (void *)vs; - } - vxlan_port->vs = vs; - - return vport; - -error: - return ERR_PTR(err); -} - -static int vxlan_ext_gbp(struct sk_buff *skb) -{ - const struct ovs_tunnel_info *tun_info; - const struct ovs_vxlan_opts *opts; - - tun_info = OVS_CB(skb)->egress_tun_info; - opts = tun_info->options; - - if (tun_info->tunnel.tun_flags & TUNNEL_VXLAN_OPT && - tun_info->options_len >= sizeof(*opts)) - return opts->gbp; - else - return 0; -} - -static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) -{ - struct net *net = ovs_dp_get_net(vport->dp); - struct vxlan_port *vxlan_port = vxlan_vport(vport); - struct sock *sk = vxlan_port->vs->sock->sk; - __be16 dst_port = inet_sk(sk)->inet_sport; - const struct ovs_key_ipv4_tunnel *tun_key; - struct vxlan_metadata md = {0}; - struct rtable *rt; - struct flowi4 fl; - __be16 src_port; - __be16 df; - int err; - u32 vxflags; - - if (unlikely(!OVS_CB(skb)->egress_tun_info)) { - err = -EINVAL; - goto error; - } - - tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - goto error; - } - - df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? - htons(IP_DF) : 0; - - skb->ignore_df = 1; - - src_port = udp_flow_src_port(net, skb, 0, 0, true); - md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8); - md.gbp = vxlan_ext_gbp(skb); - vxflags = vxlan_port->exts | - (tun_key->tun_flags & TUNNEL_CSUM ? VXLAN_F_UDP_CSUM : 0); - - err = vxlan_xmit_skb(rt, sk, skb, fl.saddr, tun_key->ipv4_dst, - tun_key->ipv4_tos, tun_key->ipv4_ttl, df, - src_port, dst_port, - &md, false, vxflags); - if (err < 0) - ip_rt_put(rt); - return err; -error: - kfree_skb(skb); - return err; -} - -static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *egress_tun_info) -{ - struct net *net = ovs_dp_get_net(vport->dp); - struct vxlan_port *vxlan_port = vxlan_vport(vport); - __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport; - __be16 src_port; - int port_min; - int port_max; - - inet_get_local_port_range(net, &port_min, &port_max); - src_port = udp_flow_src_port(net, skb, 0, 0, true); - - return ovs_tunnel_get_egress_info(egress_tun_info, net, - OVS_CB(skb)->egress_tun_info, - IPPROTO_UDP, skb->mark, - src_port, dst_port); -} - -static const char *vxlan_get_name(const struct vport *vport) -{ - struct vxlan_port *vxlan_port = vxlan_vport(vport); - return vxlan_port->name; -} - -static struct vport_ops ovs_vxlan_vport_ops = { - .type = OVS_VPORT_TYPE_VXLAN, - .create = vxlan_tnl_create, - .destroy = vxlan_tnl_destroy, - .get_name = vxlan_get_name, - .get_options = vxlan_get_options, - .send = vxlan_tnl_send, - .get_egress_tun_info = vxlan_get_egress_tun_info, - .owner = THIS_MODULE, -}; - -static int __init ovs_vxlan_tnl_init(void) -{ - return ovs_vport_ops_register(&ovs_vxlan_vport_ops); -} - -static void __exit ovs_vxlan_tnl_exit(void) -{ - ovs_vport_ops_unregister(&ovs_vxlan_vport_ops); -} - -module_init(ovs_vxlan_tnl_init); -module_exit(ovs_vxlan_tnl_exit); - -MODULE_DESCRIPTION("OVS: VXLAN switching port"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("vport-type-4"); diff --git a/net/openvswitch/vport-vxlan.h b/net/openvswitch/vport-vxlan.h deleted file mode 100644 index 4b08233e73d5..000000000000 --- a/net/openvswitch/vport-vxlan.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef VPORT_VXLAN_H -#define VPORT_VXLAN_H 1 - -#include <linux/kernel.h> -#include <linux/types.h> - -struct ovs_vxlan_opts { - __u32 gbp; -}; - -#endif diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 067a3fff1d2c..d14f59403c5e 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -113,7 +113,7 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) struct vport *vport; hlist_for_each_entry_rcu(vport, bucket, hash_node) - if (!strcmp(name, vport->ops->get_name(vport)) && + if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; @@ -226,7 +226,7 @@ struct vport *ovs_vport_add(const struct vport_parms *parms) } bucket = hash_bucket(ovs_dp_get_net(vport->dp), - vport->ops->get_name(vport)); + ovs_vport_name(vport)); hlist_add_head_rcu(&vport->hash_node, bucket); return vport; } @@ -469,7 +469,7 @@ u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb) * skb->data should point to the Ethernet header. */ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb, - const struct ovs_tunnel_info *tun_info) + const struct ip_tunnel_info *tun_info) { struct pcpu_sw_netstats *stats; struct sw_flow_key key; @@ -572,22 +572,22 @@ void ovs_vport_deferred_free(struct vport *vport) } EXPORT_SYMBOL_GPL(ovs_vport_deferred_free); -int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, +int ovs_tunnel_get_egress_info(struct ip_tunnel_info *egress_tun_info, struct net *net, - const struct ovs_tunnel_info *tun_info, + const struct ip_tunnel_info *tun_info, u8 ipproto, u32 skb_mark, __be16 tp_src, __be16 tp_dst) { - const struct ovs_key_ipv4_tunnel *tun_key; + const struct ip_tunnel_key *tun_key; struct rtable *rt; struct flowi4 fl; if (unlikely(!tun_info)) return -EINVAL; - tun_key = &tun_info->tunnel; + tun_key = &tun_info->key; /* Route lookup to get srouce IP address. * The process may need to be changed if the corresponding process @@ -602,22 +602,22 @@ int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, /* Generate egress_tun_info based on tun_info, * saddr, tp_src and tp_dst */ - __ovs_flow_tun_info_init(egress_tun_info, - fl.saddr, tun_key->ipv4_dst, - tun_key->ipv4_tos, - tun_key->ipv4_ttl, - tp_src, tp_dst, - tun_key->tun_id, - tun_key->tun_flags, - tun_info->options, - tun_info->options_len); + __ip_tunnel_info_init(egress_tun_info, + fl.saddr, tun_key->ipv4_dst, + tun_key->ipv4_tos, + tun_key->ipv4_ttl, + tp_src, tp_dst, + tun_key->tun_id, + tun_key->tun_flags, + tun_info->options, + tun_info->options_len); return 0; } EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info); int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *info) + struct ip_tunnel_info *info) { /* get_egress_tun_info() is only implemented on tunnel ports. */ if (unlikely(!vport->ops->get_egress_tun_info)) diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index bc85331a6c60..1a689c28b5a6 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -27,6 +27,7 @@ #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/u64_stats_sync.h> +#include <net/route.h> #include "datapath.h" @@ -58,15 +59,15 @@ u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *); int ovs_vport_send(struct vport *, struct sk_buff *); -int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, +int ovs_tunnel_get_egress_info(struct ip_tunnel_info *egress_tun_info, struct net *net, - const struct ovs_tunnel_info *tun_info, + const struct ip_tunnel_info *tun_info, u8 ipproto, u32 skb_mark, __be16 tp_src, __be16 tp_dst); int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *info); + struct ip_tunnel_info *info); /* The following definitions are for implementers of vport devices: */ @@ -106,7 +107,7 @@ struct vport_portids { * @detach_list: list used for detaching vport in net-exit call. */ struct vport { - struct rcu_head rcu; + struct net_device *dev; struct datapath *dp; struct vport_portids __rcu *upcall_portids; u16 port_no; @@ -119,6 +120,7 @@ struct vport { struct vport_err_stats err_stats; struct list_head detach_list; + struct rcu_head rcu; }; /** @@ -176,7 +178,7 @@ struct vport_ops { int (*send)(struct vport *, struct sk_buff *); int (*get_egress_tun_info)(struct vport *, struct sk_buff *, - struct ovs_tunnel_info *); + struct ip_tunnel_info *); struct module *owner; struct list_head list; @@ -226,7 +228,7 @@ static inline struct vport *vport_from_priv(void *priv) } void ovs_vport_receive(struct vport *, struct sk_buff *, - const struct ovs_tunnel_info *); + const struct ip_tunnel_info *); static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) @@ -235,11 +237,16 @@ static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb, skb->csum = csum_add(skb->csum, csum_partial(start, len, 0)); } +static inline const char *ovs_vport_name(struct vport *vport) +{ + return vport->dev ? vport->dev->name : vport->ops->get_name(vport); +} + int ovs_vport_ops_register(struct vport_ops *ops); void ovs_vport_ops_unregister(struct vport_ops *ops); static inline struct rtable *ovs_tunnel_route_lookup(struct net *net, - const struct ovs_key_ipv4_tunnel *key, + const struct ip_tunnel_key *key, u32 mark, struct flowi4 *fl, u8 protocol) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index af427a3dbcba..074a32f466f8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -27,6 +27,15 @@ #include <net/act_api.h> #include <net/netlink.h> +static void free_tcf(struct rcu_head *head) +{ + struct tcf_common *p = container_of(head, struct tcf_common, tcfc_rcu); + + free_percpu(p->cpu_bstats); + free_percpu(p->cpu_qstats); + kfree(p); +} + void tcf_hash_destroy(struct tc_action *a) { struct tcf_common *p = a->priv; @@ -41,7 +50,7 @@ void tcf_hash_destroy(struct tc_action *a) * gen_estimator est_timer() might access p->tcfc_lock * or bstats, wait a RCU grace period before freeing p */ - kfree_rcu(p, tcfc_rcu); + call_rcu(&p->tcfc_rcu, free_tcf); } EXPORT_SYMBOL(tcf_hash_destroy); @@ -230,15 +239,16 @@ void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est) if (est) gen_kill_estimator(&pc->tcfc_bstats, &pc->tcfc_rate_est); - kfree_rcu(pc, tcfc_rcu); + call_rcu(&pc->tcfc_rcu, free_tcf); } EXPORT_SYMBOL(tcf_hash_cleanup); int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, - int size, int bind) + int size, int bind, bool cpustats) { struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = kzalloc(size, GFP_KERNEL); + int err = -ENOMEM; if (unlikely(!p)) return -ENOMEM; @@ -246,18 +256,32 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, if (bind) p->tcfc_bindcnt = 1; + if (cpustats) { + p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + if (!p->cpu_bstats) { +err1: + kfree(p); + return err; + } + p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); + if (!p->cpu_qstats) { +err2: + free_percpu(p->cpu_bstats); + goto err1; + } + } spin_lock_init(&p->tcfc_lock); INIT_HLIST_NODE(&p->tcfc_head); p->tcfc_index = index ? index : tcf_hash_new_index(hinfo); p->tcfc_tm.install = jiffies; p->tcfc_tm.lastuse = jiffies; if (est) { - int err = gen_new_estimator(&p->tcfc_bstats, NULL, - &p->tcfc_rate_est, - &p->tcfc_lock, est); + err = gen_new_estimator(&p->tcfc_bstats, p->cpu_bstats, + &p->tcfc_rate_est, + &p->tcfc_lock, est); if (err) { - kfree(p); - return err; + free_percpu(p->cpu_qstats); + goto err2; } } @@ -615,10 +639,10 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, if (err < 0) goto errout; - if (gnet_stats_copy_basic(&d, NULL, &p->tcfc_bstats) < 0 || + if (gnet_stats_copy_basic(&d, p->cpu_bstats, &p->tcfc_bstats) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfc_bstats, &p->tcfc_rate_est) < 0 || - gnet_stats_copy_queue(&d, NULL, + gnet_stats_copy_queue(&d, p->cpu_qstats, &p->tcfc_qstats, p->tcfc_qstats.qlen) < 0) goto errout; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 1df78289e248..e9e923a8c747 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -281,7 +281,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (!tcf_hash_check(parm->index, act, bind)) { ret = tcf_hash_create(parm->index, est, act, - sizeof(*prog), bind); + sizeof(*prog), bind, false); if (ret < 0) goto destroy_fp; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 295d14bd6c67..f2b540220ad0 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -108,7 +108,8 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_CONNMARK_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), + bind, false); if (ret) return ret; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 4cd5cf1aedf8..b07c535ba8e7 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -62,7 +62,8 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, parm = nla_data(tb[TCA_CSUM_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), + bind, false); if (ret) return ret; ret = ACT_P_CREATED; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 7fffc2272701..5c1b05170736 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -28,14 +28,18 @@ #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) { - if (!gact->tcfg_pval || prandom_u32() % gact->tcfg_pval) + smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ + if (prandom_u32() % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } static int gact_determ(struct tcf_gact *gact) { - if (!gact->tcfg_pval || gact->tcf_bstats.packets % gact->tcfg_pval) + u32 pack = atomic_inc_return(&gact->packets); + + smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ + if (pack % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } @@ -85,7 +89,8 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, #endif if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), + bind, true); if (ret) return ret; ret = ACT_P_CREATED; @@ -99,16 +104,19 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, gact = to_gact(a); - spin_lock_bh(&gact->tcf_lock); + ASSERT_RTNL(); gact->tcf_action = parm->action; #ifdef CONFIG_GACT_PROB if (p_parm) { gact->tcfg_paction = p_parm->paction; - gact->tcfg_pval = p_parm->pval; + gact->tcfg_pval = max_t(u16, 1, p_parm->pval); + /* Make sure tcfg_pval is written before tcfg_ptype + * coupled with smp_rmb() in gact_net_rand() & gact_determ() + */ + smp_wmb(); gact->tcfg_ptype = p_parm->ptype; } #endif - spin_unlock_bh(&gact->tcf_lock); if (ret == ACT_P_CREATED) tcf_hash_insert(a); return ret; @@ -118,23 +126,21 @@ static int tcf_gact(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_gact *gact = a->priv; - int action = TC_ACT_SHOT; + int action = READ_ONCE(gact->tcf_action); - spin_lock(&gact->tcf_lock); #ifdef CONFIG_GACT_PROB - if (gact->tcfg_ptype) - action = gact_rand[gact->tcfg_ptype](gact); - else - action = gact->tcf_action; -#else - action = gact->tcf_action; + { + u32 ptype = READ_ONCE(gact->tcfg_ptype); + + if (ptype) + action = gact_rand[ptype](gact); + } #endif - gact->tcf_bstats.bytes += qdisc_pkt_len(skb); - gact->tcf_bstats.packets++; + bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), skb); if (action == TC_ACT_SHOT) - gact->tcf_qstats.drops++; - gact->tcf_tm.lastuse = jiffies; - spin_unlock(&gact->tcf_lock); + qstats_drop_inc(this_cpu_ptr(gact->common.cpu_qstats)); + + tcf_lastuse_update(&gact->tcf_tm); return action; } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index cbc8dd7dd48a..99c9cc1c7af9 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -114,7 +114,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, index = nla_get_u32(tb[TCA_IPT_INDEX]); if (!tcf_hash_check(index, a, bind) ) { - ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind); + ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind, false); if (ret) return ret; ret = ACT_P_CREATED; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index a42a3b257226..19cd8904efa0 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -35,9 +35,11 @@ static LIST_HEAD(mirred_list); static void tcf_mirred_release(struct tc_action *a, int bind) { struct tcf_mirred *m = to_mirred(a); + struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); + list_del(&m->tcfm_list); - if (m->tcfm_dev) - dev_put(m->tcfm_dev); + if (dev) + dev_put(dev); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { @@ -93,7 +95,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (!tcf_hash_check(parm->index, a, bind)) { if (dev == NULL) return -EINVAL; - ret = tcf_hash_create(parm->index, est, a, sizeof(*m), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*m), + bind, true); if (ret) return ret; ret = ACT_P_CREATED; @@ -105,18 +108,18 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } m = to_mirred(a); - spin_lock_bh(&m->tcf_lock); + ASSERT_RTNL(); m->tcf_action = parm->action; m->tcfm_eaction = parm->eaction; if (dev != NULL) { m->tcfm_ifindex = parm->ifindex; if (ret != ACT_P_CREATED) - dev_put(m->tcfm_dev); + dev_put(rcu_dereference_protected(m->tcfm_dev, 1)); dev_hold(dev); - m->tcfm_dev = dev; + rcu_assign_pointer(m->tcfm_dev, dev); m->tcfm_ok_push = ok_push; } - spin_unlock_bh(&m->tcf_lock); + if (ret == ACT_P_CREATED) { list_add(&m->tcfm_list, &mirred_list); tcf_hash_insert(a); @@ -131,20 +134,22 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, struct tcf_mirred *m = a->priv; struct net_device *dev; struct sk_buff *skb2; + int retval, err; u32 at; - int retval, err = 1; - spin_lock(&m->tcf_lock); - m->tcf_tm.lastuse = jiffies; - bstats_update(&m->tcf_bstats, skb); + tcf_lastuse_update(&m->tcf_tm); + + bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); - dev = m->tcfm_dev; - if (!dev) { - printk_once(KERN_NOTICE "tc mirred: target device is gone\n"); + rcu_read_lock(); + retval = READ_ONCE(m->tcf_action); + dev = rcu_dereference(m->tcfm_dev); + if (unlikely(!dev)) { + pr_notice_once("tc mirred: target device is gone\n"); goto out; } - if (!(dev->flags & IFF_UP)) { + if (unlikely(!(dev->flags & IFF_UP))) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); goto out; @@ -152,7 +157,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, at = G_TC_AT(skb->tc_verd); skb2 = skb_clone(skb, GFP_ATOMIC); - if (skb2 == NULL) + if (!skb2) goto out; if (!(at & AT_EGRESS)) { @@ -168,16 +173,13 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, skb2->dev = dev; err = dev_queue_xmit(skb2); -out: if (err) { - m->tcf_qstats.overlimits++; +out: + qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats)); if (m->tcfm_eaction != TCA_EGRESS_MIRROR) retval = TC_ACT_SHOT; - else - retval = m->tcf_action; - } else - retval = m->tcf_action; - spin_unlock(&m->tcf_lock); + } + rcu_read_unlock(); return retval; } @@ -216,14 +218,16 @@ static int mirred_device_event(struct notifier_block *unused, struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tcf_mirred *m; + ASSERT_RTNL(); if (event == NETDEV_UNREGISTER) list_for_each_entry(m, &mirred_list, tcfm_list) { - spin_lock_bh(&m->tcf_lock); - if (m->tcfm_dev == dev) { + if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); - m->tcfm_dev = NULL; + /* Note : no rcu grace period necessary, as + * net_device are already rcu protected. + */ + RCU_INIT_POINTER(m->tcfm_dev, NULL); } - spin_unlock_bh(&m->tcf_lock); } return NOTIFY_DONE; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 270a030d5fd0..5be0b3c1c5b0 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -55,7 +55,8 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, parm = nla_data(tb[TCA_NAT_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), + bind, false); if (ret) return ret; ret = ACT_P_CREATED; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 17e6d6669c7f..ce8676ad892f 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -57,7 +57,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (!tcf_hash_check(parm->index, a, bind)) { if (!parm->nkeys) return -EINVAL; - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), + bind, false); if (ret) return ret; p = to_pedit(a); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 6a8d9488613a..d6b708d6afdf 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -103,7 +103,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, defdata = nla_data(tb[TCA_DEF_DATA]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*d), + bind, false); if (ret) return ret; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index fcfeeaf838be..6751b5f8c046 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,7 +99,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_SKBEDIT_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*d), + bind, false); if (ret) return ret; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index d735ecf0b1a7..796785e0bf96 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -116,7 +116,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, action = parm->v_action; if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*v), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*v), + bind, false); if (ret) return ret; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index ea611b216412..4c85bd3a750c 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -30,35 +30,16 @@ static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct cls_cgroup_head *head = rcu_dereference_bh(tp->root); - u32 classid; - - classid = task_cls_state(current)->classid; - - /* - * Due to the nature of the classifier it is required to ignore all - * packets originating from softirq context as accessing `current' - * would lead to false results. - * - * This test assumes that all callers of dev_queue_xmit() explicitely - * disable bh. Knowing this, it is possible to detect softirq based - * calls by looking at the number of nested bh disable calls because - * softirqs always disables bh. - */ - if (in_serving_softirq()) { - /* If there is an sk_classid we'll use that. */ - if (!skb->sk) - return -1; - classid = skb->sk->sk_classid; - } + u32 classid = task_get_classid(skb); if (!classid) return -1; - if (!tcf_em_tree_match(skb, &head->ematches, NULL)) return -1; res->classid = classid; res->class = 0; + return tcf_exts_exec(skb, &head->exts, res); } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index b8d73bca683c..ffaeea63d473 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -186,7 +186,6 @@ struct qfq_sched { u64 oldV, V; /* Precise virtual times. */ struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */ - u32 num_active_agg; /* Num. of active aggregates */ u32 wsum; /* weight sum */ u32 iwsum; /* inverse weight sum */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 59e80356672b..4345790ad326 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -487,23 +487,35 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, */ rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { + struct net_device *odev; + if (!laddr->valid) continue; - if ((laddr->state == SCTP_ADDR_SRC) && - (AF_INET == laddr->a.sa.sa_family)) { - fl4->fl4_sport = laddr->a.v4.sin_port; - flowi4_update_output(fl4, - asoc->base.sk->sk_bound_dev_if, - RT_CONN_FLAGS(asoc->base.sk), - daddr->v4.sin_addr.s_addr, - laddr->a.v4.sin_addr.s_addr); - - rt = ip_route_output_key(sock_net(sk), fl4); - if (!IS_ERR(rt)) { - dst = &rt->dst; - goto out_unlock; - } - } + if (laddr->state != SCTP_ADDR_SRC || + AF_INET != laddr->a.sa.sa_family) + continue; + + fl4->fl4_sport = laddr->a.v4.sin_port; + flowi4_update_output(fl4, + asoc->base.sk->sk_bound_dev_if, + RT_CONN_FLAGS(asoc->base.sk), + daddr->v4.sin_addr.s_addr, + laddr->a.v4.sin_addr.s_addr); + + rt = ip_route_output_key(sock_net(sk), fl4); + if (IS_ERR(rt)) + continue; + + /* Ensure the src address belongs to the output + * interface. + */ + odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr, + false); + if (!odev || odev->ifindex != fl4->flowi4_oif) + continue; + + dst = &rt->dst; + break; } out_unlock: diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 3ee27b7704ff..d7eaa7354cf7 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -853,7 +853,7 @@ nomem: /* * Respond to a normal COOKIE ACK chunk. - * We are the side that is being asked for an association. + * We are the side that is asking for an association. * * RFC 2960 5.1 Normal Establishment of an Association * diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 9f2add3cba26..33bafa2e703e 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -910,13 +910,9 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) if (switchdev_port_attr_get(dev, &attr)) return NULL; - if (nhsel > 0) { - if (prev_attr.u.ppid.id_len != attr.u.ppid.id_len) + if (nhsel > 0 && + !netdev_phys_item_id_same(&prev_attr.u.ppid, &attr.u.ppid)) return NULL; - if (memcmp(prev_attr.u.ppid.id, attr.u.ppid.id, - attr.u.ppid.id_len)) - return NULL; - } prev_attr = attr; } @@ -1043,3 +1039,106 @@ void switchdev_fib_ipv4_abort(struct fib_info *fi) fi->fib_net->ipv4.fib_offload_disabled = true; } EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_abort); + +static bool switchdev_port_same_parent_id(struct net_device *a, + struct net_device *b) +{ + struct switchdev_attr a_attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .flags = SWITCHDEV_F_NO_RECURSE, + }; + struct switchdev_attr b_attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .flags = SWITCHDEV_F_NO_RECURSE, + }; + + if (switchdev_port_attr_get(a, &a_attr) || + switchdev_port_attr_get(b, &b_attr)) + return false; + + return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid); +} + +static u32 switchdev_port_fwd_mark_get(struct net_device *dev, + struct net_device *group_dev) +{ + struct net_device *lower_dev; + struct list_head *iter; + + netdev_for_each_lower_dev(group_dev, lower_dev, iter) { + if (lower_dev == dev) + continue; + if (switchdev_port_same_parent_id(dev, lower_dev)) + return lower_dev->offload_fwd_mark; + return switchdev_port_fwd_mark_get(dev, lower_dev); + } + + return dev->ifindex; +} + +static void switchdev_port_fwd_mark_reset(struct net_device *group_dev, + u32 old_mark, u32 *reset_mark) +{ + struct net_device *lower_dev; + struct list_head *iter; + + netdev_for_each_lower_dev(group_dev, lower_dev, iter) { + if (lower_dev->offload_fwd_mark == old_mark) { + if (!*reset_mark) + *reset_mark = lower_dev->ifindex; + lower_dev->offload_fwd_mark = *reset_mark; + } + switchdev_port_fwd_mark_reset(lower_dev, old_mark, reset_mark); + } +} + +/** + * switchdev_port_fwd_mark_set - Set port offload forwarding mark + * + * @dev: port device + * @group_dev: containing device + * @joining: true if dev is joining group; false if leaving group + * + * An ungrouped port's offload mark is just its ifindex. A grouped + * port's (member of a bridge, for example) offload mark is the ifindex + * of one of the ports in the group with the same parent (switch) ID. + * Ports on the same device in the same group will have the same mark. + * + * Example: + * + * br0 ifindex=9 + * sw1p1 ifindex=2 mark=2 + * sw1p2 ifindex=3 mark=2 + * sw2p1 ifindex=4 mark=5 + * sw2p2 ifindex=5 mark=5 + * + * If sw2p2 leaves the bridge, we'll have: + * + * br0 ifindex=9 + * sw1p1 ifindex=2 mark=2 + * sw1p2 ifindex=3 mark=2 + * sw2p1 ifindex=4 mark=4 + * sw2p2 ifindex=5 mark=5 + */ +void switchdev_port_fwd_mark_set(struct net_device *dev, + struct net_device *group_dev, + bool joining) +{ + u32 mark = dev->ifindex; + u32 reset_mark = 0; + + if (group_dev && joining) { + mark = switchdev_port_fwd_mark_get(dev, group_dev); + } else if (group_dev && !joining) { + if (dev->offload_fwd_mark == mark) + /* Ohoh, this port was the mark reference port, + * but it's leaving the group, so reset the + * mark for the remaining ports in the group. + */ + switchdev_port_fwd_mark_reset(group_dev, mark, + &reset_mark); + } + + dev->offload_fwd_mark = mark; +} +EXPORT_SYMBOL_GPL(switchdev_port_fwd_mark_set); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index a816382fc8af..8b010c976b2f 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -316,6 +316,29 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, } } +void tipc_bclink_sync_state(struct tipc_node *n, struct tipc_msg *hdr) +{ + u16 last = msg_last_bcast(hdr); + int mtyp = msg_type(hdr); + + if (unlikely(msg_user(hdr) != LINK_PROTOCOL)) + return; + if (mtyp == STATE_MSG) { + tipc_bclink_update_link_state(n, last); + return; + } + /* Compatibility: older nodes don't know BCAST_PROTOCOL synchronization, + * and transfer synch info in LINK_PROTOCOL messages. + */ + if (tipc_node_is_up(n)) + return; + if ((mtyp != RESET_MSG) && (mtyp != ACTIVATE_MSG)) + return; + n->bclink.last_sent = last; + n->bclink.last_in = last; + n->bclink.oos_state = 0; +} + /** * bclink_peek_nack - monitor retransmission requests sent by other nodes * @@ -358,10 +381,9 @@ int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list) /* Prepare clone of message for local node */ skb = tipc_msg_reassemble(list); - if (unlikely(!skb)) { - __skb_queue_purge(list); + if (unlikely(!skb)) return -EHOSTUNREACH; - } + /* Broadcast to all nodes */ if (likely(bclink)) { tipc_bclink_lock(net); @@ -413,7 +435,7 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) * all nodes in the cluster don't ACK at the same time */ if (((seqno - tn->own_addr) % TIPC_MIN_LINK_WIN) == 0) { - tipc_link_proto_xmit(node->active_links[node->addr & 1], + tipc_link_proto_xmit(node_active_link(node, node->addr), STATE_MSG, 0, 0, 0, 0); tn->bcl->stats.sent_acks++; } @@ -925,7 +947,6 @@ int tipc_bclink_init(struct net *net) tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT); bcl->bearer_id = MAX_BEARERS; rcu_assign_pointer(tn->bearer_list[MAX_BEARERS], &bcbearer->bearer); - bcl->state = WORKING_WORKING; bcl->pmsg = (struct tipc_msg *)&bcl->proto_msg; msg_set_prevnode(bcl->pmsg, tn->own_addr); strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 3c290a48f720..d74c69bcf60b 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -133,5 +133,6 @@ void tipc_bclink_wakeup_users(struct net *net); int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg); int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]); void tipc_bclink_input(struct net *net); +void tipc_bclink_sync_state(struct tipc_node *n, struct tipc_msg *msg); #endif diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 00bc0e620532..eae58a6b121c 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -470,6 +470,32 @@ void tipc_bearer_send(struct net *net, u32 bearer_id, struct sk_buff *buf, rcu_read_unlock(); } +/* tipc_bearer_xmit() -send buffer to destination over bearer + */ +void tipc_bearer_xmit(struct net *net, u32 bearer_id, + struct sk_buff_head *xmitq, + struct tipc_media_addr *dst) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_bearer *b; + struct sk_buff *skb, *tmp; + + if (skb_queue_empty(xmitq)) + return; + + rcu_read_lock(); + b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); + if (likely(b)) { + skb_queue_walk_safe(xmitq, skb, tmp) { + __skb_dequeue(xmitq); + b->media->send_msg(net, skb, b, dst); + /* Until we remove cloning in tipc_l2_send_msg(): */ + kfree_skb(skb); + } + } + rcu_read_unlock(); +} + /** * tipc_l2_rcv_msg - handle incoming TIPC message from an interface * @buf: the received packet diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index dc714d977768..6426f242f626 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -217,5 +217,8 @@ void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); void tipc_bearer_send(struct net *net, u32 bearer_id, struct sk_buff *buf, struct tipc_media_addr *dest); +void tipc_bearer_xmit(struct net *net, u32 bearer_id, + struct sk_buff_head *xmitq, + struct tipc_media_addr *dst); #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/core.h b/net/tipc/core.h index 0fcf133d5cb7..f4ed67778c54 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -129,6 +129,11 @@ static inline int less(u16 left, u16 right) return less_eq(left, right) && (mod(right) != mod(left)); } +static inline int in_range(u16 val, u16 min, u16 max) +{ + return !less(val, min) && !more(val, max); +} + #ifdef CONFIG_SYSCTL int tipc_register_sysctl(void); void tipc_unregister_sysctl(void); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 967e292f53c8..164d08907d6f 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -35,7 +35,7 @@ */ #include "core.h" -#include "link.h" +#include "node.h" #include "discover.h" /* min delay during bearer start up */ @@ -125,7 +125,6 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *node; - struct tipc_link *link; struct tipc_media_addr maddr; struct sk_buff *rbuf; struct tipc_msg *msg = buf_msg(buf); @@ -170,13 +169,10 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, return; tipc_node_lock(node); node->capabilities = caps; - link = node->links[bearer->identity]; /* Prepare to validate requesting node's signature and media address */ sign_match = (signature == node->signature); - addr_match = link && !memcmp(&link->media_addr, &maddr, sizeof(maddr)); - link_up = link && tipc_link_is_up(link); - + tipc_node_check_dest(node, bearer, &link_up, &addr_match, &maddr); /* These three flags give us eight permutations: */ @@ -239,16 +235,8 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, if (accept_sign) node->signature = signature; - if (accept_addr) { - if (!link) - link = tipc_link_create(node, bearer, &maddr); - if (link) { - memcpy(&link->media_addr, &maddr, sizeof(maddr)); - tipc_link_reset(link); - } else { - respond = false; - } - } + if (accept_addr && !tipc_node_update_dest(node, bearer, &maddr)) + respond = false; /* Send response, if necessary */ if (respond && (mtyp == DSC_REQ_MSG)) { diff --git a/net/tipc/link.c b/net/tipc/link.c index eaa9fe54b4ae..b63d57390bb7 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -77,36 +77,70 @@ static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { }; /* - * Out-of-range value for link session numbers + * Interval between NACKs when packets arrive out of order */ -#define INVALID_SESSION 0x10000 - +#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2) /* - * Link state events: + * Out-of-range value for link session numbers */ -#define STARTING_EVT 856384768 /* link processing trigger */ -#define TRAFFIC_MSG_EVT 560815u /* rx'd ??? */ -#define SILENCE_EVT 560817u /* timer dicovered silence from peer */ +#define WILDCARD_SESSION 0x10000 -/* - * State value stored in 'failover_pkts' +/* State value stored in 'failover_pkts' */ #define FIRST_FAILOVER 0xffffu -static void link_handle_out_of_seq_msg(struct tipc_link *link, - struct sk_buff *skb); -static void tipc_link_proto_rcv(struct tipc_link *link, - struct sk_buff *skb); -static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol); -static void link_state_event(struct tipc_link *l_ptr, u32 event); +/* Link FSM states and events: + */ +enum { + TIPC_LINK_WORKING, + TIPC_LINK_PROBING, + TIPC_LINK_RESETTING, + TIPC_LINK_ESTABLISHING +}; + +enum { + PEER_RESET_EVT = RESET_MSG, + ACTIVATE_EVT = ACTIVATE_MSG, + TRAFFIC_EVT, /* Any other valid msg from peer */ + SILENCE_EVT /* Peer was silent during last timer interval*/ +}; + +/* Link FSM state checking routines + */ +static int link_working(struct tipc_link *l) +{ + return l->state == TIPC_LINK_WORKING; +} + +static int link_probing(struct tipc_link *l) +{ + return l->state == TIPC_LINK_PROBING; +} + +static int link_resetting(struct tipc_link *l) +{ + return l->state == TIPC_LINK_RESETTING; +} + +static int link_establishing(struct tipc_link *l) +{ + return l->state == TIPC_LINK_ESTABLISHING; +} + +static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq); +static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, + u16 rcvgap, int tolerance, int priority, + struct sk_buff_head *xmitq); static void link_reset_statistics(struct tipc_link *l_ptr); static void link_print(struct tipc_link *l_ptr, const char *str); -static void tipc_link_sync_xmit(struct tipc_link *l); +static void tipc_link_build_bcast_sync_msg(struct tipc_link *l, + struct sk_buff_head *xmitq); static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf); static void tipc_link_input(struct tipc_link *l, struct sk_buff *skb); static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb); static bool tipc_link_failover_rcv(struct tipc_link *l, struct sk_buff **skb); -static void link_set_timer(struct tipc_link *link, unsigned long time); + /* * Simple link routines */ @@ -115,26 +149,13 @@ static unsigned int align(unsigned int i) return (i + 3) & ~3u; } -static void tipc_link_release(struct kref *kref) -{ - kfree(container_of(kref, struct tipc_link, ref)); -} - -static void tipc_link_get(struct tipc_link *l_ptr) -{ - kref_get(&l_ptr->ref); -} - -static void tipc_link_put(struct tipc_link *l_ptr) -{ - kref_put(&l_ptr->ref, tipc_link_release); -} - static struct tipc_link *tipc_parallel_link(struct tipc_link *l) { - if (l->owner->active_links[0] != l) - return l->owner->active_links[0]; - return l->owner->active_links[1]; + struct tipc_node *n = l->owner; + + if (node_active_link(n, 0) != l) + return node_active_link(n, 0); + return node_active_link(n, 1); } /* @@ -144,74 +165,14 @@ int tipc_link_is_up(struct tipc_link *l_ptr) { if (!l_ptr) return 0; - return link_working_working(l_ptr) || link_working_unknown(l_ptr); + return link_working(l_ptr) || link_probing(l_ptr); } -int tipc_link_is_active(struct tipc_link *l_ptr) +int tipc_link_is_active(struct tipc_link *l) { - return (l_ptr->owner->active_links[0] == l_ptr) || - (l_ptr->owner->active_links[1] == l_ptr); -} - -/** - * link_timeout - handle expiration of link timer - * @l_ptr: pointer to link - */ -static void link_timeout(unsigned long data) -{ - struct tipc_link *l_ptr = (struct tipc_link *)data; - struct sk_buff *skb; - - tipc_node_lock(l_ptr->owner); - - /* update counters used in statistical profiling of send traffic */ - l_ptr->stats.accu_queue_sz += skb_queue_len(&l_ptr->transmq); - l_ptr->stats.queue_sz_counts++; - - skb = skb_peek(&l_ptr->transmq); - if (skb) { - struct tipc_msg *msg = buf_msg(skb); - u32 length = msg_size(msg); - - if ((msg_user(msg) == MSG_FRAGMENTER) && - (msg_type(msg) == FIRST_FRAGMENT)) { - length = msg_size(msg_get_wrapped(msg)); - } - if (length) { - l_ptr->stats.msg_lengths_total += length; - l_ptr->stats.msg_length_counts++; - if (length <= 64) - l_ptr->stats.msg_length_profile[0]++; - else if (length <= 256) - l_ptr->stats.msg_length_profile[1]++; - else if (length <= 1024) - l_ptr->stats.msg_length_profile[2]++; - else if (length <= 4096) - l_ptr->stats.msg_length_profile[3]++; - else if (length <= 16384) - l_ptr->stats.msg_length_profile[4]++; - else if (length <= 32768) - l_ptr->stats.msg_length_profile[5]++; - else - l_ptr->stats.msg_length_profile[6]++; - } - } - - /* do all other link processing performed on a periodic basis */ - if (l_ptr->silent_intv_cnt || tipc_bclink_acks_missing(l_ptr->owner)) - link_state_event(l_ptr, SILENCE_EVT); - l_ptr->silent_intv_cnt++; - if (skb_queue_len(&l_ptr->backlogq)) - tipc_link_push_packets(l_ptr); - link_set_timer(l_ptr, l_ptr->keepalive_intv); - tipc_node_unlock(l_ptr->owner); - tipc_link_put(l_ptr); -} + struct tipc_node *n = l->owner; -static void link_set_timer(struct tipc_link *link, unsigned long time) -{ - if (!mod_timer(&link->timer, jiffies + time)) - tipc_link_get(link); + return (node_active_link(n, 0) == l) || (node_active_link(n, 1) == l); } /** @@ -224,7 +185,9 @@ static void link_set_timer(struct tipc_link *link, unsigned long time) */ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, struct tipc_bearer *b_ptr, - const struct tipc_media_addr *media_addr) + const struct tipc_media_addr *media_addr, + struct sk_buff_head *inputq, + struct sk_buff_head *namedq) { struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); struct tipc_link *l_ptr; @@ -240,7 +203,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, return NULL; } - if (n_ptr->links[b_ptr->identity]) { + if (n_ptr->links[b_ptr->identity].link) { tipc_addr_string_fill(addr_string, n_ptr->addr); pr_err("Attempt to establish second link on <%s> to %s\n", b_ptr->name, addr_string); @@ -252,7 +215,6 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, pr_warn("Link creation failed, no memory\n"); return NULL; } - kref_init(&l_ptr->ref); l_ptr->addr = peer; if_name = strchr(b_ptr->name, ':') + 1; sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:unknown", @@ -263,10 +225,10 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, /* note: peer i/f name is updated by reset/activate message */ memcpy(&l_ptr->media_addr, media_addr, sizeof(*media_addr)); l_ptr->owner = n_ptr; - l_ptr->peer_session = INVALID_SESSION; + l_ptr->peer_session = WILDCARD_SESSION; l_ptr->bearer_id = b_ptr->identity; - link_set_supervision_props(l_ptr, b_ptr->tolerance); - l_ptr->state = RESET_UNKNOWN; + l_ptr->tolerance = b_ptr->tolerance; + l_ptr->state = TIPC_LINK_RESETTING; l_ptr->pmsg = (struct tipc_msg *)&l_ptr->proto_msg; msg = l_ptr->pmsg; @@ -286,13 +248,11 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, __skb_queue_head_init(&l_ptr->backlogq); __skb_queue_head_init(&l_ptr->deferdq); skb_queue_head_init(&l_ptr->wakeupq); - skb_queue_head_init(&l_ptr->inputq); - skb_queue_head_init(&l_ptr->namedq); + l_ptr->inputq = inputq; + l_ptr->namedq = namedq; + skb_queue_head_init(l_ptr->inputq); link_reset_statistics(l_ptr); tipc_node_attach_link(n_ptr, l_ptr); - setup_timer(&l_ptr->timer, link_timeout, (unsigned long)l_ptr); - link_state_event(l_ptr, STARTING_EVT); - return l_ptr; } @@ -303,13 +263,8 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, void tipc_link_delete(struct tipc_link *l) { tipc_link_reset(l); - if (del_timer(&l->timer)) - tipc_link_put(l); - l->flags |= LINK_STOPPED; - /* Delete link now, or when timer is finished: */ tipc_link_reset_fragments(l); tipc_node_detach_link(l->owner, l); - tipc_link_put(l); } void tipc_link_delete_list(struct net *net, unsigned int bearer_id) @@ -321,7 +276,7 @@ void tipc_link_delete_list(struct net *net, unsigned int bearer_id) rcu_read_lock(); list_for_each_entry_rcu(node, &tn->node_list, list) { tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (link) tipc_link_delete(link); tipc_node_unlock(node); @@ -329,12 +284,219 @@ void tipc_link_delete_list(struct net *net, unsigned int bearer_id) rcu_read_unlock(); } +/* tipc_link_build_bcast_sync_msg() - synchronize broadcast link endpoints. + * + * Give a newly added peer node the sequence number where it should + * start receiving and acking broadcast packets. + */ +static void tipc_link_build_bcast_sync_msg(struct tipc_link *l, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb; + struct sk_buff_head list; + + skb = tipc_msg_create(BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, + 0, l->addr, link_own_addr(l), 0, 0, 0); + if (!skb) + return; + __skb_queue_head_init(&list); + __skb_queue_tail(&list, skb); + tipc_link_xmit(l, &list, xmitq); +} + +/** + * tipc_link_fsm_evt - link finite state machine + * @l: pointer to link + * @evt: state machine event to be processed + * @xmitq: queue to prepend created protocol message, if any + */ +static int tipc_link_fsm_evt(struct tipc_link *l, int evt, + struct sk_buff_head *xmitq) +{ + int mtyp = 0, rc = 0; + struct tipc_link *pl; + enum { + LINK_RESET = 1, + LINK_ACTIVATE = (1 << 1), + SND_PROBE = (1 << 2), + SND_STATE = (1 << 3), + SND_RESET = (1 << 4), + SND_ACTIVATE = (1 << 5), + SND_BCAST_SYNC = (1 << 6) + } actions = 0; + + if (l->exec_mode == TIPC_LINK_BLOCKED) + return rc; + + switch (l->state) { + case TIPC_LINK_WORKING: + switch (evt) { + case TRAFFIC_EVT: + case ACTIVATE_EVT: + break; + case SILENCE_EVT: + l->state = TIPC_LINK_PROBING; + actions |= SND_PROBE; + break; + case PEER_RESET_EVT: + actions |= LINK_RESET | SND_ACTIVATE; + break; + default: + pr_debug("%s%u WORKING\n", link_unk_evt, evt); + } + break; + case TIPC_LINK_PROBING: + switch (evt) { + case TRAFFIC_EVT: + case ACTIVATE_EVT: + l->state = TIPC_LINK_WORKING; + break; + case PEER_RESET_EVT: + actions |= LINK_RESET | SND_ACTIVATE; + break; + case SILENCE_EVT: + if (l->silent_intv_cnt <= l->abort_limit) { + actions |= SND_PROBE; + break; + } + actions |= LINK_RESET | SND_RESET; + break; + default: + pr_err("%s%u PROBING\n", link_unk_evt, evt); + } + break; + case TIPC_LINK_RESETTING: + switch (evt) { + case TRAFFIC_EVT: + break; + case ACTIVATE_EVT: + pl = node_active_link(l->owner, 0); + if (pl && link_probing(pl)) + break; + actions |= LINK_ACTIVATE; + if (!l->owner->working_links) + actions |= SND_BCAST_SYNC; + break; + case PEER_RESET_EVT: + l->state = TIPC_LINK_ESTABLISHING; + actions |= SND_ACTIVATE; + break; + case SILENCE_EVT: + actions |= SND_RESET; + break; + default: + pr_err("%s%u in RESETTING\n", link_unk_evt, evt); + } + break; + case TIPC_LINK_ESTABLISHING: + switch (evt) { + case TRAFFIC_EVT: + case ACTIVATE_EVT: + pl = node_active_link(l->owner, 0); + if (pl && link_probing(pl)) + break; + actions |= LINK_ACTIVATE; + if (!l->owner->working_links) + actions |= SND_BCAST_SYNC; + break; + case PEER_RESET_EVT: + break; + case SILENCE_EVT: + actions |= SND_ACTIVATE; + break; + default: + pr_err("%s%u ESTABLISHING\n", link_unk_evt, evt); + } + break; + default: + pr_err("Unknown link state %u/%u\n", l->state, evt); + } + + /* Perform actions as decided by FSM */ + if (actions & LINK_RESET) { + l->exec_mode = TIPC_LINK_BLOCKED; + rc |= TIPC_LINK_DOWN_EVT; + } + if (actions & LINK_ACTIVATE) { + l->exec_mode = TIPC_LINK_OPEN; + rc |= TIPC_LINK_UP_EVT; + } + if (actions & (SND_STATE | SND_PROBE)) + mtyp = STATE_MSG; + if (actions & SND_RESET) + mtyp = RESET_MSG; + if (actions & SND_ACTIVATE) + mtyp = ACTIVATE_MSG; + if (actions & (SND_PROBE | SND_STATE | SND_RESET | SND_ACTIVATE)) + tipc_link_build_proto_msg(l, mtyp, actions & SND_PROBE, + 0, 0, 0, xmitq); + if (actions & SND_BCAST_SYNC) + tipc_link_build_bcast_sync_msg(l, xmitq); + return rc; +} + +/* link_profile_stats - update statistical profiling of traffic + */ +static void link_profile_stats(struct tipc_link *l) +{ + struct sk_buff *skb; + struct tipc_msg *msg; + int length; + + /* Update counters used in statistical profiling of send traffic */ + l->stats.accu_queue_sz += skb_queue_len(&l->transmq); + l->stats.queue_sz_counts++; + + skb = skb_peek(&l->transmq); + if (!skb) + return; + msg = buf_msg(skb); + length = msg_size(msg); + + if (msg_user(msg) == MSG_FRAGMENTER) { + if (msg_type(msg) != FIRST_FRAGMENT) + return; + length = msg_size(msg_get_wrapped(msg)); + } + l->stats.msg_lengths_total += length; + l->stats.msg_length_counts++; + if (length <= 64) + l->stats.msg_length_profile[0]++; + else if (length <= 256) + l->stats.msg_length_profile[1]++; + else if (length <= 1024) + l->stats.msg_length_profile[2]++; + else if (length <= 4096) + l->stats.msg_length_profile[3]++; + else if (length <= 16384) + l->stats.msg_length_profile[4]++; + else if (length <= 32768) + l->stats.msg_length_profile[5]++; + else + l->stats.msg_length_profile[6]++; +} + +/* tipc_link_timeout - perform periodic task as instructed from node timeout + */ +int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) +{ + int rc = 0; + + link_profile_stats(l); + if (l->silent_intv_cnt) + rc = tipc_link_fsm_evt(l, SILENCE_EVT, xmitq); + else if (link_working(l) && tipc_bclink_acks_missing(l->owner)) + tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, 0, xmitq); + l->silent_intv_cnt++; + return rc; +} + /** * link_schedule_user - schedule a message sender for wakeup after congestion * @link: congested link * @list: message that was attempted sent * Create pseudo msg to send back to user when congestion abates - * Only consumes message if there is an error + * Does not consume buffer list */ static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) { @@ -347,8 +509,7 @@ static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) /* This really cannot happen... */ if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) { pr_warn("%s<%s>, send queue full", link_rst_msg, link->name); - tipc_link_reset(link); - goto err; + return -ENOBUFS; } /* Non-blocking sender: */ if (TIPC_SKB_CB(skb_peek(list))->wakeup_pending) @@ -358,15 +519,12 @@ static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, addr, addr, oport, 0, 0); if (!skb) - goto err; + return -ENOBUFS; TIPC_SKB_CB(skb)->chain_sz = skb_queue_len(list); TIPC_SKB_CB(skb)->chain_imp = imp; skb_queue_tail(&link->wakeupq, skb); link->stats.link_congs++; return -ELINKCONG; -err: - __skb_queue_purge(list); - return -ENOBUFS; } /** @@ -388,8 +546,8 @@ void link_prepare_wakeup(struct tipc_link *l) if ((pnd[imp] + l->backlog[imp].len) >= lim) break; skb_unlink(skb, &l->wakeupq); - skb_queue_tail(&l->inputq, skb); - l->owner->inputq = &l->inputq; + skb_queue_tail(l->inputq, skb); + l->owner->inputq = l->inputq; l->owner->action_flags |= TIPC_MSG_EVT; } } @@ -436,21 +594,22 @@ void tipc_link_reset(struct tipc_link *l_ptr) msg_set_session(l_ptr->pmsg, ((msg_session(l_ptr->pmsg) + 1) & 0xffff)); /* Link is down, accept any session */ - l_ptr->peer_session = INVALID_SESSION; + l_ptr->peer_session = WILDCARD_SESSION; /* Prepare for renewed mtu size negotiation */ l_ptr->mtu = l_ptr->advertised_mtu; - l_ptr->state = RESET_UNKNOWN; + l_ptr->state = TIPC_LINK_RESETTING; - if ((prev_state == RESET_UNKNOWN) || (prev_state == RESET_RESET)) + if ((prev_state == TIPC_LINK_RESETTING) || + (prev_state == TIPC_LINK_ESTABLISHING)) return; - tipc_node_link_down(l_ptr->owner, l_ptr); + tipc_node_link_down(l_ptr->owner, l_ptr->bearer_id); tipc_bearer_remove_dest(owner->net, l_ptr->bearer_id, l_ptr->addr); if (was_active_link && tipc_node_is_up(l_ptr->owner) && (pl != l_ptr)) { - l_ptr->flags |= LINK_FAILINGOVER; + l_ptr->exec_mode = TIPC_LINK_BLOCKED; l_ptr->failover_checkpt = l_ptr->rcv_nxt; pl->failover_pkts = FIRST_FAILOVER; pl->failover_checkpt = l_ptr->rcv_nxt; @@ -462,7 +621,7 @@ void tipc_link_reset(struct tipc_link *l_ptr) __skb_queue_purge(&l_ptr->transmq); __skb_queue_purge(&l_ptr->deferdq); if (!owner->inputq) - owner->inputq = &l_ptr->inputq; + owner->inputq = l_ptr->inputq; skb_queue_splice_init(&l_ptr->wakeupq, owner->inputq); if (!skb_queue_empty(owner->inputq)) owner->action_flags |= TIPC_MSG_EVT; @@ -470,173 +629,32 @@ void tipc_link_reset(struct tipc_link *l_ptr) l_ptr->reasm_buf = NULL; l_ptr->rcv_unacked = 0; l_ptr->snd_nxt = 1; + l_ptr->rcv_nxt = 1; l_ptr->silent_intv_cnt = 0; + l_ptr->stats.recv_info = 0; l_ptr->stale_count = 0; link_reset_statistics(l_ptr); } -static void link_activate(struct tipc_link *link) +void tipc_link_activate(struct tipc_link *link) { struct tipc_node *node = link->owner; link->rcv_nxt = 1; link->stats.recv_info = 1; link->silent_intv_cnt = 0; - tipc_node_link_up(node, link); + link->state = TIPC_LINK_WORKING; + link->exec_mode = TIPC_LINK_OPEN; + tipc_node_link_up(node, link->bearer_id); tipc_bearer_add_dest(node->net, link->bearer_id, link->addr); } /** - * link_state_event - link finite state machine - * @l_ptr: pointer to link - * @event: state machine event to process - */ -static void link_state_event(struct tipc_link *l_ptr, unsigned int event) -{ - struct tipc_link *other; - unsigned long timer_intv = l_ptr->keepalive_intv; - - if (l_ptr->flags & LINK_STOPPED) - return; - - if (!(l_ptr->flags & LINK_STARTED) && (event != STARTING_EVT)) - return; /* Not yet. */ - - if (l_ptr->flags & LINK_FAILINGOVER) - return; - - switch (l_ptr->state) { - case WORKING_WORKING: - switch (event) { - case TRAFFIC_MSG_EVT: - case ACTIVATE_MSG: - l_ptr->silent_intv_cnt = 0; - break; - case SILENCE_EVT: - if (!l_ptr->silent_intv_cnt) { - if (tipc_bclink_acks_missing(l_ptr->owner)) - tipc_link_proto_xmit(l_ptr, STATE_MSG, - 0, 0, 0, 0); - break; - } - l_ptr->state = WORKING_UNKNOWN; - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - break; - case RESET_MSG: - pr_debug("%s<%s>, requested by peer\n", - link_rst_msg, l_ptr->name); - tipc_link_reset(l_ptr); - l_ptr->state = RESET_RESET; - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0); - break; - default: - pr_debug("%s%u in WW state\n", link_unk_evt, event); - } - break; - case WORKING_UNKNOWN: - switch (event) { - case TRAFFIC_MSG_EVT: - case ACTIVATE_MSG: - l_ptr->state = WORKING_WORKING; - l_ptr->silent_intv_cnt = 0; - break; - case RESET_MSG: - pr_debug("%s<%s>, requested by peer while probing\n", - link_rst_msg, l_ptr->name); - tipc_link_reset(l_ptr); - l_ptr->state = RESET_RESET; - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0); - break; - case SILENCE_EVT: - if (!l_ptr->silent_intv_cnt) { - l_ptr->state = WORKING_WORKING; - if (tipc_bclink_acks_missing(l_ptr->owner)) - tipc_link_proto_xmit(l_ptr, STATE_MSG, - 0, 0, 0, 0); - } else if (l_ptr->silent_intv_cnt < - l_ptr->abort_limit) { - tipc_link_proto_xmit(l_ptr, STATE_MSG, - 1, 0, 0, 0); - } else { /* Link has failed */ - pr_debug("%s<%s>, peer not responding\n", - link_rst_msg, l_ptr->name); - tipc_link_reset(l_ptr); - l_ptr->state = RESET_UNKNOWN; - tipc_link_proto_xmit(l_ptr, RESET_MSG, - 0, 0, 0, 0); - } - break; - default: - pr_err("%s%u in WU state\n", link_unk_evt, event); - } - break; - case RESET_UNKNOWN: - switch (event) { - case TRAFFIC_MSG_EVT: - break; - case ACTIVATE_MSG: - other = l_ptr->owner->active_links[0]; - if (other && link_working_unknown(other)) - break; - l_ptr->state = WORKING_WORKING; - link_activate(l_ptr); - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - if (l_ptr->owner->working_links == 1) - tipc_link_sync_xmit(l_ptr); - break; - case RESET_MSG: - l_ptr->state = RESET_RESET; - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 1, 0, 0, 0); - break; - case STARTING_EVT: - l_ptr->flags |= LINK_STARTED; - link_set_timer(l_ptr, timer_intv); - break; - case SILENCE_EVT: - tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0); - break; - default: - pr_err("%s%u in RU state\n", link_unk_evt, event); - } - break; - case RESET_RESET: - switch (event) { - case TRAFFIC_MSG_EVT: - case ACTIVATE_MSG: - other = l_ptr->owner->active_links[0]; - if (other && link_working_unknown(other)) - break; - l_ptr->state = WORKING_WORKING; - link_activate(l_ptr); - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - if (l_ptr->owner->working_links == 1) - tipc_link_sync_xmit(l_ptr); - break; - case RESET_MSG: - break; - case SILENCE_EVT: - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0); - break; - default: - pr_err("%s%u in RR state\n", link_unk_evt, event); - } - break; - default: - pr_err("Unknown link state %u/%u\n", l_ptr->state, event); - } -} - -/** * __tipc_link_xmit(): same as tipc_link_xmit, but destlink is known & locked * @link: link to use * @list: chain of buffers containing message * - * Consumes the buffer chain, except when returning -ELINKCONG, - * since the caller then may want to make more send attempts. + * Consumes the buffer chain, except when returning an error code, * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted */ @@ -660,10 +678,9 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, if (unlikely(link->backlog[i].len >= link->backlog[i].limit)) return link_schedule_user(link, list); } - if (unlikely(msg_size(msg) > mtu)) { - __skb_queue_purge(list); + if (unlikely(msg_size(msg) > mtu)) return -EMSGSIZE; - } + /* Prepare each packet for sending, and add to relevant queue: */ while (skb_queue_len(list)) { skb = skb_peek(list); @@ -700,101 +717,90 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, return 0; } -static void skb2list(struct sk_buff *skb, struct sk_buff_head *list) -{ - skb_queue_head_init(list); - __skb_queue_tail(list, skb); -} - -static int __tipc_link_xmit_skb(struct tipc_link *link, struct sk_buff *skb) -{ - struct sk_buff_head head; - - skb2list(skb, &head); - return __tipc_link_xmit(link->owner->net, link, &head); -} - -/* tipc_link_xmit_skb(): send single buffer to destination - * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE - * messages, which will not be rejected - * The only exception is datagram messages rerouted after secondary - * lookup, which are rare and safe to dispose of anyway. - * TODO: Return real return value, and let callers use - * tipc_wait_for_sendpkt() where applicable - */ -int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, - u32 selector) -{ - struct sk_buff_head head; - int rc; - - skb2list(skb, &head); - rc = tipc_link_xmit(net, &head, dnode, selector); - if (rc == -ELINKCONG) - kfree_skb(skb); - return 0; -} - /** - * tipc_link_xmit() is the general link level function for message sending - * @net: the applicable net namespace + * tipc_link_xmit(): enqueue buffer list according to queue situation + * @link: link to use * @list: chain of buffers containing message - * @dsz: amount of user data to be sent - * @dnode: address of destination node - * @selector: a number used for deterministic link selection - * Consumes the buffer chain, except when returning -ELINKCONG - * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE + * @xmitq: returned list of packets to be sent by caller + * + * Consumes the buffer chain, except when returning -ELINKCONG, + * since the caller then may want to make more send attempts. + * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS + * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted */ -int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, - u32 selector) +int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, + struct sk_buff_head *xmitq) { - struct tipc_link *link = NULL; - struct tipc_node *node; - int rc = -EHOSTUNREACH; + struct tipc_msg *hdr = buf_msg(skb_peek(list)); + unsigned int maxwin = l->window; + unsigned int i, imp = msg_importance(hdr); + unsigned int mtu = l->mtu; + u16 ack = l->rcv_nxt - 1; + u16 seqno = l->snd_nxt; + u16 bc_last_in = l->owner->bclink.last_in; + struct sk_buff_head *transmq = &l->transmq; + struct sk_buff_head *backlogq = &l->backlogq; + struct sk_buff *skb, *_skb, *bskb; - node = tipc_node_find(net, dnode); - if (node) { - tipc_node_lock(node); - link = node->active_links[selector & 1]; - if (link) - rc = __tipc_link_xmit(net, link, list); - tipc_node_unlock(node); - tipc_node_put(node); + /* Match msg importance against this and all higher backlog limits: */ + for (i = imp; i <= TIPC_SYSTEM_IMPORTANCE; i++) { + if (unlikely(l->backlog[i].len >= l->backlog[i].limit)) + return link_schedule_user(l, list); } - if (link) - return rc; + if (unlikely(msg_size(hdr) > mtu)) + return -EMSGSIZE; - if (likely(in_own_node(net, dnode))) { - tipc_sk_rcv(net, list); - return 0; - } + /* Prepare each packet for sending, and add to relevant queue: */ + while (skb_queue_len(list)) { + skb = skb_peek(list); + hdr = buf_msg(skb); + msg_set_seqno(hdr, seqno); + msg_set_ack(hdr, ack); + msg_set_bcast_ack(hdr, bc_last_in); - __skb_queue_purge(list); - return rc; + if (likely(skb_queue_len(transmq) < maxwin)) { + _skb = skb_clone(skb, GFP_ATOMIC); + if (!_skb) + return -ENOBUFS; + __skb_dequeue(list); + __skb_queue_tail(transmq, skb); + __skb_queue_tail(xmitq, _skb); + l->rcv_unacked = 0; + seqno++; + continue; + } + if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) { + kfree_skb(__skb_dequeue(list)); + l->stats.sent_bundled++; + continue; + } + if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) { + kfree_skb(__skb_dequeue(list)); + __skb_queue_tail(backlogq, bskb); + l->backlog[msg_importance(buf_msg(bskb))].len++; + l->stats.sent_bundled++; + l->stats.sent_bundles++; + continue; + } + l->backlog[imp].len += skb_queue_len(list); + skb_queue_splice_tail_init(list, backlogq); + } + l->snd_nxt = seqno; + return 0; } -/* - * tipc_link_sync_xmit - synchronize broadcast link endpoints. - * - * Give a newly added peer node the sequence number where it should - * start receiving and acking broadcast packets. - * - * Called with node locked - */ -static void tipc_link_sync_xmit(struct tipc_link *link) +static void skb2list(struct sk_buff *skb, struct sk_buff_head *list) { - struct sk_buff *skb; - struct tipc_msg *msg; + skb_queue_head_init(list); + __skb_queue_tail(list, skb); +} - skb = tipc_buf_acquire(INT_H_SIZE); - if (!skb) - return; +static int __tipc_link_xmit_skb(struct tipc_link *link, struct sk_buff *skb) +{ + struct sk_buff_head head; - msg = buf_msg(skb); - tipc_msg_init(link_own_addr(link), msg, BCAST_PROTOCOL, STATE_MSG, - INT_H_SIZE, link->addr); - msg_set_last_bcast(msg, link->owner->bclink.acked); - __tipc_link_xmit_skb(link, skb); + skb2list(skb, &head); + return __tipc_link_xmit(link->owner->net, link, &head); } /* @@ -847,6 +853,34 @@ void tipc_link_push_packets(struct tipc_link *link) link->snd_nxt = seqno; } +void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) +{ + struct sk_buff *skb, *_skb; + struct tipc_msg *hdr; + u16 seqno = l->snd_nxt; + u16 ack = l->rcv_nxt - 1; + + while (skb_queue_len(&l->transmq) < l->window) { + skb = skb_peek(&l->backlogq); + if (!skb) + break; + _skb = skb_clone(skb, GFP_ATOMIC); + if (!_skb) + break; + __skb_dequeue(&l->backlogq); + hdr = buf_msg(skb); + l->backlog[msg_importance(hdr)].len--; + __skb_queue_tail(&l->transmq, skb); + __skb_queue_tail(xmitq, _skb); + msg_set_ack(hdr, ack); + msg_set_seqno(hdr, seqno); + msg_set_bcast_ack(hdr, l->owner->bclink.last_in); + l->rcv_unacked = 0; + seqno++; + } + l->snd_nxt = seqno; +} + void tipc_link_reset_all(struct tipc_node *node) { char addr_string[16]; @@ -858,9 +892,9 @@ void tipc_link_reset_all(struct tipc_node *node) tipc_addr_string_fill(addr_string, node->addr)); for (i = 0; i < MAX_BEARERS; i++) { - if (node->links[i]) { - link_print(node->links[i], "Resetting link\n"); - tipc_link_reset(node->links[i]); + if (node->links[i].link) { + link_print(node->links[i].link, "Resetting link\n"); + tipc_link_reset(node->links[i].link); } } @@ -877,9 +911,13 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, if (l_ptr->addr) { /* Handle failure on standard link */ - link_print(l_ptr, "Resetting link\n"); + link_print(l_ptr, "Resetting link "); + pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n", + msg_user(msg), msg_type(msg), msg_size(msg), + msg_errcode(msg)); + pr_info("sqno %u, prev: %x, src: %x\n", + msg_seqno(msg), msg_prevnode(msg), msg_orignode(msg)); tipc_link_reset(l_ptr); - } else { /* Handle failure on broadcast link */ struct tipc_node *n_ptr; @@ -940,6 +978,41 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *skb, } } +static int tipc_link_retransm(struct tipc_link *l, int retransm, + struct sk_buff_head *xmitq) +{ + struct sk_buff *_skb, *skb = skb_peek(&l->transmq); + struct tipc_msg *hdr; + + if (!skb) + return 0; + + /* Detect repeated retransmit failures on same packet */ + if (likely(l->last_retransm != buf_seqno(skb))) { + l->last_retransm = buf_seqno(skb); + l->stale_count = 1; + } else if (++l->stale_count > 100) { + link_retransmit_failure(l, skb); + return TIPC_LINK_DOWN_EVT; + } + skb_queue_walk(&l->transmq, skb) { + if (!retransm) + return 0; + hdr = buf_msg(skb); + _skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC); + if (!_skb) + return 0; + hdr = buf_msg(_skb); + msg_set_ack(hdr, l->rcv_nxt - 1); + msg_set_bcast_ack(hdr, l->owner->bclink.last_in); + _skb->priority = TC_PRIO_CONTROL; + __skb_queue_tail(xmitq, _skb); + retransm--; + l->stats.retransmitted++; + } + return 0; +} + /* link_synch(): check if all packets arrived before the synch * point have been consumed * Returns true if the parallel links are synched, otherwise false @@ -959,168 +1032,13 @@ static bool link_synch(struct tipc_link *l) /* Is it still in the input queue ? */ post_synch = mod(pl->rcv_nxt - l->synch_point) - 1; - if (skb_queue_len(&pl->inputq) > post_synch) + if (skb_queue_len(pl->inputq) > post_synch) return false; synched: - l->flags &= ~LINK_SYNCHING; + l->exec_mode = TIPC_LINK_OPEN; return true; } -static void link_retrieve_defq(struct tipc_link *link, - struct sk_buff_head *list) -{ - u16 seq_no; - - if (skb_queue_empty(&link->deferdq)) - return; - - seq_no = buf_seqno(skb_peek(&link->deferdq)); - if (seq_no == link->rcv_nxt) - skb_queue_splice_tail_init(&link->deferdq, list); -} - -/** - * tipc_rcv - process TIPC packets/messages arriving from off-node - * @net: the applicable net namespace - * @skb: TIPC packet - * @b_ptr: pointer to bearer message arrived on - * - * Invoked with no locks held. Bearer pointer must point to a valid bearer - * structure (i.e. cannot be NULL), but bearer can be inactive. - */ -void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct sk_buff_head head; - struct tipc_node *n_ptr; - struct tipc_link *l_ptr; - struct sk_buff *skb1, *tmp; - struct tipc_msg *msg; - u16 seq_no; - u16 ackd; - u32 released; - - skb2list(skb, &head); - - while ((skb = __skb_dequeue(&head))) { - /* Ensure message is well-formed */ - if (unlikely(!tipc_msg_validate(skb))) - goto discard; - - /* Handle arrival of a non-unicast link message */ - msg = buf_msg(skb); - if (unlikely(msg_non_seq(msg))) { - if (msg_user(msg) == LINK_CONFIG) - tipc_disc_rcv(net, skb, b_ptr); - else - tipc_bclink_rcv(net, skb); - continue; - } - - /* Discard unicast link messages destined for another node */ - if (unlikely(!msg_short(msg) && - (msg_destnode(msg) != tn->own_addr))) - goto discard; - - /* Locate neighboring node that sent message */ - n_ptr = tipc_node_find(net, msg_prevnode(msg)); - if (unlikely(!n_ptr)) - goto discard; - - tipc_node_lock(n_ptr); - /* Locate unicast link endpoint that should handle message */ - l_ptr = n_ptr->links[b_ptr->identity]; - if (unlikely(!l_ptr)) - goto unlock; - - /* Verify that communication with node is currently allowed */ - if ((n_ptr->action_flags & TIPC_WAIT_PEER_LINKS_DOWN) && - msg_user(msg) == LINK_PROTOCOL && - (msg_type(msg) == RESET_MSG || - msg_type(msg) == ACTIVATE_MSG) && - !msg_redundant_link(msg)) - n_ptr->action_flags &= ~TIPC_WAIT_PEER_LINKS_DOWN; - - if (tipc_node_blocked(n_ptr)) - goto unlock; - - /* Validate message sequence number info */ - seq_no = msg_seqno(msg); - ackd = msg_ack(msg); - - /* Release acked messages */ - if (unlikely(n_ptr->bclink.acked != msg_bcast_ack(msg))) - tipc_bclink_acknowledge(n_ptr, msg_bcast_ack(msg)); - - released = 0; - skb_queue_walk_safe(&l_ptr->transmq, skb1, tmp) { - if (more(buf_seqno(skb1), ackd)) - break; - __skb_unlink(skb1, &l_ptr->transmq); - kfree_skb(skb1); - released = 1; - } - - /* Try sending any messages link endpoint has pending */ - if (unlikely(skb_queue_len(&l_ptr->backlogq))) - tipc_link_push_packets(l_ptr); - - if (released && !skb_queue_empty(&l_ptr->wakeupq)) - link_prepare_wakeup(l_ptr); - - /* Process the incoming packet */ - if (unlikely(!link_working_working(l_ptr))) { - if (msg_user(msg) == LINK_PROTOCOL) { - tipc_link_proto_rcv(l_ptr, skb); - link_retrieve_defq(l_ptr, &head); - skb = NULL; - goto unlock; - } - - /* Traffic message. Conditionally activate link */ - link_state_event(l_ptr, TRAFFIC_MSG_EVT); - - if (link_working_working(l_ptr)) { - /* Re-insert buffer in front of queue */ - __skb_queue_head(&head, skb); - skb = NULL; - goto unlock; - } - goto unlock; - } - - /* Link is now in state WORKING_WORKING */ - if (unlikely(seq_no != l_ptr->rcv_nxt)) { - link_handle_out_of_seq_msg(l_ptr, skb); - link_retrieve_defq(l_ptr, &head); - skb = NULL; - goto unlock; - } - l_ptr->silent_intv_cnt = 0; - - /* Synchronize with parallel link if applicable */ - if (unlikely((l_ptr->flags & LINK_SYNCHING) && !msg_dup(msg))) { - if (!link_synch(l_ptr)) - goto unlock; - } - l_ptr->rcv_nxt++; - if (unlikely(!skb_queue_empty(&l_ptr->deferdq))) - link_retrieve_defq(l_ptr, &head); - if (unlikely(++l_ptr->rcv_unacked >= TIPC_MIN_LINK_WIN)) { - l_ptr->stats.sent_acks++; - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0); - } - tipc_link_input(l_ptr, skb); - skb = NULL; -unlock: - tipc_node_unlock(n_ptr); - tipc_node_put(n_ptr); -discard: - if (unlikely(skb)) - kfree_skb(skb); - } -} - /* tipc_data_input - deliver data and name distr msgs to upper layer * * Consumes buffer if message is of right type @@ -1138,16 +1056,16 @@ static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb) case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: case CONN_MANAGER: - if (tipc_skb_queue_tail(&link->inputq, skb, dport)) { - node->inputq = &link->inputq; + if (tipc_skb_queue_tail(link->inputq, skb, dport)) { + node->inputq = link->inputq; node->action_flags |= TIPC_MSG_EVT; } return true; case NAME_DISTRIBUTOR: node->bclink.recv_permitted = true; - node->namedq = &link->namedq; - skb_queue_tail(&link->namedq, skb); - if (skb_queue_len(&link->namedq) == 1) + node->namedq = link->namedq; + skb_queue_tail(link->namedq, skb); + if (skb_queue_len(link->namedq) == 1) node->action_flags |= TIPC_NAMED_MSG_EVT; return true; case MSG_BUNDLER: @@ -1174,13 +1092,10 @@ static void tipc_link_input(struct tipc_link *link, struct sk_buff *skb) struct sk_buff *iskb; int pos = 0; - if (likely(tipc_data_input(link, skb))) - return; - switch (msg_user(msg)) { case TUNNEL_PROTOCOL: if (msg_dup(msg)) { - link->flags |= LINK_SYNCHING; + link->exec_mode = TIPC_LINK_TUNNEL; link->synch_point = msg_seqno(msg_get_wrapped(msg)); kfree_skb(skb); break; @@ -1215,6 +1130,110 @@ static void tipc_link_input(struct tipc_link *link, struct sk_buff *skb) }; } +static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) +{ + bool released = false; + struct sk_buff *skb, *tmp; + + skb_queue_walk_safe(&l->transmq, skb, tmp) { + if (more(buf_seqno(skb), acked)) + break; + __skb_unlink(skb, &l->transmq); + kfree_skb(skb); + released = true; + } + return released; +} + +/* tipc_link_rcv - process TIPC packets/messages arriving from off-node + * @link: the link that should handle the message + * @skb: TIPC packet + * @xmitq: queue to place packets to be sent after this call + */ +int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq) +{ + struct sk_buff_head *arrvq = &l->deferdq; + struct sk_buff *tmp; + struct tipc_msg *hdr; + u16 seqno, rcv_nxt; + int rc = 0; + + if (unlikely(!__tipc_skb_queue_sorted(arrvq, skb))) { + if (!(skb_queue_len(arrvq) % TIPC_NACK_INTV)) + tipc_link_build_proto_msg(l, STATE_MSG, 0, + 0, 0, 0, xmitq); + return rc; + } + + skb_queue_walk_safe(arrvq, skb, tmp) { + hdr = buf_msg(skb); + + /* Verify and update link state */ + if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) { + __skb_dequeue(arrvq); + rc |= tipc_link_proto_rcv(l, skb, xmitq); + continue; + } + + if (unlikely(!link_working(l))) { + rc |= tipc_link_fsm_evt(l, TRAFFIC_EVT, xmitq); + if (!link_working(l)) { + kfree_skb(__skb_dequeue(arrvq)); + return rc; + } + } + + l->silent_intv_cnt = 0; + + /* Forward queues and wake up waiting users */ + if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) { + tipc_link_advance_backlog(l, xmitq); + if (unlikely(!skb_queue_empty(&l->wakeupq))) + link_prepare_wakeup(l); + } + + /* Defer reception if there is a gap in the sequence */ + seqno = msg_seqno(hdr); + rcv_nxt = l->rcv_nxt; + if (unlikely(less(rcv_nxt, seqno))) { + l->stats.deferred_recv++; + return rc; + } + + __skb_dequeue(arrvq); + + /* Drop if packet already received */ + if (unlikely(more(rcv_nxt, seqno))) { + l->stats.duplicates++; + kfree_skb(skb); + return rc; + } + + /* Synchronize with parallel link if applicable */ + if (unlikely(l->exec_mode == TIPC_LINK_TUNNEL)) + if (!msg_dup(hdr) && !link_synch(l)) { + kfree_skb(skb); + return rc; + } + + /* Packet can be delivered */ + l->rcv_nxt++; + l->stats.recv_info++; + if (unlikely(!tipc_data_input(l, skb))) + tipc_link_input(l, skb); + + /* Ack at regular intervals */ + if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) { + l->rcv_unacked = 0; + l->stats.sent_acks++; + tipc_link_build_proto_msg(l, STATE_MSG, + 0, 0, 0, 0, xmitq); + } + } + return rc; +} + /** * tipc_link_defer_pkt - Add out-of-sequence message to deferred reception queue * @@ -1255,235 +1274,85 @@ u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *skb) } /* - * link_handle_out_of_seq_msg - handle arrival of out-of-sequence packet + * Send protocol message to the other endpoint. */ -static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, - struct sk_buff *buf) +void tipc_link_proto_xmit(struct tipc_link *l, u32 msg_typ, int probe_msg, + u32 gap, u32 tolerance, u32 priority) { - u32 seq_no = buf_seqno(buf); - - if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) { - tipc_link_proto_rcv(l_ptr, buf); - return; - } - - /* Record OOS packet arrival */ - l_ptr->silent_intv_cnt = 0; + struct sk_buff *skb = NULL; + struct sk_buff_head xmitq; - /* - * Discard packet if a duplicate; otherwise add it to deferred queue - * and notify peer of gap as per protocol specification - */ - if (less(seq_no, l_ptr->rcv_nxt)) { - l_ptr->stats.duplicates++; - kfree_skb(buf); + __skb_queue_head_init(&xmitq); + tipc_link_build_proto_msg(l, msg_typ, probe_msg, gap, + tolerance, priority, &xmitq); + skb = __skb_dequeue(&xmitq); + if (!skb) return; - } - - if (tipc_link_defer_pkt(&l_ptr->deferdq, buf)) { - l_ptr->stats.deferred_recv++; - if ((skb_queue_len(&l_ptr->deferdq) % TIPC_MIN_LINK_WIN) == 1) - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0); - } else { - l_ptr->stats.duplicates++; - } + tipc_bearer_send(l->owner->net, l->bearer_id, skb, &l->media_addr); + l->rcv_unacked = 0; + kfree_skb(skb); } -/* - * Send protocol message to the other endpoint. +/* tipc_link_build_proto_msg: prepare link protocol message for transmission */ -void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, - u32 gap, u32 tolerance, u32 priority) +static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, + u16 rcvgap, int tolerance, int priority, + struct sk_buff_head *xmitq) { - struct sk_buff *buf = NULL; - struct tipc_msg *msg = l_ptr->pmsg; - u32 msg_size = sizeof(l_ptr->proto_msg); - int r_flag; - u16 last_rcv; - - /* Don't send protocol message during link failover */ - if (l_ptr->flags & LINK_FAILINGOVER) - return; - - /* Abort non-RESET send if communication with node is prohibited */ - if ((tipc_node_blocked(l_ptr->owner)) && (msg_typ != RESET_MSG)) + struct sk_buff *skb = NULL; + struct tipc_msg *hdr = l->pmsg; + u16 snd_nxt = l->snd_nxt; + u16 rcv_nxt = l->rcv_nxt; + u16 rcv_last = rcv_nxt - 1; + int node_up = l->owner->bclink.recv_permitted; + + /* Don't send protocol message during reset or link failover */ + if (l->exec_mode == TIPC_LINK_BLOCKED) return; - /* Create protocol message with "out-of-sequence" sequence number */ - msg_set_type(msg, msg_typ); - msg_set_net_plane(msg, l_ptr->net_plane); - msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); - msg_set_last_bcast(msg, tipc_bclink_get_last_sent(l_ptr->owner->net)); + msg_set_type(hdr, mtyp); + msg_set_net_plane(hdr, l->net_plane); + msg_set_bcast_ack(hdr, l->owner->bclink.last_in); + msg_set_last_bcast(hdr, tipc_bclink_get_last_sent(l->owner->net)); + msg_set_link_tolerance(hdr, tolerance); + msg_set_linkprio(hdr, priority); + msg_set_redundant_link(hdr, node_up); + msg_set_seq_gap(hdr, 0); - if (msg_typ == STATE_MSG) { - u16 next_sent = l_ptr->snd_nxt; + /* Compatibility: created msg must not be in sequence with pkt flow */ + msg_set_seqno(hdr, snd_nxt + U16_MAX / 2); - if (!tipc_link_is_up(l_ptr)) + if (mtyp == STATE_MSG) { + if (!tipc_link_is_up(l)) return; - msg_set_next_sent(msg, next_sent); - if (!skb_queue_empty(&l_ptr->deferdq)) { - last_rcv = buf_seqno(skb_peek(&l_ptr->deferdq)); - gap = mod(last_rcv - l_ptr->rcv_nxt); + msg_set_next_sent(hdr, snd_nxt); + + /* Override rcvgap if there are packets in deferred queue */ + if (!skb_queue_empty(&l->deferdq)) + rcvgap = buf_seqno(skb_peek(&l->deferdq)) - rcv_nxt; + if (rcvgap) { + msg_set_seq_gap(hdr, rcvgap); + l->stats.sent_nacks++; } - msg_set_seq_gap(msg, gap); - if (gap) - l_ptr->stats.sent_nacks++; - msg_set_link_tolerance(msg, tolerance); - msg_set_linkprio(msg, priority); - msg_set_max_pkt(msg, l_ptr->mtu); - msg_set_ack(msg, mod(l_ptr->rcv_nxt - 1)); - msg_set_probe(msg, probe_msg != 0); - if (probe_msg) - l_ptr->stats.sent_probes++; - l_ptr->stats.sent_states++; - } else { /* RESET_MSG or ACTIVATE_MSG */ - msg_set_ack(msg, mod(l_ptr->failover_checkpt - 1)); - msg_set_seq_gap(msg, 0); - msg_set_next_sent(msg, 1); - msg_set_probe(msg, 0); - msg_set_link_tolerance(msg, l_ptr->tolerance); - msg_set_linkprio(msg, l_ptr->priority); - msg_set_max_pkt(msg, l_ptr->advertised_mtu); + msg_set_ack(hdr, rcv_last); + msg_set_probe(hdr, probe); + if (probe) + l->stats.sent_probes++; + l->stats.sent_states++; + } else { + /* RESET_MSG or ACTIVATE_MSG */ + msg_set_max_pkt(hdr, l->advertised_mtu); + msg_set_ack(hdr, l->failover_checkpt - 1); + msg_set_next_sent(hdr, 1); } - - r_flag = (l_ptr->owner->working_links > tipc_link_is_up(l_ptr)); - msg_set_redundant_link(msg, r_flag); - msg_set_linkprio(msg, l_ptr->priority); - msg_set_size(msg, msg_size); - - msg_set_seqno(msg, mod(l_ptr->snd_nxt + (0xffff / 2))); - - buf = tipc_buf_acquire(msg_size); - if (!buf) + skb = tipc_buf_acquire(msg_size(hdr)); + if (!skb) return; - - skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg)); - buf->priority = TC_PRIO_CONTROL; - tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, buf, - &l_ptr->media_addr); - l_ptr->rcv_unacked = 0; - kfree_skb(buf); + skb_copy_to_linear_data(skb, hdr, msg_size(hdr)); + skb->priority = TC_PRIO_CONTROL; + __skb_queue_head(xmitq, skb); } -/* - * Receive protocol message : - * Note that network plane id propagates through the network, and may - * change at any time. The node with lowest address rules - */ -static void tipc_link_proto_rcv(struct tipc_link *l_ptr, - struct sk_buff *buf) -{ - u32 rec_gap = 0; - u32 msg_tol; - struct tipc_msg *msg = buf_msg(buf); - - if (l_ptr->flags & LINK_FAILINGOVER) - goto exit; - - if (l_ptr->net_plane != msg_net_plane(msg)) - if (link_own_addr(l_ptr) > msg_prevnode(msg)) - l_ptr->net_plane = msg_net_plane(msg); - - switch (msg_type(msg)) { - - case RESET_MSG: - if (!link_working_unknown(l_ptr) && - (l_ptr->peer_session != INVALID_SESSION)) { - if (less_eq(msg_session(msg), l_ptr->peer_session)) - break; /* duplicate or old reset: ignore */ - } - - if (!msg_redundant_link(msg) && (link_working_working(l_ptr) || - link_working_unknown(l_ptr))) { - /* - * peer has lost contact -- don't allow peer's links - * to reactivate before we recognize loss & clean up - */ - l_ptr->owner->action_flags |= TIPC_WAIT_OWN_LINKS_DOWN; - } - - link_state_event(l_ptr, RESET_MSG); - - /* fall thru' */ - case ACTIVATE_MSG: - /* Update link settings according other endpoint's values */ - strcpy((strrchr(l_ptr->name, ':') + 1), (char *)msg_data(msg)); - - msg_tol = msg_link_tolerance(msg); - if (msg_tol > l_ptr->tolerance) - link_set_supervision_props(l_ptr, msg_tol); - - if (msg_linkprio(msg) > l_ptr->priority) - l_ptr->priority = msg_linkprio(msg); - - if (l_ptr->mtu > msg_max_pkt(msg)) - l_ptr->mtu = msg_max_pkt(msg); - - /* Synchronize broadcast link info, if not done previously */ - if (!tipc_node_is_up(l_ptr->owner)) { - l_ptr->owner->bclink.last_sent = - l_ptr->owner->bclink.last_in = - msg_last_bcast(msg); - l_ptr->owner->bclink.oos_state = 0; - } - - l_ptr->peer_session = msg_session(msg); - l_ptr->peer_bearer_id = msg_bearer_id(msg); - - if (msg_type(msg) == ACTIVATE_MSG) - link_state_event(l_ptr, ACTIVATE_MSG); - break; - case STATE_MSG: - - msg_tol = msg_link_tolerance(msg); - if (msg_tol) - link_set_supervision_props(l_ptr, msg_tol); - - if (msg_linkprio(msg) && - (msg_linkprio(msg) != l_ptr->priority)) { - pr_debug("%s<%s>, priority change %u->%u\n", - link_rst_msg, l_ptr->name, - l_ptr->priority, msg_linkprio(msg)); - l_ptr->priority = msg_linkprio(msg); - tipc_link_reset(l_ptr); /* Enforce change to take effect */ - break; - } - - /* Record reception; force mismatch at next timeout: */ - l_ptr->silent_intv_cnt = 0; - - link_state_event(l_ptr, TRAFFIC_MSG_EVT); - l_ptr->stats.recv_states++; - if (link_reset_unknown(l_ptr)) - break; - - if (less_eq(l_ptr->rcv_nxt, msg_next_sent(msg))) - rec_gap = mod(msg_next_sent(msg) - l_ptr->rcv_nxt); - - if (msg_probe(msg)) - l_ptr->stats.recv_probes++; - - /* Protocol message before retransmits, reduce loss risk */ - if (l_ptr->owner->bclink.recv_permitted) - tipc_bclink_update_link_state(l_ptr->owner, - msg_last_bcast(msg)); - - if (rec_gap || (msg_probe(msg))) { - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, - rec_gap, 0, 0); - } - if (msg_seq_gap(msg)) { - l_ptr->stats.recv_nacks++; - tipc_link_retransmit(l_ptr, skb_peek(&l_ptr->transmq), - msg_seq_gap(msg)); - } - break; - } -exit: - kfree_skb(buf); -} - - /* tipc_link_tunnel_xmit(): Tunnel one packet via a link belonging to * a different bearer. Owner node is locked. */ @@ -1496,7 +1365,7 @@ static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr, struct sk_buff *skb; u32 length = msg_size(msg); - tunnel = l_ptr->owner->active_links[selector & 1]; + tunnel = node_active_link(l_ptr->owner, selector & 1); if (!tipc_link_is_up(tunnel)) { pr_warn("%stunnel link no longer available\n", link_co_err); return; @@ -1522,7 +1391,7 @@ static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr, void tipc_link_failover_send_queue(struct tipc_link *l_ptr) { int msgcount; - struct tipc_link *tunnel = l_ptr->owner->active_links[0]; + struct tipc_link *tunnel = node_active_link(l_ptr->owner, 0); struct tipc_msg tunnel_hdr; struct sk_buff *skb; int split_bundles; @@ -1556,8 +1425,8 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) return; } - split_bundles = (l_ptr->owner->active_links[0] != - l_ptr->owner->active_links[1]); + split_bundles = (node_active_link(l_ptr->owner, 0) != + node_active_link(l_ptr->owner, 0)); skb_queue_walk(&l_ptr->transmq, skb) { struct tipc_msg *msg = buf_msg(skb); @@ -1660,7 +1529,7 @@ static bool tipc_link_failover_rcv(struct tipc_link *link, if (bearer_id == link->bearer_id) goto exit; - pl = link->owner->links[bearer_id]; + pl = link->owner->links[bearer_id].link; if (pl && tipc_link_is_up(pl)) tipc_link_reset(pl); @@ -1691,22 +1560,100 @@ static bool tipc_link_failover_rcv(struct tipc_link *link, } exit: if (!link->failover_pkts && pl) - pl->flags &= ~LINK_FAILINGOVER; + pl->exec_mode = TIPC_LINK_OPEN; kfree_skb(*skb); *skb = iskb; return *skb; } -static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol) +/* tipc_link_proto_rcv(): receive link level protocol message : + * Note that network plane id propagates through the network, and may + * change at any time. The node with lowest numerical id determines + * network plane + */ +static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq) { - unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4; + struct tipc_msg *hdr = buf_msg(skb); + u16 rcvgap = 0; + u16 nacked_gap = msg_seq_gap(hdr); + u16 peers_snd_nxt = msg_next_sent(hdr); + u16 peers_tol = msg_link_tolerance(hdr); + u16 peers_prio = msg_linkprio(hdr); + char *if_name; + int rc = 0; - if ((tol < TIPC_MIN_LINK_TOL) || (tol > TIPC_MAX_LINK_TOL)) - return; + if (l->exec_mode == TIPC_LINK_BLOCKED) + goto exit; + + if (link_own_addr(l) > msg_prevnode(hdr)) + l->net_plane = msg_net_plane(hdr); + + switch (msg_type(hdr)) { + case RESET_MSG: + + /* Ignore duplicate RESET with old session number */ + if ((less_eq(msg_session(hdr), l->peer_session)) && + (l->peer_session != WILDCARD_SESSION)) + break; + /* fall thru' */ + case ACTIVATE_MSG: + + /* Complete own link name with peer's interface name */ + if_name = strrchr(l->name, ':') + 1; + if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) + break; + if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME) + break; + strncpy(if_name, msg_data(hdr), TIPC_MAX_IF_NAME); + + /* Update own tolerance if peer indicates a non-zero value */ + if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) + l->tolerance = peers_tol; - l_ptr->tolerance = tol; - l_ptr->keepalive_intv = msecs_to_jiffies(intv); - l_ptr->abort_limit = tol / (jiffies_to_msecs(l_ptr->keepalive_intv)); + /* Update own priority if peer's priority is higher */ + if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) + l->priority = peers_prio; + + l->peer_session = msg_session(hdr); + l->peer_bearer_id = msg_bearer_id(hdr); + rc = tipc_link_fsm_evt(l, msg_type(hdr), xmitq); + if (l->mtu > msg_max_pkt(hdr)) + l->mtu = msg_max_pkt(hdr); + break; + case STATE_MSG: + /* Update own tolerance if peer indicates a non-zero value */ + if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) + l->tolerance = peers_tol; + + l->silent_intv_cnt = 0; + l->stats.recv_states++; + if (msg_probe(hdr)) + l->stats.recv_probes++; + rc = tipc_link_fsm_evt(l, TRAFFIC_EVT, xmitq); + if (!tipc_link_is_up(l)) + break; + + /* Has peer sent packets we haven't received yet ? */ + if (more(peers_snd_nxt, l->rcv_nxt)) + rcvgap = peers_snd_nxt - l->rcv_nxt; + if (rcvgap || (msg_probe(hdr))) + tipc_link_build_proto_msg(l, STATE_MSG, 0, rcvgap, + 0, 0, xmitq); + tipc_link_release_pkts(l, msg_ack(hdr)); + + /* If NACK, retransmit will now start at right position */ + if (nacked_gap) { + rc |= tipc_link_retransm(l, nacked_gap, xmitq); + l->stats.recv_nacks++; + } + tipc_link_advance_backlog(l, xmitq); + if (unlikely(!skb_queue_empty(&l->wakeupq))) + link_prepare_wakeup(l); + } +exit: + kfree_skb(skb); + return rc; } void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) @@ -1743,7 +1690,7 @@ static struct tipc_node *tipc_link_find_owner(struct net *net, list_for_each_entry_rcu(n_ptr, &tn->node_list, list) { tipc_node_lock(n_ptr); for (i = 0; i < MAX_BEARERS; i++) { - l_ptr = n_ptr->links[i]; + l_ptr = n_ptr->links[i].link; if (l_ptr && !strcmp(l_ptr->name, link_name)) { *bearer_id = i; found_node = n_ptr; @@ -1770,27 +1717,28 @@ static void link_reset_statistics(struct tipc_link *l_ptr) l_ptr->stats.recv_info = l_ptr->rcv_nxt; } -static void link_print(struct tipc_link *l_ptr, const char *str) +static void link_print(struct tipc_link *l, const char *str) { - struct tipc_net *tn = net_generic(l_ptr->owner->net, tipc_net_id); - struct tipc_bearer *b_ptr; - - rcu_read_lock(); - b_ptr = rcu_dereference_rtnl(tn->bearer_list[l_ptr->bearer_id]); - if (b_ptr) - pr_info("%s Link %x<%s>:", str, l_ptr->addr, b_ptr->name); - rcu_read_unlock(); - - if (link_working_unknown(l_ptr)) - pr_cont(":WU\n"); - else if (link_reset_reset(l_ptr)) - pr_cont(":RR\n"); - else if (link_reset_unknown(l_ptr)) - pr_cont(":RU\n"); - else if (link_working_working(l_ptr)) - pr_cont(":WW\n"); + struct sk_buff *hskb = skb_peek(&l->transmq); + u16 head = hskb ? msg_seqno(buf_msg(hskb)) : l->snd_nxt; + u16 tail = l->snd_nxt - 1; + + pr_info("%s Link <%s>:", str, l->name); + + if (link_probing(l)) + pr_cont(":P\n"); + else if (link_establishing(l)) + pr_cont(":E\n"); + else if (link_resetting(l)) + pr_cont(":R\n"); + else if (link_working(l)) + pr_cont(":W\n"); else pr_cont("\n"); + + pr_info("XMTQ: %u [%u-%u], BKLGQ: %u, SNDNX: %u, RCVNX: %u\n", + skb_queue_len(&l->transmq), head, tail, + skb_queue_len(&l->backlogq), l->snd_nxt, l->rcv_nxt); } /* Parse and validate nested (link) properties valid for media, bearer and link @@ -1865,7 +1813,7 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info) tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (!link) { res = -EINVAL; goto out; @@ -1885,7 +1833,7 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info) u32 tol; tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]); - link_set_supervision_props(link, tol); + link->tolerance = tol; tipc_link_proto_xmit(link, STATE_MSG, 0, 0, tol, 0); } if (props[TIPC_NLA_PROP_PRIO]) { @@ -2055,10 +2003,11 @@ static int __tipc_nl_add_node_links(struct net *net, struct tipc_nl_msg *msg, for (i = *prev_link; i < MAX_BEARERS; i++) { *prev_link = i; - if (!node->links[i]) + if (!node->links[i].link) continue; - err = __tipc_nl_add_link(net, msg, node->links[i], NLM_F_MULTI); + err = __tipc_nl_add_link(net, msg, + node->links[i].link, NLM_F_MULTI); if (err) return err; } @@ -2172,7 +2121,7 @@ int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info) return -EINVAL; tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (!link) { tipc_node_unlock(node); nlmsg_free(msg.skb); @@ -2227,7 +2176,7 @@ int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info) tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (!link) { tipc_node_unlock(node); return -EINVAL; diff --git a/net/tipc/link.h b/net/tipc/link.h index ae0a0ea572f2..37cfd7d7bf7d 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -49,19 +49,21 @@ */ #define INVALID_LINK_SEQ 0x10000 -/* Link working states + +/* Link endpoint receive states */ -#define WORKING_WORKING 560810u -#define WORKING_UNKNOWN 560811u -#define RESET_UNKNOWN 560812u -#define RESET_RESET 560813u +enum { + TIPC_LINK_OPEN, + TIPC_LINK_BLOCKED, + TIPC_LINK_TUNNEL +}; -/* Link endpoint execution states +/* Events returned from link at packet reception or at timeout */ -#define LINK_STARTED 0x0001 -#define LINK_STOPPED 0x0002 -#define LINK_SYNCHING 0x0004 -#define LINK_FAILINGOVER 0x0008 +enum { + TIPC_LINK_UP_EVT = 1, + TIPC_LINK_DOWN_EVT = (1 << 1) +}; /* Starting value for maximum packet size negotiation on unicast links * (unless bearer MTU is less) @@ -106,7 +108,6 @@ struct tipc_stats { * @timer: link timer * @owner: pointer to peer node * @refcnt: reference counter for permanent references (owner node & timer) - * @flags: execution state flags for link endpoint instance * @peer_session: link session # being used by peer end of link * @peer_bearer_id: bearer id used by link's peer endpoint * @bearer_id: local bearer id used by link @@ -119,6 +120,7 @@ struct tipc_stats { * @pmsg: convenience pointer to "proto_msg" field * @priority: current link priority * @net_plane: current link network plane ('A' through 'H') + * @exec_mode: transmit/receive mode for link endpoint instance * @backlog_limit: backlog queue congestion thresholds (indexed by importance) * @exp_msg_count: # of tunnelled messages expected during link changeover * @reset_rcv_checkpt: seq # of last acknowledged message at time of link reset @@ -144,12 +146,9 @@ struct tipc_link { u32 addr; char name[TIPC_MAX_LINK_NAME]; struct tipc_media_addr media_addr; - struct timer_list timer; struct tipc_node *owner; - struct kref ref; /* Management and link supervision data */ - unsigned int flags; u32 peer_session; u32 peer_bearer_id; u32 bearer_id; @@ -165,6 +164,7 @@ struct tipc_link { struct tipc_msg *pmsg; u32 priority; char net_plane; + u8 exec_mode; u16 synch_point; /* Failover */ @@ -192,8 +192,8 @@ struct tipc_link { u16 rcv_nxt; u32 rcv_unacked; struct sk_buff_head deferdq; - struct sk_buff_head inputq; - struct sk_buff_head namedq; + struct sk_buff_head *inputq; + struct sk_buff_head *namedq; /* Congestion handling */ struct sk_buff_head wakeupq; @@ -207,9 +207,11 @@ struct tipc_link { struct tipc_port; -struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, - struct tipc_bearer *b_ptr, - const struct tipc_media_addr *media_addr); +struct tipc_link *tipc_link_create(struct tipc_node *n, + struct tipc_bearer *b, + const struct tipc_media_addr *maddr, + struct sk_buff_head *inputq, + struct sk_buff_head *namedq); void tipc_link_delete(struct tipc_link *link); void tipc_link_delete_list(struct net *net, unsigned int bearer_id); void tipc_link_failover_send_queue(struct tipc_link *l_ptr); @@ -221,12 +223,11 @@ void tipc_link_purge_queues(struct tipc_link *l_ptr); void tipc_link_purge_backlog(struct tipc_link *l); void tipc_link_reset_all(struct tipc_node *node); void tipc_link_reset(struct tipc_link *l_ptr); -int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, - u32 selector); -int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dest, - u32 selector); +void tipc_link_activate(struct tipc_link *link); int __tipc_link_xmit(struct net *net, struct tipc_link *link, struct sk_buff_head *list); +int tipc_link_xmit(struct tipc_link *link, struct sk_buff_head *list, + struct sk_buff_head *xmitq); void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob, u32 gap, u32 tolerance, u32 priority); void tipc_link_push_packets(struct tipc_link *l_ptr); @@ -243,33 +244,12 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info); int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info); int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]); void link_prepare_wakeup(struct tipc_link *l); - +int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq); +int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq); static inline u32 link_own_addr(struct tipc_link *l) { return msg_prevnode(l->pmsg); } -/* - * Link status checking routines - */ -static inline int link_working_working(struct tipc_link *l_ptr) -{ - return l_ptr->state == WORKING_WORKING; -} - -static inline int link_working_unknown(struct tipc_link *l_ptr) -{ - return l_ptr->state == WORKING_UNKNOWN; -} - -static inline int link_reset_unknown(struct tipc_link *l_ptr) -{ - return l_ptr->state == RESET_UNKNOWN; -} - -static inline int link_reset_reset(struct tipc_link *l_ptr) -{ - return l_ptr->state == RESET_RESET; -} - #endif diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 19c45fb66238..2f1563b47e24 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -38,6 +38,7 @@ #define _TIPC_MSG_H #include <linux/tipc.h> +#include "core.h" /* * Constants and routines used to read and write TIPC payload message headers @@ -658,12 +659,12 @@ static inline void msg_set_link_selector(struct tipc_msg *m, u32 n) /* * Word 5 */ -static inline u32 msg_session(struct tipc_msg *m) +static inline u16 msg_session(struct tipc_msg *m) { return msg_bits(m, 5, 16, 0xffff); } -static inline void msg_set_session(struct tipc_msg *m, u32 n) +static inline void msg_set_session(struct tipc_msg *m, u16 n) { msg_set_bits(m, 5, 16, 0xffff, n); } @@ -766,6 +767,22 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } +static inline bool msg_is_traffic(struct tipc_msg *m) +{ + if (likely(msg_user(m) != LINK_PROTOCOL)) + return true; + if ((msg_type(m) == RESET_MSG) || (msg_type(m) == ACTIVATE_MSG)) + return false; + return true; +} + +static inline bool msg_peer_is_up(struct tipc_msg *m) +{ + if (likely(msg_is_traffic(m))) + return false; + return msg_redundant_link(m); +} + struct sk_buff *tipc_buf_acquire(u32 size); bool tipc_msg_validate(struct sk_buff *skb); bool tipc_msg_reverse(u32 own_addr, struct sk_buff *buf, u32 *dnode, @@ -879,4 +896,36 @@ static inline bool tipc_skb_queue_tail(struct sk_buff_head *list, return rv; } +/* tipc_skb_queue_sorted(); sort pkt into list according to sequence number + * @list: list to be appended to + * @skb: buffer to add + * Returns true if queue should treated further, otherwise false + */ +static inline bool __tipc_skb_queue_sorted(struct sk_buff_head *list, + struct sk_buff *skb) +{ + struct sk_buff *_skb, *tmp; + struct tipc_msg *hdr = buf_msg(skb); + u16 seqno = msg_seqno(hdr); + + if (skb_queue_empty(list) || (msg_user(hdr) == LINK_PROTOCOL)) { + __skb_queue_head(list, skb); + return true; + } + if (likely(less(seqno, buf_seqno(skb_peek(list))))) { + __skb_queue_head(list, skb); + return true; + } + if (!more(seqno, buf_seqno(skb_peek_tail(list)))) { + skb_queue_walk_safe(list, _skb, tmp) { + if (likely(less(seqno, buf_seqno(_skb)))) { + __skb_queue_before(list, _skb, skb); + return true; + } + } + } + __skb_queue_tail(list, skb); + return false; +} + #endif diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 41e7b7e4dda0..e6018b7eb197 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -96,13 +96,13 @@ void named_cluster_distribute(struct net *net, struct sk_buff *skb) dnode = node->addr; if (in_own_node(net, dnode)) continue; - if (!tipc_node_active_links(node)) + if (!tipc_node_is_up(node)) continue; oskb = pskb_copy(skb, GFP_ATOMIC); if (!oskb) break; msg_set_destnode(buf_msg(oskb), dnode); - tipc_link_xmit_skb(net, oskb, dnode, dnode); + tipc_node_xmit_skb(net, oskb, dnode, dnode); } rcu_read_unlock(); @@ -223,7 +223,7 @@ void tipc_named_node_up(struct net *net, u32 dnode) &tn->nametbl->publ_list[TIPC_ZONE_SCOPE]); rcu_read_unlock(); - tipc_link_xmit(net, &head, dnode, dnode); + tipc_node_xmit(net, &head, dnode, dnode); } static void tipc_publ_subscribe(struct net *net, struct publication *publ, diff --git a/net/tipc/node.c b/net/tipc/node.c index 0b1d61a5f853..e92f84afbf95 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -40,10 +40,13 @@ #include "name_distr.h" #include "socket.h" #include "bcast.h" +#include "discover.h" static void node_lost_contact(struct tipc_node *n_ptr); static void node_established_contact(struct tipc_node *n_ptr); static void tipc_node_delete(struct tipc_node *node); +static void tipc_node_timeout(unsigned long data); +static void tipc_node_fsm_evt(struct tipc_node *n, int evt); struct tipc_sock_conn { u32 port; @@ -132,6 +135,7 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) INIT_LIST_HEAD(&n_ptr->list); INIT_LIST_HEAD(&n_ptr->publ_list); INIT_LIST_HEAD(&n_ptr->conn_sks); + skb_queue_head_init(&n_ptr->bclink.namedq); __skb_queue_head_init(&n_ptr->bclink.deferdq); hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]); list_for_each_entry_rcu(temp_node, &tn->node_list, list) { @@ -139,14 +143,32 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) break; } list_add_tail_rcu(&n_ptr->list, &temp_node->list); - n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN; + n_ptr->state = SELF_DOWN_PEER_LEAVING; n_ptr->signature = INVALID_NODE_SIG; + n_ptr->active_links[0] = INVALID_BEARER_ID; + n_ptr->active_links[1] = INVALID_BEARER_ID; tipc_node_get(n_ptr); + setup_timer(&n_ptr->timer, tipc_node_timeout, (unsigned long)n_ptr); + n_ptr->keepalive_intv = U32_MAX; exit: spin_unlock_bh(&tn->node_list_lock); return n_ptr; } +static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l) +{ + unsigned long tol = l->tolerance; + unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4; + unsigned long keepalive_intv = msecs_to_jiffies(intv); + + /* Link with lowest tolerance determines timer interval */ + if (keepalive_intv < n->keepalive_intv) + n->keepalive_intv = keepalive_intv; + + /* Ensure link's abort limit corresponds to current interval */ + l->abort_limit = l->tolerance / jiffies_to_msecs(n->keepalive_intv); +} + static void tipc_node_delete(struct tipc_node *node) { list_del_rcu(&node->list); @@ -160,8 +182,11 @@ void tipc_node_stop(struct net *net) struct tipc_node *node, *t_node; spin_lock_bh(&tn->node_list_lock); - list_for_each_entry_safe(node, t_node, &tn->node_list, list) + list_for_each_entry_safe(node, t_node, &tn->node_list, list) { + if (del_timer(&node->timer)) + tipc_node_put(node); tipc_node_put(node); + } spin_unlock_bh(&tn->node_list_lock); } @@ -219,131 +244,170 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) tipc_node_put(node); } +/* tipc_node_timeout - handle expiration of node timer + */ +static void tipc_node_timeout(unsigned long data) +{ + struct tipc_node *n = (struct tipc_node *)data; + struct sk_buff_head xmitq; + struct tipc_link *l; + struct tipc_media_addr *maddr; + int bearer_id; + int rc = 0; + + __skb_queue_head_init(&xmitq); + + for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { + tipc_node_lock(n); + l = n->links[bearer_id].link; + if (l) { + /* Link tolerance may change asynchronously: */ + tipc_node_calculate_timer(n, l); + rc = tipc_link_timeout(l, &xmitq); + if (rc & TIPC_LINK_DOWN_EVT) + tipc_link_reset(l); + } + tipc_node_unlock(n); + maddr = &n->links[bearer_id].maddr; + tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr); + } + if (!mod_timer(&n->timer, jiffies + n->keepalive_intv)) + tipc_node_get(n); + tipc_node_put(n); +} + /** * tipc_node_link_up - handle addition of link * * Link becomes active (alone or shared) or standby, depending on its priority. */ -void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) +void tipc_node_link_up(struct tipc_node *n, int bearer_id) { - struct tipc_link **active = &n_ptr->active_links[0]; + int *slot0 = &n->active_links[0]; + int *slot1 = &n->active_links[1]; + struct tipc_link_entry *links = n->links; + struct tipc_link *l = n->links[bearer_id].link; - n_ptr->working_links++; - n_ptr->action_flags |= TIPC_NOTIFY_LINK_UP; - n_ptr->link_id = l_ptr->peer_bearer_id << 16 | l_ptr->bearer_id; + /* Leave room for tunnel header when returning 'mtu' to users: */ + links[bearer_id].mtu = l->mtu - INT_H_SIZE; + + n->working_links++; + n->action_flags |= TIPC_NOTIFY_LINK_UP; + n->link_id = l->peer_bearer_id << 16 | l->bearer_id; pr_debug("Established link <%s> on network plane %c\n", - l_ptr->name, l_ptr->net_plane); + l->name, l->net_plane); - if (!active[0]) { - active[0] = active[1] = l_ptr; - node_established_contact(n_ptr); - goto exit; + /* No active links ? => take both active slots */ + if (*slot0 < 0) { + *slot0 = bearer_id; + *slot1 = bearer_id; + node_established_contact(n); + return; } - if (l_ptr->priority < active[0]->priority) { - pr_debug("New link <%s> becomes standby\n", l_ptr->name); - goto exit; + + /* Lower prio than current active ? => no slot */ + if (l->priority < links[*slot0].link->priority) { + pr_debug("New link <%s> becomes standby\n", l->name); + return; } - tipc_link_dup_queue_xmit(active[0], l_ptr); - if (l_ptr->priority == active[0]->priority) { - active[0] = l_ptr; - goto exit; + tipc_link_dup_queue_xmit(links[*slot0].link, l); + + /* Same prio as current active ? => take one slot */ + if (l->priority == links[*slot0].link->priority) { + *slot0 = bearer_id; + return; } - pr_debug("Old link <%s> becomes standby\n", active[0]->name); - if (active[1] != active[0]) - pr_debug("Old link <%s> becomes standby\n", active[1]->name); - active[0] = active[1] = l_ptr; -exit: - /* Leave room for changeover header when returning 'mtu' to users: */ - n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE; - n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE; + + /* Higher prio than current active => take both active slots */ + pr_debug("Old link <%s> now standby\n", links[*slot0].link->name); + *slot0 = bearer_id; + *slot1 = bearer_id; } /** - * node_select_active_links - select active link + * tipc_node_link_down - handle loss of link */ -static void node_select_active_links(struct tipc_node *n_ptr) +void tipc_node_link_down(struct tipc_node *n, int bearer_id) { - struct tipc_link **active = &n_ptr->active_links[0]; - u32 i; - u32 highest_prio = 0; + int *slot0 = &n->active_links[0]; + int *slot1 = &n->active_links[1]; + int i, highest = 0; + struct tipc_link *l, *_l; - active[0] = active[1] = NULL; + l = n->links[bearer_id].link; + n->working_links--; + n->action_flags |= TIPC_NOTIFY_LINK_DOWN; + n->link_id = l->peer_bearer_id << 16 | l->bearer_id; - for (i = 0; i < MAX_BEARERS; i++) { - struct tipc_link *l_ptr = n_ptr->links[i]; + pr_debug("Lost link <%s> on network plane %c\n", + l->name, l->net_plane); - if (!l_ptr || !tipc_link_is_up(l_ptr) || - (l_ptr->priority < highest_prio)) + /* Select new active link if any available */ + *slot0 = INVALID_BEARER_ID; + *slot1 = INVALID_BEARER_ID; + for (i = 0; i < MAX_BEARERS; i++) { + _l = n->links[i].link; + if (!_l || !tipc_link_is_up(_l)) + continue; + if (_l->priority < highest) + continue; + if (_l->priority > highest) { + highest = _l->priority; + *slot0 = i; + *slot1 = i; continue; - - if (l_ptr->priority > highest_prio) { - highest_prio = l_ptr->priority; - active[0] = active[1] = l_ptr; - } else { - active[1] = l_ptr; } + *slot1 = i; } + if (tipc_node_is_up(n)) + tipc_link_failover_send_queue(l); + else + node_lost_contact(n); } -/** - * tipc_node_link_down - handle loss of link - */ -void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr) +bool tipc_node_is_up(struct tipc_node *n) { - struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); - struct tipc_link **active; - - n_ptr->working_links--; - n_ptr->action_flags |= TIPC_NOTIFY_LINK_DOWN; - n_ptr->link_id = l_ptr->peer_bearer_id << 16 | l_ptr->bearer_id; - - if (!tipc_link_is_active(l_ptr)) { - pr_debug("Lost standby link <%s> on network plane %c\n", - l_ptr->name, l_ptr->net_plane); - return; - } - pr_debug("Lost link <%s> on network plane %c\n", - l_ptr->name, l_ptr->net_plane); - - active = &n_ptr->active_links[0]; - if (active[0] == l_ptr) - active[0] = active[1]; - if (active[1] == l_ptr) - active[1] = active[0]; - if (active[0] == l_ptr) - node_select_active_links(n_ptr); - if (tipc_node_is_up(n_ptr)) - tipc_link_failover_send_queue(l_ptr); - else - node_lost_contact(n_ptr); - - /* Leave room for changeover header when returning 'mtu' to users: */ - if (active[0]) { - n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE; - n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE; - return; - } - /* Loopback link went down? No fragmentation needed from now on. */ - if (n_ptr->addr == tn->own_addr) { - n_ptr->act_mtus[0] = MAX_MSG_SIZE; - n_ptr->act_mtus[1] = MAX_MSG_SIZE; - } + return n->active_links[0] != INVALID_BEARER_ID; } -int tipc_node_active_links(struct tipc_node *n_ptr) +void tipc_node_check_dest(struct tipc_node *n, struct tipc_bearer *b, + bool *link_up, bool *addr_match, + struct tipc_media_addr *maddr) { - return n_ptr->active_links[0] != NULL; + struct tipc_link *l = n->links[b->identity].link; + struct tipc_media_addr *curr = &n->links[b->identity].maddr; + + *link_up = l && tipc_link_is_up(l); + *addr_match = l && !memcmp(curr, maddr, sizeof(*maddr)); } -int tipc_node_is_up(struct tipc_node *n_ptr) +bool tipc_node_update_dest(struct tipc_node *n, struct tipc_bearer *b, + struct tipc_media_addr *maddr) { - return tipc_node_active_links(n_ptr); + struct tipc_link *l = n->links[b->identity].link; + struct tipc_media_addr *curr = &n->links[b->identity].maddr; + struct sk_buff_head *inputq = &n->links[b->identity].inputq; + + if (!l) { + l = tipc_link_create(n, b, maddr, inputq, &n->bclink.namedq); + if (!l) + return false; + tipc_node_calculate_timer(n, l); + if (n->link_cnt == 1) { + if (!mod_timer(&n->timer, jiffies + n->keepalive_intv)) + tipc_node_get(n); + } + } + memcpy(&l->media_addr, maddr, sizeof(*maddr)); + memcpy(curr, maddr, sizeof(*maddr)); + tipc_link_reset(l); + return true; } void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) { - n_ptr->links[l_ptr->bearer_id] = l_ptr; + n_ptr->links[l_ptr->bearer_id].link = l_ptr; n_ptr->link_cnt++; } @@ -352,15 +416,151 @@ void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) int i; for (i = 0; i < MAX_BEARERS; i++) { - if (l_ptr != n_ptr->links[i]) + if (l_ptr != n_ptr->links[i].link) continue; - n_ptr->links[i] = NULL; + n_ptr->links[i].link = NULL; n_ptr->link_cnt--; } } +/* tipc_node_fsm_evt - node finite state machine + * Determines when contact is allowed with peer node + */ +static void tipc_node_fsm_evt(struct tipc_node *n, int evt) +{ + int state = n->state; + + switch (state) { + case SELF_DOWN_PEER_DOWN: + switch (evt) { + case SELF_ESTABL_CONTACT_EVT: + state = SELF_UP_PEER_COMING; + break; + case PEER_ESTABL_CONTACT_EVT: + state = SELF_COMING_PEER_UP; + break; + case SELF_LOST_CONTACT_EVT: + case PEER_LOST_CONTACT_EVT: + break; + default: + pr_err("Unknown node fsm evt %x/%x\n", state, evt); + } + break; + case SELF_UP_PEER_UP: + switch (evt) { + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_LEAVING; + break; + case PEER_LOST_CONTACT_EVT: + state = SELF_LEAVING_PEER_DOWN; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + break; + default: + pr_err("Unknown node fsm evt %x/%x\n", state, evt); + } + break; + case SELF_DOWN_PEER_LEAVING: + switch (evt) { + case PEER_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_DOWN; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + case SELF_LOST_CONTACT_EVT: + break; + default: + pr_err("Unknown node fsm evt %x/%x\n", state, evt); + } + break; + case SELF_UP_PEER_COMING: + switch (evt) { + case PEER_ESTABL_CONTACT_EVT: + state = SELF_UP_PEER_UP; + break; + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_LEAVING; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_LOST_CONTACT_EVT: + break; + default: + pr_err("Unknown node fsm evt %x/%x\n", state, evt); + } + break; + case SELF_COMING_PEER_UP: + switch (evt) { + case SELF_ESTABL_CONTACT_EVT: + state = SELF_UP_PEER_UP; + break; + case PEER_LOST_CONTACT_EVT: + state = SELF_LEAVING_PEER_DOWN; + break; + case SELF_LOST_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + break; + default: + pr_err("Unknown node fsm evt %x/%x\n", state, evt); + } + break; + case SELF_LEAVING_PEER_DOWN: + switch (evt) { + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_DOWN; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + case PEER_LOST_CONTACT_EVT: + break; + default: + pr_err("Unknown node fsm evt %x/%x\n", state, evt); + } + break; + default: + pr_err("Unknown node fsm state %x\n", state); + break; + } + + n->state = state; +} + +bool tipc_node_filter_skb(struct tipc_node *n, struct tipc_link *l, + struct tipc_msg *hdr) +{ + int state = n->state; + + if (likely(state == SELF_UP_PEER_UP)) + return true; + + if (state == SELF_DOWN_PEER_DOWN) + return true; + + if (state == SELF_UP_PEER_COMING) { + /* If not traffic msg, peer may still be ESTABLISHING */ + if (tipc_link_is_up(l) && msg_is_traffic(hdr)) + tipc_node_fsm_evt(n, PEER_ESTABL_CONTACT_EVT); + return true; + } + + if (state == SELF_COMING_PEER_UP) + return true; + + if (state == SELF_LEAVING_PEER_DOWN) + return false; + + if (state == SELF_DOWN_PEER_LEAVING) { + if (msg_peer_is_up(hdr)) + return false; + tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT); + return true; + } + return false; +} + static void node_established_contact(struct tipc_node *n_ptr) { + tipc_node_fsm_evt(n_ptr, SELF_ESTABL_CONTACT_EVT); n_ptr->action_flags |= TIPC_NOTIFY_NODE_UP; n_ptr->bclink.oos_state = 0; n_ptr->bclink.acked = tipc_bclink_get_last_sent(n_ptr->net); @@ -396,21 +596,18 @@ static void node_lost_contact(struct tipc_node *n_ptr) /* Abort any ongoing link failover */ for (i = 0; i < MAX_BEARERS; i++) { - struct tipc_link *l_ptr = n_ptr->links[i]; + struct tipc_link *l_ptr = n_ptr->links[i].link; if (!l_ptr) continue; - l_ptr->flags &= ~LINK_FAILINGOVER; + l_ptr->exec_mode = TIPC_LINK_OPEN; l_ptr->failover_checkpt = 0; l_ptr->failover_pkts = 0; kfree_skb(l_ptr->failover_skb); l_ptr->failover_skb = NULL; tipc_link_reset_fragments(l_ptr); } - - n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN; - /* Prevent re-contact with node until cleanup is done */ - n_ptr->action_flags |= TIPC_WAIT_PEER_LINKS_DOWN; + tipc_node_fsm_evt(n_ptr, SELF_LOST_CONTACT_EVT); /* Notify publications from this node */ n_ptr->action_flags |= TIPC_NOTIFY_NODE_DOWN; @@ -453,7 +650,7 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr, goto exit; tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (link) { strncpy(linkname, link->name, len); err = 0; @@ -559,6 +756,160 @@ msg_full: return -EMSGSIZE; } +static struct tipc_link *tipc_node_select_link(struct tipc_node *n, int sel, + int *bearer_id, + struct tipc_media_addr **maddr) +{ + int id = n->active_links[sel & 1]; + + if (unlikely(id < 0)) + return NULL; + + *bearer_id = id; + *maddr = &n->links[id].maddr; + return n->links[id].link; +} + +/** + * tipc_node_xmit() is the general link level function for message sending + * @net: the applicable net namespace + * @list: chain of buffers containing message + * @dnode: address of destination node + * @selector: a number used for deterministic link selection + * Consumes the buffer chain, except when returning -ELINKCONG + * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE + */ +int tipc_node_xmit(struct net *net, struct sk_buff_head *list, + u32 dnode, int selector) +{ + struct tipc_link *l = NULL; + struct tipc_node *n; + struct sk_buff_head xmitq; + struct tipc_media_addr *maddr; + int bearer_id; + int rc = -EHOSTUNREACH; + + __skb_queue_head_init(&xmitq); + n = tipc_node_find(net, dnode); + if (likely(n)) { + tipc_node_lock(n); + l = tipc_node_select_link(n, selector, &bearer_id, &maddr); + if (likely(l)) + rc = tipc_link_xmit(l, list, &xmitq); + if (unlikely(rc == -ENOBUFS)) + tipc_link_reset(l); + tipc_node_unlock(n); + tipc_node_put(n); + } + if (likely(!rc)) { + tipc_bearer_xmit(net, bearer_id, &xmitq, maddr); + return 0; + } + if (likely(in_own_node(net, dnode))) { + tipc_sk_rcv(net, list); + return 0; + } + return rc; +} + +/* tipc_node_xmit_skb(): send single buffer to destination + * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE + * messages, which will not be rejected + * The only exception is datagram messages rerouted after secondary + * lookup, which are rare and safe to dispose of anyway. + * TODO: Return real return value, and let callers use + * tipc_wait_for_sendpkt() where applicable + */ +int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, + u32 selector) +{ + struct sk_buff_head head; + int rc; + + skb_queue_head_init(&head); + __skb_queue_tail(&head, skb); + rc = tipc_node_xmit(net, &head, dnode, selector); + if (rc == -ELINKCONG) + kfree_skb(skb); + return 0; +} + +/** + * tipc_rcv - process TIPC packets/messages arriving from off-node + * @net: the applicable net namespace + * @skb: TIPC packet + * @bearer: pointer to bearer message arrived on + * + * Invoked with no locks held. Bearer pointer must point to a valid bearer + * structure (i.e. cannot be NULL), but bearer can be inactive. + */ +void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) +{ + struct sk_buff_head xmitq; + struct tipc_node *n; + struct tipc_link *l; + struct tipc_msg *hdr; + struct tipc_media_addr *maddr; + int bearer_id = b->identity; + int rc = 0; + + __skb_queue_head_init(&xmitq); + + /* Ensure message is well-formed */ + if (unlikely(!tipc_msg_validate(skb))) + goto discard; + + /* Handle arrival of a non-unicast link packet */ + hdr = buf_msg(skb); + if (unlikely(msg_non_seq(hdr))) { + if (msg_user(hdr) == LINK_CONFIG) + tipc_disc_rcv(net, skb, b); + else + tipc_bclink_rcv(net, skb); + return; + } + + /* Locate neighboring node that sent packet */ + n = tipc_node_find(net, msg_prevnode(hdr)); + if (unlikely(!n)) + goto discard; + tipc_node_lock(n); + + /* Locate link endpoint that should handle packet */ + l = n->links[bearer_id].link; + if (unlikely(!l)) + goto unlock; + + /* Is reception of this packet permitted at the moment ? */ + if (unlikely(n->state != SELF_UP_PEER_UP)) + if (!tipc_node_filter_skb(n, l, hdr)) + goto unlock; + + if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) + tipc_bclink_sync_state(n, hdr); + + /* Release acked broadcast messages */ + if (unlikely(n->bclink.acked != msg_bcast_ack(hdr))) + tipc_bclink_acknowledge(n, msg_bcast_ack(hdr)); + + /* Check protocol and update link state */ + rc = tipc_link_rcv(l, skb, &xmitq); + + if (unlikely(rc & TIPC_LINK_UP_EVT)) + tipc_link_activate(l); + if (unlikely(rc & TIPC_LINK_DOWN_EVT)) + tipc_link_reset(l); + skb = NULL; +unlock: + tipc_node_unlock(n); + tipc_sk_rcv(net, &n->links[bearer_id].inputq); + maddr = &n->links[bearer_id].maddr; + tipc_bearer_xmit(net, bearer_id, &xmitq, maddr); + tipc_node_put(n); +discard: + kfree_skb(skb); +} + int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; diff --git a/net/tipc/node.h b/net/tipc/node.h index 5a834cf142c8..5e7016802077 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -45,6 +45,26 @@ /* Out-of-range value for node signature */ #define INVALID_NODE_SIG 0x10000 +#define INVALID_BEARER_ID -1 + +/* Node FSM states and events: + */ +enum { + SELF_DOWN_PEER_DOWN = 0xdd, + SELF_UP_PEER_UP = 0xaa, + SELF_DOWN_PEER_LEAVING = 0xd1, + SELF_UP_PEER_COMING = 0xac, + SELF_COMING_PEER_UP = 0xca, + SELF_LEAVING_PEER_DOWN = 0x1d, +}; + +enum { + SELF_ESTABL_CONTACT_EVT = 0xec, + SELF_LOST_CONTACT_EVT = 0x1c, + PEER_ESTABL_CONTACT_EVT = 0xfec, + PEER_LOST_CONTACT_EVT = 0xf1c +}; + /* Flags used to take different actions according to flag type * TIPC_WAIT_PEER_LINKS_DOWN: wait to see that peer's links are down * TIPC_WAIT_OWN_LINKS_DOWN: wait until peer node is declared down @@ -54,8 +74,6 @@ */ enum { TIPC_MSG_EVT = 1, - TIPC_WAIT_PEER_LINKS_DOWN = (1 << 1), - TIPC_WAIT_OWN_LINKS_DOWN = (1 << 2), TIPC_NOTIFY_NODE_DOWN = (1 << 3), TIPC_NOTIFY_NODE_UP = (1 << 4), TIPC_WAKEUP_BCAST_USERS = (1 << 5), @@ -85,10 +103,17 @@ struct tipc_node_bclink { u32 deferred_size; struct sk_buff_head deferdq; struct sk_buff *reasm_buf; - int inputq_map; + struct sk_buff_head namedq; bool recv_permitted; }; +struct tipc_link_entry { + struct tipc_link *link; + u32 mtu; + struct sk_buff_head inputq; + struct tipc_media_addr maddr; +}; + /** * struct tipc_node - TIPC node structure * @addr: network address of node @@ -98,9 +123,8 @@ struct tipc_node_bclink { * @hash: links to adjacent nodes in unsorted hash chain * @inputq: pointer to input queue containing messages for msg event * @namedq: pointer to name table input queue with name table messages - * @curr_link: the link holding the node lock, if any - * @active_links: pointers to active links to node - * @links: pointers to all links to node + * @active_links: bearer ids of active links, used as index into links[] array + * @links: array containing references to all links to node * @action_flags: bit mask of different types of node actions * @bclink: broadcast-related info * @list: links to adjacent nodes in sorted list of cluster's nodes @@ -120,12 +144,12 @@ struct tipc_node { struct hlist_node hash; struct sk_buff_head *inputq; struct sk_buff_head *namedq; - struct tipc_link *active_links[2]; - u32 act_mtus[2]; - struct tipc_link *links[MAX_BEARERS]; + int active_links[2]; + struct tipc_link_entry links[MAX_BEARERS]; int action_flags; struct tipc_node_bclink bclink; struct list_head list; + int state; int link_cnt; u16 working_links; u16 capabilities; @@ -133,6 +157,8 @@ struct tipc_node { u32 link_id; struct list_head publ_list; struct list_head conn_sks; + unsigned long keepalive_intv; + struct timer_list timer; struct rcu_head rcu; }; @@ -140,18 +166,25 @@ struct tipc_node *tipc_node_find(struct net *net, u32 addr); void tipc_node_put(struct tipc_node *node); struct tipc_node *tipc_node_create(struct net *net, u32 addr); void tipc_node_stop(struct net *net); +void tipc_node_check_dest(struct tipc_node *n, struct tipc_bearer *bearer, + bool *link_up, bool *addr_match, + struct tipc_media_addr *maddr); +bool tipc_node_update_dest(struct tipc_node *n, struct tipc_bearer *bearer, + struct tipc_media_addr *maddr); void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); -void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr); -void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr); -int tipc_node_active_links(struct tipc_node *n_ptr); -int tipc_node_is_up(struct tipc_node *n_ptr); +void tipc_node_link_down(struct tipc_node *n_ptr, int bearer_id); +void tipc_node_link_up(struct tipc_node *n_ptr, int bearer_id); +bool tipc_node_is_up(struct tipc_node *n); int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, char *linkname, size_t len); void tipc_node_unlock(struct tipc_node *node); +int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, + int selector); +int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, + u32 selector); int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port); void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port); - int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb); static inline void tipc_node_lock(struct tipc_node *node) @@ -159,26 +192,30 @@ static inline void tipc_node_lock(struct tipc_node *node) spin_lock_bh(&node->lock); } -static inline bool tipc_node_blocked(struct tipc_node *node) +static inline struct tipc_link *node_active_link(struct tipc_node *n, int sel) { - return (node->action_flags & (TIPC_WAIT_PEER_LINKS_DOWN | - TIPC_NOTIFY_NODE_DOWN | TIPC_WAIT_OWN_LINKS_DOWN)); + int bearer_id = n->active_links[sel & 1]; + + if (unlikely(bearer_id == INVALID_BEARER_ID)) + return NULL; + + return n->links[bearer_id].link; } -static inline uint tipc_node_get_mtu(struct net *net, u32 addr, u32 selector) +static inline unsigned int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel) { - struct tipc_node *node; - u32 mtu; - - node = tipc_node_find(net, addr); + struct tipc_node *n; + int bearer_id; + unsigned int mtu = MAX_MSG_SIZE; - if (likely(node)) { - mtu = node->act_mtus[selector & 1]; - tipc_node_put(node); - } else { - mtu = MAX_MSG_SIZE; - } + n = tipc_node_find(net, addr); + if (unlikely(!n)) + return mtu; + bearer_id = n->active_links[sel & 1]; + if (likely(bearer_id != INVALID_BEARER_ID)) + mtu = n->links[bearer_id].mtu; + tipc_node_put(n); return mtu; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3a7567f690f3..5b0b08d58fcc 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -261,7 +261,7 @@ static void tsk_rej_rx_queue(struct sock *sk) while ((skb = __skb_dequeue(&sk->sk_receive_queue))) { if (tipc_msg_reverse(own_node, skb, &dnode, TIPC_ERR_NO_PORT)) - tipc_link_xmit_skb(sock_net(sk), skb, dnode, 0); + tipc_node_xmit_skb(sock_net(sk), skb, dnode, 0); } } @@ -443,7 +443,7 @@ static int tipc_release(struct socket *sock) } if (tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, TIPC_ERR_NO_PORT)) - tipc_link_xmit_skb(net, skb, dnode, 0); + tipc_node_xmit_skb(net, skb, dnode, 0); } } @@ -456,7 +456,7 @@ static int tipc_release(struct socket *sock) tsk_own_node(tsk), tsk_peer_port(tsk), tsk->portid, TIPC_ERR_NO_PORT); if (skb) - tipc_link_xmit_skb(net, skb, dnode, tsk->portid); + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); tipc_node_remove_conn(net, dnode, tsk->portid); } @@ -686,21 +686,22 @@ new_mtu: do { rc = tipc_bclink_xmit(net, pktchain); - if (likely(rc >= 0)) { - rc = dsz; - break; + if (likely(!rc)) + return dsz; + + if (rc == -ELINKCONG) { + tsk->link_cong = 1; + rc = tipc_wait_for_sndmsg(sock, &timeo); + if (!rc) + continue; } + __skb_queue_purge(pktchain); if (rc == -EMSGSIZE) { msg->msg_iter = save; goto new_mtu; } - if (rc != -ELINKCONG) - break; - tipc_sk(sk)->link_cong = 1; - rc = tipc_wait_for_sndmsg(sock, &timeo); - if (rc) - __skb_queue_purge(pktchain); - } while (!rc); + break; + } while (1); return rc; } @@ -924,24 +925,25 @@ new_mtu: do { skb = skb_peek(pktchain); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_link_xmit(net, pktchain, dnode, tsk->portid); - if (likely(rc >= 0)) { + rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid); + if (likely(!rc)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; - rc = dsz; - break; + return dsz; } + if (rc == -ELINKCONG) { + tsk->link_cong = 1; + rc = tipc_wait_for_sndmsg(sock, &timeo); + if (!rc) + continue; + } + __skb_queue_purge(pktchain); if (rc == -EMSGSIZE) { m->msg_iter = save; goto new_mtu; } - if (rc != -ELINKCONG) - break; - tsk->link_cong = 1; - rc = tipc_wait_for_sndmsg(sock, &timeo); - if (rc) - __skb_queue_purge(pktchain); - } while (!rc); + break; + } while (1); return rc; } @@ -1043,15 +1045,16 @@ next: return rc; do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_link_xmit(net, pktchain, dnode, portid); + rc = tipc_node_xmit(net, pktchain, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; if (sent == dsz) - break; + return dsz; goto next; } if (rc == -EMSGSIZE) { + __skb_queue_purge(pktchain); tsk->max_pkt = tipc_node_get_mtu(net, dnode, portid); m->msg_iter = save; @@ -1059,13 +1062,13 @@ next: } if (rc != -ELINKCONG) break; + tsk->link_cong = 1; } rc = tipc_wait_for_sndpkt(sock, &timeo); - if (rc) - __skb_queue_purge(pktchain); } while (!rc); + __skb_queue_purge(pktchain); return sent ? sent : rc; } @@ -1221,7 +1224,7 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack) return; msg = buf_msg(skb); msg_set_msgcnt(msg, ack); - tipc_link_xmit_skb(net, skb, dnode, msg_link_selector(msg)); + tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg)); } static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) @@ -1700,7 +1703,7 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) return 0; } if (!err || tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, -err)) - tipc_link_xmit_skb(net, skb, dnode, tsk->portid); + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); return 0; } @@ -1796,7 +1799,7 @@ int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) if (!tipc_msg_reverse(tn->own_addr, skb, &dnode, -err)) continue; xmit: - tipc_link_xmit_skb(net, skb, dnode, dport); + tipc_node_xmit_skb(net, skb, dnode, dport); } return err ? -EHOSTUNREACH : 0; } @@ -2089,7 +2092,7 @@ restart: } if (tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, TIPC_CONN_SHUTDOWN)) - tipc_link_xmit_skb(net, skb, dnode, + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); } else { dnode = tsk_peer_node(tsk); @@ -2099,7 +2102,7 @@ restart: 0, dnode, tsk_own_node(tsk), tsk_peer_port(tsk), tsk->portid, TIPC_CONN_SHUTDOWN); - tipc_link_xmit_skb(net, skb, dnode, tsk->portid); + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); } tsk->connected = 0; sock->state = SS_DISCONNECTING; @@ -2161,7 +2164,7 @@ static void tipc_sk_timeout(unsigned long data) } bh_unlock_sock(sk); if (skb) - tipc_link_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid); + tipc_node_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid); exit: sock_put(sk); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index bd16c6c7e1e7..0cebf1fc37a2 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2048,7 +2048,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, xfrm_audit_policy_delete(xp, 1, true); } else { // reset the timers here? - WARN(1, "Dont know what to do with soft policy expire\n"); + WARN(1, "Don't know what to do with soft policy expire\n"); } km_policy_expired(xp, p->dir, up->hard, nlh->nlmsg_pid); diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index bdf1c1607b80..c77c872fe8ee 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -60,4 +60,29 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) = (void *) BPF_FUNC_l4_csum_replace; +#if defined(__x86_64__) + +#define PT_REGS_PARM1(x) ((x)->di) +#define PT_REGS_PARM2(x) ((x)->si) +#define PT_REGS_PARM3(x) ((x)->dx) +#define PT_REGS_PARM4(x) ((x)->cx) +#define PT_REGS_PARM5(x) ((x)->r8) +#define PT_REGS_RET(x) ((x)->sp) +#define PT_REGS_FP(x) ((x)->bp) +#define PT_REGS_RC(x) ((x)->ax) +#define PT_REGS_SP(x) ((x)->sp) + +#elif defined(__s390x__) + +#define PT_REGS_PARM1(x) ((x)->gprs[2]) +#define PT_REGS_PARM2(x) ((x)->gprs[3]) +#define PT_REGS_PARM3(x) ((x)->gprs[4]) +#define PT_REGS_PARM4(x) ((x)->gprs[5]) +#define PT_REGS_PARM5(x) ((x)->gprs[6]) +#define PT_REGS_RET(x) ((x)->gprs[14]) +#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->gprs[2]) +#define PT_REGS_SP(x) ((x)->gprs[15]) + +#endif #endif diff --git a/samples/bpf/tracex1_kern.c b/samples/bpf/tracex1_kern.c index 31620463701a..3f450a8fa1f3 100644 --- a/samples/bpf/tracex1_kern.c +++ b/samples/bpf/tracex1_kern.c @@ -29,7 +29,7 @@ int bpf_prog1(struct pt_regs *ctx) int len; /* non-portable! works for the given kernel only */ - skb = (struct sk_buff *) ctx->di; + skb = (struct sk_buff *) PT_REGS_PARM1(ctx); dev = _(skb->dev); diff --git a/samples/bpf/tracex2_kern.c b/samples/bpf/tracex2_kern.c index dc50f4f2943f..b32367cfbff4 100644 --- a/samples/bpf/tracex2_kern.c +++ b/samples/bpf/tracex2_kern.c @@ -27,10 +27,10 @@ int bpf_prog2(struct pt_regs *ctx) long init_val = 1; long *value; - /* x64 specific: read ip of kfree_skb caller. + /* x64/s390x specific: read ip of kfree_skb caller. * non-portable version of __builtin_return_address(0) */ - bpf_probe_read(&loc, sizeof(loc), (void *)ctx->sp); + bpf_probe_read(&loc, sizeof(loc), (void *)PT_REGS_RET(ctx)); value = bpf_map_lookup_elem(&my_map, &loc); if (value) @@ -79,7 +79,7 @@ struct bpf_map_def SEC("maps") my_hist_map = { SEC("kprobe/sys_write") int bpf_prog3(struct pt_regs *ctx) { - long write_size = ctx->dx; /* arg3 */ + long write_size = PT_REGS_PARM3(ctx); long init_val = 1; long *value; struct hist_key key = {}; diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c index 255ff2792366..bf337fbb0947 100644 --- a/samples/bpf/tracex3_kern.c +++ b/samples/bpf/tracex3_kern.c @@ -23,7 +23,7 @@ struct bpf_map_def SEC("maps") my_map = { SEC("kprobe/blk_mq_start_request") int bpf_prog1(struct pt_regs *ctx) { - long rq = ctx->di; + long rq = PT_REGS_PARM1(ctx); u64 val = bpf_ktime_get_ns(); bpf_map_update_elem(&my_map, &rq, &val, BPF_ANY); @@ -51,7 +51,7 @@ struct bpf_map_def SEC("maps") lat_map = { SEC("kprobe/blk_update_request") int bpf_prog2(struct pt_regs *ctx) { - long rq = ctx->di; + long rq = PT_REGS_PARM1(ctx); u64 *value, l, base; u32 index; diff --git a/samples/bpf/tracex4_kern.c b/samples/bpf/tracex4_kern.c index 126b80512228..ac4671420cf1 100644 --- a/samples/bpf/tracex4_kern.c +++ b/samples/bpf/tracex4_kern.c @@ -27,7 +27,7 @@ struct bpf_map_def SEC("maps") my_map = { SEC("kprobe/kmem_cache_free") int bpf_prog1(struct pt_regs *ctx) { - long ptr = ctx->si; + long ptr = PT_REGS_PARM2(ctx); bpf_map_delete_elem(&my_map, &ptr); return 0; @@ -36,11 +36,11 @@ int bpf_prog1(struct pt_regs *ctx) SEC("kretprobe/kmem_cache_alloc_node") int bpf_prog2(struct pt_regs *ctx) { - long ptr = ctx->ax; + long ptr = PT_REGS_RC(ctx); long ip = 0; /* get ip address of kmem_cache_alloc_node() caller */ - bpf_probe_read(&ip, sizeof(ip), (void *)(ctx->bp + sizeof(ip))); + bpf_probe_read(&ip, sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); struct pair v = { .val = bpf_ktime_get_ns(), diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c index b71fe07a7a7a..b3f4295bf288 100644 --- a/samples/bpf/tracex5_kern.c +++ b/samples/bpf/tracex5_kern.c @@ -24,7 +24,7 @@ int bpf_prog1(struct pt_regs *ctx) { struct seccomp_data sd = {}; - bpf_probe_read(&sd, sizeof(sd), (void *)ctx->di); + bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM1(ctx)); /* dispatch into next BPF program depending on syscall number */ bpf_tail_call(ctx, &progs, sd.nr); @@ -42,7 +42,7 @@ PROG(__NR_write)(struct pt_regs *ctx) { struct seccomp_data sd = {}; - bpf_probe_read(&sd, sizeof(sd), (void *)ctx->di); + bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM1(ctx)); if (sd.args[2] == 512) { char fmt[] = "write(fd=%d, buf=%p, size=%d)\n"; bpf_trace_printk(fmt, sizeof(fmt), @@ -55,7 +55,7 @@ PROG(__NR_read)(struct pt_regs *ctx) { struct seccomp_data sd = {}; - bpf_probe_read(&sd, sizeof(sd), (void *)ctx->di); + bpf_probe_read(&sd, sizeof(sd), (void *)PT_REGS_PARM1(ctx)); if (sd.args[2] > 128 && sd.args[2] <= 1024) { char fmt[] = "read(fd=%d, buf=%p, size=%d)\n"; bpf_trace_printk(fmt, sizeof(fmt), |